diff options
Diffstat (limited to 'arch')
99 files changed, 665 insertions, 528 deletions
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 7462a7911002..4c7b0414a3ff 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -57,7 +57,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { wtint(0); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_dead(void) diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index c6606f4d20d6..fb98440c0bd4 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -243,10 +243,8 @@ static inline int constant_fls(unsigned int x) x <<= 2; r -= 2; } - if (!(x & 0x80000000u)) { - x <<= 1; + if (!(x & 0x80000000u)) r -= 1; - } return r; } diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index f1ed17edb085..163641726a2b 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -134,8 +134,10 @@ #ifdef CONFIG_ARC_HAS_PAE40 #define PTE_BITS_NON_RWX_IN_PD1 (0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 #else #define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /************************************************************************** diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index b23986f98450..f73da203b170 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -38,15 +38,27 @@ #ifdef CONFIG_ARC_DW2_UNWIND -static void seed_unwind_frame_info(struct task_struct *tsk, - struct pt_regs *regs, - struct unwind_frame_info *frame_info) +static int +seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, + struct unwind_frame_info *frame_info) { - /* - * synchronous unwinding (e.g. dump_stack) - * - uses current values of SP and friends - */ - if (tsk == NULL && regs == NULL) { + if (regs) { + /* + * Asynchronous unwinding of intr/exception + * - Just uses the pt_regs passed + */ + frame_info->task = tsk; + + frame_info->regs.r27 = regs->fp; + frame_info->regs.r28 = regs->sp; + frame_info->regs.r31 = regs->blink; + frame_info->regs.r63 = regs->ret; + frame_info->call_frame = 0; + } else if (tsk == NULL || tsk == current) { + /* + * synchronous unwinding (e.g. dump_stack) + * - uses current values of SP and friends + */ unsigned long fp, sp, blink, ret; frame_info->task = current; @@ -63,13 +75,17 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r31 = blink; frame_info->regs.r63 = ret; frame_info->call_frame = 0; - } else if (regs == NULL) { + } else { /* - * Asynchronous unwinding of sleeping task - * - Gets SP etc from task's pt_regs (saved bottom of kernel - * mode stack of task) + * Asynchronous unwinding of a likely sleeping task + * - first ensure it is actually sleeping + * - if so, it will be in __switch_to, kernel mode SP of task + * is safe-kept and BLINK at a well known location in there */ + if (tsk->state == TASK_RUNNING) + return -1; + frame_info->task = tsk; frame_info->regs.r27 = TSK_K_FP(tsk); @@ -90,19 +106,8 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r28 += 60; frame_info->call_frame = 0; - } else { - /* - * Asynchronous unwinding of intr/exception - * - Just uses the pt_regs passed - */ - frame_info->task = tsk; - - frame_info->regs.r27 = regs->fp; - frame_info->regs.r28 = regs->sp; - frame_info->regs.r31 = regs->blink; - frame_info->regs.r63 = regs->ret; - frame_info->call_frame = 0; } + return 0; } #endif @@ -116,7 +121,8 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, unsigned int address; struct unwind_frame_info frame_info; - seed_unwind_frame_info(tsk, regs, &frame_info); + if (seed_unwind_frame_info(tsk, regs, &frame_info)) + return 0; while (1) { address = UNW_PC(&frame_info); diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index c340acd989a0..9bb3c24f3677 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -30,14 +30,14 @@ * -Changes related to MMU v2 (Rel 4.8) * * Vineetg: Aug 29th 2008 - * -In TLB Flush operations (Metal Fix MMU) there is a explict command to + * -In TLB Flush operations (Metal Fix MMU) there is a explicit command to * flush Micro-TLBS. If TLB Index Reg is invalid prior to TLBIVUTLB cmd, * it fails. Thus need to load it with ANY valid value before invoking * TLBIVUTLB cmd * * Vineetg: Aug 21th 2008: * -Reduced the duration of IRQ lockouts in TLB Flush routines - * -Multiple copies of TLB erase code seperated into a "single" function + * -Multiple copies of TLB erase code separated into a "single" function * -In TLB Flush routines, interrupt disabling moved UP to retrieve ASID * in interrupt-safe region. * @@ -66,7 +66,7 @@ * * Although J-TLB is 2 way set assoc, ARC700 caches J-TLB into uTLBS which has * much higher associativity. u-D-TLB is 8 ways, u-I-TLB is 4 ways. - * Given this, the thrasing problem should never happen because once the 3 + * Given this, the thrashing problem should never happen because once the 3 * J-TLB entries are created (even though 3rd will knock out one of the prev * two), the u-D-TLB and u-I-TLB will have what is required to accomplish memcpy * @@ -127,7 +127,7 @@ static void utlb_invalidate(void) * There was however an obscure hardware bug, where uTLB flush would * fail when a prior probe for J-TLB (both totally unrelated) would * return lkup err - because the entry didn't exist in MMU. - * The Workround was to set Index reg with some valid value, prior to + * The Workaround was to set Index reg with some valid value, prior to * flush. This was fixed in MMU v3 */ unsigned int idx; @@ -272,7 +272,7 @@ noinline void local_flush_tlb_all(void) } /* - * Flush the entrie MM for userland. The fastest way is to move to Next ASID + * Flush the entire MM for userland. The fastest way is to move to Next ASID */ noinline void local_flush_tlb_mm(struct mm_struct *mm) { @@ -303,7 +303,7 @@ noinline void local_flush_tlb_mm(struct mm_struct *mm) * Difference between this and Kernel Range Flush is * -Here the fastest way (if range is too large) is to move to next ASID * without doing any explicit Shootdown - * -In case of kernel Flush, entry has to be shot down explictly + * -In case of kernel Flush, entry has to be shot down explicitly */ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) @@ -620,7 +620,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, * Super Page size is configurable in hardware (4K to 16M), but fixed once * RTL builds. * - * The exact THP size a Linx configuration will support is a function of: + * The exact THP size a Linux configuration will support is a function of: * - MMU page size (typical 8K, RTL fixed) * - software page walker address split between PGD:PTE:PFN (typical * 11:8:13, but can be changed with 1 line) @@ -698,7 +698,7 @@ void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, #endif -/* Read the Cache Build Confuration Registers, Decode them and save into +/* Read the Cache Build Configuration Registers, Decode them and save into * the cpuinfo structure for later use. * No Validation is done here, simply read/convert the BCRs */ @@ -803,13 +803,13 @@ void arc_mmu_init(void) pr_info("%s", arc_mmu_mumbojumbo(0, str, sizeof(str))); /* - * Can't be done in processor.h due to header include depenedencies + * Can't be done in processor.h due to header include dependencies */ BUILD_BUG_ON(!IS_ALIGNED((CONFIG_ARC_KVADDR_SIZE << 20), PMD_SIZE)); /* * stack top size sanity check, - * Can't be done in processor.h due to header include depenedencies + * Can't be done in processor.h due to header include dependencies */ BUILD_BUG_ON(!IS_ALIGNED(STACK_TOP, PMD_SIZE)); @@ -881,7 +881,7 @@ void arc_mmu_init(void) * the duplicate one. * -Knob to be verbose abt it.(TODO: hook them up to debugfs) */ -volatile int dup_pd_silent; /* Be slient abt it or complain (default) */ +volatile int dup_pd_silent; /* Be silent abt it or complain (default) */ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, struct pt_regs *regs) @@ -948,7 +948,7 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, /*********************************************************************** * Diagnostic Routines - * -Called from Low Level TLB Hanlders if things don;t look good + * -Called from Low Level TLB Handlers if things don;t look good **********************************************************************/ #ifdef CONFIG_ARC_DBG_TLB_PARANOIA diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi index c220dc3c4e0f..243e35f7a56c 100644 --- a/arch/arm/boot/dts/am437x-l4.dtsi +++ b/arch/arm/boot/dts/am437x-l4.dtsi @@ -521,7 +521,7 @@ ranges = <0x0 0x100000 0x8000>; mac_sw: switch@0 { - compatible = "ti,am4372-cpsw","ti,cpsw-switch"; + compatible = "ti,am4372-cpsw-switch", "ti,cpsw-switch"; reg = <0x0 0x4000>; ranges = <0 0 0x4000>; clocks = <&cpsw_125mhz_gclk>, <&dpll_clksel_mac_clk>; diff --git a/arch/arm/boot/dts/dra76x.dtsi b/arch/arm/boot/dts/dra76x.dtsi index b69c7d40f5d8..2f326151116b 100644 --- a/arch/arm/boot/dts/dra76x.dtsi +++ b/arch/arm/boot/dts/dra76x.dtsi @@ -32,8 +32,8 @@ interrupts = <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "int0", "int1"; - clocks = <&mcan_clk>, <&l3_iclk_div>; - clock-names = "cclk", "hclk"; + clocks = <&l3_iclk_div>, <&mcan_clk>; + clock-names = "hclk", "cclk"; bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; }; }; diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 34793aabdb65..58df9fd79a76 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -81,7 +81,6 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_BINFMT_MISC=y CONFIG_CMA=y CONFIG_ZSMALLOC=m -CONFIG_ZSMALLOC_PGTABLE_MAPPING=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 3502c2f746ca..baf7d0204eb5 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -75,6 +75,8 @@ #define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) #define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 + /* * PMD_SHIFT determines the size of the area a second-level page table can map * PGDIR_SHIFT determines what a third-level page table entry can map diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index fbb6693c3352..2b85d175e999 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -25,6 +25,8 @@ #define PTE_HWTABLE_OFF (0) #define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u64)) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 + /* * PGDIR_SHIFT determines the size a top-level page table entry can map. */ diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 8e6ace03e960..9f199b1e8383 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -71,7 +71,7 @@ void arch_cpu_idle(void) arm_pm_idle(); else cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_prepare(void) diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 3ee7bdff86b2..3f62a0c9450d 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -7,7 +7,6 @@ config ARCH_OMAP2 