Main MIPS changes for v5.2:

- A set of memblock initialization improvements thanks to Serge Semin, tidying up after our conversion from bootmem to memblock back in v4.20. - Our eBPF JIT the previously supported only MIPS64r2 through MIPS64r5 is improved to also support MIPS64r6. Support for MIPS32 systems is introduced, with the caveat that it only works for programs that don't use 64 bit registers or operations - those will bail out & need to be interpreted. - Improvements to the allocation & configuration of our exception vector that should fix issues seen on some platforms using recent versions of U-Boot. - Some minor improvements to code generated for jump labels, along with enabling them by default for generic kernels. -----BEGIN PGP SIGNATURE----- iIsEABYIADMWIQRgLjeFAZEXQzy86/s+p5+stXUA3QUCXNNB2RUccGF1bC5idXJ0 b25AbWlwcy5jb20ACgkQPqefrLV1AN1zeAD/U/ScowcQE8ynoY97nA70d3UmbETH YETUX5WcOfR65O8A/1hvMX8QJ1x87XUlNTkE6Gdh/itAZJpJWiSo3dnd1GoF =L9IJ -----END PGP SIGNATURE----- Merge tag 'mips_5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux Pull MIPS updates from Paul Burton: - A set of memblock initialization improvements thanks to Serge Semin, tidying up after our conversion from bootmem to memblock back in v4.20. - Our eBPF JIT the previously supported only MIPS64r2 through MIPS64r5 is improved to also support MIPS64r6. Support for MIPS32 systems is introduced, with the caveat that it only works for programs that don't use 64 bit registers or operations - those will bail out & need to be interpreted. - Improvements to the allocation & configuration of our exception vector that should fix issues seen on some platforms using recent versions of U-Boot. - Some minor improvements to code generated for jump labels, along with enabling them by default for generic kernels. * tag 'mips_5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux: (27 commits) mips: Manually call fdt_init_reserved_mem() method mips: Make sure dt memory regions are valid mips: Perform early low memory test mips: Dump memblock regions for debugging mips: Add reserve-nomap memory type support mips: Use memblock to reserve the __nosave memory range mips: Discard post-CMA-init foreach loop mips: Reserve memory for the kernel image resources MIPS: Remove duplicate EBase configuration MIPS: Sync icache for whole exception vector MIPS: Always allocate exception vector for MIPSr2+ MIPS: Use memblock_phys_alloc() for exception vector mips: Combine memblock init and memory reservation loops mips: Discard rudiments from bootmem_init mips: Make sure kernel .bss exists in boot mem pool mips: vdso: drop unnecessary cc-ldoption Revert "MIPS: ralink: fix cpu clock of mt7621 and add dt clk devices" MIPS: generic: Enable CONFIG_JUMP_LABEL MIPS: jump_label: Use compact branches for >= r6 MIPS: jump_label: Remove redundant nops ...
2024-09-29 22:02:02 +00:00 · 2019-05-08 16:41:47 -07:00 · 2019-05-08 16:41:47 -07:00 · 92fab77b6b
commit 92fab77b6b
parent ef75bd71c5 3751cbda8f
22 changed files with 341 additions and 1825 deletions
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@ -44,8 +44,7 @@ config MIPS
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT
-	select HAVE_CBPF_JIT if (!64BIT && !CPU_MICROMIPS)
-	select HAVE_EBPF_JIT if (64BIT && !CPU_MICROMIPS)
+	select HAVE_EBPF_JIT if (!CPU_MICROMIPS)
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
@ -2474,7 +2473,6 @@ config SB1_PASS_2_1_WORKAROUNDS
 	depends on CPU_SB1 && CPU_SB1_PASS_2
 	default y

-
 choice
 	prompt "SmartMIPS or microMIPS ASE support"

--- a/arch/mips/configs/generic_defconfig
+++ b/arch/mips/configs/generic_defconfig
@ -26,6 +26,7 @@ CONFIG_MIPS_CPS=y
 CONFIG_HIGHMEM=y
 CONFIG_NR_CPUS=16
 CONFIG_MIPS_O32_FP64_SUPPORT=y
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_TRIM_UNUSED_KSYMS=y
--- a/arch/mips/include/asm/bootinfo.h
+++ b/arch/mips/include/asm/bootinfo.h
@ -92,6 +92,7 @@ extern unsigned long mips_machtype;
 #define BOOT_MEM_ROM_DATA	2
 #define BOOT_MEM_RESERVED	3
 #define BOOT_MEM_INIT_RAM	4
+#define BOOT_MEM_NOMAP		5

 /*
 * A memory map that's built upon what was determined
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@ -11,6 +11,7 @@
 #ifndef __ASSEMBLY__

 #include <linux/types.h>
+#include <asm/isa-rev.h>

 #define JUMP_LABEL_NOP_SIZE 4

@ -21,15 +22,20 @@
 #endif

 #ifdef CONFIG_CPU_MICROMIPS
-#define B_INSN "b32"
+# define B_INSN "b32"
+# define J_INSN "j32"
+#elif MIPS_ISA_REV >= 6
+# define B_INSN "bc"
+# define J_INSN "bc"
 #else
-#define B_INSN "b"
+# define B_INSN "b"
+# define J_INSN "j"
 #endif

 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:\t" B_INSN " 2f\n\t"
-		"2:\tnop\n\t"
+		"2:\t.insn\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
 		".popsection\n\t"
@ -42,8 +48,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran

 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\tj %l[l_yes]\n\t"
-		"nop\n\t"
+	asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
 		".popsection\n\t"
--- a/arch/mips/include/asm/uasm.h
+++ b/arch/mips/include/asm/uasm.h
@ -86,14 +86,18 @@ Ip_u2u1(_ctcmsa);
 Ip_u2u1s3(_daddiu);
 Ip_u3u1u2(_daddu);
 Ip_u1u2(_ddivu);
+Ip_u3u1u2(_ddivu_r6);
 Ip_u1(_di);
 Ip_u2u1msbu3(_dins);
 Ip_u2u1msbu3(_dinsm);
 Ip_u2u1msbu3(_dinsu);
 Ip_u1u2(_divu);
+Ip_u3u1u2(_divu_r6);
 Ip_u1u2u3(_dmfc0);
+Ip_u3u1u2(_dmodu);
 Ip_u1u2u3(_dmtc0);
 Ip_u1u2(_dmultu);
+Ip_u3u1u2(_dmulu);
 Ip_u2u1u3(_drotr);
 Ip_u2u1u3(_drotr32);
 Ip_u2u1(_dsbh);
@ -131,6 +135,7 @@ Ip_u1u2u3(_mfc0);
 Ip_u1u2u3(_mfhc0);
 Ip_u1(_mfhi);
 Ip_u1(_mflo);
+Ip_u3u1u2(_modu);
 Ip_u3u1u2(_movn);
 Ip_u3u1u2(_movz);
 Ip_u1u2u3(_mtc0);
@ -139,6 +144,7 @@ Ip_u1(_mthi);
 Ip_u1(_mtlo);
 Ip_u3u1u2(_mul);
 Ip_u1u2(_multu);
+Ip_u3u1u2(_mulu);
 Ip_u3u1u2(_nor);
 Ip_u3u1u2(_or);
 Ip_u2u1u3(_ori);
@ -149,6 +155,8 @@ Ip_u2s3u1(_sb);
 Ip_u2s3u1(_sc);
 Ip_u2s3u1(_scd);
 Ip_u2s3u1(_sd);
+Ip_u3u1u2(_seleqz);
+Ip_u3u1u2(_selnez);
 Ip_u2s3u1(_sh);
 Ip_u2u1u3(_sll);
 Ip_u3u2u1(_sllv);
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@ -55,9 +55,9 @@ enum spec_op {
 	spec3_unused_op, spec4_unused_op, slt_op, sltu_op,
 	dadd_op, daddu_op, dsub_op, dsubu_op,
 	tge_op, tgeu_op, tlt_op, tltu_op,
-	teq_op, spec5_unused_op, tne_op, spec6_unused_op,
-	dsll_op, spec7_unused_op, dsrl_op, dsra_op,
-	dsll32_op, spec8_unused_op, dsrl32_op, dsra32_op
+	teq_op, seleqz_op, tne_op, selnez_op,
+	dsll_op, spec5_unused_op, dsrl_op, dsra_op,
+	dsll32_op, spec6_unused_op, dsrl32_op, dsra32_op
 };

