Merge branch 'open_state'

Documentation/fb/efifb.txt

@@ -27,5 +27,11 @@ You have to add the following kernel parameters in your elilo.conf:
 	Macbook Pro 17", iMac 20" :
 		video=efifb:i20
 
+Accepted options:
+
+nowc	Don't map the framebuffer write combined. This can be used
+	to workaround side-effects and slowdowns on other CPU cores
+	when large amounts of console data are written.
+
 --
 Edgar Hucek <gimli@dark-green.com>

Documentation/gpio/gpio-legacy.txt

@@ -459,7 +459,7 @@ pin controller?
 
 This is done by registering "ranges" of pins, which are essentially
 cross-reference tables. These are described in
-Documentation/pinctrl.txt
+Documentation/driver-api/pinctl.rst
 
 While the pin allocation is totally managed by the pinctrl subsystem,
 gpio (under gpiolib) is still maintained by gpio drivers. It may happen

MAINTAINERS

@@ -1161,7 +1161,7 @@ M:	Brendan Higgins <brendanhiggins@google.com>
 R:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
 R:	Joel Stanley <joel@jms.id.au>
 L:	linux-i2c@vger.kernel.org
-L:	openbmc@lists.ozlabs.org
+L:	openbmc@lists.ozlabs.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/irqchip/irq-aspeed-i2c-ic.c
 F:	drivers/i2c/busses/i2c-aspeed.c
@@ -5834,7 +5834,7 @@ F:	drivers/staging/greybus/spi.c
 F:	drivers/staging/greybus/spilib.c
 F:	drivers/staging/greybus/spilib.h
 
-GREYBUS LOOBACK/TIME PROTOCOLS DRIVERS
+GREYBUS LOOPBACK/TIME PROTOCOLS DRIVERS
 M:	Bryan O'Donoghue <pure.logic@nexus-software.ie>
 S:	Maintained
 F:	drivers/staging/greybus/loopback.c
@@ -10383,7 +10383,7 @@ L:	linux-gpio@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git
 S:	Maintained
 F:	Documentation/devicetree/bindings/pinctrl/
-F:	Documentation/pinctrl.txt
+F:	Documentation/driver-api/pinctl.rst
 F:	drivers/pinctrl/
 F:	include/linux/pinctrl/
 
@@ -14004,6 +14004,7 @@ F:	drivers/block/virtio_blk.c
 F:	include/linux/virtio*.h
 F:	include/uapi/linux/virtio_*.h
 F:	drivers/crypto/virtio/
+F:	mm/balloon_compaction.c
 
 VIRTIO CRYPTO DRIVER
 M:	Gonglei <arei.gonglei@huawei.com>

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 13
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*

arch/arm/include/asm/tlb.h

@@ -148,7 +148,8 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->fullmm = !(start | (end+1));
@@ -166,8 +167,14 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
 }
 
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+			unsigned long start, unsigned long end, bool force)
 {
+	if (force) {
+		tlb->range_start = start;
+		tlb->range_end = end;
+	}
+
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */

arch/ia64/include/asm/tlb.h

@@ -168,7 +168,8 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->max = ARRAY_SIZE(tlb->local);
@@ -185,8 +186,11 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
  * collected.
  */
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+			unsigned long start, unsigned long end, bool force)
 {
+	if (force)
+		tlb->need_flush = 1;
 	/*
 	 * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
 	 * tlb->end_addr.

arch/mips/Kconfig

@@ -2260,7 +2260,7 @@ config CPU_R4K_CACHE_TLB
 
 config MIPS_MT_SMP
 	bool "MIPS MT SMP support (1 TC on each available VPE)"
-	depends on SYS_SUPPORTS_MULTITHREADING && !CPU_MIPSR6
+	depends on SYS_SUPPORTS_MULTITHREADING && !CPU_MIPSR6 && !CPU_MICROMIPS
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select SYNC_R4K

arch/mips/Makefile

@@ -243,8 +243,21 @@ include arch/mips/Kbuild.platforms
 ifdef CONFIG_PHYSICAL_START
 load-y					= $(CONFIG_PHYSICAL_START)
 endif
-entry-y				= 0x$(shell $(NM) vmlinux 2>/dev/null \
+
+entry-noisa-y				= 0x$(shell $(NM) vmlinux 2>/dev/null \
 					| grep "\bkernel_entry\b" | cut -f1 -d \ )
+ifdef CONFIG_CPU_MICROMIPS
+  #
+  # Set the ISA bit, since the kernel_entry symbol in the ELF will have it
+  # clear which would lead to images containing addresses which bootloaders may
+  # jump to as MIPS32 code.
+  #
+  entry-y = $(patsubst %0,%1,$(patsubst %2,%3,$(patsubst %4,%5, \
+              $(patsubst %6,%7,$(patsubst %8,%9,$(patsubst %a,%b, \
+              $(patsubst %c,%d,$(patsubst %e,%f,$(entry-noisa-y)))))))))
+else
+  entry-y = $(entry-noisa-y)
+endif
 
 cflags-y			+= -I$(srctree)/arch/mips/include/asm/mach-generic
 drivers-$(CONFIG_PCI)		+= arch/mips/pci/

arch/mips/boot/compressed/.gitignore

@@ -0,0 +1,2 @@
+ashldi3.c
+bswapsi.c

arch/mips/cavium-octeon/octeon-usb.c

@@ -13,9 +13,9 @@
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/of_platform.h>
+#include <linux/io.h>
 
 #include <asm/octeon/octeon.h>
-#include <asm/octeon/cvmx-gpio-defs.h>
 
 /* USB Control Register */
 union cvm_usbdrd_uctl_ctl {

arch/mips/dec/int-handler.S

@@ -147,23 +147,12 @@
 		 * Find irq with highest priority
 		 */
 		# open coded PTR_LA t1, cpu_mask_nr_tbl
-#if (_MIPS_SZPTR == 32)
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		# open coded la t1, cpu_mask_nr_tbl
 		lui	t1, %hi(cpu_mask_nr_tbl)
 		addiu	t1, %lo(cpu_mask_nr_tbl)
-
-#endif
-#if (_MIPS_SZPTR == 64)
-		# open coded dla t1, cpu_mask_nr_tbl
-		.set	push
-		.set	noat
-		lui	t1, %highest(cpu_mask_nr_tbl)
-		lui	AT, %hi(cpu_mask_nr_tbl)
-		daddiu	t1, t1, %higher(cpu_mask_nr_tbl)
-		daddiu	AT, AT, %lo(cpu_mask_nr_tbl)
-		dsll	t1, 32
-		daddu	t1, t1, AT
-		.set	pop
+#else
+#error GCC `-msym32' option required for 64-bit DECstation builds
 #endif
 1:		lw	t2,(t1)
 		nop
@@ -214,23 +203,12 @@
 		 * Find irq with highest priority
 		 */
 		# open coded PTR_LA t1,asic_mask_nr_tbl
-#if (_MIPS_SZPTR == 32)
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		# open coded la t1, asic_mask_nr_tbl
 		lui	t1, %hi(asic_mask_nr_tbl)
 		addiu	t1, %lo(asic_mask_nr_tbl)
-
-#endif
-#if (_MIPS_SZPTR == 64)
-		# open coded dla t1, asic_mask_nr_tbl
-		.set	push
-		.set	noat
-		lui	t1, %highest(asic_mask_nr_tbl)
-		lui	AT, %hi(asic_mask_nr_tbl)
-		daddiu	t1, t1, %higher(asic_mask_nr_tbl)
-		daddiu	AT, AT, %lo(asic_mask_nr_tbl)
-		dsll	t1, 32
-		daddu	t1, t1, AT
-		.set	pop
+#else
+#error GCC `-msym32' option required for 64-bit DECstation builds
 #endif
 2:		lw	t2,(t1)
 		nop

arch/mips/include/asm/cache.h

@@ -9,6 +9,8 @@
 #ifndef _ASM_CACHE_H
 #define _ASM_CACHE_H
 
+#include <kmalloc.h>
+
 #define L1_CACHE_SHIFT		CONFIG_MIPS_L1_CACHE_SHIFT
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 

arch/mips/include/asm/cpu-features.h

@@ -428,6 +428,9 @@
 #ifndef cpu_scache_line_size
 #define cpu_scache_line_size()	cpu_data[0].scache.linesz
 #endif
+#ifndef cpu_tcache_line_size
+#define cpu_tcache_line_size()	cpu_data[0].tcache.linesz
+#endif
 
 #ifndef cpu_hwrena_impl_bits
 #define cpu_hwrena_impl_bits		0

arch/mips/include/asm/octeon/cvmx-l2c-defs.h

@@ -33,6 +33,10 @@
 #define CVMX_L2C_DBG (CVMX_ADD_IO_SEG(0x0001180080000030ull))
 #define CVMX_L2C_CFG (CVMX_ADD_IO_SEG(0x0001180080000000ull))
 #define CVMX_L2C_CTL (CVMX_ADD_IO_SEG(0x0001180080800000ull))
+#define CVMX_L2C_ERR_TDTX(block_id)					       \
+	(CVMX_ADD_IO_SEG(0x0001180080A007E0ull) + ((block_id) & 3) * 0x40000ull)
+#define CVMX_L2C_ERR_TTGX(block_id)					       \
+	(CVMX_ADD_IO_SEG(0x0001180080A007E8ull) + ((block_id) & 3) * 0x40000ull)
 #define CVMX_L2C_LCKBASE (CVMX_ADD_IO_SEG(0x0001180080000058ull))
 #define CVMX_L2C_LCKOFF (CVMX_ADD_IO_SEG(0x0001180080000060ull))
 #define CVMX_L2C_PFCTL (CVMX_ADD_IO_SEG(0x0001180080000090ull))
@@ -66,9 +70,40 @@
 		((offset) & 1) * 8)
 #define CVMX_L2C_WPAR_PPX(offset) (CVMX_ADD_IO_SEG(0x0001180080840000ull)    + \
 		((offset) & 31) * 8)
-#define CVMX_L2D_FUS3 (CVMX_ADD_IO_SEG(0x00011800800007B8ull))
 
 
+union cvmx_l2c_err_tdtx {
+	uint64_t u64;
+	struct cvmx_l2c_err_tdtx_s {
+		__BITFIELD_FIELD(uint64_t dbe:1,
+		__BITFIELD_FIELD(uint64_t sbe:1,
+		__BITFIELD_FIELD(uint64_t vdbe:1,
+		__BITFIELD_FIELD(uint64_t vsbe:1,
+		__BITFIELD_FIELD(uint64_t syn:10,
+		__BITFIELD_FIELD(uint64_t reserved_22_49:28,
+		__BITFIELD_FIELD(uint64_t wayidx:18,
+		__BITFIELD_FIELD(uint64_t reserved_2_3:2,
+		__BITFIELD_FIELD(uint64_t type:2,
+		;)))))))))
+	} s;
+};
+
+union cvmx_l2c_err_ttgx {
+	uint64_t u64;
+	struct cvmx_l2c_err_ttgx_s {
+		__BITFIELD_FIELD(uint64_t dbe:1,
+		__BITFIELD_FIELD(uint64_t sbe:1,
+		__BITFIELD_FIELD(uint64_t noway:1,
+		__BITFIELD_FIELD(uint64_t reserved_56_60:5,
+		__BITFIELD_FIELD(uint64_t syn:6,
+		__BITFIELD_FIELD(uint64_t reserved_22_49:28,
+		__BITFIELD_FIELD(uint64_t wayidx:15,
+		__BITFIELD_FIELD(uint64_t reserved_2_6:5,
+		__BITFIELD_FIELD(uint64_t type:2,
+		;)))))))))
+	} s;
+};
+
 union cvmx_l2c_cfg {
 	uint64_t u64;
 	struct cvmx_l2c_cfg_s {

arch/mips/include/asm/octeon/cvmx-l2d-defs.h

@@ -0,0 +1,60 @@
+/***********************license start***************
+ * Author: Cavium Networks
+ *
+ * Contact: support@caviumnetworks.com
+ * This file is part of the OCTEON SDK
+ *
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ *
+ * This file 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 file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this file; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ * or visit http://www.gnu.org/licenses/.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium Networks for more information
+ ***********************license end**************************************/
+
+#ifndef __CVMX_L2D_DEFS_H__
+#define __CVMX_L2D_DEFS_H__
+
+#define CVMX_L2D_ERR	(CVMX_ADD_IO_SEG(0x0001180080000010ull))
+#define CVMX_L2D_FUS3	(CVMX_ADD_IO_SEG(0x00011800800007B8ull))
+
+
+union cvmx_l2d_err {
+	uint64_t u64;
+	struct cvmx_l2d_err_s {
+		__BITFIELD_FIELD(uint64_t reserved_6_63:58,
+		__BITFIELD_FIELD(uint64_t bmhclsel:1,
+		__BITFIELD_FIELD(uint64_t ded_err:1,
+		__BITFIELD_FIELD(uint64_t sec_err:1,
+		__BITFIELD_FIELD(uint64_t ded_intena:1,
+		__BITFIELD_FIELD(uint64_t sec_intena:1,
+		__BITFIELD_FIELD(uint64_t ecc_ena:1,
+		;)))))))
+	} s;
+};
+
+union cvmx_l2d_fus3 {
+	uint64_t u64;
+	struct cvmx_l2d_fus3_s {
+		__BITFIELD_FIELD(uint64_t reserved_40_63:24,
+		__BITFIELD_FIELD(uint64_t ema_ctl:3,
+		__BITFIELD_FIELD(uint64_t reserved_34_36:3,
+		__BITFIELD_FIELD(uint64_t q3fus:34,
+		;))))
+	} s;
+};
+
+#endif

arch/mips/include/asm/octeon/cvmx.h

@@ -62,6 +62,7 @@ enum cvmx_mips_space {
 #include <asm/octeon/cvmx-iob-defs.h>
 #include <asm/octeon/cvmx-ipd-defs.h>
 #include <asm/octeon/cvmx-l2c-defs.h>
+#include <asm/octeon/cvmx-l2d-defs.h>
 #include <asm/octeon/cvmx-l2t-defs.h>
 #include <asm/octeon/cvmx-led-defs.h>
 #include <asm/octeon/cvmx-mio-defs.h>

arch/mips/kernel/smp.c

@@ -376,9 +376,6 @@ asmlinkage void start_secondary(void)
 	cpumask_set_cpu(cpu, &cpu_coherent_mask);
 	notify_cpu_starting(cpu);
 
-	complete(&cpu_running);
-	synchronise_count_slave(cpu);
-
 	set_cpu_online(cpu, true);
 
 	set_cpu_sibling_map(cpu);
@@ -386,6 +383,9 @@ asmlinkage void start_secondary(void)
 
 	calculate_cpu_foreign_map();
 
+	complete(&cpu_running);
+	synchronise_count_slave(cpu);
+
 	/*
 	 * irq will be enabled in ->smp_finish(), enabling it too early
 	 * is dangerous.

arch/mips/mm/uasm-mips.c

@@ -48,7 +48,7 @@
 
 #include "uasm.c"
 
-static const struct insn const insn_table[insn_invalid] = {
+static const struct insn insn_table[insn_invalid] = {
 	[insn_addiu]	= {M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM},
 	[insn_addu]	= {M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD},
 	[insn_and]	= {M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD},