depends on ARCH_MULTI_V6 select ARCH_OMAP2PLUS select CPU_V6 - select PM_GENERIC_DOMAINS if PM select SOC_HAS_OMAP2_SDRC config ARCH_OMAP3 @@ -106,6 +105,8 @@ config ARCH_OMAP2PLUS select OMAP_DM_TIMER select OMAP_GPMC select PINCTRL + select PM_GENERIC_DOMAINS if PM + select PM_GENERIC_DOMAINS_OF if PM select RESET_CONTROLLER select SOC_BUS select TI_SYSC diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index a92d277f81a0..c8d317fafe2e 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -175,8 +175,11 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, if (mpuss_can_lose_context) { error = cpu_cluster_pm_enter(); if (error) { - omap_set_pwrdm_state(mpu_pd, PWRDM_POWER_ON); - goto cpu_cluster_pm_out; + index = 0; + cx = state_ptr + index; + pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state); + omap_set_pwrdm_state(mpu_pd, cx->mpu_state); + mpuss_can_lose_context = 0; } } } @@ -184,7 +187,6 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, omap4_enter_lowpower(dev->cpu, cx->cpu_state); cpu_done[dev->cpu] = true; -cpu_cluster_pm_out: /* Wakeup CPU1 only if it is not offlined */ if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) { diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi index 55259f973b5a..aef8f2b00778 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi @@ -5,20 +5,20 @@ usb { compatible = "simple-bus"; dma-ranges; - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x0 0x0 0x68500000 0x00400000>; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0x0 0x0 0x0 0x68500000 0x0 0x00400000>; usbphy0: usb-phy@0 { compatible = "brcm,sr-usb-combo-phy"; - reg = <0x00000000 0x100>; + reg = <0x0 0x00000000 0x0 0x100>; #phy-cells = <1>; status = "disabled"; }; xhci0: usb@1000 { compatible = "generic-xhci"; - reg = <0x00001000 0x1000>; + reg = <0x0 0x00001000 0x0 0x1000>; interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0 1>, <&usbphy0 0>; phy-names = "phy0", "phy1"; @@ -28,7 +28,7 @@ bdc0: usb@2000 { compatible = "brcm,bdc-v0.16"; - reg = <0x00002000 0x1000>; + reg = <0x0 0x00002000 0x0 0x1000>; interrupts = <GIC_SPI 259 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0 0>, <&usbphy0 1>; phy-names = "phy0", "phy1"; @@ -38,21 +38,21 @@ usbphy1: usb-phy@10000 { compatible = "brcm,sr-usb-combo-phy"; - reg = <0x00010000 0x100>; + reg = <0x0 0x00010000 0x0 0x100>; #phy-cells = <1>; status = "disabled"; }; usbphy2: usb-phy@20000 { compatible = "brcm,sr-usb-hs-phy"; - reg = <0x00020000 0x100>; + reg = <0x0 0x00020000 0x0 0x100>; #phy-cells = <0>; status = "disabled"; }; xhci1: usb@11000 { compatible = "generic-xhci"; - reg = <0x00011000 0x1000>; + reg = <0x0 0x00011000 0x0 0x1000>; interrupts = <GIC_SPI 263 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy1 1>, <&usbphy2>, <&usbphy1 0>; phy-names = "phy0", "phy1", "phy2"; @@ -62,7 +62,7 @@ bdc1: usb@21000 { compatible = "brcm,bdc-v0.16"; - reg = <0x00021000 0x1000>; + reg = <0x0 0x00021000 0x0 0x1000>; interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy2>; phy-names = "phy0"; diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts index 381a84912ba8..c28d51cc5797 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts @@ -10,18 +10,6 @@ model = "NVIDIA Jetson TX2 Developer Kit"; compatible = "nvidia,p2771-0000", "nvidia,tegra186"; - aconnect { - status = "okay"; - - dma-controller@2930000 { - status = "okay"; - }; - - interrupt-controller@2a40000 { - status = "okay"; - }; - }; - i2c@3160000 { power-monitor@42 { compatible = "ti,ina3221"; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi index a2893be80507..0dc8304a2edd 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi @@ -54,7 +54,7 @@ status = "okay"; }; - serial@c280000 { + serial@3100000 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index e9c90f0f44ff..93438d2b9469 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -1161,7 +1161,7 @@ hsp_aon: hsp@c150000 { compatible = "nvidia,tegra194-hsp", "nvidia,tegra186-hsp"; - reg = <0x0c150000 0xa0000>; + reg = <0x0c150000 0x90000>; interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi index e18e1a9a3011..a9caaf7c0d67 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi @@ -1663,16 +1663,6 @@ vin-supply = <&vdd_5v0_sys>; }; - vdd_usb_vbus_otg: regulator@11 { - compatible = "regulator-fixed"; - regulator-name = "USB_VBUS_EN0"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>; - enable-active-high; - vin-supply = <&vdd_5v0_sys>; - }; - vdd_hdmi: regulator@10 { compatible = "regulator-fixed"; regulator-name = "VDD_HDMI_5V0"; @@ -1712,4 +1702,14 @@ enable-active-high; vin-supply = <&vdd_3v3_sys>; }; + + vdd_usb_vbus_otg: regulator@14 { + compatible = "regulator-fixed"; + regulator-name = "USB_VBUS_EN0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>; + enable-active-high; + vin-supply = <&vdd_5v0_sys>; + }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts index f6e6a24829af..b5d9a5526272 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts @@ -8,7 +8,7 @@ compatible = "nvidia,tegra234-vdk", "nvidia,tegra234"; aliases { - sdhci3 = "/cbb@0/sdhci@3460000"; + mmc3 = "/bus@0/mmc@3460000"; serial0 = &uarta; }; @@ -17,12 +17,12 @@ stdout-path = "serial0:115200n8"; }; - cbb@0 { + bus@0 { serial@3100000 { status = "okay"; }; - sdhci@3460000 { + mmc@3460000 { status = "okay"; bus-width = <8>; non-removable; diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index a94dac76bf3f..59e0cbfa2214 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -179,22 +179,22 @@ }; soc: soc { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0 0 0 0xffffffff>; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0 0 0 0 0x0 0xffffffff>; dma-ranges; compatible = "simple-bus"; prng: qrng@e1000 { compatible = "qcom,prng-ee"; - reg = <0xe3000 0x1000>; + reg = <0x0 0xe3000 0x0 0x1000>; clocks = <&gcc GCC_PRNG_AHB_CLK>; clock-names = "core"; }; cryptobam: dma@704000 { compatible = "qcom,bam-v1.7.0"; - reg = <0x00704000 0x20000>; + reg = <0x0 0x00704000 0x0 0x20000>; interrupts = <GIC_SPI 207 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_CRYPTO_AHB_CLK>; clock-names = "bam_clk"; @@ -206,7 +206,7 @@ crypto: crypto@73a000 { compatible = "qcom,crypto-v5.1"; - reg = <0x0073a000 0x6000>; + reg = <0x0 0x0073a000 0x0 0x6000>; clocks = <&gcc GCC_CRYPTO_AHB_CLK>, <&gcc GCC_CRYPTO_AXI_CLK>, <&gcc GCC_CRYPTO_CLK>; @@ -217,7 +217,7 @@ tlmm: pinctrl@1000000 { compatible = "qcom,ipq6018-pinctrl"; - reg = <0x01000000 0x300000>; + reg = <0x0 0x01000000 0x0 0x300000>; interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>; gpio-controller; #gpio-cells = <2>; @@ -235,7 +235,7 @@ gcc: gcc@1800000 { compatible = "qcom,gcc-ipq6018"; - reg = <0x01800000 0x80000>; + reg = <0x0 0x01800000 0x0 0x80000>; clocks = <&xo>, <&sleep_clk>; clock-names = "xo", "sleep_clk"; #clock-cells = <1>; @@ -244,17 +244,17 @@ tcsr_mutex_regs: syscon@1905000 { compatible = "syscon"; - reg = <0x01905000 0x8000>; + reg = <0x0 0x01905000 0x0 0x8000>; }; tcsr_q6: syscon@1945000 { compatible = "syscon"; - reg = <0x01945000 0xe000>; + reg = <0x0 0x01945000 0x0 0xe000>; }; blsp_dma: dma@7884000 { compatible = "qcom,bam-v1.7.0"; - reg = <0x07884000 0x2b000>; + reg = <0x0 0x07884000 0x0 0x2b000>; interrupts = <GIC_SPI 238 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_AHB_CLK>; clock-names = "bam_clk"; @@ -264,7 +264,7 @@ blsp1_uart3: serial@78b1000 { compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; - reg = <0x078b1000 0x200>; + reg = <0x0 0x078b1000 0x0 0x200>; interrupts = <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_UART3_APPS_CLK>, <&gcc GCC_BLSP1_AHB_CLK>; @@ -276,7 +276,7 @@ compatible = "qcom,spi-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b5000 0x600>; + reg = <0x0 0x078b5000 0x0 0x600>; interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>, @@ -291,7 +291,7 @@ compatible = "qcom,spi-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b6000 0x600>; + reg = <0x0 0x078b6000 0x0 0x600>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP2_SPI_APPS_CLK>, @@ -306,7 +306,7 @@ compatible = "qcom,i2c-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b6000 0x600>; + reg = <0x0 0x078b6000 0x0 0x600>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_AHB_CLK>, <&gcc GCC_BLSP1_QUP2_I2C_APPS_CLK>; @@ -321,7 +321,7 @@ compatible = "qcom,i2c-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b7000 0x600>; + reg = <0x0 0x078b7000 0x0 0x600>; interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_AHB_CLK>, <&gcc GCC_BLSP1_QUP3_I2C_APPS_CLK>; @@ -336,24 +336,24 @@ compatible = "qcom,msm-qgic2"; interrupt-controller; #interrupt-cells = <0x3>; - reg = <0x0b000000 0x1000>, /*GICD*/ - <0x0b002000 0x1000>, /*GICC*/ - <0x0b001000 0x1000>, /*GICH*/ - <0x0b004000 0x1000>; /*GICV*/ + reg = <0x0 0x0b000000 0x0 0x1000>, /*GICD*/ + <0x0 0x0b002000 0x0 0x1000>, /*GICC*/ + <0x0 0x0b001000 0x0 0x1000>, /*GICH*/ + <0x0 0x0b004000 0x0 0x1000>; /*GICV*/ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>; }; watchdog@b017000 { compatible = "qcom,kpss-wdt"; interrupts = <GIC_SPI 3 IRQ_TYPE_EDGE_RISING>; - reg = <0x0b017000 0x40>; + reg = <0x0 0x0b017000 0x0 0x40>; clocks = <&sleep_clk>; timeout-sec = <10>; }; apcs_glb: mailbox@b111000 { compatible = "qcom,ipq6018-apcs-apps-global"; - reg = <0x0b111000 0x1000>; + reg = <0x0 0x0b111000 0x0 0x1000>; #clock-cells = <1>; clocks = <&a53pll>, <&xo>; clock-names = "pll", "xo"; @@ -362,7 +362,7 @@ a53pll: clock@b116000 { compatible = "qcom,ipq6018-a53pll"; - reg = <0x0b116000 0x40>; + reg = <0x0 0x0b116000 0x0 0x40>; #clock-cells = <0>; clocks = <&xo>; clock-names = "xo"; @@ -377,68 +377,68 @@ }; timer@b120000 { - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; ranges; compatible = "arm,armv7-timer-mem"; - reg = <0x0b120000 0x1000>; + reg = <0x0 0x0b120000 0x0 0x1000>; clock-frequency = <19200000>; frame@b120000 { frame-number = <0>; interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b121000 0x1000>, - <0x0b122000 0x1000>; + reg = <0x0 0x0b121000 0x0 0x1000>, + <0x0 0x0b122000 0x0 0x1000>; }; frame@b123000 { frame-number = <1>; interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>; - reg = <0xb123000 0x1000>; + reg = <0x0 0xb123000 0x0 0x1000>; status = "disabled"; }; frame@b124000 { frame-number = <2>; interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b124000 0x1000>; + reg = <0x0 0x0b124000 0x0 0x1000>; status = "disabled"; }; frame@b125000 { frame-number = <3>; interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b125000 0x1000>; + reg = <0x0 0x0b125000 0x0 0x1000>; status = "disabled"; }; frame@b126000 { frame-number = <4>; interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b126000 0x1000>; + reg = <0x0 0x0b126000 0x0 0x1000>; status = "disabled"; }; frame@b127000 { frame-number = <5>; interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b127000 0x1000>; + reg = <0x0 0x0b127000 0x0 0x1000>; status = "disabled"; }; frame@b128000 { frame-number = <6>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b128000 0x1000>; + reg = <0x0 0x0b128000 0x0 0x1000>; status = "disabled"; }; }; q6v5_wcss: remoteproc@cd00000 { compatible = "qcom,ipq8074-wcss-pil"; - reg = <0x0cd00000 0x4040>, - <0x004ab000 0x20>; + reg = <0x0 0x0cd00000 0x0 0x4040>, + <0x0 0x004ab000 0x0 0x20>; reg-names = "qdsp6", "rmb"; interrupts-extended = <&intc GIC_SPI 325 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts index 35bd6b904b9c..337681038519 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts +++ b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts @@ -243,7 +243,6 @@ interrupts = <RK_PB2 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&pmic_int>; - rockchip,system-power-controller; wakeup-source; #clock-cells = <1>; clock-output-names = "rk808-clkout1", "xin32k"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts index be7a31d81632..2ee07d15a6e3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts @@ -20,7 +20,7 @@ gmac_clk: gmac-clock { compatible = "fixed-clock"; clock-frequency = <125000000>; - clock-output-names = "gmac_clk"; + clock-output-names = "gmac_clkin"; #clock-cells = <0>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi index e7a459fa4322..20309076dbac 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi @@ -74,14 +74,14 @@ label = "red:diy"; gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>; default-state = "off"; - linux,default-trigger = "mmc1"; + linux,default-trigger = "mmc2"; }; yellow_led: led-2 { label = "yellow:yellow-led"; gpios = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>; default-state = "off"; - linux,default-trigger = "mmc0"; + linux,default-trigger = "mmc1"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index ada724b12f01..7a9a7aca86c6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -29,6 +29,9 @@ i2c6 = &i2c6; i2c7 = &i2c7; i2c8 = &i2c8; + mmc0 = &sdio0; + mmc1 = &sdmmc; + mmc2 = &sdhci; serial0 = &uart0; serial1 = &uart1; serial2 = &uart2; diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index ec213b4a1650..1c26d7baa67f 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -128,6 +128,9 @@ static inline void local_daif_inherit(struct pt_regs *regs) { unsigned long flags = regs->pstate & DAIF_MASK; + if (interrupts_enabled(regs)) + trace_hardirqs_on(); + /* * We can't use local_daif_restore(regs->pstate) here as * system_has_prio_mask_debugging() won't restore the I bit if it can diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 99b9383cd036..0756191f44f6 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -31,7 +31,12 @@ static inline u32 disr_to_esr(u64 disr) return esr; } +asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs); +asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs); asmlinkage void enter_from_user_mode(void); +asmlinkage void exit_to_user_mode(void); +void arm64_enter_nmi(struct pt_regs *regs); +void arm64_exit_nmi(struct pt_regs *regs); void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); void do_bti(struct pt_regs *regs); diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 4ff12a7adcfd..5628289b9d5e 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -115,8 +115,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) -#define pte_valid_young(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) #define pte_valid_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) @@ -124,9 +122,12 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. + * Note that we can't make any assumptions based on the state of the access + * flag, since ptep_clear_flush_young() elides a DSB when invalidating the + * TLB. */ #define pte_accessible(mm, pte) \ - (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (subject to the @@ -164,13 +165,6 @@ static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) return pmd; } -static inline pte_t pte_wrprotect(pte_t pte) -{ - pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); - return pte; -} - static inline pte_t pte_mkwrite(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); @@ -196,6 +190,20 @@ static inline pte_t pte_mkdirty(pte_t pte) return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); + + pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + return pte; +} + static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); @@ -845,12 +853,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres pte = READ_ONCE(*ptep); do { old_pte = pte; - /* - * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY - * clear), set the PTE_DIRTY bit. - */ - if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h index 4266262101fe..006946745352 100644 --- a/arch/arm64/include/asm/probes.h +++ b/arch/arm64/include/asm/probes.h @@ -7,6 +7,8 @@ #ifndef _ARM_PROBES_H #define _ARM_PROBES_H +#include <asm/insn.h> + typedef u32 probe_opcode_t; typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *); diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 997cf8c8cd52..28c85b87b8cd 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -193,6 +193,10 @@ struct pt_regs { /* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */ u64 pmr_save; u64 stackframe[2]; + + /* Only valid for some EL1 exceptions. */ + u64 lockdep_hardirqs; + u64 exit_rcu; }; static inline bool in_syscall(struct pt_regs const *regs) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index e2ef4c2edf06..801861d05426 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -987,7 +987,7 @@ #define SYS_TFSR_EL1_TF0_SHIFT 0 #define SYS_TFSR_EL1_TF1_SHIFT 1 #define SYS_TFSR_EL1_TF0 (UL(1) << SYS_TFSR_EL1_TF0_SHIFT) -#define SYS_TFSR_EL1_TF1 (UK(2) << SYS_TFSR_EL1_TF1_SHIFT) +#define SYS_TFSR_EL1_TF1 (UL(1) << SYS_TFSR_EL1_TF1_SHIFT) /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */ #define SYS_MPIDR_SAFE_VAL (BIT(31)) diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 43d4c329775f..70e0a7591245 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -17,40 +17,164 @@ #include <asm/mmu.h> #include <asm/sysreg.h> -static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) +/* + * This is intended to match the logic in irqentry_enter(), handling the kernel + * mode transitions only. + */ +static void noinstr enter_from_kernel_mode(struct pt_regs *regs) +{ + regs->exit_rcu = false; + + if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) { + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_irq_enter(); + trace_hardirqs_off_finish(); + + regs->exit_rcu = true; + return; + } + + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_irq_enter_check_tick(); + trace_hardirqs_off_finish(); +} + +/* + * This is intended to match the logic in irqentry_exit(), handling the kernel + * mode transitions only, and with preemption handled elsewhere. + */ +static void noinstr exit_to_kernel_mode(struct pt_regs *regs) +{ + lockdep_assert_irqs_disabled(); + + if (interrupts_enabled(regs)) { + if (regs->exit_rcu) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + rcu_irq_exit(); + lockdep_hardirqs_on(CALLER_ADDR0); + return; + } + + trace_hardirqs_on(); + } else { + if (regs->exit_rcu) + rcu_irq_exit(); + } +} + +void noinstr arm64_enter_nmi(struct pt_regs *regs) +{ + regs->lockdep_hardirqs = lockdep_hardirqs_enabled(); + + __nmi_enter(); + lockdep_hardirqs_off(CALLER_ADDR0); + lockdep_hardirq_enter(); + rcu_nmi_enter(); + + trace_hardirqs_off_finish(); + ftrace_nmi_enter(); +} + +void noinstr arm64_exit_nmi(struct pt_regs *regs) +{ + bool restore = regs->lockdep_hardirqs; + + ftrace_nmi_exit(); + if (restore) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + } + + rcu_nmi_exit(); + lockdep_hardirq_exit(); + if (restore) + lockdep_hardirqs_on(CALLER_ADDR0); + __nmi_exit(); +} + +asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) + arm64_enter_nmi(regs); + else + enter_from_kernel_mode(regs); +} + +asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) + arm64_exit_nmi(regs); + else + exit_to_kernel_mode(regs); +} + +static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); + enter_from_kernel_mode(regs); local_daif_inherit(regs); far = untagged_addr(far); do_mem_abort(far, esr, regs); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_abort); -static void notrace el1_pc(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_pc(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); + enter_from_kernel_mode(regs); local_daif_inherit(regs); do_sp_pc_abort(far, esr, regs); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_pc); -static void notrace el1_undef(struct pt_regs *regs) +static void noinstr el1_undef(struct pt_regs *regs) { + enter_from_kernel_mode(regs); local_daif_inherit(regs); do_undefinstr(regs); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_undef); -static void notrace el1_inv(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_inv(struct pt_regs *regs, unsigned long esr) { + enter_from_kernel_mode(regs); local_daif_inherit(regs); bad_mode(regs, 0, esr); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_inv); -static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) +static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs) +{ + regs->lockdep_hardirqs = lockdep_hardirqs_enabled(); + + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_nmi_enter(); + + trace_hardirqs_off_finish(); +} + +static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs) +{ + bool restore = regs->lockdep_hardirqs; + + if (restore) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + } + + rcu_nmi_exit(); + if (restore) + lockdep_hardirqs_on(CALLER_ADDR0); +} + +static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -62,18 +186,21 @@ static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + arm64_enter_el1_dbg(regs); do_debug_exception(far, esr, regs); + arm64_exit_el1_dbg(regs); } -NOKPROBE_SYMBOL(el1_dbg); -static void notrace el1_fpac(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_fpac(struct pt_regs *regs, unsigned long esr) { + enter_from_kernel_mode(regs); local_daif_inherit(regs); do_ptrauth_fault(regs, esr); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_fpac); -asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) +asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); @@ -106,20 +233,34 @@ asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) el1_inv(regs, esr); } } -NOKPROBE_SYMBOL(el1_sync_handler); -static