 /*
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@ -58,15 +58,14 @@ resume_kernel:
 	local_irq_disable
 	lw	t0, TI_PRE_COUNT($28)
 	bnez	t0, restore_all
-need_resched:
 	LONG_L	t0, TI_FLAGS($28)
 	andi	t1, t0, _TIF_NEED_RESCHED
 	beqz	t1, restore_all
 	LONG_L	t0, PT_STATUS(sp)		# Interrupts off?
 	andi	t0, 1
 	beqz	t0, restore_all
-	jal	preempt_schedule_irq
-	b	need_resched
+	PTR_LA	ra, restore_all
+	j	preempt_schedule_irq
 #endif

 FEXPORT(ret_from_kernel_thread)
--- a/arch/mips/kernel/jump_label.c
+++ b/arch/mips/kernel/jump_label.c
@ -40,18 +40,38 @@ void arch_jump_label_transform(struct jump_entry *e,
 {
 	union mips_instruction *insn_p;
 	union mips_instruction insn;
+	long offset;

 	insn_p = (union mips_instruction *)msk_isa16_mode(e->code);

-	/* Jump only works within an aligned region its delay slot is in. */
-	BUG_ON((e->target & ~J_RANGE_MASK) != ((e->code + 4) & ~J_RANGE_MASK));
-
 	/* Target must have the right alignment and ISA must be preserved. */
 	BUG_ON((e->target & J_ALIGN_MASK) != J_ISA_BIT);

 	if (type == JUMP_LABEL_JMP) {
+		if (!IS_ENABLED(CONFIG_CPU_MICROMIPS) && MIPS_ISA_REV >= 6) {
+			offset = e->target - ((unsigned long)insn_p + 4);
+			offset >>= 2;
+
+			/*
+			 * The branch offset must fit in the instruction's 26
+			 * bit field.
+			 */
+			WARN_ON((offset >= BIT(25)) ||
+				(offset < -(long)BIT(25)));
+
+			insn.j_format.opcode = bc6_op;
+			insn.j_format.target = offset;
+		} else {
+			/*
+			 * Jump only works within an aligned region its delay
+			 * slot is in.
+			 */
+			WARN_ON((e->target & ~J_RANGE_MASK) !=
+				((e->code + 4) & ~J_RANGE_MASK));
+
 			insn.j_format.opcode = J_ISA_BIT ? mm_j32_op : j_op;
 			insn.j_format.target = e->target >> J_RANGE_SHIFT;
+		}
 	} else {
 		insn.word = 0; /* nop */
 	}
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@ -41,13 +41,27 @@ char *mips_get_machine_name(void)
 #ifdef CONFIG_USE_OF
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
-	return add_memory_region(base, size, BOOT_MEM_RAM);
+	if (base >= PHYS_ADDR_MAX) {
+		pr_warn("Trying to add an invalid memory region, skipped\n");
+		return;
+	}
+
+	/* Truncate the passed memory region instead of type casting */
+	if (base + size - 1 >= PHYS_ADDR_MAX || base + size < base) {
+		pr_warn("Truncate memory region %llx @ %llx to size %llx\n",
+			size, base, PHYS_ADDR_MAX - base);
+		size = PHYS_ADDR_MAX - base;
+	}
+
+	add_memory_region(base, size, BOOT_MEM_RAM);
 }

 int __init early_init_dt_reserve_memory_arch(phys_addr_t base,
 					phys_addr_t size, bool nomap)
 {
-	add_memory_region(base, size, BOOT_MEM_RESERVED);
+	add_memory_region(base, size,
+			  nomap ? BOOT_MEM_NOMAP : BOOT_MEM_RESERVED);
+
 	return 0;
 }

--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@ -27,6 +27,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/decompress/generic.h>
 #include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>

 #include <asm/addrspace.h>
 #include <asm/bootinfo.h>
@ -178,6 +179,7 @@ static bool __init __maybe_unused memory_region_available(phys_addr_t start,
 				in_ram = true;
 			break;
 		case BOOT_MEM_RESERVED:
+		case BOOT_MEM_NOMAP:
 			if ((start >= start_ && start < end_) ||
 			    (start < start_ && start + size >= start_))
 				free = false;
@ -213,6 +215,9 @@ static void __init print_memory_map(void)
 		case BOOT_MEM_RESERVED:
 			printk(KERN_CONT "(reserved)\n");
 			break;
+		case BOOT_MEM_NOMAP:
+			printk(KERN_CONT "(nomap)\n");
+			break;
 		default:
 			printk(KERN_CONT "type %lu\n", boot_mem_map.map[i].type);
 			break;
@ -371,7 +376,6 @@ static void __init bootmem_init(void)

 static void __init bootmem_init(void)
 {
-	unsigned long reserved_end;
 	phys_addr_t ramstart = PHYS_ADDR_MAX;
 	int i;

@ -382,10 +386,10 @@ static void __init bootmem_init(void)
 	 * will reserve the area used for the initrd.
 	 */
 	init_initrd();
-	reserved_end = (unsigned long) PFN_UP(__pa_symbol(&_end));

-	memblock_reserve(PHYS_OFFSET,
-			 (reserved_end << PAGE_SHIFT) - PHYS_OFFSET);
+	/* Reserve memory occupied by kernel. */
+	memblock_reserve(__pa_symbol(&_text),
+			__pa_symbol(&_end) - __pa_symbol(&_text));

 	/*
 	 * max_low_pfn is not a number of pages. The number of pages
@ -394,10 +398,7 @@ static void __init bootmem_init(void)
 	min_low_pfn = ~0UL;
 	max_low_pfn = 0;

-	/*
-	 * Find the highest page frame number we have available
-	 * and the lowest used RAM address
-	 */
+	/* Find the highest and lowest page frame numbers we have available. */
 	for (i = 0; i < boot_mem_map.nr_map; i++) {
 		unsigned long start, end;

@ -427,13 +428,6 @@ static void __init bootmem_init(void)
 			max_low_pfn = end;
 		if (start < min_low_pfn)
 			min_low_pfn = start;
-		if (end <= reserved_end)
-			continue;
-#ifdef CONFIG_BLK_DEV_INITRD
-		/* Skip zones before initrd and initrd itself */
-		if (initrd_end && end <= (unsigned long)PFN_UP(__pa(initrd_end)))
-			continue;
-#endif
 	}

 	if (min_low_pfn >= max_low_pfn)
@ -474,6 +468,7 @@ static void __init bootmem_init(void)
 		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 	}

+	/* Install all valid RAM ranges to the memblock memory region */
 	for (i = 0; i < boot_mem_map.nr_map; i++) {
 		unsigned long start, end;

