Ver código fonte

Merge branch 'kvm-ppc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

This fix was intended for 4.13, but didn't get in because both
maintainers were on vacation.

Paul Mackerras:
 "It adds mutual exclusion between list_add_rcu and list_del_rcu calls
  on the kvm->arch.spapr_tce_tables list.  Without this, userspace could
  potentially trigger corruption of the list and cause a host crash or
  worse."
Radim Krčmář 8 anos atrás
pai
commit
5f54c8b2d4
100 arquivos alterados com 2827 adições e 495 exclusões
  1. 6 0
      Documentation/fb/efifb.txt
  2. 1 1
      Documentation/gpio/gpio-legacy.txt
  3. 11 8
      Documentation/printk-formats.txt
  4. 4 4
      MAINTAINERS
  5. 1 1
      Makefile
  6. 1 0
      arch/arm/boot/dts/imx25.dtsi
  7. 2 2
      arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi
  8. 8 8
      arch/arm/boot/dts/imx7d-sdb.dts
  9. 6 6
      arch/arm/boot/dts/sama5d2.dtsi
  10. 9 2
      arch/arm/include/asm/tlb.h
  11. 1 0
      arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
  12. 1 0
      arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
  13. 1 0
      arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
  14. 3 0
      arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
  15. 1 1
      arch/arm64/boot/dts/renesas/salvator-common.dtsi
  16. 2 2
      arch/arm64/include/asm/arch_timer.h
  17. 2 2
      arch/arm64/include/asm/elf.h
  18. 6 2
      arch/ia64/include/asm/tlb.h
  19. 1 1
      arch/mips/Kconfig
  20. 14 1
      arch/mips/Makefile
  21. 2 0
      arch/mips/boot/compressed/.gitignore
  22. 1 1
      arch/mips/cavium-octeon/octeon-usb.c
  23. 6 28
      arch/mips/dec/int-handler.S
  24. 2 0
      arch/mips/include/asm/cache.h
  25. 3 0
      arch/mips/include/asm/cpu-features.h
  26. 36 1
      arch/mips/include/asm/octeon/cvmx-l2c-defs.h
  27. 60 0
      arch/mips/include/asm/octeon/cvmx-l2d-defs.h
  28. 1 0
      arch/mips/include/asm/octeon/cvmx.h
  29. 3 3
      arch/mips/kernel/smp.c
  30. 1 1
      arch/mips/mm/uasm-mips.c
  31. 1950 0
      arch/mips/net/ebpf_jit.c
  32. 3 4
      arch/mips/pci/pci.c
  33. 4 2
      arch/mips/vdso/gettimeofday.c
  34. 1 1
      arch/powerpc/Kconfig
  35. 2 1
      arch/powerpc/configs/powernv_defconfig
  36. 2 1
      arch/powerpc/configs/ppc64_defconfig
  37. 2 1
      arch/powerpc/configs/pseries_defconfig
  38. 18 42
      arch/powerpc/kernel/entry_64.S
  39. 3 6
      arch/powerpc/kernel/process.c
  40. 3 3
      arch/powerpc/kernel/smp.c
  41. 36 13
      arch/powerpc/kernel/watchdog.c
  42. 34 23
      arch/powerpc/kvm/book3s_64_vio.c
  43. 3 0
      arch/powerpc/kvm/book3s_hv_rmhandlers.S
  44. 65 3
      arch/powerpc/kvm/book3s_xive_template.c
  45. 38 3
      arch/powerpc/platforms/powernv/idle.c
  46. 11 6
      arch/s390/include/asm/tlb.h
  47. 2 1
      arch/s390/net/bpf_jit_comp.c
  48. 5 3
      arch/sh/include/asm/tlb.h
  49. 16 0
      arch/sparc/include/asm/spitfire.h
  50. 6 0
      arch/sparc/kernel/cpu.c
  51. 1 0
      arch/sparc/kernel/cpumap.c
  52. 14 8
      arch/sparc/kernel/head_64.S
  53. 13 2
      arch/sparc/kernel/setup_64.c
  54. 13 1
      arch/sparc/mm/init_64.c
  55. 10 3
      arch/um/include/asm/tlb.h
  56. 2 1
      arch/x86/Kconfig
  57. 36 31
      arch/x86/crypto/sha1_avx2_x86_64_asm.S
  58. 1 1
      arch/x86/crypto/sha1_ssse3_glue.c
  59. 2 0
      arch/x86/entry/entry_64.S
  60. 7 9
      arch/x86/events/core.c
  61. 1 1
      arch/x86/events/intel/bts.c
  62. 1 1
      arch/x86/events/intel/p4.c
  63. 1 1
      arch/x86/events/intel/rapl.c
  64. 1 1
      arch/x86/events/intel/uncore.c
  65. 6 6
      arch/x86/events/intel/uncore_nhmex.c
  66. 3 3
      arch/x86/events/intel/uncore_snb.c
  67. 21 21
      arch/x86/events/intel/uncore_snbep.c
  68. 1 1
      arch/x86/include/asm/cpufeatures.h
  69. 2 2
      arch/x86/include/asm/elf.h
  70. 3 3
      arch/x86/include/asm/fpu/internal.h
  71. 10 0
      arch/x86/include/asm/hypervisor.h
  72. 1 0
      arch/x86/include/asm/kvm_host.h
  73. 3 0
      arch/x86/kernel/cpu/aperfmperf.c
  74. 1 1
      arch/x86/kernel/cpu/mcheck/therm_throt.c
  75. 2 2
      arch/x86/kernel/cpu/microcode/core.c
  76. 15 3
      arch/x86/kernel/cpu/mtrr/main.c
  77. 4 3
      arch/x86/kernel/head64.c
  78. 2 2
      arch/x86/kernel/ksysfs.c
  79. 17 13
      arch/x86/kernel/smpboot.c
  80. 1 1
      arch/x86/kvm/cpuid.c
  81. 0 5
      arch/x86/kvm/kvm_cache_regs.h
  82. 1 1
      arch/x86/kvm/mmu.h
  83. 1 8
      arch/x86/kvm/svm.c
  84. 8 17
      arch/x86/kvm/vmx.c
  85. 14 3
      arch/x86/kvm/x86.c
  86. 3 0
      arch/x86/mm/init.c
  87. 3 4
      arch/x86/mm/mmap.c
  88. 2 2
      arch/x86/platform/uv/tlb_uv.c
  89. 37 22
      arch/x86/xen/enlighten_hvm.c
  90. 2 0
      arch/xtensa/include/asm/Kbuild
  91. 0 15
      arch/xtensa/include/asm/device.h
  92. 0 18
      arch/xtensa/include/asm/param.h
  93. 0 2
      arch/xtensa/kernel/xtensa_ksyms.c
  94. 8 8
      arch/xtensa/mm/cache.c
  95. 17 5
      block/bfq-iosched.h
  96. 81 65
      block/bfq-wf2q.c
  97. 4 2
      block/bio-integrity.c
  98. 7 1
      block/blk-mq-pci.c
  99. 10 6
      block/blk-mq.c
  100. 34 2
      drivers/acpi/spcr.c