void notrace el0_da(struct pt_regs *regs, unsigned long esr) +asmlinkage void noinstr enter_from_user_mode(void) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit_irqoff(); + trace_hardirqs_off_finish(); +} + +asmlinkage void noinstr exit_to_user_mode(void) +{ + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + user_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +static void noinstr el0_da(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); far = untagged_addr(far); do_mem_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el0_da); -static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_ia(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -131,90 +272,80 @@ static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) if (!is_ttbr0_addr(far)) arm64_apply_bp_hardening(); - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_mem_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el0_ia); -static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_fpsimd_acc(esr, regs); } -NOKPROBE_SYMBOL(el0_fpsimd_acc); -static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sve_acc(esr, regs); } -NOKPROBE_SYMBOL(el0_sve_acc); -static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_fpsimd_exc(esr, regs); } -NOKPROBE_SYMBOL(el0_fpsimd_exc); -static void notrace el0_sys(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_sys(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sysinstr(esr, regs); } -NOKPROBE_SYMBOL(el0_sys); -static void notrace el0_pc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_pc(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); if (!is_ttbr0_addr(instruction_pointer(regs))) arm64_apply_bp_hardening(); - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el0_pc); -static void notrace el0_sp(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_sp(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(regs->sp, esr, regs); } -NOKPROBE_SYMBOL(el0_sp); -static void notrace el0_undef(struct pt_regs *regs) +static void noinstr el0_undef(struct pt_regs *regs) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_undefinstr(regs); } -NOKPROBE_SYMBOL(el0_undef); -static void notrace el0_bti(struct pt_regs *regs) +static void noinstr el0_bti(struct pt_regs *regs) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_bti(regs); } -NOKPROBE_SYMBOL(el0_bti); -static void notrace el0_inv(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); bad_el0_sync(regs, 0, esr); } -NOKPROBE_SYMBOL(el0_inv); -static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr) { /* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */ unsigned long far = read_sysreg(far_el1); @@ -222,30 +353,28 @@ static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - user_exit_irqoff(); + enter_from_user_mode(); do_debug_exception(far, esr, regs); local_daif_restore(DAIF_PROCCTX_NOIRQ); } -NOKPROBE_SYMBOL(el0_dbg); -static void notrace el0_svc(struct pt_regs *regs) +static void noinstr el0_svc(struct pt_regs *regs) { if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + enter_from_user_mode(); do_el0_svc(regs); } -NOKPROBE_SYMBOL(el0_svc); -static void notrace el0_fpac(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_ptrauth_fault(regs, esr); } -NOKPROBE_SYMBOL(el0_fpac); -asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) +asmlinkage void noinstr el0_sync_handler(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); @@ -297,27 +426,25 @@ asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) el0_inv(regs, esr); } } -NOKPROBE_SYMBOL(el0_sync_handler); #ifdef CONFIG_COMPAT -static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_cp15instr(esr, regs); } -NOKPROBE_SYMBOL(el0_cp15); -static void notrace el0_svc_compat(struct pt_regs *regs) +static void noinstr el0_svc_compat(struct pt_regs *regs) { if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + enter_from_user_mode(); do_el0_svc_compat(regs); } -NOKPROBE_SYMBOL(el0_svc_compat); -asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) +asmlinkage void noinstr el0_sync_compat_handler(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); @@ -360,5 +487,4 @@ asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) el0_inv(regs, esr); } } -NOKPROBE_SYMBOL(el0_sync_compat_handler); #endif /* CONFIG_COMPAT */ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index b295fb912b12..d72c818b019c 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -30,18 +30,18 @@ #include <asm/unistd.h> /* - * Context tracking subsystem. Used to instrument transitions - * between user and kernel mode. + * Context tracking and irqflag tracing need to instrument transitions between + * user and kernel mode. */ - .macro ct_user_exit_irqoff -#ifdef CONFIG_CONTEXT_TRACKING + .macro user_exit_irqoff +#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS) bl enter_from_user_mode #endif .endm - .macro ct_user_enter -#ifdef CONFIG_CONTEXT_TRACKING - bl context_tracking_user_enter + .macro user_enter_irqoff +#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS) + bl exit_to_user_mode #endif .endm @@ -298,9 +298,6 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING alternative_else_nop_endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR - .if \el == 0 - ct_user_enter - .endif #ifdef CONFIG_ARM64_SW_TTBR0_PAN alternative_if_not ARM64_HAS_PAN @@ -637,16 +634,8 @@ SYM_CODE_START_LOCAL_NOALIGN(el1_irq) gic_prio_irq_setup pmr=x20, tmp=x1 enable_da_f -#ifdef CONFIG_ARM64_PSEUDO_NMI - test_irqs_unmasked res=x0, pmr=x20 - cbz x0, 1f - bl asm_nmi_enter -1: -#endif - -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif + mov x0, sp + bl enter_el1_irq_or_nmi irq_handler @@ -665,26 +654,8 @@ alternative_else_nop_endif 1: #endif -#ifdef CONFIG_ARM64_PSEUDO_NMI - /* - * When using IRQ priority masking, we can get spurious interrupts while - * PMR is set to GIC_PRIO_IRQOFF. An NMI might also have occurred in a - * section with interrupts disabled. Skip tracing in those cases. - */ - test_irqs_unmasked res=x0, pmr=x20 - cbz x0, 1f - bl asm_nmi_exit -1: -#endif - -#ifdef CONFIG_TRACE_IRQFLAGS -#ifdef CONFIG_ARM64_PSEUDO_NMI - test_irqs_unmasked res=x0, pmr=x20 - cbnz x0, 1f -#endif - bl trace_hardirqs_on -1: -#endif + mov x0, sp + bl exit_el1_irq_or_nmi kernel_exit 1 SYM_CODE_END(el1_irq) @@ -726,21 +697,14 @@ SYM_CODE_START_LOCAL_NOALIGN(el0_irq) kernel_entry 0 el0_irq_naked: gic_prio_irq_setup pmr=x20, tmp=x0 - ct_user_exit_irqoff + user_exit_irqoff enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - tbz x22, #55, 1f bl do_el0_irq_bp_hardening 1: irq_handler -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_on -#endif b ret_to_user SYM_CODE_END(el0_irq) @@ -759,7 +723,7 @@ SYM_CODE_START_LOCAL(el0_error) el0_error_naked: mrs x25, esr_el1 gic_prio_kentry_setup tmp=x2 - ct_user_exit_irqoff + user_exit_irqoff enable_dbg mov x0, sp mov x1, x25 @@ -774,13 +738,17 @@ SYM_CODE_END(el0_error) SYM_CODE_START_LOCAL(ret_to_user) disable_daif gic_prio_kentry_setup tmp=x3 - ldr x1, [tsk, #TSK_TI_FLAGS] - and x2, x1, #_TIF_WORK_MASK +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif + ldr x19, [tsk, #TSK_TI_FLAGS] + and x2, x19, #_TIF_WORK_MASK cbnz x2, work_pending finish_ret_to_user: + user_enter_irqoff /* Ignore asynchronous tag check faults in the uaccess routines */ clear_mte_async_tcf - enable_step_tsk x1, x2 + enable_step_tsk x19, x2 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK bl stackleak_erase #endif @@ -791,11 +759,9 @@ finish_ret_to_user: */ work_pending: mov x0, sp // 'regs' + mov x1, x19 bl do_notify_resume -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_on // enabled while in userspace -#endif - ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for single-step + ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step b finish_ret_to_user SYM_CODE_END(ret_to_user) diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 9cf2fb87584a..60456a62da11 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -67,18 +67,3 @@ void __init init_IRQ(void) local_daif_restore(DAIF_PROCCTX_NOIRQ); } } - -/* - * Stubs to make nmi_enter/exit() code callable from ASM - */ -asmlinkage void notrace asm_nmi_enter(void) -{ - nmi_enter(); -} -NOKPROBE_SYMBOL(asm_nmi_enter); - -asmlinkage void notrace asm_nmi_exit(void) -{ - nmi_exit(); -} -NOKPROBE_SYMBOL(asm_nmi_exit); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index a47a40ec6ad9..ed919f633ed8 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -72,13 +72,13 @@ EXPORT_SYMBOL_GPL(pm_power_off); void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); -static void __cpu_do_idle(void) +static void noinstr __cpu_do_idle(void) { dsb(sy); wfi(); } -static void __cpu_do_idle_irqprio(void) +static void noinstr __cpu_do_idle_irqprio(void) { unsigned long pmr; unsigned long daif_bits; @@ -108,7 +108,7 @@ static void __cpu_do_idle_irqprio(void) * ensure that interrupts are not masked at the PMR (because the core will * not wake up if we block the wake up signal in the interrupt controller). */ -void cpu_do_idle(void) +void noinstr cpu_do_idle(void) { if (system_uses_irq_prio_masking()) __cpu_do_idle_irqprio(); @@ -119,14 +119,14 @@ void cpu_do_idle(void) /* * This is our default idle handler. */ -void arch_cpu_idle(void) +void noinstr arch_cpu_idle(void) { /* * This should do all the clock switching and wait for interrupt * tricks */ cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 7689f2031c0c..793c46d6a447 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -10,6 +10,7 @@ #include <linux/uaccess.h> #include <asm/alternative.h> +#include <asm/exception.h> #include <asm/kprobes.h> #include <asm/mmu.h> #include <asm/ptrace.h> @@ -223,16 +224,16 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs, } -asmlinkage __kprobes notrace unsigned long +asmlinkage noinstr unsigned long __sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg) { unsigned long ret; - nmi_enter(); + arm64_enter_nmi(regs); ret = _sdei_handler(regs, arg); - nmi_exit(); + arm64_exit_nmi(regs); return ret; } diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index e4c0dadf0d92..f8f758e4a306 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -121,7 +121,6 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, cortex_a76_erratum_1463225_svc_handler(); local_daif_restore(DAIF_PROCCTX); - user_exit(); if (system_supports_mte() && (flags & _TIF_MTE_ASYNC_FAULT)) { /* diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 8af4e0e85736..2059d8f43f55 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -34,6 +34,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> +#include <asm/exception.h> #include <asm/extable.h> #include <asm/insn.h> #include <asm/kprobes.h> @@ -753,8 +754,10 @@ const char *esr_get_class_string(u32 esr) * bad_mode handles the impossible case in the exception vector. This is always * fatal. */ -asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) +asmlinkage void notrace bad_mode(struct pt_regs *regs, int reason, unsigned int esr) { + arm64_enter_nmi(regs); + console_verbose(); pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n", @@ -786,7 +789,7 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) __aligned(16); -asmlinkage void handle_bad_stack(struct pt_regs *regs) +asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr); @@ -794,6 +797,8 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs) unsigned int esr = read_sysreg(esr_el1); unsigned long far = read_sysreg(far_el1); + arm64_enter_nmi(regs); + console_verbose(); pr_emerg("Insufficient stack space to handle exception!"); @@ -865,23 +870,16 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr) } } -asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr) +asmlinkage void noinstr do_serror(struct pt_regs *regs, unsigned int esr) { - nmi_enter(); + arm64_enter_nmi(regs); /* non-RAS errors are not containable */ if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr)) arm64_serror_panic(regs, esr); - nmi_exit(); -} - -asmlinkage void enter_from_user_mode(void) -{ - CT_WARN_ON(ct_state() != CONTEXT_USER); - user_exit_irqoff(); + arm64_exit_nmi(regs); } -NOKPROBE_SYMBOL(enter_from_user_mode); /* GENERIC_BUG traps */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S index bb2d986ff696..a797abace13f 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S @@ -13,6 +13,11 @@ SECTIONS { HYP_SECTION(.text) + /* + * .hyp..data..percpu needs to be page aligned to maintain the same + * alignment for when linking into vmlinux. + */ + . = ALIGN(PAGE_SIZE); HYP_SECTION_NAME(.data..percpu) : { PERCPU_INPUT(L1_CACHE_BYTES) } diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 52d6f24f65dc..15a6c98ee92f 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -273,6 +273,23 @@ static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, return extract_bytes(value, addr & 7, len); } +static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + int target_vcpu_id = vcpu->vcpu_id; + u64 value; + + value = (u64)(mpidr & GENMASK(23, 0)) << 32; + value |= ((target_vcpu_id & 0xffff) << 8); + + if (vgic_has_its(vcpu->kvm)) + value |= GICR_TYPER_PLPIS; + + /* reporting of the Last bit is not supported for userspace */ + return extract_bytes(value, addr & 7, len); +} + static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { @@ -593,8 +610,9 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { REGISTER_DESC_WITH_LENGTH(GICR_IIDR, vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_TYPER, - vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8, + REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER, + vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, + vgic_uaccess_read_v3r_typer, vgic_mmio_uaccess_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_WAKER, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 1ee94002801f..795d224f184f 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -789,25 +789,6 @@ void __init hook_debug_fault_code(int nr, */ static void debug_exception_enter(struct pt_regs *regs) { - /* - * Tell lockdep we disabled irqs in entry.S. Do nothing if they were - * already disabled to preserve the last enabled/disabled addresses. - */ - if (interrupts_enabled(regs)) - trace_hardirqs_off(); - - if (user_mode(regs)) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - } else { - /* - * We might have interrupted pretty much anything. In - * fact, if we're a debug exception, we can even interrupt - * NMI processing. We don't want this code makes in_nmi() - * to return true, but we need to notify RCU. - */ - rcu_nmi_enter(); - } - preempt_disable(); /* This code is a bit fragile. Test it. */ @@ -818,12 +799,6 @@ NOKPROBE_SYMBOL(debug_exception_enter); static void debug_exception_exit(struct pt_regs *regs) { preempt_enable_no_resched(); - - if (!user_mode(regs)) - rcu_nmi_exit(); - - if (interrupts_enabled(regs)) - trace_hardirqs_on(); } NOKPROBE_SYMBOL(debug_exception_exit); diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index f730869e21ee..69af6bc87e64 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -102,6 +102,6 @@ void arch_cpu_idle(void) #ifdef CONFIG_CPU_PM_STOP asm volatile("stop\n"); #endif - local_irq_enable(); + raw_local_irq_enable(); } #endif diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index aea0a40b77a9..bc1364db58fe 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -57,7 +57,7 @@ asmlinkage void ret_from_kernel_thread(void); */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); __asm__("sleep"); } diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 5a0a95d93ddb..67767c5ed98c 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -44,7 +44,7 @@ void arch_cpu_idle(void) { __vmwait(); /* interrupts wake us up, but irqs are still disabled */ - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6b61a703bcf5..c9ff8796b509 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -239,7 +239,7 @@ void arch_cpu_idle(void) if (mark_idle) (*mark_idle)(1); - safe_halt(); + raw_safe_halt(); if (mark_idle) (*mark_idle)(0); diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index a9e46e525cd0..f99860771ff4 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -149,5 +149,5 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpregs) void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index a950fc1ddb4d..6c0532d7b211 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -154,6 +154,7 @@ static inline void pmd_clear(pmd_t *pmdp) #if defined(CONFIG_XPA) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 #define pte_pfn(x) (((unsigned long)((x).pte_high >> _PFN_SHIFT)) | (unsigned long)((x).pte_low << _PAGE_PRESENT_SHIFT)) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) @@ -169,6 +170,7 @@ pfn_pte(unsigned long pfn, pgprot_t prot) #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #define pte_pfn(x) ((unsigned long)((x).pte_high >> 6)) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) @@ -183,6 +185,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) #else +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #ifdef CONFIG_CPU_VR41XX #define pte_pfn(x) ((unsigned long)((x).pte >> (PAGE_SHIFT + 2))) #define pfn_pte(pfn, prot) __pte(((pfn) << (PAGE_SHIFT + 2)) | pgprot_val(prot)) diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 5bc3b04693c7..18e69ebf5691 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -33,19 +33,19 @@ static void __cpuidle r3081_wait(void) { unsigned long cfg = read_c0_conf(); write_c0_conf(cfg | R30XX_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } static void __cpuidle r39xx_wait(void) { if (!need_resched()) write_c0_conf(read_c0_conf() | TX39_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } void __cpuidle r4k_wait(void) { - local_irq_enable(); + raw_local_irq_enable(); __r4k_wait(); } @@ -64,7 +64,7 @@ void __cpuidle r4k_wait_irqoff(void) " .set arch=r4000 \n" " wait \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -84,7 +84,7 @@ static void __cpuidle rm7k_wait_irqoff(void) " wait \n" " mtc0 $1, $12 # stalls until W stage \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -257,7 +257,7 @@ void arch_cpu_idle(void) if (cpu_wait) cpu_wait(); else - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_CPU_IDLE diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 4ffe857e6ada..50b4eb19a6cc 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 0ff391f00334..3c98728cce24 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -79,7 +79,7 @@ void machine_power_off(void) */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); if (mfspr(SPR_UPR) & SPR_UPR_PMP) mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME); } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index f196d96e2f9f..a92a23d6acd9 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -169,7 +169,7 @@ void __cpuidle arch_cpu_idle_dead(void) void __cpuidle arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); /* nop on real hardware, qemu will idle sleep. */ asm volatile("or %%r10,%%r10,%%r10\n":::); diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index d9eb0da845e1..5c8c06215dd4 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -247,7 +247,6 @@ KBUILD_CFLAGS += $(call cc-option,-mno-string) cpu-as-$(CONFIG_40x) += -Wa,-m405 cpu-as-$(CONFIG_44x) += -Wa,-m440 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) -cpu-as-$(CONFIG_E200) += -Wa,-me200 cpu-as-$(CONFIG_E500) += -Wa,-me500 # When using '-many -mpower4' gas will first try and find a matching power4 diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 36443cda8dcf..1376be95e975 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -36,8 +36,10 @@ static inline bool pte_user(pte_t pte) */ #ifdef CONFIG_PTE_64BIT #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index 28716e2f13e3..a39e2d193fdc 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -63,6 +63,8 @@ #else /* !