@ -481,98 +476,38 @@ static void __init bootmem_init(void)
 		end = PFN_DOWN(boot_mem_map.map[i].addr
 				+ boot_mem_map.map[i].size);

-		if (start <= min_low_pfn)
+		if (start < min_low_pfn)
 			start = min_low_pfn;
-		if (start >= end)
-			continue;
-
 #ifndef CONFIG_HIGHMEM
+		/* Ignore highmem regions if highmem is unsupported */
 		if (end > max_low_pfn)
 			end = max_low_pfn;
-
-		/*
-		 * ... finally, is the area going away?
-		 */
+#endif
 		if (end <= start)
 			continue;
-#endif

 		memblock_add_node(PFN_PHYS(start), PFN_PHYS(end - start), 0);
-	}

-	/*
-	 * Register fully available low RAM pages with the bootmem allocator.
-	 */
-	for (i = 0; i < boot_mem_map.nr_map; i++) {
-		unsigned long start, end, size;
-
-		start = PFN_UP(boot_mem_map.map[i].addr);
-		end   = PFN_DOWN(boot_mem_map.map[i].addr
-				    + boot_mem_map.map[i].size);
-
-		/*
-		 * Reserve usable memory.
-		 */
+		/* Reserve any memory except the ordinary RAM ranges. */
 		switch (boot_mem_map.map[i].type) {
 		case BOOT_MEM_RAM:
 			break;
-		case BOOT_MEM_INIT_RAM:
-			memory_present(0, start, end);
-			continue;
-		default:
-			/* Not usable memory */
-			if (start > min_low_pfn && end < max_low_pfn)
-				memblock_reserve(boot_mem_map.map[i].addr,
-						boot_mem_map.map[i].size);
-
+		case BOOT_MEM_NOMAP: /* Discard the range from the system. */
+			memblock_remove(PFN_PHYS(start), PFN_PHYS(end - start));
 			continue;
+		default: /* Reserve the rest of the memory types at boot time */
+			memblock_reserve(PFN_PHYS(start), PFN_PHYS(end - start));
+			break;
 		}

 		/*
-		 * We are rounding up the start address of usable memory
-		 * and at the end of the usable range downwards.
+		 * In any case the added to the memblock memory regions
+		 * (highmem/lowmem, available/reserved, etc) are considered
+		 * as present, so inform sparsemem about them.
 		 */
-		if (start >= max_low_pfn)
-			continue;
-		if (start < reserved_end)
-			start = reserved_end;
-		if (end > max_low_pfn)
-			end = max_low_pfn;
-
-		/*
-		 * ... finally, is the area going away?
-		 */
-		if (end <= start)
-			continue;
-		size = end - start;
-
-		/* Register lowmem ranges */
 		memory_present(0, start, end);
 	}

-#ifdef CONFIG_RELOCATABLE
-	/*
-	 * The kernel reserves all memory below its _end symbol as bootmem,
-	 * but the kernel may now be at a much higher address. The memory
-	 * between the original and new locations may be returned to the system.
-	 */
-	if (__pa_symbol(_text) > __pa_symbol(VMLINUX_LOAD_ADDRESS)) {
-		unsigned long offset;
-		extern void show_kernel_relocation(const char *level);
-
-		offset = __pa_symbol(_text) - __pa_symbol(VMLINUX_LOAD_ADDRESS);
-		memblock_free(__pa_symbol(VMLINUX_LOAD_ADDRESS), offset);
-
-#if defined(CONFIG_DEBUG_KERNEL) && defined(CONFIG_DEBUG_INFO)
-		/*
-		 * This information is necessary when debugging the kernel
-		 * But is a security vulnerability otherwise!
-		 */
-		show_kernel_relocation(KERN_INFO);
-#endif
-	}
-#endif
-
 	/*
 	 * Reserve initrd memory if needed.
 	 */
@ -781,7 +716,6 @@ static void __init request_crashkernel(struct resource *res)
 */
 static void __init arch_mem_init(char **cmdline_p)
 {
-	struct memblock_region *reg;
 	extern void plat_mem_setup(void);

 	/*
@ -809,6 +743,9 @@ static void __init arch_mem_init(char **cmdline_p)
 	arch_mem_addpart(PFN_UP(__pa_symbol(&__init_begin)) << PAGE_SHIFT,
 			 PFN_DOWN(__pa_symbol(&__init_end)) << PAGE_SHIFT,
 			 BOOT_MEM_INIT_RAM);
+	arch_mem_addpart(PFN_DOWN(__pa_symbol(&__bss_start)) << PAGE_SHIFT,
+			 PFN_UP(__pa_symbol(&__bss_stop)) << PAGE_SHIFT,
+			 BOOT_MEM_RAM);

 	pr_info("Determined physical RAM map:\n");
 	print_memory_map();
@ -884,13 +821,16 @@ static void __init arch_mem_init(char **cmdline_p)
 	plat_swiotlb_setup();

 	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
-	/* Tell bootmem about cma reserved memblock section */
-	for_each_memblock(reserved, reg)
-		if (reg->size != 0)
-			memblock_reserve(reg->base, reg->size);

-	reserve_bootmem_region(__pa_symbol(&__nosave_begin),
-			__pa_symbol(&__nosave_end)); /* Reserve for hibernation */
+	/* Reserve for hibernation. */
+	memblock_reserve(__pa_symbol(&__nosave_begin),
+		__pa_symbol(&__nosave_end) - __pa_symbol(&__nosave_begin));
+
+	fdt_init_reserved_mem();
+
+	memblock_dump_all();
+
+	early_memtest(PFN_PHYS(min_low_pfn), PFN_PHYS(max_low_pfn));
 }

 static void __init resource_init(void)
@ -935,6 +875,7 @@ static void __init resource_init(void)
 			res->flags |= IORESOURCE_SYSRAM;
 			break;
 		case BOOT_MEM_RESERVED:
+		case BOOT_MEM_NOMAP:
 		default:
 			res->name = "reserved";
 		}
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@ -2151,7 +2151,7 @@ static void configure_hwrena(void)

 static void configure_exception_vector(void)
 {
-	if (cpu_has_veic || cpu_has_vint) {
+	if (cpu_has_mips_r2_r6) {
 		unsigned long sr = set_c0_status(ST0_BEV);
 		/* If available, use WG to set top bits of EBASE */
 		if (cpu_has_ebase_wg) {
@ -2163,6 +2163,8 @@ static void configure_exception_vector(void)
 		}
 		write_c0_ebase(ebase);
 		write_c0_status(sr);
+	}
+	if (cpu_has_veic || cpu_has_vint) {
 		/* Setting vector spacing enables EI/VI mode  */
 		change_c0_intctl(0x3e0, VECTORSPACING);
 	}
@ -2193,22 +2195,6 @@ void per_cpu_trap_init(bool is_boot_cpu)
 	 *  o read IntCtl.IPFDC to determine the fast debug channel interrupt
 	 */
 	if (cpu_has_mips_r2_r6) {
-		/*
-		 * We shouldn't trust a secondary core has a sane EBASE register
-		 * so use the one calculated by the boot CPU.
-		 */
-		if (!is_boot_cpu) {
-			/* If available, use WG to set top bits of EBASE */
-			if (cpu_has_ebase_wg) {
-#ifdef CONFIG_64BIT
-				write_c0_ebase_64(ebase | MIPS_EBASE_WG);
-#else
-				write_c0_ebase(ebase | MIPS_EBASE_WG);
-#endif
-			}
-			write_c0_ebase(ebase);
-		}
-
 		cp0_compare_irq_shift = CAUSEB_TI - CAUSEB_IP;
 		cp0_compare_irq = (read_c0_intctl() >> INTCTLB_IPTI) & 7;
 		cp0_perfcount_irq = (read_c0_intctl() >> INTCTLB_IPPCI) & 7;
@ -2284,19 +2270,27 @@ void __init trap_init(void)
 	extern char except_vec3_generic;
 	extern char except_vec4;
 	extern char except_vec3_r4000;
-	unsigned long i;
+	unsigned long i, vec_size;
+	phys_addr_t ebase_pa;

 	check_wait();

