diff options
Diffstat (limited to 'arch')
143 files changed, 941 insertions, 469 deletions
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 9acbeba832c0..dcaa44e408ac 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -88,6 +88,8 @@ arcpct: pct { compatible = "snps,archs-pct"; + interrupt-parent = <&cpu_intc>; + interrupts = <20>; }; /* TIMER0 with interrupt for clockevent */ @@ -208,7 +210,7 @@ reg = <0x8000 0x2000>; interrupts = <10>; interrupt-names = "macirq"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; snps,pbl = <32>; snps,multicast-filter-bins = <256>; clocks = <&gmacclk>; @@ -226,7 +228,7 @@ #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; - phy0: ethernet-phy@0 { + phy0: ethernet-phy@0 { /* Micrel KSZ9031 */ reg = <0>; }; }; diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index b747f2ec2928..6147db925248 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -18,10 +18,10 @@ * vineetg: April 2010 * -Switched pgtable_t from being struct page * to unsigned long * =Needed so that Page Table allocator (pte_alloc_one) is not forced to - * to deal with struct page. Thay way in future we can make it allocate + * deal with struct page. That way in future we can make it allocate * multiple PG Tbls in one Page Frame * =sweet side effect is avoiding calls to ugly page_address( ) from the - * pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate + * pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate) * * Amit Bhor, Sameer Dhavale: Codito Technologies 2004 */ diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 661fd842ea97..79849f37e782 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -562,7 +562,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev) { struct arc_reg_pct_build pct_bcr; struct arc_reg_cc_build cc_bcr; - int i, has_interrupts; + int i, has_interrupts, irq; int counter_size; /* in bits */ union cc_name { @@ -637,13 +637,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev) .attr_groups = arc_pmu->attr_groups, }; - if (has_interrupts) { - int irq = platform_get_irq(pdev, 0); - - if (irq < 0) { - pr_err("Cannot get IRQ number for the platform\n"); - return -ENODEV; - } + if (has_interrupts && (irq = platform_get_irq(pdev, 0) >= 0)) { arc_pmu->irq = irq; @@ -652,9 +646,9 @@ static int arc_pmu_device_probe(struct platform_device *pdev) this_cpu_ptr(&arc_pmu_cpu)); on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1); - - } else + } else { arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + } /* * perf parser doesn't really like '-' symbol in events name, so let's diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 28e8bf04b253..a331bb5d8319 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -18,44 +18,37 @@ #define ARC_PATH_MAX 256 -/* - * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25) - * -Prints 3 regs per line and a CR. - * -To continue, callee regs right after scratch, special handling of CR - */ -static noinline void print_reg_file(long *reg_rev, int start_num) +static noinline void print_regs_scratch(struct pt_regs *regs) { - unsigned int i; - char buf[512]; - int n = 0, len = sizeof(buf); - - for (i = start_num; i < start_num + 13; i++) { - n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t", - i, (unsigned long)*reg_rev); - - if (((i + 1) % 3) == 0) - n += scnprintf(buf + n, len - n, "\n"); - - /* because pt_regs has regs reversed: r12..r0, r25..r13 */ - if (is_isa_arcv2() && start_num == 0) - reg_rev++; - else - reg_rev--; - } - - if (start_num != 0) - n += scnprintf(buf + n, len - n, "\n\n"); + pr_cont("BTA: 0x%08lx\n SP: 0x%08lx FP: 0x%08lx BLK: %pS\n", + regs->bta, regs->sp, regs->fp, (void *)regs->blink); + pr_cont("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", + regs->lp_start, regs->lp_end, regs->lp_count); - /* To continue printing callee regs on same line as scratch regs */ - if (start_num == 0) - pr_info("%s", buf); - else - pr_cont("%s\n", buf); + pr_info("r00: 0x%08lx\tr01: 0x%08lx\tr02: 0x%08lx\n" \ + "r03: 0x%08lx\tr04: 0x%08lx\tr05: 0x%08lx\n" \ + "r06: 0x%08lx\tr07: 0x%08lx\tr08: 0x%08lx\n" \ + "r09: 0x%08lx\tr10: 0x%08lx\tr11: 0x%08lx\n" \ + "r12: 0x%08lx\t", + regs->r0, regs->r1, regs->r2, + regs->r3, regs->r4, regs->r5, + regs->r6, regs->r7, regs->r8, + regs->r9, regs->r10, regs->r11, + regs->r12); } -static void show_callee_regs(struct callee_regs *cregs) +static void print_regs_callee(struct callee_regs *regs) { - print_reg_file(&(cregs->r13), 13); + pr_cont("r13: 0x%08lx\tr14: 0x%08lx\n" \ + "r15: 0x%08lx\tr16: 0x%08lx\tr17: 0x%08lx\n" \ + "r18: 0x%08lx\tr19: 0x%08lx\tr20: 0x%08lx\n" \ + "r21: 0x%08lx\tr22: 0x%08lx\tr23: 0x%08lx\n" \ + "r24: 0x%08lx\tr25: 0x%08lx\n", + regs->r13, regs->r14, + regs->r15, regs->r16, regs->r17, + regs->r18, regs->r19, regs->r20, + regs->r21, regs->r22, regs->r23, + regs->r24, regs->r25); } static void print_task_path_n_nm(struct task_struct *tsk) @@ -175,7 +168,7 @@ static void show_ecr_verbose(struct pt_regs *regs) void show_regs(struct pt_regs *regs) { struct task_struct *tsk = current; - struct callee_regs *cregs; + struct callee_regs *cregs = (struct callee_regs *)tsk->thread.callee_reg; /* * generic code calls us with preemption disabled, but some calls @@ -204,25 +197,15 @@ void show_regs(struct pt_regs *regs) STS_BIT(regs, A2), STS_BIT(regs, A1), STS_BIT(regs, E2), STS_BIT(regs, E1)); #else - pr_cont(" [%2s%2s%2s%2s]", + pr_cont(" [%2s%2s%2s%2s] ", STS_BIT(regs, IE), (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE)); #endif - pr_cont(" BTA: 0x%08lx\n SP: 0x%08lx FP: 0x%08lx BLK: %pS\n", - regs->bta, regs->sp, regs->fp, (void *)regs->blink); - pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", - regs->lp_start, regs->lp_end, regs->lp_count); - - /* print regs->r0 thru regs->r12 - * Sequential printing was generating horrible code - */ - print_reg_file(&(regs->r0), 0); - /* If Callee regs were saved, display them too */ - cregs = (struct callee_regs *)current->thread.callee_reg; + print_regs_scratch(regs); if (cregs) - show_callee_regs(cregs); + print_regs_callee(cregs); preempt_disable(); } diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index f886ac69d8ad..3a35b82a718e 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -26,8 +26,8 @@ static unsigned long low_mem_sz; #ifdef CONFIG_HIGHMEM static unsigned long min_high_pfn, max_high_pfn; -static u64 high_mem_start; -static u64 high_mem_sz; +static phys_addr_t high_mem_start; +static phys_addr_t high_mem_sz; #endif #ifdef CONFIG_DISCONTIGMEM @@ -69,6 +69,7 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) high_mem_sz = size; in_use = 1; memblock_add_node(base, size, 1); + memblock_reserve(base, size); #endif } @@ -157,7 +158,7 @@ void __init setup_arch_memory(void) min_high_pfn = PFN_DOWN(high_mem_start); max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz); - max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn; + max_zone_pfn[ZONE_HIGHMEM] = min_low_pfn; high_memory = (void *)(min_high_pfn << PAGE_SHIFT); kmap_init(); @@ -166,22 +167,26 @@ void __init setup_arch_memory(void) free_area_init(max_zone_pfn); } -/* - * mem_init - initializes memory - * - * Frees up bootmem - * Calculates and displays memory available/used - */ -void __init mem_init(void) +static void __init highmem_init(void) { #ifdef CONFIG_HIGHMEM unsigned long tmp; - reset_all_zones_managed_pages(); + memblock_free(high_mem_start, high_mem_sz); for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++) free_highmem_page(pfn_to_page(tmp)); #endif +} +/* + * mem_init - initializes memory + * + * Frees up bootmem + * Calculates and displays memory available/used + */ +void __init mem_init(void) +{ memblock_free_all(); + highmem_init(); mem_init_print_info(NULL); } diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h index a4a61531c7fb..77712c5ffe84 100644 --- a/arch/arc/plat-eznps/include/plat/ctop.h +++ b/arch/arc/plat-eznps/include/plat/ctop.h @@ -33,7 +33,6 @@ #define CTOP_AUX_DPC (CTOP_AUX_BASE + 0x02C) #define CTOP_AUX_LPC (CTOP_AUX_BASE + 0x030) #define CTOP_AUX_EFLAGS (CTOP_AUX_BASE + 0x080) -#define CTOP_AUX_IACK (CTOP_AUX_BASE + 0x088) #define CTOP_AUX_GPA1 (CTOP_AUX_BASE + 0x08C) #define CTOP_AUX_UDMC (CTOP_AUX_BASE + 0x300) diff --git a/arch/arm/boot/dts/at91-sama5d2_icp.dts b/arch/arm/boot/dts/at91-sama5d2_icp.dts index 8d19925fc09e..6783cf16ff81 100644 --- a/arch/arm/boot/dts/at91-sama5d2_icp.dts +++ b/arch/arm/boot/dts/at91-sama5d2_icp.dts @@ -116,7 +116,6 @@ switch0: ksz8563@0 { compatible = "microchip,ksz8563"; reg = <0>; - phy-mode = "mii"; reset-gpios = <&pioA PIN_PD4 GPIO_ACTIVE_LOW>; spi-max-frequency = <500000>; @@ -140,6 +139,7 @@ reg = <2>; label = "cpu"; ethernet = <&macb0>; + phy-mode = "mii"; fixed-link { speed = <100>; full-duplex; diff --git a/arch/arm/boot/dts/bcm-hr2.dtsi b/arch/arm/boot/dts/bcm-hr2.dtsi index cbebed5f050e..e8df458aad39 100644 --- a/arch/arm/boot/dts/bcm-hr2.dtsi +++ b/arch/arm/boot/dts/bcm-hr2.dtsi @@ -217,7 +217,7 @@ }; qspi: spi@27200 { - compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"; + compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi"; reg = <0x027200 0x184>, <0x027000 0x124>, <0x11c408 0x004>, diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi index 0346ea621f0f..c846fa3c244d 100644 --- a/arch/arm/boot/dts/bcm-nsp.dtsi +++ b/arch/arm/boot/dts/bcm-nsp.dtsi @@ -284,7 +284,7 @@ }; qspi: spi@27200 { - compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"; + compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi"; reg = <0x027200 0x184>, <0x027000 0x124>, <0x11c408 0x004>, diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi index f7ae5a4530b8..d94357b21f7e 100644 --- a/arch/arm/boot/dts/bcm2835-rpi.dtsi +++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi @@ -13,7 +13,7 @@ soc { firmware: firmware { - compatible = "raspberrypi,bcm2835-firmware", "simple-bus"; + compatible = "raspberrypi,bcm2835-firmware", "simple-mfd"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index 2d9b4dd05830..0016720ce530 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -488,7 +488,7 @@ }; spi@18029200 { - compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"; + compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi"; reg = <0x18029200 0x184>, <0x18029000 0x124>, <0x1811b408 0x004>, diff --git a/arch/arm/boot/dts/imx6q-logicpd.dts b/arch/arm/boot/dts/imx6q-logicpd.dts index 7a3d1d3e54a9..8f94364ba484 100644 --- a/arch/arm/boot/dts/imx6q-logicpd.dts +++ b/arch/arm/boot/dts/imx6q-logicpd.dts @@ -13,7 +13,7 @@ backlight: backlight-lvds { compatible = "pwm-backlight"; - pwms = <&pwm3 0 20000>; + pwms = <&pwm3 0 20000 0>; brightness-levels = <0 4 8 16 32 64 128 255>; default-brightness-level = <6>; power-supply = <®_lcd>; diff --git a/arch/arm/boot/dts/imx6q-prtwd2.dts b/arch/arm/boot/dts/imx6q-prtwd2.dts index dffafbcaa7af..349959d38020 100644 --- a/arch/arm/boot/dts/imx6q-prtwd2.dts +++ b/arch/arm/boot/dts/imx6q-prtwd2.dts @@ -30,7 +30,7 @@ }; /* PRTWD2 rev 1 bitbang I2C for Ethernet Switch */ - i2c@4 { + i2c { compatible = "i2c-gpio"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c4>; diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi index 7705285d9e3c..4d01c3300b97 100644 --- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi @@ -22,8 +22,6 @@ gpio-keys { compatible = "gpio-keys"; - #address-cells = <1>; - #size-cells = <0>; user-pb { label = "user_pb"; diff --git a/arch/arm/boot/dts/imx6sx-pinfunc.h b/arch/arm/boot/dts/imx6sx-pinfunc.h index 0b02c7e60c17..f4dc46207954 100644 --- a/arch/arm/boot/dts/imx6sx-pinfunc.h +++ b/arch/arm/boot/dts/imx6sx-pinfunc.h @@ -1026,7 +1026,7 @@ #define MX6SX_PAD_QSPI1B_DQS__SIM_M_HADDR_15 0x01B0 0x04F8 0x0000 0x7 0x0 #define MX6SX_PAD_QSPI1B_SCLK__QSPI1_B_SCLK 0x01B4 0x04FC 0x0000 0x0 0x0 #define MX6SX_PAD_QSPI1B_SCLK__UART3_DCE_RX 0x01B4 0x04FC 0x0840 0x1 0x4 -#define MX6SX_PAD_QSPI1B_SCLK__UART3_DTE_TX 0x01B4 0x04FC 0x0000 0x0 0x0 +#define MX6SX_PAD_QSPI1B_SCLK__UART3_DTE_TX 0x01B4 0x04FC 