__ASSEMBLY__ */ +#include <linux/jump_label.h> + DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); #ifdef CONFIG_PPC_KUAP diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index e0b52940e43c..750918451dd2 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -242,6 +242,18 @@ extern void radix_init_pseries(void); static inline void radix_init_pseries(void) { }; #endif +#ifdef CONFIG_HOTPLUG_CPU +#define arch_clear_mm_cpumask_cpu(cpu, mm) \ + do { \ + if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { \ + atomic_dec(&(mm)->context.active_cpus); \ + cpumask_clear_cpu(cpu, mm_cpumask(mm)); \ + } \ + } while (0) + +void cleanup_cpu_mmu_context(void); +#endif + static inline int get_user_context(mm_context_t *ctx, unsigned long ea) { int index = ea >> MAX_EA_BITS_PER_CONTEXT; diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index ee2243ba96cf..96522f7f0618 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -153,8 +153,10 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f63a3d3bca3d..4d01f09ecf80 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1000,8 +1000,6 @@ TRAMP_REAL_BEGIN(system_reset_idle_wake) * Vectors for the FWNMI option. Share common code. */ TRAMP_REAL_BEGIN(system_reset_fwnmi) - /* XXX: fwnmi guest could run a nested/PR guest, so why no test? */ - __IKVM_REAL(system_reset)=0 GEN_INT_ENTRY system_reset, virt=0 #endif /* CONFIG_PPC_PSERIES */ @@ -1412,6 +1410,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) * If none is found, do a Linux page fault. Linux page faults can happen in * kernel mode due to user copy operations of course. * + * KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest + * MMU context, which may cause a DSI in the host, which must go to the + * KVM handler. MSR[IR] is not enabled, so the real-mode handler will + * always be used regardless of AIL setting. + * * - Radix MMU * The hardware loads from the Linux page table directly, so a fault goes * immediately to Linux page fault. @@ -1422,10 +1425,8 @@ INT_DEFINE_BEGIN(data_access) IVEC=0x300 IDAR=1 IDSISR=1 -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_SKIP=1 IKVM_REAL=1 -#endif INT_DEFINE_END(data_access) EXC_REAL_BEGIN(data_access, 0x300, 0x80) @@ -1464,6 +1465,8 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) * ppc64_bolted_size (first segment). The kernel handler must avoid stomping * on user-handler data structures. * + * KVM: Same as 0x300, DSLB must test for KVM guest. + * * A dedicated save area EXSLB is used (XXX: but it actually need not be * these days, we could use EXGEN). */ @@ -1472,10 +1475,8 @@ INT_DEFINE_BEGIN(data_access_slb) IAREA=PACA_EXSLB IRECONCILE=0 IDAR=1 -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_SKIP=1 IKVM_REAL=1 -#endif INT_DEFINE_END(data_access_slb) EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 2aa16d5368e1..a0dda2a1f2df 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -156,6 +156,7 @@ __after_mmu_off: bl initial_bats bl load_segment_registers BEGIN_MMU_FTR_SECTION + bl reloc_offset bl early_hash_table END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) #if defined(CONFIG_BOOTX_TEXT) @@ -920,7 +921,7 @@ early_hash_table: ori r6, r6, 3 /* 256kB table */ mtspr SPRN_SDR1, r6 lis r6, early_hash@h - lis r3, Hash@ha + addis r3, r3, Hash@ha stw r6, Hash@l(r3) blr diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index ae0e2632393d..1f835539fda4 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -52,9 +52,9 @@ void arch_cpu_idle(void) * interrupts enabled, some don't. */ if (irqs_disabled()) - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); /* * Go into low thread priority and possibly * low power mode. diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 85215e79db42..a0ebc29f30b2 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1214,12 +1214,9 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) static bool kvmppc_xive_vcpu_id_valid(struct kvmppc_xive *xive, u32 cpu) { /* We have a block of xive->nr_servers VPs. We just need to check - * raw vCPU ids are below the expected limit for this guest's - * core stride ; kvmppc_pack_vcpu_id() will pack them down to an - * index that can be safely used to compute a VP id that belongs - * to the VP block. + * packed vCPU ids are below that. */ - return cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode; + return kvmppc_pack_vcpu_id(xive->kvm, cpu) < xive->nr_servers; } int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp) diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index d0c2db0e07fa..a59a94f02733 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -251,6 +251,13 @@ static vm_fault_t xive_native_esb_fault(struct vm_fault *vmf) } state = &sb->irq_state[src]; + + /* Some sanity checking */ + if (!state->valid) { + pr_devel("%s: source %lx invalid !\n", __func__, irq); + return VM_FAULT_SIGBUS; + } + kvmppc_xive_select_irq(state, &hw_num, &xd); arch_spin_lock(&sb->lock); diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index 0203cdf48c54..52e170bd95ae 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -68,7 +68,7 @@ static __always_inline void tlbiel_hash_set_isa300(unsigned int set, unsigned in rs = ((unsigned long)pid << PPC_BITLSHIFT(31)); asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) - : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r) + : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "i"(r) : "memory"); } @@ -92,16 +92,15 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) asm volatile("ptesync": : :"memory"); /* - * Flush the first set of the TLB, and any caching of partition table - * entries. Then flush the remaining sets of the TLB. Hash mode uses - * partition scoped TLB translations. + * Flush the partition table cache if this is HV mode. */ - tlbiel_hash_set_isa300(0, is, 0, 2, 0); - for (set = 1; set < num_sets; set++) - tlbiel_hash_set_isa300(set, is, 0, 0, 0); + if (early_cpu_has_feature(CPU_FTR_HVMODE)) + tlbiel_hash_set_isa300(0, is, 0, 2, 0); /* - * Now invalidate the process table cache. + * Now invalidate the process table cache. UPRT=0 HPT modes (what + * current hardware implements) do not use the process table, but + * add the flushes anyway. * * From ISA v3.0B p. 1078: * The following forms are invalid. @@ -110,6 +109,14 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) */ tlbiel_hash_set_isa300(0, is, 0, 2, 1); + /* + * Then flush the sets of the TLB proper. Hash mode uses + * partition scoped TLB translations, which may be flushed + * in !HV mode. + */ + for (set = 0; set < num_sets; set++) + tlbiel_hash_set_isa300(set, is, 0, 0, 0); + ppc_after_tlbiel_barrier(); asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory"); diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index 1c54821de7bf..0c8557220ae2 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -17,6 +17,7 @@ #include <linux/export.h> #include <linux/gfp.h> #include <linux/slab.h> +#include <linux/cpu.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> @@ -307,3 +308,22 @@ void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next) isync(); } #endif + +/** + * cleanup_cpu_mmu_context - Clean up MMU details for this CPU (newly offlined) + * + * This clears the CPU from mm_cpumask for all processes, and then flushes the + * local TLB to ensure TLB coherency in case the CPU is onlined again. + * + * KVM guest translations are not necessarily flushed here. If KVM started + * using mm_cpumask or the Linux APIs which do, this would have to be resolved. + */ +#ifdef CONFIG_HOTPLUG_CPU +void cleanup_cpu_mmu_context(void) +{ + int cpu = smp_processor_id(); + + clear_tasks_mm_cpumask(cpu); + tlbiel_all(); +} +#endif diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 63f61d8b55e5..f2bf98bdcea2 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -742,8 +742,7 @@ static int __init parse_numa_properties(void) of_node_put(cpu); } - if (likely(nid > 0)) - node_set_online(nid); + node_set_online(nid); } get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells); diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 74ebe664b016..adae2a6712e1 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -911,6 +911,8 @@ static int smp_core99_cpu_disable(void) mpic_cpu_set_priority(0xf); + cleanup_cpu_mmu_context(); + return 0; } diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 46115231a3b2..4426a109ec2f 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -211,11 +211,16 @@ static void __init pnv_init(void) add_preferred_console("hvc", 0, NULL); if (!radix_enabled()) { + size_t size = sizeof(struct slb_entry) * mmu_slb_size; int i; /* Allocate per cpu area to save old slb contents during MCE */ - for_each_possible_cpu(i) - paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i)); + for_each_possible_cpu(i) { + paca_ptrs[i]->mce_faulty_slbs = + memblock_alloc_node(size, + __alignof__(struct slb_entry), + cpu_to_node(i)); + } } } diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 54c4ba45c7ce..cbb67813cd5d 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -143,6 +143,9 @@ static int pnv_smp_cpu_disable(void) xive_smp_disable_cpu(); else xics_migrate_irqs_away(); + + cleanup_cpu_mmu_context(); + return 0; } diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index f2837e33bf5d..a02012f1b04a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -90,6 +90,9 @@ static int pseries_cpu_disable(void) xive_smp_disable_cpu(); else xics_migrate_irqs_away(); + + cleanup_cpu_mmu_context(); + return 0; } diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h index b0ab66e5fdb1..5b2e79e5bfa5 100644 --- a/arch/riscv/include/asm/pgtable-32.h +++ b/arch/riscv/include/asm/pgtable-32.h @@ -14,4 +14,6 @@ #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 34 + #endif /* _ASM_RISCV_PGTABLE_32_H */ diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index 82a5693b1861..134388cbaaa1 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -4,6 +4,8 @@ #ifndef __ASSEMBLY__ +#include <asm/barrier.h> + static inline void cpu_relax(void) { #ifdef __riscv_muldiv diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 19225ec65db6..dd5f985b1f40 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -36,7 +36,7 @@ extern asmlinkage void ret_from_kernel_thread(void); void arch_cpu_idle(void) { wait_for_interrupt(); - local_irq_enable(); + raw_local_irq_enable(); } void show_regs(struct pt_regs *regs) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index c424cc6dd833..117f3212a8e4 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -75,6 +75,7 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; early_ioremap_setup(); + jump_label_init(); parse_early_param(); efi_init(); diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index cb8f9e4cfcbf..0cfd6da784f8 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -44,7 +44,7 @@ SYSCFLAGS_vdso.so.dbg = $(c_flags) $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ - -Wl,--build-id -Wl,--hash-style=both + -Wl,--build-id=sha1 -Wl,--hash-style=both # We also create a special relocatable object that should mirror the symbol # table and layout of the linked DSO. With ld --just-symbols we can then diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 2012c1cf0853..483051e10db3 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -53,11 +53,11 @@ int main(void) /* stack_frame offsets */ OFFSET(__SF_BACKCHAIN, stack_frame, back_chain); OFFSET(__SF_GPRS, stack_frame, gprs); - OFFSET(__SF_EMPTY, stack_frame, empty1); - OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]); - OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]); - OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]); - OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[3]); + OFFSET(__SF_EMPTY, stack_frame, empty1[0]); + OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[1]); + OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[2]); + OFFSET(__SF_SIE_REASON, stack_frame, empty1[3]); + OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[4]); BLANK(); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); BLANK(); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 