diff options
author | Kevin Hilman <khilman@linaro.org> | 2015-06-16 15:29:36 -0700 |
---|---|---|
committer | Kevin Hilman <khilman@linaro.org> | 2015-06-16 15:29:36 -0700 |
commit | b0477f5f8ec85bf8a82f6aa6eee308d72c418032 (patch) | |
tree | d520be10a261f418dbf4539f1d2b5d48d74ba0d3 /arch | |
parent | 13a29d9ad242f0bf3b31afe812c81558d54892de (diff) | |
parent | 9a004a75a3305fbd3c253f38cd0788164c4fbd56 (diff) |
Merge branch 'linux-linaro-lsk-v3.18' into linux-linaro-lsk-v3.18-androidlsk-v3.18-15.07-android
Diffstat (limited to 'arch')
120 files changed, 1125 insertions, 537 deletions
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 067551b6920a..9917a45fc430 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -99,7 +99,7 @@ static inline void atomic_##op(int i, atomic_t *v) \ atomic_ops_unlock(flags); \ } -#define ATOMIC_OP_RETURN(op, c_op) \ +#define ATOMIC_OP_RETURN(op, c_op, asm_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ unsigned long flags; \ diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index 4e5a59ee1501..db06fa397f79 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -71,6 +71,10 @@ }; internal-regs { + rtc@10300 { + /* No crystal connected to the internal RTC */ + status = "disabled"; + }; serial@12000 { status = "okay"; }; diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi index a5441d5482a6..3cc8b8320345 100644 --- a/arch/arm/boot/dts/dove.dtsi +++ b/arch/arm/boot/dts/dove.dtsi @@ -154,7 +154,7 @@ uart2: serial@12200 { compatible = "ns16550a"; - reg = <0x12000 0x100>; + reg = <0x12200 0x100>; reg-shift = <2>; interrupts = <9>; clocks = <&core_clk 0>; @@ -163,7 +163,7 @@ uart3: serial@12300 { compatible = "ns16550a"; - reg = <0x12100 0x100>; + reg = <0x12300 0x100>; reg-shift = <2>; interrupts = <10>; clocks = <&core_clk 0>; diff --git a/arch/arm/boot/dts/imx23-olinuxino.dts b/arch/arm/boot/dts/imx23-olinuxino.dts index 7e6eef2488e8..82045398bf1f 100644 --- a/arch/arm/boot/dts/imx23-olinuxino.dts +++ b/arch/arm/boot/dts/imx23-olinuxino.dts @@ -12,6 +12,7 @@ */ /dts-v1/; +#include <dt-bindings/gpio/gpio.h> #include "imx23.dtsi" / { @@ -93,6 +94,7 @@ ahb@80080000 { usb0: usb@80080000 { + dr_mode = "host"; vbus-supply = <®_usb0_vbus>; status = "okay"; }; @@ -122,7 +124,7 @@ user { label = "green"; - gpios = <&gpio2 1 1>; + gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>; }; }; }; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index e4d3aecc4ed2..677f81d9dcd5 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -428,6 +428,7 @@ pwm4: pwm@53fc8000 { compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; + #pwm-cells = <2>; reg = <0x53fc8000 0x4000>; clocks = <&clks 108>, <&clks 52>; clock-names = "ipg", "per"; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index 107d713e1cbe..12ac5f7e0a2e 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -531,7 +531,7 @@ fec: ethernet@1002b000 { compatible = "fsl,imx27-fec"; - reg = <0x1002b000 0x4000>; + reg = <0x1002b000 0x1000>; interrupts = <50>; clocks = <&clks IMX27_CLK_FEC_IPG_GATE>, <&clks IMX27_CLK_FEC_AHB_GATE>; diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index 47f68ac868d4..5ed245a3f9ac 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -900,7 +900,7 @@ 80 81 68 69 70 71 72 73 74 75 76 77>; - interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty", + interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty", "saif0", "saif1", "i2c0", "i2c1", "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx", "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx"; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi index 0e50bb0a6b94..413569752422 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi @@ -31,6 +31,7 @@ regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; gpio = <&gpio4 15 0>; + enable-active-high; }; reg_usb_h1_vbus: regulator@1 { @@ -40,6 +41,7 @@ regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; gpio = <&gpio1 0 0>; + enable-active-high; }; }; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index bc82a12d4c2c..ae630a928acd 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -445,6 +445,8 @@ DRVDD-supply = <&vmmc2>; IOVDD-supply = <&vio>; DVDD-supply = <&vio>; + + ai3x-micbias-vg = <1>; }; tlv320aic3x_aux: tlv320aic3x@19 { @@ -456,6 +458,8 @@ DRVDD-supply = <&vmmc2>; IOVDD-supply = <&vio>; DVDD-supply = <&vio>; + + ai3x-micbias-vg = <2>; }; tsl2563: tsl2563@29 { diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi index 9d2323020d34..563640f59a41 100644 --- a/arch/arm/boot/dts/ste-dbx5x0.dtsi +++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi @@ -995,23 +995,6 @@ status = "disabled"; }; - vmmci: regulator-gpio { - compatible = "regulator-gpio"; - - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <2900000>; - regulator-name = "mmci-reg"; - regulator-type = "voltage"; - - startup-delay-us = <100>; - enable-active-high; - - states = <1800000 0x1 - 2900000 0x0>; - - status = "disabled"; - }; - mcde@a0350000 { compatible = "stericsson,mcde"; reg = <0xa0350000 0x1000>, /* MCDE */ diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi index bf8f0eddc2c0..744c1e3a744d 100644 --- a/arch/arm/boot/dts/ste-href.dtsi +++ b/arch/arm/boot/dts/ste-href.dtsi @@ -111,6 +111,21 @@ pinctrl-1 = <&i2c3_sleep_mode>; }; + vmmci: regulator-gpio { + compatible = "regulator-gpio"; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-name = "mmci-reg"; + regulator-type = "voltage"; + + startup-delay-us = <100>; + enable-active-high; + + states = <1800000 0x1 + 2900000 0x0>; + }; + // External Micro SD slot sdi0_per1@80126000 { arm,primecell-periphid = <0x10480180>; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index 3e97a669f15e..17c4422def0e 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -146,8 +146,21 @@ }; vmmci: regulator-gpio { + compatible = "regulator-gpio"; + gpios = <&gpio7 4 0x4>; enable-gpio = <&gpio6 25 0x4>; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-name = "mmci-reg"; + regulator-type = "voltage"; + + startup-delay-us = <100>; + enable-active-high; + + states = <1800000 0x1 + 2900000 0x0>; }; // External Micro SD slot diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index afb9cafd3786..674d03f4ba15 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -115,7 +115,7 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs); the loader. We need to make sure that it is out of the way of the program that it will "exec", and that there is sufficient room for the brk. */ -#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3) +#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) /* When the program starts, a1 contains a pointer to a function to be registered with atexit, as per the SVR4 ABI. A value of 0 means we diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index b9db269c6e61..66ce17655bb9 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -33,6 +33,11 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr = HCR_GUEST_MASK; +} + static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) { return 1; diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index acb0d5712716..16d9d788d0b8 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -44,6 +44,7 @@ #ifndef __ASSEMBLY__ +#include <linux/highmem.h> #include <asm/cacheflush.h> #include <asm/pgalloc.h> @@ -52,6 +53,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t); void free_boot_hyp_pgd(void); void free_hyp_pgds(void); +void stage2_unmap_vm(struct kvm *kvm); int kvm_alloc_stage2_pgd(struct kvm *kvm); void kvm_free_stage2_pgd(struct kvm *kvm); int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, @@ -126,29 +128,28 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) +#define kvm_pgd_index(addr) pgd_index(addr) + static inline bool kvm_page_empty(void *ptr) { struct page *ptr_page = virt_to_page(ptr); return page_count(ptr_page) == 1; } - #define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) #define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp) #define kvm_pud_table_empty(kvm, pudp) (0) #define KVM_PREALLOC_LEVEL 0 -static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd) +static inline void *kvm_get_hwpgd(struct kvm *kvm) { - return 0; + return kvm->arch.pgd; } -static inline void kvm_free_hwpgd(struct kvm *kvm) { } - -static inline void *kvm_get_hwpgd(struct kvm *kvm) +static inline unsigned int kvm_get_hwpgd_size(void) { - return kvm->arch.pgd; + return PTRS_PER_S2_PGD * sizeof(pgd_t); } struct kvm; @@ -160,12 +161,10 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; } -static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, - unsigned long size) +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, + bool ipa_uncached) { - if (!vcpu_has_cache_enabled(vcpu)) - kvm_flush_dcache_to_poc((void *)hva, size); - /* * If we are going to insert an instruction page and the icache is * either VIPT or PIPT, there is a potential problem where the host @@ -177,15 +176,73 @@ static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, * * VIVT caches are tagged using both the ASID and the VMID and doesn't * need any kind of flushing (DDI 0406C.b - Page B3-1392). + * + * We need to do this through a kernel mapping (using the + * user-space mapping has proved to be the wrong + * solution). For that, we need to kmap one page at a time, + * and iterate over the range. */ - if (icache_is_pipt()) { - __cpuc_coherent_user_range(hva, hva + size); - } else if (!icache_is_vivt_asid_tagged()) { + + bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached; + + VM_BUG_ON(size & ~PAGE_MASK); + + if (!need_flush && !icache_is_pipt()) + goto vipt_cache; + + while (size) { + void *va = kmap_atomic_pfn(pfn); + + if (need_flush) + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + if (icache_is_pipt()) + __cpuc_coherent_user_range((unsigned long)va, + (unsigned long)va + PAGE_SIZE); + + size -= PAGE_SIZE; + pfn++; + + kunmap_atomic(va); + } + +vipt_cache: + if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) { /* any kind of VIPT cache */ __flush_icache_all(); } } +static inline void __kvm_flush_dcache_pte(pte_t pte) +{ + void *va = kmap_atomic(pte_page(pte)); + + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + kunmap_atomic(va); +} + +static inline void __kvm_flush_dcache_pmd(pmd_t pmd) +{ + unsigned long size = PMD_SIZE; + pfn_t pfn = pmd_pfn(pmd); + + while (size) { + void *va = kmap_atomic_pfn(pfn); + + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + pfn++; + size -= PAGE_SIZE; + + kunmap_atomic(va); + } +} + +static inline void __kvm_flush_dcache_pud(pud_t pud) +{ +} + #define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x)) void stage2_flush_vm(struct kvm *kvm); diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 09ee408c1a67..b404cf886029 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -193,8 +193,14 @@ struct kvm_arch_memory_slot { #define KVM_ARM_IRQ_CPU_IRQ 0 #define KVM_ARM_IRQ_CPU_FIQ 1 -/* Highest supported SPI, from VGIC_NR_IRQS */ +/* + * This used to hold the highest supported SPI, but it is now obsolete + * and only here to provide source code level compatibility with older + * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS. + */ +#ifndef __KERNEL__ #define KVM_ARM_IRQ_GIC_MAX 127 +#endif /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 03120e656aea..2ecc7d15bc09 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_CPU_PJ4B) += pj4-cp0.o obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o perf_event_cpu.o +CFLAGS_pj4-cp0.o := -marm AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 6bb09d4abdea..eb6f1927b2c7 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -33,7 +33,9 @@ ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq @ disable interrupts - ldr r1, [tsk, #TI_FLAGS] + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing + tst r1, #_TIF_SYSCALL_WORK + bne __sys_trace_return tst r1, #_TIF_WORK_MASK bne fast_work_pending asm_trace_hardirqs_on diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c index c4cc50e58c13..cfb354ff2a60 100644 --- a/arch/arm/kernel/hibernate.c +++ b/arch/arm/kernel/hibernate.c @@ -22,6 +22,7 @@ #include <asm/suspend.h> #include <asm/memory.h> #include <asm/sections.h> +#include "reboot.h" int pfn_is_nosave(unsigned long pfn) { @@ -61,7 +62,7 @@ static int notrace arch_save_image(unsigned long unused) ret = swsusp_save(); if (ret == 0) - soft_restart(virt_to_phys(cpu_resume)); + _soft_restart(virt_to_phys(cpu_resume), false); return ret; } @@ -86,7 +87,7 @@ static void notrace arch_restore_image(void *unused) for (pbe = restore_pblist; pbe; pbe = pbe->next) copy_page(pbe->orig_address, pbe->address); - soft_restart(virt_to_phys(cpu_resume)); + _soft_restart(virt_to_phys(cpu_resume), false); } static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata; diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S index ad58e565fe98..49fadbda8c63 100644 --- a/arch/arm/kernel/iwmmxt.S +++ b/arch/arm/kernel/iwmmxt.S @@ -58,6 +58,7 @@ #define MMX_SIZE (0x98) .text + .arm /* * Lazy switching of Concan coprocessor context @@ -182,6 +183,8 @@ concan_load: tmcr wCon, r2 ret lr +ENDPROC(iwmmxt_task_enable) + /* * Back up Concan regs to save area and disable access to them * (mainly for gdb or sleep mode usage) @@ -232,6 +235,8 @@ ENTRY(iwmmxt_task_disable) 1: msr cpsr_c, ip @ restore interrupt mode ldmfd sp!, {r4, pc} +ENDPROC(iwmmxt_task_disable) + /* * Copy Concan state to given memory address * @@ -268,6 +273,8 @@ ENTRY(iwmmxt_task_copy) msr cpsr_c, ip @ restore interrupt mode ret r3 +ENDPROC(iwmmxt_task_copy) + /* * Restore Concan state from given memory address * @@ -304,6 +311,8 @@ ENTRY(iwmmxt_task_restore) msr cpsr_c, ip @ restore interrupt mode ret r3 +ENDPROC(iwmmxt_task_restore) + /* * Concan handling on task switch * @@ -335,6 +344,8 @@ ENTRY(iwmmxt_task_switch) mrc p15, 0, r1, c2, c0, 0 sub pc, lr, r1, lsr #32 @ cpwait and return +ENDPROC(iwmmxt_task_switch) + /* * Remove Concan ownership of given task * @@ -353,6 +364,8 @@ ENTRY(iwmmxt_task_release) msr cpsr_c, r2 @ restore interrupts ret lr +ENDPROC(iwmmxt_task_release) + .data concan_owner: .word 0 diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 06562719a330..617ec4ab4d81 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -42,6 +42,7 @@ #include <asm/system_misc.h> #include <asm/mach/time.h> #include <asm/tls.h> +#include "reboot.h" #ifdef