+ 6 - 0
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>

+ 1 - 1
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

+ 11 - 8
Documentation/printk-formats.txt

@@ -58,20 +58,23 @@ Symbols/Function Pointers
 	%ps	versatile_init
 	%pB	prev_fn_of_versatile_init+0x88/0x88
 
-For printing symbols and function pointers. The ``S`` and ``s`` specifiers
-result in the symbol name with (``S``) or without (``s``) offsets. Where
-this is used on a kernel without KALLSYMS - the symbol address is
-printed instead.
+The ``F`` and ``f`` specifiers are for printing function pointers,
+for example, f->func, &gettimeofday. They have the same result as
+``S`` and ``s`` specifiers. But they do an extra conversion on
+ia64, ppc64 and parisc64 architectures where the function pointers
+are actually function descriptors.
+
+The ``S`` and ``s`` specifiers can be used for printing symbols
+from direct addresses, for example, __builtin_return_address(0),
+(void *)regs->ip. They result in the symbol name with (``S``) or
+without (``s``) offsets. If KALLSYMS are disabled then the symbol
+address is printed instead.
 
 The ``B`` specifier results in the symbol name with offsets and should be
 used when printing stack backtraces. The specifier takes into
 consideration the effect of compiler optimisations which may occur
 when tail-call``s are used and marked with the noreturn GCC attribute.
 
-On ia64, ppc64 and parisc64 architectures function pointers are
-actually function descriptors which must first be resolved. The ``F`` and
-``f`` specifiers perform this resolution and then provide the same
-functionality as the ``S`` and ``s`` specifiers.
 
 Kernel Pointers
 ===============

+ 4 - 4
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
@@ -7110,7 +7110,6 @@ M:	Marc Zyngier <marc.zyngier@arm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
-T:	git git://git.infradead.org/users/jcooper/linux.git irqchip/core
 F:	Documentation/devicetree/bindings/interrupt-controller/
 F:	drivers/irqchip/
 
@@ -10398,7 +10397,7 @@ 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/
 
@@ -14019,6 +14018,7 @@ 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>

+ 1 - 1
Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 13
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*

+ 1 - 0
arch/arm/boot/dts/imx25.dtsi

@@ -297,6 +297,7 @@
 				#address-cells = <1>;
 				#size-cells = <1>;
 				status = "disabled";
+				ranges;
 
 				adc: adc@50030800 {
 					compatible = "fsl,imx25-gcq";

+ 2 - 2
arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi

@@ -507,7 +507,7 @@
 	pinctrl_pcie: pciegrp {
 		fsl,pins = <
 			/* PCIe reset */
-			MX6QDL_PAD_EIM_BCLK__GPIO6_IO31	0x030b0
+			MX6QDL_PAD_EIM_DA0__GPIO3_IO00	0x030b0
 			MX6QDL_PAD_EIM_DA4__GPIO3_IO04	0x030b0
 		>;
 	};
@@ -668,7 +668,7 @@
 &pcie {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_pcie>;
-	reset-gpio = <&gpio6 31 GPIO_ACTIVE_LOW>;
+	reset-gpio = <&gpio3 0 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 

+ 8 - 8
arch/arm/boot/dts/imx7d-sdb.dts

@@ -557,6 +557,14 @@
 			>;
 		};
 
+		pinctrl_spi4: spi4grp {
+			fsl,pins = <
+				MX7D_PAD_GPIO1_IO09__GPIO1_IO9	0x59
+				MX7D_PAD_GPIO1_IO12__GPIO1_IO12	0x59
+				MX7D_PAD_GPIO1_IO13__GPIO1_IO13	0x59
+			>;
+		};
+
 		pinctrl_tsc2046_pendown: tsc2046_pendown {
 			fsl,pins = <
 				MX7D_PAD_EPDC_BDR1__GPIO2_IO29		0x59
@@ -697,13 +705,5 @@
 		fsl,pins = <
 			MX7D_PAD_LPSR_GPIO1_IO01__PWM1_OUT		0x110b0
 		>;
-
-		pinctrl_spi4: spi4grp {
-			fsl,pins = <
-				MX7D_PAD_GPIO1_IO09__GPIO1_IO9	0x59
-				MX7D_PAD_GPIO1_IO12__GPIO1_IO12	0x59
-				MX7D_PAD_GPIO1_IO13__GPIO1_IO13	0x59
-			>;
-		};
 	};
 };

+ 6 - 6
arch/arm/boot/dts/sama5d2.dtsi

@@ -303,7 +303,7 @@
 			#size-cells = <1>;
 			atmel,smc = <&hsmc>;
 			reg = <0x10000000 0x10000000
-			       0x40000000 0x30000000>;
+			       0x60000000 0x30000000>;
 			ranges = <0x0 0x0 0x10000000 0x10000000
 				  0x1 0x0 0x60000000 0x10000000
 				  0x2 0x0 0x70000000 0x10000000
@@ -1048,18 +1048,18 @@
 			};
 
 			hsmc: hsmc@f8014000 {
-				compatible = "atmel,sama5d3-smc", "syscon", "simple-mfd";
+				compatible = "atmel,sama5d2-smc", "syscon", "simple-mfd";
 				reg = <0xf8014000 0x1000>;
-				interrupts = <5 IRQ_TYPE_LEVEL_HIGH 6>;
+				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 6>;
 				clocks = <&hsmc_clk>;
 				#address-cells = <1>;
 				#size-cells = <1>;
 				ranges;
 
-				pmecc: ecc-engine@ffffc070 {
+				pmecc: ecc-engine@f8014070 {
 					compatible = "atmel,sama5d2-pmecc";
-					reg = <0xffffc070 0x490>,
-					      <0xffffc500 0x100>;
+					reg = <0xf8014070 0x490>,
+					      <0xf8014500 0x100>;
 				};
 			};
 

+ 9 - 2
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 */

+ 1 - 0
arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts

@@ -51,6 +51,7 @@
 	compatible = "sinovoip,bananapi-m64", "allwinner,sun50i-a64";
 
 	aliases {
+		ethernet0 = &emac;
 		serial0 = &uart0;
 		serial1 = &uart1;
 	};

+ 1 - 0
arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts

@@ -51,6 +51,7 @@
 	compatible = "pine64,pine64", "allwinner,sun50i-a64";
 
 	aliases {
+		ethernet0 = &emac;
 		serial0 = &uart0;
 		serial1 = &uart1;
 		serial2 = &uart2;