arch/mips/net/ebpf_jit.c

@@ -0,0 +1,1950 @@
+/*
+ * Just-In-Time compiler for eBPF filters on MIPS
+ *
+ * Copyright (c) 2017 Cavium, Inc.
+ *
+ * Based on code from:
+ *
+ * Copyright (c) 2014 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 <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/slab.h>
+#include <asm/bitops.h>
+#include <asm/byteorder.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu-features.h>
+#include <asm/uasm.h>
+
+/* Registers used by JIT */
+#define MIPS_R_ZERO	0
+#define MIPS_R_AT	1
+#define MIPS_R_V0	2	/* BPF_R0 */
+#define MIPS_R_V1	3
+#define MIPS_R_A0	4	/* BPF_R1 */
+#define MIPS_R_A1	5	/* BPF_R2 */
+#define MIPS_R_A2	6	/* BPF_R3 */
+#define MIPS_R_A3	7	/* BPF_R4 */
+#define MIPS_R_A4	8	/* BPF_R5 */
+#define MIPS_R_T4	12	/* BPF_AX */
+#define MIPS_R_T5	13
+#define MIPS_R_T6	14
+#define MIPS_R_T7	15
+#define MIPS_R_S0	16	/* BPF_R6 */
+#define MIPS_R_S1	17	/* BPF_R7 */
+#define MIPS_R_S2	18	/* BPF_R8 */
+#define MIPS_R_S3	19	/* BPF_R9 */
+#define MIPS_R_S4	20	/* BPF_TCC */
+#define MIPS_R_S5	21
+#define MIPS_R_S6	22
+#define MIPS_R_S7	23
+#define MIPS_R_T8	24
+#define MIPS_R_T9	25
+#define MIPS_R_SP	29
+#define MIPS_R_RA	31
+
+/* eBPF flags */
+#define EBPF_SAVE_S0	BIT(0)
+#define EBPF_SAVE_S1	BIT(1)
+#define EBPF_SAVE_S2	BIT(2)
+#define EBPF_SAVE_S3	BIT(3)
+#define EBPF_SAVE_S4	BIT(4)
+#define EBPF_SAVE_RA	BIT(5)
+#define EBPF_SEEN_FP	BIT(6)
+#define EBPF_SEEN_TC	BIT(7)
+#define EBPF_TCC_IN_V1	BIT(8)
+
+/*
+ * For the mips64 ISA, we need to track the value range or type for
+ * each JIT register.  The BPF machine requires zero extended 32-bit
+ * values, but the mips64 ISA requires sign extended 32-bit values.
+ * At each point in the BPF program we track the state of every
+ * register so that we can zero extend or sign extend as the BPF
+ * semantics require.
+ */
+enum reg_val_type {
+	/* uninitialized */
+	REG_UNKNOWN,
+	/* not known to be 32-bit compatible. */
+	REG_64BIT,
+	/* 32-bit compatible, no truncation needed for 64-bit ops. */
+	REG_64BIT_32BIT,
+	/* 32-bit compatible, need truncation for 64-bit ops. */
+	REG_32BIT,
+	/* 32-bit zero extended. */
+	REG_32BIT_ZERO_EX,
+	/* 32-bit no sign/zero extension needed. */
+	REG_32BIT_POS
+};
+
+/*
+ * high bit of offsets indicates if long branch conversion done at
+ * this insn.
+ */
+#define OFFSETS_B_CONV	BIT(31)
+
+/**
+ * struct jit_ctx - JIT context
+ * @skf:		The sk_filter
+ * @stack_size:		eBPF stack size
+ * @tmp_offset:		eBPF $sp offset to 8-byte temporary memory
+ * @idx:		Instruction index
+ * @flags:		JIT flags
+ * @offsets:		Instruction offsets
+ * @target:		Memory location for the compiled filter
+ * @reg_val_types	Packed enum reg_val_type for each register.
+ */
+struct jit_ctx {
+	const struct bpf_prog *skf;
+	int stack_size;
+	int tmp_offset;
+	u32 idx;
+	u32 flags;
+	u32 *offsets;
+	u32 *target;
+	u64 *reg_val_types;
+	unsigned int long_b_conversion:1;
+	unsigned int gen_b_offsets:1;
+};
+
+static void set_reg_val_type(u64 *rvt, int reg, enum reg_val_type type)
+{
+	*rvt &= ~(7ull << (reg * 3));
+	*rvt |= ((u64)type << (reg * 3));
+}
+
+static enum reg_val_type get_reg_val_type(const struct jit_ctx *ctx,
+					  int index, int reg)
+{
+	return (ctx->reg_val_types[index] >> (reg * 3)) & 7;
+}
+
+/* Simply emit the instruction if the JIT memory space has been allocated */
+#define emit_instr(ctx, func, ...)			\
+do {							\
+	if ((ctx)->target != NULL) {			\
+		u32 *p = &(ctx)->target[ctx->idx];	\
+		uasm_i_##func(&p, ##__VA_ARGS__);	\
+	}						\
+	(ctx)->idx++;					\
+} while (0)
+
+static unsigned int j_target(struct jit_ctx *ctx, int target_idx)
+{
+	unsigned long target_va, base_va;
+	unsigned int r;
+
+	if (!ctx->target)
+		return 0;
+
+	base_va = (unsigned long)ctx->target;
+	target_va = base_va + (ctx->offsets[target_idx] & ~OFFSETS_B_CONV);
+
+	if ((base_va & ~0x0ffffffful) != (target_va & ~0x0ffffffful))
+		return (unsigned int)-1;
+	r = target_va & 0x0ffffffful;
+	return r;
+}
+
+/* Compute the immediate value for PC-relative branches. */
+static u32 b_imm(unsigned int tgt, struct jit_ctx *ctx)
+{
+	if (!ctx->gen_b_offsets)
+		return 0;
+
+	/*
+	 * We want a pc-relative branch.  tgt is the instruction offset
+	 * we want to jump to.
+
+	 * Branch on MIPS:
+	 * I: target_offset <- sign_extend(offset)
+	 * I+1: PC += target_offset (delay slot)
+	 *
+	 * ctx->idx currently points to the branch instruction
+	 * but the offset is added to the delay slot so we need
+	 * to subtract 4.
+	 */
+	return (ctx->offsets[tgt] & ~OFFSETS_B_CONV) -
+		(ctx->idx * 4) - 4;
+}
+
+int bpf_jit_enable __read_mostly;
+
+enum which_ebpf_reg {
+	src_reg,
+	src_reg_no_fp,
+	dst_reg,
+	dst_reg_fp_ok
+};
+
+/*
+ * For eBPF, the register mapping naturally falls out of the
+ * requirements of eBPF and the MIPS n64 ABI.  We don't maintain a
+ * separate frame pointer, so BPF_REG_10 relative accesses are
+ * adjusted to be $sp relative.
+ */
+int ebpf_to_mips_reg(struct jit_ctx *ctx, const struct bpf_insn *insn,
+		     enum which_ebpf_reg w)
+{
+	int ebpf_reg = (w == src_reg || w == src_reg_no_fp) ?
+		insn->src_reg : insn->dst_reg;
+
+	switch (ebpf_reg) {
+	case BPF_REG_0:
+		return MIPS_R_V0;
+	case BPF_REG_1:
+		return MIPS_R_A0;
+	case BPF_REG_2:
+		return MIPS_R_A1;
+	case BPF_REG_3:
+		return MIPS_R_A2;
+	case BPF_REG_4:
+		return MIPS_R_A3;
+	case BPF_REG_5:
+		return MIPS_R_A4;
+	case BPF_REG_6:
+		ctx->flags |= EBPF_SAVE_S0;
+		return MIPS_R_S0;
+	case BPF_REG_7:
+		ctx->flags |= EBPF_SAVE_S1;
+		return MIPS_R_S1;
+	case BPF_REG_8:
+		ctx->flags |= EBPF_SAVE_S2;
+		return MIPS_R_S2;
+	case BPF_REG_9:
+		ctx->flags |= EBPF_SAVE_S3;
+		return MIPS_R_S3;
+	case BPF_REG_10:
+		if (w == dst_reg || w == src_reg_no_fp)
+			goto bad_reg;
+		ctx->flags |= EBPF_SEEN_FP;
+		/*
+		 * Needs special handling, return something that
+		 * cannot be clobbered just in case.
+		 */
+		return MIPS_R_ZERO;
+	case BPF_REG_AX:
+		return MIPS_R_T4;
+	default:
+bad_reg:
+		WARN(1, "Illegal bpf reg: %d\n", ebpf_reg);
+		return -EINVAL;
+	}
+}
+/*
+ * eBPF stack frame will be something like:
+ *
+ *  Entry $sp ------>   +--------------------------------+
+ *                      |   $ra  (optional)              |
+ *                      +--------------------------------+
+ *                      |   $s0  (optional)              |
+ *                      +--------------------------------+
+ *                      |   $s1  (optional)              |
+ *                      +--------------------------------+
+ *                      |   $s2  (optional)              |
+ *                      +--------------------------------+
+ *                      |   $s3  (optional)              |
+ *                      +--------------------------------+
+ *                      |   $s4  (optional)              |
+ *                      +--------------------------------+
+ *                      |   tmp-storage  (if $ra saved)  |
+ * $sp + tmp_offset --> +--------------------------------+ <--BPF_REG_10
+ *                      |   BPF_REG_10 relative storage  |
+ *                      |    MAX_BPF_STACK (optional)    |
+ *                      |      .                         |
+ *                      |      .                         |
+ *                      |      .                         |
+ *     $sp -------->    +--------------------------------+
+ *
+ * If BPF_REG_10 is never referenced, then the MAX_BPF_STACK sized
+ * area is not allocated.
+ */
+static int gen_int_prologue(struct jit_ctx *ctx)
+{
+	int stack_adjust = 0;
+	int store_offset;
+	int locals_size;
+
+	if (ctx->flags & EBPF_SAVE_RA)
+		/*
+		 * If RA we are doing a function call and may need
+		 * extra 8-byte tmp area.
+		 */
+		stack_adjust += 16;
+	if (ctx->flags & EBPF_SAVE_S0)
+		stack_adjust += 8;
+	if (ctx->flags & EBPF_SAVE_S1)
+		stack_adjust += 8;
+	if (ctx->flags & EBPF_SAVE_S2)
+		stack_adjust += 8;
+	if (ctx->flags & EBPF_SAVE_S3)
+		stack_adjust += 8;
+	if (ctx->flags & EBPF_SAVE_S4)
+		stack_adjust += 8;
+
+	BUILD_BUG_ON(MAX_BPF_STACK & 7);
+	locals_size = (ctx->flags & EBPF_SEEN_FP) ? MAX_BPF_STACK : 0;
+
+	stack_adjust += locals_size;
+	ctx->tmp_offset = locals_size;
+
+	ctx->stack_size = stack_adjust;
+
+	/*
+	 * First instruction initializes the tail call count (TCC).
+	 * 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);
+	if (stack_adjust)
+		emit_instr(ctx, daddiu, MIPS_R_SP, MIPS_R_SP, -stack_adjust);
+	else
+		return 0;
+
+	store_offset = stack_adjust - 8;
+
+	if (ctx->flags & EBPF_SAVE_RA) {
+		emit_instr(ctx, sd, MIPS_R_RA, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S0) {
+		emit_instr(ctx, sd, MIPS_R_S0, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S1) {
+		emit_instr(ctx, sd, MIPS_R_S1, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S2) {
+		emit_instr(ctx, sd, MIPS_R_S2, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S3) {
+		emit_instr(ctx, sd, MIPS_R_S3, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S4) {
+		emit_instr(ctx, sd, MIPS_R_S4, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+
+	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);
+
+	return 0;
+}
+
+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 r0 = MIPS_R_V0;
+
+	if (dest_reg == MIPS_R_RA &&
+	    get_reg_val_type(ctx, prog->len, BPF_REG_0) == REG_32BIT_ZERO_EX)
+		/* Don't let zero extended value escape. */
+		emit_instr(ctx, sll, r0, r0, 0);
+
+	if (ctx->flags & EBPF_SAVE_RA) {
+		emit_instr(ctx, ld, MIPS_R_RA, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S0) {
+		emit_instr(ctx, ld, MIPS_R_S0, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S1) {
+		emit_instr(ctx, ld, MIPS_R_S1, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S2) {
+		emit_instr(ctx, ld, MIPS_R_S2, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S3) {
+		emit_instr(ctx, ld, MIPS_R_S3, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	if (ctx->flags & EBPF_SAVE_S4) {
+		emit_instr(ctx, ld, MIPS_R_S4, store_offset, MIPS_R_SP);
+		store_offset -= 8;
+	}
+	emit_instr(ctx, jr, dest_reg);
+
+	if (stack_adjust)
+		emit_instr(ctx, daddiu, MIPS_R_SP, MIPS_R_SP, stack_adjust);
+	else
+		emit_instr(ctx, nop);
+
+	return 0;
+}
+
+static void gen_imm_to_reg(const struct bpf_insn *insn, int reg,
+			   struct jit_ctx *ctx)
+{
+	if (insn->imm >= S16_MIN && insn->imm <= S16_MAX) {
+		emit_instr(ctx, addiu, reg, MIPS_R_ZERO, insn->imm);
+	} else {
+		int lower = (s16)(insn->imm & 0xffff);
+		int upper = insn->imm - lower;
+
+		emit_instr(ctx, lui, reg, upper >> 16);
+		emit_instr(ctx, addiu, reg, reg, lower);
+	}
+
+}
+
+static int gen_imm_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
+			int idx)
+{
+	int upper_bound, lower_bound;
+	int dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+
+	if (dst < 0)
+		return dst;
+
+	switch (BPF_OP(insn->code)) {
+	case BPF_MOV:
+	case BPF_ADD:
+		upper_bound = S16_MAX;
+		lower_bound = S16_MIN;
+		break;
+	case BPF_SUB:
+		upper_bound = -(int)S16_MIN;
+		lower_bound = -(int)S16_MAX;
+		break;
+	case BPF_AND:
+	case BPF_OR:
+	case BPF_XOR:
+		upper_bound = 0xffff;
+		lower_bound = 0;
+		break;
+	case BPF_RSH:
+	case BPF_LSH:
+	case BPF_ARSH:
+		/* Shift amounts are truncated, no need for bounds */
+		upper_bound = S32_MAX;
+		lower_bound = S32_MIN;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * Immediate move clobbers the register, so no sign/zero
+	 * extension needed.
+	 */
+	if (BPF_CLASS(insn->code) == BPF_ALU64 &&
+	    BPF_OP(insn->code) != BPF_MOV &&
+	    get_reg_val_type(ctx, idx, insn->dst_reg) == REG_32BIT)
+		emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
+	/* BPF_ALU | BPF_LSH doesn't need separate sign extension */
+	if (BPF_CLASS(insn->code) == BPF_ALU &&
+	    BPF_OP(insn->code) != BPF_LSH &&
+	    BPF_OP(insn->code) != BPF_MOV &&
+	    get_reg_val_type(ctx, idx, insn->dst_reg) != REG_32BIT)
+		emit_instr(ctx, sll, dst, dst, 0);
+
+	if (insn->imm >= lower_bound && insn->imm <= upper_bound) {
+		/* single insn immediate case */
+		switch (BPF_OP(insn->code) | BPF_CLASS(insn->code)) {
+		case BPF_ALU64 | BPF_MOV:
+			emit_instr(ctx, daddiu, dst, MIPS_R_ZERO, insn->imm);
+			break;
+		case BPF_ALU64 | BPF_AND:
+		case BPF_ALU | BPF_AND:
+			emit_instr(ctx, andi, dst, dst, insn->imm);
+			break;
+		case BPF_ALU64 | BPF_OR:
+		case BPF_ALU | BPF_OR:
+			emit_instr(ctx, ori, dst, dst, insn->imm);
+			break;
+		case BPF_ALU64 | BPF_XOR:
+		case BPF_ALU | BPF_XOR:
+			emit_instr(ctx, xori, dst, dst, insn->imm);
+			break;
+		case BPF_ALU64 | BPF_ADD:
+			emit_instr(ctx, daddiu, dst, dst, insn->imm);
+			break;
+		case BPF_ALU64 | BPF_SUB:
+			emit_instr(ctx, daddiu, dst, dst, -insn->imm);
+			break;
+		case BPF_ALU64 | BPF_RSH:
+			emit_instr(ctx, dsrl_safe, dst, dst, insn->imm & 0x3f);
+			break;
+		case BPF_ALU | BPF_RSH:
+			emit_instr(ctx, srl, dst, dst, insn->imm & 0x1f);
+			break;
+		case BPF_ALU64 | BPF_LSH:
+			emit_instr(ctx, dsll_safe, dst, dst, insn->imm & 0x3f);
+			break;
+		case BPF_ALU | BPF_LSH:
+			emit_instr(ctx, sll, dst, dst, insn->imm & 0x1f);
+			break;
+		case BPF_ALU64 | BPF_ARSH:
+			emit_instr(ctx, dsra_safe, dst, dst, insn->imm & 0x3f);
+			break;
+		case BPF_ALU | BPF_ARSH:
+			emit_instr(ctx, sra, dst, dst, insn->imm & 0x1f);
+			break;
+		case BPF_ALU | BPF_MOV:
+			emit_instr(ctx, addiu, dst, MIPS_R_ZERO, insn->imm);
+			break;
+		case BPF_ALU | BPF_ADD:
+			emit_instr(ctx, addiu, dst, dst, insn->imm);
+			break;
+		case BPF_ALU | BPF_SUB:
+			emit_instr(ctx, addiu, dst, dst, -insn->imm);
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else {
+		/* multi insn immediate case */
+		if (BPF_OP(insn->code) == BPF_MOV) {
+			gen_imm_to_reg(insn, dst, ctx);
+		} else {
+			gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+			switch (BPF_OP(insn->code) | BPF_CLASS(insn->code)) {
+			case BPF_ALU64 | BPF_AND:
+			case BPF_ALU | BPF_AND:
+				emit_instr(ctx, and, dst, dst, MIPS_R_AT);
+				break;
+			case BPF_ALU64 | BPF_OR:
+			case BPF_ALU | BPF_OR:
+				emit_instr(ctx, or, dst, dst, MIPS_R_AT);
+				break;
+			case BPF_ALU64 | BPF_XOR:
+			case BPF_ALU | BPF_XOR:
+				emit_instr(ctx, xor, dst, dst, MIPS_R_AT);
+				break;
+			case BPF_ALU64 | BPF_ADD:
+				emit_instr(ctx, daddu, dst, dst, MIPS_R_AT);
+				break;
+			case BPF_ALU64 | BPF_SUB:
+				emit_instr(ctx, dsubu, dst, dst, MIPS_R_AT);
+				break;
+			case BPF_ALU | BPF_ADD:
+				emit_instr(ctx, addu, dst, dst, MIPS_R_AT);
+				break;
+			case BPF_ALU | BPF_SUB:
+				emit_instr(ctx, subu, dst, dst, MIPS_R_AT);
+				break;
+			default:
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void * __must_check
+ool_skb_header_pointer(const struct sk_buff *skb, int offset,
+		       int len, void *buffer)
+{
+	return skb_header_pointer(skb, offset, len, buffer);
+}
+
+static int size_to_len(const struct bpf_insn *insn)
+{
+	switch (BPF_SIZE(insn->code)) {
+	case BPF_B:
+		return 1;
+	case BPF_H:
+		return 2;
+	case BPF_W:
+		return 4;
+	case BPF_DW:
+		return 8;
+	}
+	return 0;
+}
+
+static void emit_const_to_reg(struct jit_ctx *ctx, int dst, u64 value)
+{
+	if (value >= 0xffffffffffff8000ull || value < 0x8000ull) {
+		emit_instr(ctx, daddiu, dst, MIPS_R_ZERO, (int)value);
+	} else if (value >= 0xffffffff80000000ull ||
+		   (value < 0x80000000 && value > 0xffff)) {
+		emit_instr(ctx, lui, dst, (s32)(s16)(value >> 16));
+		emit_instr(ctx, ori, dst, dst, (unsigned int)(value & 0xffff));
+	} else {
+		int i;
+		bool seen_part = false;
+		int needed_shift = 0;
+
+		for (i = 0; i < 4; i++) {
+			u64 part = (value >> (16 * (3 - i))) & 0xffff;
+
+			if (seen_part && needed_shift > 0 && (part || i == 3)) {
+				emit_instr(ctx, dsll_safe, dst, dst, needed_shift);
+				needed_shift = 0;
+			}
+			if (part) {
+				if (i == 0 || (!seen_part && i < 3 && part < 0x8000)) {
+					emit_instr(ctx, lui, dst, (s32)(s16)part);
+					needed_shift = -16;
+				} else {
+					emit_instr(ctx, ori, dst,
+						   seen_part ? dst : MIPS_R_ZERO,
+						   (unsigned int)part);
+				}
+				seen_part = true;
+			}
+			if (seen_part)
+				needed_shift += 16;
+		}
+	}
+}
+
+static int emit_bpf_tail_call(struct jit_ctx *ctx, int this_idx)
+{
+	int off, b_off;
+
+	ctx->flags |= EBPF_SEEN_TC;
+	/*
+	 * if (index >= array->map.max_entries)
+	 *     goto out;
+	 */
+	off = offsetof(struct bpf_array, map.max_entries);
+	emit_instr(ctx, lwu, MIPS_R_T5, off, MIPS_R_A1);
+	emit_instr(ctx, sltu, MIPS_R_AT, MIPS_R_T5, MIPS_R_A2);
+	b_off = b_imm(this_idx + 1, ctx);
+	emit_instr(ctx, bne, MIPS_R_AT, MIPS_R_ZERO, b_off);
+	/*
+	 * if (--TCC < 0)
+	 *     goto out;
+	 */
+	/* Delay slot */
+	emit_instr(ctx, daddiu, MIPS_R_T5,
+		   (ctx->flags & EBPF_TCC_IN_V1) ? MIPS_R_V1 : MIPS_R_S4, -1);
+	b_off = b_imm(this_idx + 1, ctx);
+	emit_instr(ctx, bltz, MIPS_R_T5, b_off);
+	/*
+	 * prog = array->ptrs[index];
+	 * if (prog == NULL)
+	 *     goto out;
+	 */
+	/* Delay slot */
+	emit_instr(ctx, dsll, MIPS_R_T8, MIPS_R_A2, 3);
+	emit_instr(ctx, daddu, MIPS_R_T8, MIPS_R_T8, MIPS_R_A1);
+	off = offsetof(struct bpf_array, ptrs);
+	emit_instr(ctx, ld, MIPS_R_AT, off, MIPS_R_T8);
+	b_off = b_imm(this_idx + 1, ctx);
+	emit_instr(ctx, beq, MIPS_R_AT, MIPS_R_ZERO, b_off);
+	/* Delay slot */
+	emit_instr(ctx, nop);
+
+	/* goto *(prog->bpf_func + 4); */
+	off = offsetof(struct bpf_prog, bpf_func);
+	emit_instr(ctx, ld, MIPS_R_T9, off, MIPS_R_AT);
+	/* All systems are go... propagate TCC */
+	emit_instr(ctx, daddu, MIPS_R_V1, MIPS_R_T5, MIPS_R_ZERO);
+	/* Skip first instruction (TCC initialization) */
+	emit_instr(ctx, daddiu, MIPS_R_T9, MIPS_R_T9, 4);
+	return build_int_epilogue(ctx, MIPS_R_T9);
+}
+
+static bool use_bbit_insns(void)
+{
+	switch (current_cpu_type()) {
+	case CPU_CAVIUM_OCTEON:
+	case CPU_CAVIUM_OCTEON_PLUS:
+	case CPU_CAVIUM_OCTEON2:
+	case CPU_CAVIUM_OCTEON3:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_bad_offset(int b_off)
+{
+	return b_off > 0x1ffff || b_off < -0x20000;
+}
+
+/* Returns the number of insn slots consumed. */
+static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
+			  int this_idx, int exit_idx)
+{
+	int src, dst, r, td, ts, mem_off, b_off;
+	bool need_swap, did_move, cmp_eq;
+	unsigned int target;
+	u64 t64;
+	s64 t64s;
+
+	switch (insn->code) {
+	case BPF_ALU64 | BPF_ADD | BPF_K: /* ALU64_IMM */
+	case BPF_ALU64 | BPF_SUB | BPF_K: /* ALU64_IMM */
+	case BPF_ALU64 | BPF_OR | BPF_K: /* ALU64_IMM */
+	case BPF_ALU64 | BPF_AND | BPF_K: /* ALU64_IMM */
+	case BPF_ALU64 | BPF_LSH | BPF_K: /* ALU64_IMM */
+	case BPF_ALU64 | BPF_RSH | BPF_K: /* ALU64_IMM */
+	case BPF_ALU64 | BPF_XOR | BPF_K: /* ALU64_IMM */
+	case BPF_ALU64 | BPF_ARSH | BPF_K: /* ALU64_IMM */
+	case BPF_ALU64 | BPF_MOV | BPF_K: /* ALU64_IMM */
+	case BPF_ALU | BPF_MOV | BPF_K: /* ALU32_IMM */
+	case BPF_ALU | BPF_ADD | BPF_K: /* ALU32_IMM */
+	case BPF_ALU | BPF_SUB | BPF_K: /* ALU32_IMM */
+	case BPF_ALU | BPF_OR | BPF_K: /* ALU64_IMM */
+	case BPF_ALU | BPF_AND | BPF_K: /* ALU64_IMM */
+	case BPF_ALU | BPF_LSH | BPF_K: /* ALU64_IMM */
+	case BPF_ALU | BPF_RSH | BPF_K: /* ALU64_IMM */
+	case BPF_ALU | BPF_XOR | BPF_K: /* ALU64_IMM */
+	case BPF_ALU | BPF_ARSH | BPF_K: /* ALU64_IMM */
+		r = gen_imm_insn(insn, ctx, this_idx);
+		if (r < 0)
+			return r;
+		break;
+	case BPF_ALU64 | BPF_MUL | BPF_K: /* ALU64_IMM */
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (dst < 0)
+			return dst;
+		if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT)
+			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
+		if (insn->imm == 1) /* Mult by 1 is a nop */
+			break;
+		gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+		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);
+		if (dst < 0)
+			return dst;
+		if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT)
+			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
+		emit_instr(ctx, dsubu, dst, MIPS_R_ZERO, dst);
+		break;
+	case BPF_ALU | BPF_MUL | BPF_K: /* ALU_IMM */
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (dst < 0)
+			return dst;
+		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
+		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) {
+			/* sign extend */
+			emit_instr(ctx, sll, dst, dst, 0);
+		}
+		if (insn->imm == 1) /* Mult by 1 is a nop */
+			break;
+		gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+		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);
+		if (dst < 0)
+			return dst;
+		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
+		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) {
+			/* sign extend */
+			emit_instr(ctx, sll, dst, dst, 0);
+		}
+		emit_instr(ctx, subu, dst, MIPS_R_ZERO, dst);
+		break;
+	case BPF_ALU | BPF_DIV | BPF_K: /* ALU_IMM */
+	case BPF_ALU | BPF_MOD | BPF_K: /* ALU_IMM */
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (dst < 0)
+			return dst;
+		if (insn->imm == 0) { /* Div by zero */
+			b_off = b_imm(exit_idx, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
+			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
+		}
+		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
+		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX)
+			/* sign extend */
+			emit_instr(ctx, sll, dst, dst, 0);
+		if (insn->imm == 1) {
+			/* div by 1 is a nop, mod by 1 is zero */
+			if (BPF_OP(insn->code) == BPF_MOD)
+				emit_instr(ctx, addu, dst, MIPS_R_ZERO, MIPS_R_ZERO);
+			break;
+		}
+		gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+		emit_instr(ctx, divu, dst, MIPS_R_AT);
+		if (BPF_OP(insn->code) == BPF_DIV)
+			emit_instr(ctx, mflo, dst);
+		else
+			emit_instr(ctx, mfhi, dst);
+		break;
+	case BPF_ALU64 | BPF_DIV | BPF_K: /* ALU_IMM */
+	case BPF_ALU64 | BPF_MOD | BPF_K: /* ALU_IMM */
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (dst < 0)
+			return dst;
+		if (insn->imm == 0) { /* Div by zero */
+			b_off = b_imm(exit_idx, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
+			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
+		}
+		if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT)
+			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
+
+		if (insn->imm == 1) {
+			/* div by 1 is a nop, mod by 1 is zero */
+			if (BPF_OP(insn->code) == BPF_MOD)
+				emit_instr(ctx, addu, dst, MIPS_R_ZERO, MIPS_R_ZERO);
+			break;
+		}
+		gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+		emit_instr(ctx, ddivu, dst, MIPS_R_AT);
+		if (BPF_OP(insn->code) == BPF_DIV)
+			emit_instr(ctx, mflo, dst);
+		else
+			emit_instr(ctx, mfhi, dst);
+		break;
+	case BPF_ALU64 | BPF_MOV | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_ADD | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_SUB | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_XOR | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_OR | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_AND | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_MUL | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_DIV | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_MOD | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_LSH | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_RSH | BPF_X: /* ALU64_REG */
+	case BPF_ALU64 | BPF_ARSH | BPF_X: /* ALU64_REG */
+		src = ebpf_to_mips_reg(ctx, insn, src_reg);
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (src < 0 || dst < 0)
+			return -EINVAL;
+		if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT)
+			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
+		did_move = false;
+		if (insn->src_reg == BPF_REG_10) {
+			if (BPF_OP(insn->code) == BPF_MOV) {
+				emit_instr(ctx, daddiu, dst, MIPS_R_SP, MAX_BPF_STACK);
+				did_move = true;
+			} else {
+				emit_instr(ctx, daddiu, MIPS_R_AT, MIPS_R_SP, MAX_BPF_STACK);
+				src = MIPS_R_AT;
+			}
+		} else if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) {
+			int tmp_reg = MIPS_R_AT;
+
+			if (BPF_OP(insn->code) == BPF_MOV) {
+				tmp_reg = dst;
+				did_move = true;
+			}
+			emit_instr(ctx, daddu, tmp_reg, src, MIPS_R_ZERO);
+			emit_instr(ctx, dinsu, tmp_reg, MIPS_R_ZERO, 32, 32);
+			src = MIPS_R_AT;
+		}
+		switch (BPF_OP(insn->code)) {
+		case BPF_MOV:
+			if (!did_move)
+				emit_instr(ctx, daddu, dst, src, MIPS_R_ZERO);
+			break;
+		case BPF_ADD:
+			emit_instr(ctx, daddu, dst, dst, src);
+			break;
+		case BPF_SUB:
+			emit_instr(ctx, dsubu, dst, dst, src);
+			break;
+		case BPF_XOR:
+			emit_instr(ctx, xor, dst, dst, src);
+			break;
+		case BPF_OR:
+			emit_instr(ctx, or, dst, dst, src);
+			break;
+		case BPF_AND:
+			emit_instr(ctx, and, dst, dst, src);
+			break;
+		case BPF_MUL:
+			emit_instr(ctx, dmultu, dst, src);
+			emit_instr(ctx, mflo, dst);
+			break;
+		case BPF_DIV:
+		case BPF_MOD:
+			b_off = b_imm(exit_idx, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
+			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
+			emit_instr(ctx, ddivu, dst, src);
+			if (BPF_OP(insn->code) == BPF_DIV)
+				emit_instr(ctx, mflo, dst);
+			else
+				emit_instr(ctx, mfhi, dst);
+			break;
+		case BPF_LSH:
+			emit_instr(ctx, dsllv, dst, dst, src);
+			break;
+		case BPF_RSH:
+			emit_instr(ctx, dsrlv, dst, dst, src);
+			break;
+		case BPF_ARSH:
+			emit_instr(ctx, dsrav, dst, dst, src);
+			break;
+		default:
+			pr_err("ALU64_REG NOT HANDLED\n");
+			return -EINVAL;
+		}
+		break;
+	case BPF_ALU | BPF_MOV | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_ADD | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_SUB | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_XOR | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_OR | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_AND | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_MUL | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_DIV | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_MOD | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_LSH | BPF_X: /* ALU_REG */
+	case BPF_ALU | BPF_RSH | BPF_X: /* ALU_REG */
+		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (src < 0 || dst < 0)
+			return -EINVAL;
+		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
+		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) {
+			/* sign extend */
+			emit_instr(ctx, sll, dst, dst, 0);
+		}
+		did_move = false;
+		ts = get_reg_val_type(ctx, this_idx, insn->src_reg);
+		if (ts == REG_64BIT || ts == REG_32BIT_ZERO_EX) {
+			int tmp_reg = MIPS_R_AT;
+
+			if (BPF_OP(insn->code) == BPF_MOV) {
+				tmp_reg = dst;
+				did_move = true;
+			}
+			/* sign extend */
+			emit_instr(ctx, sll, tmp_reg, src, 0);
+			src = MIPS_R_AT;
+		}
+		switch (BPF_OP(insn->code)) {
+		case BPF_MOV:
+			if (!did_move)
+				emit_instr(ctx, addu, dst, src, MIPS_R_ZERO);
+			break;
+		case BPF_ADD:
+			emit_instr(ctx, addu, dst, dst, src);
+			break;
+		case BPF_SUB:
+			emit_instr(ctx, subu, dst, dst, src);
+			break;
+		case BPF_XOR:
+			emit_instr(ctx, xor, dst, dst, src);
+			break;
+		case BPF_OR:
+			emit_instr(ctx, or, dst, dst, src);
+			break;
+		case BPF_AND:
+			emit_instr(ctx, and, dst, dst, src);
+			break;
+		case BPF_MUL:
+			emit_instr(ctx, mul, dst, dst, src);
+			break;
+		case BPF_DIV:
+		case BPF_MOD:
+			b_off = b_imm(exit_idx, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
+			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
+			emit_instr(ctx, divu, dst, src);
+			if (BPF_OP(insn->code) == BPF_DIV)
+				emit_instr(ctx, mflo, dst);
+			else
+				emit_instr(ctx, mfhi, dst);