CONFIG_CC_STACKPROTECTOR #include <linux/stackprotector.h> @@ -133,7 +134,7 @@ static void __soft_restart(void *addr) BUG(); } -void soft_restart(unsigned long addr) +void _soft_restart(unsigned long addr, bool disable_l2) { u64 *stack = soft_restart_stack + ARRAY_SIZE(soft_restart_stack); @@ -142,7 +143,7 @@ void soft_restart(unsigned long addr) local_fiq_disable(); /* Disable the L2 if we're the last man standing. */ - if (num_online_cpus() == 1) + if (disable_l2) outer_disable(); /* Change to the new stack and continue with the reset. */ @@ -152,6 +153,11 @@ void soft_restart(unsigned long addr) BUG(); } +void soft_restart(unsigned long addr) +{ + _soft_restart(addr, num_online_cpus() == 1); +} + /* * Function pointers to optional machine specific functions */ diff --git a/arch/arm/kernel/reboot.h b/arch/arm/kernel/reboot.h new file mode 100644 index 000000000000..c87f05816d6b --- /dev/null +++ b/arch/arm/kernel/reboot.h @@ -0,0 +1,6 @@ +#ifndef REBOOT_H +#define REBOOT_H + +extern void _soft_restart(unsigned long addr, bool disable_l2); + +#endif diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 9e193c8a959e..ed5834e8e2ac 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -213,6 +213,11 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) int err; struct kvm_vcpu *vcpu; + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) { + err = -EBUSY; + goto out; + } + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); if (!vcpu) { err = -ENOMEM; @@ -419,6 +424,7 @@ static void update_vttbr(struct kvm *kvm) static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; int ret; if (likely(vcpu->arch.has_run_once)) @@ -427,15 +433,23 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) vcpu->arch.has_run_once = true; /* - * Initialize the VGIC before running a vcpu the first time on - * this VM. + * Map the VGIC hardware resources before running a vcpu the first + * time on this VM. */ - if (unlikely(!vgic_initialized(vcpu->kvm))) { - ret = kvm_vgic_init(vcpu->kvm); + if (unlikely(!vgic_initialized(kvm))) { + ret = kvm_vgic_map_resources(kvm); if (ret) return ret; } + /* + * Enable the arch timers only if we have an in-kernel VGIC + * and it has been properly initialized, since we cannot handle + * interrupts from the virtual timer with a userspace gic. + */ + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) + kvm_timer_enable(kvm); + return 0; } @@ -639,8 +653,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, if (!irqchip_in_kernel(kvm)) return -ENXIO; - if (irq_num < VGIC_NR_PRIVATE_IRQS || - irq_num > KVM_ARM_IRQ_GIC_MAX) + if (irq_num < VGIC_NR_PRIVATE_IRQS) return -EINVAL; return kvm_vgic_inject_irq(kvm, 0, irq_num, level); @@ -659,10 +672,21 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, return ret; /* + * Ensure a rebooted VM will fault in RAM pages and detect if the + * guest MMU is turned off and flush the caches as needed. + */ + if (vcpu->arch.has_run_once) + stage2_unmap_vm(vcpu->kvm); + + vcpu_reset_hcr(vcpu); + + /* * Handle the "start in power-off" case by marking the VCPU as paused. */ - if (__test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) + if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) vcpu->arch.pause = true; + else + vcpu->arch.pause = false; return 0; } diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index cc0b78769bd8..8c97208b9b97 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { - vcpu->arch.hcr = HCR_GUEST_MASK; return 0; } diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 8664ff17cbbe..cba52cf6ed3f 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -58,6 +58,26 @@ static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa); } +/* + * D-Cache management functions. They take the page table entries by + * value, as they are flushing the cache using the kernel mapping (or + * kmap on 32bit). + */ +static void kvm_flush_dcache_pte(pte_t pte) +{ + __kvm_flush_dcache_pte(pte); +} + +static void kvm_flush_dcache_pmd(pmd_t pmd) +{ + __kvm_flush_dcache_pmd(pmd); +} + +static void kvm_flush_dcache_pud(pud_t pud) +{ + __kvm_flush_dcache_pud(pud); +} + static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, int min, int max) { @@ -119,6 +139,26 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) put_page(virt_to_page(pmd)); } +/* + * Unmapping vs dcache management: + * + * If a guest maps certain memory pages as uncached, all writes will + * bypass the data cache and go directly to RAM. However, the CPUs + * can still speculate reads (not writes) and fill cache lines with + * data. + * + * Those cache lines will be *clean* cache lines though, so a + * clean+invalidate operation is equivalent to an invalidate + * operation, because no cache lines are marked dirty. + * + * Those clean cache lines could be filled prior to an uncached write + * by the guest, and the cache coherent IO subsystem would therefore + * end up writing old data to disk. + * + * This is why right after unmapping a page/section and invalidating + * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure + * the IO subsystem will never hit in the cache. + */ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { @@ -128,9 +168,16 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, start_pte = pte = pte_offset_kernel(pmd, addr); do { if (!pte_none(*pte)) { + pte_t old_pte = *pte; + kvm_set_pte(pte, __pte(0)); - put_page(virt_to_page(pte)); kvm_tlb_flush_vmid_ipa(kvm, addr); + + /* No need to invalidate the cache for device mappings */ + if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(old_pte); + + put_page(virt_to_page(pte)); } } while (pte++, addr += PAGE_SIZE, addr != end); @@ -149,8 +196,13 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud, next = kvm_pmd_addr_end(addr, end); if (!pmd_none(*pmd)) { if (kvm_pmd_huge(*pmd)) { + pmd_t old_pmd = *pmd; + pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pmd(old_pmd); + put_page(virt_to_page(pmd)); } else { unmap_ptes(kvm, pmd, addr, next); @@ -173,8 +225,13 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd, next = kvm_pud_addr_end(addr, end); if (!pud_none(*pud)) { if (pud_huge(*pud)) { + pud_t old_pud = *pud; + pud_clear(pud); kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pud(old_pud); + put_page(virt_to_page(pud)); } else { unmap_pmds(kvm, pud, addr, next); @@ -194,7 +251,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, phys_addr_t addr = start, end = start + size; phys_addr_t next; - pgd = pgdp + pgd_index(addr); + pgd = pgdp + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); if (!pgd_none(*pgd)) @@ -209,10 +266,9 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, pte = pte_offset_kernel(pmd, addr); do { - if (!pte_none(*pte)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE); - } + if (!pte_none(*pte) && + (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(*pte); } while (pte++, addr += PAGE_SIZE, addr != end); } @@ -226,12 +282,10 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, do { next = kvm_pmd_addr_end(addr, end); if (!pmd_none(*pmd)) { - if (kvm_pmd_huge(*pmd)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE); - } else { + if (kvm_pmd_huge(*pmd)) + kvm_flush_dcache_pmd(*pmd); + else stage2_flush_ptes(kvm, pmd, addr, next); - } } } while (pmd++, addr = next, addr != end); } @@ -246,12 +300,10 @@ static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd, do { next = kvm_pud_addr_end(addr, end); if (!pud_none(*pud)) { - if (pud_huge(*pud)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE); - } else { + if (pud_huge(*pud)) + kvm_flush_dcache_pud(*pud); + else stage2_flush_pmds(kvm, pud, addr, next); - } } } while (pud++, addr = next, addr != end); } @@ -264,7 +316,7 @@ static void stage2_flush_memslot(struct kvm *kvm, phys_addr_t next; pgd_t *pgd; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); stage2_flush_puds(kvm, pgd, addr, next); @@ -541,6 +593,20 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr) __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE); } +/* Free the HW pgd, one page at a time */ +static void kvm_free_hwpgd(void *hwpgd) +{ + free_pages_exact(hwpgd, kvm_get_hwpgd_size()); +} + +/* Allocate the HW PGD, making sure that each page gets its own refcount */ +static void *kvm_alloc_hwpgd(void) +{ + unsigned int size = kvm_get_hwpgd_size(); + + return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); +} + /** * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation. * @kvm: The KVM struct pointer for the VM. @@ -554,15 +620,31 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr) */ int kvm_alloc_stage2_pgd(struct kvm *kvm) { - int ret; pgd_t *pgd; + void *hwpgd; if (kvm->arch.pgd != NULL) { kvm_err("kvm_arch already initialized?\n"); return -EINVAL; } + hwpgd = kvm_alloc_hwpgd(); + if (!hwpgd) + return -ENOMEM; + + /* When the kernel uses more levels of page tables than the + * guest, we allocate a fake PGD and pre-populate it to point + * to the next-level page table, which will be the real + * initial page table pointed to by the VTTBR. + * + * When KVM_PREALLOC_LEVEL==2, we allocate a single page for + * the PMD and the kernel will use folded pud. + * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD + * pages. + */ if (KVM_PREALLOC_LEVEL > 0) { + int i; + /* * Allocate fake pgd for the page table manipulation macros to * work. This is not used by the hardware and we have no @@ -570,30 +652,32 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) */ pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), GFP_KERNEL | __GFP_ZERO); + + if (!pgd) { + kvm_free_hwpgd(hwpgd); + return -ENOMEM; + } + + /* Plug the HW PGD into the fake one. */ + for (i = 0; i < PTRS_PER_S2_PGD; i++) { + if (KVM_PREALLOC_LEVEL == 1) + pgd_populate(NULL, pgd + i, + (pud_t *)hwpgd + i * PTRS_PER_PUD); + else if (KVM_PREALLOC_LEVEL == 2) + pud_populate(NULL, pud_offset(pgd, 0) + i, + (pmd_t *)hwpgd + i * PTRS_PER_PMD); + } } else { /* * Allocate actual first-level Stage-2 page table used by the * hardware for Stage-2 page table walks. */ - pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER); + pgd = (pgd_t *)hwpgd; } - if (!pgd) - return -ENOMEM; - - ret = kvm_prealloc_hwpgd(kvm, pgd); - if (ret) - goto out_err; - kvm_clean_pgd(pgd); kvm->arch.pgd = pgd; return 0; -out_err: - if (KVM_PREALLOC_LEVEL > 0) - kfree(pgd); - else - free_pages((unsigned long)pgd, S2_PGD_ORDER); - return ret; } /** @@ -612,6 +696,71 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) unmap_range(kvm, kvm->arch.pgd, start, size); } +static void stage2_unmap_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + hva_t hva = memslot->userspace_addr; + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t size = PAGE_SIZE * memslot->npages; + hva_t reg_end = hva + size; + + /* + * A memory region could potentially cover multiple VMAs, and any holes + * between them, so iterate over all of them to find out if we should + * unmap any of them. + * + * +--------------------------------------------+ + * +---------------+----------------+ +----------------+ + * | : VMA 1 | VMA 2 | | VMA 3 : | + * +---------------+----------------+ +----------------+ + * | memory region | + * +--------------------------------------------+ + */ + do { + struct vm_area_struct *vma = find_vma(current->mm, hva); + hva_t vm_start, vm_end; + + if (!vma || vma->vm_start >= reg_end) + break; + + /* + * Take the intersection of this VMA with the memory region + */ + vm_start = max(hva, vma->vm_start); + vm_end = min(reg_end, vma->vm_end); + + if (!(vma->vm_flags & VM_PFNMAP)) { + gpa_t gpa = addr + (vm_start - memslot->userspace_addr); + unmap_stage2_range(kvm, gpa, vm_end - vm_start); + } + hva = vm_end; + } while (hva < reg_end); +} + +/** + * stage2_unmap_vm - Unmap Stage-2 RAM mappings + * @kvm: The struct kvm pointer + * + * Go through the memregions and unmap any reguler RAM + * backing memory already mapped to the VM. + */ +void stage2_unmap_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_unmap_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); +} + /** * kvm_free_stage2_pgd - free all stage-2 tables * @kvm: The KVM struct pointer for the VM. @@ -629,11 +778,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm) return; unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); - kvm_free_hwpgd(kvm); + kvm_free_hwpgd(kvm_get_hwpgd(kvm)); if (KVM_PREALLOC_LEVEL > 0) kfree(kvm->arch.pgd); - else - free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER); + kvm->arch.pgd = NULL; } @@ -643,7 +791,7 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache pgd_t *pgd; pud_t *pud; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); if (WARN_ON(pgd_none(*pgd))) { if (!cache) return NULL; @@ -840,6 +988,12 @@ static bool kvm_is_device_pfn(unsigned long pfn) return !pfn_valid(pfn); } +static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, bool uncached) +{ + __coherent_cache_guest_page(vcpu, pfn, size, uncached); +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_memory_slot *memslot, unsigned long hva, unsigned long fault_status) @@ -853,6 +1007,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct vm_area_struct *vma; pfn_t pfn; pgprot_t mem_type = PAGE_S2; + bool fault_ipa_uncached; write_fault = kvm_is_write_fault(vcpu); if (fault_status == FSC_PERM && !write_fault) { @@ -919,6 +1074,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (!hugetlb && !force_pte) hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa); + fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT; + if (hugetlb) { pmd_t new_pmd = pfn_pmd(pfn, mem_type); new_pmd = pmd_mkhuge(new_pmd); @@ -926,7 +1083,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pmd_writable(&new_pmd); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE); + coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached); ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); } else { pte_t new_pte = pfn_pte(pfn, mem_type); @@ -934,7 +1091,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pte_writable(&new_pte); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva, PAGE_SIZE); + coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached); ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE)); } @@ -1294,11 +1451,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, hva = vm_end; } while (hva < reg_end); - if (ret) { - spin_lock(&kvm->mmu_lock); + spin_lock(&kvm->mmu_lock); + if (ret) unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size); - spin_unlock(&kvm->mmu_lock); - } + else + stage2_flush_memslot(kvm, memslot); + spin_unlock(&kvm->mmu_lock); return ret; } @@ -1310,6 +1468,15 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages) { + /* + * Readonly memslots are not incoherent with the caches by definition, + * but in practice, they are used mostly to emulate ROMs or NOR flashes + * that the guest may consider devices and hence map as uncached. + * To prevent incoherency issues in these cases, tag all readonly + * regions as incoherent. + */ + if (slot->flags & KVM_MEM_READONLY) + slot->flags |= KVM_MEMSLOT_INCOHERENT; return 0; } diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 09cf37737ee2..58cb3248d277 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -15,6 +15,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/preempt.h> #include <linux/kvm_host.h> #include <linux/wait.h> @@ -166,6 +167,23 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type) { + int i; + struct kvm_vcpu *tmp; + + /* + * The KVM ABI specifies that a system event exit may call KVM_RUN + * again and may perform shutdown/reboot at a later time that when the + * actual request is made. Since we are implementing PSCI and a + * caller of PSCI reboot and shutdown expects that the system shuts + * down or reboots immediately, let's make sure that VCPUs are not run + * after this call is handled and before the VCPUs have been + * re-initialized. + */ + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + tmp->arch.pause = true; + kvm_vcpu_kick(tmp); + } + memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); vcpu->run->system_event.type = type; vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 2ffccd4eb084..01efe130912e 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -448,8 +448,9 @@ static int __init coherency_late_init(void) armada_375_coherency_init_wa(); } - bus_register_notifier(&platform_bus_type, - &mvebu_hwcc_nb); + if (coherency_available()) + bus_register_notifier(&platform_bus_type, + &mvebu_hwcc_nb); return 0; } diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c index bbd8664d1bac..6f8a85c5965c 100644 --- a/arch/arm/mach-mvebu/pmsu.c +++ b/arch/arm/mach-mvebu/pmsu.c @@ -415,6 +415,9 @@ static __init int armada_38x_cpuidle_init(void) void __iomem *mpsoc_base; u32 reg; + pr_warn("CPU idle is currently broken on Armada 38x: disabling"); + return 0; + np = of_find_compatible_node(NULL, NULL, "marvell,armada-380-coherency-fabric"); if (!np) @@ -476,6 +479,16 @@ static int __init mvebu_v7_cpu_pm_init(void) return 0; of_node_put(np); + /* + * Currently the CPU idle support for Armada 38x is broken, as + * the CPU hotplug uses some of the CPU idle functions it is + * broken too, so let's disable it + */ + if (of_machine_is_compatible("marvell,armada380")) { + cpu_hotplug_disable(); + pr_warn("CPU hotplug support is currently broken on Armada 38x: disabling"); + } + if (of_machine_is_compatible("marvell,armadaxp")) ret = armada_xp_cpuidle_init(); else if (of_machine_is_compatible("marvell,armada370")) @@ -489,7 +502,8 @@ static int __init mvebu_v7_cpu_pm_init(void) return ret; mvebu_v7_pmsu_enable_l2_powerdown_onidle(); - platform_device_register(&mvebu_v7_cpuidle_device); + if (mvebu_v7_cpuidle_device.name) + platform_device_register(&mvebu_v7_cpuidle_device); cpu_pm_register_notifier(&mvebu_v7_cpu_pm_notifier); return 0; diff --git a/arch/arm/mach-omap2/prm-regbits-34xx.h b/arch/arm/mach-omap2/prm-regbits-34xx.h index cbefbd7cfdb5..661d753df584 100644 --- a/arch/arm/mach-omap2/prm-regbits-34xx.h +++ b/arch/arm/mach-omap2/prm-regbits-34xx.h @@ -112,6 +112,7 @@ #define OMAP3430_VC_CMD_ONLP_SHIFT 16 #define OMAP3430_VC_CMD_RET_SHIFT 8 #define OMAP3430_VC_CMD_OFF_SHIFT 0 +#define OMAP3430_SREN_MASK (1 << 4) #define OMAP3430_HSEN_MASK (1 << 3) #define OMAP3430_MCODE_MASK (0x7 << 0) #define OMAP3430_VALID_MASK (1 << 24) diff --git a/arch/arm/mach-omap2/prm-regbits-44xx.h b/arch/arm/mach-omap2/prm-regbits-44xx.h index b1c7a33e00e7..e794828dee55 100644 --- a/arch/arm/mach-omap2/prm-regbits-44xx.h +++ b/arch/arm/mach-omap2/prm-regbits-44xx.h @@ -35,6 +35,7 @@ #define OMAP4430_GLOBAL_WARM_SW_RST_SHIFT 1 #define OMAP4430_GLOBAL_WUEN_MASK (1 << 16) #define OMAP4430_HSMCODE_MASK (0x7 << 0) +#define OMAP4430_SRMODEEN_MASK (1 << 4) #define OMAP4430_HSMODEEN_MASK (1 << 3) #define OMAP4430_HSSCLL_SHIFT 24 #define OMAP4430_ICEPICK_RST_SHIFT 9 diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index d1dedc8195ed..eafd120b53f1 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -203,23 +203,8 @@ save_context_wfi: */ ldr r1, kernel_flush blx r1 - /* - * The kernel doesn't interwork: v7_flush_dcache_all in particluar will - * always return in Thumb state when CONFIG_THUMB2_KERNEL is enabled. - * This sequence switches back to ARM. Note that .align may insert a - * nop: bx pc needs to be word-aligned in order to work. - */ - THUMB( .thumb ) - THUMB( .align ) - THUMB( bx pc ) - THUMB( nop ) - .arm - b omap3_do_wfi - -/* - * Local variables - */ +ENDPROC(omap34xx_cpu_suspend) omap3_do_wfi_sram_addr: .word omap3_do_wfi_sram kernel_flush: @@ -364,10 +349,7 @@ exit_nonoff_modes: * =================================== */ ldmfd sp!, {r4 - r11, pc} @ restore regs and return - -/* - * Local variables - */ +ENDPROC(omap3_do_wfi) sdrc_power: .word SDRC_POWER_V cm_idlest1_core: diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c index be9ef834fa81..076fd20d7e5a 100644 --- a/arch/arm/mach-omap2/vc.c +++ b/arch/arm/mach-omap2/vc.c @@ -316,7 +316,8 @@ static void __init omap3_vc_init_pmic_signaling(struct voltagedomain *voltdm) * idle. And we can also scale voltages to zero for off-idle. * Note that no actual voltage scaling during off-idle will * happen unless the board specific twl4030 PMIC scripts are - * loaded. + * loaded. See also omap_vc_i2c_init for comments regarding + * erratum i531. */ val = voltdm->read(OMAP3_PRM_VOLTCTRL_OFFSET); if (!(val & OMAP3430_PRM_VOLTCTRL_SEL_OFF)) { @@ -704,9 +705,16 @@ static void __init omap_vc_i2c_init(struct voltagedomain *voltdm) return; } + /* + * Note that for omap3 OMAP3430_SREN_MASK clears SREN to work around + * erratum i531 "Extra Power Consumed When Repeated Start Operation + * Mode Is Enabled on I2C Interface Dedicated for Smart Reflex (I2C4)". + * Otherwise I2C4 eventually leads into about 23mW extra power being + * consumed even during off idle using VMODE. + */ i2c_high_speed = voltdm->pmic->i2c_high_speed; if (i2c_high_speed) - voltdm->rmw(vc->common->i2c_cfg_hsen_mask, + voltdm->rmw(vc->common->i2c_cfg_clear_mask, vc->common->i2c_cfg_hsen_mask, vc->common->i2c_cfg_reg); diff --git a/arch/arm/mach-omap2/vc.h b/arch/arm/mach-omap2/vc.h index cdbdd78e755e..89b83b7ff3ec 100644 --- a/arch/arm/mach-omap2/vc.h +++ b/arch/arm/mach-omap2/vc.h @@ -34,6 +34,7 @@ struct voltagedomain; * @cmd_ret_shift: RET field shift in PRM_VC_CMD_VAL_* register * @cmd_off_shift: OFF field shift in PRM_VC_CMD_VAL_* register * @i2c_cfg_reg: I2C configuration register offset + * @i2c_cfg_clear_mask: high-speed mode bit clear mask in I2C config register * @i2c_cfg_hsen_mask: high-speed mode bit field mask in I2C config register * @i2c_mcode_mask: MCODE field mask for I2C config register * @@ -52,6 +53,7 @@ struct omap_vc_common { u8 cmd_ret_shift; u8 cmd_off_shift; u8 i2c_cfg_reg; + u8 i2c_cfg_clear_mask; u8 i2c_cfg_hsen_mask; u8 i2c_mcode_mask; }; diff --git a/arch/arm/mach-omap2/vc3xxx_data.c b/arch/arm/mach-omap2/vc3xxx_data.c index 75bc4aa22b3a..71d74c9172c1 100644 --- a/arch/arm/mach-omap2/vc3xxx_data.c +++ b/arch/arm/mach-omap2/vc3xxx_data.c @@ -40,6 +40,7 @@ static struct omap_vc_common omap3_vc_common = { .cmd_onlp_shift = OMAP3430_VC_CMD_ONLP_SHIFT, .cmd_ret_shift = OMAP3430_VC_CMD_RET_SHIFT, .cmd_off_shift = OMAP3430_VC_CMD_OFF_SHIFT, + .i2c_cfg_clear_mask = OMAP3430_SREN_MASK | OMAP3430_HSEN_MASK, .i2c_cfg_hsen_mask = OMAP3430_HSEN_MASK, .i2c_cfg_reg = OMAP3_PRM_VC_I2C_CFG_OFFSET, .i2c_mcode_mask = OMAP3430_MCODE_MASK, diff --git a/arch/arm/mach-omap2/vc44xx_data.c b/arch/arm/mach-omap2/vc44xx_data.c index 085e5d6a04fd..2abd5fa8a697 100644 --- a/arch/arm/mach-omap2/vc44xx_data.c +++ b/arch/arm/mach-omap2/vc44xx_data.c @@ -42,6 +42,7 @@ static const struct omap_vc_common omap4_vc_common = { .cmd_ret_shift = OMAP4430_RET_SHIFT, .cmd_off_shift = OMAP4430_OFF_SHIFT, .i2c_cfg_reg = OMAP4_PRM_VC_CFG_I2C_MODE_OFFSET, + .i2c_cfg_clear_mask = OMAP4430_SRMODEEN_MASK | OMAP4430_HSMODEEN_MASK, .i2c_cfg_hsen_mask = OMAP4430_HSMODEEN_MASK, .i2c_mcode_mask = OMAP4430_HSMCODE_MASK, }; diff --git a/arch/arm/mach-s3c64xx/crag6410.h b/arch/arm/mach-s3c64xx/crag6410.h index 7bc66682687e..dcbe17f5e5f8 100644 --- a/arch/arm/mach-s3c64xx/crag6410.h +++ b/arch/arm/mach-s3c64xx/crag6410.h @@ -14,6 +14,7 @@ #include <mach/gpio-samsung.h> #define GLENFARCLAS_PMIC_IRQ_BASE IRQ_BOARD_START +#define BANFF_PMIC_IRQ_BASE (IRQ_BOARD_START + 64) #define PCA935X_GPIO_BASE GPIO_BOARD_START #define CODEC_GPIO_BASE (GPIO_BOARD_START + 8) diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c index 10b913baab28..65c426bc45f7 100644 --- a/arch/arm/mach-s3c64xx/mach-crag6410.c +++ b/arch/arm/mach-s3c64xx/mach-crag6410.c @@ -554,6 +554,7 @@ static struct wm831x_touch_pdata touch_pdata = { static struct wm831x_pdata crag_pmic_pdata = { .wm831x_num = 1, + .irq_base = BANFF_PMIC_IRQ_BASE, .gpio_base = BANFF_PMIC_GPIO_BASE, .soft_shutdown = true, diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index 66781bf34077..c72412415093 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -36,12 +36,6 @@ * of type casting from pmd_t * to pte_t *. */ -struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, - int write) -{ - return ERR_PTR(-EINVAL); -} - int pud_huge(pud_t pud) { return 0; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 9f98cec7fe1e..fb9d305c874b 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1118,22 +1118,22 @@ void __init sanity_check_meminfo(void) } /* - * Find the first non-section-aligned page, and point + * Find the first non-pmd-aligned page, and point * memblock_limit at it. This relies on rounding the - * limit down to be section-aligned, which happens at - * the end of this function. + * limit down to be pmd-aligned, which happens at the + * end of this function. * * With this algorithm, the start or end of almost any - * bank can be non-section-aligned. The only exception - * is that the start of the bank 0 must be section- + * bank can be non-pmd-aligned. The only exception is + * that the start of the bank 0 must be section- * aligned, since otherwise memory would need to be * allocated when mapping the start of bank 0, which * occurs before any free memory is mapped. */ if (!memblock_limit) { - if (!IS_ALIGNED(block_start, SECTION_SIZE)) + if (!IS_ALIGNED(block_start, PMD_SIZE)) memblock_limit = block_start; - else if (!IS_ALIGNED(block_end, SECTION_SIZE)) + else if (!IS_ALIGNED(block_end, PMD_SIZE)) memblock_limit = arm_lowmem_limit; } @@ -1143,12 +1143,12 @@ void __init sanity_check_meminfo(void) high_memory = __va(arm_lowmem_limit - 1) + 1; /* - * Round the memblock limit down to a section size. This + * Round the memblock limit down to a pmd size. This * helps to ensure that we will allocate memory from the - * last full section, which should be mapped. + * last full pmd, which should be mapped. */ if (memblock_limit) - memblock_limit = round_down(memblock_limit, SECTION_SIZE); + memblock_limit = round_down(memblock_limit, PMD_SIZE); if (!memblock_limit) memblock_limit = arm_lowmem_limit; diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index e1268f905026..f412b53ed268 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -449,10 +449,21 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx) return; } #endif - if (rm != ARM_R0) - emit(ARM_MOV_R(ARM_R0, rm), ctx); + + /* + * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4 + * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into + * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm + * before using it as a source for ARM_R1. + * + * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is + * ARM_R5 (r_X) so there is no particular register overlap + * issues. + */ if (rn != ARM_R1) emit(ARM_MOV_R(ARM_R1, rn), ctx); + if (rm != ARM_R0) + emit(ARM_MOV_R(ARM_R0, rm), ctx); ctx->seen |= SEEN_CALL; emit_mov_i(ARM_R3, (u32)jit_udiv, ctx); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 5674a55b5518..865a7e28ea2d 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -38,6 +38,13 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; + if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) + vcpu->arch.hcr_el2 &= ~HCR_RW; +} + static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2012c4ba8d67..dbd32127dbb6 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -200,6 +200,7 @@ struct kvm_vcpu *kvm_arm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); u64 kvm_call_hyp(void *hypfn, ...); +void force_vm_exit(const cpumask_t *mask); int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, int exception_index); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 0caf7a59f6a1..a205e957d5c4 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -83,6 +83,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t); void free_boot_hyp_pgd(void); void free_hyp_pgds(void); +void stage2_unmap_vm(struct kvm *kvm); int kvm_alloc_stage2_pgd(struct kvm *kvm); void kvm_free_stage2_pgd(struct kvm *kvm); int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, @@ -136,6 +137,8 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) #define PTRS_PER_S2_PGD (1 << PTRS_PER_S2_PGD_SHIFT) #define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) +#define kvm_pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1)) + /* * If we are concatenating first level stage-2 page tables, we would have less * than or equal to 16 pointers in the fake PGD, because that's what the @@ -149,43 +152,6 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) #define KVM_PREALLOC_LEVEL (0) #endif -/** - * kvm_prealloc_hwpgd - allocate inital table for VTTBR - * @kvm: The KVM struct pointer for the VM. - * @pgd: The kernel pseudo pgd - * - * When the kernel uses more levels of page tables than the guest, we allocate - * a fake PGD and pre-populate it to point to the next-level