0x0000 0x1 0x0 #define MX6SX_PAD_QSPI1B_SCLK__ECSPI3_SCLK 0x01B4 0x04FC 0x0730 0x2 0x1 #define MX6SX_PAD_QSPI1B_SCLK__ESAI_RX_HF_CLK 0x01B4 0x04FC 0x0780 0x3 0x2 #define MX6SX_PAD_QSPI1B_SCLK__CSI1_DATA_16 0x01B4 0x04FC 0x06DC 0x4 0x1 diff --git a/arch/arm/boot/dts/imx7d-zii-rmu2.dts b/arch/arm/boot/dts/imx7d-zii-rmu2.dts index e5e20b07f184..7cb6153fc650 100644 --- a/arch/arm/boot/dts/imx7d-zii-rmu2.dts +++ b/arch/arm/boot/dts/imx7d-zii-rmu2.dts @@ -58,7 +58,7 @@ <&clks IMX7D_ENET1_TIME_ROOT_CLK>; assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>; assigned-clock-rates = <0>, <100000000>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&fec1_phy>; status = "okay"; diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi index 367439639da9..b7ea37ad4e55 100644 --- a/arch/arm/boot/dts/imx7ulp.dtsi +++ b/arch/arm/boot/dts/imx7ulp.dtsi @@ -394,7 +394,7 @@ clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>, <&pcc3 IMX7ULP_CLK_PCTLC>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc1 0 0 32>; + gpio-ranges = <&iomuxc1 0 0 20>; }; gpio_ptd: gpio@40af0000 { @@ -408,7 +408,7 @@ clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>, <&pcc3 IMX7ULP_CLK_PCTLD>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc1 0 32 32>; + gpio-ranges = <&iomuxc1 0 32 12>; }; gpio_pte: gpio@40b00000 { @@ -422,7 +422,7 @@ clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>, <&pcc3 IMX7ULP_CLK_PCTLE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc1 0 64 32>; + gpio-ranges = <&iomuxc1 0 64 16>; }; gpio_ptf: gpio@40b10000 { @@ -436,7 +436,7 @@ clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>, <&pcc3 IMX7ULP_CLK_PCTLF>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc1 0 96 32>; + gpio-ranges = <&iomuxc1 0 96 20>; }; }; diff --git a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi index 100396f6c2fe..395e05f10d36 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi @@ -51,6 +51,8 @@ &mcbsp2 { status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&mcbsp2_pins>; }; &charger { @@ -102,35 +104,18 @@ regulator-max-microvolt = <3300000>; }; - lcd0: display@0 { - compatible = "panel-dpi"; - label = "28"; - status = "okay"; - /* default-on; */ + lcd0: display { + /* This isn't the exact LCD, but the timings meet spec */ + compatible = "logicpd,type28"; pinctrl-names = "default"; pinctrl-0 = <&lcd_enable_pin>; - enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>; /* gpio155, lcd INI */ + backlight = <&bl>; + enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>; port { lcd_in: endpoint { remote-endpoint = <&dpi_out>; }; }; - - panel-timing { - clock-frequency = <9000000>; - hactive = <480>; - vactive = <272>; - hfront-porch = <3>; - hback-porch = <2>; - hsync-len = <42>; - vback-porch = <3>; - vfront-porch = <2>; - vsync-len = <11>; - hsync-active = <1>; - vsync-active = <1>; - de-active = <1>; - pixelclk-active = <0>; - }; }; bl: backlight { diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi index 381f0e82bb70..b0f6613e6d54 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi @@ -81,6 +81,8 @@ }; &mcbsp2 { + pinctrl-names = "default"; + pinctrl-0 = <&mcbsp2_pins>; status = "okay"; }; diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi index 069af9a19bb6..827373ef1a54 100644 --- a/arch/arm/boot/dts/ls1021a.dtsi +++ b/arch/arm/boot/dts/ls1021a.dtsi @@ -182,7 +182,7 @@ #address-cells = <1>; #size-cells = <0>; reg = <0x0 0x1550000 0x0 0x10000>, - <0x0 0x40000000 0x0 0x40000000>; + <0x0 0x40000000 0x0 0x20000000>; reg-names = "QuadSPI", "QuadSPI-memory"; interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>; clock-names = "qspi_en", "qspi"; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index 5da9cff7a53c..a82c96258a93 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -488,11 +488,11 @@ }; }; - target-module@5000 { + target-module@4000 { compatible = "ti,sysc-omap2", "ti,sysc"; - reg = <0x5000 0x4>, - <0x5010 0x4>, - <0x5014 0x4>; + reg = <0x4000 0x4>, + <0x4010 0x4>, + <0x4014 0x4>; reg-names = "rev", "sysc", "syss"; ti,sysc-sidle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, @@ -504,7 +504,7 @@ ti,syss-mask = <1>; #address-cells = <1>; #size-cells = <1>; - ranges = <0 0x5000 0x1000>; + ranges = <0 0x4000 0x1000>; dsi1: encoder@0 { compatible = "ti,omap5-dsi"; @@ -514,8 +514,9 @@ reg-names = "proto", "phy", "pll"; interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; - clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>; - clock-names = "fck"; + clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>, + <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>; + clock-names = "fck", "sys_clk"; }; }; @@ -545,8 +546,9 @@ reg-names = "proto", "phy", "pll"; interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; - clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>; - clock-names = "fck"; + clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>, + <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>; + clock-names = "fck", "sys_clk"; }; }; diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi index fc4abef143a0..0013ec3463c4 100644 --- a/arch/arm/boot/dts/socfpga_arria10.dtsi +++ b/arch/arm/boot/dts/socfpga_arria10.dtsi @@ -821,7 +821,7 @@ timer3: timer3@ffd00100 { compatible = "snps,dw-apb-timer"; interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>; - reg = <0xffd01000 0x100>; + reg = <0xffd00100 0x100>; clocks = <&l4_sys_free_clk>; clock-names = "timer"; resets = <&rst L4SYSTIMER1_RESET>; diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi index 0fe03aa0367f..2259d11af721 100644 --- a/arch/arm/boot/dts/vfxxx.dtsi +++ b/arch/arm/boot/dts/vfxxx.dtsi @@ -495,7 +495,7 @@ }; ocotp: ocotp@400a5000 { - compatible = "fsl,vf610-ocotp"; + compatible = "fsl,vf610-ocotp", "syscon"; reg = <0x400a5000 0x1000>; clocks = <&clks VF610_CLK_OCOTP>; }; diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig index a9755c501bec..b06e537d5149 100644 --- a/arch/arm/configs/integrator_defconfig +++ b/arch/arm/configs/integrator_defconfig @@ -1,13 +1,11 @@ CONFIG_SYSVIPC=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_PARTITION_ADVANCED=y CONFIG_ARCH_MULTI_V4T=y CONFIG_ARCH_MULTI_V5=y # CONFIG_ARCH_MULTI_V7 is not set @@ -15,19 +13,17 @@ CONFIG_ARCH_INTEGRATOR=y CONFIG_ARCH_INTEGRATOR_AP=y CONFIG_INTEGRATOR_IMPD1=y CONFIG_ARCH_INTEGRATOR_CP=y -CONFIG_PCI=y -CONFIG_PREEMPT=y CONFIG_AEABI=y # CONFIG_ATAGS is not set -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp" CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPUFREQ_DT=y -CONFIG_CMA=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_PARTITION_ADVANCED=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -37,6 +33,7 @@ CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y # CONFIG_IPV6 is not set +CONFIG_PCI=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_AFS_PARTS=y @@ -52,9 +49,12 @@ CONFIG_BLK_DEV_RAM_SIZE=8192 CONFIG_NETDEVICES=y CONFIG_E100=y CONFIG_SMC91X=y +CONFIG_INPUT_EVDEV=y # CONFIG_KEYBOARD_ATKBD is not set +CONFIG_KEYBOARD_GPIO=y # CONFIG_SERIO_SERPORT is not set CONFIG_DRM=y +CONFIG_DRM_DISPLAY_CONNECTOR=y CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_PL111=y CONFIG_FB_MODE_HELPERS=y diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c index 24dd5bbe60e4..094337dc1bc7 100644 --- a/arch/arm/mach-imx/cpuidle-imx6q.c +++ b/arch/arm/mach-imx/cpuidle-imx6q.c @@ -24,7 +24,9 @@ static int imx6q_enter_wait(struct cpuidle_device *dev, imx6_set_lpm(WAIT_UNCLOCKED); raw_spin_unlock(&cpuidle_lock); + rcu_idle_enter(); cpu_do_idle(); + rcu_idle_exit(); raw_spin_lock(&cpuidle_lock); if (num_idle_cpus-- == num_online_cpus()) @@ -44,7 +46,7 @@ static struct cpuidle_driver imx6q_cpuidle_driver = { { .exit_latency = 50, .target_residency = 75, - .flags = CPUIDLE_FLAG_TIMER_STOP, + .flags = CPUIDLE_FLAG_TIMER_STOP | CPUIDLE_FLAG_RCU_IDLE, .enter = imx6q_enter_wait, .name = "WAIT", .desc = "Clock off", diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c index 54aff33e55e6..bfa5e1b8dba7 100644 --- a/arch/arm/mach-omap2/omap-iommu.c +++ b/arch/arm/mach-omap2/omap-iommu.c @@ -74,7 +74,7 @@ static struct powerdomain *_get_pwrdm(struct device *dev) return pwrdm; clk = of_clk_get(dev->of_node->parent, 0); - if (!clk) { + if (IS_ERR(clk)) { dev_err(dev, "no fck found\n"); return NULL; } diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index e93145d72c26..a6ab3689b2f4 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -150,7 +150,7 @@ static int xen_starting_cpu(unsigned int cpu) pr_info("Xen: initializing cpu%d\n", cpu); vcpup = per_cpu_ptr(xen_vcpu_info, cpu); - info.mfn = virt_to_gfn(vcpup); + info.mfn = percpu_to_gfn(vcpup); info.offset = xen_offset_in_page(vcpup); err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu), diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi index 15f7b0ed3836..39802066232e 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi @@ -745,7 +745,7 @@ }; qspi: spi@66470200 { - compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi"; + compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi"; reg = <0x66470200 0x184>, <0x66470000 0x124>, <0x67017408 0x004>, diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile index a39f0a1723e0..903c0eb61290 100644 --- a/arch/arm64/boot/dts/freescale/Makefile +++ b/arch/arm64/boot/dts/freescale/Makefile @@ -28,6 +28,7 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-honeycomb.dtb dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-qds.dtb dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-rdb.dtb +dtb-$(CONFIG_ARCH_MXC) += imx8mm-beacon-kit.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-evk.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mn-evk.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mn-ddr4-evk.dtb diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 9de2aa1c573c..a5154f13a18e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -702,7 +702,7 @@ reg = <0x30bd0000 0x10000>; interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MP_CLK_SDMA1_ROOT>, - <&clk IMX8MP_CLK_SDMA1_ROOT>; + <&clk IMX8MP_CLK_AHB>; clock-names = "ipg", "ahb"; #dma-cells = <3>; fsl,sdma-ram-script-name = "imx/sdma/sdma-imx7d.bin"; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index f70435cf9ad5..561fa792fe5a 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -423,7 +423,7 @@ tmu: tmu@30260000 { compatible = "fsl,imx8mq-tmu"; reg = <0x30260000 0x10000>; - interrupt = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MQ_CLK_TMU_ROOT>; little-endian; fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x70061>; diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 1a39e0ef776b..5b9ec032ce8d 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -686,6 +686,8 @@ clocks = <&pericfg CLK_PERI_MSDC30_0_PD>, <&topckgen CLK_TOP_MSDC50_0_SEL>; clock-names = "source", "hclk"; + resets = <&pericfg MT7622_PERI_MSDC0_SW_RST>; + reset-names = "hrst"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi index 34d249d85da7..8eb61dd9921e 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi @@ -337,8 +337,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03400000 0x0 0x10000>; interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC1>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC1>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRA &emc>, @@ -366,8 +367,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03420000 0x0 0x10000>; interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC2>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC2>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC2>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRAA &emc>, @@ -390,8 +392,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03440000 0x0 0x10000>; interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC3>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC3>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCR &emc>, @@ -416,8 +419,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03460000 0x0 0x10000>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC4>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; assigned-clocks = <&bpmp TEGRA186_CLK_SDMMC4>, <&bpmp TEGRA186_CLK_PLLC4_VCO>; assigned-clock-parents = <&bpmp TEGRA186_CLK_PLLC4_VCO>; diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index 48160f48003a..ca5cb6aef5ee 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -460,8 +460,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03400000 0x10000>; interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC1>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA194_RESET_SDMMC1>; reset-names = "sdhci"; interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCRA &emc>, @@ -485,8 +486,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03440000 0x10000>; interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC3>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA194_RESET_SDMMC3>; reset-names = "sdhci"; interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCR &emc>, @@ -511,8 +513,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03460000 0x10000>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC4>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; assigned-clocks = <&bpmp TEGRA194_CLK_SDMMC4>, <&bpmp TEGRA194_CLK_PLLC4>; assigned-clock-parents = diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi index 829f786af133..8cca2166a446 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi @@ -1194,8 +1194,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0000 0x0 0x200>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC1>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 14>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3", "sdmmc-1v8", @@ -1222,8 +1223,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0200 0x0 0x200>; interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC2>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC2>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 9>; reset-names = "sdhci"; pinctrl-names = "sdmmc-1v8-drv"; @@ -1239,8 +1241,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0400 0x0 0x200>; interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC3>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 69>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3", "sdmmc-1v8", @@ -1262,8 +1265,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0600 0x0 0x200>; interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC4>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 15>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3-drv", "sdmmc-1v8-drv"; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 9174ddc76bdc..3ec99f13c259 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -13,6 +13,7 @@ */ #include <dt-bindings/power/xlnx-zynqmp-power.h> +#include <dt-bindings/reset/xlnx-zynqmp-resets.h> / { compatible = "xlnx,zynqmp"; @@ -558,6 +559,15 @@ }; }; + psgtr: phy@fd400000 { + compatible = "xlnx,zynqmp-psgtr-v1.1"; + status = "disabled"; + reg = <0x0 0xfd400000 0x0 0x40000>, + <0x0 0xfd3d0000 0x0 0x1000>; + reg-names = "serdes", "siou"; + #phy-cells = <4>; + }; + rtc: rtc@ffa60000 { compatible = "xlnx,zynqmp-rtc"; status = "disabled"; @@ -601,7 +611,7 @@ power-domains = <&zynqmp_firmware PD_SD_1>; }; - smmu: smmu@fd800000 { + smmu: iommu@fd800000 { compatible = "arm,mmu-500"; reg = <0x0 0xfd800000 0x0 0x20000>; status = "disabled"; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index e0f33826819f..6d04b9577b0b 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -724,6 +724,17 @@ CONFIG_USB_GADGET=y CONFIG_USB_RENESAS_USBHS_UDC=m CONFIG_USB_RENESAS_USB3=m CONFIG_USB_TEGRA_XUDC=m +CONFIG_USB_CONFIGFS=m +CONFIG_USB_CONFIGFS_SERIAL=y +CONFIG_USB_CONFIGFS_ACM=y +CONFIG_USB_CONFIGFS_OBEX=y +CONFIG_USB_CONFIGFS_NCM=y +CONFIG_USB_CONFIGFS_ECM=y +CONFIG_USB_CONFIGFS_ECM_SUBSET=y +CONFIG_USB_CONFIGFS_RNDIS=y +CONFIG_USB_CONFIGFS_EEM=y +CONFIG_USB_CONFIGFS_MASS_STORAGE=y +CONFIG_USB_CONFIGFS_F_FS=y CONFIG_TYPEC=m CONFIG_TYPEC_TCPM=m CONFIG_TYPEC_FUSB302=m @@ -914,6 +925,7 @@ CONFIG_ARCH_TEGRA_194_SOC=y CONFIG_ARCH_K3_AM6_SOC=y CONFIG_ARCH_K3_J721E_SOC=y CONFIG_TI_SCI_PM_DOMAINS=y +CONFIG_EXTCON_PTN5150=m CONFIG_EXTCON_USB_GPIO=y CONFIG_EXTCON_USBC_CROS_EC=y CONFIG_IIO=y diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S index b357164379f6..63a52ad9a75c 100644 --- a/arch/arm64/crypto/aes-neonbs-core.S +++ b/arch/arm64/crypto/aes-neonbs-core.S @@ -788,7 +788,7 @@ SYM_FUNC_START_LOCAL(__xts_crypt8) 0: mov bskey, x21 mov rounds, x22 - br x7 + br x16 SYM_FUNC_END(__xts_crypt8) .macro __xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7 @@ -806,7 +806,7 @@ SYM_FUNC_END(__xts_crypt8) uzp1 v30.4s, v30.4s, v25.4s ld1 {v25.16b}, [x24] -99: adr x7, \do8 +99: adr x16, \do8 bl __xts_crypt8 ldp q16, q17, [sp, #.Lframe_local_offset] diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 96eccb107ec2..5ef2669ccd6c 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -298,15 +298,15 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; } -static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW); } +/* Always check for S1PTW *before* using this. */ static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { - return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) || - kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ + return kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR; } static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) @@ -335,6 +335,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW; } +static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); +} + static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC; @@ -372,6 +377,9 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) { + if (kvm_vcpu_abt_iss1tw(vcpu)) + return true; + if (kvm_vcpu_trap_is_iabt(vcpu)) return false; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 8785ebf9bc29..bb5e5b88d439 