+			break;
+		case BPF_LSH:
+			emit_instr(ctx, sllv, dst, dst, src);
+			break;
+		case BPF_RSH:
+			emit_instr(ctx, srlv, dst, dst, src);
+			break;
+		default:
+			pr_err("ALU_REG NOT HANDLED\n");
+			return -EINVAL;
+		}
+		break;
+	case BPF_JMP | BPF_EXIT:
+		if (this_idx + 1 < exit_idx) {
+			b_off = b_imm(exit_idx, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
+			emit_instr(ctx, nop);
+		}
+		break;
+	case BPF_JMP | BPF_JEQ | BPF_K: /* JMP_IMM */
+	case BPF_JMP | BPF_JNE | BPF_K: /* JMP_IMM */
+		cmp_eq = (BPF_OP(insn->code) == BPF_JEQ);
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok);
+		if (dst < 0)
+			return dst;
+		if (insn->imm == 0) {
+			src = MIPS_R_ZERO;
+		} else {
+			gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+			src = MIPS_R_AT;
+		}
+		goto jeq_common;
+	case BPF_JMP | BPF_JEQ | BPF_X: /* JMP_REG */
+	case BPF_JMP | BPF_JNE | BPF_X:
+	case BPF_JMP | BPF_JSGT | BPF_X:
+	case BPF_JMP | BPF_JSGE | BPF_X:
+	case BPF_JMP | BPF_JGT | BPF_X:
+	case BPF_JMP | BPF_JGE | BPF_X:
+	case BPF_JMP | BPF_JSET | BPF_X:
+		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (src < 0 || dst < 0)
+			return -EINVAL;
+		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
+		ts = get_reg_val_type(ctx, this_idx, insn->src_reg);
+		if (td == REG_32BIT && ts != REG_32BIT) {
+			emit_instr(ctx, sll, MIPS_R_AT, src, 0);
+			src = MIPS_R_AT;
+		} else if (ts == REG_32BIT && td != REG_32BIT) {
+			emit_instr(ctx, sll, MIPS_R_AT, dst, 0);
+			dst = MIPS_R_AT;
+		}
+		if (BPF_OP(insn->code) == BPF_JSET) {
+			emit_instr(ctx, and, MIPS_R_AT, dst, src);
+			cmp_eq = false;
+			dst = MIPS_R_AT;
+			src = MIPS_R_ZERO;
+		} else if (BPF_OP(insn->code) == BPF_JSGT) {
+			emit_instr(ctx, dsubu, MIPS_R_AT, dst, src);
+			if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) {
+				b_off = b_imm(exit_idx, ctx);
+				if (is_bad_offset(b_off))
+					return -E2BIG;
+				emit_instr(ctx, blez, MIPS_R_AT, b_off);
+				emit_instr(ctx, nop);
+				return 2; /* We consumed the exit. */
+			}
+			b_off = b_imm(this_idx + insn->off + 1, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_instr(ctx, bgtz, MIPS_R_AT, b_off);
+			emit_instr(ctx, nop);
+			break;
+		} else if (BPF_OP(insn->code) == BPF_JSGE) {
+			emit_instr(ctx, slt, MIPS_R_AT, dst, src);
+			cmp_eq = true;
+			dst = MIPS_R_AT;
+			src = MIPS_R_ZERO;
+		} else if (BPF_OP(insn->code) == BPF_JGT) {
+			/* dst or src could be AT */
+			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);
+			emit_instr(ctx, or, MIPS_R_AT, MIPS_R_T9, MIPS_R_AT);
+			cmp_eq = true;
+			dst = MIPS_R_AT;
+			src = MIPS_R_ZERO;
+		} else if (BPF_OP(insn->code) == BPF_JGE) {
+			emit_instr(ctx, sltu, MIPS_R_AT, dst, src);
+			cmp_eq = true;
+			dst = MIPS_R_AT;
+			src = MIPS_R_ZERO;
+		} else { /* JNE/JEQ case */
+			cmp_eq = (BPF_OP(insn->code) == BPF_JEQ);
+		}
+jeq_common:
+		/*
+		 * If the next insn is EXIT and we are jumping arround
+		 * only it, invert the sense of the compare and
+		 * conditionally jump to the exit.  Poor man's branch
+		 * chaining.
+		 */
+		if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) {
+			b_off = b_imm(exit_idx, ctx);
+			if (is_bad_offset(b_off)) {
+				target = j_target(ctx, exit_idx);
+				if (target == (unsigned int)-1)
+					return -E2BIG;
+				cmp_eq = !cmp_eq;
+				b_off = 4 * 3;
+				if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) {
+					ctx->offsets[this_idx] |= OFFSETS_B_CONV;
+					ctx->long_b_conversion = 1;
+				}
+			}
+
+			if (cmp_eq)
+				emit_instr(ctx, bne, dst, src, b_off);
+			else
+				emit_instr(ctx, beq, dst, src, b_off);
+			emit_instr(ctx, nop);
+			if (ctx->offsets[this_idx] & OFFSETS_B_CONV) {
+				emit_instr(ctx, j, target);
+				emit_instr(ctx, nop);
+			}
+			return 2; /* We consumed the exit. */
+		}
+		b_off = b_imm(this_idx + insn->off + 1, ctx);
+		if (is_bad_offset(b_off)) {
+			target = j_target(ctx, this_idx + insn->off + 1);
+			if (target == (unsigned int)-1)
+				return -E2BIG;
+			cmp_eq = !cmp_eq;
+			b_off = 4 * 3;
+			if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) {
+				ctx->offsets[this_idx] |= OFFSETS_B_CONV;
+				ctx->long_b_conversion = 1;
+			}
+		}
+
+		if (cmp_eq)
+			emit_instr(ctx, beq, dst, src, b_off);
+		else
+			emit_instr(ctx, bne, dst, src, b_off);
+		emit_instr(ctx, nop);
+		if (ctx->offsets[this_idx] & OFFSETS_B_CONV) {
+			emit_instr(ctx, j, target);
+			emit_instr(ctx, nop);
+		}
+		break;
+	case BPF_JMP | BPF_JSGT | BPF_K: /* JMP_IMM */
+	case BPF_JMP | BPF_JSGE | BPF_K: /* JMP_IMM */
+		cmp_eq = (BPF_OP(insn->code) == BPF_JSGE);
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok);
+		if (dst < 0)
+			return dst;
+
+		if (insn->imm == 0) {
+			if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) {
+				b_off = b_imm(exit_idx, ctx);
+				if (is_bad_offset(b_off))
+					return -E2BIG;
+				if (cmp_eq)
+					emit_instr(ctx, bltz, dst, b_off);
+				else
+					emit_instr(ctx, blez, dst, b_off);
+				emit_instr(ctx, nop);
+				return 2; /* We consumed the exit. */
+			}
+			b_off = b_imm(this_idx + insn->off + 1, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			if (cmp_eq)
+				emit_instr(ctx, bgez, dst, b_off);
+			else
+				emit_instr(ctx, bgtz, dst, b_off);
+			emit_instr(ctx, nop);
+			break;
+		}
+		/*
+		 * only "LT" compare available, so we must use imm + 1
+		 * to generate "GT"
+		 */
+		t64s = insn->imm + (cmp_eq ? 0 : 1);
+		if (t64s >= S16_MIN && t64s <= S16_MAX) {
+			emit_instr(ctx, slti, MIPS_R_AT, dst, (int)t64s);
+			src = MIPS_R_AT;
+			dst = MIPS_R_ZERO;
+			cmp_eq = true;
+			goto jeq_common;
+		}
+		emit_const_to_reg(ctx, MIPS_R_AT, (u64)t64s);
+		emit_instr(ctx, slt, MIPS_R_AT, dst, MIPS_R_AT);
+		src = MIPS_R_AT;
+		dst = MIPS_R_ZERO;
+		cmp_eq = true;
+		goto jeq_common;
+
+	case BPF_JMP | BPF_JGT | BPF_K:
+	case BPF_JMP | BPF_JGE | BPF_K:
+		cmp_eq = (BPF_OP(insn->code) == BPF_JGE);
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok);
+		if (dst < 0)
+			return dst;
+		/*
+		 * only "LT" compare available, so we must use imm + 1
+		 * to generate "GT"
+		 */
+		t64s = (u64)(u32)(insn->imm) + (cmp_eq ? 0 : 1);
+		if (t64s >= 0 && t64s <= S16_MAX) {
+			emit_instr(ctx, sltiu, MIPS_R_AT, dst, (int)t64s);
+			src = MIPS_R_AT;
+			dst = MIPS_R_ZERO;
+			cmp_eq = true;
+			goto jeq_common;
+		}
+		emit_const_to_reg(ctx, MIPS_R_AT, (u64)t64s);
+		emit_instr(ctx, sltu, MIPS_R_AT, dst, MIPS_R_AT);
+		src = MIPS_R_AT;
+		dst = MIPS_R_ZERO;
+		cmp_eq = true;
+		goto jeq_common;
+
+	case BPF_JMP | BPF_JSET | BPF_K: /* JMP_IMM */
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok);
+		if (dst < 0)
+			return dst;
+
+		if (use_bbit_insns() && hweight32((u32)insn->imm) == 1) {
+			if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) {
+				b_off = b_imm(exit_idx, ctx);
+				if (is_bad_offset(b_off))
+					return -E2BIG;
+				emit_instr(ctx, bbit0, dst, ffs((u32)insn->imm) - 1, b_off);
+				emit_instr(ctx, nop);
+				return 2; /* We consumed the exit. */
+			}
+			b_off = b_imm(this_idx + insn->off + 1, ctx);
+			if (is_bad_offset(b_off))
+				return -E2BIG;
+			emit_instr(ctx, bbit1, dst, ffs((u32)insn->imm) - 1, b_off);
+			emit_instr(ctx, nop);
+			break;
+		}
+		t64 = (u32)insn->imm;
+		emit_const_to_reg(ctx, MIPS_R_AT, t64);
+		emit_instr(ctx, and, MIPS_R_AT, dst, MIPS_R_AT);
+		src = MIPS_R_AT;
+		dst = MIPS_R_ZERO;
+		cmp_eq = false;
+		goto jeq_common;
+
+	case BPF_JMP | BPF_JA:
+		/*
+		 * Prefer relative branch for easier debugging, but
+		 * fall back if needed.
+		 */
+		b_off = b_imm(this_idx + insn->off + 1, ctx);
+		if (is_bad_offset(b_off)) {
+			target = j_target(ctx, this_idx + insn->off + 1);
+			if (target == (unsigned int)-1)
+				return -E2BIG;
+			emit_instr(ctx, j, target);
+		} else {
+			emit_instr(ctx, b, b_off);
+		}
+		emit_instr(ctx, nop);
+		break;
+	case BPF_LD | BPF_DW | BPF_IMM:
+		if (insn->src_reg != 0)
+			return -EINVAL;
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (dst < 0)
+			return dst;
+		t64 = ((u64)(u32)insn->imm) | ((u64)(insn + 1)->imm << 32);
+		emit_const_to_reg(ctx, dst, t64);
+		return 2; /* Double slot insn */
+
+	case BPF_JMP | BPF_CALL:
+		ctx->flags |= EBPF_SAVE_RA;
+		t64s = (s64)insn->imm + (s64)__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 */
+		emit_instr(ctx, nop);
+		break;
+
+	case BPF_JMP | BPF_TAIL_CALL:
+		if (emit_bpf_tail_call(ctx, this_idx))
+			return -EINVAL;
+		break;
+
+	case BPF_LD | BPF_B | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_DW | BPF_ABS:
+		ctx->flags |= EBPF_SAVE_RA;
+
+		gen_imm_to_reg(insn, MIPS_R_A1, ctx);
+		emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn));
+
+		if (insn->imm < 0) {
+			emit_const_to_reg(ctx, MIPS_R_T9, (u64)bpf_internal_load_pointer_neg_helper);
+		} else {
+			emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer);
+			emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset);
+		}
+		goto ld_skb_common;
+
+	case BPF_LD | BPF_B | BPF_IND:
+	case BPF_LD | BPF_H | BPF_IND:
+	case BPF_LD | BPF_W | BPF_IND:
+	case BPF_LD | BPF_DW | BPF_IND:
+		ctx->flags |= EBPF_SAVE_RA;
+		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
+		if (src < 0)
+			return src;
+		ts = get_reg_val_type(ctx, this_idx, insn->src_reg);
+		if (ts == REG_32BIT_ZERO_EX) {
+			/* sign extend */
+			emit_instr(ctx, sll, MIPS_R_A1, src, 0);
+			src = MIPS_R_A1;
+		}
+		if (insn->imm >= S16_MIN && insn->imm <= S16_MAX) {
+			emit_instr(ctx, daddiu, MIPS_R_A1, src, insn->imm);
+		} else {
+			gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+			emit_instr(ctx, daddu, MIPS_R_A1, MIPS_R_AT, src);
+		}
+		/* truncate to 32-bit int */
+		emit_instr(ctx, sll, MIPS_R_A1, MIPS_R_A1, 0);
+		emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset);
+		emit_instr(ctx, slt, MIPS_R_AT, MIPS_R_A1, MIPS_R_ZERO);
+
+		emit_const_to_reg(ctx, MIPS_R_T8, (u64)bpf_internal_load_pointer_neg_helper);
+		emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer);
+		emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn));
+		emit_instr(ctx, movn, MIPS_R_T9, MIPS_R_T8, MIPS_R_AT);
+
+ld_skb_common:
+		emit_instr(ctx, jalr, MIPS_R_RA, MIPS_R_T9);
+		/* delay slot move */
+		emit_instr(ctx, daddu, MIPS_R_A0, MIPS_R_S0, MIPS_R_ZERO);
+
+		/* Check the error value */
+		b_off = b_imm(exit_idx, ctx);
+		if (is_bad_offset(b_off)) {
+			target = j_target(ctx, exit_idx);
+			if (target == (unsigned int)-1)
+				return -E2BIG;
+
+			if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) {
+				ctx->offsets[this_idx] |= OFFSETS_B_CONV;
+				ctx->long_b_conversion = 1;
+			}
+			emit_instr(ctx, bne, MIPS_R_V0, MIPS_R_ZERO, 4 * 3);
+			emit_instr(ctx, nop);
+			emit_instr(ctx, j, target);
+			emit_instr(ctx, nop);
+		} else {
+			emit_instr(ctx, beq, MIPS_R_V0, MIPS_R_ZERO, b_off);
+			emit_instr(ctx, nop);
+		}
+
+#ifdef __BIG_ENDIAN
+		need_swap = false;
+#else
+		need_swap = true;
+#endif
+		dst = MIPS_R_V0;
+		switch (BPF_SIZE(insn->code)) {
+		case BPF_B:
+			emit_instr(ctx, lbu, dst, 0, MIPS_R_V0);
+			break;
+		case BPF_H:
+			emit_instr(ctx, lhu, dst, 0, MIPS_R_V0);
+			if (need_swap)
+				emit_instr(ctx, wsbh, dst, dst);
+			break;
+		case BPF_W:
+			emit_instr(ctx, lw, dst, 0, MIPS_R_V0);
+			if (need_swap) {
+				emit_instr(ctx, wsbh, dst, dst);
+				emit_instr(ctx, rotr, dst, dst, 16);
+			}
+			break;
+		case BPF_DW:
+			emit_instr(ctx, ld, dst, 0, MIPS_R_V0);
+			if (need_swap) {
+				emit_instr(ctx, dsbh, dst, dst);
+				emit_instr(ctx, dshd, dst, dst);
+			}
+			break;
+		}
+
+		break;
+	case BPF_ALU | BPF_END | BPF_FROM_BE:
+	case BPF_ALU | BPF_END | BPF_FROM_LE:
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (dst < 0)
+			return dst;
+		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
+		if (insn->imm == 64 && td == REG_32BIT)
+			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
+
+		if (insn->imm != 64 &&
+		    (td == REG_64BIT || td == REG_32BIT_ZERO_EX)) {
+			/* sign extend */
+			emit_instr(ctx, sll, dst, dst, 0);
+		}
+
+#ifdef __BIG_ENDIAN
+		need_swap = (BPF_SRC(insn->code) == BPF_FROM_LE);
+#else
+		need_swap = (BPF_SRC(insn->code) == BPF_FROM_BE);
+#endif
+		if (insn->imm == 16) {
+			if (need_swap)
+				emit_instr(ctx, wsbh, dst, dst);
+			emit_instr(ctx, andi, dst, dst, 0xffff);
+		} else if (insn->imm == 32) {
+			if (need_swap) {
+				emit_instr(ctx, wsbh, dst, dst);
+				emit_instr(ctx, rotr, dst, dst, 16);
+			}
+		} else { /* 64-bit*/
+			if (need_swap) {
+				emit_instr(ctx, dsbh, dst, dst);
+				emit_instr(ctx, dshd, dst, dst);
+			}
+		}
+		break;
+
+	case BPF_ST | BPF_B | BPF_MEM:
+	case BPF_ST | BPF_H | BPF_MEM:
+	case BPF_ST | BPF_W | BPF_MEM:
+	case BPF_ST | BPF_DW | BPF_MEM:
+		if (insn->dst_reg == BPF_REG_10) {
+			ctx->flags |= EBPF_SEEN_FP;
+			dst = MIPS_R_SP;
+			mem_off = insn->off + MAX_BPF_STACK;
+		} else {
+			dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+			if (dst < 0)
+				return dst;
+			mem_off = insn->off;
+		}
+		gen_imm_to_reg(insn, MIPS_R_AT, ctx);
+		switch (BPF_SIZE(insn->code)) {
+		case BPF_B:
+			emit_instr(ctx, sb, MIPS_R_AT, mem_off, dst);
+			break;
+		case BPF_H:
+			emit_instr(ctx, sh, MIPS_R_AT, mem_off, dst);
+			break;
+		case BPF_W:
+			emit_instr(ctx, sw, MIPS_R_AT, mem_off, dst);
+			break;
+		case BPF_DW:
+			emit_instr(ctx, sd, MIPS_R_AT, mem_off, dst);
+			break;
+		}
+		break;
+
+	case BPF_LDX | BPF_B | BPF_MEM:
+	case BPF_LDX | BPF_H | BPF_MEM:
+	case BPF_LDX | BPF_W | BPF_MEM:
+	case BPF_LDX | BPF_DW | BPF_MEM:
+		if (insn->src_reg == BPF_REG_10) {
+			ctx->flags |= EBPF_SEEN_FP;
+			src = MIPS_R_SP;
+			mem_off = insn->off + MAX_BPF_STACK;
+		} else {
+			src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
+			if (src < 0)
+				return src;
+			mem_off = insn->off;
+		}
+		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+		if (dst < 0)
+			return dst;
+		switch (BPF_SIZE(insn->code)) {
+		case BPF_B:
+			emit_instr(ctx, lbu, dst, mem_off, src);
+			break;
+		case BPF_H:
+			emit_instr(ctx, lhu, dst, mem_off, src);
+			break;
+		case BPF_W:
+			emit_instr(ctx, lw, dst, mem_off, src);
+			break;
+		case BPF_DW:
+			emit_instr(ctx, ld, dst, mem_off, src);
+			break;
+		}
+		break;
+
+	case BPF_STX | BPF_B | BPF_MEM:
+	case BPF_STX | BPF_H | BPF_MEM:
+	case BPF_STX | BPF_W | BPF_MEM:
+	case BPF_STX | BPF_DW | BPF_MEM:
+	case BPF_STX | BPF_W | BPF_XADD:
+	case BPF_STX | BPF_DW | BPF_XADD:
+		if (insn->dst_reg == BPF_REG_10) {
+			ctx->flags |= EBPF_SEEN_FP;
+			dst = MIPS_R_SP;
+			mem_off = insn->off + MAX_BPF_STACK;
+		} else {
+			dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
+			if (dst < 0)
+				return dst;
+			mem_off = insn->off;
+		}
+		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
+		if (src < 0)
+			return dst;
+		if (BPF_MODE(insn->code) == BPF_XADD) {
+			switch (BPF_SIZE(insn->code)) {
+			case BPF_W:
+				if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) {
+					emit_instr(ctx, sll, MIPS_R_AT, src, 0);
+					src = MIPS_R_AT;
+				}
+				emit_instr(ctx, ll, MIPS_R_T8, mem_off, dst);
+				emit_instr(ctx, addu, MIPS_R_T8, MIPS_R_T8, src);
+				emit_instr(ctx, sc, MIPS_R_T8, mem_off, dst);
+				/*
+				 * On failure back up to LL (-4
+				 * instructions of 4 bytes each
+				 */
+				emit_instr(ctx, beq, MIPS_R_T8, MIPS_R_ZERO, -4 * 4);
+				emit_instr(ctx, nop);
+				break;
+			case BPF_DW:
+				if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) {
+					emit_instr(ctx, daddu, MIPS_R_AT, src, MIPS_R_ZERO);
+					emit_instr(ctx, dinsu, MIPS_R_AT, MIPS_R_ZERO, 32, 32);
+					src = MIPS_R_AT;
+				}
+				emit_instr(ctx, lld, MIPS_R_T8, mem_off, dst);
+				emit_instr(ctx, daddu, MIPS_R_T8, MIPS_R_T8, src);
+				emit_instr(ctx, scd, MIPS_R_T8, mem_off, dst);
+				emit_instr(ctx, beq, MIPS_R_T8, MIPS_R_ZERO, -4 * 4);
+				emit_instr(ctx, nop);
+				break;
+			}
+		} else { /* BPF_MEM */
+			switch (BPF_SIZE(insn->code)) {
+			case BPF_B:
+				emit_instr(ctx, sb, src, mem_off, dst);
+				break;
+			case BPF_H:
+				emit_instr(ctx, sh, src, mem_off, dst);
+				break;
+			case BPF_W:
+				emit_instr(ctx, sw, src, mem_off, dst);
+				break;
+			case BPF_DW:
+				if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) {
+					emit_instr(ctx, daddu, MIPS_R_AT, src, MIPS_R_ZERO);
+					emit_instr(ctx, dinsu, MIPS_R_AT, MIPS_R_ZERO, 32, 32);
+					src = MIPS_R_AT;
+				}
+				emit_instr(ctx, sd, src, mem_off, dst);
+				break;
+			}
+		}
+		break;
+
+	default:
+		pr_err("NOT HANDLED %d - (%02x)\n",
+		       this_idx, (unsigned int)insn->code);
+		return -EINVAL;
+	}
+	return 1;
+}
+
+#define RVT_VISITED_MASK 0xc000000000000000ull
+#define RVT_FALL_THROUGH 0x4000000000000000ull
+#define RVT_BRANCH_TAKEN 0x8000000000000000ull
+#define RVT_DONE (RVT_FALL_THROUGH | RVT_BRANCH_TAKEN)
+
+static int build_int_body(struct jit_ctx *ctx)
+{
+	const struct bpf_prog *prog = ctx->skf;
+	const struct bpf_insn *insn;
+	int i, r;
+
+	for (i = 0; i < prog->len; ) {
+		insn = prog->insnsi + i;
+		if ((ctx->reg_val_types[i] & RVT_VISITED_MASK) == 0) {
+			/* dead instruction, don't emit it. */
+			i++;
+			continue;
+		}
+
+		if (ctx->target == NULL)
+			ctx->offsets[i] = (ctx->offsets[i] & OFFSETS_B_CONV) | (ctx->idx * 4);
+
+		r = build_one_insn(insn, ctx, i, prog->len);
+		if (r < 0)
+			return r;
+		i += r;
+	}
+	/* epilogue offset */
+	if (ctx->target == NULL)
+		ctx->offsets[i] = ctx->idx * 4;
+
+	/*
+	 * All exits have an offset of the epilogue, some offsets may
+	 * not have been set due to banch-around threading, so set
+	 * them now.
+	 */
+	if (ctx->target == NULL)
+		for (i = 0; i < prog->len; i++) {
+			insn = prog->insnsi + i;
+			if (insn->code == (BPF_JMP | BPF_EXIT))
+				ctx->offsets[i] = ctx->idx * 4;
+		}
+	return 0;
+}
+
+/* return the last idx processed, or negative for error */
+static int reg_val_propagate_range(struct jit_ctx *ctx, u64 initial_rvt,
+				   int start_idx, bool follow_taken)
+{
+	const struct bpf_prog *prog = ctx->skf;
+	const struct bpf_insn *insn;
+	u64 exit_rvt = initial_rvt;
+	u64 *rvt = ctx->reg_val_types;
+	int idx;
+	int reg;
+
+	for (idx = start_idx; idx < prog->len; idx++) {
+		rvt[idx] = (rvt[idx] & RVT_VISITED_MASK) | exit_rvt;
+		insn = prog->insnsi + idx;
+		switch (BPF_CLASS(insn->code)) {
+		case BPF_ALU:
+			switch (BPF_OP(insn->code)) {
+			case BPF_ADD:
+			case BPF_SUB:
+			case BPF_MUL:
+			case BPF_DIV:
+			case BPF_OR:
+			case BPF_AND:
+			case BPF_LSH:
+			case BPF_RSH:
+			case BPF_NEG:
+			case BPF_MOD:
+			case BPF_XOR:
+				set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT);
+				break;
+			case BPF_MOV:
+				if (BPF_SRC(insn->code)) {
+					set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT);
+				} else {
+					/* IMM to REG move*/
+					if (insn->imm >= 0)
+						set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS);
+					else
+						set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT);
+				}
+				break;
+			case BPF_END:
+				if (insn->imm == 64)
+					set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT);
+				else if (insn->imm == 32)
+					set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT);
+				else /* insn->imm == 16 */
+					set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS);
+				break;
+			}
+			rvt[idx] |= RVT_DONE;
+			break;
+		case BPF_ALU64:
+			switch (BPF_OP(insn->code)) {
+			case BPF_MOV:
+				if (BPF_SRC(insn->code)) {
+					/* REG to REG move*/
+					set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT);
+				} else {
+					/* IMM to REG move*/
+					if (insn->imm >= 0)
+						set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS);
+					else
+						set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT_32BIT);
+				}
+				break;
+			default:
+				set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT);
+			}
+			rvt[idx] |= RVT_DONE;
+			break;
+		case BPF_LD:
+			switch (BPF_SIZE(insn->code)) {
+			case BPF_DW:
+				if (BPF_MODE(insn->code) == BPF_IMM) {
+					s64 val;
+
+					val = (s64)((u32)insn->imm | ((u64)(insn + 1)->imm << 32));
+					if (val > 0 && val <= S32_MAX)
+						set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS);
+					else if (val >= S32_MIN && val <= S32_MAX)
+						set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT_32BIT);
+					else
+						set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT);
+					rvt[idx] |= RVT_DONE;
+					idx++;
+				} else {
+					set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT);
+				}
+				break;
+			case BPF_B:
+			case BPF_H:
+				set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS);
+				break;
+			case BPF_W:
+				if (BPF_MODE(insn->code) == BPF_IMM)
+					set_reg_val_type(&exit_rvt, insn->dst_reg,
+							 insn->imm >= 0 ? REG_32BIT_POS : REG_32BIT);
+				else
+					set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT);
+				break;
+			}
+			rvt[idx] |= RVT_DONE;
+			break;
+		case BPF_LDX:
+			switch (BPF_SIZE(insn->code)) {
+			case BPF_DW:
+				set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT);
+				break;
+			case BPF_B:
+			case BPF_H:
+				set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS);
+				break;
+			case BPF_W:
+				set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT);
+				break;
+			}
+			rvt[idx] |= RVT_DONE;
+			break;
+		case BPF_JMP:
+			switch (BPF_OP(insn->code)) {
+			case BPF_EXIT:
+				rvt[idx] = RVT_DONE | exit_rvt;
+				rvt[prog->len] = exit_rvt;
+				return idx;
+			case BPF_JA:
+				rvt[idx] |= RVT_DONE;
+				idx += insn->off;
+				break;
+			case BPF_JEQ:
+			case BPF_JGT:
+			case BPF_JGE:
+			case BPF_JSET:
+			case BPF_JNE:
+			case BPF_JSGT:
+			case BPF_JSGE:
+				if (follow_taken) {
+					rvt[idx] |= RVT_BRANCH_TAKEN;
+					idx += insn->off;
+					follow_taken = false;
+				} else {
+					rvt[idx] |= RVT_FALL_THROUGH;
+				}
+				break;
+			case BPF_CALL:
+				set_reg_val_type(&exit_rvt, BPF_REG_0, REG_64BIT);
+				/* Upon call return, argument registers are clobbered. */
+				for (reg = BPF_REG_0; reg <= BPF_REG_5; reg++)
+					set_reg_val_type(&exit_rvt, reg, REG_64BIT);
+
+				rvt[idx] |= RVT_DONE;
+				break;
+			default:
+				WARN(1, "Unhandled BPF_JMP case.\n");
+				rvt[idx] |= RVT_DONE;
+				break;
+			}
+			break;
+		default:
+			rvt[idx] |= RVT_DONE;
+			break;
+		}
+	}
+	return idx;
+}
+
+/*
+ * Track the value range (i.e. 32-bit vs. 64-bit) of each register at
+ * each eBPF insn.  This allows unneeded sign and zero extension
+ * operations to be omitted.
+ *
+ * Doesn't handle yet confluence of control paths with conflicting
+ * ranges, but it is good enough for most sane code.
+ */
+static int reg_val_propagate(struct jit_ctx *ctx)
+{
+	const struct bpf_prog *prog = ctx->skf;
+	u64 exit_rvt;
+	int reg;
+	int i;
+
+	/*
+	 * 11 registers * 3 bits/reg leaves top bits free for other
+	 * uses.  Bit-62..63 used to see if we have visited an insn.
+	 */
+	exit_rvt = 0;
+
+	/* Upon entry, argument registers are 64-bit. */
+	for (reg = BPF_REG_1; reg <= BPF_REG_5; reg++)
+		set_reg_val_type(&exit_rvt, reg, REG_64BIT);
+
+	/*
+	 * First follow all conditional branches on the fall-through
+	 * edge of control flow..
+	 */
+	reg_val_propagate_range(ctx, exit_rvt, 0, false);
+restart_search:
+	/*
+	 * Then repeatedly find the first conditional branch where
+	 * both edges of control flow have not been taken, and follow
+	 * the branch taken edge.  We will end up restarting the
+	 * search once per conditional branch insn.
+	 */
+	for (i = 0; i < prog->len; i++) {
+		u64 rvt = ctx->reg_val_types[i];
+
+		if ((rvt & RVT_VISITED_MASK) == RVT_DONE ||
+		    (rvt & RVT_VISITED_MASK) == 0)
+			continue;
+		if ((rvt & RVT_VISITED_MASK) == RVT_FALL_THROUGH) {
+			reg_val_propagate_range(ctx, rvt & ~RVT_VISITED_MASK, i, true);
+		} else { /* RVT_BRANCH_TAKEN */
+			WARN(1, "Unexpected RVT_BRANCH_TAKEN case.\n");
+			reg_val_propagate_range(ctx, rvt & ~RVT_VISITED_MASK, i, false);
+		}
+		goto restart_search;
+	}
+	/*
+	 * Eventually all conditional branches have been followed on
+	 * both branches and we are done.  Any insn that has not been
+	 * visited at this point is dead.
+	 */
+
+	return 0;
+}
+
+static void jit_fill_hole(void *area, unsigned int size)
+{
+	u32 *p;
+
+	/* We are guaranteed to have aligned memory. */
+	for (p = area; size >= sizeof(u32); size -= sizeof(u32))
+		uasm_i_break(&p, BRK_BUG); /* Increments p */
+}
+
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+{
+	struct bpf_prog *orig_prog = prog;
+	bool tmp_blinded = false;
+	struct bpf_prog *tmp;
+	struct bpf_binary_header *header = NULL;
+	struct jit_ctx ctx;
+	unsigned int image_size;
+	u8 *image_ptr;
+
+	if (!bpf_jit_enable || !cpu_has_mips64r2)
+		return prog;
+
+	tmp = bpf_jit_blind_constants(prog);
+	/* If blinding was requested and we failed during blinding,
+	 * we must fall back to the interpreter.
+	 */
+	if (IS_ERR(tmp))
+		return orig_prog;
+	if (tmp != prog) {
+		tmp_blinded = true;
+		prog = tmp;
+	}
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	ctx.offsets = kcalloc(prog->len + 1, sizeof(*ctx.offsets), GFP_KERNEL);
+	if (ctx.offsets == NULL)
+		goto out_err;
+
+	ctx.reg_val_types = kcalloc(prog->len + 1, sizeof(*ctx.reg_val_types), GFP_KERNEL);
+	if (ctx.reg_val_types == NULL)
+		goto out_err;
+
+	ctx.skf = prog;
+
+	if (reg_val_propagate(&ctx))
+		goto out_err;
+
+	/*
+	 * First pass discovers used resources and instruction offsets
+	 * assuming short branches are used.
+	 */
+	if (build_int_body(&ctx))
+		goto out_err;
+
+	/*
+	 * If no calls are made (EBPF_SAVE_RA), then tail call count
+	 * in $v1, else we must save in n$s4.
+	 */
+	if (ctx.flags & EBPF_SEEN_TC) {
+		if (ctx.flags & EBPF_SAVE_RA)
+			ctx.flags |= EBPF_SAVE_S4;
+		else
+			ctx.flags |= EBPF_TCC_IN_V1;
+	}
+
+	/*
+	 * Second pass generates offsets, if any branches are out of
+	 * range a jump-around long sequence is generated, and we have
+	 * to try again from the beginning to generate the new
+	 * offsets.  This is done until no additional conversions are
+	 * necessary.
+	 */
+	do {
+		ctx.idx = 0;
+		ctx.gen_b_offsets = 1;
+		ctx.long_b_conversion = 0;
+		if (gen_int_prologue(&ctx))
+			goto out_err;
+		if (build_int_body(&ctx))
+			goto out_err;
+		if (build_int_epilogue(&ctx, MIPS_R_RA))
+			goto out_err;
+	} while (ctx.long_b_conversion);
+
+	image_size = 4 * ctx.idx;
+
+	header = bpf_jit_binary_alloc(image_size, &image_ptr,
+				      sizeof(u32), jit_fill_hole);
+	if (header == NULL)
+		goto out_err;
+
+	ctx.target = (u32 *)image_ptr;
+
+	/* Third pass generates the code */
+	ctx.idx = 0;
+	if (gen_int_prologue(&ctx))
+		goto out_err;
+	if (build_int_body(&ctx))
+		goto out_err;
+	if (build_int_epilogue(&ctx, MIPS_R_RA))
+		goto out_err;
+
+	/* Update the icache */
+	flush_icache_range((unsigned long)ctx.target,
+			   (unsigned long)(ctx.target + ctx.idx * sizeof(u32)));
+
+	if (bpf_jit_enable > 1)
+		/* Dump JIT code */
+		bpf_jit_dump(prog->len, image_size, 2, ctx.target);
+
+	bpf_jit_binary_lock_ro(header);
+	prog->bpf_func = (void *)ctx.target;
+	prog->jited = 1;
+	prog->jited_len = image_size;
+out_normal:
+	if (tmp_blinded)
+		bpf_jit_prog_release_other(prog, prog == orig_prog ?
+					   tmp : orig_prog);
+	kfree(ctx.offsets);
+	kfree(ctx.reg_val_types);
+
+	return prog;
+
+out_err:
+	prog = orig_prog;
+	if (header)
+		bpf_jit_binary_free(header);
+	goto out_normal;
+}