-	if (cpu_has_veic || cpu_has_vint) {
-		unsigned long size = 0x200 + VECTORSPACING*64;
-		phys_addr_t ebase_pa;
+	if (!cpu_has_mips_r2_r6) {
+		ebase = CAC_BASE;
+		ebase_pa = virt_to_phys((void *)ebase);
+		vec_size = 0x400;

-		ebase = (unsigned long)
-			memblock_alloc(size, 1 << fls(size));
-		if (!ebase)
+		memblock_reserve(ebase_pa, vec_size);
+	} else {
+		if (cpu_has_veic || cpu_has_vint)
+			vec_size = 0x200 + VECTORSPACING*64;
+		else
+			vec_size = PAGE_SIZE;
+
+		ebase_pa = memblock_phys_alloc(vec_size, 1 << fls(vec_size));
+		if (!ebase_pa)
 			panic("%s: Failed to allocate %lu bytes align=0x%x\n",
-			      __func__, size, 1 << fls(size));
+			      __func__, vec_size, 1 << fls(vec_size));

 		/*
 		 * Try to ensure ebase resides in KSeg0 if possible.
@ -2309,23 +2303,10 @@ void __init trap_init(void)
 		 * EVA is special though as it allows segments to be rearranged
 		 * and to become uncached during cache error handling.
 		 */
-		ebase_pa = __pa(ebase);
 		if (!IS_ENABLED(CONFIG_EVA) && !WARN_ON(ebase_pa >= 0x20000000))
 			ebase = CKSEG0ADDR(ebase_pa);
-	} else {
-		ebase = CAC_BASE;
-
-		if (cpu_has_mips_r2_r6) {
-			if (cpu_has_ebase_wg) {
-#ifdef CONFIG_64BIT
-				ebase = (read_c0_ebase_64() & ~0xfff);
-#else
-				ebase = (read_c0_ebase() & ~0xfff);
-#endif
-			} else {
-				ebase += (read_c0_ebase() & 0x3ffff000);
-			}
-		}
+		else
+			ebase = (unsigned long)phys_to_virt(ebase_pa);
 	}

 	if (cpu_has_mmips) {
@ -2459,7 +2440,7 @@ void __init trap_init(void)
 	else
 		set_handler(0x080, &except_vec3_generic, 0x80);

-	local_flush_icache_range(ebase, ebase + 0x400);
+	local_flush_icache_range(ebase, ebase + vec_size);

 	sort_extable(__start___dbe_table, __stop___dbe_table);

--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@ -1141,9 +1141,7 @@ enum emulation_result kvm_mips_emul_tlbwr(struct kvm_vcpu *vcpu)
 	unsigned long pc = vcpu->arch.pc;
 	int index;

-	get_random_bytes(&index, sizeof(index));
-	index &= (KVM_MIPS_GUEST_TLB_SIZE - 1);
-
+	index = prandom_u32_max(KVM_MIPS_GUEST_TLB_SIZE);
 	tlb = &vcpu->arch.guest_tlb[index];

 	kvm_mips_invalidate_guest_tlb(vcpu, tlb);
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@ -76,14 +76,22 @@ static const struct insn insn_table[insn_invalid] = {
 	[insn_daddiu]	= {M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM},
 	[insn_daddu]	= {M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD},
 	[insn_ddivu]	= {M(spec_op, 0, 0, 0, 0, ddivu_op), RS | RT},
+	[insn_ddivu_r6]	= {M(spec_op, 0, 0, 0, ddivu_ddivu6_op, ddivu_op),
+				RS | RT | RD},
 	[insn_di]	= {M(cop0_op, mfmc0_op, 0, 12, 0, 0), RT},
 	[insn_dins]	= {M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE},
 	[insn_dinsm]	= {M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE},
 	[insn_dinsu]	= {M(spec3_op, 0, 0, 0, 0, dinsu_op), RS | RT | RD | RE},
 	[insn_divu]	= {M(spec_op, 0, 0, 0, 0, divu_op), RS | RT},
+	[insn_divu_r6]	= {M(spec_op, 0, 0, 0, divu_divu6_op, divu_op),
+				RS | RT | RD},
 	[insn_dmfc0]	= {M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET},
+	[insn_dmodu]	= {M(spec_op, 0, 0, 0, ddivu_dmodu_op, ddivu_op),
+				RS | RT | RD},
 	[insn_dmtc0]	= {M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET},
 	[insn_dmultu]	= {M(spec_op, 0, 0, 0, 0, dmultu_op), RS | RT},
+	[insn_dmulu]	= {M(spec_op, 0, 0, 0, dmult_dmul_op, dmultu_op),
+				RS | RT | RD},
 	[insn_drotr]	= {M(spec_op, 1, 0, 0, 0, dsrl_op), RT | RD | RE},
 	[insn_drotr32]	= {M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE},
 	[insn_dsbh]	= {M(spec3_op, 0, 0, 0, dsbh_op, dbshfl_op), RT | RD},
@ -132,12 +140,16 @@ static const struct insn insn_table[insn_invalid] = {
 	[insn_mfhc0]	= {M(cop0_op, mfhc0_op, 0, 0, 0, 0),  RT | RD | SET},
 	[insn_mfhi]	= {M(spec_op, 0, 0, 0, 0, mfhi_op), RD},
 	[insn_mflo]	= {M(spec_op, 0, 0, 0, 0, mflo_op), RD},
+	[insn_modu]	= {M(spec_op, 0, 0, 0, divu_modu_op, divu_op),
+				RS | RT | RD},
 	[insn_movn]	= {M(spec_op, 0, 0, 0, 0, movn_op), RS | RT | RD},
 	[insn_movz]	= {M(spec_op, 0, 0, 0, 0, movz_op), RS | RT | RD},
 	[insn_mtc0]	= {M(cop0_op, mtc_op, 0, 0, 0, 0),  RT | RD | SET},
 	[insn_mthc0]	= {M(cop0_op, mthc0_op, 0, 0, 0, 0),  RT | RD | SET},
 	[insn_mthi]	= {M(spec_op, 0, 0, 0, 0, mthi_op), RS},
 	[insn_mtlo]	= {M(spec_op, 0, 0, 0, 0, mtlo_op), RS},
+	[insn_mulu]	= {M(spec_op, 0, 0, 0, multu_mulu_op, multu_op),
+				RS | RT | RD},
 #ifndef CONFIG_CPU_MIPSR6
 	[insn_mul]	= {M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD},
 #else
@ -163,6 +175,8 @@ static const struct insn insn_table[insn_invalid] = {
 	[insn_scd]	= {M6(spec3_op, 0, 0, 0, scd6_op),  RS | RT | SIMM9},
 #endif
 	[insn_sd]	= {M(sd_op, 0, 0, 0, 0, 0),  RS | RT | SIMM},
+	[insn_seleqz]	= {M(spec_op, 0, 0, 0, 0, seleqz_op), RS | RT | RD},
+	[insn_selnez]	= {M(spec_op, 0, 0, 0, 0, selnez_op), RS | RT | RD},
 	[insn_sh]	= {M(sh_op, 0, 0, 0, 0, 0),  RS | RT | SIMM},
 	[insn_sll]	= {M(spec_op, 0, 0, 0, 0, sll_op),  RT | RD | RE},
 	[insn_sllv]	= {M(spec_op, 0, 0, 0, 0, sllv_op),  RS | RT | RD},
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@ -50,21 +50,22 @@ enum opcode {
 	insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bgtz, insn_blez,
 	insn_bltz, insn_bltzl, insn_bne, insn_break, insn_cache, insn_cfc1,
 	insn_cfcmsa, insn_ctc1, insn_ctcmsa, insn_daddiu, insn_daddu, insn_ddivu,
-	insn_di, insn_dins, insn_dinsm, insn_dinsu, insn_divu, insn_dmfc0,
-	insn_dmtc0, insn_dmultu, insn_drotr, insn_drotr32, insn_dsbh, insn_dshd,
-	insn_dsll, insn_dsll32, insn_dsllv, insn_dsra, insn_dsra32, insn_dsrav,
-	insn_dsrl, insn_dsrl32, insn_dsrlv, insn_dsubu, insn_eret, insn_ext,
-	insn_ins, insn_j, insn_jal, insn_jalr, insn_jr, insn_lb, insn_lbu,
-	insn_ld, insn_lddir, insn_ldpte, insn_ldx, insn_lh, insn_lhu,
-	insn_ll, insn_lld, insn_lui, insn_lw, insn_lwu, insn_lwx, insn_mfc0,
-	insn_mfhc0, insn_mfhi, insn_mflo, insn_movn, insn_movz, insn_mtc0,
-	insn_mthc0, insn_mthi, insn_mtlo, insn_mul, insn_multu, insn_nor,
-	insn_or, insn_ori, insn_pref, insn_rfe, insn_rotr, insn_sb,
-	insn_sc, insn_scd, insn_sd, insn_sh, insn_sll, insn_sllv,
-	insn_slt, insn_slti, insn_sltiu, insn_sltu, insn_sra, insn_srav,
-	insn_srl, insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall,
-	insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh,
-	insn_xor, insn_xori, insn_yield,
+	insn_ddivu_r6, insn_di, insn_dins, insn_dinsm, insn_dinsu, insn_divu,
+	insn_divu_r6, insn_dmfc0, insn_dmodu, insn_dmtc0, insn_dmultu,
+	insn_dmulu, insn_drotr, insn_drotr32, insn_dsbh, insn_dshd, insn_dsll,
+	insn_dsll32, insn_dsllv, insn_dsra, insn_dsra32, insn_dsrav, insn_dsrl,
+	insn_dsrl32, insn_dsrlv, insn_dsubu, insn_eret, insn_ext, insn_ins,
+	insn_j, insn_jal, insn_jalr, insn_jr, insn_lb, insn_lbu, insn_ld,
+	insn_lddir, insn_ldpte, insn_ldx, insn_lh, insn_lhu, insn_ll, insn_lld,
+	insn_lui, insn_lw, insn_lwu, insn_lwx, insn_mfc0, insn_mfhc0, insn_mfhi,
+	insn_mflo, insn_modu, insn_movn, insn_movz, insn_mtc0, insn_mthc0,
+	insn_mthi, insn_mtlo, insn_mul, insn_multu, insn_mulu, insn_nor,
+	insn_or, insn_ori, insn_pref, insn_rfe, insn_rotr, insn_sb, insn_sc,
+	insn_scd, insn_seleqz, insn_selnez, insn_sd, insn_sh, insn_sll,
+	insn_sllv, insn_slt, insn_slti, insn_sltiu, insn_sltu, insn_sra,
+	insn_srav, insn_srl, insn_srlv, insn_subu, insn_sw, insn_sync,
+	insn_syscall, insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait,
+	insn_wsbh, insn_xor, insn_xori, insn_yield,
 	insn_invalid /* insn_invalid must be last */
 };