+ 1 - 0
arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts

@@ -53,6 +53,7 @@
 		     "allwinner,sun50i-a64";
 
 	aliases {
+		ethernet0 = &emac;
 		serial0 = &uart0;
 	};
 

+ 3 - 0
arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi

@@ -120,5 +120,8 @@
 };
 
 &pio {
+	interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
 	compatible = "allwinner,sun50i-h5-pinctrl";
 };

+ 1 - 1
arch/arm64/boot/dts/renesas/salvator-common.dtsi

@@ -45,7 +45,7 @@
 		stdout-path = "serial0:115200n8";
 	};
 
-	audio_clkout: audio_clkout {
+	audio_clkout: audio-clkout {
 		/*
 		 * This is same as <&rcar_sound 0>
 		 * but needed to avoid cs2000/rcar_sound probe dead-lock

+ 2 - 2
arch/arm64/include/asm/arch_timer.h

@@ -65,13 +65,13 @@ DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
 	u64 _val;							\
 	if (needs_unstable_timer_counter_workaround()) {		\
 		const struct arch_timer_erratum_workaround *wa;		\
-		preempt_disable();					\
+		preempt_disable_notrace();				\
 		wa = __this_cpu_read(timer_unstable_counter_workaround); \
 		if (wa && wa->read_##reg)				\
 			_val = wa->read_##reg();			\
 		else							\
 			_val = read_sysreg(reg);			\
-		preempt_enable();					\
+		preempt_enable_notrace();				\
 	} else {							\
 		_val = read_sysreg(reg);				\
 	}								\

+ 2 - 2
arch/arm64/include/asm/elf.h

@@ -114,10 +114,10 @@
 
 /*
  * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
  * space open for things that want to use the area for 32-bit pointers.
  */
-#define ELF_ET_DYN_BASE		0x100000000UL
+#define ELF_ET_DYN_BASE		(2 * TASK_SIZE_64 / 3)
 
 #ifndef __ASSEMBLY__
 

+ 6 - 2
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.

+ 1 - 1
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

+ 14 - 1
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/

+ 2 - 0
arch/mips/boot/compressed/.gitignore

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

+ 1 - 1
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 {

+ 6 - 28
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

+ 2 - 0
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)
 

+ 3 - 0
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

+ 36 - 1
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 {

+ 60 - 0
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

+ 1 - 0
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>

+ 3 - 3
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.

+ 1 - 1
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},

+ 1950 - 0
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;
+}

+ 3 - 4
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);
 

+ 4 - 2
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;
 }

+ 1 - 1
arch/powerpc/Kconfig

@@ -199,7 +199,7 @@ config PPC
 	select HAVE_OPTPROBES			if PPC64
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI		if PPC64
-	select HAVE_HARDLOCKUP_DETECTOR_PERF	if HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if SMP

+ 2 - 1
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

+ 2 - 1
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

+ 2 - 1
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

+ 18 - 42
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

+ 3 - 6
arch/powerpc/kernel/process.c

@@ -362,7 +362,8 @@ void enable_kernel_vsx(void)
 
 	cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
 
-	if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) {
+	if (current->thread.regs &&
+	    (current->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP))) {
 		check_if_tm_restore_required(current);
 		/*
 		 * If a thread has already been reclaimed then the
@@ -386,7 +387,7 @@ void flush_vsx_to_thread(struct task_struct *tsk)
 {
 	if (tsk->thread.regs) {
 		preempt_disable();
-		if (tsk->thread.regs->msr & MSR_VSX) {
+		if (tsk->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP)) {
 			BUG_ON(tsk != current);
 			giveup_vsx(tsk);
 		}
@@ -511,10 +512,6 @@ 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;

+ 3 - 3
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);
 	}
 

+ 36 - 13
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;

+ 34 - 23
arch/powerpc/kvm/book3s_64_vio.c

@@ -265,8 +265,11 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 {
 	struct kvmppc_spapr_tce_table *stt = filp->private_data;
 	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
+	struct kvm *kvm = stt->kvm;
 
+	mutex_lock(&kvm->lock);
 	list_del_rcu(&stt->list);
+	mutex_unlock(&kvm->lock);
 
 	list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
 		WARN_ON(!kref_read(&stit->kref));
@@ -294,6 +297,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				   struct kvm_create_spapr_tce_64 *args)
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
+	struct kvmppc_spapr_tce_table *siter;
 	unsigned long npages, size;
 	int ret = -ENOMEM;
 	int i;
@@ -301,25 +305,17 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	if (!args->size)
 		return -EINVAL;
 
-	/* Check this LIOBN hasn't been previously allocated */
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == args->liobn)
-			return -EBUSY;
-	}
-
 	size = _ALIGN_UP(args->size, PAGE_SIZE >> 3);
 	npages = kvmppc_tce_pages(size);
 	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
-	if (ret) {
-		stt = NULL;
-		goto fail;
-	}
+	if (ret)
+		return ret;
 
 	ret = -ENOMEM;
 	stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
 		      GFP_KERNEL);
 	if (!stt)
-		goto fail;
+		goto fail_acct;
 
 	stt->liobn = args->liobn;
 	stt->page_shift = args->page_shift;
@@ -334,24 +330,39 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 			goto fail;
 	}
 
-	kvm_get_kvm(kvm);
-
 	mutex_lock(&kvm->lock);
-	list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
+
+	/* Check this LIOBN hasn't been previously allocated */
+	ret = 0;
+	list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) {
+		if (siter->liobn == args->liobn) {
+			ret = -EBUSY;
+			break;
+		}
+	}
+
+	if (!ret)
+		ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
+				       stt, O_RDWR | O_CLOEXEC);
+
+	if (ret >= 0) {
+		list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
+		kvm_get_kvm(kvm);
+	}
 
 	mutex_unlock(&kvm->lock);
 
-	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				stt, O_RDWR | O_CLOEXEC);
+	if (ret >= 0)
+		return ret;
 
-fail:
-	if (stt) {
-		for (i = 0; i < npages; i++)
-			if (stt->pages[i])
-				__free_page(stt->pages[i]);
+ fail:
+	for (i = 0; i < npages; i++)
+		if (stt->pages[i])
+			__free_page(stt->pages[i]);
 
-		kfree(stt);
-	}
+	kfree(stt);
+ fail_acct:
+	kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
 	return ret;
 }
 

+ 3 - 0
arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1298,6 +1298,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	/* Hypervisor doorbell - exit only if host IPI flag set */
 	cmpwi	r12, BOOK3S_INTERRUPT_H_DOORBELL
 	bne	3f
+BEGIN_FTR_SECTION
+	PPC_MSGSYNC
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
 	beq	4f

+ 65 - 3
arch/powerpc/kvm/book3s_xive_template.c

@@ -16,7 +16,22 @@ static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
 	u8 cppr;
 	u16 ack;
 