arch/mips/pci/pci.c

@@ -28,16 +28,15 @@ EXPORT_SYMBOL(PCIBIOS_MIN_MEM);
 
 static int __init pcibios_set_cache_line_size(void)
 {
-	struct cpuinfo_mips *c = &current_cpu_data;
 	unsigned int lsize;
 
 	/*
 	 * Set PCI cacheline size to that of the highest level in the
 	 * cache hierarchy.
 	 */
-	lsize = c->dcache.linesz;
-	lsize = c->scache.linesz ? : lsize;
-	lsize = c->tcache.linesz ? : lsize;
+	lsize = cpu_dcache_line_size();
+	lsize = cpu_scache_line_size() ? : lsize;
+	lsize = cpu_tcache_line_size() ? : lsize;
 
 	BUG_ON(!lsize);
 

arch/mips/vdso/gettimeofday.c

@@ -35,7 +35,8 @@ static __always_inline long gettimeofday_fallback(struct timeval *_tv,
 	"       syscall\n"
 	: "=r" (ret), "=r" (error)
 	: "r" (tv), "r" (tz), "r" (nr)
-	: "memory");
+	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
+	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
 
 	return error ? -ret : ret;
 }
@@ -55,7 +56,8 @@ static __always_inline long clock_gettime_fallback(clockid_t _clkid,
 	"       syscall\n"
 	: "=r" (ret), "=r" (error)
 	: "r" (clkid), "r" (ts), "r" (nr)
-	: "memory");
+	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
+	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
 
 	return error ? -ret : ret;
 }

arch/powerpc/configs/powernv_defconfig

@@ -293,7 +293,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y

arch/powerpc/configs/ppc64_defconfig

@@ -324,7 +324,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y

arch/powerpc/configs/pseries_defconfig

@@ -291,7 +291,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y

arch/powerpc/kernel/entry_64.S

@@ -223,17 +223,27 @@ system_call_exit:
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	.Lsyscall_exit_work
 
-	/* If MSR_FP and MSR_VEC are set in user msr, then no need to restore */
-	li	r7,MSR_FP
+	andi.	r0,r8,MSR_FP
+	beq 2f
 #ifdef CONFIG_ALTIVEC
-	oris	r7,r7,MSR_VEC@h
+	andis.	r0,r8,MSR_VEC@h
+	bne	3f
 #endif
-	and	r0,r8,r7
-	cmpd	r0,r7
-	bne	.Lsyscall_restore_math
-.Lsyscall_restore_math_cont:
+2:	addi    r3,r1,STACK_FRAME_OVERHEAD
+#ifdef CONFIG_PPC_BOOK3S
+	li	r10,MSR_RI
+	mtmsrd	r10,1		/* Restore RI */
+#endif
+	bl	restore_math
+#ifdef CONFIG_PPC_BOOK3S
+	li	r11,0
+	mtmsrd	r11,1
+#endif
+	ld	r8,_MSR(r1)
+	ld	r3,RESULT(r1)
+	li	r11,-MAX_ERRNO
 
-	cmpld	r3,r11
+3:	cmpld	r3,r11
 	ld	r5,_CCR(r1)
 	bge-	.Lsyscall_error
 .Lsyscall_error_cont:
@@ -267,40 +277,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	std	r5,_CCR(r1)
 	b	.Lsyscall_error_cont
 
-.Lsyscall_restore_math:
-	/*
-	 * Some initial tests from restore_math to avoid the heavyweight
-	 * C code entry and MSR manipulations.
-	 */
-	LOAD_REG_IMMEDIATE(r0, MSR_TS_MASK)
-	and.	r0,r0,r8
-	bne	1f
-
-	ld	r7,PACACURRENT(r13)
-	lbz	r0,THREAD+THREAD_LOAD_FP(r7)
-#ifdef CONFIG_ALTIVEC
-	lbz	r6,THREAD+THREAD_LOAD_VEC(r7)
-	add	r0,r0,r6
-#endif
-	cmpdi	r0,0
-	beq	.Lsyscall_restore_math_cont
-
-1:	addi    r3,r1,STACK_FRAME_OVERHEAD
-#ifdef CONFIG_PPC_BOOK3S
-	li	r10,MSR_RI
-	mtmsrd	r10,1		/* Restore RI */
-#endif
-	bl	restore_math
-#ifdef CONFIG_PPC_BOOK3S
-	li	r11,0
-	mtmsrd	r11,1
-#endif
-	/* Restore volatiles, reload MSR from updated one */
-	ld	r8,_MSR(r1)
-	ld	r3,RESULT(r1)
-	li	r11,-MAX_ERRNO
-	b	.Lsyscall_restore_math_cont
-
 /* Traced system call support */
 .Lsyscall_dotrace:
 	bl	save_nvgprs

arch/powerpc/kernel/process.c

@@ -511,10 +511,6 @@ void restore_math(struct pt_regs *regs)
 {
 	unsigned long msr;
 
-	/*
-	 * Syscall exit makes a similar initial check before branching
-	 * to restore_math. Keep them in synch.
-	 */
 	if (!msr_tm_active(regs->msr) &&
 		!current->thread.load_fp && !loadvec(current->thread))
 		return;

arch/powerpc/kernel/smp.c

@@ -351,7 +351,7 @@ static void nmi_ipi_lock_start(unsigned long *flags)
 	hard_irq_disable();
 	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
 		raw_local_irq_restore(*flags);
-		cpu_relax();
+		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
 		raw_local_irq_save(*flags);
 		hard_irq_disable();
 	}
@@ -360,7 +360,7 @@ static void nmi_ipi_lock_start(unsigned long *flags)
 static void nmi_ipi_lock(void)
 {
 	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
-		cpu_relax();
+		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
 }
 
 static void nmi_ipi_unlock(void)
@@ -475,7 +475,7 @@ int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
 	nmi_ipi_lock_start(&flags);
 	while (nmi_ipi_busy_count) {
 		nmi_ipi_unlock_end(&flags);
-		cpu_relax();
+		spin_until_cond(nmi_ipi_busy_count == 0);
 		nmi_ipi_lock_start(&flags);
 	}
 

arch/powerpc/kernel/watchdog.c

@@ -71,15 +71,20 @@ static inline void wd_smp_lock(unsigned long *flags)
 	 * This may be called from low level interrupt handlers at some
 	 * point in future.
 	 */
-	local_irq_save(*flags);
-	while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock)))
-		cpu_relax();
+	raw_local_irq_save(*flags);
+	hard_irq_disable(); /* Make it soft-NMI safe */
+	while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) {
+		raw_local_irq_restore(*flags);
+		spin_until_cond(!test_bit(0, &__wd_smp_lock));
+		raw_local_irq_save(*flags);
+		hard_irq_disable();
+	}
 }
 
 static inline void wd_smp_unlock(unsigned long *flags)
 {
 	clear_bit_unlock(0, &__wd_smp_lock);
-	local_irq_restore(*flags);
+	raw_local_irq_restore(*flags);
 }
 
 static void wd_lockup_ipi(struct pt_regs *regs)
@@ -96,10 +101,10 @@ static void wd_lockup_ipi(struct pt_regs *regs)
 		nmi_panic(regs, "Hard LOCKUP");
 }
 
-static void set_cpu_stuck(int cpu, u64 tb)
+static void set_cpumask_stuck(const struct cpumask *cpumask, u64 tb)
 {
-	cpumask_set_cpu(cpu, &wd_smp_cpus_stuck);
-	cpumask_clear_cpu(cpu, &wd_smp_cpus_pending);
+	cpumask_or(&wd_smp_cpus_stuck, &wd_smp_cpus_stuck, cpumask);
+	cpumask_andnot(&wd_smp_cpus_pending, &wd_smp_cpus_pending, cpumask);
 	if (cpumask_empty(&wd_smp_cpus_pending)) {
 		wd_smp_last_reset_tb = tb;
 		cpumask_andnot(&wd_smp_cpus_pending,
@@ -107,6 +112,10 @@ static void set_cpu_stuck(int cpu, u64 tb)
 				&wd_smp_cpus_stuck);
 	}
 }
+static void set_cpu_stuck(int cpu, u64 tb)
+{
+	set_cpumask_stuck(cpumask_of(cpu), tb);
+}
 
 static void watchdog_smp_panic(int cpu, u64 tb)
 {
@@ -135,11 +144,9 @@ static void watchdog_smp_panic(int cpu, u64 tb)
 	}
 	smp_flush_nmi_ipi(1000000);
 
-	/* Take the stuck CPU out of the watch group */
-	for_each_cpu(c, &wd_smp_cpus_pending)
-		set_cpu_stuck(c, tb);
+	/* Take the stuck CPUs out of the watch group */
+	set_cpumask_stuck(&wd_smp_cpus_pending, tb);
 
-out:
 	wd_smp_unlock(&flags);
 
 	printk_safe_flush();
@@ -152,6 +159,11 @@ out:
 
 	if (hardlockup_panic)
 		nmi_panic(NULL, "Hard LOCKUP");
+
+	return;
+
+out:
+	wd_smp_unlock(&flags);
 }
 
 static void wd_smp_clear_cpu_pending(int cpu, u64 tb)
@@ -258,9 +270,11 @@ static void wd_timer_fn(unsigned long data)
 
 void arch_touch_nmi_watchdog(void)
 {
+	unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000;
 	int cpu = smp_processor_id();
 
-	watchdog_timer_interrupt(cpu);
+	if (get_tb() - per_cpu(wd_timer_tb, cpu) >= ticks)
+		watchdog_timer_interrupt(cpu);
 }
 EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
@@ -283,6 +297,8 @@ static void stop_watchdog_timer_on(unsigned int cpu)
 
 static int start_wd_on_cpu(unsigned int cpu)
 {
+	unsigned long flags;
+
 	if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) {
 		WARN_ON(1);
 		return 0;
@@ -297,12 +313,14 @@ static int start_wd_on_cpu(unsigned int cpu)
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
 		return 0;
 
+	wd_smp_lock(&flags);
 	cpumask_set_cpu(cpu, &wd_cpus_enabled);
 	if (cpumask_weight(&wd_cpus_enabled) == 1) {
 		cpumask_set_cpu(cpu, &wd_smp_cpus_pending);
 		wd_smp_last_reset_tb = get_tb();
 	}
-	smp_wmb();
+	wd_smp_unlock(&flags);
+
 	start_watchdog_timer_on(cpu);
 
 	return 0;
@@ -310,12 +328,17 @@ static int start_wd_on_cpu(unsigned int cpu)
 
 static int stop_wd_on_cpu(unsigned int cpu)
 {
+	unsigned long flags;
+
 	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
 		return 0; /* Can happen in CPU unplug case */
 
 	stop_watchdog_timer_on(cpu);
 
+	wd_smp_lock(&flags);
 	cpumask_clear_cpu(cpu, &wd_cpus_enabled);
+	wd_smp_unlock(&flags);
+
 	wd_smp_clear_cpu_pending(cpu, get_tb());
 
 	return 0;

arch/powerpc/platforms/powernv/idle.c

@@ -56,6 +56,7 @@ u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
  */
 static u64 pnv_deepest_stop_psscr_val;
 static u64 pnv_deepest_stop_psscr_mask;
+static u64 pnv_deepest_stop_flag;
 static bool deepest_stop_found;
 
 static int pnv_save_sprs_for_deep_states(void)
@@ -185,8 +186,40 @@ static void pnv_alloc_idle_core_states(void)
 
 	update_subcore_sibling_mask();
 
-	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
-		pnv_save_sprs_for_deep_states();
+	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) {
+		int rc = pnv_save_sprs_for_deep_states();
+
+		if (likely(!rc))
+			return;
+
+		/*
+		 * The stop-api is unable to restore hypervisor
+		 * resources on wakeup from platform idle states which
+		 * lose full context. So disable such states.
+		 */
+		supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT;
+		pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n");
+		pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");
+
+		if (cpu_has_feature(CPU_FTR_ARCH_300) &&
+		    (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
+			/*
+			 * Use the default stop state for CPU-Hotplug
+			 * if available.
+			 */
+			if (default_stop_found) {
+				pnv_deepest_stop_psscr_val =
+					pnv_default_stop_val;
+				pnv_deepest_stop_psscr_mask =
+					pnv_default_stop_mask;
+				pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
+					pnv_deepest_stop_psscr_val);
+			} else { /* Fallback to snooze loop for CPU-Hotplug */
+				deepest_stop_found = false;
+				pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
+			}
+		}
+	}
 }
 
 u32 pnv_get_supported_cpuidle_states(void)
@@ -375,7 +408,8 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 						pnv_deepest_stop_psscr_val;
 		srr1 = power9_idle_stop(psscr);
 
-	} else if (idle_states & OPAL_PM_WINKLE_ENABLED) {
+	} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
+		   (idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
 		srr1 = power7_idle_insn(PNV_THREAD_WINKLE);
 	} else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
 		   (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
@@ -553,6 +587,7 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
 			max_residency_ns = residency_ns[i];
 			pnv_deepest_stop_psscr_val = psscr_val[i];
 			pnv_deepest_stop_psscr_mask = psscr_mask[i];
+			pnv_deepest_stop_flag = flags[i];
 			deepest_stop_found = true;
 		}
 

arch/s390/include/asm/tlb.h

@@ -47,10 +47,9 @@ struct mmu_table_batch {
 extern void tlb_table_flush(struct mmu_gather *tlb);
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
-static inline void tlb_gather_mmu(struct mmu_gather *tlb,
-				  struct mm_struct *mm,
-				  unsigned long start,
-				  unsigned long end)
+static inline void
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->start = start;
@@ -76,9 +75,15 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 	tlb_flush_mmu_free(tlb);
 }
 
-static inline void tlb_finish_mmu(struct mmu_gather *tlb,
-				  unsigned long start, unsigned long end)
+static inline void
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
+	if (force) {
+		tlb->start = start;
+		tlb->end = end;
+	}
+
 	tlb_flush_mmu(tlb);
 }
 

arch/s390/net/bpf_jit_comp.c

@@ -1253,7 +1253,8 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 		insn_count = bpf_jit_insn(jit, fp, i);
 		if (insn_count < 0)
 			return -1;
-		jit->addrs[i + 1] = jit->prg; /* Next instruction address */
+		/* Next instruction address */
+		jit->addrs[i + insn_count] = jit->prg;
 	}
 	bpf_jit_epilogue(jit);
 

arch/sh/include/asm/tlb.h

@@ -36,7 +36,8 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+		unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->start = start;
@@ -47,9 +48,10 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
 }
 
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
-	if (tlb->fullmm)
+	if (tlb->fullmm || force)
 		flush_tlb_mm(tlb->mm);
 
 	/* keep the page table cache within bounds */

arch/sparc/include/asm/spitfire.h

@@ -47,10 +47,26 @@
 #define SUN4V_CHIP_NIAGARA5	0x05
 #define SUN4V_CHIP_SPARC_M6	0x06
 #define SUN4V_CHIP_SPARC_M7	0x07
+#define SUN4V_CHIP_SPARC_M8	0x08
 #define SUN4V_CHIP_SPARC64X	0x8a
 #define SUN4V_CHIP_SPARC_SN	0x8b
 #define SUN4V_CHIP_UNKNOWN	0xff
 
+/*
+ * The following CPU_ID_xxx constants are used
+ * to identify the CPU type in the setup phase
+ * (see head_64.S)
+ */
+#define CPU_ID_NIAGARA1		('1')
+#define CPU_ID_NIAGARA2		('2')
+#define CPU_ID_NIAGARA3		('3')
+#define CPU_ID_NIAGARA4		('4')
+#define CPU_ID_NIAGARA5		('5')
+#define CPU_ID_M6		('6')
+#define CPU_ID_M7		('7')
+#define CPU_ID_M8		('8')
+#define CPU_ID_SONOMA1		('N')
+
 #ifndef __ASSEMBLY__
 
 enum ultra_tlb_layout {

arch/sparc/kernel/cpu.c

@@ -506,6 +506,12 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "sparc-m7";
 		break;
 
