Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Small overlapping change conflict ('net' changed a line,
'net-next' added a line right afterwards) in flexcan.c
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Documentation/devicetree/bindings/hwmon/jc42.txt

@@ -34,6 +34,10 @@ Required properties:
 
 - reg: I2C address
 
+Optional properties:
+- smbus-timeout-disable: When set, the smbus timeout function will be disabled.
+			 This is not supported on all chips.
+
 Example:
 
 temp-sensor@1a {

Documentation/sysctl/vm.txt

@@ -158,10 +158,6 @@ Note: the minimum value allowed for dirty_bytes is two pages (in bytes); any
 value lower than this limit will be ignored and the old configuration will be
 retained.
 
-Note: the value of dirty_bytes also must be set greater than
-dirty_background_bytes or the amount of memory corresponding to
-dirty_background_ratio.
-
 ==============================================================
 
 dirty_expire_centisecs
@@ -181,9 +177,6 @@ generating disk writes will itself start writing out dirty data.
 
 The total available memory is not equal to total system memory.
 
-Note: dirty_ratio must be set greater than dirty_background_ratio or
-ratio corresponding to dirty_background_bytes.
-
 ==============================================================
 
 dirty_writeback_centisecs

MAINTAINERS

@@ -554,13 +554,13 @@ S:	Orphan
 F:	Documentation/filesystems/affs.txt
 F:	fs/affs/
 
-AFS FILESYSTEM & AF_RXRPC SOCKET DOMAIN
+AFS FILESYSTEM
 M:	David Howells <dhowells@redhat.com>
 L:	linux-afs@lists.infradead.org
 S:	Supported
 F:	fs/afs/
-F:	include/net/af_rxrpc.h
-F:	net/rxrpc/af_rxrpc.c
+F:	include/trace/events/afs.h
+F:	Documentation/filesystems/afs.txt
 W:	https://www.infradead.org/~dhowells/kafs/
 
 AGPGART DRIVER
@@ -6174,7 +6174,6 @@ M:	Jean Delvare <jdelvare@suse.com>
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 W:	http://hwmon.wiki.kernel.org/
-T:	quilt http://jdelvare.nerim.net/devel/linux/jdelvare-hwmon/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
 S:	Maintained
 F:	Documentation/hwmon/
@@ -11782,6 +11781,18 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jes/linux.git rtl8xxxu-deve
 S:	Maintained
 F:	drivers/net/wireless/realtek/rtl8xxxu/
 
+RXRPC SOCKETS (AF_RXRPC)
+M:	David Howells <dhowells@redhat.com>
+L:	linux-afs@lists.infradead.org
+S:	Supported
+F:	net/rxrpc/
+F:	include/keys/rxrpc-type.h
+F:	include/net/af_rxrpc.h
+F:	include/trace/events/rxrpc.h
+F:	include/uapi/linux/rxrpc.h
+F:	Documentation/networking/rxrpc.txt
+W:	https://www.infradead.org/~dhowells/kafs/
+
 S3 SAVAGE FRAMEBUFFER DRIVER
 M:	Antonino Daplas <adaplas@gmail.com>
 L:	linux-fbdev@vger.kernel.org
@@ -13653,10 +13664,8 @@ F:	drivers/net/wireless/ti/
 F:	include/linux/wl12xx.h
 
 TILE ARCHITECTURE
-M:	Chris Metcalf <cmetcalf@mellanox.com>
 W:	http://www.mellanox.com/repository/solutions/tile-scm/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile.git
-S:	Supported
+S:	Orphan
 F:	arch/tile/
 F:	drivers/char/tile-srom.c
 F:	drivers/edac/tile_edac.c

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*

arch/arm/include/asm/pgtable-3level.h

@@ -221,7 +221,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
 }
 #define	__HAVE_ARCH_PTE_SPECIAL
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
 #define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))
 #define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))

arch/arm/kernel/entry-header.S

@@ -300,7 +300,7 @@
 	mov	r2, sp
 	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
-	tst	r1, #0xcf
+	tst	r1, #PSR_I_BIT | 0x0f
 	bne	1f
 	msr	spsr_cxsf, r1			@ save in spsr_svc
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
@@ -332,7 +332,7 @@
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [sp, #\offset + S_PC]	@ get pc
 	add	sp, sp, #\offset + S_SP
-	tst	r1, #0xcf
+	tst	r1, #PSR_I_BIT | 0x0f
 	bne	1f
 	msr	spsr_cxsf, r1			@ save in spsr_svc
 

arch/arm64/Makefile

@@ -83,9 +83,6 @@ endif
 
 ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
 KBUILD_LDFLAGS_MODULE	+= -T $(srctree)/arch/arm64/kernel/module.lds
-ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
-KBUILD_LDFLAGS_MODULE	+= $(objtree)/arch/arm64/kernel/ftrace-mod.o
-endif
 endif
 
 # Default value

arch/arm64/include/asm/cacheflush.h

@@ -38,7 +38,7 @@
  *
  *	See Documentation/cachetlb.txt for more information. Please note that
  *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
- *	VIPT or ASID-tagged VIVT I-cache.
+ *	VIPT I-cache.
  *
  *	flush_cache_mm(mm)
  *

arch/arm64/include/asm/module.h

@@ -32,7 +32,7 @@ struct mod_arch_specific {
 	struct mod_plt_sec	init;
 
 	/* for CONFIG_DYNAMIC_FTRACE */
-	void			*ftrace_trampoline;
+	struct plt_entry 	*ftrace_trampoline;
 };
 #endif
 
@@ -45,4 +45,48 @@ extern u64 module_alloc_base;
 #define module_alloc_base	((u64)_etext - MODULES_VSIZE)
 #endif
 
+struct plt_entry {
+	/*
+	 * A program that conforms to the AArch64 Procedure Call Standard
+	 * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
+	 * IP1 (x17) may be inserted at any branch instruction that is
+	 * exposed to a relocation that supports long branches. Since that
+	 * is exactly what we are dealing with here, we are free to use x16
+	 * as a scratch register in the PLT veneers.
+	 */
+	__le32	mov0;	/* movn	x16, #0x....			*/
+	__le32	mov1;	/* movk	x16, #0x...., lsl #16		*/
+	__le32	mov2;	/* movk	x16, #0x...., lsl #32		*/
+	__le32	br;	/* br	x16				*/
+};
+
+static inline struct plt_entry get_plt_entry(u64 val)
+{
+	/*
+	 * MOVK/MOVN/MOVZ opcode:
+	 * +--------+------------+--------+-----------+-------------+---------+
+	 * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
+	 * +--------+------------+--------+-----------+-------------+---------+
+	 *
+	 * Rd     := 0x10 (x16)
+	 * hw     := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
+	 * opc    := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
+	 * sf     := 1 (64-bit variant)
+	 */
+	return (struct plt_entry){
+		cpu_to_le32(0x92800010 | (((~val      ) & 0xffff)) << 5),
+		cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
+		cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
+		cpu_to_le32(0xd61f0200)
+	};
+}
+
+static inline bool plt_entries_equal(const struct plt_entry *a,
+				     const struct plt_entry *b)
+{
+	return a->mov0 == b->mov0 &&
+	       a->mov1 == b->mov1 &&
+	       a->mov2 == b->mov2;
+}
+
 #endif /* __ASM_MODULE_H */

arch/arm64/include/asm/pgtable.h

@@ -345,7 +345,6 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))

arch/arm64/kernel/Makefile

@@ -61,6 +61,3 @@ extra-y					+= $(head-y) vmlinux.lds
 ifeq ($(CONFIG_DEBUG_EFI),y)
 AFLAGS_head.o += -DVMLINUX_PATH="\"$(realpath $(objtree)/vmlinux)\""
 endif
-
-# will be included by each individual module but not by the core kernel itself
-extra-$(CONFIG_DYNAMIC_FTRACE) += ftrace-mod.o

arch/arm64/kernel/cpu_ops.c

@@ -31,13 +31,13 @@ extern const struct cpu_operations cpu_psci_ops;
 
 const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
-static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const dt_supported_cpu_ops[] __initconst = {
 	&smp_spin_table_ops,
 	&cpu_psci_ops,
 	NULL,
 };
 