@ -287,13 +288,17 @@ I_u2u1(_cfcmsa)
 I_u1u2(_ctc1)
 I_u2u1(_ctcmsa)
 I_u1u2(_ddivu)
+I_u3u1u2(_ddivu_r6)
 I_u1u2u3(_dmfc0)
+I_u3u1u2(_dmodu)
 I_u1u2u3(_dmtc0)
 I_u1u2(_dmultu)
+I_u3u1u2(_dmulu)
 I_u2u1s3(_daddiu)
 I_u3u1u2(_daddu)
 I_u1(_di);
 I_u1u2(_divu)
+I_u3u1u2(_divu_r6)
 I_u2u1(_dsbh);
 I_u2u1(_dshd);
 I_u2u1u3(_dsll)
@ -327,6 +332,7 @@ I_u2s3u1(_lw)
 I_u2s3u1(_lwu)
 I_u1u2u3(_mfc0)
 I_u1u2u3(_mfhc0)
+I_u3u1u2(_modu)
 I_u3u1u2(_movn)
 I_u3u1u2(_movz)
 I_u1(_mfhi)
@ -337,6 +343,7 @@ I_u1(_mthi)
 I_u1(_mtlo)
 I_u3u1u2(_mul)
 I_u1u2(_multu)
+I_u3u1u2(_mulu)
 I_u3u1u2(_nor)
 I_u3u1u2(_or)
 I_u2u1u3(_ori)
@ -345,6 +352,8 @@ I_u2s3u1(_sb)
 I_u2s3u1(_sc)
 I_u2s3u1(_scd)
 I_u2s3u1(_sd)
+I_u3u1u2(_seleqz)
+I_u3u1u2(_selnez)
 I_u2s3u1(_sh)
 I_u2u1u3(_sll)
 I_u3u2u1(_sllv)
--- a/arch/mips/net/Makefile
+++ b/arch/mips/net/Makefile
@ -1,4 +1,3 @@
 # MIPS networking code