+	case SUN4V_CHIP_SPARC_M8:
+		sparc_cpu_type = "SPARC-M8";
+		sparc_fpu_type = "SPARC-M8 integrated FPU";
+		sparc_pmu_type = "sparc-m8";
+		break;
+
 	case SUN4V_CHIP_SPARC_SN:
 		sparc_cpu_type = "SPARC-SN";
 		sparc_fpu_type = "SPARC-SN integrated FPU";

arch/sparc/kernel/cpumap.c

@@ -328,6 +328,7 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	case SUN4V_CHIP_NIAGARA5:
 	case SUN4V_CHIP_SPARC_M6:
 	case SUN4V_CHIP_SPARC_M7:
+	case SUN4V_CHIP_SPARC_M8:
 	case SUN4V_CHIP_SPARC_SN:
 	case SUN4V_CHIP_SPARC64X:
 		rover_inc_table = niagara_iterate_method;

arch/sparc/kernel/head_64.S

@@ -424,22 +424,25 @@ EXPORT_SYMBOL(sun4v_chip_type)
 	 nop
 
 70:	ldub	[%g1 + 7], %g2
-	cmp	%g2, '3'
+	cmp	%g2, CPU_ID_NIAGARA3
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA3, %g4
-	cmp	%g2, '4'
+	cmp	%g2, CPU_ID_NIAGARA4
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA4, %g4
-	cmp	%g2, '5'
+	cmp	%g2, CPU_ID_NIAGARA5
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA5, %g4
-	cmp	%g2, '6'
+	cmp	%g2, CPU_ID_M6
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_SPARC_M6, %g4
-	cmp	%g2, '7'
+	cmp	%g2, CPU_ID_M7
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_SPARC_M7, %g4
-	cmp	%g2, 'N'
+	cmp	%g2, CPU_ID_M8
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M8, %g4
+	cmp	%g2, CPU_ID_SONOMA1
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_SPARC_SN, %g4
 	ba,pt	%xcc, 49f
@@ -448,10 +451,10 @@ EXPORT_SYMBOL(sun4v_chip_type)
 91:	sethi	%hi(prom_cpu_compatible), %g1
 	or	%g1, %lo(prom_cpu_compatible), %g1
 	ldub	[%g1 + 17], %g2
-	cmp	%g2, '1'
+	cmp	%g2, CPU_ID_NIAGARA1
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA1, %g4
-	cmp	%g2, '2'
+	cmp	%g2, CPU_ID_NIAGARA2
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA2, %g4
 	
@@ -600,6 +603,9 @@ niagara_tlb_fixup:
 	be,pt	%xcc, niagara4_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_M7
+	be,pt	%xcc, niagara4_patch
+	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M8
 	be,pt	%xcc, niagara4_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_SN

arch/sparc/kernel/setup_64.c

@@ -288,10 +288,17 @@ static void __init sun4v_patch(void)
 
 	sun4v_patch_2insn_range(&__sun4v_2insn_patch,
 				&__sun4v_2insn_patch_end);
-	if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
-	    sun4v_chip_type == SUN4V_CHIP_SPARC_SN)
+
+	switch (sun4v_chip_type) {
+	case SUN4V_CHIP_SPARC_M7:
+	case SUN4V_CHIP_SPARC_M8:
+	case SUN4V_CHIP_SPARC_SN:
 		sun_m7_patch_2insn_range(&__sun_m7_2insn_patch,
 					 &__sun_m7_2insn_patch_end);
+		break;
+	default:
+		break;
+	}
 
 	sun4v_hvapi_init();
 }
@@ -529,6 +536,7 @@ static void __init init_sparc64_elf_hwcap(void)
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M8 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_SN ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_BLKINIT;
@@ -538,6 +546,7 @@ static void __init init_sparc64_elf_hwcap(void)
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M8 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_SN ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_N2;
@@ -568,6 +577,7 @@ static void __init init_sparc64_elf_hwcap(void)
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M8 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_SN ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
@@ -578,6 +588,7 @@ static void __init init_sparc64_elf_hwcap(void)
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M8 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_SN ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |

arch/sparc/mm/init_64.c

@@ -1944,12 +1944,22 @@ static void __init setup_page_offset(void)
 			break;
 		case SUN4V_CHIP_SPARC_M7:
 		case SUN4V_CHIP_SPARC_SN:
-		default:
 			/* M7 and later support 52-bit virtual addresses.  */
 			sparc64_va_hole_top =    0xfff8000000000000UL;
 			sparc64_va_hole_bottom = 0x0008000000000000UL;
 			max_phys_bits = 49;
 			break;
+		case SUN4V_CHIP_SPARC_M8:
+		default:
+			/* M8 and later support 54-bit virtual addresses.
+			 * However, restricting M8 and above VA bits to 53
+			 * as 4-level page table cannot support more than
+			 * 53 VA bits.
+			 */
+			sparc64_va_hole_top =    0xfff0000000000000UL;
+			sparc64_va_hole_bottom = 0x0010000000000000UL;
+			max_phys_bits = 51;
+			break;
 		}
 	}
 
@@ -2161,6 +2171,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 	 */
 	switch (sun4v_chip_type) {
 	case SUN4V_CHIP_SPARC_M7:
+	case SUN4V_CHIP_SPARC_M8:
 	case SUN4V_CHIP_SPARC_SN:
 		pagecv_flag = 0x00;
 		break;
@@ -2313,6 +2324,7 @@ void __init paging_init(void)
 	 */
 	switch (sun4v_chip_type) {
 	case SUN4V_CHIP_SPARC_M7:
+	case SUN4V_CHIP_SPARC_M8:
 	case SUN4V_CHIP_SPARC_SN:
 		page_cache4v_flag = _PAGE_CP_4V;
 		break;

arch/um/include/asm/tlb.h

@@ -45,7 +45,8 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+		unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->start = start;
@@ -80,13 +81,19 @@ tlb_flush_mmu(struct mmu_gather *tlb)
 	tlb_flush_mmu_free(tlb);
 }
 
-/* tlb_finish_mmu
+/* arch_tlb_finish_mmu
  *	Called at the end of the shootdown operation to free up any resources
  *	that were required.
  */
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
+	if (force) {
+		tlb->start = start;
+		tlb->end = end;
+		tlb->need_flush = 1;
+	}
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */

arch/x86/include/asm/hypervisor.h

@@ -43,6 +43,9 @@ struct hypervisor_x86 {
 
 	/* pin current vcpu to specified physical cpu (run rarely) */
 	void		(*pin_vcpu)(int);
+
+	/* called during init_mem_mapping() to setup early mappings. */
+	void		(*init_mem_mapping)(void);
 };
 
 extern const struct hypervisor_x86 *x86_hyper;
@@ -57,8 +60,15 @@ extern const struct hypervisor_x86 x86_hyper_kvm;
 extern void init_hypervisor_platform(void);
 extern bool hypervisor_x2apic_available(void);
 extern void hypervisor_pin_vcpu(int cpu);
+
+static inline void hypervisor_init_mem_mapping(void)
+{
+	if (x86_hyper && x86_hyper->init_mem_mapping)
+		x86_hyper->init_mem_mapping();
+}
 #else
 static inline void init_hypervisor_platform(void) { }
 static inline bool hypervisor_x2apic_available(void) { return false; }
+static inline void hypervisor_init_mem_mapping(void) { }
 #endif /* CONFIG_HYPERVISOR_GUEST */
 #endif /* _ASM_X86_HYPERVISOR_H */

arch/x86/mm/init.c

@@ -18,6 +18,7 @@
 #include <asm/dma.h>		/* for MAX_DMA_PFN */
 #include <asm/microcode.h>
 #include <asm/kaslr.h>
+#include <asm/hypervisor.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -636,6 +637,8 @@ void __init init_mem_mapping(void)
 	load_cr3(swapper_pg_dir);
 	__flush_tlb_all();
 
+	hypervisor_init_mem_mapping();
+
 	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
 }
 

arch/x86/xen/enlighten_hvm.c

@@ -12,6 +12,7 @@
 #include <asm/setup.h>
 #include <asm/hypervisor.h>
 #include <asm/e820/api.h>
+#include <asm/early_ioremap.h>
 
 #include <asm/xen/cpuid.h>
 #include <asm/xen/hypervisor.h>
@@ -21,38 +22,50 @@
 #include "mmu.h"
 #include "smp.h"
 
-void __ref xen_hvm_init_shared_info(void)
+static unsigned long shared_info_pfn;
+
+void xen_hvm_init_shared_info(void)
 {
 	struct xen_add_to_physmap xatp;
-	u64 pa;
-
-	if (HYPERVISOR_shared_info == &xen_dummy_shared_info) {
-		/*
-		 * Search for a free page starting at 4kB physical address.
-		 * Low memory is preferred to avoid an EPT large page split up
-		 * by the mapping.
-		 * Starting below X86_RESERVE_LOW (usually 64kB) is fine as
-		 * the BIOS used for HVM guests is well behaved and won't
-		 * clobber memory other than the first 4kB.
-		 */
-		for (pa = PAGE_SIZE;
-		     !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) ||
-		     memblock_is_reserved(pa);
-		     pa += PAGE_SIZE)
-			;
-
-		memblock_reserve(pa, PAGE_SIZE);
-		HYPERVISOR_shared_info = __va(pa);
-	}
 
 	xatp.domid = DOMID_SELF;
 	xatp.idx = 0;
 	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = virt_to_pfn(HYPERVISOR_shared_info);
+	xatp.gpfn = shared_info_pfn;
 	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
 		BUG();
 }
 
+static void __init reserve_shared_info(void)
+{
+	u64 pa;
+
+	/*
+	 * Search for a free page starting at 4kB physical address.
+	 * Low memory is preferred to avoid an EPT large page split up
+	 * by the mapping.
+	 * Starting below X86_RESERVE_LOW (usually 64kB) is fine as
+	 * the BIOS used for HVM guests is well behaved and won't
+	 * clobber memory other than the first 4kB.
+	 */
+	for (pa = PAGE_SIZE;
+	     !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) ||
+	     memblock_is_reserved(pa);
+	     pa += PAGE_SIZE)
+		;
+
+	shared_info_pfn = PHYS_PFN(pa);
+
+	memblock_reserve(pa, PAGE_SIZE);
+	HYPERVISOR_shared_info = early_memremap(pa, PAGE_SIZE);
+}
+
+static void __init xen_hvm_init_mem_mapping(void)
+{
+	early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE);
+	HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn));
+}
+
 static void __init init_hvm_pv_info(void)
 {
 	int major, minor;
@@ -153,6 +166,7 @@ static void __init xen_hvm_guest_init(void)
 
 	init_hvm_pv_info();
 
+	reserve_shared_info();
 	xen_hvm_init_shared_info();
 
 	/*
@@ -218,5 +232,6 @@ const struct hypervisor_x86 x86_hyper_xen_hvm = {
 	.init_platform          = xen_hvm_guest_init,
 	.pin_vcpu               = xen_pin_vcpu,
 	.x2apic_available       = xen_x2apic_para_available,
+	.init_mem_mapping	= xen_hvm_init_mem_mapping,
 };
 EXPORT_SYMBOL(x86_hyper_xen_hvm);

arch/xtensa/include/asm/Kbuild

@@ -1,5 +1,6 @@
 generic-y += bug.h
 generic-y += clkdev.h
+generic-y += device.h
 generic-y += div64.h
 generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
@@ -17,6 +18,7 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += param.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += rwsem.h

arch/xtensa/include/asm/device.h

@@ -1,15 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-#ifndef _ASM_XTENSA_DEVICE_H
-#define _ASM_XTENSA_DEVICE_H
-
-struct dev_archdata {
-};
-
-struct pdev_archdata {
-};
-
-#endif /* _ASM_XTENSA_DEVICE_H */

arch/xtensa/include/asm/param.h

@@ -1,18 +0,0 @@
-/*
- * include/asm-xtensa/param.h
- *
- * 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) 2001 - 2005 Tensilica Inc.
- */
-#ifndef _XTENSA_PARAM_H
-#define _XTENSA_PARAM_H
-
-#include <uapi/asm/param.h>
-
-# define HZ		CONFIG_HZ	/* internal timer frequency */
-# define USER_HZ	100		/* for user interfaces in "ticks" */
-# define CLOCKS_PER_SEC (USER_HZ)	/* frequnzy at which times() counts */
-#endif /* _XTENSA_PARAM_H */

arch/xtensa/kernel/xtensa_ksyms.c

@@ -94,13 +94,11 @@ unsigned long __sync_fetch_and_or_4(unsigned long *p, unsigned long v)
 }
 EXPORT_SYMBOL(__sync_fetch_and_or_4);
 
-#ifdef CONFIG_NET
 /*
  * Networking support
  */
 EXPORT_SYMBOL(csum_partial);
 EXPORT_SYMBOL(csum_partial_copy_generic);
-#endif /* CONFIG_NET */
 
 /*
  * Architecture-specific symbols

arch/xtensa/mm/cache.c

@@ -103,6 +103,7 @@ void clear_user_highpage(struct page *page, unsigned long vaddr)
 	clear_page_alias(kvaddr, paddr);
 	preempt_enable();
 }
+EXPORT_SYMBOL(clear_user_highpage);
 
 void copy_user_highpage(struct page *dst, struct page *src,
 			unsigned long vaddr, struct vm_area_struct *vma)
@@ -119,10 +120,7 @@ void copy_user_highpage(struct page *dst, struct page *src,
 	copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr);
 	preempt_enable();
 }
-
-#endif /* DCACHE_WAY_SIZE > PAGE_SIZE */
-
-#if (DCACHE_WAY_SIZE > PAGE_SIZE) && XCHAL_DCACHE_IS_WRITEBACK
+EXPORT_SYMBOL(copy_user_highpage);
 
 /*
  * Any time the kernel writes to a user page cache page, or it is about to
@@ -176,7 +174,7 @@ void flush_dcache_page(struct page *page)
 
 	/* There shouldn't be an entry in the cache for this page anymore. */
 }
-
+EXPORT_SYMBOL(flush_dcache_page);
 
 /*
  * For now, flush the whole cache. FIXME??
@@ -188,6 +186,7 @@ void local_flush_cache_range(struct vm_area_struct *vma,
 	__flush_invalidate_dcache_all();
 	__invalidate_icache_all();
 }
+EXPORT_SYMBOL(local_flush_cache_range);
 
 /* 
  * Remove any entry in the cache for this page. 
@@ -207,8 +206,9 @@ void local_flush_cache_page(struct vm_area_struct *vma, unsigned long address,
 	__flush_invalidate_dcache_page_alias(virt, phys);
 	__invalidate_icache_page_alias(virt, phys);
 }
+EXPORT_SYMBOL(local_flush_cache_page);
 
-#endif
+#endif /* DCACHE_WAY_SIZE > PAGE_SIZE */
 
 void
 update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep)
@@ -225,7 +225,7 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep)
 
 	flush_tlb_page(vma, addr);
 
-#if (DCACHE_WAY_SIZE > PAGE_SIZE) && XCHAL_DCACHE_IS_WRITEBACK
+#if (DCACHE_WAY_SIZE > PAGE_SIZE)
 
 	if (!PageReserved(page) && test_bit(PG_arch_1, &page->flags)) {
 		unsigned long phys = page_to_phys(page);
@@ -256,7 +256,7 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep)
  * flush_dcache_page() on the page.
  */
 
-#if (DCACHE_WAY_SIZE > PAGE_SIZE) && XCHAL_DCACHE_IS_WRITEBACK
+#if (DCACHE_WAY_SIZE > PAGE_SIZE)
 
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		unsigned long vaddr, void *dst, const void *src,

block/bfq-iosched.h

@@ -71,17 +71,29 @@ struct bfq_service_tree {
  *
  * bfq_sched_data is the basic scheduler queue.  It supports three
  * ioprio_classes, and can be used either as a toplevel queue or as an
- * intermediate queue on a hierarchical setup.  @next_in_service
- * points to the active entity of the sched_data service trees that
- * will be scheduled next. It is used to reduce the number of steps
- * needed for each hierarchical-schedule update.
+ * intermediate queue in a hierarchical setup.
  *
  * The supported ioprio_classes are the same as in CFQ, in descending
  * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
  * Requests from higher priority queues are served before all the
  * requests from lower priority queues; among requests of the same
  * queue requests are served according to B-WF2Q+.
- * All the fields are protected by the queue lock of the containing bfqd.
+ *
+ * The schedule is implemented by the service trees, plus the field
+ * @next_in_service, which points to the entity on the active trees
+ * that will be served next, if 1) no changes in the schedule occurs
+ * before the current in-service entity is expired, 2) the in-service
+ * queue becomes idle when it expires, and 3) if the entity pointed by
+ * in_service_entity is not a queue, then the in-service child entity
+ * of the entity pointed by in_service_entity becomes idle on
+ * expiration. This peculiar definition allows for the following
+ * optimization, not yet exploited: while a given entity is still in
+ * service, we already know which is the best candidate for next
+ * service among the other active entitities in the same parent
+ * entity. We can then quickly compare the timestamps of the
+ * in-service entity with those of such best candidate.
+ *
+ * All fields are protected by the lock of the containing bfqd.
  */
 struct bfq_sched_data {
 	/* entity in service */

block/bfq-wf2q.c

@@ -188,21 +188,23 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
 
 /*
  * This function tells whether entity stops being a candidate for next
- * service, according to the following logic.
+ * service, according to the restrictive definition of the field
+ * next_in_service. In particular, this function is invoked for an
+ * entity that is about to be set in service.
  *
- * This function is invoked for an entity that is about to be set in
- * service. If such an entity is a queue, then the entity is no longer
- * a candidate for next service (i.e, a candidate entity to serve
- * after the in-service entity is expired). The function then returns
- * true.
+ * If entity is a queue, then the entity is no longer a candidate for
+ * next service according to the that definition, because entity is
+ * about to become the in-service queue. This function then returns
+ * true if entity is a queue.
  *
- * In contrast, the entity could stil be a candidate for next service
- * if it is not a queue, and has more than one child. In fact, even if
- * one of its children is about to be set in service, other children
- * may still be the next to serve. As a consequence, a non-queue
- * entity is not a candidate for next-service only if it has only one
- * child. And only if this condition holds, then the function returns
- * true for a non-queue entity.
+ * In contrast, entity could still be a candidate for next service if
+ * it is not a queue, and has more than one active child. In fact,
+ * even if one of its children is about to be set in service, other
+ * active children may still be the next to serve, for the parent
+ * entity, even according to the above definition. As a consequence, a
+ * non-queue entity is not a candidate for next-service only if it has
+ * only one active child. And only if this condition holds, then this
+ * function returns true for a non-queue entity.
  */
 static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 {
@@ -213,6 +215,18 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 
 	bfqg = container_of(entity, struct bfq_group, entity);
 
+	/*
+	 * The field active_entities does not always contain the
+	 * actual number of active children entities: it happens to
+	 * not account for the in-service entity in case the latter is
+	 * removed from its active tree (which may get done after
+	 * invoking the function bfq_no_longer_next_in_service in
+	 * bfq_get_next_queue). Fortunately, here, i.e., while
+	 * bfq_no_longer_next_in_service is not yet completed in
+	 * bfq_get_next_queue, bfq_active_extract has not yet been
+	 * invoked, and thus active_entities still coincides with the
+	 * actual number of active entities.
+	 */
 	if (bfqg->active_entities == 1)
 		return true;
 
@@ -954,7 +968,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
  * one of its children receives a new request.
  *
  * Basically, this function updates the timestamps of entity and
- * inserts entity into its active tree, ater possible extracting it
+ * inserts entity into its active tree, ater possibly extracting it
  * from its idle tree.
  */
 static void __bfq_activate_entity(struct bfq_entity *entity,
@@ -1048,7 +1062,7 @@ static void __bfq_requeue_entity(struct bfq_entity *entity)
 		entity->start = entity->finish;
 		/*
 		 * In addition, if the entity had more than one child
-		 * when set in service, then was not extracted from
+		 * when set in service, then it was not extracted from
 		 * the active tree. This implies that the position of
 		 * the entity in the active tree may need to be
 		 * changed now, because we have just updated the start
@@ -1056,9 +1070,8 @@ static void __bfq_requeue_entity(struct bfq_entity *entity)
 		 * time in a moment (the requeueing is then, more
 		 * precisely, a repositioning in this case). To
 		 * implement this repositioning, we: 1) dequeue the
-		 * entity here, 2) update the finish time and
-		 * requeue the entity according to the new
-		 * timestamps below.
+		 * entity here, 2) update the finish time and requeue
+		 * the entity according to the new timestamps below.
 		 */
 		if (entity->tree)
 			bfq_active_extract(st, entity);
@@ -1105,9 +1118,10 @@ static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
 
 
 /**
- * bfq_activate_entity - activate or requeue an entity representing a bfq_queue,
- *			 and activate, requeue or reposition all ancestors
- *			 for which such an update becomes necessary.
+ * bfq_activate_requeue_entity - activate or requeue an entity representing a
+ *				 bfq_queue, and activate, requeue or reposition
+ *				 all ancestors for which such an update becomes
+ *				 necessary.
  * @entity: the entity to activate.
  * @non_blocking_wait_rq: true if this entity was waiting for a request
  * @requeue: true if this is a requeue, which implies that bfqq is
@@ -1135,9 +1149,9 @@ static void bfq_activate_requeue_entity(struct bfq_entity *entity,
  * @ins_into_idle_tree: if false, the entity will not be put into the
  *			idle tree.
  *
- * Deactivates an entity, independently from its previous state.  Must
+ * Deactivates an entity, independently of its previous state.  Must
  * be invoked only if entity is on a service tree. Extracts the entity
- * from that tree, and if necessary and allowed, puts it on the idle
+ * from that tree, and if necessary and allowed, puts it into the idle
  * tree.
  */
 bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
@@ -1158,8 +1172,10 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
 	st = bfq_entity_service_tree(entity);
 	is_in_service = entity == sd->in_service_entity;
 
-	if (is_in_service)
+	if (is_in_service) {
 		bfq_calc_finish(entity, entity->service);
+		sd->in_service_entity = NULL;
+	}
 
 	if (entity->tree == &st->active)
 		bfq_active_extract(st, entity);
@@ -1177,7 +1193,7 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
 /**
  * bfq_deactivate_entity - deactivate an entity representing a bfq_queue.
  * @entity: the entity to deactivate.
- * @ins_into_idle_tree: true if the entity can be put on the idle tree
+ * @ins_into_idle_tree: true if the entity can be put into the idle tree
  */
 static void bfq_deactivate_entity(struct bfq_entity *entity,
 				  bool ins_into_idle_tree,
@@ -1208,16 +1224,29 @@ static void bfq_deactivate_entity(struct bfq_entity *entity,
 			 */
 			bfq_update_next_in_service(sd, NULL);
 
-		if (sd->next_in_service)
+		if (sd->next_in_service || sd->in_service_entity) {
 			/*
-			 * The parent entity is still backlogged,
-			 * because next_in_service is not NULL. So, no
-			 * further upwards deactivation must be
-			 * performed.  Yet, next_in_service has
-			 * changed.  Then the schedule does need to be
-			 * updated upwards.
+			 * The parent entity is still active, because
+			 * either next_in_service or in_service_entity
+			 * is not NULL. So, no further upwards
+			 * deactivation must be performed.  Yet,
+			 * next_in_service has changed.	Then the
+			 * schedule does need to be updated upwards.
+			 *
+			 * NOTE If in_service_entity is not NULL, then
+			 * next_in_service may happen to be NULL,
+			 * although the parent entity is evidently
+			 * active. This happens if 1) the entity
+			 * pointed by in_service_entity is the only
+			 * active entity in the parent entity, and 2)
+			 * according to the definition of
+			 * next_in_service, the in_service_entity
+			 * cannot be considered as
+			 * next_in_service. See the comments on the
+			 * definition of next_in_service for details.
 			 */
 			break;
+		}
 
 		/*
 		 * If we get here, then the parent is no more
@@ -1494,47 +1523,34 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 
 		/*
 		 * If entity is no longer a candidate for next
-		 * service, then we extract it from its active tree,
-		 * for the following reason. To further boost the
-		 * throughput in some special case, BFQ needs to know
-		 * which is the next candidate entity to serve, while
-		 * there is already an entity in service. In this
-		 * respect, to make it easy to compute/update the next
-		 * candidate entity to serve after the current
-		 * candidate has been set in service, there is a case
-		 * where it is necessary to extract the current
-		 * candidate from its service tree. Such a case is
-		 * when the entity just set in service cannot be also
-		 * a candidate for next service. Details about when
-		 * this conditions holds are reported in the comments
-		 * on the function bfq_no_longer_next_in_service()
-		 * invoked below.
+		 * service, then it must be extracted from its active
+		 * tree, so as to make sure that it won't be
+		 * considered when computing next_in_service. See the
+		 * comments on the function
+		 * bfq_no_longer_next_in_service() for details.
 		 */
 		if (bfq_no_longer_next_in_service(entity))
 			bfq_active_extract(bfq_entity_service_tree(entity),
 					   entity);
 
 		/*
-		 * For the same reason why we may have just extracted
-		 * entity from its active tree, we may need to update
-		 * next_in_service for the sched_data of entity too,
-		 * regardless of whether entity has been extracted.
-		 * In fact, even if entity has not been extracted, a
-		 * descendant entity may get extracted. Such an event
-		 * would cause a change in next_in_service for the
-		 * level of the descendant entity, and thus possibly
-		 * back to upper levels.
+		 * Even if entity is not to be extracted according to
+		 * the above check, a descendant entity may get
+		 * extracted in one of the next iterations of this
+		 * loop. Such an event could cause a change in
+		 * next_in_service for the level of the descendant
+		 * entity, and thus possibly back to this level.
 		 *
-		 * We cannot perform the resulting needed update
-		 * before the end of this loop, because, to know which
-		 * is the correct next-to-serve candidate entity for
-		 * each level, we need first to find the leaf entity
-		 * to set in service. In fact, only after we know
-		 * which is the next-to-serve leaf entity, we can
-		 * discover whether the parent entity of the leaf
-		 * entity becomes the next-to-serve, and so on.
+		 * However, we cannot perform the resulting needed
+		 * update of next_in_service for this level before the
+		 * end of the whole loop, because, to know which is
+		 * the correct next-to-serve candidate entity for each
+		 * level, we need first to find the leaf entity to set
+		 * in service. In fact, only after we know which is
+		 * the next-to-serve leaf entity, we can discover
+		 * whether the parent entity of the leaf entity
+		 * becomes the next-to-serve, and so on.
 		 */
-
 	}
 
 	bfqq = bfq_entity_to_bfqq(entity);

block/bio-integrity.c

@@ -387,9 +387,11 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  */
 bool __bio_integrity_endio(struct bio *bio)
 {
-	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status) {
-		struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 
+	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
+	    (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->profile->verify_fn) {
 		INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
 		queue_work(kintegrityd_wq, &bip->bip_work);
 		return false;

block/blk-mq.c

@@ -301,11 +301,12 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 	struct elevator_queue *e = q->elevator;
 	struct request *rq;
 	unsigned int tag;
+	struct blk_mq_ctx *local_ctx = NULL;
 
 	blk_queue_enter_live(q);
 	data->q = q;
 	if (likely(!data->ctx))
-		data->ctx = blk_mq_get_ctx(q);
+		data->ctx = local_ctx = blk_mq_get_ctx(q);
 	if (likely(!data->hctx))
 		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
 	if (op & REQ_NOWAIT)
@@ -324,6 +325,10 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 
 	tag = blk_mq_get_tag(data);
 	if (tag == BLK_MQ_TAG_FAIL) {
+		if (local_ctx) {
+			blk_mq_put_ctx(local_ctx);
+			data->ctx = NULL;
+		}
 		blk_queue_exit(q);
 		return NULL;
 	}
@@ -356,12 +361,12 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 
 	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
 