-static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const acpi_supported_cpu_ops[] __initconst = {
 #ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
 	&acpi_parking_protocol_ops,
 #endif
@@ -47,7 +47,7 @@ static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = {
 
 static const struct cpu_operations * __init cpu_get_ops(const char *name)
 {
-	const struct cpu_operations **ops;
+	const struct cpu_operations *const *ops;
 
 	ops = acpi_disabled ? dt_supported_cpu_ops : acpi_supported_cpu_ops;
 

arch/arm64/kernel/fpsimd.c

@@ -1026,10 +1026,10 @@ void fpsimd_update_current_state(struct fpsimd_state *state)
 
 	local_bh_disable();
 
-	if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
-		current->thread.fpsimd_state = *state;
+	current->thread.fpsimd_state = *state;
+	if (system_supports_sve() && test_thread_flag(TIF_SVE))
 		fpsimd_to_sve(current);
-	}
+
 	task_fpsimd_load();
 
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {

arch/arm64/kernel/ftrace-mod.S

-/*
- * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-	.section	".text.ftrace_trampoline", "ax"
-	.align		3
-0:	.quad		0
-__ftrace_trampoline:
-	ldr		x16, 0b
-	br		x16
-ENDPROC(__ftrace_trampoline)

arch/arm64/kernel/ftrace.c

@@ -76,7 +76,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
 #ifdef CONFIG_ARM64_MODULE_PLTS
-		unsigned long *trampoline;
+		struct plt_entry trampoline;
 		struct module *mod;
 
 		/*
@@ -104,22 +104,24 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		 * is added in the future, but for now, the pr_err() below
 		 * deals with a theoretical issue only.
 		 */
-		trampoline = (unsigned long *)mod->arch.ftrace_trampoline;
-		if (trampoline[0] != addr) {
-			if (trampoline[0] != 0) {
+		trampoline = get_plt_entry(addr);
+		if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+				       &trampoline)) {
+			if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+					       &(struct plt_entry){})) {
 				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
 				return -EINVAL;
 			}
 
 			/* point the trampoline to our ftrace entry point */
 			module_disable_ro(mod);
-			trampoline[0] = addr;
+			*mod->arch.ftrace_trampoline = trampoline;
 			module_enable_ro(mod, true);
 
 			/* update trampoline before patching in the branch */
 			smp_wmb();
 		}
-		addr = (unsigned long)&trampoline[1];
+		addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
 #else /* CONFIG_ARM64_MODULE_PLTS */
 		return -EINVAL;
 #endif /* CONFIG_ARM64_MODULE_PLTS */

arch/arm64/kernel/module-plts.c

@@ -11,21 +11,6 @@
 #include <linux/module.h>
 #include <linux/sort.h>
 
-struct plt_entry {
-	/*
-	 * A program that conforms to the AArch64 Procedure Call Standard
-	 * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
-	 * IP1 (x17) may be inserted at any branch instruction that is
-	 * exposed to a relocation that supports long branches. Since that
-	 * is exactly what we are dealing with here, we are free to use x16
-	 * as a scratch register in the PLT veneers.
-	 */
-	__le32	mov0;	/* movn	x16, #0x....			*/
-	__le32	mov1;	/* movk	x16, #0x...., lsl #16		*/
-	__le32	mov2;	/* movk	x16, #0x...., lsl #32		*/
-	__le32	br;	/* br	x16				*/
-};
-
 static bool in_init(const struct module *mod, void *loc)
 {
 	return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size;
@@ -40,33 +25,14 @@ u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
 	int i = pltsec->plt_num_entries;
 	u64 val = sym->st_value + rela->r_addend;
 
-	/*
-	 * MOVK/MOVN/MOVZ opcode:
-	 * +--------+------------+--------+-----------+-------------+---------+
-	 * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
-	 * +--------+------------+--------+-----------+-------------+---------+
-	 *
-	 * Rd     := 0x10 (x16)
-	 * hw     := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
-	 * opc    := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
-	 * sf     := 1 (64-bit variant)
-	 */
-	plt[i] = (struct plt_entry){
-		cpu_to_le32(0x92800010 | (((~val      ) & 0xffff)) << 5),
-		cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
-		cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
-		cpu_to_le32(0xd61f0200)
-	};
+	plt[i] = get_plt_entry(val);
 
 	/*
 	 * Check if the entry we just created is a duplicate. Given that the
 	 * relocations are sorted, this will be the last entry we allocated.
 	 * (if one exists).
 	 */
-	if (i > 0 &&
-	    plt[i].mov0 == plt[i - 1].mov0 &&
-	    plt[i].mov1 == plt[i - 1].mov1 &&
-	    plt[i].mov2 == plt[i - 1].mov2)
+	if (i > 0 && plt_entries_equal(plt + i, plt + i - 1))
 		return (u64)&plt[i - 1];
 
 	pltsec->plt_num_entries++;
@@ -154,6 +120,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	unsigned long core_plts = 0;
 	unsigned long init_plts = 0;
 	Elf64_Sym *syms = NULL;
+	Elf_Shdr *tramp = NULL;
 	int i;
 
 	/*
@@ -165,6 +132,10 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			mod->arch.core.plt = sechdrs + i;
 		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
 			mod->arch.init.plt = sechdrs + i;
+		else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
+			 !strcmp(secstrings + sechdrs[i].sh_name,
+				 ".text.ftrace_trampoline"))
+			tramp = sechdrs + i;
 		else if (sechdrs[i].sh_type == SHT_SYMTAB)
 			syms = (Elf64_Sym *)sechdrs[i].sh_addr;
 	}
@@ -215,5 +186,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	mod->arch.init.plt_num_entries = 0;
 	mod->arch.init.plt_max_entries = init_plts;
 
+	if (tramp) {
+		tramp->sh_type = SHT_NOBITS;
+		tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+		tramp->sh_addralign = __alignof__(struct plt_entry);
+		tramp->sh_size = sizeof(struct plt_entry);
+	}
+
 	return 0;
 }

arch/arm64/kernel/module.lds

 SECTIONS {
 	.plt (NOLOAD) : { BYTE(0) }
 	.init.plt (NOLOAD) : { BYTE(0) }
+	.text.ftrace_trampoline (NOLOAD) : { BYTE(0) }
 }

arch/arm64/kernel/perf_event.c

@@ -262,12 +262,6 @@ static const unsigned armv8_a73_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 
 	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
 	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
-
-	[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
-	[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
-
-	[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
-	[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
 };
 
 static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]

arch/arm64/mm/context.c

@@ -96,12 +96,6 @@ static void flush_context(unsigned int cpu)
 
 	set_reserved_asid_bits();
 
-	/*
-	 * Ensure the generation bump is observed before we xchg the
-	 * active_asids.
-	 */
-	smp_wmb();
-
 	for_each_possible_cpu(i) {
 		asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
 		/*
@@ -117,7 +111,10 @@ static void flush_context(unsigned int cpu)
 		per_cpu(reserved_asids, i) = asid;
 	}
 
-	/* Queue a TLB invalidate and flush the I-cache if necessary. */
+	/*
+	 * Queue a TLB invalidation for each CPU to perform on next
+	 * context-switch
+	 */
 	cpumask_setall(&tlb_flush_pending);
 }
 
@@ -202,11 +199,18 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 	asid = atomic64_read(&mm->context.id);
 