page table, which - * will be the real initial page table pointed to by the VTTBR. - * - * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and - * the kernel will use folded pud. When KVM_PREALLOC_LEVEL==1, we - * allocate 2 consecutive PUD pages. - */ -static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd) -{ - unsigned int i; - unsigned long hwpgd; - - if (KVM_PREALLOC_LEVEL == 0) - return 0; - - hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT); - if (!hwpgd) - return -ENOMEM; - - for (i = 0; i < PTRS_PER_S2_PGD; i++) { - if (KVM_PREALLOC_LEVEL == 1) - pgd_populate(NULL, pgd + i, - (pud_t *)hwpgd + i * PTRS_PER_PUD); - else if (KVM_PREALLOC_LEVEL == 2) - pud_populate(NULL, pud_offset(pgd, 0) + i, - (pmd_t *)hwpgd + i * PTRS_PER_PMD); - } - - return 0; -} - static inline void *kvm_get_hwpgd(struct kvm *kvm) { pgd_t *pgd = kvm->arch.pgd; @@ -202,12 +168,11 @@ static inline void *kvm_get_hwpgd(struct kvm *kvm) return pmd_offset(pud, 0); } -static inline void kvm_free_hwpgd(struct kvm *kvm) +static inline unsigned int kvm_get_hwpgd_size(void) { - if (KVM_PREALLOC_LEVEL > 0) { - unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm); - free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT); - } + if (KVM_PREALLOC_LEVEL > 0) + return PTRS_PER_S2_PGD * PAGE_SIZE; + return PTRS_PER_S2_PGD * sizeof(pgd_t); } static inline bool kvm_page_empty(void *ptr) @@ -242,20 +207,42 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; } -static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, - unsigned long size) +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, + bool ipa_uncached) { - if (!vcpu_has_cache_enabled(vcpu)) - kvm_flush_dcache_to_poc((void *)hva, size); + void *va = page_address(pfn_to_page(pfn)); + + if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached) + kvm_flush_dcache_to_poc(va, size); if (!icache_is_aliasing()) { /* PIPT */ - flush_icache_range(hva, hva + size); + flush_icache_range((unsigned long)va, + (unsigned long)va + size); } else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */ /* any kind of VIPT cache */ __flush_icache_all(); } } +static inline void __kvm_flush_dcache_pte(pte_t pte) +{ + struct page *page = pte_page(pte); + kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE); +} + +static inline void __kvm_flush_dcache_pmd(pmd_t pmd) +{ + struct page *page = pmd_page(pmd); + kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE); +} + +static inline void __kvm_flush_dcache_pud(pud_t pud) +{ + struct page *page = pud_page(pud); + kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE); +} + #define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x)) void stage2_flush_vm(struct kvm *kvm); diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 8e38878c87c6..d9e9822efcee 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -179,8 +179,14 @@ struct kvm_arch_memory_slot { #define KVM_ARM_IRQ_CPU_IRQ 0 #define KVM_ARM_IRQ_CPU_FIQ 1 -/* Highest supported SPI, from VGIC_NR_IRQS */ +/* + * This used to hold the highest supported SPI, but it is now obsolete + * and only here to provide source code level compatibility with older + * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS. + */ +#ifndef __KERNEL__ #define KVM_ARM_IRQ_GIC_MAX 127 +#endif /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 76794692c20b..84d5959ff874 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { - vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; return 0; } diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index b72aa9f9215c..a767f6a4ce54 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -1014,6 +1014,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa) * Instead, we invalidate Stage-2 for this IPA, and the * whole of Stage-1. Weep... */ + lsr x1, x1, #12 tlbi ipas2e1is, x1 /* * We have to ensure completion of the invalidation at Stage-2, diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 70a7816535cd..0b4326578985 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -90,7 +90,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (!cpu_has_32bit_el1()) return -EINVAL; cpu_reset = &default_regs_reset32; - vcpu->arch.hcr_el2 &= ~HCR_RW; } else { cpu_reset = &default_regs_reset; } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index df34a70caca1..6efbb52cb92e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -67,8 +67,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) *ret_page = phys_to_page(phys); ptr = (void *)val; - if (flags & __GFP_ZERO) - memset(ptr, 0, size); + memset(ptr, 0, size); } return ptr; @@ -113,8 +112,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, *dma_handle = phys_to_dma(dev, page_to_phys(page)); addr = page_address(page); - if (flags & __GFP_ZERO) - memset(addr, 0, size); + memset(addr, 0, size); return addr; } else { return swiotlb_alloc_coherent(dev, size, dma_handle, flags); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 023747bf4dd7..2de9d2e59d96 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -38,12 +38,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) } #endif -struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, - int write) -{ - return ERR_PTR(-EINVAL); -} - int pmd_huge(pmd_t pmd) { return !(pmd_val(pmd) & PMD_TABLE_BIT); diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index edba042b2325..dc6a4842683a 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -487,7 +487,7 @@ emit_cond_jmp: return -EINVAL; } - imm64 = (u64)insn1.imm << 32 | imm; + imm64 = (u64)insn1.imm << 32 | (u32)imm; emit_a64_mov_i64(dst, imm64, ctx); return 1; diff --git a/arch/c6x/kernel/time.c b/arch/c6x/kernel/time.c index 356ee84cad95..04845aaf5985 100644 --- a/arch/c6x/kernel/time.c +++ b/arch/c6x/kernel/time.c @@ -49,7 +49,7 @@ u64 sched_clock(void) return (tsc * sched_clock_multiplier) >> SCHED_CLOCK_SHIFT; } -void time_init(void) +void __init time_init(void) { u64 tmp = (u64)NSEC_PER_SEC << SCHED_CLOCK_SHIFT; diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 76069c18ee42..52b7604b5215 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -114,12 +114,6 @@ int pud_huge(pud_t pud) return 0; } -struct page * -follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) -{ - return NULL; -} - void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c index 3c32075d2945..7ca80ac42ed5 100644 --- a/arch/metag/mm/hugetlbpage.c +++ b/arch/metag/mm/hugetlbpage.c @@ -94,12 +94,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 0; } -struct page *follow_huge_addr(struct mm_struct *mm, - unsigned long address, int write) -{ - return ERR_PTR(-EINVAL); -} - int pmd_huge(pmd_t pmd) { return pmd_page_shift(pmd) > PAGE_SHIFT; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 9536ef912f59..155bb7f5ad28 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2048,7 +2048,7 @@ config MIPS_CMP config MIPS_CPS bool "MIPS Coherent Processing System support" - depends on SYS_SUPPORTS_MIPS_CPS + depends on SYS_SUPPORTS_MIPS_CPS && !64BIT select MIPS_CM select MIPS_CPC select MIPS_CPS_PM if HOTPLUG_CPU diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c index b3ae068ca4fa..3fd369d74444 100644 --- a/arch/mips/bcm47xx/board.c +++ b/arch/mips/bcm47xx/board.c @@ -247,8 +247,8 @@ static __init const struct bcm47xx_board_type *bcm47xx_board_get_nvram(void) } if (bcm47xx_nvram_getenv("hardware_version", buf1, sizeof(buf1)) >= 0 && - bcm47xx_nvram_getenv("boardtype", buf2, sizeof(buf2)) >= 0) { - for (e2 = bcm47xx_board_list_boot_hw; e2->value1; e2++) { + bcm47xx_nvram_getenv("boardnum", buf2, sizeof(buf2)) >= 0) { + for (e2 = bcm47xx_board_list_hw_version_num; e2->value1; e2++) { if (!strstarts(buf1, e2->value1) && !strcmp(buf2, e2->value2)) return &e2->board; diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c index e1f27d653f60..7019e2967009 100644 --- a/arch/mips/bcm63xx/prom.c +++ b/arch/mips/bcm63xx/prom.c @@ -17,7 +17,6 @@ #include <bcm63xx_cpu.h> #include <bcm63xx_io.h> #include <bcm63xx_regs.h> -#include <bcm63xx_gpio.h> void __init prom_init(void) { @@ -53,9 +52,6 @@ void __init prom_init(void) reg &= ~mask; bcm_perf_writel(reg, PERF_CKCTL_REG); - /* register gpiochip */ - bcm63xx_gpio_init(); - /* do low level board init */ board_prom_init(); diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c index 6660c7ddf87b..240fb4ffa55c 100644 --- a/arch/mips/bcm63xx/setup.c +++ b/arch/mips/bcm63xx/setup.c @@ -20,6 +20,7 @@ #include <bcm63xx_cpu.h> #include <bcm63xx_regs.h> #include <bcm63xx_io.h> +#include <bcm63xx_gpio.h> void bcm63xx_machine_halt(void) { @@ -160,6 +161,9 @@ void __init plat_mem_setup(void) int __init bcm63xx_register_devices(void) { + /* register gpiochip */ + bcm63xx_gpio_init(); + return board_register_devices(); } diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c index 02f244475207..c76a289b95b5 100644 --- a/arch/mips/cavium-octeon/dma-octeon.c +++ b/arch/mips/cavium-octeon/dma-octeon.c @@ -306,7 +306,7 @@ void __init plat_swiotlb_setup(void) swiotlbsize = 64 * (1<<20); } #endif -#ifdef CONFIG_USB_OCTEON_OHCI +#ifdef CONFIG_USB_OHCI_HCD_PLATFORM /* OCTEON II ohci is only 32-bit. */ if (OCTEON_IS_MODEL(OCTEON_CN6XXX) && max_addr >= 0x100000000ul) swiotlbsize = 64 * (1<<20); diff --git a/arch/mips/include/asm/asm-eva.h b/arch/mips/include/asm/asm-eva.h index e41c56e375b1..1e38f0e1ea3e 100644 --- a/arch/mips/include/asm/asm-eva.h +++ b/arch/mips/include/asm/asm-eva.h @@ -11,6 +11,36 @@ #define __ASM_ASM_EVA_H #ifndef __ASSEMBLY__ + +/* Kernel variants */ + +#define kernel_cache(op, base) "cache " op ", " base "\n" +#define kernel_ll(reg, addr) "ll " reg ", " addr "\n" +#define kernel_sc(reg, addr) "sc " reg ", " addr "\n" +#define kernel_lw(reg, addr) "lw " reg ", " addr "\n" +#define kernel_lwl(reg, addr) "lwl " reg ", " addr "\n" +#define kernel_lwr(reg, addr) "lwr " reg ", " addr "\n" +#define kernel_lh(reg, addr) "lh " reg ", " addr "\n" +#define kernel_lb(reg, addr) "lb " reg ", " addr "\n" +#define kernel_lbu(reg, addr) "lbu " reg ", " addr "\n" +#define kernel_sw(reg, addr) "sw " reg ", " addr "\n" +#define kernel_swl(reg, addr) "swl " reg ", " addr "\n" +#define kernel_swr(reg, addr) "swr " reg ", " addr "\n" +#define kernel_sh(reg, addr) "sh " reg ", " addr "\n" +#define kernel_sb(reg, addr) "sb " reg ", " addr "\n" + +#ifdef CONFIG_32BIT +/* + * No 'sd' or 'ld' instructions in 32-bit but the code will + * do the correct thing + */ +#define kernel_sd(reg, addr) user_sw(reg, addr) +#define kernel_ld(reg, addr) user_lw(reg, addr) +#else +#define kernel_sd(reg, addr) "sd " reg", " addr "\n" +#define kernel_ld(reg, addr) "ld " reg", " addr "\n" +#endif /* CONFIG_32BIT */ + #ifdef CONFIG_EVA #define __BUILD_EVA_INSN(insn, reg, addr) \ @@ -41,37 +71,60 @@ #else -#define user_cache(op, base) "cache " op ", " base "\n" -#define user_ll(reg, addr) "ll " reg ", " addr "\n" -#define user_sc(reg, addr) "sc " reg ", " addr "\n" -#define user_lw(reg, addr) "lw " reg ", " addr "\n" -#define user_lwl(reg, addr) "lwl " reg ", " addr "\n" -#define user_lwr(reg, addr) "lwr " reg ", " addr "\n" -#define user_lh(reg, addr) "lh " reg ", " addr "\n" -#define user_lb(reg, addr) "lb " reg ", " addr "\n" -#define user_lbu(reg, addr) "lbu " reg ", " addr "\n" -#define user_sw(reg, addr) "sw " reg ", " addr "\n" -#define user_swl(reg, addr) "swl " reg ", " addr "\n" -#define user_swr(reg, addr) "swr " reg ", " addr "\n" -#define user_sh(reg, addr) "sh " reg ", " addr "\n" -#define user_sb(reg, addr) "sb " reg ", " addr "\n" +#define user_cache(op, base) kernel_cache(op, base) +#define user_ll(reg, addr) kernel_ll(reg, addr) +#define user_sc(reg, addr) kernel_sc(reg, addr) +#define user_lw(reg, addr) kernel_lw(reg, addr) +#define user_lwl(reg, addr) kernel_lwl(reg, addr) +#define user_lwr(reg, addr) kernel_lwr(reg, addr) +#define user_lh(reg, addr) kernel_lh(reg, addr) +#define user_lb(reg, addr) kernel_lb(reg, addr) +#define user_lbu(reg, addr) kernel_lbu(reg, addr) +#define user_sw(reg, addr) kernel_sw(reg, addr) +#define user_swl(reg, addr) kernel_swl(reg, addr) +#define user_swr(reg, addr) kernel_swr(reg, addr) +#define user_sh(reg, addr) kernel_sh(reg, addr) +#define user_sb(reg, addr) kernel_sb(reg, addr) #ifdef CONFIG_32BIT -/* - * No 'sd' or 'ld' instructions in 32-bit but the code will - * do the correct thing - */ -#define user_sd(reg, addr) user_sw(reg, addr) -#define user_ld(reg, addr) user_lw(reg, addr) +#define user_sd(reg, addr) kernel_sw(reg, addr) +#define user_ld(reg, addr) kernel_lw(reg, addr) #else -#define user_sd(reg, addr) "sd " reg", " addr "\n" -#define user_ld(reg, addr) "ld " reg", " addr "\n" +#define user_sd(reg, addr) kernel_sd(reg, addr) +#define user_ld(reg, addr) kernel_ld(reg, addr) #endif /* CONFIG_32BIT */ #endif /* CONFIG_EVA */ #else /* __ASSEMBLY__ */ +#define kernel_cache(op, base) cache op, base +#define kernel_ll(reg, addr) ll reg, addr +#define kernel_sc(reg, addr) sc reg, addr +#define kernel_lw(reg, addr) lw reg, addr +#define kernel_lwl(reg, addr) lwl reg, addr +#define kernel_lwr(reg, addr) lwr reg, addr +#define kernel_lh(reg, addr) lh reg, addr +#define kernel_lb(reg, addr) lb reg, addr +#define kernel_lbu(reg, addr) lbu reg, addr +#define kernel_sw(reg, addr) sw reg, addr +#define kernel_swl(reg, addr) swl reg, addr +#define kernel_swr(reg, addr) swr reg, addr +#define kernel_sh(reg, addr) sh reg, addr +#define kernel_sb(reg, addr) sb reg, addr + +#ifdef CONFIG_32BIT +/* + * No 'sd' or 'ld' instructions in 32-bit but the code will + * do the correct thing + */ +#define kernel_sd(reg, addr) user_sw(reg, addr) +#define kernel_ld(reg, addr) user_lw(reg, addr) +#else +#define kernel_sd(reg, addr) sd reg, addr +#define kernel_ld(reg, addr) ld reg, addr +#endif /* CONFIG_32BIT */ + #ifdef CONFIG_EVA #define __BUILD_EVA_INSN(insn, reg, addr) \ @@ -101,31 +154,27 @@ #define user_sd(reg, addr) user_sw(reg, addr) #else -#define user_cache(op, base) cache op, base -#define user_ll(reg, addr) ll reg, addr -#define user_sc(reg, addr) sc reg, addr -#define user_lw(reg, addr) lw reg, addr -#define user_lwl(reg, addr) lwl reg, addr -#define user_lwr(reg, addr) lwr reg, addr -#define user_lh(reg, addr) lh reg, addr -#define user_lb(reg, addr) lb reg, addr -#define user_lbu(reg, addr) lbu reg, addr -#define user_sw(reg, addr) sw reg, addr -#define user_swl(reg, addr) swl reg, addr -#define user_swr(reg, addr) swr reg, addr -#define