-	blk_mq_put_ctx(alloc_data.ctx);
-	blk_queue_exit(q);
-
 	if (!rq)
 		return ERR_PTR(-EWOULDBLOCK);
 
+	blk_mq_put_ctx(alloc_data.ctx);
+	blk_queue_exit(q);
+
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
@@ -407,11 +412,11 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 
 	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
 
-	blk_queue_exit(q);
-
 	if (!rq)
 		return ERR_PTR(-EWOULDBLOCK);
 
+	blk_queue_exit(q);
+
 	return rq;
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
@@ -679,8 +684,8 @@ EXPORT_SYMBOL(blk_mq_kick_requeue_list);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q,
 				    unsigned long msecs)
 {
-	kblockd_schedule_delayed_work(&q->requeue_work,
-				      msecs_to_jiffies(msecs));
+	kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work,
+				    msecs_to_jiffies(msecs));
 }
 EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
 

drivers/acpi/spcr.c

@@ -16,6 +16,16 @@
 #include <linux/kernel.h>
 #include <linux/serial_core.h>
 
+/*
+ * Erratum 44 for QDF2432v1 and QDF2400v1 SoCs describes the BUSY bit as
+ * occasionally getting stuck as 1. To avoid the potential for a hang, check
+ * TXFE == 0 instead of BUSY == 1. This may not be suitable for all UART
+ * implementations, so only do so if an affected platform is detected in
+ * parse_spcr().
+ */
+bool qdf2400_e44_present;
+EXPORT_SYMBOL(qdf2400_e44_present);
+
 /*
  * Some Qualcomm Datacenter Technologies SoCs have a defective UART BUSY bit.
  * Detect them by examining the OEM fields in the SPCR header, similiar to PCI
@@ -147,8 +157,30 @@ int __init parse_spcr(bool earlycon)
 		goto done;
 	}
 
-	if (qdf2400_erratum_44_present(&table->header))
-		uart = "qdf2400_e44";
+	/*
+	 * If the E44 erratum is required, then we need to tell the pl011
+	 * driver to implement the work-around.
+	 *
+	 * The global variable is used by the probe function when it
+	 * creates the UARTs, whether or not they're used as a console.
+	 *
+	 * If the user specifies "traditional" earlycon, the qdf2400_e44
+	 * console name matches the EARLYCON_DECLARE() statement, and
+	 * SPCR is not used.  Parameter "earlycon" is false.
+	 *
+	 * If the user specifies "SPCR" earlycon, then we need to update
+	 * the console name so that it also says "qdf2400_e44".  Parameter
+	 * "earlycon" is true.
+	 *
+	 * For consistency, if we change the console name, then we do it
+	 * for everyone, not just earlycon.
+	 */
+	if (qdf2400_erratum_44_present(&table->header)) {
+		qdf2400_e44_present = true;
+		if (earlycon)
+			uart = "qdf2400_e44";
+	}
+
 	if (xgene_8250_erratum_present(table))
 		iotype = "mmio32";
 

drivers/base/firmware_class.c

@@ -30,7 +30,6 @@
 #include <linux/syscore_ops.h>
 #include <linux/reboot.h>
 #include <linux/security.h>
-#include <linux/swait.h>
 
 #include <generated/utsrelease.h>
 
@@ -112,13 +111,13 @@ static inline long firmware_loading_timeout(void)
  * state of the firmware loading.
  */
 struct fw_state {
-	struct swait_queue_head wq;
+	struct completion completion;
 	enum fw_status status;
 };
 
 static void fw_state_init(struct fw_state *fw_st)
 {
-	init_swait_queue_head(&fw_st->wq);
+	init_completion(&fw_st->completion);
 	fw_st->status = FW_STATUS_UNKNOWN;
 }
 
@@ -131,9 +130,7 @@ static int __fw_state_wait_common(struct fw_state *fw_st, long timeout)
 {
 	long ret;
 
-	ret = swait_event_interruptible_timeout(fw_st->wq,
-				__fw_state_is_done(READ_ONCE(fw_st->status)),
-				timeout);
+	ret = wait_for_completion_killable_timeout(&fw_st->completion, timeout);
 	if (ret != 0 && fw_st->status == FW_STATUS_ABORTED)
 		return -ENOENT;
 	if (!ret)
@@ -148,35 +145,34 @@ static void __fw_state_set(struct fw_state *fw_st,
 	WRITE_ONCE(fw_st->status, status);
 
 	if (status == FW_STATUS_DONE || status == FW_STATUS_ABORTED)
-		swake_up(&fw_st->wq);
+		complete_all(&fw_st->completion);
 }
 
 #define fw_state_start(fw_st)					\
 	__fw_state_set(fw_st, FW_STATUS_LOADING)
 #define fw_state_done(fw_st)					\
 	__fw_state_set(fw_st, FW_STATUS_DONE)
+#define fw_state_aborted(fw_st)					\
+	__fw_state_set(fw_st, FW_STATUS_ABORTED)
 #define fw_state_wait(fw_st)					\
 	__fw_state_wait_common(fw_st, MAX_SCHEDULE_TIMEOUT)
 
-#ifndef CONFIG_FW_LOADER_USER_HELPER
-
-#define fw_state_is_aborted(fw_st)	false
-
-#else /* CONFIG_FW_LOADER_USER_HELPER */
-
 static int __fw_state_check(struct fw_state *fw_st, enum fw_status status)
 {
 	return fw_st->status == status;
 }
 
+#define fw_state_is_aborted(fw_st)				\
+	__fw_state_check(fw_st, FW_STATUS_ABORTED)
+
+#ifdef CONFIG_FW_LOADER_USER_HELPER
+
 #define fw_state_aborted(fw_st)					\
 	__fw_state_set(fw_st, FW_STATUS_ABORTED)
 #define fw_state_is_done(fw_st)					\
 	__fw_state_check(fw_st, FW_STATUS_DONE)
 #define fw_state_is_loading(fw_st)				\
 	__fw_state_check(fw_st, FW_STATUS_LOADING)
-#define fw_state_is_aborted(fw_st)				\
-	__fw_state_check(fw_st, FW_STATUS_ABORTED)
 #define fw_state_wait_timeout(fw_st, timeout)			\
 	__fw_state_wait_common(fw_st, timeout)
 
@@ -1200,6 +1196,28 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name,
 	return 1; /* need to load */
 }
 
+/*
+ * Batched requests need only one wake, we need to do this step last due to the
+ * fallback mechanism. The buf is protected with kref_get(), and it won't be
+ * released until the last user calls release_firmware().
+ *
+ * Failed batched requests are possible as well, in such cases we just share
+ * the struct firmware_buf and won't release it until all requests are woken
+ * and have gone through this same path.
+ */
+static void fw_abort_batch_reqs(struct firmware *fw)
+{
+	struct firmware_buf *buf;
+
+	/* Loaded directly? */
+	if (!fw || !fw->priv)
+		return;
+
+	buf = fw->priv;
+	if (!fw_state_is_aborted(&buf->fw_st))
+		fw_state_aborted(&buf->fw_st);
+}
+
 /* called from request_firmware() and request_firmware_work_func() */
 static int
 _request_firmware(const struct firmware **firmware_p, const char *name,
@@ -1243,6 +1261,7 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 
  out:
 	if (ret < 0) {
+		fw_abort_batch_reqs(fw);
 		release_firmware(fw);
 		fw = NULL;
 	}

drivers/block/sunvdc.c

@@ -875,6 +875,56 @@ static void print_version(void)
 		printk(KERN_INFO "%s", version);
 }
 
+struct vdc_check_port_data {
+	int	dev_no;
+	char	*type;
+};
+
+static int vdc_device_probed(struct device *dev, void *arg)
+{
+	struct vio_dev *vdev = to_vio_dev(dev);
+	struct vdc_check_port_data *port_data;
+
+	port_data = (struct vdc_check_port_data *)arg;
+
+	if ((vdev->dev_no == port_data->dev_no) &&
+	    (!(strcmp((char *)&vdev->type, port_data->type))) &&
+		dev_get_drvdata(dev)) {
+		/* This device has already been configured
+		 * by vdc_port_probe()
+		 */
+		return 1;
+	} else {
+		return 0;
+	}
+}
+
+/* Determine whether the VIO device is part of an mpgroup
+ * by locating all the virtual-device-port nodes associated
+ * with the parent virtual-device node for the VIO device
+ * and checking whether any of these nodes are vdc-ports
+ * which have already been configured.
+ *
+ * Returns true if this device is part of an mpgroup and has
+ * already been probed.
+ */
+static bool vdc_port_mpgroup_check(struct vio_dev *vdev)
+{
+	struct vdc_check_port_data port_data;
+	struct device *dev;
+
+	port_data.dev_no = vdev->dev_no;
+	port_data.type = (char *)&vdev->type;
+
+	dev = device_find_child(vdev->dev.parent, &port_data,
+				vdc_device_probed);
+
+	if (dev)
+		return true;
+
+	return false;
+}
+
 static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 {
 	struct mdesc_handle *hp;
@@ -893,6 +943,14 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 		goto err_out_release_mdesc;
 	}
 
+	/* Check if this device is part of an mpgroup */
+	if (vdc_port_mpgroup_check(vdev)) {
+		printk(KERN_WARNING
+			"VIO: Ignoring extra vdisk port %s",
+			dev_name(&vdev->dev));
+		goto err_out_release_mdesc;
+	}
+
 	port = kzalloc(sizeof(*port), GFP_KERNEL);
 	err = -ENOMEM;
 	if (!port) {
@@ -943,6 +1001,9 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	if (err)
 		goto err_out_free_tx_ring;
 
+	/* Note that the device driver_data is used to determine
+	 * whether the port has been probed.
+	 */
 	dev_set_drvdata(&vdev->dev, port);
 
 	mdesc_release(hp);

drivers/block/zram/zram_drv.c

@@ -308,7 +308,7 @@ static ssize_t comp_algorithm_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
 	struct zram *zram = dev_to_zram(dev);
-	char compressor[CRYPTO_MAX_ALG_NAME];
+	char compressor[ARRAY_SIZE(zram->compressor)];
 	size_t sz;
 
 	strlcpy(compressor, buf, sizeof(compressor));
@@ -327,7 +327,7 @@ static ssize_t comp_algorithm_store(struct device *dev,
 		return -EBUSY;
 	}
 
-	strlcpy(zram->compressor, compressor, sizeof(compressor));
+	strcpy(zram->compressor, compressor);
 	up_write(&zram->init_lock);
 	return len;
 }

drivers/char/random.c

@@ -1492,7 +1492,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
 #ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM
 	print_once = true;
 #endif
-	pr_notice("random: %s called from %pF with crng_init=%d\n",
+	pr_notice("random: %s called from %pS with crng_init=%d\n",
 		  func_name, caller, crng_init);
 }
 

drivers/cpuidle/cpuidle-powernv.c

@@ -235,6 +235,7 @@ static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len,
 	return -1;
 }
 
+extern u32 pnv_get_supported_cpuidle_states(void);
 static int powernv_add_idle_states(void)
 {
 	struct device_node *power_mgt;
@@ -248,6 +249,8 @@ static int powernv_add_idle_states(void)
 	const char *names[CPUIDLE_STATE_MAX];
 	u32 has_stop_states = 0;
 	int i, rc;
+	u32 supported_flags = pnv_get_supported_cpuidle_states();
+
 
 	/* Currently we have snooze statically defined */
 
@@ -362,6 +365,13 @@ static int powernv_add_idle_states(void)
 	for (i = 0; i < dt_idle_states; i++) {
 		unsigned int exit_latency, target_residency;
 		bool stops_timebase = false;
+
+		/*
+		 * Skip the platform idle state whose flag isn't in
+		 * the supported_cpuidle_states flag mask.
+		 */
+		if ((flags[i] & supported_flags) != flags[i])
+			continue;
 		/*
 		 * If an idle state has exit latency beyond
 		 * POWERNV_THRESHOLD_LATENCY_NS then don't use it

drivers/crypto/inside-secure/safexcel_hash.c

@@ -883,10 +883,7 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 	if (ret)
 		return ret;
 
-	memcpy(ctx->ipad, &istate.state, SHA1_DIGEST_SIZE);
-	memcpy(ctx->opad, &ostate.state, SHA1_DIGEST_SIZE);
-
-	for (i = 0; i < ARRAY_SIZE(istate.state); i++) {
+	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++) {
 		if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) ||
 		    ctx->opad[i] != le32_to_cpu(ostate.state[i])) {
 			ctx->base.needs_inv = true;
@@ -894,6 +891,9 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 		}
 	}
 
+	memcpy(ctx->ipad, &istate.state, SHA1_DIGEST_SIZE);
+	memcpy(ctx->opad, &ostate.state, SHA1_DIGEST_SIZE);
+
 	return 0;
 }
 

drivers/dma-buf/sync_file.c

@@ -304,7 +304,7 @@ static int sync_file_release(struct inode *inode, struct file *file)
 {
 	struct sync_file *sync_file = file->private_data;
 
-	if (test_bit(POLL_ENABLED, &sync_file->fence->flags))
+	if (test_bit(POLL_ENABLED, &sync_file->flags))
 		dma_fence_remove_callback(sync_file->fence, &sync_file->cb);
 	dma_fence_put(sync_file->fence);
 	kfree(sync_file);
@@ -318,7 +318,8 @@ static unsigned int sync_file_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &sync_file->wq, wait);
 
-	if (!test_and_set_bit(POLL_ENABLED, &sync_file->fence->flags)) {
+	if (list_empty(&sync_file->cb.node) &&
+	    !test_and_set_bit(POLL_ENABLED, &sync_file->flags)) {
 		if (dma_fence_add_callback(sync_file->fence, &sync_file->cb,
 					   fence_check_cb_func) < 0)
 			wake_up_all(&sync_file->wq);

drivers/gpu/drm/bridge/tc358767.c

@@ -1255,7 +1255,7 @@ static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id)
 
 	/* port@2 is the output port */
 	ret = drm_of_find_panel_or_bridge(dev->of_node, 2, 0, &tc->panel, NULL);
-	if (ret)
+	if (ret && ret != -ENODEV)
 		return ret;
 
 	/* Shut down GPIO is optional */

drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c

@@ -270,8 +270,8 @@ static int submit_reloc(struct etnaviv_gem_submit *submit, void *stream,
 		if (ret)
 			return ret;
 
-		if (r->reloc_offset >= bo->obj->base.size - sizeof(*ptr)) {
-			DRM_ERROR("relocation %u outside object", i);
+		if (r->reloc_offset > bo->obj->base.size - sizeof(*ptr)) {
+			DRM_ERROR("relocation %u outside object\n", i);
 			return -EINVAL;
 		}
 

drivers/gpu/drm/exynos/exynos_drm_fb.c

@@ -145,13 +145,19 @@ static struct drm_framebuffer *
 exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		      const struct drm_mode_fb_cmd2 *mode_cmd)
 {
+	const struct drm_format_info *info = drm_get_format_info(dev, mode_cmd);
 	struct exynos_drm_gem *exynos_gem[MAX_FB_BUFFER];
 	struct drm_gem_object *obj;
 	struct drm_framebuffer *fb;
 	int i;
 	int ret;
 
-	for (i = 0; i < drm_format_num_planes(mode_cmd->pixel_format); i++) {
+	for (i = 0; i < info->num_planes; i++) {
+		unsigned int height = (i == 0) ? mode_cmd->height :
+				     DIV_ROUND_UP(mode_cmd->height, info->vsub);
+		unsigned long size = height * mode_cmd->pitches[i] +
+				     mode_cmd->offsets[i];
+
 		obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[i]);
 		if (!obj) {
 			DRM_ERROR("failed to lookup gem object\n");
@@ -160,6 +166,12 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		}
 
 		exynos_gem[i] = to_exynos_gem(obj);
+
+		if (size > exynos_gem[i]->size) {
+			i++;
+			ret = -EINVAL;
+			goto err;
+		}
 	}
 
 	fb = exynos_drm_framebuffer_init(dev, mode_cmd, exynos_gem, i);

drivers/gpu/drm/i915/gvt/execlist.c

@@ -46,6 +46,8 @@
 #define same_context(a, b) (((a)->context_id == (b)->context_id) && \
 		((a)->lrca == (b)->lrca))
 
+static void clean_workloads(struct intel_vgpu *vgpu, unsigned long engine_mask);
+
 static int context_switch_events[] = {
 	[RCS] = RCS_AS_CONTEXT_SWITCH,
 	[BCS] = BCS_AS_CONTEXT_SWITCH,
@@ -499,10 +501,10 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 static int complete_execlist_workload(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
-	struct intel_vgpu_execlist *execlist =
-		&vgpu->execlist[workload->ring_id];
+	int ring_id = workload->ring_id;
+	struct intel_vgpu_execlist *execlist = &vgpu->execlist[ring_id];
 	struct intel_vgpu_workload *next_workload;
-	struct list_head *next = workload_q_head(vgpu, workload->ring_id)->next;
+	struct list_head *next = workload_q_head(vgpu, ring_id)->next;
 	bool lite_restore = false;
 	int ret;
 
@@ -512,10 +514,25 @@ static int complete_execlist_workload(struct intel_vgpu_workload *workload)
 	release_shadow_batch_buffer(workload);
 	release_shadow_wa_ctx(&workload->wa_ctx);
 
-	if (workload->status || vgpu->resetting)
+	if (workload->status || (vgpu->resetting_eng & ENGINE_MASK(ring_id))) {
+		/* if workload->status is not successful means HW GPU
+		 * has occurred GPU hang or something wrong with i915/GVT,
+		 * and GVT won't inject context switch interrupt to guest.
+		 * So this error is a vGPU hang actually to the guest.
+		 * According to this we should emunlate a vGPU hang. If
+		 * there are pending workloads which are already submitted
+		 * from guest, we should clean them up like HW GPU does.
+		 *
+		 * if it is in middle of engine resetting, the pending
+		 * workloads won't be submitted to HW GPU and will be
+		 * cleaned up during the resetting process later, so doing
+		 * the workload clean up here doesn't have any impact.
+		 **/
+		clean_workloads(vgpu, ENGINE_MASK(ring_id));
 		goto out;
+	}
 
-	if (!list_empty(workload_q_head(vgpu, workload->ring_id))) {
+	if (!list_empty(workload_q_head(vgpu, ring_id))) {
 		struct execlist_ctx_descriptor_format *this_desc, *next_desc;
 
 		next_workload = container_of(next,

drivers/gpu/drm/i915/gvt/firmware.c

@@ -72,11 +72,13 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt)
 	struct intel_gvt_device_info *info = &gvt->device_info;
 	struct pci_dev *pdev = gvt->dev_priv->drm.pdev;
 	struct intel_gvt_mmio_info *e;
+	struct gvt_mmio_block *block = gvt->mmio.mmio_block;
+	int num = gvt->mmio.num_mmio_block;
 	struct gvt_firmware_header *h;
 	void *firmware;
 	void *p;
 	unsigned long size, crc32_start;
-	int i;
+	int i, j;
 	int ret;
 
 	size = sizeof(*h) + info->mmio_size + info->cfg_space_size;
@@ -105,6 +107,13 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt)
 	hash_for_each(gvt->mmio.mmio_info_table, i, e, node)
 		*(u32 *)(p + e->offset) = I915_READ_NOTRACE(_MMIO(e->offset));
 
+	for (i = 0; i < num; i++, block++) {
+		for (j = 0; j < block->size; j += 4)
+			*(u32 *)(p + INTEL_GVT_MMIO_OFFSET(block->offset) + j) =
+				I915_READ_NOTRACE(_MMIO(INTEL_GVT_MMIO_OFFSET(
+							block->offset) + j));
+	}
+
 	memcpy(gvt->firmware.mmio, p, info->mmio_size);
 
 	crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4;

drivers/gpu/drm/i915/gvt/gvt.h

@@ -149,7 +149,7 @@ struct intel_vgpu {
 	bool active;
 	bool pv_notified;
 	bool failsafe;
-	bool resetting;
+	unsigned int resetting_eng;
 	void *sched_data;
 	struct vgpu_sched_ctl sched_ctl;
 
@@ -195,6 +195,15 @@ struct intel_gvt_fence {
 	unsigned long vgpu_allocated_fence_num;
 };
 
+/* Special MMIO blocks. */
+struct gvt_mmio_block {
+	unsigned int device;
+	i915_reg_t   offset;
+	unsigned int size;
+	gvt_mmio_func read;
+	gvt_mmio_func write;
+};
+
 #define INTEL_GVT_MMIO_HASH_BITS 11
 
 struct intel_gvt_mmio {
@@ -214,6 +223,9 @@ struct intel_gvt_mmio {
 /* This reg could be accessed by unaligned address */
 #define F_UNALIGN	(1 << 6)
 
+	struct gvt_mmio_block *mmio_block;
+	unsigned int num_mmio_block;
+
 	DECLARE_HASHTABLE(mmio_info_table, INTEL_GVT_MMIO_HASH_BITS);
 	unsigned int num_tracked_mmio;
 };

drivers/gpu/drm/i915/gvt/handlers.c

@@ -2857,31 +2857,15 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	return 0;
 }
 
-/* Special MMIO blocks. */
-static struct gvt_mmio_block {
-	unsigned int device;
-	i915_reg_t   offset;
-	unsigned int size;
-	gvt_mmio_func read;
-	gvt_mmio_func write;
-} gvt_mmio_blocks[] = {
-	{D_SKL_PLUS, _MMIO(CSR_MMIO_START_RANGE), 0x3000, NULL, NULL},
-	{D_ALL, _MMIO(MCHBAR_MIRROR_BASE_SNB), 0x40000, NULL, NULL},
-	{D_ALL, _MMIO(VGT_PVINFO_PAGE), VGT_PVINFO_SIZE,
-		pvinfo_mmio_read, pvinfo_mmio_write},
-	{D_ALL, LGC_PALETTE(PIPE_A, 0), 1024, NULL, NULL},
-	{D_ALL, LGC_PALETTE(PIPE_B, 0), 1024, NULL, NULL},
-	{D_ALL, LGC_PALETTE(PIPE_C, 0), 1024, NULL, NULL},
-};
-
 static struct gvt_mmio_block *find_mmio_block(struct intel_gvt *gvt,
 					      unsigned int offset)
 {
 	unsigned long device = intel_gvt_get_device_type(gvt);
-	struct gvt_mmio_block *block = gvt_mmio_blocks;
+	struct gvt_mmio_block *block = gvt->mmio.mmio_block;
+	int num = gvt->mmio.num_mmio_block;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(gvt_mmio_blocks); i++, block++) {
+	for (i = 0; i < num; i++, block++) {
 		if (!(device & block->device))
 			continue;
 		if (offset >= INTEL_GVT_MMIO_OFFSET(block->offset) &&
@@ -2912,6 +2896,17 @@ void intel_gvt_clean_mmio_info(struct intel_gvt *gvt)
 	gvt->mmio.mmio_attribute = NULL;
 }
 
+/* Special MMIO blocks. */
+static struct gvt_mmio_block mmio_blocks[] = {
+	{D_SKL_PLUS, _MMIO(CSR_MMIO_START_RANGE), 0x3000, NULL, NULL},
+	{D_ALL, _MMIO(MCHBAR_MIRROR_BASE_SNB), 0x40000, NULL, NULL},
+	{D_ALL, _MMIO(VGT_PVINFO_PAGE), VGT_PVINFO_SIZE,
+		pvinfo_mmio_read, pvinfo_mmio_write},
+	{D_ALL, LGC_PALETTE(PIPE_A, 0), 1024, NULL, NULL},
+	{D_ALL, LGC_PALETTE(PIPE_B, 0), 1024, NULL, NULL},
+	{D_ALL, LGC_PALETTE(PIPE_C, 0), 1024, NULL, NULL},
+};
+
 /**
  * intel_gvt_setup_mmio_info - setup MMIO information table for GVT device
  * @gvt: GVT device
@@ -2951,6 +2946,9 @@ int intel_gvt_setup_mmio_info(struct intel_gvt *gvt)
 			goto err;
 	}
 