 	/*
-	 * The memory ordering here is subtle. We rely on the control
-	 * dependency between the generation read and the update of
-	 * active_asids to ensure that we are synchronised with a
-	 * parallel rollover (i.e. this pairs with the smp_wmb() in
-	 * flush_context).
+	 * The memory ordering here is subtle.
+	 * If our ASID matches the current generation, then we update
+	 * our active_asids entry with a relaxed xchg. Racing with a
+	 * concurrent rollover means that either:
+	 *
+	 * - We get a zero back from the xchg and end up waiting on the
+	 *   lock. Taking the lock synchronises with the rollover and so
+	 *   we are forced to see the updated generation.
+	 *
+	 * - We get a valid ASID back from the xchg, which means the
+	 *   relaxed xchg in flush_context will treat us as reserved
+	 *   because atomic RmWs are totally ordered for a given location.
 	 */
 	if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits)
 	    && atomic64_xchg_relaxed(&per_cpu(active_asids, cpu), asid))

arch/arm64/mm/pgd.c

@@ -26,7 +26,7 @@
 #include <asm/page.h>
 #include <asm/tlbflush.h>
 
-static struct kmem_cache *pgd_cache;
+static struct kmem_cache *pgd_cache __ro_after_init;
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {

arch/mips/include/asm/pgtable.h

@@ -552,7 +552,7 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t pmd);
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_WRITE);

arch/mips/kvm/mips.c

@@ -445,10 +445,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int r = -EINTR;
-	sigset_t sigsaved;
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+	kvm_sigset_activate(vcpu);
 
 	if (vcpu->mmio_needed) {
 		if (!vcpu->mmio_is_write)
@@ -480,8 +478,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	local_irq_enable();
 
 out:
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	kvm_sigset_deactivate(vcpu);
 
 	return r;
 }

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -1005,7 +1005,6 @@ static inline int pmd_protnone(pmd_t pmd)
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 #define __pmd_write(pmd)	__pte_write(pmd_pte(pmd))
 #define pmd_savedwrite(pmd)	pte_savedwrite(pmd_pte(pmd))

arch/powerpc/include/asm/kvm_ppc.h

@@ -180,6 +180,7 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
 		struct iommu_group *grp);
 extern int kvmppc_switch_mmu_to_hpt(struct kvm *kvm);
 extern int kvmppc_switch_mmu_to_radix(struct kvm *kvm);
+extern void kvmppc_setup_partition_table(struct kvm *kvm);
 
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);

arch/powerpc/kernel/misc_64.S

@@ -623,7 +623,9 @@ BEGIN_FTR_SECTION
 	 * NOTE, we rely on r0 being 0 from above.
 	 */
 	mtspr	SPRN_IAMR,r0
+BEGIN_FTR_SECTION_NESTED(42)
 	mtspr	SPRN_AMOR,r0
+END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 	/* save regs for local vars on new stack.

arch/powerpc/kernel/process.c

@@ -1569,16 +1569,22 @@ void arch_release_task_struct(struct task_struct *t)
  */
 int set_thread_tidr(struct task_struct *t)
 {
+	int rc;
+
 	if (!cpu_has_feature(CPU_FTR_ARCH_300))
 		return -EINVAL;
 
 	if (t != current)
 		return -EINVAL;
 
-	t->thread.tidr = assign_thread_tidr();
-	if (t->thread.tidr < 0)
-		return t->thread.tidr;
+	if (t->thread.tidr)
+		return 0;
+
+	rc = assign_thread_tidr();
+	if (rc < 0)
+		return rc;
 
+	t->thread.tidr = rc;
 	mtspr(SPRN_TIDR, t->thread.tidr);
 
 	return 0;

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -1238,8 +1238,9 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize,
 	unsigned long vpte, rpte, guest_rpte;
 	int ret;
 	struct revmap_entry *rev;
-	unsigned long apsize, psize, avpn, pteg, hash;
+	unsigned long apsize, avpn, pteg, hash;
 	unsigned long new_idx, new_pteg, replace_vpte;
+	int pshift;
 
 	hptep = (__be64 *)(old->virt + (idx << 4));
 
@@ -1298,8 +1299,8 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize,
 		goto out;
 
 	rpte = be64_to_cpu(hptep[1]);
-	psize = hpte_base_page_size(vpte, rpte);
-	avpn = HPTE_V_AVPN_VAL(vpte) & ~((psize - 1) >> 23);
+	pshift = kvmppc_hpte_base_page_shift(vpte, rpte);
+	avpn = HPTE_V_AVPN_VAL(vpte) & ~(((1ul << pshift) - 1) >> 23);
 	pteg = idx / HPTES_PER_GROUP;
 	if (vpte & HPTE_V_SECONDARY)
 		pteg = ~pteg;
@@ -1311,20 +1312,20 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize,
 		offset = (avpn & 0x1f) << 23;
 		vsid = avpn >> 5;
 		/* We can find more bits from the pteg value */
-		if (psize < (1ULL << 23))
-			offset |= ((vsid ^ pteg) & old_hash_mask) * psize;
+		if (pshift < 23)
+			offset |= ((vsid ^ pteg) & old_hash_mask) << pshift;
 
-		hash = vsid ^ (offset / psize);
+		hash = vsid ^ (offset >> pshift);
 	} else {
 		unsigned long offset, vsid;
 
 		/* We only have 40 - 23 bits of seg_off in avpn */
 		offset = (avpn & 0x1ffff) << 23;
 		vsid = avpn >> 17;
-		if (psize < (1ULL << 23))
-			offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) * psize;
+		if (pshift < 23)
+			offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) << pshift;
 
-		hash = vsid ^ (vsid << 25) ^ (offset / psize);
+		hash = vsid ^ (vsid << 25) ^ (offset >> pshift);
 	}
 
 	new_pteg = hash & new_hash_mask;
@@ -1801,6 +1802,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 	ssize_t nb;
 	long int err, ret;
 	int mmu_ready;
+	int pshift;
 
 	if (!access_ok(VERIFY_READ, buf, count))
 		return -EFAULT;
@@ -1855,6 +1857,9 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 			err = -EINVAL;
 			if (!(v & HPTE_V_VALID))
 				goto out;
+			pshift = kvmppc_hpte_base_page_shift(v, r);
+			if (pshift <= 0)
+				goto out;
 			lbuf += 2;
 			nb += HPTE_SIZE;
 
@@ -1869,14 +1874,18 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 				goto out;
 			}
 			if (!mmu_ready && is_vrma_hpte(v)) {
-				unsigned long psize = hpte_base_page_size(v, r);
-				unsigned long senc = slb_pgsize_encoding(psize);
-				unsigned long lpcr;
+				unsigned long senc, lpcr;
 
+				senc = slb_pgsize_encoding(1ul << pshift);
 				kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
 					(VRMA_VSID << SLB_VSID_SHIFT_1T);
-				lpcr = senc << (LPCR_VRMASD_SH - 4);
-				kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+				if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+					lpcr = senc << (LPCR_VRMASD_SH - 4);
+					kvmppc_update_lpcr(kvm, lpcr,
+							   LPCR_VRMASD);
+				} else {
+					kvmppc_setup_partition_table(kvm);
+				}
 				mmu_ready = 1;
 			}
 			++i;

arch/powerpc/kvm/book3s_hv.c

@@ -120,7 +120,6 @@ MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
 
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
-static void kvmppc_setup_partition_table(struct kvm *kvm);
 
 static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
 		int *ip)
@@ -3574,7 +3573,7 @@ static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
 	return;
 }
 
-static void kvmppc_setup_partition_table(struct kvm *kvm)
+void kvmppc_setup_partition_table(struct kvm *kvm)
 {
 	unsigned long dw0, dw1;
 

arch/powerpc/kvm/powerpc.c

@@ -1407,7 +1407,6 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int r;
-	sigset_t sigsaved;
 
 	if (vcpu->mmio_needed) {
 		vcpu->mmio_needed = 0;
@@ -1448,16 +1447,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 #endif
 	}
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+	kvm_sigset_activate(vcpu);
 
 	if (run->immediate_exit)
 		r = -EINTR;
 	else
 		r = kvmppc_vcpu_run(run, vcpu);
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	kvm_sigset_deactivate(vcpu);
 
 	return r;
 }

arch/powerpc/mm/hash_native_64.c

@@ -47,7 +47,8 @@
 
 DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
-static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
+						int apsize, int ssize)
 {
 	unsigned long va;
 	unsigned int penc;
@@ -100,7 +101,15 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 			     : "memory");
 		break;
 	}
-	trace_tlbie(0, 0, va, 0, 0, 0, 0);
+	return va;
+}
+
+static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+{
+	unsigned long rb;
+
+	rb = ___tlbie(vpn, psize, apsize, ssize);
+	trace_tlbie(0, 0, rb, 0, 0, 0, 0);
 }
 
 static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
@@ -652,7 +661,7 @@ static void native_hpte_clear(void)
 		if (hpte_v & HPTE_V_VALID) {
 			hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
 			hptep->v = 0;
-			__tlbie(vpn, psize, apsize, ssize);
+			___tlbie(vpn, psize, apsize, ssize);
 		}
 	}
 

arch/riscv/include/asm/Kbuild

@@ -40,6 +40,7 @@ generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += sembuf.h
+generic-y += serial.h
 generic-y += setup.h
 generic-y += shmbuf.h
 generic-y += shmparam.h

arch/riscv/include/asm/asm.h

@@ -58,17 +58,17 @@
 #endif
 
 #if (__SIZEOF_INT__ == 4)
-#define INT		__ASM_STR(.word)
-#define SZINT		__ASM_STR(4)
-#define LGINT		__ASM_STR(2)
+#define RISCV_INT		__ASM_STR(.word)
+#define RISCV_SZINT		__ASM_STR(4)
+#define RISCV_LGINT		__ASM_STR(2)
 #else
 #error "Unexpected __SIZEOF_INT__"
 #endif
 