-obj-$(CONFIG_MIPS_CBPF_JIT) += bpf_jit.o bpf_jit_asm.o
 obj-$(CONFIG_MIPS_EBPF_JIT) += ebpf_jit.o
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
--- a/arch/mips/net/bpf_jit_asm.S
+++ b/arch/mips/net/bpf_jit_asm.S
@ -1,285 +0,0 @@
-/*
- * bpf_jib_asm.S: Packet/header access helper functions for MIPS/MIPS64 BPF
- * compiler.
- *
- * Copyright (C) 2015 Imagination Technologies Ltd.
- * Author: Markos Chandras <markos.chandras@imgtec.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; version 2 of the License.
- */
-
-#include <asm/asm.h>
-#include <asm/isa-rev.h>
-#include <asm/regdef.h>
-#include "bpf_jit.h"
-
-/* ABI
- *
- * r_skb_hl	skb header length
- * r_skb_data	skb data
- * r_off(a1)	offset register
- * r_A		BPF register A
- * r_X		PF register X
- * r_skb(a0)	*skb
- * r_M		*scratch memory
- * r_skb_le	skb length
- * r_s0		Scratch register 0
- * r_s1		Scratch register 1
- *
- * On entry:
- * a0: *skb
- * a1: offset (imm or imm + X)
- *
- * All non-BPF-ABI registers are free for use. On return, we only
- * care about r_ret. The BPF-ABI registers are assumed to remain
- * unmodified during the entire filter operation.
- */
-
-#define skb	a0
-#define offset	a1
-#define SKF_LL_OFF  (-0x200000) /* Can't include linux/filter.h in assembly */
-
-	/* We know better :) so prevent assembler reordering etc */
-	.set 	noreorder
-
-#define is_offset_negative(TYPE)				\
-	/* If offset is negative we have more work to do */	\
-	slti	t0, offset, 0;					\
-	bgtz	t0, bpf_slow_path_##TYPE##_neg;			\
-	/* Be careful what follows in DS. */
-
-#define is_offset_in_header(SIZE, TYPE)				\
-	/* Reading from header? */				\
-	addiu	$r_s0, $r_skb_hl, -SIZE;			\
-	slt	t0, $r_s0, offset;				\
-	bgtz	t0, bpf_slow_path_##TYPE;			\
-
-LEAF(sk_load_word)
-	is_offset_negative(word)
-FEXPORT(sk_load_word_positive)
-	is_offset_in_header(4, word)
-	/* Offset within header boundaries */
-	PTR_ADDU t1, $r_skb_data, offset
-	.set	reorder
-	lw	$r_A, 0(t1)
-	.set	noreorder
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-# if MIPS_ISA_REV >= 2
-	wsbh	t0, $r_A
-	rotr	$r_A, t0, 16
-# else
-	sll	t0, $r_A, 24
-	srl	t1, $r_A, 24
-	srl	t2, $r_A, 8
-	or	t0, t0, t1
-	andi	t2, t2, 0xff00
-	andi	t1, $r_A, 0xff00
-	or	t0, t0, t2
-	sll	t1, t1, 8
-	or	$r_A, t0, t1
-# endif
-#endif
-	jr	$r_ra
-	 move	$r_ret, zero
-	END(sk_load_word)
-
-LEAF(sk_load_half)
-	is_offset_negative(half)
-FEXPORT(sk_load_half_positive)
-	is_offset_in_header(2, half)
-	/* Offset within header boundaries */
-	PTR_ADDU t1, $r_skb_data, offset
-	lhu	$r_A, 0(t1)
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-# if MIPS_ISA_REV >= 2
-	wsbh	$r_A, $r_A
-# else
-	sll	t0, $r_A, 8
-	srl	t1, $r_A, 8
-	andi	t0, t0, 0xff00
-	or	$r_A, t0, t1
-# endif
-#endif
-	jr	$r_ra
-	 move	$r_ret, zero
-	END(sk_load_half)
-
-LEAF(sk_load_byte)
-	is_offset_negative(byte)
-FEXPORT(sk_load_byte_positive)
-	is_offset_in_header(1, byte)
-	/* Offset within header boundaries */
-	PTR_ADDU t1, $r_skb_data, offset
-	lbu	$r_A, 0(t1)
-	jr	$r_ra
-	 move	$r_ret, zero
-	END(sk_load_byte)
-
-/*
- * call skb_copy_bits:
- * (prototype in linux/skbuff.h)
- *
- * int skb_copy_bits(sk_buff *skb, int offset, void *to, int len)
- *
- * o32 mandates we leave 4 spaces for argument registers in case
- * the callee needs to use them. Even though we don't care about
- * the argument registers ourselves, we need to allocate that space
- * to remain ABI compliant since the callee may want to use that space.
- * We also allocate 2 more spaces for $r_ra and our return register (*to).
- *
- * n64 is a bit different. The *caller* will allocate the space to preserve
- * the arguments. So in 64-bit kernels, we allocate the 4-arg space for no
- * good reason but it does not matter that much really.
- *
- * (void *to) is returned in r_s0
- *
- */
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-#define DS_OFFSET(SIZE) (4 * SZREG)
-#else
-#define DS_OFFSET(SIZE) ((4 * SZREG) + (4 - SIZE))
-#endif
-#define bpf_slow_path_common(SIZE)				\
-	/* Quick check. Are we within reasonable boundaries? */ \
-	LONG_ADDIU	$r_s1, $r_skb_len, -SIZE;		\
-	sltu		$r_s0, offset, $r_s1;			\
-	beqz		$r_s0, fault;				\
-	/* Load 4th argument in DS */				\
-	 LONG_ADDIU	a3, zero, SIZE;				\
-	PTR_ADDIU	$r_sp, $r_sp, -(6 * SZREG);		\
-	PTR_LA		t0, skb_copy_bits;			\
-	PTR_S		$r_ra, (5 * SZREG)($r_sp);		\
-	/* Assign low slot to a2 */				\
-	PTR_ADDIU	a2, $r_sp, DS_OFFSET(SIZE);		\
-	jalr		t0;					\
-	/* Reset our destination slot (DS but it's ok) */	\
-	 INT_S		zero, (4 * SZREG)($r_sp);		\
-	/*							\
-	 * skb_copy_bits returns 0 on success and -EFAULT	\
-	 * on error. Our data live in a2. Do not bother with	\
-	 * our data if an error has been returned.		\
-	 */							\
-	/* Restore our frame */					\
-	PTR_L		$r_ra, (5 * SZREG)($r_sp);		\
-	INT_L		$r_s0, (4 * SZREG)($r_sp);		\
-	bltz		v0, fault;				\
-	 PTR_ADDIU	$r_sp, $r_sp, 6 * SZREG;		\
-	move		$r_ret, zero;				\
-
-NESTED(bpf_slow_path_word, (6 * SZREG), $r_sp)
-	bpf_slow_path_common(4)
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-# if MIPS_ISA_REV >= 2
-	wsbh	t0, $r_s0
-	jr	$r_ra
-	 rotr	$r_A, t0, 16
-# else
-	sll	t0, $r_s0, 24
-	srl	t1, $r_s0, 24
-	srl	t2, $r_s0, 8
-	or	t0, t0, t1
-	andi	t2, t2, 0xff00
-	andi	t1, $r_s0, 0xff00
-	or	t0, t0, t2
-	sll	t1, t1, 8
-	jr	$r_ra
-	 or	$r_A, t0, t1
-# endif
-#else
-	jr	$r_ra
-	 move	$r_A, $r_s0
-#endif
-
-	END(bpf_slow_path_word)
-
-NESTED(bpf_slow_path_half, (6 * SZREG), $r_sp)
-	bpf_slow_path_common(2)
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-# if MIPS_ISA_REV >= 2
-	jr	$r_ra
-	 wsbh	$r_A, $r_s0
-# else
-	sll	t0, $r_s0, 8
-	andi	t1, $r_s0, 0xff00
-	andi	t0, t0, 0xff00
-	srl	t1, t1, 8
-	jr	$r_ra
-	 or	$r_A, t0, t1
-# endif
-#else
-	jr	$r_ra
-	 move	$r_A, $r_s0
-#endif
-
-	END(bpf_slow_path_half)
-
-NESTED(bpf_slow_path_byte, (6 * SZREG), $r_sp)
-	bpf_slow_path_common(1)
-	jr	$r_ra
-	 move	$r_A, $r_s0
-
-	END(bpf_slow_path_byte)
-
-/*
- * Negative entry points
- */
-	.macro bpf_is_end_of_data
-	li	t0, SKF_LL_OFF
-	/* Reading link layer data? */
-	slt	t1, offset, t0
-	bgtz	t1, fault
-	/* Be careful what follows in DS. */
-	.endm
-/*
- * call skb_copy_bits:
- * (prototype in linux/filter.h)
- *
- * void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb,
- *                                            int k, unsigned int size)
- *
- * see above (bpf_slow_path_common) for ABI restrictions
- */
-#define bpf_negative_common(SIZE)					\
-	PTR_ADDIU	$r_sp, $r_sp, -(6 * SZREG);			\
-	PTR_LA		t0, bpf_internal_load_pointer_neg_helper;	\
-	PTR_S		$r_ra, (5 * SZREG)($r_sp);			\
-	jalr		t0;						\
-	 li		a2, SIZE;					\
-	PTR_L		$r_ra, (5 * SZREG)($r_sp);			\
-	/* Check return pointer */					\
-	beqz		v0, fault;					\
-	 PTR_ADDIU	$r_sp, $r_sp, 6 * SZREG;			\
-	/* Preserve our pointer */					\
-	move		$r_s0, v0;					\
-	/* Set return value */						\
-	move		$r_ret, zero;					\
-
-bpf_slow_path_word_neg:
-	bpf_is_end_of_data
-NESTED(sk_load_word_negative, (6 * SZREG), $r_sp)
-	bpf_negative_common(4)
-	jr	$r_ra
-	 lw	$r_A, 0($r_s0)
-	END(sk_load_word_negative)
-
-bpf_slow_path_half_neg:
-	bpf_is_end_of_data
-NESTED(sk_load_half_negative, (6 * SZREG), $r_sp)
-	bpf_negative_common(2)
-	jr	$r_ra
-	 lhu	$r_A, 0($r_s0)
-	END(sk_load_half_negative)
-
-bpf_slow_path_byte_neg:
-	bpf_is_end_of_data
-NESTED(sk_load_byte_negative, (6 * SZREG), $r_sp)
-	bpf_negative_common(1)
-	jr	$r_ra
-	 lbu	$r_A, 0($r_s0)
-	END(sk_load_byte_negative)
-
-fault:
-	jr	$r_ra
-	 addiu $r_ret, zero, 1
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@ -22,6 +22,7 @@
 #include <asm/byteorder.h>
 #include <asm/cacheflush.h>
 #include <asm/cpu-features.h>
+#include <asm/isa-rev.h>
 #include <asm/uasm.h>