5346545b9860..92beb1444644 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -763,12 +763,7 @@ ENTRY(io_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tmhh %r8,0x300 - jz 1f TRACE_IRQS_OFF -1: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) .Lio_loop: lgr %r2,%r11 # pass pointer to pt_regs @@ -791,12 +786,7 @@ ENTRY(io_int_handler) TSTMSK __LC_CPU_FLAGS,_CIF_WORK jnz .Lio_work .Lio_restore: -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tm __PT_PSW(%r11),3 - jno 0f TRACE_IRQS_ON -0: -#endif mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) tm __PT_PSW+1(%r11),0x01 # returning to user ? jno .Lio_exit_kernel @@ -976,12 +966,7 @@ ENTRY(ext_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tmhh %r8,0x300 - jz 1f TRACE_IRQS_OFF -1: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs lghi %r3,EXT_INTERRUPT @@ -1068,6 +1053,7 @@ EXPORT_SYMBOL(save_fpu_regs) * %r4 */ load_fpu_regs: + stnsm __SF_EMPTY(%r15),0xfc lg %r4,__LC_CURRENT aghi %r4,__TASK_thread TSTMSK __LC_CPU_FLAGS,_CIF_FPU @@ -1099,6 +1085,7 @@ load_fpu_regs: .Lload_fpu_regs_done: ni __LC_CPU_FLAGS+7,255-_CIF_FPU .Lload_fpu_regs_exit: + ssm __SF_EMPTY(%r15) BR_EX %r14 .Lload_fpu_regs_end: ENDPROC(load_fpu_regs) diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index f7f1e64e0d98..2b85096964f8 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -33,10 +33,10 @@ void enabled_wait(void) PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; clear_cpu_flag(CIF_NOHZ_DELAY); - local_irq_save(flags); + raw_local_irq_save(flags); /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); - local_irq_restore(flags); + raw_local_irq_restore(flags); /* Account time spent with enabled wait psw loaded as idle time. */ raw_write_seqcount_begin(&idle->seqcount); @@ -123,7 +123,7 @@ void arch_cpu_idle_enter(void) void arch_cpu_idle(void) { enabled_wait(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_exit(void) diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 14bd9d58edc9..883bfed9f5c2 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -129,8 +129,15 @@ int uv_destroy_page(unsigned long paddr) .paddr = paddr }; - if (uv_call(0, (u64)&uvcb)) + if (uv_call(0, (u64)&uvcb)) { + /* + * Older firmware uses 107/d as an indication of a non secure + * page. Let us emulate the newer variant (no-op). + */ + if (uvcb.header.rc == 0x107 && uvcb.header.rrc == 0xd) + return 0; return -EINVAL; + } return 0; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 6b74b92c1a58..425d3d75320b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2312,7 +2312,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) struct kvm_s390_pv_unp unp = {}; r = -EINVAL; - if (!kvm_s390_pv_is_protected(kvm)) + if (!kvm_s390_pv_is_protected(kvm) || !mm_is_protected(kvm->mm)) break; r = -EFAULT; @@ -3564,7 +3564,6 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->pp = 0; vcpu->arch.sie_block->fpf &= ~FPF_BPBC; vcpu->arch.sie_block->todpr = 0; - vcpu->arch.sie_block->cpnc = 0; } } @@ -3582,7 +3581,6 @@ static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu) regs->etoken = 0; regs->etoken_extension = 0; - regs->diag318 = 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index eb99e2f95ebe..f5847f9dec7c 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -208,7 +208,6 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; - atomic_set(&kvm->mm->context.is_protected, 1); return 0; } @@ -228,6 +227,8 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, *rrc = uvcb.header.rrc; KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x", *rc, *rrc); + if (!cc) + atomic_set(&kvm->mm->context.is_protected, 1); return cc ? -EINVAL : 0; } diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index daca7bad66de..8c0c68e7770e 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(__delay); static void __udelay_disabled(unsigned long long usecs) { - unsigned long cr0, cr0_new, psw_mask, flags; + unsigned long cr0, cr0_new, psw_mask; struct s390_idle_data idle; u64 end; @@ -45,9 +45,8 @@ static void __udelay_disabled(unsigned long long usecs) psw_mask = __extract_psw() | PSW_MASK_EXT | PSW_MASK_WAIT; set_clock_comparator(end); set_cpu_flag(CIF_IGNORE_IRQ); - local_irq_save(flags); psw_idle(&idle, psw_mask); - local_irq_restore(flags); + trace_hardirqs_off(); clear_cpu_flag(CIF_IGNORE_IRQ); set_clock_comparator(S390_lowcore.clock_comparator); __ctl_load(cr0, 0, 0); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index cfb0017f33a7..64795d034926 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2690,6 +2690,8 @@ static const struct mm_walk_ops reset_acc_walk_ops = { #include <linux/sched/mm.h> void s390_reset_acc(struct mm_struct *mm) { + if (!mm_is_protected(mm)) + return; /* * we might be called during * reset: we walk the pages and clear diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 743f257cf2cb..75217fb63d7b 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -103,9 +103,10 @@ static int zpci_set_irq_affinity(struct irq_data *data, const struct cpumask *de { struct msi_desc *entry = irq_get_msi_desc(data->irq); struct msi_msg msg = entry->msg; + int cpu_addr = smp_cpu_get_cpu_address(cpumask_first(dest)); msg.address_lo &= 0xff0000ff; - msg.address_lo |= (cpumask_first(dest) << 8); + msg.address_lo |= (cpu_addr << 8); pci_write_msi_msg(data->irq, &msg); return IRQ_SET_MASK_OK; @@ -238,6 +239,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) unsigned long bit; struct msi_desc *msi; struct msi_msg msg; + int cpu_addr; int rc, irq; zdev->aisb = -1UL; @@ -287,9 +289,15 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) handle_percpu_irq); msg.data = hwirq - bit; if (irq_delivery == DIRECTED) { + if (msi->affinity) + cpu = cpumask_first(&msi->affinity->mask); + else + cpu = 0; + cpu_addr = smp_cpu_get_cpu_address(cpu); + msg.address_lo = zdev->msi_addr & 0xff0000ff; - msg.address_lo |= msi->affinity ? - (cpumask_first(&msi->affinity->mask) << 8) : 0; + msg.address_lo |= (cpu_addr << 8); + for_each_possible_cpu(cpu) { airq_iv_set_data(zpci_ibv[cpu], hwirq, irq); } diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 0dc0f52f9bb8..f59814983bd5 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -22,7 +22,7 @@ static void (*sh_idle)(void); void default_idle(void) { set_bl_bit(); - local_irq_enable(); + raw_local_irq_enable(); /* Isn't this racy ? */ cpu_sleep(); clear_bl_bit(); diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c index 065e2d4b7290..396f46bca52e 100644 --- a/arch/sparc/kernel/leon_pmc.c +++ b/arch/sparc/kernel/leon_pmc.c @@ -50,7 +50,7 @@ static void pmc_leon_idle_fixup(void) register unsigned int address = (unsigned int)leon3_irqctrl_regs; /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); __asm__ __volatile__ ( "wr %%g0, %%asr19\n" @@ -66,7 +66,7 @@ static void pmc_leon_idle_fixup(void) static void pmc_leon_idle(void) { /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); /* For systems without power-down, this will be no-op */ __asm__ __volatile__ ("wr %g0, %asr19\n\t"); diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index adfcaeab3ddc..a02363735915 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -74,7 +74,7 @@ void arch_cpu_idle(void) { if (sparc_idle) (*sparc_idle)(); - local_irq_enable(); + raw_local_irq_enable(); } /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */ diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index a75093b993f9..6f8c7822fc06 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -62,11 +62,11 @@ void arch_cpu_idle(void) { if (tlb_type != hypervisor) { touch_nmi_watchdog(); - local_irq_enable(); + raw_local_irq_enable(); } else { unsigned long pstate; - local_irq_enable(); + raw_local_irq_enable(); /* The sun4v sleeping code requires that we have PSTATE.IE cleared over * the cpu sleep hypervisor call. diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 3bed09538dd9..9505a7e87396 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -217,7 +217,7 @@ void arch_cpu_idle(void) { cpu_tasks[current_thread_info()->cpu].pid = os_getpid(); um_idle_sleep(); - local_irq_enable(); + raw_local_irq_enable(); } int __cant_sleep(void) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 324ddd7fd0aa..7e5f33a0d0e2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1656,6 +1656,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index e039a933aca3..29dd27b5a339 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -88,8 +88,6 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx, static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { - trace_hardirqs_on(); - mds_idle_clear_cpu_buffers(); /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 581fb7223ad0..d41b70fe4918 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -739,11 +739,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + spectre_v2_user_ibpb = mode; switch (cmd) { case SPECTRE_V2_USER_CMD_FORCE: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: static_branch_enable(&switch_mm_always_ibpb); + spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT; break; case SPECTRE_V2_USER_CMD_PRCTL: case SPECTRE_V2_USER_CMD_AUTO: @@ -757,8 +759,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", static_key_enabled(&switch_mm_always_ibpb) ? "always-on" : "conditional"); - - spectre_v2_user_ibpb = mode; } /* diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 4102b866e7c0..32b7099e3511 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1384,8 +1384,10 @@ noinstr void do_machine_check(struct pt_regs *regs) * When there's any problem use only local no_way_out state. */ if (!lmce) { - if (mce_end(order) < 0) - no_way_out = worst >= MCE_PANIC_SEVERITY; + if (mce_end(order) < 0) { + if (!no_way_out) + no_way_out = worst >= MCE_PANIC_SEVERITY; + } } else { /* * If there was a fatal machine check we should have diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index af323e2e3100..6f4ca4bea625 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -507,6 +507,24 @@ unlock: return ret ?: nbytes; } +/** + * rdtgroup_remove - the helper to remove resource group safely + * @rdtgrp: resource group to remove + * + * On resource group creation via a mkdir, an extra kernfs_node reference is + * taken to ensure that the rdtgroup structure remains accessible for the + * rdtgroup_kn_unlock() calls where it is removed. + * + * Drop the extra reference here, then free the rdtgroup structure. + * + * Return: void + */ +static void rdtgroup_remove(struct