 #if (__SIZEOF_SHORT__ == 2)
-#define SHORT		__ASM_STR(.half)
-#define SZSHORT		__ASM_STR(2)
-#define LGSHORT		__ASM_STR(1)
+#define RISCV_SHORT		__ASM_STR(.half)
+#define RISCV_SZSHORT		__ASM_STR(2)
+#define RISCV_LGSHORT		__ASM_STR(1)
 #else
 #error "Unexpected __SIZEOF_SHORT__"
 #endif

arch/riscv/include/asm/atomic.h

@@ -50,30 +50,30 @@ static __always_inline void atomic64_set(atomic64_t *v, long i)
  * have the AQ or RL bits set.  These don't return anything, so there's only
  * one version to worry about.
  */
-#define ATOMIC_OP(op, asm_op, c_op, I, asm_type, c_type, prefix)				\
-static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
-{												\
-	__asm__ __volatile__ (									\
-		"amo" #asm_op "." #asm_type " zero, %1, %0"					\
-		: "+A" (v->counter)								\
-		: "r" (I)									\
-		: "memory");									\
+#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix)				\
+static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)	\
+{											\
+	__asm__ __volatile__ (								\
+		"amo" #asm_op "." #asm_type " zero, %1, %0"				\
+		: "+A" (v->counter)							\
+		: "r" (I)								\
+		: "memory");								\
 }
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I)			\
-        ATOMIC_OP (op, asm_op, c_op, I, w,  int,   )
+#define ATOMIC_OPS(op, asm_op, I)			\
+        ATOMIC_OP (op, asm_op, I, w,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, c_op, I)			\
-        ATOMIC_OP (op, asm_op, c_op, I, w,  int,   )	\
-        ATOMIC_OP (op, asm_op, c_op, I, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I)			\
+        ATOMIC_OP (op, asm_op, I, w,  int,   )	\
+        ATOMIC_OP (op, asm_op, I, d, long, 64)
 #endif
 
-ATOMIC_OPS(add, add, +,  i)
-ATOMIC_OPS(sub, add, +, -i)
-ATOMIC_OPS(and, and, &,  i)
-ATOMIC_OPS( or,  or, |,  i)
-ATOMIC_OPS(xor, xor, ^,  i)
+ATOMIC_OPS(add, add,  i)
+ATOMIC_OPS(sub, add, -i)
+ATOMIC_OPS(and, and,  i)
+ATOMIC_OPS( or,  or,  i)
+ATOMIC_OPS(xor, xor,  i)
 
 #undef ATOMIC_OP
 #undef ATOMIC_OPS
@@ -83,7 +83,7 @@ ATOMIC_OPS(xor, xor, ^,  i)
  * There's two flavors of these: the arithmatic ops have both fetch and return
  * versions, while the logical ops only have fetch versions.
  */
-#define ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix)			\
+#define ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, asm_type, c_type, prefix)				\
 static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v)	\
 {													\
 	register c_type ret;										\
@@ -103,13 +103,13 @@ static __always_inline c_type atomic##prefix##_##op##_return##c_or(c_type i, ato
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
+        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, w,  int,   )	\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
+        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, w,  int,   )	\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, d, long, 64)	\
+        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, d, long, 64)	\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
 #endif
 
@@ -126,28 +126,28 @@ ATOMIC_OPS(sub, add, +, -i, .aqrl,         )
 #undef ATOMIC_OPS
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or)				\
+        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )		\
-        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or)				\
+        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w,  int,   )	\
+        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, d, long, 64)
 #endif
 
-ATOMIC_OPS(and, and, &,  i,      , _relaxed)
-ATOMIC_OPS(and, and, &,  i, .aq  , _acquire)
-ATOMIC_OPS(and, and, &,  i, .rl  , _release)
-ATOMIC_OPS(and, and, &,  i, .aqrl,         )
+ATOMIC_OPS(and, and, i,      , _relaxed)
+ATOMIC_OPS(and, and, i, .aq  , _acquire)
+ATOMIC_OPS(and, and, i, .rl  , _release)
+ATOMIC_OPS(and, and, i, .aqrl,         )
 
-ATOMIC_OPS( or,  or, |,  i,      , _relaxed)
-ATOMIC_OPS( or,  or, |,  i, .aq  , _acquire)
-ATOMIC_OPS( or,  or, |,  i, .rl  , _release)
-ATOMIC_OPS( or,  or, |,  i, .aqrl,         )
+ATOMIC_OPS( or,  or, i,      , _relaxed)
+ATOMIC_OPS( or,  or, i, .aq  , _acquire)
+ATOMIC_OPS( or,  or, i, .rl  , _release)
+ATOMIC_OPS( or,  or, i, .aqrl,         )
 
-ATOMIC_OPS(xor, xor, ^,  i,      , _relaxed)
-ATOMIC_OPS(xor, xor, ^,  i, .aq  , _acquire)
-ATOMIC_OPS(xor, xor, ^,  i, .rl  , _release)
-ATOMIC_OPS(xor, xor, ^,  i, .aqrl,         )
+ATOMIC_OPS(xor, xor, i,      , _relaxed)
+ATOMIC_OPS(xor, xor, i, .aq  , _acquire)
+ATOMIC_OPS(xor, xor, i, .rl  , _release)
+ATOMIC_OPS(xor, xor, i, .aqrl,         )
 
 #undef ATOMIC_OPS
 
@@ -182,13 +182,13 @@ ATOMIC_OPS(add_negative, add,  <, 0)
 #undef ATOMIC_OP
 #undef ATOMIC_OPS
 
-#define ATOMIC_OP(op, func_op, c_op, I, c_type, prefix)				\
+#define ATOMIC_OP(op, func_op, I, c_type, prefix)				\
 static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v)	\
 {										\
 	atomic##prefix##_##func_op(I, v);					\
 }
 
-#define ATOMIC_FETCH_OP(op, func_op, c_op, I, c_type, prefix)				\
+#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix)					\
 static __always_inline c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)	\
 {											\
 	return atomic##prefix##_fetch_##func_op(I, v);					\
@@ -202,16 +202,16 @@ static __always_inline c_type atomic##prefix##_##op##_return(atomic##prefix##_t
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, c_op, I)						\
-        ATOMIC_OP       (op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I,  int,   )				\
+        ATOMIC_OP       (op, asm_op,       I,  int,   )				\
+        ATOMIC_FETCH_OP (op, asm_op,       I,  int,   )				\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, c_op, I)						\
-        ATOMIC_OP       (op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I,  int,   )				\
+        ATOMIC_OP       (op, asm_op,       I,  int,   )				\
+        ATOMIC_FETCH_OP (op, asm_op,       I,  int,   )				\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_OP       (op, asm_op, c_op, I, long, 64)				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, long, 64)				\
+        ATOMIC_OP       (op, asm_op,       I, long, 64)				\
+        ATOMIC_FETCH_OP (op, asm_op,       I, long, 64)				\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
 #endif
 
