Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

Pull MIPS fixes from Ralf Baechle:
 "Lantiq:
    - Fix adding xbar resoures causing a panic

  Loongson3:
    - Some Loongson 3A don't identify themselves as having an FTLB so
      hardwire that knowledge into CPU probing.
    - Handle Loongson 3 TLB peculiarities in the fast path of the RDHWR
      emulation.
    - Fix invalid FTLB entries with huge page on VTLB+FTLB platforms
    - Add missing calculation of S-cache and V-cache cache-way size

  Ralink:
    - Fix typos in rt3883 pinctrl data

  Generic:
    - Force o32 fp64 support on 32bit MIPS64r6 kernels
    - Yet another build fix after the linux/sched.h changes
    - Wire up statx system call
    - Fix stack unwinding after introduction of IRQ stack
    - Fix spinlock code to build even for microMIPS with recent binutils

  SMP-CPS:
    - Fix retrieval of VPE mask on big endian CPUs"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus:
  MIPS: IRQ Stack: Unwind IRQ stack onto task stack
  MIPS: c-r4k: Fix Loongson-3's vcache/scache waysize calculation
  MIPS: Flush wrong invalid FTLB entry for huge page
  MIPS: Check TLB before handle_ri_rdhwr() for Loongson-3
  MIPS: Add MIPS_CPU_FTLB for Loongson-3A R2
  MIPS: Lantiq: fix missing xbar kernel panic
  MIPS: smp-cps: Fix retrieval of VPE mask on big endian CPUs
  MIPS: Wire up statx system call
  MIPS: Include asm/ptrace.h now linux/sched.h doesn't
  MIPS: ralink: Fix typos in rt3883 pinctrl
  MIPS: End spinlocks with .insn
  MIPS: Force o32 fp64 support on 32bit MIPS64r6 kernels

arch/mips/Kconfig

@@ -1531,7 +1531,7 @@ config CPU_MIPS64_R6
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
 	select GENERIC_CSUM
-	select MIPS_O32_FP64_SUPPORT if MIPS32_O32
+	select MIPS_O32_FP64_SUPPORT if 32BIT || MIPS32_O32
 	select HAVE_KVM
 	help
 	  Choose this option to build a kernel for release 6 or later of the

arch/mips/include/asm/fpu.h

@@ -21,6 +21,7 @@
 #include <asm/cpu-features.h>
 #include <asm/fpu_emulator.h>
 #include <asm/hazards.h>
+#include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/current.h>
 #include <asm/msa.h>

arch/mips/include/asm/irq.h

@@ -18,9 +18,24 @@
 #include <irq.h>
 
 #define IRQ_STACK_SIZE			THREAD_SIZE
+#define IRQ_STACK_START			(IRQ_STACK_SIZE - sizeof(unsigned long))
 
 extern void *irq_stack[NR_CPUS];
 
+/*
+ * The highest address on the IRQ stack contains a dummy frame put down in
+ * genex.S (handle_int & except_vec_vi_handler) which is structured as follows:
+ *
+ *   top ------------
+ *       | task sp  | <- irq_stack[cpu] + IRQ_STACK_START
+ *       ------------
+ *       |          | <- First frame of IRQ context
+ *       ------------
+ *
+ * task sp holds a copy of the task stack pointer where the struct pt_regs
+ * from exception entry can be found.
+ */
+
 static inline bool on_irq_stack(int cpu, unsigned long sp)
 {
 	unsigned long low = (unsigned long)irq_stack[cpu];

arch/mips/include/asm/spinlock.h

@@ -127,7 +127,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 		"	andi	%[ticket], %[ticket], 0xffff		\n"
 		"	bne	%[ticket], %[my_ticket], 4f		\n"
 		"	 subu	%[ticket], %[my_ticket], %[ticket]	\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		"	.subsection 2					\n"
 		"4:	andi	%[ticket], %[ticket], 0xffff		\n"
 		"	sll	%[ticket], 5				\n"
@@ -202,7 +202,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 		"	sc	%[ticket], %[ticket_ptr]		\n"
 		"	beqz	%[ticket], 1b				\n"
 		"	 li	%[ticket], 1				\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		"	.subsection 2					\n"
 		"3:	b	2b					\n"
 		"	 li	%[ticket], 0				\n"
@@ -382,7 +382,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 		"	.set	reorder					\n"
 		__WEAK_LLSC_MB
 		"	li	%2, 1					\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
 		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
@@ -422,7 +422,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 			"	lui	%1, 0x8000			\n"
 			"	sc	%1, %0				\n"
 			"	li	%2, 1				\n"
-			"2:						\n"
+			"2:	.insn					\n"
 			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp),
 			  "=&r" (ret)
 			: GCC_OFF_SMALL_ASM() (rw->lock)

arch/mips/include/uapi/asm/unistd.h

@@ -386,17 +386,18 @@
 #define __NR_pkey_mprotect		(__NR_Linux + 363)
 #define __NR_pkey_alloc			(__NR_Linux + 364)
 #define __NR_pkey_free			(__NR_Linux + 365)
+#define __NR_statx			(__NR_Linux + 366)
 