user_sh(reg, addr) sh reg, addr -#define user_sb(reg, addr) sb reg, addr +#define user_cache(op, base) kernel_cache(op, base) +#define user_ll(reg, addr) kernel_ll(reg, addr) +#define user_sc(reg, addr) kernel_sc(reg, addr) +#define user_lw(reg, addr) kernel_lw(reg, addr) +#define user_lwl(reg, addr) kernel_lwl(reg, addr) +#define user_lwr(reg, addr) kernel_lwr(reg, addr) +#define user_lh(reg, addr) kernel_lh(reg, addr) +#define user_lb(reg, addr) kernel_lb(reg, addr) +#define user_lbu(reg, addr) kernel_lbu(reg, addr) +#define user_sw(reg, addr) kernel_sw(reg, addr) +#define user_swl(reg, addr) kernel_swl(reg, addr) +#define user_swr(reg, addr) kernel_swr(reg, addr) +#define user_sh(reg, addr) kernel_sh(reg, addr) +#define user_sb(reg, addr) kernel_sb(reg, addr) #ifdef CONFIG_32BIT -/* - * No 'sd' or 'ld' instructions in 32-bit but the code will - * do the correct thing - */ -#define user_sd(reg, addr) user_sw(reg, addr) -#define user_ld(reg, addr) user_lw(reg, addr) +#define user_sd(reg, addr) kernel_sw(reg, addr) +#define user_ld(reg, addr) kernel_lw(reg, addr) #else -#define user_sd(reg, addr) sd reg, addr -#define user_ld(reg, addr) ld reg, addr +#define user_sd(reg, addr) kernel_sd(reg, addr) +#define user_ld(reg, addr) kernel_sd(reg, addr) #endif /* CONFIG_32BIT */ #endif /* CONFIG_EVA */ diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index dd562414cd5e..99f71e87ce31 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -150,6 +150,7 @@ static inline void lose_fpu(int save) } disable_msa(); clear_thread_flag(TIF_USEDMSA); + __disable_fpu(); } else if (is_fpu_owner()) { if (save) _save_fp(current); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index f2c249796ea8..4e3205a3bee2 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -321,6 +321,7 @@ enum mips_mmu_types { #define T_TRAP 13 /* Trap instruction */ #define T_VCEI 14 /* Virtual coherency exception */ #define T_FPE 15 /* Floating point exception */ +#define T_MSADIS 21 /* MSA disabled exception */ #define T_WATCH 23 /* Watch address reference */ #define T_VCED 31 /* Virtual coherency data */ @@ -577,6 +578,7 @@ struct kvm_mips_callbacks { int (*handle_syscall)(struct kvm_vcpu *vcpu); int (*handle_res_inst)(struct kvm_vcpu *vcpu); int (*handle_break)(struct kvm_vcpu *vcpu); + int (*handle_msa_disabled)(struct kvm_vcpu *vcpu); int (*vm_init)(struct kvm *kvm); int (*vcpu_init)(struct kvm_vcpu *vcpu); int (*vcpu_setup)(struct kvm_vcpu *vcpu); diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h index fa1f3cfbae8d..d68e685cde60 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h @@ -50,7 +50,6 @@ #define cpu_has_mips32r2 0 #define cpu_has_mips64r1 0 #define cpu_has_mips64r2 1 -#define cpu_has_mips_r2_exec_hazard 0 #define cpu_has_dsp 0 #define cpu_has_dsp2 0 #define cpu_has_mipsmt 0 diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h index 64ba56a02843..1884609741a8 100644 --- a/arch/mips/include/asm/octeon/pci-octeon.h +++ b/arch/mips/include/asm/octeon/pci-octeon.h @@ -11,9 +11,6 @@ #include <linux/pci.h> -/* Some PCI cards require delays when accessing config space. */ -#define PCI_CONFIG_SPACE_DELAY 10000 - /* * The physical memory base mapped by BAR1. 256MB at the end of the * first 4GB. diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S index 4353d323f017..39d682937d52 100644 --- a/arch/mips/kernel/entry.S +++ b/arch/mips/kernel/entry.S @@ -10,6 +10,7 @@ #include <asm/asm.h> #include <asm/asmmacro.h> +#include <asm/compiler.h> #include <asm/regdef.h> #include <asm/mipsregs.h> #include <asm/stackframe.h> @@ -166,7 +167,7 @@ syscall_exit_work: * For C code use the inline version named instruction_hazard(). */ LEAF(mips_ihb) - .set mips32r2 + .set MIPS_ISA_LEVEL_RAW jr.hb ra nop END(mips_ihb) diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index e6e16a1d4add..0854f17829f3 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -88,6 +88,12 @@ static void __init cps_smp_setup(void) /* Make core 0 coherent with everything */ write_gcr_cl_coherence(0xff); + +#ifdef CONFIG_MIPS_MT_FPAFF + /* If we have an FPU, enroll ourselves in the FPU-full mask */ + if (cpu_has_fpu) + cpu_set(0, mt_fpu_cpumask); +#endif /* CONFIG_MIPS_MT_FPAFF */ } static void __init cps_prepare_cpus(unsigned int max_cpus) diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index fb3e8dfd1ff6..838d3a6a5b7d 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -2176,6 +2176,7 @@ enum emulation_result kvm_mips_check_privilege(unsigned long cause, case T_SYSCALL: case T_BREAK: case T_RES_INST: + case T_MSADIS: break; case T_COP_UNUSABLE: diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 270bbd41769e..39074fb83bad 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -1119,6 +1119,10 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) ret = kvm_mips_callbacks->handle_break(vcpu); break; + case T_MSADIS: + ret = kvm_mips_callbacks->handle_msa_disabled(vcpu); + break; + default: kvm_err("Exception Code: %d, not yet handled, @ PC: %p, inst: 0x%08x BadVaddr: %#lx Status: %#lx\n", exccode, opc, kvm_get_inst(opc, vcpu), badvaddr, diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index fd7257b70e65..4372cc86650c 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -330,6 +330,33 @@ static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu) return ret; } +static int kvm_trap_emul_handle_msa_disabled(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + /* No MSA supported in guest, guest reserved instruction exception */ + er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu); + + switch (er) { + case EMULATE_DONE: + ret = RESUME_GUEST; + break; + + case EMULATE_FAIL: + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + break; + + default: + BUG(); + } + return ret; +} + static int kvm_trap_emul_vm_init(struct kvm *kvm) { return 0; @@ -470,6 +497,7 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { .handle_syscall = kvm_trap_emul_handle_syscall, .handle_res_inst = kvm_trap_emul_handle_res_inst, .handle_break = kvm_trap_emul_handle_break, + .handle_msa_disabled = kvm_trap_emul_handle_msa_disabled, .vm_init = kvm_trap_emul_vm_init, .vcpu_init = kvm_trap_emul_vcpu_init, diff --git a/arch/mips/loongson/loongson-3/irq.c b/arch/mips/loongson/loongson-3/irq.c index ca1c62af5188..8f5209aff01e 100644 --- a/arch/mips/loongson/loongson-3/irq.c +++ b/arch/mips/loongson/loongson-3/irq.c @@ -44,6 +44,7 @@ void mach_irq_dispatch(unsigned int pending) static struct irqaction cascade_irqaction = { .handler = no_action, + .flags = IRQF_NO_SUSPEND, .name = "cascade", }; diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c index 4ec8ee10d371..06e0f421b41b 100644 --- a/arch/mips/mm/hugetlbpage.c +++ b/arch/mips/mm/hugetlbpage.c @@ -68,12 +68,6 @@ int is_aligned_hugepage_range(unsigned long addr, unsigned long len) return 0; } -struct page * -follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) -{ - return ERR_PTR(-EINVAL); -} - int pmd_huge(pmd_t pmd) { return (pmd_val(pmd) & _PAGE_HUGE) != 0; @@ -83,15 +77,3 @@ int pud_huge(pud_t pud) { return (pud_val(pud) & _PAGE_HUGE) != 0; } - -struct page * -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - struct page *page; - - page = pte_page(*(pte_t *)pmd); - if (page) - page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT); - return page; -} diff --git a/arch/mips/mti-malta/malta-memory.c b/arch/mips/mti-malta/malta-memory.c index 8fddd2cdbff7..efe366d618b1 100644 --- a/arch/mips/mti-malta/malta-memory.c +++ b/arch/mips/mti-malta/malta-memory.c @@ -53,6 +53,12 @@ fw_memblock_t * __init fw_getmdesc(int eva) pr_warn("memsize not set in YAMON, set to default (32Mb)\n"); physical_memsize = 0x02000000; } else { + if (memsize > (256 << 20)) { /* memsize should be capped to 256M */ + pr_warn("Unsupported memsize value (0x%lx) detected! " + "Using 0x10000000 (256M) instead\n", + memsize); + memsize = 256 << 20; + } /* If ememsize is set, then set physical_memsize to that */ physical_memsize = ememsize ? : memsize; } diff --git a/arch/mips/netlogic/xlp/ahci-init-xlp2.c b/arch/mips/netlogic/xlp/ahci-init-xlp2.c index c83dbf3689e2..7b066a44e679 100644 --- a/arch/mips/netlogic/xlp/ahci-init-xlp2.c +++ b/arch/mips/netlogic/xlp/ahci-init-xlp2.c @@ -203,6 +203,7 @@ static u8 read_phy_reg(u64 regbase, u32 addr, u32 physel) static void config_sata_phy(u64 regbase) { u32 port, i, reg; + u8 val; for (port = 0; port < 2; port++) { for (i = 0, reg = RXCDRCALFOSC0; reg <= CALDUTY; reg++, i++) @@ -210,6 +211,18 @@ static void config_sata_phy(u64 regbase) for (i = 0, reg = RXDPIF; reg <= PPMDRIFTMAX_HI; reg++, i++) write_phy_reg(regbase, reg, port, sata_phy_config2[i]); + + /* Fix for PHY link up failures at lower temperatures */ + write_phy_reg(regbase, 0x800F, port, 0x1f); + + val = read_phy_reg(regbase, 0x0029, port); + write_phy_reg(regbase, 0x0029, port, val | (0x7 << 1)); + + val = read_phy_reg(regbase, 0x0056, port); + write_phy_reg(regbase, 0x0056, port, val & ~(1 << 3)); + + val = read_phy_reg(regbase, 0x0018, port); + write_phy_reg(regbase, 0x0018, port, val & ~(0x7 << 0)); } } diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c index 59cccd95688b..14d3351227ef 100644 --- a/arch/mips/pci/pci-octeon.c +++ b/arch/mips/pci/pci-octeon.c @@ -214,6 +214,8 @@ const char *octeon_get_pci_interrupts(void) return "AAABAAAAAAAAAAAAAAAAAAAAAAAAAAAA"; case CVMX_BOARD_TYPE_BBGW_REF: return "AABCD"; + case CVMX_BOARD_TYPE_CUST_DSR1000N: + return "CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC"; case CVMX_BOARD_TYPE_THUNDER: case CVMX_BOARD_TYPE_EBH3000: default: @@ -271,9 +273,6 @@ static int octeon_read_config(struct pci_bus *bus, unsigned int devfn, pci_addr.s.func = devfn & 0x7; pci_addr.s.reg = reg; -#if PCI_CONFIG_SPACE_DELAY - udelay(PCI_CONFIG_SPACE_DELAY); -#endif switch (size) { case 4: *val = le32_to_cpu(cvmx_read64_uint32(pci_addr.u64)); @@ -308,9 +307,6 @@ static int octeon_write_config(struct pci_bus *bus, unsigned int devfn, pci_addr.s.func = devfn & 0x7; pci_addr.s.reg = reg; -#if PCI_CONFIG_SPACE_DELAY - udelay(PCI_CONFIG_SPACE_DELAY); -#endif switch (size) { case 4: cvmx_write64_uint32(pci_addr.u64, cpu_to_le32(val)); diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c index 5e36c33e5543..38335af0a7f3 100644 --- a/arch/mips/pci/pcie-octeon.c +++ b/arch/mips/pci/pcie-octeon.c @@ -1762,14 +1762,6 @@ static int octeon_pcie_write_config(unsigned int pcie_port, struct pci_bus *bus, default: return PCIBIOS_FUNC_NOT_SUPPORTED; } -#if PCI_CONFIG_SPACE_DELAY - /* - * Delay on writes so that devices have time to come up. Some - * bridges need this to allow time for the secondary busses to - * work - */ - udelay(PCI_CONFIG_SPACE_DELAY); -#endif return PCIBIOS_SUCCESSFUL; } diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S index 32a7c828f073..e7567c8a9e79 100644 --- a/arch/mips/power/hibernate.S +++ b/arch/mips/power/hibernate.S @@ -30,6 +30,8 @@ LEAF(swsusp_arch_suspend) END(swsusp_arch_suspend) LEAF(swsusp_arch_resume) + /* Avoid TLB mismatch during and after kernel resume */ + jal local_flush_tlb_all PTR_L t0, restore_pblist 0: PTR_L t1, PBE_ADDRESS(t0) /* source */ @@ -43,7 +45,6 @@ LEAF(swsusp_arch_resume) bne t1, t3, 1b PTR_L t0, PBE_NEXT(t0) bnez t0, 0b - jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */ PTR_LA t0, saved_regs PTR_L ra, PT_R31(t0) PTR_L sp, PT_R29(t0) diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index 77e8a9620e18..d50914d5191e 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -7,6 +7,11 @@ config CLKEVT_RT3352 select CLKSRC_OF select CLKSRC_MMIO +config RALINK_ILL_ACC + bool + depends on SOC_RT305X + default y + choice prompt "Ralink SoC selection" default SOC_RT305X diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h index 3391d061eccc..78c9fd32c554 100644 --- a/arch/parisc/include/asm/elf.h +++ b/arch/parisc/include/asm/elf.h @@ -348,6 +348,10 @@ struct pt_regs; /* forward declaration... */ #define ELF_HWCAP 0 +#define STACK_RND_MASK (is_32bit_task() ? \ + 0x7ff >> (PAGE_SHIFT - 12) : \ + 0x3ffff >> (PAGE_SHIFT - 12)) + struct mm_struct; extern unsigned long arch_randomize_brk(struct mm_struct *); #define arch_randomize_brk arch_randomize_brk diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index e1ffea2f9a0b..5aba01ac457f 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -77,6 +77,9 @@ static unsigned long mmap_upper_limit(void) if (stack_base > STACK_SIZE_MAX) stack_base = STACK_SIZE_MAX; + /* Add space for stack randomization. */ + stack_base += (STACK_RND_MASK << PAGE_SHIFT); + return PAGE_ALIGN(STACK_TOP - stack_base); } diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 40198d50b4c2..8005b79ecbcf 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -61,12 +61,22 @@ struct cache_type_info { }; /* These are used to index the cache_type_info array. */ -#define CACHE_TYPE_UNIFIED 0 -#define CACHE_TYPE_INSTRUCTION 1 -#define CACHE_TYPE_DATA 2 +#define CACHE_TYPE_UNIFIED 0 /* cache-size, cache-block-size, etc. */ +#define CACHE_TYPE_UNIFIED_D 1 /* d-cache-size, d-cache-block-size, etc */ +#define CACHE_TYPE_INSTRUCTION 2 +#define CACHE_TYPE_DATA 3 static const struct cache_type_info cache_type_info[] = { { + /* Embedded systems that use cache-size, cache-block-size, + * etc. for the Unified (typically L2) cache. */ + .name = "Unified", + .size_prop = "cache-size", + .line_size_props = { "cache-line-size", + "cache-block-size", }, + .nr_sets_prop = "cache-sets", + }, + { /* PowerPC Processor binding says the [di]-cache-* * must be equal on unified caches, so just use * d-cache properties. */ @@ -293,7 +303,8 @@ static struct cache *cache_find_first_sibling(struct cache *cache) { struct cache *iter; - if (cache->type == CACHE_TYPE_UNIFIED) + if (cache->type == CACHE_TYPE_UNIFIED || + cache->type == CACHE_TYPE_UNIFIED_D) return cache; list_for_each_entry(iter, &cache_list, list) @@ -324,16 +335,29 @@ static bool cache_node_is_unified(const struct device_node *np) return of_get_property(np, "cache-unified", NULL); } -static struct cache *cache_do_one_devnode_unified(struct device_node *node, - int level) +/* + * Unified caches can have two different sets of tags. Most embedded + * use cache-size, etc. for the unified cache size, but open firmware systems + * use d-cache-size, etc. Check on initialization for which type we have, and + * return the appropriate structure type. Assume it's embedded if it isn't + * open firmware. If it's yet a 3rd type, then there will be missing entries + * in /sys/devices/system/cpu/cpu0/cache/index2/, and this code will need + * to be extended further. + */ +static int cache_is_unified_d(const struct device_node *np) { - struct cache *cache; + return of_get_property(np, + cache_type_info[CACHE_TYPE_UNIFIED_D].size_prop, NULL) ? + CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED; +} +/* + */ +static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level) +{ pr_debug("creating L%d ucache for %s\n", level, node->full_name); - cache = new_cache(CACHE_TYPE_UNIFIED, level, node); - - return cache; + return new_cache(cache_is_unified_d(node), level, node); } static struct cache *cache_do_one_devnode_split(struct device_node *node, diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index f096e72262f4..1db685104ffc 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -213,6 +213,7 @@ SECTIONS *(.opd) } + . = ALIGN(256); .got : AT(ADDR(.got) - LOAD_OFFSET) { __toc_start = .; #ifndef CONFIG_RELOCATABLE diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 6a4a5fcb9730..17e83a043bba 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -704,6 +704,14 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, return NULL; } +struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + BUG(); + return NULL; +} + static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, unsigned long sz) { diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 2396dda282cd..ead55351b254 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -243,7 +243,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry, sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); - for (;;) { + while (entry->nr < PERF_MAX_STACK_DEPTH) { fp = (unsigned long __user *) sp; if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp)) return; diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 8a106b4172e0..28e558d3316d 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -163,7 +163,7 @@ static unsigned int iic_get_irq(void) void iic_setup_cpu(void) { - out_be64(&__get_cpu_var(cpu_iic).regs->prio, 0xff); + out_be64(&this_cpu_ptr(&cpu_iic)->regs->prio, 0xff); } u8 iic_get_target_id(int cpu) diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 2b90ff8a93be..59ef76c5f4f4 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -197,7 +197,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); - for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift) + for (i = 0; i < npages; i++, uaddr += (1 << tbl->it_page_shift)) io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask); mb(); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 3f596706a5b7..86a7256d84e5 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1645,7 +1645,8 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose, region.start += phb->ioda.io_segsize; index++; } - } else if (res->flags & IORESOURCE_MEM) { + } else if ((res->flags & IORESOURCE_MEM) && + !pnv_pci_is_mem_pref_64(res->flags)) { region.start = res->start - hose->mem_offset[0] - phb->ioda.m32_pci_base; diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c index 7940dc90e80b..b258110da952 100644 --- a/arch/s390/crypto/ghash_s390.c +++ b/arch/s390/crypto/ghash_s390.c @@ -16,11 +16,12 @@ #define GHASH_DIGEST_SIZE 16 struct ghash_ctx { - u8 icv[16]; - u8 key[16]; + u8 key[GHASH_BLOCK_SIZE]; }; struct ghash_desc_ctx { + u8 icv[GHASH_BLOCK_SIZE]; + u8 key[GHASH_BLOCK_SIZE]; u8 buffer[GHASH_BLOCK_SIZE]; u32 bytes; }; @@ -28,8 +29,10 @@ struct ghash_desc_ctx { static int ghash_init(struct shash_desc *desc) { struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); memset(dctx, 0, sizeof(*dctx)); + memcpy(dctx->key, ctx->key, GHASH_BLOCK_SIZE); return 0; } @@ -45,7 +48,6 @@ static int ghash_setkey(struct crypto_shash *tfm, } memcpy(ctx->key, key, GHASH_BLOCK_SIZE); - memset(ctx->icv, 0, GHASH_BLOCK_SIZE); return 0; } @@ -54,7 +56,6 @@ static int ghash_update(struct shash_desc *desc, const u8 *src, unsigned int srclen) { struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); - struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); unsigned int n; u8 *buf = dctx->buffer; int ret; @@ -70,7 +71,7 @@ static int ghash_update(struct shash_desc *desc, src += n; if (!dctx->bytes) { - ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, + ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE); if (ret != GHASH_BLOCK_SIZE) return -EIO; @@ -79,7 +80,7 @@ static int ghash_update(struct shash_desc *desc, n = srclen & ~(GHASH_BLOCK_SIZE - 1); if (n) { - ret = crypt_s390_kimd(KIMD_GHASH, ctx, src, n); + ret = crypt_s390_kimd(KIMD_GHASH, dctx, src, n); if (ret != n) return -EIO; src += n; @@ -94,7 +95,7 @@ static int ghash_update(struct shash_desc *desc, return 0; } -static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx) +static int ghash_flush(struct ghash_desc_ctx *dctx) { u8 *buf = dctx->buffer; int ret; @@ -104,24 +105,24 @@ static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx) memset(pos, 0, dctx->bytes); - ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, GHASH_BLOCK_SIZE); + ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE); if (ret != GHASH_BLOCK_SIZE) return -EIO; + + dctx->bytes = 0; } - dctx->bytes = 0; return 0; } static int ghash_final(struct shash_desc *desc, u8 *dst) { struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); - struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); int ret; - ret = ghash_flush(ctx, dctx); + ret = ghash_flush(dctx); if (!ret) - memcpy(dst, ctx->icv, GHASH_BLOCK_SIZE); + memcpy(dst, dctx->icv, GHASH_BLOCK_SIZE); return ret; } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 57c882761dea..b0373b44b320 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -582,7 +582,7 @@ static inline int pmd_large(pmd_t pmd) return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0; } -static inline int pmd_pfn(pmd_t pmd) +static inline unsigned long pmd_pfn(pmd_t pmd) { unsigned long origin_mask; diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index 1c4c5accd220..d3236c9e226b 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -138,6 +138,8 @@ int pfn_is_nosave(unsigned long pfn) { unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end)); + unsigned long eshared_pfn = PFN_DOWN(__pa(&_eshared)) - 1; + unsigned long stext_pfn = PFN_DOWN(__pa(&_stext)); /* Always save lowcore pages (LC protection might be enabled). */ if (pfn <= LC_PAGES) @@ -145,6 +147,8 @@ int pfn_is_nosave(unsigned long pfn) if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn) return 1; /* Skip memory holes and read-only pages (NSS, DCSS, ...). */ + if (pfn >= stext_pfn && pfn <= eshared_pfn) + return ipl_info.type == IPL_TYPE_NSS ? 1 : 0; if (tprot(PFN_PHYS(pfn))) return 1; return 0; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 29e2e5aa2111..cd6344d334cb 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -16,6 +16,7 @@ #include <linux/mmu_context.h> #include <linux/signal.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <asm/asm-offsets.h> #include <asm/uaccess.h> #include "kvm-s390.h" @@ -784,7 +785,6 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, if ((!schid && !cr6) || (schid && cr6)) return NULL; - mutex_lock(&kvm->lock); fi = &kvm->arch.float_int; spin_lock(&fi->lock); inti = NULL; @@ -812,7 +812,6 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, if (list_empty(&fi->list)) atomic_set(&fi->active, 0); spin_unlock(&fi->lock); - mutex_unlock(&kvm->lock); return inti; } @@ -825,7 +824,6 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) int sigcpu; int rc = 0; - mutex_lock(&kvm->lock); fi = &kvm->arch.float_int; spin_lock(&fi->lock); if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) { @@ -868,7 +866,6 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu)); unlock_fi: spin_unlock(&fi->lock); - mutex_unlock(&kvm->lock); return rc; } @@ -930,10 +927,10 @@ int kvm_s390_inject_vm(struct kvm *kvm, return rc; } -void kvm_s390_reinject_io_int(struct kvm *kvm, +int kvm_s390_reinject_io_int(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { - __inject_vm(kvm, inti); + return __inject_vm(kvm, inti); } int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, @@ -1029,7 +1026,6 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm) struct kvm_s390_float_interrupt *fi; struct kvm_s390_interrupt_info *n, *inti = NULL; - mutex_lock(&kvm->lock); fi = &kvm->arch.float_int; spin_lock(&fi->lock); list_for_each_entry_safe(inti, n, &fi->list, list) { @@ -1039,66 +1035,68 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm) fi->irq_count = 0; atomic_set(&fi->active, 0); spin_unlock(&fi->lock); - mutex_unlock(&kvm->lock); } -static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti, - u8 *addr) +static void inti_to_irq(struct kvm_s390_interrupt_info *inti, + struct kvm_s390_irq *irq) { - struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr; - struct kvm_s390_irq irq = {0}; - - irq.type = inti->type; + irq->type = inti->type; switch (inti->type) { case KVM_S390_INT_PFAULT_INIT: case KVM_S390_INT_PFAULT_DONE: case KVM_S390_INT_VIRTIO: case KVM_S390_INT_SERVICE: - irq.u.ext = inti->ext; + irq->u.ext = inti->ext; break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - irq.u.io = inti->io; + irq->u.io = inti->io; break; case KVM_S390_MCHK: - irq.u.mchk = inti->mchk; + irq->u.mchk = inti->mchk; break; - default: - return -EINVAL; } - - if (copy_to_user(uptr, &irq, sizeof(irq))) - return -EFAULT; - - return 0; } -static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len) +static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) { struct kvm_s390_interrupt_info *inti; struct kvm_s390_float_interrupt *fi; + struct kvm_s390_irq *buf; + int max_irqs; int ret = 0; int n = 0; - mutex_lock(&kvm->lock); + if (len > KVM_S390_FLIC_MAX_BUFFER || len == 0) + return -EINVAL; + + /* + * We are already using -ENOMEM to signal + * userspace it may retry with a bigger buffer, + * so we need to use something else for this case + */ + buf = vzalloc(len); + if (!buf) + return -ENOBUFS; + + max_irqs = len / sizeof(struct kvm_s390_irq); + fi = &kvm->arch.float_int; spin_lock(&fi->lock); - list_for_each_entry(inti, &fi->list, list) { - if (len < sizeof(struct kvm_s390_irq)) { + if (n == max_irqs) { /* signal userspace to try again */ ret = -ENOMEM; break; } - ret = copy_irq_to_user(inti, buf); - if (ret) - break; - buf += sizeof(struct kvm_s390_irq); - len -= sizeof(struct kvm_s390_irq); + inti_to_irq(inti, &buf[n]); n++; } - spin_unlock(&fi->lock); - mutex_unlock(&kvm->lock); + if (!ret && n > 0) { + if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n)) + ret = -EFAULT; + } + vfree(buf); return ret < 0 ? ret : n; } @@ -1109,7 +1107,7 @@ static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) switch (attr->group) { case KVM_DEV_FLIC_GET_ALL_IRQS: - r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr, + r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr, attr->attr); break; default: diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 244d02303182..4c173474ecfe 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -148,8 +148,8 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, u64 cr6, u64 schid); -void kvm_s390_reinject_io_int(struct kvm *kvm, - struct kvm_s390_interrupt_info *inti); +int kvm_s390_reinject_io_int(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti); int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked); /* implemented in priv.c */ diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 9c565b6b4ccb..a30102c4d707 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -228,18 +228,19 @@ static int handle_tpi(struct kvm_vcpu *vcpu) struct kvm_s390_interrupt_info *inti; unsigned long len; u32 tpi_data[3]; - int cc, rc; + int rc; u64 addr; - rc = 0; addr = kvm_s390_get_base_disp_s(vcpu); if (addr & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - cc = 0; + inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0); - if (!inti) - goto no_interrupt; - cc = 1; + if (!inti) { + kvm_s390_set_psw_cc(vcpu, 0); + return 0; + } + tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr; tpi_data[1] = inti->io.io_int_parm; tpi_data[2] = inti->io.io_int_word; @@ -250,30 +251,38 @@ static int handle_tpi(struct kvm_vcpu *vcpu) */ len = sizeof(tpi_data) - 4; rc = write_guest(vcpu, addr, &tpi_data, len); - if (rc) - return kvm_s390_inject_prog_cond(vcpu, rc); + if (rc) { + rc = kvm_s390_inject_prog_cond(vcpu, rc); + goto reinject_interrupt; + } } else { /* * Store the three-word I/O interruption code into * the appropriate lowcore area. */ len = sizeof(tpi_data); - if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) + if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) { + /* failed writes to the low core are not recoverable */ rc = -EFAULT; + goto reinject_interrupt; + } } + + /* irq was successfully handed to the guest */ + kfree(inti); + kvm_s390_set_psw_cc(vcpu, 1); + return 0; +reinject_interrupt: /* * If we encounter a problem storing the interruption code, the * instruction is suppressed from the guest's view: reinject the * interrupt. */ - if (!rc) + if (kvm_s390_reinject_io_int(vcpu->kvm, inti)) { kfree(inti); - else - kvm_s390_reinject_io_int(vcpu->kvm, inti); -no_interrupt: - /* Set condition code and we're done. */ - if (!rc) - kvm_s390_set_psw_cc(vcpu, cc); + rc = -EFAULT; + } + /* don't set the cc, a pgm irq was injected or we drop to user space */ return rc ? -EFAULT : 0; } @@ -461,6 +470,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) for (n = mem->count - 1; n > 0 ; n--) memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0])); + memset(&mem->vm[0], 0, sizeof(mem->vm[0])); mem->vm[0].cpus_total = cpus; mem->vm[0].cpus_configured = cpus; mem->vm[0].cpus_standby = 0; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 3c80d2e38f03..210ffede0153 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -192,12 +192,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 0; } -struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, - int write) -{ - return ERR_PTR(-EINVAL); -} - int pmd_huge(pmd_t pmd) { if (!MACHINE_HAS_HPAGE) @@ -210,17 +204,3 @@ int pud_huge(pud_t pud) { return 0; } - -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmdp, int write) -{ - struct page *page; - - if (!MACHINE_HAS_HPAGE) - return NULL; - - page = pmd_page(*pmdp); - if (page) - page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT); - return page; -} diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index d7762349ea48..534bc978af8a 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -67,12 +67,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 0; } -struct page *follow_huge_addr(struct mm_struct *mm, - unsigned long address, int write) -{ - return ERR_PTR(-EINVAL); -} - int pmd_huge(pmd_t pmd) { return 0; @@ -82,9 +76,3 @@ int pud_huge(pud_t pud) { return 0; } - -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - return NULL; -} diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index d329537739c6..4242eab12e10 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -215,12 +215,6 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, return entry; } -struct page *follow_huge_addr(struct mm_struct *mm, - unsigned long address, int write) -{ - return ERR_PTR(-EINVAL); -} - int pmd_huge(pmd_t pmd) { return 0; @@ -230,9 +224,3 @@ int pud_huge(pud_t pud) { return 0; } - -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - return NULL; -} diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c index e514899e1100..8a00c7b7b862 100644 --- a/arch/tile/mm/hugetlbpage.c +++ b/arch/tile/mm/hugetlbpage.c @@ -150,12 +150,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) return NULL; } -struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, - int write) -{ - return ERR_PTR(-EINVAL); -} - int pmd_huge(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_HUGE_PAGE); @@ -166,28 +160,6 @@ int pud_huge(pud_t pud) return !!