@@ -300,8 +300,13 @@ static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
 
 /*
  * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
- * {cmp,}xchg and the operations that return, so they need a barrier.  We just
- * use the other implementations directly.
+ * {cmp,}xchg and the operations that return, so they need a barrier.
+ */
+/*
+ * FIXME: atomic_cmpxchg_{acquire,release,relaxed} are all implemented by
+ * assigning the same barrier to both the LR and SC operations, but that might
+ * not make any sense.  We're waiting on a memory model specification to
+ * determine exactly what the right thing to do is here.
  */
 #define ATOMIC_OP(c_t, prefix, c_or, size, asm_or)						\
 static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) 	\

arch/riscv/include/asm/barrier.h

@@ -38,29 +38,6 @@
 #define smp_rmb()	RISCV_FENCE(r,r)
 #define smp_wmb()	RISCV_FENCE(w,w)
 
-/*
- * These fences exist to enforce ordering around the relaxed AMOs.  The
- * documentation defines that
- * "
- *     atomic_fetch_add();
- *   is equivalent to:
- *     smp_mb__before_atomic();
- *     atomic_fetch_add_relaxed();
- *     smp_mb__after_atomic();
- * "
- * So we emit full fences on both sides.
- */
-#define __smb_mb__before_atomic()	smp_mb()
-#define __smb_mb__after_atomic()	smp_mb()
-
-/*
- * These barriers prevent accesses performed outside a spinlock from being moved
- * inside a spinlock.  Since RISC-V sets the aq/rl bits on our spinlock only
- * enforce release consistency, we need full fences here.
- */
-#define smb_mb__before_spinlock()	smp_mb()
-#define smb_mb__after_spinlock()	smp_mb()
-
 #include <asm-generic/barrier.h>
 
 #endif /* __ASSEMBLY__ */

arch/riscv/include/asm/bitops.h

@@ -67,7 +67,7 @@
 		: "memory");
 
 #define __test_and_op_bit(op, mod, nr, addr) 			\
-	__test_and_op_bit_ord(op, mod, nr, addr, )
+	__test_and_op_bit_ord(op, mod, nr, addr, .aqrl)
 #define __op_bit(op, mod, nr, addr)				\
 	__op_bit_ord(op, mod, nr, addr, )
 

arch/riscv/include/asm/bug.h

@@ -27,8 +27,8 @@
 typedef u32 bug_insn_t;
 
 #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-#define __BUG_ENTRY_ADDR	INT " 1b - 2b"
-#define __BUG_ENTRY_FILE	INT " %0 - 2b"
+#define __BUG_ENTRY_ADDR	RISCV_INT " 1b - 2b"
+#define __BUG_ENTRY_FILE	RISCV_INT " %0 - 2b"
 #else
 #define __BUG_ENTRY_ADDR	RISCV_PTR " 1b"
 #define __BUG_ENTRY_FILE	RISCV_PTR " %0"
@@ -38,7 +38,7 @@ typedef u32 bug_insn_t;
 #define __BUG_ENTRY			\
 	__BUG_ENTRY_ADDR "\n\t"		\
 	__BUG_ENTRY_FILE "\n\t"		\
-	SHORT " %1"
+	RISCV_SHORT " %1"
 #else
 #define __BUG_ENTRY			\
 	__BUG_ENTRY_ADDR

arch/riscv/include/asm/cacheflush.h

@@ -18,22 +18,44 @@
 
 #undef flush_icache_range
 #undef flush_icache_user_range
+#undef flush_dcache_page
 
 static inline void local_flush_icache_all(void)
 {
 	asm volatile ("fence.i" ::: "memory");
 }
 
+#define PG_dcache_clean PG_arch_1
+
+static inline void flush_dcache_page(struct page *page)
+{
+	if (test_bit(PG_dcache_clean, &page->flags))
+		clear_bit(PG_dcache_clean, &page->flags);
+}
+
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range(start, end) flush_icache_all()
+#define flush_icache_user_range(vma, pg, addr, len) flush_icache_all()
+
 #ifndef CONFIG_SMP
 
-#define flush_icache_range(start, end) local_flush_icache_all()
-#define flush_icache_user_range(vma, pg, addr, len) local_flush_icache_all()
+#define flush_icache_all() local_flush_icache_all()
+#define flush_icache_mm(mm, local) flush_icache_all()
 
 #else /* CONFIG_SMP */
 
-#define flush_icache_range(start, end) sbi_remote_fence_i(0)
-#define flush_icache_user_range(vma, pg, addr, len) sbi_remote_fence_i(0)
+#define flush_icache_all() sbi_remote_fence_i(0)
+void flush_icache_mm(struct mm_struct *mm, bool local);
 
 #endif /* CONFIG_SMP */
 
+/*
+ * Bits in sys_riscv_flush_icache()'s flags argument.
+ */
+#define SYS_RISCV_FLUSH_ICACHE_LOCAL 1UL
+#define SYS_RISCV_FLUSH_ICACHE_ALL   (SYS_RISCV_FLUSH_ICACHE_LOCAL)
+
 #endif /* _ASM_RISCV_CACHEFLUSH_H */

arch/riscv/include/asm/io.h

@@ -19,6 +19,8 @@
 #ifndef _ASM_RISCV_IO_H
 #define _ASM_RISCV_IO_H
 
+#include <linux/types.h>
+
 #ifdef CONFIG_MMU
 
 extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
@@ -32,7 +34,7 @@ extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 #define ioremap_wc(addr, size) ioremap((addr), (size))
 #define ioremap_wt(addr, size) ioremap((addr), (size))
 
-extern void iounmap(void __iomem *addr);
+extern void iounmap(volatile void __iomem *addr);
 
 #endif /* CONFIG_MMU */
 
@@ -250,7 +252,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 			const ctype *buf = buffer;				\
 										\
 			do {							\
-				__raw_writeq(*buf++, addr);			\
+				__raw_write ## len(*buf++, addr);		\
 			} while (--count);					\
 		}								\
 		afence;								\
@@ -266,9 +268,9 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar())
 __io_reads_ins(ins,  u8, b, __io_pbr(), __io_par())
 __io_reads_ins(ins, u16, w, __io_pbr(), __io_par())
 __io_reads_ins(ins, u32, l, __io_pbr(), __io_par())
-#define insb(addr, buffer, count) __insb((void __iomem *)addr, buffer, count)
-#define insw(addr, buffer, count) __insw((void __iomem *)addr, buffer, count)
-#define insl(addr, buffer, count) __insl((void __iomem *)addr, buffer, count)
+#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count)
+#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count)
+#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count)
 
 __io_writes_outs(writes,  u8, b, __io_bw(), __io_aw())
 __io_writes_outs(writes, u16, w, __io_bw(), __io_aw())
@@ -280,9 +282,9 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw())
 __io_writes_outs(outs,  u8, b, __io_pbw(), __io_paw())
 __io_writes_outs(outs, u16, w, __io_pbw(), __io_paw())
 __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw())
-#define outsb(addr, buffer, count) __outsb((void __iomem *)addr, buffer, count)
-#define outsw(addr, buffer, count) __outsw((void __iomem *)addr, buffer, count)
-#define outsl(addr, buffer, count) __outsl((void __iomem *)addr, buffer, count)
+#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count)
+#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count)
+#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count)
 
 #ifdef CONFIG_64BIT
 __io_reads_ins(reads, u64, q, __io_br(), __io_ar())

arch/riscv/include/asm/mmu.h

@@ -19,6 +19,10 @@
 
 typedef struct {
 	void *vdso;
+#ifdef CONFIG_SMP
+	/* A local icache flush is needed before user execution can resume. */
+	cpumask_t icache_stale_mask;
+#endif
 } mm_context_t;
 
 #endif /* __ASSEMBLY__ */

arch/riscv/include/asm/mmu_context.h

 /*
  * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
  *
  *   This program is free software; you can redistribute it and/or
  *   modify it under the terms of the GNU General Public License
@@ -14,11 +15,13 @@
 #ifndef _ASM_RISCV_MMU_CONTEXT_H
 #define _ASM_RISCV_MMU_CONTEXT_H
 