+	gvt->mmio.mmio_block = mmio_blocks;
+	gvt->mmio.num_mmio_block = ARRAY_SIZE(mmio_blocks);
+
 	gvt_dbg_mmio("traced %u virtual mmio registers\n",
 		     gvt->mmio.num_tracked_mmio);
 	return 0;
@@ -3030,7 +3028,7 @@ int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset,
 	gvt_mmio_func func;
 	int ret;
 
-	if (WARN_ON(bytes > 4))
+	if (WARN_ON(bytes > 8))
 		return -EINVAL;
 
 	/*

drivers/gpu/drm/i915/gvt/scheduler.c

@@ -432,7 +432,8 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 
 		i915_gem_request_put(fetch_and_zero(&workload->req));
 
-		if (!workload->status && !vgpu->resetting) {
+		if (!workload->status && !(vgpu->resetting_eng &
+					   ENGINE_MASK(ring_id))) {
 			update_guest_context(workload);
 
 			for_each_set_bit(event, workload->pending_events,

drivers/gpu/drm/i915/gvt/vgpu.c

@@ -480,11 +480,13 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
+	unsigned int resetting_eng = dmlr ? ALL_ENGINES : engine_mask;
 
 	gvt_dbg_core("------------------------------------------\n");
 	gvt_dbg_core("resseting vgpu%d, dmlr %d, engine_mask %08x\n",
 		     vgpu->id, dmlr, engine_mask);
-	vgpu->resetting = true;
+
+	vgpu->resetting_eng = resetting_eng;
 
 	intel_vgpu_stop_schedule(vgpu);
 	/*
@@ -497,7 +499,7 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 		mutex_lock(&gvt->lock);
 	}
 
-	intel_vgpu_reset_execlist(vgpu, dmlr ? ALL_ENGINES : engine_mask);
+	intel_vgpu_reset_execlist(vgpu, resetting_eng);
 
 	/* full GPU reset or device model level reset */
 	if (engine_mask == ALL_ENGINES || dmlr) {
@@ -520,7 +522,7 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 		}
 	}
 
-	vgpu->resetting = false;
+	vgpu->resetting_eng = 0;
 	gvt_dbg_core("reset vgpu%d done\n", vgpu->id);
 	gvt_dbg_core("------------------------------------------\n");
 }

drivers/gpu/drm/i915/i915_gem_shrinker.c

@@ -43,16 +43,21 @@ static bool shrinker_lock(struct drm_i915_private *dev_priv, bool *unlock)
 		return true;
 
 	case MUTEX_TRYLOCK_FAILED:
+		*unlock = false;
+		preempt_disable();
 		do {
 			cpu_relax();
 			if (mutex_trylock(&dev_priv->drm.struct_mutex)) {
-	case MUTEX_TRYLOCK_SUCCESS:
 				*unlock = true;
-				return true;
+				break;
 			}
 		} while (!need_resched());
+		preempt_enable();
+		return *unlock;
 
-		return false;
+	case MUTEX_TRYLOCK_SUCCESS:
+		*unlock = true;
+		return true;
 	}
 
 	BUG();

drivers/gpu/drm/i915/i915_perf.c

@@ -1601,11 +1601,11 @@ static int gen8_emit_oa_config(struct drm_i915_gem_request *req)
 	u32 *cs;
 	int i;
 
-	cs = intel_ring_begin(req, n_flex_regs * 2 + 4);
+	cs = intel_ring_begin(req, ARRAY_SIZE(flex_mmio) * 2 + 4);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
-	*cs++ = MI_LOAD_REGISTER_IMM(n_flex_regs + 1);
+	*cs++ = MI_LOAD_REGISTER_IMM(ARRAY_SIZE(flex_mmio) + 1);
 
 	*cs++ = i915_mmio_reg_offset(GEN8_OACTXCONTROL);
 	*cs++ = (dev_priv->perf.oa.period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |

drivers/gpu/drm/i915/intel_color.c

@@ -398,6 +398,7 @@ static void bdw_load_gamma_lut(struct drm_crtc_state *state, u32 offset)
 		}
 
 		/* Program the max register to clamp values > 1.0. */
+		i = lut_size - 1;
 		I915_WRITE(PREC_PAL_GC_MAX(pipe, 0),
 			   drm_color_lut_extract(lut[i].red, 16));
 		I915_WRITE(PREC_PAL_GC_MAX(pipe, 1),

drivers/gpu/drm/i915/intel_panel.c

@@ -469,7 +469,7 @@ static u32 intel_panel_compute_brightness(struct intel_connector *connector,
 
 	if (i915.invert_brightness > 0 ||
 	    dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS) {
-		return panel->backlight.max - val;
+		return panel->backlight.max - val + panel->backlight.min;
 	}
 
 	return val;

drivers/gpu/drm/msm/Kconfig

@@ -5,7 +5,7 @@ config DRM_MSM
 	depends on ARCH_QCOM || (ARM && COMPILE_TEST)
 	depends on OF && COMMON_CLK
 	depends on MMU
-	select QCOM_MDT_LOADER
+	select QCOM_MDT_LOADER if ARCH_QCOM
 	select REGULATOR
 	select DRM_KMS_HELPER
 	select DRM_PANEL

drivers/gpu/drm/msm/adreno/a5xx_gpu.c

@@ -15,7 +15,7 @@
 #include <linux/cpumask.h>
 #include <linux/qcom_scm.h>
 #include <linux/dma-mapping.h>
-#include <linux/of_reserved_mem.h>
+#include <linux/of_address.h>
 #include <linux/soc/qcom/mdt_loader.h>
 #include "msm_gem.h"
 #include "msm_mmu.h"
@@ -26,16 +26,34 @@ static void a5xx_dump(struct msm_gpu *gpu);
 
 #define GPU_PAS_ID 13
 
-#if IS_ENABLED(CONFIG_QCOM_MDT_LOADER)
-
 static int zap_shader_load_mdt(struct device *dev, const char *fwname)
 {
 	const struct firmware *fw;
+	struct device_node *np;
+	struct resource r;
 	phys_addr_t mem_phys;
 	ssize_t mem_size;
 	void *mem_region = NULL;
 	int ret;
 
+	if (!IS_ENABLED(CONFIG_ARCH_QCOM))
+		return -EINVAL;
+
+	np = of_get_child_by_name(dev->of_node, "zap-shader");
+	if (!np)
+		return -ENODEV;
+
+	np = of_parse_phandle(np, "memory-region", 0);
+	if (!np)
+		return -EINVAL;
+
+	ret = of_address_to_resource(np, 0, &r);
+	if (ret)
+		return ret;
+
+	mem_phys = r.start;
+	mem_size = resource_size(&r);
+
 	/* Request the MDT file for the firmware */
 	ret = request_firmware(&fw, fwname, dev);
 	if (ret) {
@@ -51,7 +69,7 @@ static int zap_shader_load_mdt(struct device *dev, const char *fwname)
 	}
 
 	/* Allocate memory for the firmware image */
-	mem_region = dmam_alloc_coherent(dev, mem_size, &mem_phys, GFP_KERNEL);
+	mem_region = memremap(mem_phys, mem_size,  MEMREMAP_WC);
 	if (!mem_region) {
 		ret = -ENOMEM;
 		goto out;
@@ -69,16 +87,13 @@ static int zap_shader_load_mdt(struct device *dev, const char *fwname)
 		DRM_DEV_ERROR(dev, "Unable to authorize the image\n");
 
 out:
+	if (mem_region)
+		memunmap(mem_region);
+
 	release_firmware(fw);
 
 	return ret;
 }
-#else
-static int zap_shader_load_mdt(struct device *dev, const char *fwname)
-{
-	return -ENODEV;
-}
-#endif
 
 static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	struct msm_file_private *ctx)
@@ -117,12 +132,10 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	gpu->funcs->flush(gpu);
 }
 
-struct a5xx_hwcg {
+static const struct {
 	u32 offset;
 	u32 value;
-};
-
-static const struct a5xx_hwcg a530_hwcg[] = {
+} a5xx_hwcg[] = {
 	{REG_A5XX_RBBM_CLOCK_CNTL_SP0, 0x02222222},
 	{REG_A5XX_RBBM_CLOCK_CNTL_SP1, 0x02222222},
 	{REG_A5XX_RBBM_CLOCK_CNTL_SP2, 0x02222222},
@@ -217,38 +230,16 @@ static const struct a5xx_hwcg a530_hwcg[] = {
 	{REG_A5XX_RBBM_CLOCK_DELAY_VFD, 0x00002222}
 };
 
-static const struct {
-	int (*test)(struct adreno_gpu *gpu);
-	const struct a5xx_hwcg *regs;
-	unsigned int count;
-} a5xx_hwcg_regs[] = {
-	{ adreno_is_a530, a530_hwcg, ARRAY_SIZE(a530_hwcg), },
-};
-
-static void _a5xx_enable_hwcg(struct msm_gpu *gpu,
-		const struct a5xx_hwcg *regs, unsigned int count)
+void a5xx_set_hwcg(struct msm_gpu *gpu, bool state)
 {
 	unsigned int i;
 
-	for (i = 0; i < count; i++)
-		gpu_write(gpu, regs[i].offset, regs[i].value);
+	for (i = 0; i < ARRAY_SIZE(a5xx_hwcg); i++)
+		gpu_write(gpu, a5xx_hwcg[i].offset,
+			state ? a5xx_hwcg[i].value : 0);
 
-	gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0xAAA8AA00);
-	gpu_write(gpu, REG_A5XX_RBBM_ISDB_CNT, 0x182);
-}
-
-static void a5xx_enable_hwcg(struct msm_gpu *gpu)
-{
-	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(a5xx_hwcg_regs); i++) {
-		if (a5xx_hwcg_regs[i].test(adreno_gpu)) {
-			_a5xx_enable_hwcg(gpu, a5xx_hwcg_regs[i].regs,
-				a5xx_hwcg_regs[i].count);
-			return;
-		}
-	}
+	gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, state ? 0xAAA8AA00 : 0);
+	gpu_write(gpu, REG_A5XX_RBBM_ISDB_CNT, state ? 0x182 : 0x180);
 }
 
 static int a5xx_me_init(struct msm_gpu *gpu)
@@ -377,45 +368,6 @@ static int a5xx_zap_shader_resume(struct msm_gpu *gpu)
 	return ret;
 }
 
-/* Set up a child device to "own" the zap shader */
-static int a5xx_zap_shader_dev_init(struct device *parent, struct device *dev)
-{
-	struct device_node *node;
-	int ret;
-
-	if (dev->parent)
-		return 0;
-
-	/* Find the sub-node for the zap shader */
-	node = of_get_child_by_name(parent->of_node, "zap-shader");
-	if (!node) {
-		DRM_DEV_ERROR(parent, "zap-shader not found in device tree\n");
-		return -ENODEV;
-	}
-
-	dev->parent = parent;
-	dev->of_node = node;
-	dev_set_name(dev, "adreno_zap_shader");
-
-	ret = device_register(dev);
-	if (ret) {
-		DRM_DEV_ERROR(parent, "Couldn't register zap shader device\n");
-		goto out;
-	}
-
-	ret = of_reserved_mem_device_init(dev);
-	if (ret) {
-		DRM_DEV_ERROR(parent, "Unable to set up the reserved memory\n");
-		device_unregister(dev);
-	}
-
-out:
-	if (ret)
-		dev->parent = NULL;
-
-	return ret;
-}
-
 static int a5xx_zap_shader_init(struct msm_gpu *gpu)
 {
 	static bool loaded;
@@ -444,11 +396,7 @@ static int a5xx_zap_shader_init(struct msm_gpu *gpu)
 		return -ENODEV;
 	}
 
-	ret = a5xx_zap_shader_dev_init(&pdev->dev, &a5xx_gpu->zap_dev);
-
-	if (!ret)
-		ret = zap_shader_load_mdt(&a5xx_gpu->zap_dev,
-			adreno_gpu->info->zapfw);
+	ret = zap_shader_load_mdt(&pdev->dev, adreno_gpu->info->zapfw);
 
 	loaded = !ret;
 
@@ -545,7 +493,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL1, 0xA6FFFFFF);
 
 	/* Enable HWCG */
-	a5xx_enable_hwcg(gpu);
+	a5xx_set_hwcg(gpu, true);
 
 	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL2, 0x0000003F);
 
@@ -691,9 +639,6 @@ static void a5xx_destroy(struct msm_gpu *gpu)
 
 	DBG("%s", gpu->name);
 
-	if (a5xx_gpu->zap_dev.parent)
-		device_unregister(&a5xx_gpu->zap_dev);
-
 	if (a5xx_gpu->pm4_bo) {
 		if (a5xx_gpu->pm4_iova)
 			msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->aspace);
@@ -920,31 +865,30 @@ static const u32 a5xx_registers[] = {
 	0x0000, 0x0002, 0x0004, 0x0020, 0x0022, 0x0026, 0x0029, 0x002B,
 	0x002E, 0x0035, 0x0038, 0x0042, 0x0044, 0x0044, 0x0047, 0x0095,
 	0x0097, 0x00BB, 0x03A0, 0x0464, 0x0469, 0x046F, 0x04D2, 0x04D3,
-	0x04E0, 0x0533, 0x0540, 0x0555, 0xF400, 0xF400, 0xF800, 0xF807,
-	0x0800, 0x081A, 0x081F, 0x0841, 0x0860, 0x0860, 0x0880, 0x08A0,
-	0x0B00, 0x0B12, 0x0B15, 0x0B28, 0x0B78, 0x0B7F, 0x0BB0, 0x0BBD,
-	0x0BC0, 0x0BC6, 0x0BD0, 0x0C53, 0x0C60, 0x0C61, 0x0C80, 0x0C82,
-	0x0C84, 0x0C85, 0x0C90, 0x0C98, 0x0CA0, 0x0CA0, 0x0CB0, 0x0CB2,
-	0x2180, 0x2185, 0x2580, 0x2585, 0x0CC1, 0x0CC1, 0x0CC4, 0x0CC7,
-	0x0CCC, 0x0CCC, 0x0CD0, 0x0CD8, 0x0CE0, 0x0CE5, 0x0CE8, 0x0CE8,
-	0x0CEC, 0x0CF1, 0x0CFB, 0x0D0E, 0x2100, 0x211E, 0x2140, 0x2145,
-	0x2500, 0x251E, 0x2540, 0x2545, 0x0D10, 0x0D17, 0x0D20, 0x0D23,
-	0x0D30, 0x0D30, 0x20C0, 0x20C0, 0x24C0, 0x24C0, 0x0E40, 0x0E43,
-	0x0E4A, 0x0E4A, 0x0E50, 0x0E57, 0x0E60, 0x0E7C, 0x0E80, 0x0E8E,
-	0x0E90, 0x0E96, 0x0EA0, 0x0EA8, 0x0EB0, 0x0EB2, 0xE140, 0xE147,
-	0xE150, 0xE187, 0xE1A0, 0xE1A9, 0xE1B0, 0xE1B6, 0xE1C0, 0xE1C7,
-	0xE1D0, 0xE1D1, 0xE200, 0xE201, 0xE210, 0xE21C, 0xE240, 0xE268,
-	0xE000, 0xE006, 0xE010, 0xE09A, 0xE0A0, 0xE0A4, 0xE0AA, 0xE0EB,
-	0xE100, 0xE105, 0xE380, 0xE38F, 0xE3B0, 0xE3B0, 0xE400, 0xE405,
-	0xE408, 0xE4E9, 0xE4F0, 0xE4F0, 0xE280, 0xE280, 0xE282, 0xE2A3,
-	0xE2A5, 0xE2C2, 0xE940, 0xE947, 0xE950, 0xE987, 0xE9A0, 0xE9A9,
-	0xE9B0, 0xE9B6, 0xE9C0, 0xE9C7, 0xE9D0, 0xE9D1, 0xEA00, 0xEA01,
-	0xEA10, 0xEA1C, 0xEA40, 0xEA68, 0xE800, 0xE806, 0xE810, 0xE89A,
-	0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB, 0xE900, 0xE905, 0xEB80, 0xEB8F,
-	0xEBB0, 0xEBB0, 0xEC00, 0xEC05, 0xEC08, 0xECE9, 0xECF0, 0xECF0,
-	0xEA80, 0xEA80, 0xEA82, 0xEAA3, 0xEAA5, 0xEAC2, 0xA800, 0xA8FF,
-	0xAC60, 0xAC60, 0xB000, 0xB97F, 0xB9A0, 0xB9BF,
-	~0
+	0x04E0, 0x0533, 0x0540, 0x0555, 0x0800, 0x081A, 0x081F, 0x0841,
+	0x0860, 0x0860, 0x0880, 0x08A0, 0x0B00, 0x0B12, 0x0B15, 0x0B28,
+	0x0B78, 0x0B7F, 0x0BB0, 0x0BBD, 0x0BC0, 0x0BC6, 0x0BD0, 0x0C53,
+	0x0C60, 0x0C61, 0x0C80, 0x0C82, 0x0C84, 0x0C85, 0x0C90, 0x0C98,
+	0x0CA0, 0x0CA0, 0x0CB0, 0x0CB2, 0x2180, 0x2185, 0x2580, 0x2585,
+	0x0CC1, 0x0CC1, 0x0CC4, 0x0CC7, 0x0CCC, 0x0CCC, 0x0CD0, 0x0CD8,
+	0x0CE0, 0x0CE5, 0x0CE8, 0x0CE8, 0x0CEC, 0x0CF1, 0x0CFB, 0x0D0E,
+	0x2100, 0x211E, 0x2140, 0x2145, 0x2500, 0x251E, 0x2540, 0x2545,
+	0x0D10, 0x0D17, 0x0D20, 0x0D23, 0x0D30, 0x0D30, 0x20C0, 0x20C0,
+	0x24C0, 0x24C0, 0x0E40, 0x0E43, 0x0E4A, 0x0E4A, 0x0E50, 0x0E57,
+	0x0E60, 0x0E7C, 0x0E80, 0x0E8E, 0x0E90, 0x0E96, 0x0EA0, 0x0EA8,
+	0x0EB0, 0x0EB2, 0xE140, 0xE147, 0xE150, 0xE187, 0xE1A0, 0xE1A9,
+	0xE1B0, 0xE1B6, 0xE1C0, 0xE1C7, 0xE1D0, 0xE1D1, 0xE200, 0xE201,
+	0xE210, 0xE21C, 0xE240, 0xE268, 0xE000, 0xE006, 0xE010, 0xE09A,
+	0xE0A0, 0xE0A4, 0xE0AA, 0xE0EB, 0xE100, 0xE105, 0xE380, 0xE38F,
+	0xE3B0, 0xE3B0, 0xE400, 0xE405, 0xE408, 0xE4E9, 0xE4F0, 0xE4F0,
+	0xE280, 0xE280, 0xE282, 0xE2A3, 0xE2A5, 0xE2C2, 0xE940, 0xE947,
+	0xE950, 0xE987, 0xE9A0, 0xE9A9, 0xE9B0, 0xE9B6, 0xE9C0, 0xE9C7,
+	0xE9D0, 0xE9D1, 0xEA00, 0xEA01, 0xEA10, 0xEA1C, 0xEA40, 0xEA68,
+	0xE800, 0xE806, 0xE810, 0xE89A, 0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB,
+	0xE900, 0xE905, 0xEB80, 0xEB8F, 0xEBB0, 0xEBB0, 0xEC00, 0xEC05,
+	0xEC08, 0xECE9, 0xECF0, 0xECF0, 0xEA80, 0xEA80, 0xEA82, 0xEAA3,
+	0xEAA5, 0xEAC2, 0xA800, 0xA8FF, 0xAC60, 0xAC60, 0xB000, 0xB97F,
+	0xB9A0, 0xB9BF, ~0
 };
 
 static void a5xx_dump(struct msm_gpu *gpu)
@@ -1020,7 +964,14 @@ static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m)
 {
 	seq_printf(m, "status:   %08x\n",
 			gpu_read(gpu, REG_A5XX_RBBM_STATUS));
+
+	/*
+	 * Temporarily disable hardware clock gating before going into
+	 * adreno_show to avoid issues while reading the registers
+	 */
+	a5xx_set_hwcg(gpu, false);
 	adreno_show(gpu, m);
+	a5xx_set_hwcg(gpu, true);
 }
 #endif
 

drivers/gpu/drm/msm/adreno/a5xx_gpu.h

@@ -36,8 +36,6 @@ struct a5xx_gpu {
 	uint32_t gpmu_dwords;
 
 	uint32_t lm_leakage;
-
-	struct device zap_dev;
 };
 
 #define to_a5xx_gpu(x) container_of(x, struct a5xx_gpu, base)
@@ -59,5 +57,6 @@ static inline int spin_usecs(struct msm_gpu *gpu, uint32_t usecs,
 }
 
 bool a5xx_idle(struct msm_gpu *gpu);
+void a5xx_set_hwcg(struct msm_gpu *gpu, bool state);
 
 #endif /* __A5XX_GPU_H__ */

drivers/gpu/drm/msm/adreno/adreno_gpu.c

@@ -48,8 +48,15 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 		*value = adreno_gpu->base.fast_rate;
 		return 0;
 	case MSM_PARAM_TIMESTAMP:
-		if (adreno_gpu->funcs->get_timestamp)
-			return adreno_gpu->funcs->get_timestamp(gpu, value);
+		if (adreno_gpu->funcs->get_timestamp) {
+			int ret;
+
+			pm_runtime_get_sync(&gpu->pdev->dev);
+			ret = adreno_gpu->funcs->get_timestamp(gpu, value);
+			pm_runtime_put_autosuspend(&gpu->pdev->dev);
+
+			return ret;
+		}
 		return -EINVAL;
 	default:
 		DBG("%s: invalid param: %u", gpu->name, param);

drivers/gpu/drm/msm/dsi/dsi_host.c

@@ -2137,6 +2137,13 @@ void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
 	struct msm_dsi_phy_clk_request *clk_req)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	int ret;
+
+	ret = dsi_calc_clk_rate(msm_host);
+	if (ret) {
+		pr_err("%s: unable to calc clk rate, %d\n", __func__, ret);
+		return;
+	}
 
 	clk_req->bitclk_rate = msm_host->byte_clk_rate * 8;
 	clk_req->escclk_rate = msm_host->esc_clk_rate;
@@ -2280,7 +2287,6 @@ int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host,
 					struct drm_display_mode *mode)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
-	int ret;
 
 	if (msm_host->mode) {
 		drm_mode_destroy(msm_host->dev, msm_host->mode);
@@ -2293,12 +2299,6 @@ int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host,
 		return -ENOMEM;
 	}
 
-	ret = dsi_calc_clk_rate(msm_host);
-	if (ret) {
-		pr_err("%s: unable to calc clk rate, %d\n", __func__, ret);
-		return ret;
-	}
-
 	return 0;
 }
 

drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c

@@ -221,8 +221,8 @@ static void blend_setup(struct drm_crtc *crtc)
 	struct mdp5_ctl *ctl = mdp5_cstate->ctl;
 	uint32_t blend_op, fg_alpha, bg_alpha, ctl_blend_flags = 0;
 	unsigned long flags;
-	enum mdp5_pipe stage[STAGE_MAX + 1][MAX_PIPE_STAGE] = { SSPP_NONE };
-	enum mdp5_pipe r_stage[STAGE_MAX + 1][MAX_PIPE_STAGE] = { SSPP_NONE };
+	enum mdp5_pipe stage[STAGE_MAX + 1][MAX_PIPE_STAGE] = { { SSPP_NONE } };
+	enum mdp5_pipe r_stage[STAGE_MAX + 1][MAX_PIPE_STAGE] = { { SSPP_NONE } };
 	int i, plane_cnt = 0;
 	bool bg_alpha_enabled = false;
 	u32 mixer_op_mode = 0;
@@ -753,6 +753,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 	if (!handle) {
 		DBG("Cursor off");
 		cursor_enable = false;
+		mdp5_enable(mdp5_kms);
 		goto set_cursor;
 	}
 
@@ -776,6 +777,8 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 
 	get_roi(crtc, &roi_w, &roi_h);
 
+	mdp5_enable(mdp5_kms);
+
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_STRIDE(lm), stride);
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_FORMAT(lm),
 			MDP5_LM_CURSOR_FORMAT_FORMAT(CURSOR_FMT_ARGB8888));
@@ -804,6 +807,7 @@ set_cursor:
 	crtc_flush(crtc, flush_mask);
 
 end:
+	mdp5_disable(mdp5_kms);
 	if (old_bo) {
 		drm_flip_work_queue(&mdp5_crtc->unref_cursor_work, old_bo);
 		/* enable vblank to complete cursor work: */
@@ -836,6 +840,8 @@ static int mdp5_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 
 	get_roi(crtc, &roi_w, &roi_h);
 
+	mdp5_enable(mdp5_kms);
+
 	spin_lock_irqsave(&mdp5_crtc->cursor.lock, flags);
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_SIZE(lm),
 			MDP5_LM_CURSOR_SIZE_ROI_H(roi_h) |
@@ -847,6 +853,8 @@ static int mdp5_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 
 	crtc_flush(crtc, flush_mask);
 