(pud_val(pud) & _PAGE_HUGE_PAGE); } -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - struct page *page; - - page = pte_page(*(pte_t *)pmd); - if (page) - page += ((address & ~PMD_MASK) >> PAGE_SHIFT); - return page; -} - -struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) -{ - struct page *page; - - page = pte_page(*(pte_t *)pud); - if (page) - page += ((address & ~PUD_MASK) >> PAGE_SHIFT); - return page; -} - int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { return 0; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6ed0c30d6a0c..6c0709ff2f38 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -201,6 +201,7 @@ union kvm_mmu_page_role { unsigned nxe:1; unsigned cr0_wp:1; unsigned smep_andnot_wp:1; + unsigned smap_andnot_wp:1; }; }; @@ -392,6 +393,7 @@ struct kvm_vcpu_arch { struct kvm_mmu_memory_cache mmu_page_header_cache; struct fpu guest_fpu; + bool eager_fpu; u64 xcr0; u64 guest_supported_xcr0; u32 guest_xstate_size; @@ -707,6 +709,7 @@ struct kvm_x86_ops { void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); + void (*fpu_activate)(struct kvm_vcpu *vcpu); void (*fpu_deactivate)(struct kvm_vcpu *vcpu); void (*tlb_flush)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 958b90f761e5..40b35a55ce8b 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -34,6 +34,10 @@ #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ +/* AMD-specific bits */ +#define MCI_STATUS_DEFERRED (1ULL<<44) /* declare an uncorrected error */ +#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */ + /* * Note that the full MCACOD field of IA32_MCi_STATUS MSR is * bits 15:0. But bit 12 is the 'F' bit, defined for corrected diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index a1410db38a1a..653dfa7662e1 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -30,6 +30,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) :: "a" (eax), "c" (ecx)); } +static inline void __sti_mwait(unsigned long eax, unsigned long ecx) +{ + trace_hardirqs_on(); + /* "mwait %eax, %ecx;" */ + asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" + :: "a" (eax), "c" (ecx)); +} + /* * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, * which can obviate IPI to trigger checking of need_resched. diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 09edd0b65fef..10b46906767f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -3,6 +3,8 @@ enum severity_level { MCE_NO_SEVERITY, + MCE_DEFERRED_SEVERITY, + MCE_UCNA_SEVERITY = MCE_DEFERRED_SEVERITY, MCE_KEEP_SEVERITY, MCE_SOME_SEVERITY, MCE_AO_SEVERITY, @@ -21,7 +23,7 @@ struct mce_bank { char attrname[ATTR_LEN]; /* attribute name */ }; -int mce_severity(struct mce *a, int tolerant, char **msg); +int mce_severity(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); extern struct mce_bank *mce_banks; diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index c370e1c4468b..8bb433043a7f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -31,6 +31,7 @@ enum context { IN_KERNEL = 1, IN_USER = 2 }; enum ser { SER_REQUIRED = 1, NO_SER = 2 }; +enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 }; static struct severity { u64 mask; @@ -40,6 +41,7 @@ static struct severity { unsigned char mcgres; unsigned char ser; unsigned char context; + unsigned char excp; unsigned char covered; char *msg; } severities[] = { @@ -48,6 +50,8 @@ static struct severity { #define USER .context = IN_USER #define SER .ser = SER_REQUIRED #define NOSER .ser = NO_SER +#define EXCP .excp = EXCP_CONTEXT +#define NOEXCP .excp = NO_EXCP #define BITCLR(x) .mask = x, .result = 0 #define BITSET(x) .mask = x, .result = x #define MCGMASK(x, y) .mcgmask = x, .mcgres = y @@ -62,7 +66,7 @@ static struct severity { ), MCESEV( NO, "Not enabled", - BITCLR(MCI_STATUS_EN) + EXCP, BITCLR(MCI_STATUS_EN) ), MCESEV( PANIC, "Processor context corrupt", @@ -71,16 +75,20 @@ static struct severity { /* When MCIP is not set something is very confused */ MCESEV( PANIC, "MCIP not set in MCA handler", - MCGMASK(MCG_STATUS_MCIP, 0) + EXCP, MCGMASK(MCG_STATUS_MCIP, 0) ), /* Neither return not error IP -- no chance to recover -> PANIC */ MCESEV( PANIC, "Neither restart nor error IP", - MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0) + EXCP, MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0) ), MCESEV( PANIC, "In kernel and no restart IP", - KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) + EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) + ), + MCESEV( + DEFERRED, "Deferred error", + NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED) ), MCESEV( KEEP, "Corrected error", @@ -89,7 +97,7 @@ static struct severity { /* ignore OVER for UCNA */ MCESEV( - KEEP, "Uncorrected no action required", + UCNA, "Uncorrected no action required", SER, MASK(MCI_UC_SAR, MCI_STATUS_UC) ), MCESEV( @@ -178,8 +186,9 @@ static int error_context(struct mce *m) return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL; } -int mce_severity(struct mce *m, int tolerant, char **msg) +int mce_severity(struct mce *m, int tolerant, char **msg, bool is_excp) { + enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); enum context ctx = error_context(m); struct severity *s; @@ -194,6 +203,8 @@ int mce_severity(struct mce *m, int tolerant, char **msg) continue; if (s->context && ctx != s->context) continue; + if (s->excp && excp != s->excp) + continue; if (msg) *msg = s->msg; s->covered = 1; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 61a9668cebfd..b5c2276317e2 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -660,6 +660,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { int i, ret = 0; + char *tmp; for (i = 0; i < mca_cfg.banks; i++) { m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); @@ -668,8 +669,11 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); } - if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY) + + if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + *msg = tmp; ret = 1; + } } return ret; } @@ -754,7 +758,7 @@ static void mce_reign(void) for_each_possible_cpu(cpu) { int severity = mce_severity(&per_cpu(mces_seen, cpu), mca_cfg.tolerant, - &nmsg); + &nmsg, true); if (severity > global_worst) { msg = nmsg; global_worst = severity; @@ -1095,13 +1099,14 @@ void do_machine_check(struct pt_regs *regs, long error_code) */ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - severity = mce_severity(&m, cfg->tolerant, NULL); + severity = mce_severity(&m, cfg->tolerant, NULL, true); /* - * When machine check was for corrected handler don't touch, - * unless we're panicing. + * When machine check was for corrected/deferred handler don't + * touch, unless we're panicing. */ - if (severity == MCE_KEEP_SEVERITY && !no_way_out) + if ((severity == MCE_KEEP_SEVERITY || + severity == MCE_UCNA_SEVERITY) && !no_way_out) continue; __set_bit(i, toclear); if (severity == MCE_NO_SEVERITY) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 8c256749882c..611d821eac1a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -664,6 +664,7 @@ static int __init rapl_pmu_init(void) break; case 60: /* Haswell */ case 69: /* Haswell-Celeron */ + case 61: /* Broadwell */ rapl_cntr_mask = RAPL_IDX_HSW; rapl_pmu_events_group.attrs = rapl_events_hsw_attr; break; diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index a9a4229f6161..ae0fdc86b7b6 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -155,6 +155,21 @@ static void init_thread_xstate(void) xstate_size = sizeof(struct i387_fxsave_struct); else xstate_size = sizeof(struct i387_fsave_struct); + + /* + * Quirk: we don't yet handle the XSAVES* instructions + * correctly, as we don't correctly convert between + * standard and compacted format when interfacing + * with user-space - so disable it for now. + * + * The difference is small: with recent CPUs the + * compacted format is only marginally smaller than + * the standard FPU state format. + * + * ( This is easy to backport while we are fixing + * XSAVES* support. ) + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); } /* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 4eb204c6b057..5dd6c417b095 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -24,6 +24,7 @@ #include <asm/syscalls.h> #include <asm/idle.h> #include <asm/uaccess.h> +#include <asm/mwait.h> #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/debugreg.h> @@ -385,6 +386,53 @@ static void amd_e400_idle(void) default_idle(); } +/* + * Intel Core2 and older machines prefer MWAIT over HALT for C1. + * We can't rely on cpuidle installing MWAIT, because it will not load + * on systems that support only C1 -- so the boot default must be MWAIT. + * + * Some AMD machines are the opposite, they depend on using HALT. + * + * So for default C1, which is used during boot until cpuidle loads, + * use MWAIT-C1 on Intel HW that has it, else use HALT. + */ +static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) +{ + if (c->x86_vendor != X86_VENDOR_INTEL) + return 0; + + if (!cpu_has(c, X86_FEATURE_MWAIT)) + return 0; + + return 1; +} + +/* + * MONITOR/MWAIT with no hints, used for default default C1 state. + * This invokes MWAIT with interrutps enabled and no flags, + * which is backwards compatible with the original MWAIT implementation. + */ + +static void mwait_idle(void) +{ + if (!current_set_polling_and_test()) { + if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { + smp_mb(); /* quirk */ + clflush((void *)¤t_thread_info()->flags); + smp_mb(); /* quirk */ + } + + __monitor((void *)¤t_thread_info()->flags, 0, 0); + if (!need_resched()) + __sti_mwait(0, 0); + else + local_irq_enable(); + } else { + local_irq_enable(); + } + __current_clr_polling(); +} + void select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP @@ -398,6 +446,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c) /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); x86_idle = amd_e400_idle; + } else if (prefer_mwait_c1_over_halt(c)) { + pr_info("using mwait in idle threads\n"); + x86_idle = mwait_idle; } else x86_idle = default_idle; } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 88f92014ba6b..81c6d541d98a 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -16,6 +16,8 @@ #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> +#include <asm/i387.h> /* For use_eager_fpu. Ugh! */ +#include <asm/fpu-internal.h> /* For use_eager_fpu. Ugh! */ #include <asm/user.h> #include <asm/xsave.h> #include "cpuid.h" @@ -88,6 +90,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) xstate_required_size(vcpu->arch.xcr0); } + vcpu->arch.eager_fpu = guest_cpuid_has_mpx(vcpu); + /* * The existing code assumes virtual address is 48-bit in the canonical * address checks; exit if it is ever changed. diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 4452eedfaedd..9bec2b8cdced 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -111,4 +111,12 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu) best = kvm_find_cpuid_entry(vcpu, 7, 0); return best && (best->ebx & bit(X86_FEATURE_RTM)); } + +static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_MPX)); +} #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9c12e63c653f..f696dedb0fa7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3625,8 +3625,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, } } -void update_permission_bitmask(struct kvm_vcpu *vcpu, - struct kvm_mmu *mmu, bool ept) +static void update_permission_bitmask(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu, bool ept) { unsigned bit, byte, pfec; u8 map; @@ -3807,6 +3807,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); + bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); @@ -3824,6 +3825,8 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu); vcpu->arch.mmu.base_role.smep_andnot_wp = smep && !is_write_protection(vcpu); + context->base_role.smap_andnot_wp + = smap && !is_write_protection(vcpu); } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); @@ -4095,12 +4098,18 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes) { gfn_t gfn = gpa >> PAGE_SHIFT; - union kvm_mmu_page_role mask = { .word = 0 }; struct kvm_mmu_page *sp; LIST_HEAD(invalid_list); u64 entry, gentry, *spte; int npte; bool remote_flush, local_flush, zap_page; + union kvm_mmu_page_role mask = { }; + + mask.cr0_wp = 1; + mask.cr4_pae = 1; + mask.nxe = 1; + mask.smep_andnot_wp = 1; + mask.smap_andnot_wp = 1; /* * If we don't have indirect shadow pages, it means no page is @@ -4126,7 +4135,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, ++vcpu->kvm->stat.mmu_pte_write; kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); - mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { if (detect_write_misaligned(sp, gpa, bytes) || detect_write_flooding(sp)) { diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index bde8ee725754..a6b876443302 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -84,8 +84,6 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly); -void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - bool ept); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { @@ -179,6 +177,8 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, int index = (pfec >> 1) + (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1)); + WARN_ON(pfec & PFERR_RSVD_MASK); + return (mmu->permissions[index] >> pte_access) & 1; } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index fd49c867b25a..6e6d115fe9b5 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -718,6 +718,13 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, mmu_is_nested(vcpu)); if (likely(r != RET_MMIO_PF_INVALID)) return r; + + /* + * page fault with PFEC.RSVD = 1 is caused by shadow + * page fault, should not be used to walk guest page + * table. + */ + error_code &= ~PFERR_RSVD_MASK; }; r = mmu_topup_memory_caches(vcpu); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 7527cefc5a43..f7eaee1cbc54 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -4370,6 +4370,7 @@ static struct kvm_x86_ops svm_x86_ops = { .