rdtgroup *rdtgrp) +{ + kernfs_put(rdtgrp->kn); + kfree(rdtgrp); +} + struct task_move_callback { struct callback_head work; struct rdtgroup *rdtgrp; @@ -529,7 +547,7 @@ static void move_myself(struct callback_head *head) (rdtgrp->flags & RDT_DELETED)) { current->closid = 0; current->rmid = 0; - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } if (unlikely(current->flags & PF_EXITING)) @@ -1769,7 +1787,6 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, if (IS_ERR(kn_subdir)) return PTR_ERR(kn_subdir); - kernfs_get(kn_subdir); ret = rdtgroup_kn_set_ugid(kn_subdir); if (ret) return ret; @@ -1792,7 +1809,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); if (IS_ERR(kn_info)) return PTR_ERR(kn_info); - kernfs_get(kn_info); ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); if (ret) @@ -1813,12 +1829,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) goto out_destroy; } - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn_info); - ret = rdtgroup_kn_set_ugid(kn_info); if (ret) goto out_destroy; @@ -1847,12 +1857,6 @@ mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, if (dest_kn) *dest_kn = kn; - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn); - ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -2079,8 +2083,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); - kernfs_put(rdtgrp->kn); - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } else { kernfs_unbreak_active_protection(kn); } @@ -2139,13 +2142,11 @@ static int rdt_get_tree(struct fs_context *fc) &kn_mongrp); if (ret < 0) goto out_info; - kernfs_get(kn_mongrp); ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); if (ret < 0) goto out_mongrp; - kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; } @@ -2357,7 +2358,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) if (atomic_read(&sentry->waitcount) != 0) sentry->flags = RDT_DELETED; else - kfree(sentry); + rdtgroup_remove(sentry); } } @@ -2399,7 +2400,7 @@ static void rmdir_all_sub(void) if (atomic_read(&rdtgrp->waitcount) != 0) rdtgrp->flags = RDT_DELETED; else - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); @@ -2499,11 +2500,6 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, if (IS_ERR(kn)) return PTR_ERR(kn); - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that kn is always accessible. - */ - kernfs_get(kn); ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -2838,8 +2834,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, /* * kernfs_remove() will drop the reference count on "kn" which * will free it. But we still need it to stick around for the - * rdtgroup_kn_unlock(kn} call below. Take one extra reference - * here, which will be dropped inside rdtgroup_kn_unlock(). + * rdtgroup_kn_unlock(kn) call. Take one extra reference here, + * which will be dropped by kernfs_put() in rdtgroup_remove(). */ kernfs_get(kn); @@ -2880,6 +2876,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, out_idfree: free_rmid(rdtgrp->mon.rmid); out_destroy: + kernfs_put(rdtgrp->kn); kernfs_remove(rdtgrp->kn); out_free_rgrp: kfree(rdtgrp); @@ -2892,7 +2889,7 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) { kernfs_remove(rgrp->kn); free_rmid(rgrp->mon.rmid); - kfree(rgrp); + rdtgroup_remove(rgrp); } /* @@ -3049,11 +3046,6 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); list_del(&rdtgrp->mon.crdtgrp_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; @@ -3065,11 +3057,6 @@ static int rdtgroup_ctrl_remove(struct kernfs_node *kn, rdtgrp->flags = RDT_DELETED; list_del(&rdtgrp->rdtgroup_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ba4593a913fa..145a7ac0c19a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -685,7 +685,7 @@ void arch_cpu_idle(void) */ void __cpuidle default_idle(void) { - safe_halt(); + raw_safe_halt(); } #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); @@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy) /* * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power * states (local apic timer and TSC stop). + * + * XXX this function is completely buggered vs RCU and tracing. */ static void amd_e400_idle(void) { @@ -757,9 +759,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be called with * interrupts disabled. */ - local_irq_disable(); + raw_local_irq_disable(); tick_broadcast_exit(); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void) if (!need_resched()) __sti_mwait(0, 0); else - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); } __current_clr_polling(); } diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 420be871d9d4..ae64f98ec2ab 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -514,13 +514,10 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (no_iommu || swiotlb || dmar_disabled) + if (no_iommu || dmar_disabled) pr_warn("Forcing Intel-IOMMU to enabled\n"); dmar_disabled = 0; -#ifdef CONFIG_SWIOTLB - swiotlb = 0; -#endif no_iommu = 0; return 1; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 99d118ffc67d..814698e5b152 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -40,29 +40,10 @@ static int pending_userspace_extint(struct kvm_vcpu *v) * check if there is pending interrupt from * non-APIC source without intack. */ -static int kvm_cpu_has_extint(struct kvm_vcpu *v) -{ - u8 accept = kvm_apic_accept_pic_intr(v); - - if (accept) { - if (irqchip_split(v->kvm)) - return pending_userspace_extint(v); - else - return v->kvm->arch.vpic->output; - } else - return 0; -} - -/* - * check if there is injectable interrupt: - * when virtual interrupt delivery enabled, - * interrupt from apic will handled by hardware, - * we don't need to check it here. - */ -int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +int kvm_cpu_has_extint(struct kvm_vcpu *v) { /* - * FIXME: interrupt.injected represents an interrupt that it's + * FIXME: interrupt.injected represents an interrupt whose * side-effects have already been applied (e.g. bit from IRR * already moved to ISR). Therefore, it is incorrect to rely * on interrupt.injected to know if there is a pending @@ -75,6 +56,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.injected; + if (!kvm_apic_accept_pic_intr(v)) + return 0; + + if (irqchip_split(v->kvm)) + return pending_userspace_extint(v); + else + return v->kvm->arch.vpic->output; +} + +/* + * check if there is injectable interrupt: + * when virtual interrupt delivery enabled, + * interrupt from apic will handled by hardware, + * we don't need to check it here. + */ +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +{ if (kvm_cpu_has_extint(v)) return 1; @@ -91,20 +89,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr); */ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) { - /* - * FIXME: interrupt.injected represents an interrupt that it's - * side-effects have already been applied (e.g. bit from IRR - * already moved to ISR). Therefore, it is incorrect to rely - * on interrupt.injected to know if there is a pending - * interrupt in the user-mode LAPIC. - * This leads to nVMX/nSVM not be able to distinguish - * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on - * pending interrupt or should re-inject an injected - * interrupt. - */ - if (!lapic_in_kernel(v)) - return v->arch.interrupt.injected; - if (kvm_cpu_has_extint(v)) return 1; @@ -118,16 +102,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); */ static int kvm_cpu_get_extint(struct kvm_vcpu *v) { - if (kvm_cpu_has_extint(v)) { - if (irqchip_split(v->kvm)) { - int vector = v->arch.pending_external_vector; - - v->arch.pending_external_vector = -1; - return vector; - } else - return kvm_pic_read_irq(v->kvm); /* PIC */ - } else + if (!kvm_cpu_has_extint(v)) { + WARN_ON(!lapic_in_kernel(v)); return -1; + } + + if (!lapic_in_kernel(v)) + return v->arch.interrupt.nr; + + if (irqchip_split(v->kvm)) { + int vector = v->arch.pending_external_vector; + + v->arch.pending_external_vector = -1; + return vector; + } else + return kvm_pic_read_irq(v->kvm); /* PIC */ } /* @@ -135,13 +124,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) */ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) { - int vector; - - if (!lapic_in_kernel(v)) - return v->arch.interrupt.nr; - - vector = kvm_cpu_get_extint(v); - + int vector = kvm_cpu_get_extint(v); if (vector != -1) return vector; /* PIC */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 105e7859d1f2..86c33d53c90a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2465,7 +2465,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (!kvm_apic_hw_enabled(apic)) + if (!kvm_apic_present(vcpu)) return -1; __apic_update_ppr(apic, &ppr); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 5bb1939b65d8..7a6ae9e90bd7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3517,7 +3517,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { u64 sptes[PT64_ROOT_MAX_LEVEL]; struct rsvd_bits_validate *rsvd_check; - int root = vcpu->arch.mmu->root_level; + int root = vcpu->arch.mmu->shadow_root_level; int leaf; int level; bool reserved = false; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c0b14106258a..566f4d18185b 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -642,8 +642,8 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, * Its safe to read more than we are asked, caller should ensure that * destination has enough space. */ - src_paddr = round_down(src_paddr, 16); offset = src_paddr & 15; + src_paddr = round_down(src_paddr, 16); sz = round_up(sz + offset, 16); return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 1e81cfebd491..79b3a564f1c9 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1309,8 +1309,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm->avic_is_running = true; svm->msrpm = svm_vcpu_alloc_msrpm(); - if (!svm->msrpm) + if (!svm->msrpm) { + err = -ENOMEM; goto error_free_vmcb_page; + } svm_vcpu_init_msrpm(vcpu, svm->msrpm); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 078a39d489fe..e545a8a613b1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4051,21 +4051,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) { + /* + * We can accept userspace's request for interrupt injection + * as long as we have a place to store the interrupt number. + * The actual injection will happen when the CPU is able to + * deliver the interrupt. + */ + if (kvm_cpu_has_extint(vcpu)) + return false; + + /* Acknowledging ExtINT does not happen if LINT0 is masked. */ return (!lapic_in_kernel(vcpu) || kvm_apic_accept_pic_intr(vcpu)); } -/* - * if userspace requested an interrupt window, check that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { return kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); } |