-	/* XXX DD1 bug workaround: Check PIPR vs. CPPR first ! */
+	/*
+	 * Ensure any previous store to CPPR is ordered vs.
+	 * the subsequent loads from PIPR or ACK.
+	 */
+	eieio();
+
+	/*
+	 * DD1 bug workaround: If PIPR is less favored than CPPR
+	 * ignore the interrupt or we might incorrectly lose an IPB
+	 * bit.
+	 */
+	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
+		u8 pipr = __x_readb(__x_tima + TM_QW1_OS + TM_PIPR);
+		if (pipr >= xc->hw_cppr)
+			return;
+	}
 
 	/* Perform the acknowledge OS to register cycle. */
 	ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG));
@@ -235,6 +250,11 @@ skip_ipi:
 	/*
 	 * If we found an interrupt, adjust what the guest CPPR should
 	 * be as if we had just fetched that interrupt from HW.
+	 *
+	 * Note: This can only make xc->cppr smaller as the previous
+	 * loop will only exit with hirq != 0 if prio is lower than
+	 * the current xc->cppr. Thus we don't need to re-check xc->mfrr
+	 * for pending IPIs.
 	 */
 	if (hirq)
 		xc->cppr = prio;
@@ -380,6 +400,12 @@ X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
 	old_cppr = xc->cppr;
 	xc->cppr = cppr;
 
+	/*
+	 * Order the above update of xc->cppr with the subsequent
+	 * read of xc->mfrr inside push_pending_to_hw()
+	 */
+	smp_mb();
+
 	/*
 	 * We are masking less, we need to look for pending things
 	 * to deliver and set VP pending bits accordingly to trigger
@@ -420,21 +446,37 @@ X_STATIC int GLUE(X_PFX,h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr)
 	 * used to signal MFRR changes is EOId when fetched from
 	 * the queue.
 	 */
-	if (irq == XICS_IPI || irq == 0)
+	if (irq == XICS_IPI || irq == 0) {
+		/*
+		 * This barrier orders the setting of xc->cppr vs.
+		 * subsquent test of xc->mfrr done inside
+		 * scan_interrupts and push_pending_to_hw
+		 */
+		smp_mb();
 		goto bail;
+	}
 
 	/* Find interrupt source */
 	sb = kvmppc_xive_find_source(xive, irq, &src);
 	if (!sb) {
 		pr_devel(" source not found !\n");
 		rc = H_PARAMETER;
+		/* Same as above */
+		smp_mb();
 		goto bail;
 	}
 	state = &sb->irq_state[src];
 	kvmppc_xive_select_irq(state, &hw_num, &xd);
 
 	state->in_eoi = true;
-	mb();
+
+	/*
+	 * This barrier orders both setting of in_eoi above vs,
+	 * subsequent test of guest_priority, and the setting
+	 * of xc->cppr vs. subsquent test of xc->mfrr done inside
+	 * scan_interrupts and push_pending_to_hw
+	 */
+	smp_mb();
 
 again:
 	if (state->guest_priority == MASKED) {
@@ -461,6 +503,14 @@ again:
 
 	}
 
+	/*
+	 * This barrier orders the above guest_priority check
+	 * and spin_lock/unlock with clearing in_eoi below.
+	 *
+	 * It also has to be a full mb() as it must ensure
+	 * the MMIOs done in source_eoi() are completed before
+	 * state->in_eoi is visible.
+	 */
 	mb();
 	state->in_eoi = false;
 bail:
@@ -495,6 +545,18 @@ X_STATIC int GLUE(X_PFX,h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
 	/* Locklessly write over MFRR */
 	xc->mfrr = mfrr;
 
+	/*
+	 * The load of xc->cppr below and the subsequent MMIO store
+	 * to the IPI must happen after the above mfrr update is
+	 * globally visible so that:
+	 *
+	 * - Synchronize with another CPU doing an H_EOI or a H_CPPR
+	 *   updating xc->cppr then reading xc->mfrr.
+	 *
+	 * - The target of the IPI sees the xc->mfrr update
+	 */
+	mb();
+
 	/* Shoot the IPI if most favored than target cppr */
 	if (mfrr < xc->cppr)
 		__x_writeq(0, __x_trig_page(&xc->vp_ipi_data));

+ 38 - 3
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;
 		}
 

+ 11 - 6
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);
 }
 

+ 2 - 1
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);
 

+ 5 - 3
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 */

+ 16 - 0
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 {

+ 6 - 0
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";

+ 1 - 0
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;

+ 14 - 8
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

+ 13 - 2
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 |

+ 13 - 1
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;

+ 10 - 3
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 */

+ 2 - 1
arch/x86/Kconfig

@@ -100,6 +100,7 @@ config X86
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
+	select HARDLOCKUP_CHECK_TIMESTAMP	if X86_64
 	select HAVE_ACPI_APEI			if ACPI
 	select HAVE_ACPI_APEI_NMI		if ACPI
 	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
@@ -163,7 +164,7 @@ config X86
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI
-	select HAVE_HARDLOCKUP_DETECTOR_PERF	if HAVE_PERF_EVENTS_NMI
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API

+ 36 - 31
arch/x86/crypto/sha1_avx2_x86_64_asm.S

@@ -117,11 +117,10 @@
 	.set T1, REG_T1
 .endm
 
-#define K_BASE		%r8
 #define HASH_PTR	%r9
+#define BLOCKS_CTR	%r8
 #define BUFFER_PTR	%r10
 #define BUFFER_PTR2	%r13
-#define BUFFER_END	%r11
 
 #define PRECALC_BUF	%r14
 #define WK_BUF		%r15
@@ -205,14 +204,14 @@
 		 * blended AVX2 and ALU instruction scheduling
 		 * 1 vector iteration per 8 rounds
 		 */
-		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+		vmovdqu (i * 2)(BUFFER_PTR), W_TMP
 	.elseif ((i & 7) == 1)
-		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+		vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
 			 WY_TMP, WY_TMP
 	.elseif ((i & 7) == 2)
 		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
 	.elseif ((i & 7) == 4)
-		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 	.elseif ((i & 7) == 7)
 		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
 
@@ -255,7 +254,7 @@
 		vpxor	WY, WY_TMP, WY_TMP
 	.elseif ((i & 7) == 7)
 		vpxor	WY_TMP2, WY_TMP, WY
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -291,7 +290,7 @@
 		vpsrld	$30, WY, WY
 		vpor	WY, WY_TMP, WY
 	.elseif ((i & 7) == 7)
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -446,6 +445,16 @@
 
 .endm
 
+/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
+ * %1 + %2 >= %3 ? %4 : 0
+ */
+.macro ADD_IF_GE a, b, c, d
+	mov     \a, RTA
+	add     $\d, RTA
+	cmp     $\c, \b
+	cmovge  RTA, \a
+.endm
+
 /*
  * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
  */
@@ -463,13 +472,16 @@
 	lea	(2*4*80+32)(%rsp), WK_BUF
 