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, + .fpu_activate = svm_fpu_activate, .fpu_deactivate = svm_fpu_deactivate, .tlb_flush = svm_flush_tlb, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ed7039465f16..54bda28e6a12 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2381,8 +2381,7 @@ static __init void nested_vmx_setup_ctls_msrs(void) if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ - nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST; + nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | VMX_EPT_INVEPT_BIT; @@ -2396,6 +2395,10 @@ static __init void nested_vmx_setup_ctls_msrs(void) } else nested_vmx_ept_caps = 0; + if (enable_unrestricted_guest) + nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_UNRESTRICTED_GUEST; + /* miscellaneous data */ rdmsr(MSR_IA32_VMX_MISC, nested_vmx_misc_low, nested_vmx_misc_high); nested_vmx_misc_low &= VMX_MISC_SAVE_EFER_LMA; @@ -9117,6 +9120,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, + .fpu_activate = vmx_fpu_activate, .fpu_deactivate = vmx_fpu_deactivate, .tlb_flush = vmx_flush_tlb, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a38dd816015b..0bb431c3f74e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -678,8 +678,9 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | - X86_CR4_PAE | X86_CR4_SMEP; + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | + X86_CR4_SMEP | X86_CR4_SMAP; + if (cr4 & CR4_RESERVED_BITS) return 1; @@ -720,9 +721,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); - if ((cr4 ^ old_cr4) & X86_CR4_SMAP) - update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false); - if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) kvm_update_cpuid(vcpu); @@ -5779,7 +5777,6 @@ int kvm_arch_init(void *opaque) kvm_set_mmio_spte_mask(); kvm_x86_ops = ops; - kvm_init_msr_list(); kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0); @@ -6140,6 +6137,8 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) return; page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + if (is_error_page(page)) + return; kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page)); /* @@ -6994,7 +6993,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) fpu_save_init(&vcpu->arch.guest_fpu); __kernel_fpu_end(); ++vcpu->stat.fpu_reload; - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + if (!vcpu->arch.eager_fpu) + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + trace_kvm_fpu(0); } @@ -7010,11 +7011,21 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { + struct kvm_vcpu *vcpu; + if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) printk_once(KERN_WARNING "kvm: SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); - return kvm_x86_ops->vcpu_create(kvm, id); + + vcpu = kvm_x86_ops->vcpu_create(kvm, id); + + /* + * Activate fpu unconditionally in case the guest needs eager FPU. It will be + * deactivated soon if it doesn't. + */ + kvm_x86_ops->fpu_activate(vcpu); + return vcpu; } int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) @@ -7210,7 +7221,14 @@ void kvm_arch_hardware_disable(void) int kvm_arch_hardware_setup(void) { - return kvm_x86_ops->hardware_setup(); + int r; + + r = kvm_x86_ops->hardware_setup(); + if (r != 0) + return r; + + kvm_init_msr_list(); + return 0; } void kvm_arch_hardware_unsetup(void) diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 006cc914994b..9161f764121e 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -52,20 +52,8 @@ int pud_huge(pud_t pud) return 0; } -struct page * -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - return NULL; -} #else -struct page * -follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) -{ - return ERR_PTR(-EINVAL); -} - /* * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 81f57e8c8f1b..73d328f480e5 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -406,6 +406,36 @@ source "drivers/pcmcia/Kconfig" source "drivers/pci/hotplug/Kconfig" +config XTFPGA_LCD + bool "Enable XTFPGA LCD driver" + depends on XTENSA_PLATFORM_XTFPGA + default n + help + There's a 2x16 LCD on most of XTFPGA boards, kernel may output + progress messages there during bootup/shutdown. It may be useful + during board bringup. + + If unsure, say N. + +config XTFPGA_LCD_BASE_ADDR + hex "XTFPGA LCD base address" + depends on XTFPGA_LCD + default "0x0d0c0000" + help + Base address of the LCD controller inside KIO region. + Different boards from XTFPGA family have LCD controller at different + addresses. Please consult prototyping user guide for your board for + the correct address. Wrong address here may lead to hardware lockup. + +config XTFPGA_LCD_8BIT_ACCESS + bool "Use 8-bit access to XTFPGA LCD" + depends on XTFPGA_LCD + default n + help + LCD may be connected with 4- or 8-bit interface, 8-bit access may + only be used with 8-bit interface. Please consult prototyping user + guide for your board for the correct interface width. + endmenu menu "Executable file formats" diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h index db5bb72e2f4e..62d84657c60b 100644 --- a/arch/xtensa/include/uapi/asm/unistd.h +++ b/arch/xtensa/include/uapi/asm/unistd.h @@ -715,7 +715,7 @@ __SYSCALL(323, sys_process_vm_writev, 6) __SYSCALL(324, sys_name_to_handle_at, 5) #define __NR_open_by_handle_at 325 __SYSCALL(325, sys_open_by_handle_at, 3) -#define __NR_sync_file_range 326 +#define __NR_sync_file_range2 326 __SYSCALL(326, sys_sync_file_range2, 6) #define __NR_perf_event_open 327 __SYSCALL(327, sys_perf_event_open, 5) diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index d05f8feeb8d7..17b1ef3232e4 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -349,8 +349,8 @@ static void iss_net_timer(unsigned long priv) { struct iss_net_private *lp = (struct iss_net_private *)priv; - spin_lock(&lp->lock); iss_net_poll(); + spin_lock(&lp->lock); mod_timer(&lp->timer, jiffies + lp->timer_val); spin_unlock(&lp->lock); } @@ -361,7 +361,7 @@ static int iss_net_open(struct net_device *dev) struct iss_net_private *lp = netdev_priv(dev); int err; - spin_lock(&lp->lock); + spin_lock_bh(&lp->lock); err = lp->tp.open(lp); if (err < 0) @@ -376,9 +376,11 @@ static int iss_net_open(struct net_device *dev) while ((err = iss_net_rx(dev)) > 0) ; - spin_lock(&opened_lock); + spin_unlock_bh(&lp->lock); + spin_lock_bh(&opened_lock); list_add(&lp->opened_list, &opened); - spin_unlock(&opened_lock); + spin_unlock_bh(&opened_lock); + spin_lock_bh(&lp->lock); init_timer(&lp->timer); lp->timer_val = ISS_NET_TIMER_VALUE; @@ -387,7 +389,7 @@ static int iss_net_open(struct net_device *dev) mod_timer(&lp->timer, jiffies + lp->timer_val); out: - spin_unlock(&lp->lock); + spin_unlock_bh(&lp->lock); return err; } @@ -395,7 +397,7 @@ static int iss_net_close(struct net_device *dev) { struct iss_net_private *lp = netdev_priv(dev); netif_stop_queue(dev); - spin_lock(&lp->lock); + spin_lock_bh(&lp->lock); spin_lock(&opened_lock); list_del(&opened); @@ -405,18 +407,17 @@ static int iss_net_close(struct net_device *dev) lp->tp.close(lp); - spin_unlock(&lp->lock); + spin_unlock_bh(&lp->lock); return 0; } static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct iss_net_private *lp = netdev_priv(dev); - unsigned long flags; int len; netif_stop_queue(dev); - spin_lock_irqsave(&lp->lock, flags); + spin_lock_bh(&lp->lock); len = lp->tp.write(lp, &skb); @@ -438,7 +439,7 @@ static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev) pr_err("%s: %s failed(%d)\n", dev->name, __func__, len); } - spin_unlock_irqrestore(&lp->lock, flags); + spin_unlock_bh(&lp->lock); dev_kfree_skb(skb); return NETDEV_TX_OK; @@ -466,9 +467,9 @@ static int iss_net_set_mac(struct net_device *dev, void *addr) if (!is_valid_ether_addr(hwaddr->sa_data)) return -EADDRNOTAVAIL; - spin_lock(&lp->lock); + spin_lock_bh(&lp->lock); memcpy(dev->dev_addr, hwaddr->sa_data, ETH_ALEN); - spin_unlock(&lp->lock); + spin_unlock_bh(&lp->lock); return 0; } @@ -520,11 +521,11 @@ static int iss_net_configure(int index, char *init) *lp = (struct iss_net_private) { .device_list = LIST_HEAD_INIT(lp->device_list), .opened_list = LIST_HEAD_INIT(lp->opened_list), - .lock = __SPIN_LOCK_UNLOCKED(lp.lock), .dev = dev, .index = index, - }; + }; + spin_lock_init(&lp->lock); /* * If this name ends up conflicting with an existing registered * netdevice, that is OK, register_netdev{,ice}() will notice this diff --git a/arch/xtensa/platforms/xtfpga/Makefile b/arch/xtensa/platforms/xtfpga/Makefile index b9ae206340cd..7839d38b2337 100644 --- a/arch/xtensa/platforms/xtfpga/Makefile +++ b/arch/xtensa/platforms/xtfpga/Makefile @@ -6,4 +6,5 @@ # # Note 2! The CFLAGS definitions are in the main makefile... -obj-y = setup.o lcd.o +obj-y += setup.o +obj-$(CONFIG_XTFPGA_LCD) += lcd.o diff --git a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h index aeb316b7ff88..e8cc86fbba09 100644 --- a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h +++ b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h @@ -40,9 +40,6 @@ /* UART */ #define DUART16552_PADDR (XCHAL_KIO_PADDR + 0x0D050020) -/* LCD instruction and data addresses. */ -#define LCD_INSTR_ADDR ((char *)IOADDR(0x0D040000)) -#define LCD_DATA_ADDR ((char *)IOADDR(0x0D040004)) /* Misc. */ #define XTFPGA_FPGAREGS_VADDR IOADDR(0x0D020000) diff --git a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h index 0e435645af5a..4c8541ed1139 100644 --- a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h +++ b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h @@ -11,10 +11,25 @@ #ifndef __XTENSA_XTAVNET_LCD_H #define __XTENSA_XTAVNET_LCD_H +#ifdef CONFIG_XTFPGA_LCD /* Display string STR at position POS on the LCD. */ void lcd_disp_at_pos(char *str, unsigned char pos); /* Shift the contents of the LCD display left or right. */ void lcd_shiftleft(void); void lcd_shiftright(void); +#else +static inline void lcd_disp_at_pos(char *str, unsigned char pos) +{ +} + +static inline void lcd_shiftleft(void) +{ +} + +static inline void lcd_shiftright(void) +{ +} +#endif + #endif diff --git a/arch/xtensa/platforms/xtfpga/lcd.c b/arch/xtensa/platforms/xtfpga/lcd.c index 2872301598df..4dc0c1b43f4b 100644 --- a/arch/xtensa/platforms/xtfpga/lcd.c +++ b/arch/xtensa/platforms/xtfpga/lcd.c @@ -1,50 +1,63 @@ /* - * Driver for the LCD display on the Tensilica LX60 Board. + * Driver for the LCD display on the Tensilica XTFPGA board family. + * http://www.mytechcorp.com/cfdata/productFile/File1/MOC-16216B-B-A0A04.pdf * * 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, 2006 Tensilica Inc. + * Copyright (C) 2015 Cadence Design Systems Inc. */ -/* - * - * FIXME: this code is from the examples from the LX60 user guide. - * - * The lcd_pause function does busy waiting, which is probably not - * great. Maybe the code could be changed to use kernel timers, or - * change the hardware to not need to wait. - */ - +#include <linux/delay.h> #include <linux/init.h> #include <linux/io.h> #include <platform/hardware.h> #include <platform/lcd.h> -#include <linux/delay.h> -#define LCD_PAUSE_ITERATIONS 4000 +/* LCD instruction and data addresses. */ +#define LCD_INSTR_ADDR ((char *)IOADDR(CONFIG_XTFPGA_LCD_BASE_ADDR)) +#define LCD_DATA_ADDR (LCD_INSTR_ADDR + 4) + #define LCD_CLEAR 0x1 #define LCD_DISPLAY_ON 0xc /* 8bit and 2 lines display */ #define LCD_DISPLAY_MODE8BIT 0x38 +#define LCD_DISPLAY_MODE4BIT 0x28 #define LCD_DISPLAY_POS 0x80 #define LCD_SHIFT_LEFT 0x18 #define LCD_SHIFT_RIGHT 0x1c +static void lcd_put_byte(u8 *addr, u8 data) +{ +#ifdef CONFIG_XTFPGA_LCD_8BIT_ACCESS + ACCESS_ONCE(*addr) = data; +#else + ACCESS_ONCE(*addr) = data & 0xf0; + ACCESS_ONCE(*addr) = (data << 4) & 0xf0; +#endif +} + static int __init lcd_init(void) { - *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT; + ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; mdelay(5); - *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT; + ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; udelay(200); - *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT; + ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; + udelay(50); +#ifndef CONFIG_XTFPGA_LCD_8BIT_ACCESS + ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE4BIT; + udelay(50); + lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT); udelay(50); - *LCD_INSTR_ADDR = LCD_DISPLAY_ON; +#endif + lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_ON); udelay(50); - *LCD_INSTR_ADDR = LCD_CLEAR; + lcd_put_byte(LCD_INSTR_ADDR, LCD_CLEAR); mdelay(10); lcd_disp_at_pos("XTENSA LINUX", 0); return 0; @@ -52,10 +65,10 @@ static int __init lcd_init(void) void lcd_disp_at_pos(char *str, unsigned char pos) { - *LCD_INSTR_ADDR = LCD_DISPLAY_POS | pos; + lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_POS | pos); udelay(100); while (*str != 0) { - *LCD_DATA_ADDR = *str; + lcd_put_byte(LCD_DATA_ADDR, *str); udelay(200); str++; } @@ -63,13 +76,13 @@ void lcd_disp_at_pos(char *str, unsigned char pos) void lcd_shiftleft(void) { - *LCD_INSTR_ADDR = LCD_SHIFT_LEFT; + lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_LEFT); udelay(50); } void lcd_shiftright(void) { - *LCD_INSTR_ADDR = LCD_SHIFT_RIGHT; + lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_RIGHT); udelay(50); } |