+#include <linux/mm_types.h>
 #include <asm-generic/mm_hooks.h>
 
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm,
 	struct task_struct *task)
@@ -46,12 +49,54 @@ 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
+ * shoot downs, so instead we send an IPI that informs the remote harts they
+ * need to flush their local instruction caches.  To avoid pathologically slow
+ * behavior in a common case (a bunch of single-hart processes on a many-hart
+ * machine, ie 'make -j') we avoid the IPIs for harts that are not currently
+ * executing a MM context and instead schedule a deferred local instruction
+ * cache flush to be performed before execution resumes on each hart.  This
+ * actually performs that local instruction cache flush, which implicitly only
+ * refers to the current hart.
+ */
+static inline void flush_icache_deferred(struct mm_struct *mm)
+{
+#ifdef CONFIG_SMP
+	unsigned int cpu = smp_processor_id();
+	cpumask_t *mask = &mm->context.icache_stale_mask;
+
+	if (cpumask_test_cpu(cpu, mask)) {
+		cpumask_clear_cpu(cpu, mask);
+		/*
+		 * Ensure the remote hart's writes are visible to this hart.
+		 * This pairs with a barrier in flush_icache_mm.
+		 */
+		smp_mb();
+		local_flush_icache_all();
+	}
+#endif
+}
+
 static inline void switch_mm(struct mm_struct *prev,
 	struct mm_struct *next, struct task_struct *task)
 {
 	if (likely(prev != next)) {
+		/*
+		 * Mark the current MM context as inactive, and the next as
+		 * active.  This is at least used by the icache flushing
+		 * routines in order to determine who should
+		 */
+		unsigned int cpu = smp_processor_id();
+
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		cpumask_set_cpu(cpu, mm_cpumask(next));
+
 		set_pgdir(next->pgd);
 		local_flush_tlb_all();
+
+		flush_icache_deferred(next);
 	}
 }
 

arch/riscv/include/asm/pgtable.h

@@ -178,28 +178,6 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr)
 #define pte_offset_map(dir, addr)	pte_offset_kernel((dir), (addr))
 #define pte_unmap(pte)			((void)(pte))
 
-/*
- * Certain architectures need to do special things when PTEs within
- * a page table are directly modified.  Thus, the following hook is
- * made available.
- */
-static inline void set_pte(pte_t *ptep, pte_t pteval)
-{
-	*ptep = pteval;
-}
-
-static inline void set_pte_at(struct mm_struct *mm,
-	unsigned long addr, pte_t *ptep, pte_t pteval)
-{
-	set_pte(ptep, pteval);
-}
-
-static inline void pte_clear(struct mm_struct *mm,
-	unsigned long addr, pte_t *ptep)
-{
-	set_pte_at(mm, addr, ptep, __pte(0));
-}
-
 static inline int pte_present(pte_t pte)
 {
 	return (pte_val(pte) & _PAGE_PRESENT);
@@ -210,21 +188,22 @@ static inline int pte_none(pte_t pte)
 	return (pte_val(pte) == 0);
 }
 
-/* static inline int pte_read(pte_t pte) */
-
 static inline int pte_write(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_WRITE;
 }
 
+static inline int pte_exec(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_EXEC;
+}
+
 static inline int pte_huge(pte_t pte)
 {
 	return pte_present(pte)
 		&& (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
 }
 
-/* static inline int pte_exec(pte_t pte) */
-
 static inline int pte_dirty(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_DIRTY;
@@ -311,6 +290,33 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
 	return pte_val(pte_a) == pte_val(pte_b);
 }
 
+/*
+ * Certain architectures need to do special things when PTEs within
+ * a page table are directly modified.  Thus, the following hook is
+ * made available.
+ */
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+	*ptep = pteval;
+}
+
+void flush_icache_pte(pte_t pte);
+
+static inline void set_pte_at(struct mm_struct *mm,
+	unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+	if (pte_present(pteval) && pte_exec(pteval))
+		flush_icache_pte(pteval);
+
+	set_pte(ptep, pteval);
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+	unsigned long addr, pte_t *ptep)
+{
+	set_pte_at(mm, addr, ptep, __pte(0));
+}
+
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 					unsigned long address, pte_t *ptep,

arch/riscv/include/asm/spinlock.h

@@ -24,7 +24,7 @@
 
 /* FIXME: Replace this with a ticket lock, like MIPS. */
 
-#define arch_spin_is_locked(x)	((x)->lock != 0)
+#define arch_spin_is_locked(x)	(READ_ONCE((x)->lock) != 0)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
@@ -58,15 +58,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	}
 }
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_rmb();
-	do {
-		cpu_relax();
-	} while (arch_spin_is_locked(lock));
-	smp_acquire__after_ctrl_dep();
-}
-
 /***********************************************************/
 
 static inline void arch_read_lock(arch_rwlock_t *lock)

arch/riscv/include/asm/timex.h

@@ -18,7 +18,7 @@
 
 typedef unsigned long cycles_t;
 
-static inline cycles_t get_cycles(void)
+static inline cycles_t get_cycles_inline(void)
 {
 	cycles_t n;
 
@@ -27,6 +27,7 @@ static inline cycles_t get_cycles(void)
 		: "=r" (n));
 	return n;
 }
+#define get_cycles get_cycles_inline
 
 #ifdef CONFIG_64BIT
 static inline uint64_t get_cycles64(void)

arch/riscv/include/asm/tlbflush.h

@@ -17,7 +17,12 @@
 
 #ifdef CONFIG_MMU
 
-/* Flush entire local TLB */
+#include <linux/mm_types.h>
+
+/*
+ * Flush entire local TLB.  'sfence.vma' implicitly fences with the instruction
+ * cache as well, so a 'fence.i' is not necessary.
+ */
 static inline void local_flush_tlb_all(void)
 {
 	__asm__ __volatile__ ("sfence.vma" : : : "memory");

arch/riscv/include/asm/vdso-syscalls.h

+/*
+ * Copyright (C) 2017 SiFive
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ASM_RISCV_VDSO_SYSCALLS_H
+#define _ASM_RISCV_VDSO_SYSCALLS_H
+
+#ifdef CONFIG_SMP
+
+/* These syscalls are only used by the vDSO and are not in the uapi. */
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
+
+#endif
+
+#endif /* _ASM_RISCV_VDSO_H */

arch/riscv/include/asm/vdso.h

@@ -38,4 +38,8 @@ struct vdso_data {
 	(void __user *)((unsigned long)(base) + __vdso_##name);			\
 })
 
+#ifdef CONFIG_SMP
+asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
+#endif
+
 #endif /* _ASM_RISCV_VDSO_H */

arch/riscv/kernel/head.S

@@ -152,6 +152,3 @@ END(_start)
 __PAGE_ALIGNED_BSS
 	/* Empty zero page */
 	.balign PAGE_SIZE
-ENTRY(empty_zero_page)
-	.fill (empty_zero_page + PAGE_SIZE) - ., 1, 0x00
-END(empty_zero_page)

arch/riscv/kernel/riscv_ksyms.c

@@ -12,4 +12,7 @@
 /*
  * Assembly functions that may be used (directly or indirectly) by modules
  */
+EXPORT_SYMBOL(__clear_user);
 EXPORT_SYMBOL(__copy_user);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memcpy);

arch/riscv/kernel/setup.c

@@ -58,7 +58,12 @@ 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;
+EXPORT_SYMBOL(pfn_base);
+
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
 
 /* The lucky hart to first increment this variable will boot the other cores */
 atomic_t hart_lottery;

arch/riscv/kernel/smp.c

@@ -38,6 +38,13 @@ enum ipi_message_type {
 	IPI_MAX
 };
 