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		365
+#define __NR_Linux_syscalls		366
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		365
+#define __NR_O32_Linux_syscalls		366
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -730,16 +731,17 @@
 #define __NR_pkey_mprotect		(__NR_Linux + 323)
 #define __NR_pkey_alloc			(__NR_Linux + 324)
 #define __NR_pkey_free			(__NR_Linux + 325)
+#define __NR_statx			(__NR_Linux + 326)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		325
+#define __NR_Linux_syscalls		326
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		325
+#define __NR_64_Linux_syscalls		326
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1077,15 +1079,16 @@
 #define __NR_pkey_mprotect		(__NR_Linux + 327)
 #define __NR_pkey_alloc			(__NR_Linux + 328)
 #define __NR_pkey_free			(__NR_Linux + 329)
+#define __NR_statx			(__NR_Linux + 330)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		329
+#define __NR_Linux_syscalls		330
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		329
+#define __NR_N32_Linux_syscalls		330
 
 #endif /* _UAPI_ASM_UNISTD_H */

arch/mips/kernel/asm-offsets.c

@@ -102,6 +102,7 @@ void output_thread_info_defines(void)
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);
 	DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
+	DEFINE(_IRQ_STACK_START, IRQ_STACK_START);
 	BLANK();
 }
 

arch/mips/kernel/cps-vec.S

@@ -361,7 +361,7 @@ LEAF(mips_cps_get_bootcfg)
 	END(mips_cps_get_bootcfg)
 
 LEAF(mips_cps_boot_vpes)
-	PTR_L	ta2, COREBOOTCFG_VPEMASK(a0)
+	lw	ta2, COREBOOTCFG_VPEMASK(a0)
 	PTR_L	ta3, COREBOOTCFG_VPECONFIG(a0)
 
 #if defined(CONFIG_CPU_MIPSR6)

arch/mips/kernel/cpu-probe.c

@@ -1824,7 +1824,7 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 		}
 
 		decode_configs(c);
-		c->options |= MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
+		c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
 		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 		break;
 	default:

arch/mips/kernel/genex.S

@@ -215,9 +215,11 @@ NESTED(handle_int, PT_SIZE, sp)
 	beq	t0, t1, 2f
 
 	/* Switch to IRQ stack */
-	li	t1, _IRQ_STACK_SIZE
+	li	t1, _IRQ_STACK_START
 	PTR_ADD sp, t0, t1
 
+	/* Save task's sp on IRQ stack so that unwinding can follow it */
+	LONG_S	s1, 0(sp)
 2:
 	jal	plat_irq_dispatch
 
@@ -325,9 +327,11 @@ NESTED(except_vec_vi_handler, 0, sp)
 	beq	t0, t1, 2f
 
 	/* Switch to IRQ stack */
-	li	t1, _IRQ_STACK_SIZE
+	li	t1, _IRQ_STACK_START
 	PTR_ADD sp, t0, t1
 
+	/* Save task's sp on IRQ stack so that unwinding can follow it */
+	LONG_S	s1, 0(sp)
 2:
 	jalr	v0
 
@@ -519,7 +523,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	BUILD_HANDLER reserved reserved sti verbose	/* others */
 
 	.align	5
-	LEAF(handle_ri_rdhwr_vivt)
+	LEAF(handle_ri_rdhwr_tlbp)
 	.set	push
 	.set	noat
 	.set	noreorder
@@ -538,7 +542,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.set	pop
 	bltz	k1, handle_ri	/* slow path */
 	/* fall thru */
-	END(handle_ri_rdhwr_vivt)
+	END(handle_ri_rdhwr_tlbp)
 