 	# Precalc WK for first 2 blocks
-	PRECALC_OFFSET = 0
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
 	.set i, 0
 	.rept    160
 		PRECALC i
 		.set i, i + 1
 	.endr
-	PRECALC_OFFSET = 128
+
+	/* Go to next block if needed */
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
@@ -479,8 +491,8 @@ _loop:
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
-	cmp	K_BASE, BUFFER_PTR
-	jne	_begin
+	test BLOCKS_CTR, BLOCKS_CTR
+	jnz _begin
 	.align 32
 	jmp	_end
 	.align 32
@@ -512,10 +524,10 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
-	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
-	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
-
+	/* Update Counter */
+	sub $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
 	/*
 	 * rounds
 	 * 60,62,64,66,68
@@ -532,8 +544,8 @@ _loop0:
 	UPDATE_HASH	12(HASH_PTR), D
 	UPDATE_HASH	16(HASH_PTR), E
 
-	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
-	je	_loop
+	test	BLOCKS_CTR, BLOCKS_CTR
+	jz	_loop
 
 	mov	TB, B
 
@@ -575,10 +587,10 @@ _loop2:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
-
-	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
-	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+	/* update counter */
+	sub     $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
 	jmp	_loop3
 _loop3:
@@ -641,19 +653,12 @@ _loop3:
 
 	avx2_zeroupper
 
-	lea	K_XMM_AR(%rip), K_BASE
-
+	/* Setup initial values */
 	mov	CTX, HASH_PTR
 	mov	BUF, BUFFER_PTR
-	lea	64(BUF), BUFFER_PTR2
-
-	shl	$6, CNT			/* mul by 64 */
-	add	BUF, CNT
-	add	$64, CNT
-	mov	CNT, BUFFER_END
 
-	cmp	BUFFER_END, BUFFER_PTR2
-	cmovae	K_BASE, BUFFER_PTR2
+	mov	BUF, BUFFER_PTR2
+	mov	CNT, BLOCKS_CTR
 
 	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
 

+ 1 - 1
arch/x86/crypto/sha1_ssse3_glue.c

@@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
 
 static bool avx2_usable(void)
 {
-	if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
 		&& boot_cpu_has(X86_FEATURE_BMI1)
 		&& boot_cpu_has(X86_FEATURE_BMI2))
 		return true;

+ 2 - 0
arch/x86/entry/entry_64.S

@@ -1211,6 +1211,8 @@ ENTRY(nmi)
 	 * other IST entries.
 	 */
 
+	ASM_CLAC
+
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
 

+ 7 - 9
arch/x86/events/core.c

@@ -2114,7 +2114,7 @@ static void refresh_pce(void *ignored)
 	load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm));
 }
 
-static void x86_pmu_event_mapped(struct perf_event *event)
+static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
 {
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
@@ -2129,22 +2129,20 @@ static void x86_pmu_event_mapped(struct perf_event *event)
 	 * For now, this can't happen because all callers hold mmap_sem
 	 * for write.  If this changes, we'll need a different solution.
 	 */
-	lockdep_assert_held_exclusive(&current->mm->mmap_sem);
+	lockdep_assert_held_exclusive(&mm->mmap_sem);
 
-	if (atomic_inc_return(&current->mm->context.perf_rdpmc_allowed) == 1)
-		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
+	if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1)
+		on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1);
 }
 
-static void x86_pmu_event_unmapped(struct perf_event *event)
+static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
 {
-	if (!current->mm)
-		return;
 
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
 
-	if (atomic_dec_and_test(&current->mm->context.perf_rdpmc_allowed))
-		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
+	if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed))
+		on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1);
 }
 
 static int x86_pmu_event_idx(struct perf_event *event)

+ 1 - 1
arch/x86/events/intel/bts.c

@@ -69,7 +69,7 @@ struct bts_buffer {
 	struct bts_phys	buf[0];
 };
 
-struct pmu bts_pmu;
+static struct pmu bts_pmu;
 
 static size_t buf_size(struct page *page)
 {

+ 1 - 1
arch/x86/events/intel/p4.c

@@ -587,7 +587,7 @@ static __initconst const u64 p4_hw_cache_event_ids
  * P4_CONFIG_ALIASABLE or bits for P4_PEBS_METRIC, they are
  * either up to date automatically or not applicable at all.
  */
-struct p4_event_alias {
+static struct p4_event_alias {
 	u64 original;
 	u64 alternative;
 } p4_event_aliases[] = {

+ 1 - 1
arch/x86/events/intel/rapl.c

@@ -559,7 +559,7 @@ static struct attribute_group rapl_pmu_format_group = {
 	.attrs = rapl_formats_attr,
 };
 
-const struct attribute_group *rapl_attr_groups[] = {
+static const struct attribute_group *rapl_attr_groups[] = {
 	&rapl_pmu_attr_group,
 	&rapl_pmu_format_group,
 	&rapl_pmu_events_group,

+ 1 - 1
arch/x86/events/intel/uncore.c

@@ -721,7 +721,7 @@ static struct attribute *uncore_pmu_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group uncore_pmu_attr_group = {
+static const struct attribute_group uncore_pmu_attr_group = {
 	.attrs = uncore_pmu_attrs,
 };
 

+ 6 - 6
arch/x86/events/intel/uncore_nhmex.c

@@ -272,7 +272,7 @@ static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_ubox_format_group = {
+static const struct attribute_group nhmex_uncore_ubox_format_group = {
 	.name		= "format",
 	.attrs		= nhmex_uncore_ubox_formats_attr,
 };
@@ -299,7 +299,7 @@ static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_cbox_format_group = {
+static const struct attribute_group nhmex_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = nhmex_uncore_cbox_formats_attr,
 };
@@ -407,7 +407,7 @@ static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_bbox_format_group = {
+static const struct attribute_group nhmex_uncore_bbox_format_group = {
 	.name = "format",
 	.attrs = nhmex_uncore_bbox_formats_attr,
 };
@@ -484,7 +484,7 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_sbox_format_group = {
+static const struct attribute_group nhmex_uncore_sbox_format_group = {
 	.name			= "format",
 	.attrs			= nhmex_uncore_sbox_formats_attr,
 };
@@ -898,7 +898,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_mbox_format_group = {
+static const struct attribute_group nhmex_uncore_mbox_format_group = {
 	.name		= "format",
 	.attrs		= nhmex_uncore_mbox_formats_attr,
 };
@@ -1163,7 +1163,7 @@ static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_rbox_format_group = {
+static const struct attribute_group nhmex_uncore_rbox_format_group = {
 	.name = "format",
 	.attrs = nhmex_uncore_rbox_formats_attr,
 };