+
+/* Unsupported */
+int setup_profiling_timer(unsigned int multiplier)
+{
+	return -EINVAL;
+}
+
 irqreturn_t handle_ipi(void)
 {
 	unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
@@ -108,3 +115,51 @@ void smp_send_reschedule(int cpu)
 {
 	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }
+
+/*
+ * Performs an icache flush for the given MM context.  RISC-V has no direct
+ * mechanism for instruction cache shoot downs, so instead we send an IPI that
+ * informs the remote harts they need to flush their local instruction caches.
+ * To avoid pathologically slow behavior in a common case (a bunch of
+ * single-hart processes on a many-hart machine, ie 'make -j') we avoid the
+ * IPIs for harts that are not currently executing a MM context and instead
+ * schedule a deferred local instruction cache flush to be performed before
+ * execution resumes on each hart.
+ */
+void flush_icache_mm(struct mm_struct *mm, bool local)
+{
+	unsigned int cpu;
+	cpumask_t others, *mask;
+
+	preempt_disable();
+
+	/* Mark every hart's icache as needing a flush for this MM. */
+	mask = &mm->context.icache_stale_mask;
+	cpumask_setall(mask);
+	/* Flush this hart's I$ now, and mark it as flushed. */
+	cpu = smp_processor_id();
+	cpumask_clear_cpu(cpu, mask);
+	local_flush_icache_all();
+
+	/*
+	 * Flush the I$ of other harts concurrently executing, and mark them as
+	 * flushed.
+	 */
+	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
+	local |= cpumask_empty(&others);
+	if (mm != current->active_mm || !local)
+		sbi_remote_fence_i(others.bits);
+	else {
+		/*
+		 * It's assumed that at least one strongly ordered operation is
+		 * performed on this hart between setting a hart's cpumask bit
+		 * and scheduling this MM context on that hart.  Sending an SBI
+		 * remote message will do this, but in the case where no
+		 * messages are sent we still need to order this hart's writes
+		 * with flush_icache_deferred().
+		 */
+		smp_mb();
+	}
+
+	preempt_enable();
+}

arch/riscv/kernel/sys_riscv.c

@@ -14,8 +14,8 @@
  */
 
 #include <linux/syscalls.h>
-#include <asm/cmpxchg.h>
 #include <asm/unistd.h>
+#include <asm/cacheflush.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -47,3 +47,34 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
 	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12);
 }
 #endif /* !CONFIG_64BIT */
+
+#ifdef CONFIG_SMP
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * sys_riscv_flush_icache() is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
+	uintptr_t, flags)
+{
+	struct mm_struct *mm = current->mm;
+	bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0;
+
+	/* Check the reserved flags. */
+	if (unlikely(flags & !SYS_RISCV_FLUSH_ICACHE_ALL))
+		return -EINVAL;
+
+	flush_icache_mm(mm, local);
+
+	return 0;
+}
+#endif

arch/riscv/kernel/syscall_table.c

@@ -15,6 +15,7 @@
 #include <linux/linkage.h>
 #include <linux/syscalls.h>
 #include <asm-generic/syscalls.h>
+#include <asm/vdso.h>
 
 #undef __SYSCALL
 #define __SYSCALL(nr, call)	[nr] = (call),
@@ -22,4 +23,5 @@
 void *sys_call_table[__NR_syscalls] = {
 	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
 #include <asm/unistd.h>
+#include <asm/vdso-syscalls.h>
 };

arch/riscv/kernel/vdso/Makefile

 # Copied from arch/tile/kernel/vdso/Makefile
 
 # Symbols present in the vdso
-vdso-syms = rt_sigreturn
+vdso-syms  = rt_sigreturn
+vdso-syms += gettimeofday
+vdso-syms += clock_gettime
+vdso-syms += clock_getres
+vdso-syms += getcpu
+vdso-syms += flush_icache
 
 # Files to link into the vdso
 obj-vdso = $(patsubst %, %.o, $(vdso-syms))

arch/riscv/kernel/vdso/clock_getres.S

+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_clock_getres(clockid_t clock_id, struct timespec *res); */
+ENTRY(__vdso_clock_getres)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_clock_getres
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_clock_getres)

arch/riscv/kernel/vdso/clock_gettime.S

+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_clock_gettime(clockid_t clock_id, struct timespec *tp); */
+ENTRY(__vdso_clock_gettime)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_clock_gettime
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_clock_gettime)

arch/riscv/kernel/vdso/flush_icache.S

+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+#include <asm/vdso-syscalls.h>
+
+	.text
+/* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
+ENTRY(__vdso_flush_icache)
+	.cfi_startproc
+#ifdef CONFIG_SMP
+	li a7, __NR_riscv_flush_icache
+	ecall
+#else
+	fence.i
+	li a0, 0
+#endif
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_flush_icache)

arch/riscv/kernel/vdso/getcpu.S

+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
+ENTRY(__vdso_getcpu)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_getcpu
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_getcpu)

arch/riscv/kernel/vdso/gettimeofday.S

+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); */
+ENTRY(__vdso_gettimeofday)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_gettimeofday
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_gettimeofday)

arch/riscv/kernel/vdso/vdso.lds.S

@@ -70,8 +70,11 @@ VERSION
 	LINUX_4.15 {
 	global:
 		__vdso_rt_sigreturn;
-		__vdso_cmpxchg32;
-		__vdso_cmpxchg64;
+		__vdso_gettimeofday;
+		__vdso_clock_gettime;
+		__vdso_clock_getres;
+		__vdso_getcpu;
+		__vdso_flush_icache;
 	local: *;
 	};
 }

arch/riscv/lib/delay.c

@@ -84,6 +84,7 @@ void __delay(unsigned long cycles)
 	while ((unsigned long)(get_cycles() - t0) < cycles)
 		cpu_relax();
 }
+EXPORT_SYMBOL(__delay);
 
 void udelay(unsigned long usecs)
 {

arch/riscv/mm/Makefile

@@ -2,3 +2,4 @@ obj-y += init.o
 obj-y += fault.o
 obj-y += extable.o
 obj-y += ioremap.o
+obj-y += cacheflush.o

arch/riscv/mm/cacheflush.c

+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+void flush_icache_pte(pte_t pte)
+{
+	struct page *page = pte_page(pte);
+
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+		flush_icache_all();
+}

arch/riscv/mm/ioremap.c

@@ -85,7 +85,7 @@ EXPORT_SYMBOL(ioremap);
  *
  * Caller must ensure there is only one unmapping for the same pointer.
  */
-void iounmap(void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
 {
 	vunmap((void *)((unsigned long)addr & PAGE_MASK));
 }

arch/s390/Makefile

+# SPDX-License-Identifier: GPL-2.0
 #
 # s390/Makefile
 #
@@ -6,10 +7,6 @@
 # for "archclean" and "archdep" for cleaning up and making dependencies for
 # this architecture
 #
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
 # Copyright (C) 1994 by Linus Torvalds
 #
 

arch/s390/appldata/appldata_base.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Base infrastructure for Linux-z/VM Monitor Stream, Stage 1.
  * Exports appldata_register_ops() and appldata_unregister_ops() for the

arch/s390/appldata/appldata_mem.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Data gathering module for Linux-VM Monitor Stream, Stage 1.
  * Collects data related to memory management.

arch/s390/appldata/appldata_net_sum.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Data gathering module for Linux-VM Monitor Stream, Stage 1.
  * Collects accumulated network statistics (Packets received/transmitted,

arch/s390/appldata/appldata_os.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Data gathering module for Linux-VM Monitor Stream, Stage 1.
  * Collects misc. OS related data (CPU utilization, running processes).

arch/s390/boot/install.sh

 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 #
 # arch/s390x/boot/install.sh
 #
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
 # Copyright (C) 1995 by Linus Torvalds
 #
 # Adapted from code in arch/i386/boot/Makefile by H. Peter Anvin

arch/s390/crypto/aes_s390.c

+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -11,12 +12,6 @@
  *		Harald Freudenberger <freude@de.ibm.com>
  *
  * Derived from "crypto/aes_generic.c"
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #define KMSG_COMPONENT "aes_s390"

arch/s390/crypto/arch_random.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * s390 arch random implementation.
  *
  * Copyright IBM Corp. 2017
  * Author(s): Harald Freudenberger <freude@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  */
 
 #include <linux/kernel.h>

arch/s390/crypto/crc32-vx.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Crypto-API module for CRC-32 algorithms implemented with the
  * z/Architecture Vector Extension Facility.