 	LEAF(handle_ri_rdhwr)
 	.set	push

arch/mips/kernel/process.c

@@ -488,32 +488,53 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
 					      unsigned long pc,
 					      unsigned long *ra)
 {
+	unsigned long low, high, irq_stack_high;
 	struct mips_frame_info info;
 	unsigned long size, ofs;
+	struct pt_regs *regs;
 	int leaf;
-	extern void ret_from_irq(void);
-	extern void ret_from_exception(void);
 
 	if (!stack_page)
 		return 0;
 
 	/*
-	 * If we reached the bottom of interrupt context,
-	 * return saved pc in pt_regs.
+	 * IRQ stacks start at IRQ_STACK_START
+	 * task stacks at THREAD_SIZE - 32
 	 */
-	if (pc == (unsigned long)ret_from_irq ||
-	    pc == (unsigned long)ret_from_exception) {
-		struct pt_regs *regs;
-		if (*sp >= stack_page &&
-		    *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
-			regs = (struct pt_regs *)*sp;
+	low = stack_page;
+	if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) {
+		high = stack_page + IRQ_STACK_START;
+		irq_stack_high = high;
+	} else {
+		high = stack_page + THREAD_SIZE - 32;
+		irq_stack_high = 0;
+	}
+
+	/*
+	 * If we reached the top of the interrupt stack, start unwinding
+	 * the interrupted task stack.
+	 */
+	if (unlikely(*sp == irq_stack_high)) {
+		unsigned long task_sp = *(unsigned long *)*sp;
+
+		/*
+		 * Check that the pointer saved in the IRQ stack head points to
+		 * something within the stack of the current task
+		 */
+		if (!object_is_on_stack((void *)task_sp))
+			return 0;
+
+		/*
+		 * Follow pointer to tasks kernel stack frame where interrupted
+		 * state was saved.
+		 */
+		regs = (struct pt_regs *)task_sp;
 		pc = regs->cp0_epc;
 		if (!user_mode(regs) && __kernel_text_address(pc)) {
 			*sp = regs->regs[29];
 			*ra = regs->regs[31];
 			return pc;
 		}
-		}
 		return 0;
 	}
 	if (!kallsyms_lookup_size_offset(pc, &size, &ofs))
@@ -533,8 +554,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
 	if (leaf < 0)
 		return 0;
 
-	if (*sp < stack_page ||
-	    *sp + info.frame_size > stack_page + THREAD_SIZE - 32)
+	if (*sp < low || *sp + info.frame_size > high)
 		return 0;
 
 	if (leaf)

arch/mips/kernel/scall32-o32.S

@@ -600,3 +600,4 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
+	PTR	sys_statx

arch/mips/kernel/scall64-64.S

@@ -438,4 +438,5 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 5325 */
+	PTR	sys_statx
 	.size	sys_call_table,.-sys_call_table

arch/mips/kernel/scall64-n32.S

@@ -433,4 +433,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free
+	PTR	sys_statx			/* 6330 */
 	.size	sysn32_call_table,.-sysn32_call_table

arch/mips/kernel/scall64-o32.S

@@ -588,4 +588,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
+	PTR	sys_statx
 	.size	sys32_call_table,.-sys32_call_table

arch/mips/kernel/traps.c

@@ -83,7 +83,7 @@ extern asmlinkage void handle_dbe(void);
 extern asmlinkage void handle_sys(void);
 extern asmlinkage void handle_bp(void);
 extern asmlinkage void handle_ri(void);
-extern asmlinkage void handle_ri_rdhwr_vivt(void);
+extern asmlinkage void handle_ri_rdhwr_tlbp(void);
 extern asmlinkage void handle_ri_rdhwr(void);
 extern asmlinkage void handle_cpu(void);
 extern asmlinkage void handle_ov(void);
@@ -2408,9 +2408,18 @@ void __init trap_init(void)
 
 	set_except_vector(EXCCODE_SYS, handle_sys);
 	set_except_vector(EXCCODE_BP, handle_bp);
-	set_except_vector(EXCCODE_RI, rdhwr_noopt ? handle_ri :
-			  (cpu_has_vtag_icache ?
-			   handle_ri_rdhwr_vivt : handle_ri_rdhwr));
+
+	if (rdhwr_noopt)
+		set_except_vector(EXCCODE_RI, handle_ri);
+	else {
+		if (cpu_has_vtag_icache)
+			set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+		else if (current_cpu_type() == CPU_LOONGSON3)
+			set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+		else
+			set_except_vector(EXCCODE_RI, handle_ri_rdhwr);
+	}
+
 	set_except_vector(EXCCODE_CPU, handle_cpu);
 	set_except_vector(EXCCODE_OV, handle_ov);
 	set_except_vector(EXCCODE_TR, handle_tr);