+ 3 - 3
arch/x86/events/intel/uncore_snb.c

@@ -130,7 +130,7 @@ static struct attribute *snb_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group snb_uncore_format_group = {
+static const struct attribute_group snb_uncore_format_group = {
 	.name		= "format",
 	.attrs		= snb_uncore_formats_attr,
 };
@@ -289,7 +289,7 @@ static struct attribute *snb_uncore_imc_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group snb_uncore_imc_format_group = {
+static const struct attribute_group snb_uncore_imc_format_group = {
 	.name = "format",
 	.attrs = snb_uncore_imc_formats_attr,
 };
@@ -769,7 +769,7 @@ static struct attribute *nhm_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhm_uncore_format_group = {
+static const struct attribute_group nhm_uncore_format_group = {
 	.name = "format",
 	.attrs = nhm_uncore_formats_attr,
 };

+ 21 - 21
arch/x86/events/intel/uncore_snbep.c

@@ -602,27 +602,27 @@ static struct uncore_event_desc snbep_uncore_qpi_events[] = {
 	{ /* end: all zeroes */ },
 };
 
-static struct attribute_group snbep_uncore_format_group = {
+static const struct attribute_group snbep_uncore_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_ubox_format_group = {
+static const struct attribute_group snbep_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_ubox_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_cbox_format_group = {
+static const struct attribute_group snbep_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_cbox_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_pcu_format_group = {
+static const struct attribute_group snbep_uncore_pcu_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_pcu_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_qpi_format_group = {
+static const struct attribute_group snbep_uncore_qpi_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_qpi_formats_attr,
 };
@@ -1431,27 +1431,27 @@ static struct attribute *ivbep_uncore_qpi_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group ivbep_uncore_format_group = {
+static const struct attribute_group ivbep_uncore_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_ubox_format_group = {
+static const struct attribute_group ivbep_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_ubox_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_cbox_format_group = {
+static const struct attribute_group ivbep_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_cbox_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_pcu_format_group = {
+static const struct attribute_group ivbep_uncore_pcu_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_pcu_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_qpi_format_group = {
+static const struct attribute_group ivbep_uncore_qpi_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_qpi_formats_attr,
 };
@@ -1887,7 +1887,7 @@ static struct attribute *knl_uncore_ubox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_ubox_format_group = {
+static const struct attribute_group knl_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_ubox_formats_attr,
 };
@@ -1927,7 +1927,7 @@ static struct attribute *knl_uncore_cha_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_cha_format_group = {
+static const struct attribute_group knl_uncore_cha_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_cha_formats_attr,
 };
@@ -2037,7 +2037,7 @@ static struct attribute *knl_uncore_pcu_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_pcu_format_group = {
+static const struct attribute_group knl_uncore_pcu_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_pcu_formats_attr,
 };
@@ -2187,7 +2187,7 @@ static struct attribute *knl_uncore_irp_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_irp_format_group = {
+static const struct attribute_group knl_uncore_irp_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_irp_formats_attr,
 };
@@ -2385,7 +2385,7 @@ static struct attribute *hswep_uncore_ubox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hswep_uncore_ubox_format_group = {
+static const struct attribute_group hswep_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = hswep_uncore_ubox_formats_attr,
 };
@@ -2439,7 +2439,7 @@ static struct attribute *hswep_uncore_cbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hswep_uncore_cbox_format_group = {
+static const struct attribute_group hswep_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = hswep_uncore_cbox_formats_attr,
 };
@@ -2621,7 +2621,7 @@ static struct attribute *hswep_uncore_sbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hswep_uncore_sbox_format_group = {
+static const struct attribute_group hswep_uncore_sbox_format_group = {
 	.name = "format",
 	.attrs = hswep_uncore_sbox_formats_attr,
 };
@@ -3314,7 +3314,7 @@ static struct attribute *skx_uncore_cha_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_uncore_chabox_format_group = {
+static const struct attribute_group skx_uncore_chabox_format_group = {
 	.name = "format",
 	.attrs = skx_uncore_cha_formats_attr,
 };
@@ -3427,7 +3427,7 @@ static struct attribute *skx_uncore_iio_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_uncore_iio_format_group = {
+static const struct attribute_group skx_uncore_iio_format_group = {
 	.name = "format",
 	.attrs = skx_uncore_iio_formats_attr,
 };
@@ -3484,7 +3484,7 @@ static struct attribute *skx_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_uncore_format_group = {
+static const struct attribute_group skx_uncore_format_group = {
 	.name = "format",
 	.attrs = skx_uncore_formats_attr,
 };
@@ -3605,7 +3605,7 @@ static struct attribute *skx_upi_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_upi_uncore_format_group = {
+static const struct attribute_group skx_upi_uncore_format_group = {
 	.name = "format",
 	.attrs = skx_upi_uncore_formats_attr,
 };

+ 1 - 1
arch/x86/include/asm/cpufeatures.h

@@ -286,7 +286,7 @@
 #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */
+#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
 #define X86_FEATURE_VGIF	(15*32+16) /* Virtual GIF */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */

+ 2 - 2
arch/x86/include/asm/elf.h

@@ -247,11 +247,11 @@ extern int force_personality32;
 
 /*
  * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
  * space open for things that want to use the area for 32-bit pointers.
  */
 #define ELF_ET_DYN_BASE		(mmap_is_ia32() ? 0x000400000UL : \
-						  0x100000000UL)
+						  (TASK_SIZE / 3 * 2))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,

+ 3 - 3
arch/x86/include/asm/fpu/internal.h

@@ -450,10 +450,10 @@ static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
 	return 0;
 }
 
-static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate)
+static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask)
 {
 	if (use_xsave()) {
-		copy_kernel_to_xregs(&fpstate->xsave, -1);
+		copy_kernel_to_xregs(&fpstate->xsave, mask);
 	} else {
 		if (use_fxsr())
 			copy_kernel_to_fxregs(&fpstate->fxsave);
@@ -477,7 +477,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
 			: : [addr] "m" (fpstate));
 	}
 
-	__copy_kernel_to_fpregs(fpstate);
+	__copy_kernel_to_fpregs(fpstate, -1);
 }
 
 extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);

+ 10 - 0
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 */

+ 1 - 0
arch/x86/include/asm/kvm_host.h

@@ -492,6 +492,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr4;
 	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
+	u32 pkru;
 	u32 hflags;
 	u64 efer;
 	u64 apic_base;

+ 3 - 0
arch/x86/kernel/cpu/aperfmperf.c

@@ -40,13 +40,16 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	struct aperfmperf_sample *s = this_cpu_ptr(&samples);
 	ktime_t now = ktime_get();
 	s64 time_delta = ktime_ms_delta(now, s->time);
+	unsigned long flags;
 
 	/* Don't bother re-computing within the cache threshold time. */
 	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
 		return;
 
+	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
+	local_irq_restore(flags);
 
 	aperf_delta = aperf - s->aperf;
 	mperf_delta = mperf - s->mperf;