arch/s390/crypto/des_s390.c

+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -6,12 +7,6 @@
  * Copyright IBM Corp. 2003, 2011
  * Author(s): Thomas Spatzier
  *	      Jan Glauber (jan.glauber@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  */
 
 #include <linux/init.h>

arch/s390/crypto/ghash_s390.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Cryptographic API.
  *

arch/s390/crypto/paes_s390.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Cryptographic API.
  *
@@ -7,11 +8,6 @@
  *   Copyright IBM Corp. 2017
  *   Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  *		Harald Freudenberger <freude@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  */
 
 #define KMSG_COMPONENT "paes_s390"

arch/s390/crypto/prng.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright IBM Corp. 2006, 2015
  * Author(s): Jan Glauber <jan.glauber@de.ibm.com>

arch/s390/crypto/sha.h

+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Cryptographic API.
  *
@@ -5,12 +6,6 @@
  *
  * Copyright IBM Corp. 2007
  * Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 #ifndef _CRYPTO_ARCH_S390_SHA_H
 #define _CRYPTO_ARCH_S390_SHA_H

arch/s390/crypto/sha256_s390.c

+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -6,12 +7,6 @@
  * s390 Version:
  *   Copyright IBM Corp. 2005, 2011
  *   Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 #include <crypto/internal/hash.h>
 #include <linux/init.h>

arch/s390/crypto/sha512_s390.c

+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -5,12 +6,6 @@
  *
  * Copyright IBM Corp. 2007
  * Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 #include <crypto/internal/hash.h>
 #include <crypto/sha.h>

arch/s390/crypto/sha_common.c

+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Cryptographic API.
  *
@@ -5,12 +6,6 @@
  *
  * Copyright IBM Corp. 2007
  * Author(s): Jan Glauber (jang@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <crypto/internal/hash.h>

arch/s390/hypfs/inode.c

+// SPDX-License-Identifier: GPL-1.0+
 /*
  *    Hypervisor filesystem for Linux on s390.
  *
  *    Copyright IBM Corp. 2006, 2008
  *    Author(s): Michael Holzheu <holzheu@de.ibm.com>
- *    License: GPL
  */
 
 #define KMSG_COMPONENT "hypfs"

arch/s390/include/asm/cpu_mf.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * CPU-measurement facilities
  *
  *  Copyright IBM Corp. 2012
  *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *	       Jan Glauber <jang@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 #ifndef _ASM_S390_CPU_MF_H
 #define _ASM_S390_CPU_MF_H

arch/s390/include/asm/elf.h

@@ -194,13 +194,14 @@ struct arch_elf_state {
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
 
-/*
- * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
- * space open for things that want to use the area for 32-bit pointers.
- */
-#define ELF_ET_DYN_BASE		(is_compat_task() ? 0x000400000UL : \
-						    0x100000000UL)
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk. 64-bit
+   tasks are aligned to 4GB. */
+#define ELF_ET_DYN_BASE (is_compat_task() ? \
+				(STACK_TOP / 3 * 2) : \
+				(STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports. */

arch/s390/include/asm/kprobes.h

+/* SPDX-License-Identifier: GPL-2.0+ */
 #ifndef _ASM_S390_KPROBES_H
 #define _ASM_S390_KPROBES_H
 /*
  *  Kernel Probes (KProbes)
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright IBM Corp. 2002, 2006
  *
  * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel

arch/s390/include/asm/kvm_host.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * definition for kernel virtual machines on s390
  *
  * Copyright IBM Corp. 2008, 2009
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  */
 

arch/s390/include/asm/kvm_para.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * definition for paravirtual devices on s390
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
  */
 /*
@@ -20,8 +17,6 @@
  *
  * Copyright IBM Corp. 2007,2008
  * Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
  */
 #ifndef __S390_KVM_PARA_H
 #define __S390_KVM_PARA_H

arch/s390/include/asm/livepatch.h

+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * livepatch.h - s390-specific Kernel Live Patching Core
  *
@@ -7,13 +8,6 @@
  *	      Jiri Slaby
  */
 
-/*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
 #ifndef ASM_LIVEPATCH_H
 #define ASM_LIVEPATCH_H
 

arch/s390/include/asm/mmu_context.h

@@ -28,7 +28,7 @@ static inline int init_new_context(struct task_struct *tsk,
 #ifdef CONFIG_PGSTE
 	mm->context.alloc_pgste = page_table_allocate_pgste ||
 		test_thread_flag(TIF_PGSTE) ||
-		current->mm->context.alloc_pgste;
+		(current->mm && current->mm->context.alloc_pgste);
 	mm->context.has_pgste = 0;
 	mm->context.use_skey = 0;
 	mm->context.use_cmma = 0;

arch/s390/include/asm/pgtable.h

@@ -709,7 +709,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
 }
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
@@ -1264,6 +1264,12 @@ static inline pud_t pud_mkwrite(pud_t pud)
 	return pud;
 }
 
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+	return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
+}
+
 static inline pud_t pud_mkclean(pud_t pud)
 {
 	if (pud_large(pud)) {

arch/s390/include/asm/syscall.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Access to user system call parameters and results
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
 #ifndef _ASM_SYSCALL_H

arch/s390/include/asm/sysinfo.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * definition for store system information stsi
  *
  * Copyright IBM Corp. 2001, 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Ulrich Weigand <weigand@de.ibm.com>
  *		 Christian Borntraeger <borntraeger@de.ibm.com>
  */

arch/s390/include/asm/topology.h

@@ -53,6 +53,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu);
 static inline void topology_init_early(void) { }
 static inline void topology_schedule_update(void) { }
 static inline int topology_cpu_init(struct cpu *cpu) { return 0; }
+static inline int topology_cpu_dedicated(int cpu_nr) { return 0; }
 static inline void topology_expect_change(void) { }
 
 #endif /* CONFIG_SCHED_TOPOLOGY */

arch/s390/include/uapi/asm/kvm.h

@@ -6,10 +6,6 @@
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */

arch/s390/include/uapi/asm/kvm_para.h

@@ -4,9 +4,5 @@
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
  */

arch/s390/include/uapi/asm/kvm_perf.h

@@ -4,10 +4,6 @@
  *
  * Copyright 2014 IBM Corp.
  * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_KVM_PERF_S390_H

arch/s390/include/uapi/asm/virtio-ccw.h

@@ -4,10 +4,6 @@
  *
  * Copyright IBM Corp. 2013
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *  Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
  */
 #ifndef __KVM_VIRTIO_CCW_H

arch/s390/include/uapi/asm/zcrypt.h

@@ -9,20 +9,6 @@
  *	       Eric Rossman (edrossma@us.ibm.com)
  *
  *  Hotplug & misc device support: Jochen Roehrig (roehrig@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __ASM_S390_ZCRYPT_H

arch/s390/kernel/debug.c

@@ -1392,7 +1392,7 @@ int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view,
 	else
 		except_str = "-";
 	caller = (unsigned long) entry->caller;
-	rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %p  ",
+	rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %pK  ",
 		      area, sec, usec, level, except_str,
 		      entry->id.fields.cpuid, (void *)caller);
 	return rc;

arch/s390/kernel/dis.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Disassemble s390 instructions.
  *
@@ -396,9 +397,14 @@ struct s390_insn *find_insn(unsigned char *code)
 	unsigned char opfrag;
 	int i;
 
+	/* Search the opcode offset table to find an entry which
+	 * matches the beginning of the opcode. If there is no match
+	 * the last entry will be used, which is the default entry for
+	 * unknown instructions as well as 1-byte opcode instructions.
+	 */
 	for (i = 0; i < ARRAY_SIZE(opcode_offset); i++) {
 		entry = &opcode_offset[i];
-		if (entry->opcode == code[0] || entry->opcode == 0)
+		if (entry->opcode == code[0])
 			break;
 	}
 
@@ -543,7 +549,7 @@ void show_code(struct pt_regs *regs)
 		start += opsize;
 		pr_cont("%s", buffer);
 		ptr = buffer;
-		ptr += sprintf(ptr, "\n\t  ");
+		ptr += sprintf(ptr, "\n          ");
 		hops++;
 	}
 	pr_cont("\n");

arch/s390/kernel/dumpstack.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Stack dumping functions
  *