arch/mips/lantiq/xway/sysctrl.c

@@ -467,7 +467,7 @@ void __init ltq_soc_init(void)
 
 		if (!np_xbar)
 			panic("Failed to load xbar nodes from devicetree");
-		if (of_address_to_resource(np_pmu, 0, &res_xbar))
+		if (of_address_to_resource(np_xbar, 0, &res_xbar))
 			panic("Failed to get xbar resources");
 		if (!request_mem_region(res_xbar.start, resource_size(&res_xbar),
 			res_xbar.name))

arch/mips/mm/c-r4k.c

@@ -1562,6 +1562,7 @@ static void probe_vcache(void)
 	vcache_size = c->vcache.sets * c->vcache.ways * c->vcache.linesz;
 
 	c->vcache.waybit = 0;
+	c->vcache.waysize = vcache_size / c->vcache.ways;
 
 	pr_info("Unified victim cache %ldkB %s, linesize %d bytes.\n",
 		vcache_size >> 10, way_string[c->vcache.ways], c->vcache.linesz);
@@ -1664,6 +1665,7 @@ static void __init loongson3_sc_init(void)
 	/* Loongson-3 has 4 cores, 1MB scache for each. scaches are shared */
 	scache_size *= 4;
 	c->scache.waybit = 0;
+	c->scache.waysize = scache_size / c->scache.ways;
 	pr_info("Unified secondary cache %ldkB %s, linesize %d bytes.\n",
 	       scache_size >> 10, way_string[c->scache.ways], c->scache.linesz);
 	if (scache_size)

arch/mips/mm/tlbex.c

@@ -760,7 +760,8 @@ static void build_huge_update_entries(u32 **p, unsigned int pte,
 static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
 				    struct uasm_label **l,
 				    unsigned int pte,
-				    unsigned int ptr)
+				    unsigned int ptr,
+				    unsigned int flush)
 {
 #ifdef CONFIG_SMP
 	UASM_i_SC(p, pte, 0, ptr);
@@ -769,6 +770,22 @@ static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
 #else
 	UASM_i_SW(p, pte, 0, ptr);
 #endif
+	if (cpu_has_ftlb && flush) {
+		BUG_ON(!cpu_has_tlbinv);
+
+		UASM_i_MFC0(p, ptr, C0_ENTRYHI);
+		uasm_i_ori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+		UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+		build_tlb_write_entry(p, l, r, tlb_indexed);
+
+		uasm_i_xori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+		UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+		build_huge_update_entries(p, pte, ptr);
+		build_huge_tlb_write_entry(p, l, r, pte, tlb_random, 0);
+
+		return;
+	}
+
 	build_huge_update_entries(p, pte, ptr);
 	build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0);
 }
@@ -2199,7 +2216,7 @@ static void build_r4000_tlb_load_handler(void)
 		uasm_l_tlbl_goaround2(&l, p);
 	}
 	uasm_i_ori(&p, wr.r1, wr.r1, (_PAGE_ACCESSED | _PAGE_VALID));
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
 #endif
 
 	uasm_l_nopage_tlbl(&l, p);
@@ -2254,7 +2271,7 @@ static void build_r4000_tlb_store_handler(void)
 	build_tlb_probe_entry(&p);
 	uasm_i_ori(&p, wr.r1, wr.r1,
 		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
 #endif
 
 	uasm_l_nopage_tlbs(&l, p);
@@ -2310,7 +2327,7 @@ static void build_r4000_tlb_modify_handler(void)
 	build_tlb_probe_entry(&p);
 	uasm_i_ori(&p, wr.r1, wr.r1,
 		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 0);
 #endif
 
 	uasm_l_nopage_tlbm(&l, p);

arch/mips/ralink/rt3883.c

@@ -35,7 +35,7 @@ static struct rt2880_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) };
 static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
 static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
 static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) };
-static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna a", 0, 35, 3) };
+static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) };
 static struct rt2880_pmx_func pci_func[] = {
 	FUNC("pci-dev", 0, 40, 32),
 	FUNC("pci-host2", 1, 40, 32),
@@ -43,7 +43,7 @@ static struct rt2880_pmx_func pci_func[] = {
 	FUNC("pci-fnc", 3, 40, 32)
 };
 static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) };
-static struct rt2880_pmx_func ge2_func[] = { FUNC("ge1", 0, 84, 12) };
+static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) };
 
 static struct rt2880_pmx_group rt3883_pinmux_data[] = {
 	GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C),