+ 1 - 1
arch/x86/kernel/cpu/mcheck/therm_throt.c

@@ -122,7 +122,7 @@ static struct attribute *thermal_throttle_attrs[] = {
 	NULL
 };
 
-static struct attribute_group thermal_attr_group = {
+static const struct attribute_group thermal_attr_group = {
 	.attrs	= thermal_throttle_attrs,
 	.name	= "thermal_throttle"
 };

+ 2 - 2
arch/x86/kernel/cpu/microcode/core.c

@@ -561,7 +561,7 @@ static struct attribute *mc_default_attrs[] = {
 	NULL
 };
 
-static struct attribute_group mc_attr_group = {
+static const struct attribute_group mc_attr_group = {
 	.attrs			= mc_default_attrs,
 	.name			= "microcode",
 };
@@ -707,7 +707,7 @@ static struct attribute *cpu_root_microcode_attrs[] = {
 	NULL
 };
 
-static struct attribute_group cpu_root_microcode_group = {
+static const struct attribute_group cpu_root_microcode_group = {
 	.name  = "microcode",
 	.attrs = cpu_root_microcode_attrs,
 };

+ 15 - 3
arch/x86/kernel/cpu/mtrr/main.c

@@ -237,6 +237,18 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 	stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask);
 }
 
+static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base,
+				unsigned long size, mtrr_type type)
+{
+	struct set_mtrr_data data = { .smp_reg = reg,
+				      .smp_base = base,
+				      .smp_size = size,
+				      .smp_type = type
+				    };
+
+	stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask);
+}
+
 static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base,
 				      unsigned long size, mtrr_type type)
 {
@@ -370,7 +382,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 	/* Search for an empty MTRR */
 	i = mtrr_if->get_free_region(base, size, replace);
 	if (i >= 0) {
-		set_mtrr(i, base, size, type);
+		set_mtrr_cpuslocked(i, base, size, type);
 		if (likely(replace < 0)) {
 			mtrr_usage_table[i] = 1;
 		} else {
@@ -378,7 +390,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 			if (increment)
 				mtrr_usage_table[i]++;
 			if (unlikely(replace != i)) {
-				set_mtrr(replace, 0, 0, 0);
+				set_mtrr_cpuslocked(replace, 0, 0, 0);
 				mtrr_usage_table[replace] = 0;
 			}
 		}
@@ -506,7 +518,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 		goto out;
 	}
 	if (--mtrr_usage_table[reg] < 1)
-		set_mtrr(reg, 0, 0, 0);
+		set_mtrr_cpuslocked(reg, 0, 0, 0);
 	error = reg;
  out:
 	mutex_unlock(&mtrr_mutex);

+ 4 - 3
arch/x86/kernel/head64.c

@@ -53,6 +53,7 @@ void __head __startup_64(unsigned long physaddr)
 	pudval_t *pud;
 	pmdval_t *pmd, pmd_entry;
 	int i;
+	unsigned int *next_pgt_ptr;
 
 	/* Is the address too large? */
 	if (physaddr >> MAX_PHYSMEM_BITS)
@@ -91,9 +92,9 @@ void __head __startup_64(unsigned long physaddr)
 	 * creates a bunch of nonsense entries but that is fine --
 	 * it avoids problems around wraparound.
 	 */
-
-	pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
-	pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
+	next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr);
+	pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
+	pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
 
 	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
 		p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);

+ 2 - 2
arch/x86/kernel/ksysfs.c

@@ -55,7 +55,7 @@ static struct bin_attribute *boot_params_data_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group boot_params_attr_group = {
+static const struct attribute_group boot_params_attr_group = {
 	.attrs = boot_params_version_attrs,
 	.bin_attrs = boot_params_data_attrs,
 };
@@ -202,7 +202,7 @@ static struct bin_attribute *setup_data_data_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group setup_data_attr_group = {
+static const struct attribute_group setup_data_attr_group = {
 	.attrs = setup_data_type_attrs,
 	.bin_attrs = setup_data_data_attrs,
 };

+ 17 - 13
arch/x86/kernel/smpboot.c

@@ -971,7 +971,8 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle)
  * Returns zero if CPU booted OK, else error code from
  * ->wakeup_secondary_cpu.
  */
-static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
+static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
+		       int *cpu0_nmi_registered)
 {
 	volatile u32 *trampoline_status =
 		(volatile u32 *) __va(real_mode_header->trampoline_status);
@@ -979,7 +980,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	unsigned long start_ip = real_mode_header->trampoline_start;
 
 	unsigned long boot_error = 0;
-	int cpu0_nmi_registered = 0;
 	unsigned long timeout;
 
 	idle->thread.sp = (unsigned long)task_pt_regs(idle);
@@ -1035,7 +1035,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 		boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
 	else
 		boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
-						     &cpu0_nmi_registered);
+						     cpu0_nmi_registered);
 
 	if (!boot_error) {
 		/*
@@ -1080,12 +1080,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 		 */
 		smpboot_restore_warm_reset_vector();
 	}
-	/*
-	 * Clean up the nmi handler. Do this after the callin and callout sync
-	 * to avoid impact of possible long unregister time.
-	 */
-	if (cpu0_nmi_registered)
-		unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
 
 	return boot_error;
 }
@@ -1093,8 +1087,9 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int apicid = apic->cpu_present_to_apicid(cpu);
+	int cpu0_nmi_registered = 0;
 	unsigned long flags;
-	int err;
+	int err, ret = 0;
 
 	WARN_ON(irqs_disabled());
 
@@ -1131,10 +1126,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 	common_cpu_up(cpu, tidle);
 
-	err = do_boot_cpu(apicid, cpu, tidle);
+	err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
 	if (err) {
 		pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
-		return -EIO;
+		ret = -EIO;
+		goto unreg_nmi;
 	}
 
 	/*
@@ -1150,7 +1146,15 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 		touch_nmi_watchdog();
 	}
 
-	return 0;
+unreg_nmi:
+	/*
+	 * Clean up the nmi handler. Do this after the callin and callout sync
+	 * to avoid impact of possible long unregister time.
+	 */
+	if (cpu0_nmi_registered)
+		unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
+
+	return ret;
 }
 
 /**

+ 1 - 1
arch/x86/kvm/cpuid.c

@@ -474,7 +474,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
 			cpuid_mask(&entry->ecx, CPUID_7_ECX);
 			/* PKU is not yet implemented for shadow paging. */
-			if (!tdp_enabled)
+			if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
 				entry->ecx &= ~F(PKU);
 			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
 			entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);

+ 0 - 5
arch/x86/kvm/kvm_cache_regs.h

@@ -84,11 +84,6 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu)
 		| ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32);
 }
 