+	mdp5_disable(mdp5_kms);
+
 	return 0;
 }
 

drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c

@@ -299,7 +299,7 @@ static void mdp5_encoder_enable(struct drm_encoder *encoder)
 	struct mdp5_interface *intf = mdp5_encoder->intf;
 
 	if (intf->mode == MDP5_INTF_DSI_MODE_COMMAND)
-		mdp5_cmd_encoder_disable(encoder);
+		mdp5_cmd_encoder_enable(encoder);
 	else
 		mdp5_vid_encoder_enable(encoder);
 }

drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c

@@ -502,7 +502,7 @@ static int get_clk(struct platform_device *pdev, struct clk **clkp,
 		const char *name, bool mandatory)
 {
 	struct device *dev = &pdev->dev;
-	struct clk *clk = devm_clk_get(dev, name);
+	struct clk *clk = msm_clk_get(pdev, name);
 	if (IS_ERR(clk) && mandatory) {
 		dev_err(dev, "failed to get %s (%ld)\n", name, PTR_ERR(clk));
 		return PTR_ERR(clk);
@@ -887,21 +887,21 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 	}
 
 	/* mandatory clocks: */
-	ret = get_clk(pdev, &mdp5_kms->axi_clk, "bus_clk", true);
+	ret = get_clk(pdev, &mdp5_kms->axi_clk, "bus", true);
 	if (ret)
 		goto fail;
-	ret = get_clk(pdev, &mdp5_kms->ahb_clk, "iface_clk", true);
+	ret = get_clk(pdev, &mdp5_kms->ahb_clk, "iface", true);
 	if (ret)
 		goto fail;
-	ret = get_clk(pdev, &mdp5_kms->core_clk, "core_clk", true);
+	ret = get_clk(pdev, &mdp5_kms->core_clk, "core", true);
 	if (ret)
 		goto fail;
-	ret = get_clk(pdev, &mdp5_kms->vsync_clk, "vsync_clk", true);
+	ret = get_clk(pdev, &mdp5_kms->vsync_clk, "vsync", true);
 	if (ret)
 		goto fail;
 
 	/* optional clocks: */
-	get_clk(pdev, &mdp5_kms->lut_clk, "lut_clk", false);
+	get_clk(pdev, &mdp5_kms->lut_clk, "lut", false);
 
 	/* we need to set a default rate before enabling.  Set a safe
 	 * rate first, then figure out hw revision, and then set a

drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c

@@ -890,8 +890,8 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 	struct mdp5_hw_pipe *right_hwpipe;
 	const struct mdp_format *format;
 	uint32_t nplanes, config = 0;
-	struct phase_step step = { 0 };
-	struct pixel_ext pe = { 0 };
+	struct phase_step step = { { 0 } };
+	struct pixel_ext pe = { { 0 } };
 	uint32_t hdecm = 0, vdecm = 0;
 	uint32_t pix_format;
 	unsigned int rotation;

drivers/gpu/drm/msm/msm_gem.c

@@ -383,8 +383,10 @@ int msm_gem_get_iova(struct drm_gem_object *obj,
 		struct page **pages;
 
 		vma = add_vma(obj, aspace);
-		if (IS_ERR(vma))
-			return PTR_ERR(vma);
+		if (IS_ERR(vma)) {
+			ret = PTR_ERR(vma);
+			goto unlock;
+		}
 
 		pages = get_pages(obj);
 		if (IS_ERR(pages)) {
@@ -405,7 +407,7 @@ int msm_gem_get_iova(struct drm_gem_object *obj,
 
 fail:
 	del_vma(vma);
-
+unlock:
 	mutex_unlock(&msm_obj->lock);
 	return ret;
 }
@@ -928,8 +930,12 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 	if (use_vram) {
 		struct msm_gem_vma *vma;
 		struct page **pages;
+		struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+		mutex_lock(&msm_obj->lock);
 
 		vma = add_vma(obj, NULL);
+		mutex_unlock(&msm_obj->lock);
 		if (IS_ERR(vma)) {
 			ret = PTR_ERR(vma);
 			goto fail;

drivers/gpu/drm/msm/msm_gem_submit.c

@@ -34,8 +34,8 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		struct msm_gpu *gpu, uint32_t nr_bos, uint32_t nr_cmds)
 {
 	struct msm_gem_submit *submit;
-	uint64_t sz = sizeof(*submit) + (nr_bos * sizeof(submit->bos[0])) +
-		(nr_cmds * sizeof(submit->cmd[0]));
+	uint64_t sz = sizeof(*submit) + ((u64)nr_bos * sizeof(submit->bos[0])) +
+		((u64)nr_cmds * sizeof(submit->cmd[0]));
 
 	if (sz > SIZE_MAX)
 		return NULL;
@@ -451,7 +451,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (ret)
 		goto out;
 
-	if (!(args->fence & MSM_SUBMIT_NO_IMPLICIT)) {
+	if (!(args->flags & MSM_SUBMIT_NO_IMPLICIT)) {
 		ret = submit_fence_sync(submit);
 		if (ret)
 			goto out;

drivers/gpu/drm/msm/msm_gem_vma.c

@@ -42,7 +42,7 @@ void
 msm_gem_unmap_vma(struct msm_gem_address_space *aspace,
 		struct msm_gem_vma *vma, struct sg_table *sgt)
 {
-	if (!vma->iova)
+	if (!aspace || !vma->iova)
 		return;
 
 	if (aspace->mmu) {

drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c

@@ -267,6 +267,8 @@ nvkm_disp_oneinit(struct nvkm_engine *engine)
 	/* Create output path objects for each VBIOS display path. */
 	i = -1;
 	while ((data = dcb_outp_parse(bios, ++i, &ver, &hdr, &dcbE))) {
+		if (ver < 0x40) /* No support for chipsets prior to NV50. */
+			break;
 		if (dcbE.type == DCB_OUTPUT_UNUSED)
 			continue;
 		if (dcbE.type == DCB_OUTPUT_EOL)

drivers/gpu/drm/rockchip/rockchip_drm_vop.c

@@ -500,7 +500,7 @@ static void vop_line_flag_irq_disable(struct vop *vop)
 static int vop_enable(struct drm_crtc *crtc)
 {
 	struct vop *vop = to_vop(crtc);
-	int ret;
+	int ret, i;
 
 	ret = pm_runtime_get_sync(vop->dev);
 	if (ret < 0) {
@@ -533,6 +533,20 @@ static int vop_enable(struct drm_crtc *crtc)
 	}
 
 	memcpy(vop->regs, vop->regsbak, vop->len);
+	/*
+	 * We need to make sure that all windows are disabled before we
+	 * enable the crtc. Otherwise we might try to scan from a destroyed
+	 * buffer later.
+	 */
+	for (i = 0; i < vop->data->win_size; i++) {
+		struct vop_win *vop_win = &vop->win[i];
+		const struct vop_win_data *win = vop_win->data;
+
+		spin_lock(&vop->reg_lock);
+		VOP_WIN_SET(vop, win, enable, 0);
+		spin_unlock(&vop->reg_lock);
+	}
+
 	vop_cfg_done(vop);
 
 	/*
@@ -566,28 +580,11 @@ err_put_pm_runtime:
 static void vop_crtc_disable(struct drm_crtc *crtc)
 {
 	struct vop *vop = to_vop(crtc);
-	int i;
 
 	WARN_ON(vop->event);
 
 	rockchip_drm_psr_deactivate(&vop->crtc);
 
-	/*
-	 * We need to make sure that all windows are disabled before we
-	 * disable that crtc. Otherwise we might try to scan from a destroyed
-	 * buffer later.
-	 */
-	for (i = 0; i < vop->data->win_size; i++) {
-		struct vop_win *vop_win = &vop->win[i];
-		const struct vop_win_data *win = vop_win->data;
-
-		spin_lock(&vop->reg_lock);
-		VOP_WIN_SET(vop, win, enable, 0);
-		spin_unlock(&vop->reg_lock);
-	}
-
-	vop_cfg_done(vop);
-
 	drm_crtc_vblank_off(crtc);
 
 	/*
@@ -682,8 +679,10 @@ static int vop_plane_atomic_check(struct drm_plane *plane,
 	 * Src.x1 can be odd when do clip, but yuv plane start point
 	 * need align with 2 pixel.
 	 */
-	if (is_yuv_support(fb->format->format) && ((state->src.x1 >> 16) % 2))
+	if (is_yuv_support(fb->format->format) && ((state->src.x1 >> 16) % 2)) {
+		DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n");
 		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -764,7 +763,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	spin_lock(&vop->reg_lock);
 
 	VOP_WIN_SET(vop, win, format, format);
-	VOP_WIN_SET(vop, win, yrgb_vir, fb->pitches[0] >> 2);
+	VOP_WIN_SET(vop, win, yrgb_vir, DIV_ROUND_UP(fb->pitches[0], 4));
 	VOP_WIN_SET(vop, win, yrgb_mst, dma_addr);
 	if (is_yuv_support(fb->format->format)) {
 		int hsub = drm_format_horz_chroma_subsampling(fb->format->format);
@@ -778,7 +777,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 		offset += (src->y1 >> 16) * fb->pitches[1] / vsub;
 
 		dma_addr = rk_uv_obj->dma_addr + offset + fb->offsets[1];
-		VOP_WIN_SET(vop, win, uv_vir, fb->pitches[1] >> 2);
+		VOP_WIN_SET(vop, win, uv_vir, DIV_ROUND_UP(fb->pitches[1], 4));
 		VOP_WIN_SET(vop, win, uv_mst, dma_addr);
 	}
 

drivers/gpu/drm/rockchip/rockchip_drm_vop.h

@@ -282,6 +282,9 @@ static inline uint16_t scl_get_bili_dn_vskip(int src_h, int dst_h,
 
 	act_height = (src_h + vskiplines - 1) / vskiplines;
 
+	if (act_height == dst_h)
+		return GET_SCL_FT_BILI_DN(src_h, dst_h) / vskiplines;
+
 	return GET_SCL_FT_BILI_DN(act_height, dst_h);
 }
 

drivers/gpu/drm/stm/Kconfig

@@ -7,7 +7,6 @@ config DRM_STM
 	select DRM_PANEL
 	select VIDEOMODE_HELPERS
 	select FB_PROVIDE_GET_FB_UNMAPPED_AREA
-	default y
 
 	help
 	  Enable support for the on-chip display controller on

drivers/i2c/busses/Kconfig

@@ -983,7 +983,7 @@ config I2C_UNIPHIER_F
 
 config I2C_VERSATILE
 	tristate "ARM Versatile/Realview I2C bus support"
-	depends on ARCH_VERSATILE || ARCH_REALVIEW || ARCH_VEXPRESS || COMPILE_TEST
+	depends on ARCH_MPS2 || ARCH_VERSATILE || ARCH_REALVIEW || ARCH_VEXPRESS || COMPILE_TEST
 	select I2C_ALGOBIT
 	help
 	  Say yes if you want to support the I2C serial bus on ARMs Versatile

drivers/i2c/busses/i2c-designware-platdrv.c

@@ -298,6 +298,9 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	}
 
 	acpi_speed = i2c_acpi_find_bus_speed(&pdev->dev);
+	/* Some broken DSTDs use 1MiHz instead of 1MHz */
+	if (acpi_speed == 1048576)
+		acpi_speed = 1000000;
 	/*
 	 * Find bus speed from the "clock-frequency" device property, ACPI
 	 * or by using fast mode if neither is set.
@@ -319,7 +322,8 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	if (dev->clk_freq != 100000 && dev->clk_freq != 400000
 	    && dev->clk_freq != 1000000 && dev->clk_freq != 3400000) {
 		dev_err(&pdev->dev,
-			"Only 100kHz, 400kHz, 1MHz and 3.4MHz supported");
+			"%d Hz is unsupported, only 100kHz, 400kHz, 1MHz and 3.4MHz are supported\n",
+			dev->clk_freq);
 		ret = -EINVAL;
 		goto exit_reset;
 	}

drivers/i2c/i2c-core-acpi.c

@@ -230,6 +230,16 @@ void i2c_acpi_register_devices(struct i2c_adapter *adap)
 		dev_warn(&adap->dev, "failed to enumerate I2C slaves\n");
 }
 
+const struct acpi_device_id *
+i2c_acpi_match_device(const struct acpi_device_id *matches,
+		      struct i2c_client *client)
+{
+	if (!(client && matches))
+		return NULL;
+
+	return acpi_match_device(matches, &client->dev);
+}
+
 static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level,
 					   void *data, void **return_value)
 {
@@ -289,7 +299,7 @@ u32 i2c_acpi_find_bus_speed(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(i2c_acpi_find_bus_speed);
 
-static int i2c_acpi_match_adapter(struct device *dev, void *data)
+static int i2c_acpi_find_match_adapter(struct device *dev, void *data)
 {
 	struct i2c_adapter *adapter = i2c_verify_adapter(dev);
 
@@ -299,7 +309,7 @@ static int i2c_acpi_match_adapter(struct device *dev, void *data)
 	return ACPI_HANDLE(dev) == (acpi_handle)data;
 }
 
-static int i2c_acpi_match_device(struct device *dev, void *data)
+static int i2c_acpi_find_match_device(struct device *dev, void *data)
 {
 	return ACPI_COMPANION(dev) == data;
 }
@@ -309,7 +319,7 @@ static struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle)
 	struct device *dev;
 
 	dev = bus_find_device(&i2c_bus_type, NULL, handle,
-			      i2c_acpi_match_adapter);
+			      i2c_acpi_find_match_adapter);
 	return dev ? i2c_verify_adapter(dev) : NULL;
 }
 
@@ -317,7 +327,8 @@ static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev)
 {
 	struct device *dev;
 
-	dev = bus_find_device(&i2c_bus_type, NULL, adev, i2c_acpi_match_device);
+	dev = bus_find_device(&i2c_bus_type, NULL, adev,
+			      i2c_acpi_find_match_device);
 	return dev ? i2c_verify_client(dev) : NULL;
 }
 

drivers/i2c/i2c-core-base.c

@@ -357,6 +357,7 @@ static int i2c_device_probe(struct device *dev)
 	 * Tree match table entry is supplied for the probing device.
 	 */
 	if (!driver->id_table &&
+	    !i2c_acpi_match_device(dev->driver->acpi_match_table, client) &&
 	    !i2c_of_match_device(dev->driver->of_match_table, client))
 		return -ENODEV;
 

drivers/i2c/i2c-core.h

@@ -31,9 +31,18 @@ int i2c_check_addr_validity(unsigned addr, unsigned short flags);
 int i2c_check_7bit_addr_validity_strict(unsigned short addr);
 
 #ifdef CONFIG_ACPI
+const struct acpi_device_id *
+i2c_acpi_match_device(const struct acpi_device_id *matches,
+		      struct i2c_client *client);
 void i2c_acpi_register_devices(struct i2c_adapter *adap);
 #else /* CONFIG_ACPI */
 static inline void i2c_acpi_register_devices(struct i2c_adapter *adap) { }
+static inline const struct acpi_device_id *
+i2c_acpi_match_device(const struct acpi_device_id *matches,
+		      struct i2c_client *client)
+{
+	return NULL;
+}
 #endif /* CONFIG_ACPI */
 extern struct notifier_block i2c_acpi_notifier;
 

drivers/i2c/muxes/Kconfig

@@ -83,7 +83,7 @@ config I2C_MUX_PINCTRL
 	  different sets of pins at run-time.
 
 	  This driver can also be built as a module. If so, the module will be
-	  called pinctrl-i2cmux.
+	  called i2c-mux-pinctrl.
 
 config I2C_MUX_REG
 	tristate "Register-based I2C multiplexer"

drivers/iio/accel/bmc150-accel-core.c

@@ -193,7 +193,6 @@ struct bmc150_accel_data {
 	struct regmap *regmap;
 	int irq;
 	struct bmc150_accel_interrupt interrupts[BMC150_ACCEL_INTERRUPTS];
-	atomic_t active_intr;
 	struct bmc150_accel_trigger triggers[BMC150_ACCEL_TRIGGERS];
 	struct mutex mutex;
 	u8 fifo_mode, watermark;
@@ -493,11 +492,6 @@ static int bmc150_accel_set_interrupt(struct bmc150_accel_data *data, int i,
 		goto out_fix_power_state;
 	}
 
-	if (state)
-		atomic_inc(&data->active_intr);
-	else
-		atomic_dec(&data->active_intr);
-
 	return 0;
 
 out_fix_power_state:
@@ -1710,8 +1704,7 @@ static int bmc150_accel_resume(struct device *dev)
 	struct bmc150_accel_data *data = iio_priv(indio_dev);
 
 	mutex_lock(&data->mutex);
-	if (atomic_read(&data->active_intr))
-		bmc150_accel_set_mode(data, BMC150_ACCEL_SLEEP_MODE_NORMAL, 0);
+	bmc150_accel_set_mode(data, BMC150_ACCEL_SLEEP_MODE_NORMAL, 0);
 	bmc150_accel_fifo_set_mode(data);
 	mutex_unlock(&data->mutex);
 

drivers/iio/accel/st_accel_core.c

@@ -166,6 +166,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = {
 			.mask_ihl = 0x02,
 			.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
 		},
+		.sim = {
+			.addr = 0x23,
+			.value = BIT(0),
+		},
 		.multi_read_bit = true,
 		.bootime = 2,
 	},
@@ -234,6 +238,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = {
 			.mask_od = 0x40,
 			.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
 		},
+		.sim = {
+			.addr = 0x23,
+			.value = BIT(0),
+		},
 		.multi_read_bit = true,
 		.bootime = 2,
 	},
@@ -316,6 +324,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = {
 				.en_mask = 0x08,
 			},
 		},
+		.sim = {
+			.addr = 0x24,
+			.value = BIT(0),
+		},
 		.multi_read_bit = false,
 		.bootime = 2,
 	},
@@ -379,6 +391,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = {
 			.mask_int1 = 0x04,
 			.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
 		},
+		.sim = {
+			.addr = 0x21,
+			.value = BIT(1),
+		},
 		.multi_read_bit = true,
 		.bootime = 2, /* guess */
 	},
@@ -437,6 +453,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = {
 			.mask_od = 0x40,
 			.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
 		},
+		.sim = {
+			.addr = 0x21,
+			.value = BIT(7),
+		},
 		.multi_read_bit = false,
 		.bootime = 2, /* guess */
 	},
@@ -499,6 +519,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = {
 			.addr_ihl = 0x22,
 			.mask_ihl = 0x80,
 		},
+		.sim = {
+			.addr = 0x23,
+			.value = BIT(0),
+		},
 		.multi_read_bit = true,
 		.bootime = 2,
 	},
@@ -547,6 +571,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = {
 			.mask_int1 = 0x04,
 			.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
 		},
+		.sim = {
+			.addr = 0x21,
+			.value = BIT(1),
+		},
 		.multi_read_bit = false,
 		.bootime = 2,
 	},
@@ -614,6 +642,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = {
 			.mask_ihl = 0x02,
 			.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
 		},
+		.sim = {
+			.addr = 0x23,
+			.value = BIT(0),
+		},
 		.multi_read_bit = true,
 		.bootime = 2,
 	},

drivers/iio/adc/aspeed_adc.c

@@ -22,6 +22,7 @@
 
 #include <linux/iio/iio.h>
 #include <linux/iio/driver.h>
+#include <linux/iopoll.h>
 
 #define ASPEED_RESOLUTION_BITS		10
 #define ASPEED_CLOCKS_PER_SAMPLE	12
@@ -38,11 +39,17 @@
 
 #define ASPEED_ENGINE_ENABLE		BIT(0)
 
+#define ASPEED_ADC_CTRL_INIT_RDY	BIT(8)
+
+#define ASPEED_ADC_INIT_POLLING_TIME	500
+#define ASPEED_ADC_INIT_TIMEOUT		500000
+
 struct aspeed_adc_model_data {
 	const char *model_name;
 	unsigned int min_sampling_rate;	// Hz
 	unsigned int max_sampling_rate;	// Hz
 	unsigned int vref_voltage;	// mV
+	bool wait_init_sequence;
 };
 
 struct aspeed_adc_data {
@@ -211,6 +218,24 @@ static int aspeed_adc_probe(struct platform_device *pdev)
 		goto scaler_error;
 	}
 
+	model_data = of_device_get_match_data(&pdev->dev);
+
+	if (model_data->wait_init_sequence) {
+		/* Enable engine in normal mode. */
+		writel(ASPEED_OPERATION_MODE_NORMAL | ASPEED_ENGINE_ENABLE,
+		       data->base + ASPEED_REG_ENGINE_CONTROL);
+
+		/* Wait for initial sequence complete. */
+		ret = readl_poll_timeout(data->base + ASPEED_REG_ENGINE_CONTROL,
+					 adc_engine_control_reg_val,
+					 adc_engine_control_reg_val &
+					 ASPEED_ADC_CTRL_INIT_RDY,
+					 ASPEED_ADC_INIT_POLLING_TIME,
+					 ASPEED_ADC_INIT_TIMEOUT);
+		if (ret)
+			goto scaler_error;
+	}
+
 	/* Start all channels in normal mode. */
 	ret = clk_prepare_enable(data->clk_scaler->clk);
 	if (ret)
@@ -274,6 +299,7 @@ static const struct aspeed_adc_model_data ast2500_model_data = {
 	.vref_voltage = 1800, // mV
 	.min_sampling_rate = 1,
 	.max_sampling_rate = 1000000,
+	.wait_init_sequence = true,
 };
 
 static const struct of_device_id aspeed_adc_matches[] = {

drivers/iio/adc/axp288_adc.c

@@ -28,6 +28,8 @@
 #include <linux/iio/driver.h>
 
 #define AXP288_ADC_EN_MASK		0xF1
+#define AXP288_ADC_TS_PIN_GPADC		0xF2
+#define AXP288_ADC_TS_PIN_ON		0xF3
 
 enum axp288_adc_id {
 	AXP288_ADC_TS,
@@ -121,6 +123,26 @@ static int axp288_adc_read_channel(int *val, unsigned long address,
 	return IIO_VAL_INT;
 }
 
+static int axp288_adc_set_ts(struct regmap *regmap, unsigned int mode,
+				unsigned long address)
+{
+	int ret;
+
+	/* channels other than GPADC do not need to switch TS pin */
+	if (address != AXP288_GP_ADC_H)
+		return 0;
+
+	ret = regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, mode);
+	if (ret)
+		return ret;
+
+	/* When switching to the GPADC pin give things some time to settle */
+	if (mode == AXP288_ADC_TS_PIN_GPADC)
+		usleep_range(6000, 10000);
+
+	return 0;
+}
+
 static int axp288_adc_read_raw(struct iio_dev *indio_dev,
 			struct iio_chan_spec const *chan,
 			int *val, int *val2, long mask)
@@ -131,7 +153,16 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev,
 	mutex_lock(&indio_dev->mlock);
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
+		if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_GPADC,
+					chan->address)) {
+			dev_err(&indio_dev->dev, "GPADC mode\n");
+			ret = -EINVAL;
+			break;
+		}
 		ret = axp288_adc_read_channel(val, chan->address, info->regmap);
+		if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_ON,
+						chan->address))
+			dev_err(&indio_dev->dev, "TS pin restore\n");
 		break;
 	default:
 		ret = -EINVAL;
@@ -141,6 +172,15 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev,
 	return ret;
 }
 
+static int axp288_adc_set_state(struct regmap *regmap)
+{
+	/* ADC should be always enabled for internal FG to function */
+	if (regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, AXP288_ADC_TS_PIN_ON))
+		return -EIO;
+
+	return regmap_write(regmap, AXP20X_ADC_EN1, AXP288_ADC_EN_MASK);
+}
+
 static const struct iio_info axp288_adc_iio_info = {
 	.read_raw = &axp288_adc_read_raw,
 	.driver_module = THIS_MODULE,
@@ -169,7 +209,7 @@ static int axp288_adc_probe(struct platform_device *pdev)
 	 * Set ADC to enabled state at all time, including system suspend.
 	 * otherwise internal fuel gauge functionality may be affected.
 	 */
-	ret = regmap_write(info->regmap, AXP20X_ADC_EN1, AXP288_ADC_EN_MASK);
+	ret = axp288_adc_set_state(axp20x->regmap);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to enable ADC device\n");
 		return ret;

drivers/iio/adc/sun4i-gpadc-iio.c

@@ -256,6 +256,7 @@ static int sun4i_gpadc_read(struct iio_dev *indio_dev, int channel, int *val,
 
 err:
 	pm_runtime_put_autosuspend(indio_dev->dev.parent);
+	disable_irq(irq);
 	mutex_unlock(&info->mutex);
 
 	return ret;
@@ -365,7 +366,6 @@ static irqreturn_t sun4i_gpadc_temp_data_irq_handler(int irq, void *dev_id)
 		complete(&info->completion);
 
 out:
-	disable_irq_nosync(info->temp_data_irq);
 	return IRQ_HANDLED;
 }
 
@@ -380,7 +380,6 @@ static irqreturn_t sun4i_gpadc_fifo_data_irq_handler(int irq, void *dev_id)
 		complete(&info->completion);
 
 out:
-	disable_irq_nosync(info->fifo_data_irq);
 	return IRQ_HANDLED;
 }
 

drivers/iio/adc/vf610_adc.c

@@ -77,7 +77,7 @@
 #define VF610_ADC_ADSTS_MASK		0x300
 #define VF610_ADC_ADLPC_EN		0x80
 #define VF610_ADC_ADHSC_EN		0x400
-#define VF610_ADC_REFSEL_VALT		0x100
+#define VF610_ADC_REFSEL_VALT		0x800
 #define VF610_ADC_REFSEL_VBG		0x1000
 #define VF610_ADC_ADTRG_HARD		0x2000
 #define VF610_ADC_AVGS_8		0x4000