 /* Registers used by JIT */
@ -125,15 +126,21 @@ static enum reg_val_type get_reg_val_type(const struct jit_ctx *ctx,
 }

 /* Simply emit the instruction if the JIT memory space has been allocated */
-#define emit_instr(ctx, func, ...)			\
+#define emit_instr_long(ctx, func64, func32, ...)		\
 do {								\
 	if ((ctx)->target != NULL) {				\
 		u32 *p = &(ctx)->target[ctx->idx];		\
-		uasm_i_##func(&p, ##__VA_ARGS__);	\
+		if (IS_ENABLED(CONFIG_64BIT))			\
+			uasm_i_##func64(&p, ##__VA_ARGS__);	\
+		else						\
+			uasm_i_##func32(&p, ##__VA_ARGS__);	\
 	}							\
 	(ctx)->idx++;						\
 } while (0)

+#define emit_instr(ctx, func, ...)				\
+	emit_instr_long(ctx, func, func, ##__VA_ARGS__)
+
 static unsigned int j_target(struct jit_ctx *ctx, int target_idx)
 {
 	unsigned long target_va, base_va;
@ -274,17 +281,17 @@ static int gen_int_prologue(struct jit_ctx *ctx)
 		 * If RA we are doing a function call and may need
 		 * extra 8-byte tmp area.
 		 */
-		stack_adjust += 16;
+		stack_adjust += 2 * sizeof(long);
 	if (ctx->flags & EBPF_SAVE_S0)
-		stack_adjust += 8;
+		stack_adjust += sizeof(long);
 	if (ctx->flags & EBPF_SAVE_S1)
-		stack_adjust += 8;
+		stack_adjust += sizeof(long);
 	if (ctx->flags & EBPF_SAVE_S2)
-		stack_adjust += 8;
+		stack_adjust += sizeof(long);
 	if (ctx->flags & EBPF_SAVE_S3)
-		stack_adjust += 8;
+		stack_adjust += sizeof(long);
 	if (ctx->flags & EBPF_SAVE_S4)
-		stack_adjust += 8;
+		stack_adjust += sizeof(long);

 	BUILD_BUG_ON(MAX_BPF_STACK & 7);
 	locals_size = (ctx->flags & EBPF_SEEN_FP) ? MAX_BPF_STACK : 0;
@ -298,41 +305,49 @@ static int gen_int_prologue(struct jit_ctx *ctx)
 	 * On tail call we skip this instruction, and the TCC is
 	 * passed in $v1 from the caller.
 	 */
-	emit_instr(ctx, daddiu, MIPS_R_V1, MIPS_R_ZERO, MAX_TAIL_CALL_CNT);
+	emit_instr(ctx, addiu, MIPS_R_V1, MIPS_R_ZERO, MAX_TAIL_CALL_CNT);
 	if (stack_adjust)
-		emit_instr(ctx, daddiu, MIPS_R_SP, MIPS_R_SP, -stack_adjust);
+		emit_instr_long(ctx, daddiu, addiu,
+					MIPS_R_SP, MIPS_R_SP, -stack_adjust);
 	else
 		return 0;

-	store_offset = stack_adjust - 8;
+	store_offset = stack_adjust - sizeof(long);

 	if (ctx->flags & EBPF_SAVE_RA) {
-		emit_instr(ctx, sd, MIPS_R_RA, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, sd, sw,
+					MIPS_R_RA, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S0) {
-		emit_instr(ctx, sd, MIPS_R_S0, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, sd, sw,
+					MIPS_R_S0, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S1) {
-		emit_instr(ctx, sd, MIPS_R_S1, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, sd, sw,
+					MIPS_R_S1, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S2) {
-		emit_instr(ctx, sd, MIPS_R_S2, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, sd, sw,
+					MIPS_R_S2, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S3) {
-		emit_instr(ctx, sd, MIPS_R_S3, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, sd, sw,
+					MIPS_R_S3, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S4) {
-		emit_instr(ctx, sd, MIPS_R_S4, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, sd, sw,
+					MIPS_R_S4, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}

 	if ((ctx->flags & EBPF_SEEN_TC) && !(ctx->flags & EBPF_TCC_IN_V1))
-		emit_instr(ctx, daddu, MIPS_R_S4, MIPS_R_V1, MIPS_R_ZERO);
+		emit_instr_long(ctx, daddu, addu,
+					MIPS_R_S4, MIPS_R_V1, MIPS_R_ZERO);

 	return 0;
 }
@ -341,7 +356,7 @@ static int build_int_epilogue(struct jit_ctx *ctx, int dest_reg)
 {
 	const struct bpf_prog *prog = ctx->skf;
 	int stack_adjust = ctx->stack_size;
-	int store_offset = stack_adjust - 8;
+	int store_offset = stack_adjust - sizeof(long);
 	enum reg_val_type td;
 	int r0 = MIPS_R_V0;

@ -353,33 +368,40 @@ static int build_int_epilogue(struct jit_ctx *ctx, int dest_reg)
 	}

 	if (ctx->flags & EBPF_SAVE_RA) {
-		emit_instr(ctx, ld, MIPS_R_RA, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, ld, lw,
+					MIPS_R_RA, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S0) {
-		emit_instr(ctx, ld, MIPS_R_S0, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, ld, lw,
+					MIPS_R_S0, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S1) {
-		emit_instr(ctx, ld, MIPS_R_S1, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, ld, lw,
+					MIPS_R_S1, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S2) {
-		emit_instr(ctx, ld, MIPS_R_S2, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, ld, lw,
+				MIPS_R_S2, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S3) {
-		emit_instr(ctx, ld, MIPS_R_S3, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, ld, lw,
+					MIPS_R_S3, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	if (ctx->flags & EBPF_SAVE_S4) {
-		emit_instr(ctx, ld, MIPS_R_S4, store_offset, MIPS_R_SP);
-		store_offset -= 8;
+		emit_instr_long(ctx, ld, lw,
+					MIPS_R_S4, store_offset, MIPS_R_SP);
+		store_offset -= sizeof(long);
 	}
 	emit_instr(ctx, jr, dest_reg);

 	if (stack_adjust)
-		emit_instr(ctx, daddiu, MIPS_R_SP, MIPS_R_SP, stack_adjust);
+		emit_instr_long(ctx, daddiu, addiu,
+					MIPS_R_SP, MIPS_R_SP, stack_adjust);
 	else
 		emit_instr(ctx, nop);