-static inline u32 kvm_read_pkru(struct kvm_vcpu *vcpu)
-{
-	return kvm_x86_ops->get_pkru(vcpu);
-}
-
 static inline void enter_guest_mode(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hflags |= HF_GUEST_MASK;

+ 1 - 1
arch/x86/kvm/mmu.h

@@ -172,7 +172,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		* index of the protection domain, so pte_pkey * 2 is
 		* is the index of the first bit for the domain.
 		*/
-		pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3;
+		pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3;
 
 		/* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */
 		offset = (pfec & ~1) +

+ 1 - 8
arch/x86/kvm/svm.c

@@ -1117,7 +1117,7 @@ static __init int svm_hardware_setup(void)
 
 	if (vls) {
 		if (!npt_enabled ||
-		    !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) ||
+		    !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) ||
 		    !IS_ENABLED(CONFIG_X86_64)) {
 			vls = false;
 		} else {
@@ -1790,11 +1790,6 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
 }
 
-static u32 svm_get_pkru(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
 static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 {
 	switch (reg) {
@@ -5436,8 +5431,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
 
-	.get_pkru = svm_get_pkru,
-
 	.tlb_flush = svm_flush_tlb,
 
 	.run = svm_vcpu_run,

+ 8 - 17
arch/x86/kvm/vmx.c

@@ -641,8 +641,6 @@ struct vcpu_vmx {
 
 	u64 current_tsc_ratio;
 
-	bool guest_pkru_valid;
-	u32 guest_pkru;
 	u32 host_pkru;
 
 	/*
@@ -2398,11 +2396,6 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 		to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
 }
 
-static u32 vmx_get_pkru(struct kvm_vcpu *vcpu)
-{
-	return to_vmx(vcpu)->guest_pkru;
-}
-
 static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
@@ -9291,8 +9284,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
-	if (vmx->guest_pkru_valid)
-		__write_pkru(vmx->guest_pkru);
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
+	    vcpu->arch.pkru != vmx->host_pkru)
+		__write_pkru(vcpu->arch.pkru);
 
 	atomic_switch_perf_msrs(vmx);
 	debugctlmsr = get_debugctlmsr();
@@ -9440,13 +9435,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * back on host, so it is safe to read guest PKRU from current
 	 * XSAVE.
 	 */
-	if (boot_cpu_has(X86_FEATURE_OSPKE)) {
-		vmx->guest_pkru = __read_pkru();
-		if (vmx->guest_pkru != vmx->host_pkru) {
-			vmx->guest_pkru_valid = true;
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
+		vcpu->arch.pkru = __read_pkru();
+		if (vcpu->arch.pkru != vmx->host_pkru)
 			__write_pkru(vmx->host_pkru);
-		} else
-			vmx->guest_pkru_valid = false;
 	}
 
 	/*
@@ -11964,8 +11957,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
 
-	.get_pkru = vmx_get_pkru,
-
 	.tlb_flush = vmx_flush_tlb,
 
 	.run = vmx_vcpu_run,

+ 14 - 3
arch/x86/kvm/x86.c

@@ -3269,7 +3269,12 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 			u32 size, offset, ecx, edx;
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
-			memcpy(dest + offset, src, size);
+			if (feature == XFEATURE_MASK_PKRU)
+				memcpy(dest + offset, &vcpu->arch.pkru,
+				       sizeof(vcpu->arch.pkru));
+			else
+				memcpy(dest + offset, src, size);
+
 		}
 
 		valid -= feature;
@@ -3307,7 +3312,11 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 			u32 size, offset, ecx, edx;
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
-			memcpy(dest, src + offset, size);
+			if (feature == XFEATURE_MASK_PKRU)
+				memcpy(&vcpu->arch.pkru, src + offset,
+				       sizeof(vcpu->arch.pkru));
+			else
+				memcpy(dest, src + offset, size);
 		}
 
 		valid -= feature;
@@ -7667,7 +7676,9 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 */
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
-	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
+	/* PKRU is separately restored in kvm_x86_ops->run.  */
+	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
+				~XFEATURE_MASK_PKRU);
 	trace_kvm_fpu(1);
 }
 

+ 3 - 0
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);
 }
 

+ 3 - 4
arch/x86/mm/mmap.c

@@ -50,8 +50,7 @@ unsigned long tasksize_64bit(void)
 static unsigned long stack_maxrandom_size(unsigned long task_size)
 {
 	unsigned long max = 0;
-	if ((current->flags & PF_RANDOMIZE) &&
-		!(current->personality & ADDR_NO_RANDOMIZE)) {
+	if (current->flags & PF_RANDOMIZE) {
 		max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit());
 		max <<= PAGE_SHIFT;
 	}
@@ -79,13 +78,13 @@ static int mmap_is_legacy(void)
 
 static unsigned long arch_rnd(unsigned int rndbits)
 {
+	if (!(current->flags & PF_RANDOMIZE))
+		return 0;
 	return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT;
 }
 
 unsigned long arch_mmap_rnd(void)
 {
-	if (!(current->flags & PF_RANDOMIZE))
-		return 0;
 	return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits);
 }
 

+ 2 - 2
arch/x86/platform/uv/tlb_uv.c

@@ -26,7 +26,7 @@
 static struct bau_operations ops __ro_after_init;
 
 /* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */
-static int timeout_base_ns[] = {
+static const int timeout_base_ns[] = {
 		20,
 		160,
 		1280,
@@ -1216,7 +1216,7 @@ static struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg,
  * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register.
  * Such a message must be ignored.
  */
-void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
+static void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
 {
 	unsigned long mmr_image;
 	unsigned char swack_vec;

+ 37 - 22
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);

+ 2 - 0
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

+ 0 - 15
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 */

+ 0 - 18
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 */

+ 0 - 2
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

+ 8 - 8
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,

+ 17 - 5
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 */

+ 81 - 65
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);

+ 4 - 2
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;

+ 7 - 1
block/blk-mq-pci.c

@@ -36,12 +36,18 @@ int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev)
 	for (queue = 0; queue < set->nr_hw_queues; queue++) {
 		mask = pci_irq_get_affinity(pdev, queue);
 		if (!mask)
-			return -EINVAL;
+			goto fallback;
 
 		for_each_cpu(cpu, mask)
 			set->mq_map[cpu] = queue;
 	}
 
 	return 0;
+
+fallback:
+	WARN_ON_ONCE(set->nr_hw_queues > 1);
+	for_each_possible_cpu(cpu)
+		set->mq_map[cpu] = 0;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);

+ 10 - 6
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;
 	}
@@ -355,13 +360,13 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 		return ERR_PTR(ret);
 
 	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);
+
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
@@ -406,7 +411,6 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
 
 	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
-
 	blk_queue_exit(q);
 
 	if (!rq)
@@ -679,8 +683,8 @@ 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);
 

+ 34 - 2
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";
 

Alguns arquivos não foram mostrados porque muitos arquivos mudaram nesse diff