@ -646,6 +668,10 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	s64 t64s;
 	int bpf_op = BPF_OP(insn->code);

+	if (IS_ENABLED(CONFIG_32BIT) && ((BPF_CLASS(insn->code) == BPF_ALU64)
+						|| (bpf_op == BPF_DW)))
+		return -EINVAL;
+
 	switch (insn->code) {
 	case BPF_ALU64 | BPF_ADD | BPF_K: /* ALU64_IMM */
 	case BPF_ALU64 | BPF_SUB | BPF_K: /* ALU64_IMM */
@ -678,8 +704,12 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		if (insn->imm == 1) /* Mult by 1 is a nop */
 			break;
 		gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+		if (MIPS_ISA_REV >= 6) {
+			emit_instr(ctx, dmulu, dst, dst, MIPS_R_AT);
+		} else {
 			emit_instr(ctx, dmultu, MIPS_R_AT, dst);
 			emit_instr(ctx, mflo, dst);
+		}
 		break;
 	case BPF_ALU64 | BPF_NEG | BPF_K: /* ALU64_IMM */
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
@ -701,8 +731,12 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		if (insn->imm == 1) /* Mult by 1 is a nop */
 			break;
 		gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+		if (MIPS_ISA_REV >= 6) {
+			emit_instr(ctx, mulu, dst, dst, MIPS_R_AT);
+		} else {
 			emit_instr(ctx, multu, dst, MIPS_R_AT);
 			emit_instr(ctx, mflo, dst);
+		}
 		break;
 	case BPF_ALU | BPF_NEG | BPF_K: /* ALU_IMM */
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
@ -733,6 +767,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		}
 		gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+		if (MIPS_ISA_REV >= 6) {
+			if (bpf_op == BPF_DIV)
+				emit_instr(ctx, divu_r6, dst, dst, MIPS_R_AT);
+			else
+				emit_instr(ctx, modu, dst, dst, MIPS_R_AT);
+			break;
+		}
 		emit_instr(ctx, divu, dst, MIPS_R_AT);
 		if (bpf_op == BPF_DIV)
 			emit_instr(ctx, mflo, dst);
@ -755,6 +796,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		}
 		gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+		if (MIPS_ISA_REV >= 6) {
+			if (bpf_op == BPF_DIV)
+				emit_instr(ctx, ddivu_r6, dst, dst, MIPS_R_AT);
+			else
+				emit_instr(ctx, modu, dst, dst, MIPS_R_AT);
+			break;
+		}
 		emit_instr(ctx, ddivu, dst, MIPS_R_AT);
 		if (bpf_op == BPF_DIV)
 			emit_instr(ctx, mflo, dst);
@ -820,11 +868,23 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			emit_instr(ctx, and, dst, dst, src);
 			break;
 		case BPF_MUL:
+			if (MIPS_ISA_REV >= 6) {
+				emit_instr(ctx, dmulu, dst, dst, src);
+			} else {
 				emit_instr(ctx, dmultu, dst, src);
 				emit_instr(ctx, mflo, dst);
+			}
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
+			if (MIPS_ISA_REV >= 6) {
+				if (bpf_op == BPF_DIV)
+					emit_instr(ctx, ddivu_r6,
+							dst, dst, src);
+				else
+					emit_instr(ctx, modu, dst, dst, src);
+				break;
+			}
 			emit_instr(ctx, ddivu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);
@ -904,6 +964,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
+			if (MIPS_ISA_REV >= 6) {
+				if (bpf_op == BPF_DIV)
+					emit_instr(ctx, divu_r6, dst, dst, src);
+				else
+					emit_instr(ctx, modu, dst, dst, src);
+				break;
+			}
 			emit_instr(ctx, divu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);
@ -1007,8 +1074,15 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			emit_instr(ctx, dsubu, MIPS_R_T8, dst, src);
 			emit_instr(ctx, sltu, MIPS_R_AT, dst, src);
 			/* SP known to be non-zero, movz becomes boolean not */
-			emit_instr(ctx, movz, MIPS_R_T9, MIPS_R_SP, MIPS_R_T8);
-			emit_instr(ctx, movn, MIPS_R_T9, MIPS_R_ZERO, MIPS_R_T8);
+			if (MIPS_ISA_REV >= 6) {
+				emit_instr(ctx, seleqz, MIPS_R_T9,
+						MIPS_R_SP, MIPS_R_T8);
+			} else {
+				emit_instr(ctx, movz, MIPS_R_T9,
+						MIPS_R_SP, MIPS_R_T8);
+				emit_instr(ctx, movn, MIPS_R_T9,
+						MIPS_R_ZERO, MIPS_R_T8);
+			}
 			emit_instr(ctx, or, MIPS_R_AT, MIPS_R_T9, MIPS_R_AT);
 			cmp_eq = bpf_op == BPF_JGT;
 			dst = MIPS_R_AT;
@ -1235,7 +1309,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,

 	case BPF_JMP | BPF_CALL:
 		ctx->flags |= EBPF_SAVE_RA;
-		t64s = (s64)insn->imm + (s64)__bpf_call_base;
+		t64s = (s64)insn->imm + (long)__bpf_call_base;
 		emit_const_to_reg(ctx, MIPS_R_T9, (u64)t64s);
 		emit_instr(ctx, jalr, MIPS_R_RA, MIPS_R_T9);
 		/* delay slot */
@ -1367,6 +1441,17 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		if (src < 0)
 			return src;
 		if (BPF_MODE(insn->code) == BPF_XADD) {
+			/*
+			 * If mem_off does not fit within the 9 bit ll/sc
+			 * instruction immediate field, use a temp reg.
+			 */
+			if (MIPS_ISA_REV >= 6 &&
+			    (mem_off >= BIT(8) || mem_off < -BIT(8))) {
+				emit_instr(ctx, daddiu, MIPS_R_T6,
+						dst, mem_off);
+				mem_off = 0;
+				dst = MIPS_R_T6;
+			}
 			switch (BPF_SIZE(insn->code)) {
 			case BPF_W:
 				if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) {
@ -1721,7 +1806,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	unsigned int image_size;
 	u8 *image_ptr;

-	if (!prog->jit_requested || !cpu_has_mips64r2)
+	if (!prog->jit_requested || MIPS_ISA_REV < 2)
 		return prog;

 	tmp = bpf_jit_blind_constants(prog);
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@ -46,9 +46,7 @@ endif
 VDSO_LDFLAGS := \
 	-Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \
 	$(addprefix -Wl$(comma),$(filter -E%,$(KBUILD_CFLAGS))) \
-	-nostdlib -shared \
-	$(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
-	$(call cc-ldoption, -Wl$(comma)--build-id)
+	-nostdlib -shared -Wl,--hash-style=sysv -Wl,--build-id

 GCOV_PROFILE := n
 UBSAN_SANITIZE := n