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -368,7 +368,6 @@ struct kvm_vcpu_arch { /* Guest PV state */ struct { - u64 steal; u64 last_steal; gpa_t base; } steal; @@ -544,6 +543,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); void kvm_update_stolen_time(struct kvm_vcpu *vcpu); +bool kvm_arm_pvtime_supported(void); int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index a85174d05473..cada0b816c8a 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -298,8 +298,21 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: case EFI_PERSISTENT_MEMORY: - pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys); - return NULL; + if (memblock_is_map_memory(phys) || + !memblock_is_region_memory(phys, size)) { + pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys); + return NULL; + } + /* + * Mapping kernel memory is permitted if the region in + * question is covered by a single memblock with the + * NOMAP attribute set: this enables the use of ACPI + * table overrides passed via initramfs, which are + * reserved in memory using arch_reserve_mem_area() + * below. As this particular use case only requires + * read access, fall through to the R/O mapping case. + */ + fallthrough; case EFI_RUNTIME_SERVICES_CODE: /* @@ -388,3 +401,8 @@ int apei_claim_sea(struct pt_regs *regs) return err; } + +void arch_reserve_mem_area(acpi_physical_address addr, size_t size) +{ + memblock_mark_nomap(addr, size); +} diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6c8303559beb..24d75af344b1 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -476,8 +476,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM erratum 1418040", .capability = ARM64_WORKAROUND_1418040, ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), - .type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU | - ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU), + /* + * We need to allow affected CPUs to come in late, but + * also need the non-affected CPUs to be able to come + * in at any point in time. Wonderful. + */ + .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, }, #endif #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 0ce3a28e3347..2e224435c024 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -305,8 +305,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, mod->arch.core.plt_shndx = i; else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt")) mod->arch.init.plt_shndx = i; - else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && - !strcmp(secstrings + sechdrs[i].sh_name, + else if (!strcmp(secstrings + sechdrs[i].sh_name, ".text.ftrace_trampoline")) tramp = sechdrs + i; else if (sechdrs[i].sh_type == SHT_SYMTAB) diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index 295d66490584..c07d7a034941 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -50,16 +50,19 @@ static u64 pv_steal_clock(int cpu) struct pv_time_stolen_time_region *reg; reg = per_cpu_ptr(&stolen_time_region, cpu); - if (!reg->kaddr) { - pr_warn_once("stolen time enabled but not configured for cpu %d\n", - cpu); + + /* + * paravirt_steal_clock() may be called before the CPU + * online notification callback runs. Until the callback + * has run we just return zero. + */ + if (!reg->kaddr) return 0; - } return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time)); } -static int stolen_time_dying_cpu(unsigned int cpu) +static int stolen_time_cpu_down_prepare(unsigned int cpu) { struct pv_time_stolen_time_region *reg; @@ -73,7 +76,7 @@ static int stolen_time_dying_cpu(unsigned int cpu) return 0; } -static int init_stolen_time_cpu(unsigned int cpu) +static int stolen_time_cpu_online(unsigned int cpu) { struct pv_time_stolen_time_region *reg; struct arm_smccc_res res; @@ -103,19 +106,20 @@ static int init_stolen_time_cpu(unsigned int cpu) return 0; } -static int pv_time_init_stolen_time(void) +static int __init pv_time_init_stolen_time(void) { int ret; - ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING, - "hypervisor/arm/pvtime:starting", - init_stolen_time_cpu, stolen_time_dying_cpu); + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "hypervisor/arm/pvtime:online", + stolen_time_cpu_online, + stolen_time_cpu_down_prepare); if (ret < 0) return ret; return 0; } -static bool has_pv_steal_clock(void) +static bool __init has_pv_steal_clock(void) { struct arm_smccc_res res; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 77c4c9bad1b8..53acbeca4f57 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -280,7 +280,6 @@ u64 cpu_logical_map(int cpu) { return __cpu_logical_map[cpu]; } -EXPORT_SYMBOL_GPL(cpu_logical_map); void __init __no_sanitize_address setup_arch(char **cmdline_p) { diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 13e559ac7235..acf9a993dfb6 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -206,6 +206,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) */ r = 1; break; + case KVM_CAP_STEAL_TIME: + r = kvm_arm_pvtime_supported(); + break; default: r = kvm_arch_vm_ioctl_check_extension(kvm, ext); break; diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index a6840823b60e..d0f07e8cc3ff 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -449,7 +449,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && kvm_vcpu_dabt_isvalid(vcpu) && !kvm_vcpu_abt_issea(vcpu) && - !kvm_vcpu_dabt_iss1tw(vcpu); + !kvm_vcpu_abt_iss1tw(vcpu); if (valid) { int ret = __vgic_v2_perform_cpuif_access(vcpu); diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index 69eae608d670..b15d65a42042 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -31,7 +31,14 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu, isb(); } + /* + * __load_guest_stage2() includes an ISB only when the AT + * workaround is applied. Take care of the opposite condition, + * ensuring that we always have an ISB, but not two ISBs back + * to back. + */ __load_guest_stage2(mmu); + asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT)); } static void __tlb_switch_to_host(struct tlb_inv_context *cxt) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index ba00bcc0c884..3d26b47a1343 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1849,7 +1849,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu; write_fault = kvm_is_write_fault(vcpu); - exec_fault = kvm_vcpu_trap_is_iabt(vcpu); + exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); if (fault_status == FSC_PERM && !write_fault && !exec_fault) { @@ -1877,6 +1877,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) { force_pte = true; vma_pagesize = PAGE_SIZE; + vma_shift = PAGE_SHIFT; } /* @@ -1970,7 +1971,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, (fault_status == FSC_PERM && stage2_is_exec(mmu, fault_ipa, vma_pagesize)); - if (vma_pagesize == PUD_SIZE) { + /* + * If PUD_SIZE == PMD_SIZE, there is no real PUD level, and + * all we have is a 2-level page table. Trying to map a PUD in + * this case would be fatally wrong. + */ + if (PUD_SIZE != PMD_SIZE && vma_pagesize == PUD_SIZE) { pud_t new_pud = kvm_pfn_pud(pfn, mem_type); new_pud = kvm_pud_mkhuge(new_pud); @@ -2125,7 +2131,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) goto out; } - if (kvm_vcpu_dabt_iss1tw(vcpu)) { + if (kvm_vcpu_abt_iss1tw(vcpu)) { kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); ret = 1; goto out_unlock; diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c index f7b52ce1557e..920ac43077ad 100644 --- a/arch/arm64/kvm/pvtime.c +++ b/arch/arm64/kvm/pvtime.c @@ -13,25 +13,22 @@ void kvm_update_stolen_time(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; - u64 steal; - __le64 steal_le; - u64 offset; - int idx; u64 base = vcpu->arch.steal.base; + u64 last_steal = vcpu->arch.steal.last_steal; + u64 offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time); + u64 steal = 0; + int idx; if (base == GPA_INVALID) return; - /* Let's do the local bookkeeping */ - steal = vcpu->arch.steal.steal; - steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal; - vcpu->arch.steal.last_steal = current->sched_info.run_delay; - vcpu->arch.steal.steal = steal; - - steal_le = cpu_to_le64(steal); idx = srcu_read_lock(&kvm->srcu); - offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time); - kvm_put_guest(kvm, base + offset, steal_le, u64); + if (!kvm_get_guest(kvm, base + offset, steal)) { + steal = le64_to_cpu(steal); + vcpu->arch.steal.last_steal = READ_ONCE(current->sched_info.run_delay); + steal += vcpu->arch.steal.last_steal - last_steal; + kvm_put_guest(kvm, base + offset, cpu_to_le64(steal)); + } srcu_read_unlock(&kvm->srcu, idx); } @@ -43,7 +40,8 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) switch (feature) { case ARM_SMCCC_HV_PV_TIME_FEATURES: case ARM_SMCCC_HV_PV_TIME_ST: - val = SMCCC_RET_SUCCESS; + if (vcpu->arch.steal.base != GPA_INVALID) + val = SMCCC_RET_SUCCESS; break; } @@ -64,7 +62,6 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) * Start counting stolen time from the time the guest requests * the feature enabled. */ - vcpu->arch.steal.steal = 0; vcpu->arch.steal.last_steal = current->sched_info.run_delay; idx = srcu_read_lock(&kvm->srcu); @@ -74,7 +71,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) return base; } -static bool kvm_arm_pvtime_supported(void) +bool kvm_arm_pvtime_supported(void) { return !!sched_info_on(); } diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h index 4691053c5ee4..ff0444352bba 100644 --- a/arch/arm64/kvm/trace_arm.h +++ b/arch/arm64/kvm/trace_arm.h @@ -23,7 +23,7 @@ TRACE_EVENT(kvm_entry, __entry->vcpu_pc = vcpu_pc; ), - TP_printk("PC: 0x%08lx", __entry->vcpu_pc) + TP_printk("PC: 0x%016lx", __entry->vcpu_pc) ); TRACE_EVENT(kvm_exit, @@ -42,7 +42,7 @@ TRACE_EVENT(kvm_exit, __entry->vcpu_pc = vcpu_pc; ), - TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx", + TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx", __print_symbolic(__entry->ret, kvm_arm_exception_type), __entry->esr_ec, __print_symbolic(__entry->esr_ec, kvm_arm_exception_class), @@ -69,7 +69,7 @@ TRACE_EVENT(kvm_guest_fault, __entry->ipa = ipa; ), - TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx", + TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx", __entry->ipa, __entry->hsr, __entry->hxfar, __entry->vcpu_pc) ); @@ -131,7 +131,7 @@ TRACE_EVENT(kvm_mmio_emulate, __entry->cpsr = cpsr; ), - TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)", + TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)", __entry->vcpu_pc, __entry->instr, __entry->cpsr) ); @@ -149,7 +149,7 @@ TRACE_EVENT(kvm_unmap_hva_range, __entry->end = end; ), - TP_printk("mmu notifier unmap range: %#08lx -- %#08lx", + TP_printk("mmu notifier unmap range: %#016lx -- %#016lx", __entry->start, __entry->end) ); @@ -165,7 +165,7 @@ TRACE_EVENT(kvm_set_spte_hva, __entry->hva = hva; ), - TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva) + TP_printk("mmu notifier set pte hva: %#016lx", __entry->hva) ); TRACE_EVENT(kvm_age_hva, @@ -182,7 +182,7 @@ TRACE_EVENT(kvm_age_hva, __entry->end = end; ), - TP_printk("mmu notifier age hva: %#08lx -- %#08lx", + TP_printk("mmu notifier age hva: %#016lx -- %#016lx", __entry->start, __entry->end) ); @@ -198,7 +198,7 @@ TRACE_EVENT(kvm_test_age_hva, __entry->hva = hva; ), - TP_printk("mmu notifier test age hva: %#08lx", __entry->hva) + TP_printk("mmu notifier test age hva: %#016lx", __entry->hva) ); TRACE_EVENT(kvm_set_way_flush, diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h index 2c56d1e0f5bd..8d78acc4fba7 100644 --- a/arch/arm64/kvm/trace_handle_exit.h +++ b/arch/arm64/kvm/trace_handle_exit.h @@ -22,7 +22,7 @@ TRACE_EVENT(kvm_wfx_arm64, __entry->is_wfe = is_wfe; ), - TP_printk("guest executed wf%c at: 0x%08lx", + TP_printk("guest executed wf%c at: 0x%016lx", __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc) ); @@ -42,7 +42,7 @@ TRACE_EVENT(kvm_hvc_arm64, __entry->imm = imm; ), - TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)", + TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)", __entry->vcpu_pc, __entry->r0, __entry->imm) ); @@ -135,7 +135,7 @@ TRACE_EVENT(trap_reg, __entry->write_value = write_value; ), - TP_printk("%s %s reg %d (0x%08llx)", __entry->fn, __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value) + TP_printk("%s %s reg %d (0x%016llx)", __entry->fn, __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value) ); TRACE_EVENT(kvm_handle_sys_reg, diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index f8912e45be7a..ef9f1d5e989d 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -143,14 +143,17 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val, } } -static inline int bpf2a64_offset(int bpf_to, int bpf_from, +static inline int bpf2a64_offset(int bpf_insn, int off, const struct jit_ctx *ctx) { - int to = ctx->offset[bpf_to]; - /* -1 to account for the Branch instruction */ - int from = ctx->offset[bpf_from] - 1; - - return to - from; + /* BPF JMP offset is relative to the next instruction */ + bpf_insn++; + /* + * Whereas arm64 branch instructions encode the offset + * from the branch itself, so we must subtract 1 from the + * instruction offset. + */ + return ctx->offset[bpf_insn + off] - (ctx->offset[bpf_insn] - 1); } static void jit_fill_hole(void *area, unsigned int size) @@ -642,7 +645,7 @@ emit_bswap_uxt: /* JUMP off */ case BPF_JMP | BPF_JA: - jmp_offset = bpf2a64_offset(i + off, i, ctx); + jmp_offset = bpf2a64_offset(i, off, ctx); check_imm26(jmp_offset); emit(A64_B(jmp_offset), ctx); break; @@ -669,7 +672,7 @@ emit_bswap_uxt: case BPF_JMP32 | BPF_JSLE | BPF_X: emit(A64_CMP(is64, dst, src), ctx); emit_cond_jmp: - jmp_offset = bpf2a64_offset(i + off, i, ctx); + jmp_offset = bpf2a64_offset(i, off, ctx); check_imm19(jmp_offset); switch (BPF_OP(code)) { case BPF_JEQ: @@ -908,10 +911,21 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass) const struct bpf_prog *prog = ctx->prog; int i; + /* + * - offset[0] offset of the end of prologue, + * start of the 1st instruction. + * - offset[1] - offset of the end of 1st instruction, + * start of the 2nd instruction + * [....] + * - offset[3] - offset of the end of 3rd instruction, + * start of 4th instruction + */ for (i = 0; i < prog->len; i++) { const struct bpf_insn *insn = &prog->insnsi[i]; int ret; + if (ctx->image == NULL) + ctx->offset[i] = ctx->idx; ret = build_insn(insn, ctx, extra_pass); if (ret > 0) { i++; @@ -919,11 +933,16 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass) ctx->offset[i] = ctx->idx; continue; } - if (ctx->image == NULL) - ctx->offset[i] = ctx->idx; if (ret) return ret; } + /* + * offset is allocated with prog->len + 1 so fill in + * the last element with the offset after the last + * instruction (end of program) + */ + if (ctx->image == NULL) + ctx->offset[i] = ctx->idx; return 0; } @@ -1002,7 +1021,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) memset(&ctx, 0, sizeof(ctx)); ctx.prog = prog; - ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); + ctx.offset = kcalloc(prog->len + 1, sizeof(int), GFP_KERNEL); if (ctx.offset == NULL) { prog = orig_prog; goto out_off; @@ -1089,7 +1108,7 @@ skip_init_ctx: prog->jited_len = prog_size; if (!prog->is_func || extra_pass) { - bpf_prog_fill_jited_linfo(prog, ctx.offset); + bpf_prog_fill_jited_linfo(prog, ctx.offset + 1); out_off: kfree(ctx.offset); kfree(jit_data); diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h index b66ba907019c..87927eb824cc 100644 --- a/arch/ia64/include/asm/acpi.h +++ b/arch/ia64/include/asm/acpi.h @@ -74,8 +74,6 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf) buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP; } -#define acpi_unlazy_tlb(x) - #ifdef CONFIG_ACPI_NUMA extern cpumask_t early_cpu_possible_map; #define for_each_possible_early_cpu(cpu) \ diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index b49fe6f618ed..f8150ee74f29 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -3,7 +3,7 @@ * Architecture-specific kernel symbols */ -#ifdef CONFIG_VIRTUAL_MEM_MAP +#if defined(CONFIG_VIRTUAL_MEM_MAP) || defined(CONFIG_DISCONTIGMEM) #include <linux/compiler.h> #include <linux/export.h> #include <linux/memblock.h> diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 0b3fb4c7af29..8e7b8c6c576e 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -538,7 +538,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg) if (map_start < map_end) memmap_init_zone((unsigned long)(map_end - map_start), args->nid, args->zone, page_to_pfn(map_start), - MEMMAP_EARLY, NULL); + MEMINIT_EARLY, NULL); return 0; } @@ -547,8 +547,8 @@ memmap_init (unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { if (!vmem_map) { - memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, - NULL); + memmap_init_zone(size, nid, zone, start_pfn, + MEMINIT_EARLY, NULL); } else { struct page *start; struct memmap_init_callback_data args; diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 0880a003573d..3344d4a1fe89 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -46,6 +46,9 @@ unsigned long memory_size; EXPORT_SYMBOL(memory_size); unsigned long lowmem_size; +EXPORT_SYMBOL(min_low_pfn); +EXPORT_SYMBOL(max_low_pfn); + #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; EXPORT_SYMBOL(kmap_pte); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index c95fa3a2484c..8f328298f8cc 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -877,6 +877,7 @@ config SNI_RM select I8253 select I8259 select ISA + select MIPS_L1_CACHE_SHIFT_6 select SWAP_IO_SPACE if CPU_BIG_ENDIAN select SYS_HAS_CPU_R4X00 select SYS_HAS_CPU_R5000 diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 82627c264964..01427bde2397 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -148,7 +148,7 @@ void __init plat_mem_setup(void) { struct cpuinfo_mips *c = ¤t_cpu_data; - if ((c->cputype == CPU_74K) || (c->cputype == CPU_1074K)) { + if (c->cputype == CPU_74K) { pr_info("Using bcma bus\n"); #ifdef CONFIG_BCM47XX_BCMA bcm47xx_bus_type = BCM47XX_BUS_TYPE_BCMA; diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index 75a7a382da09..3288cef4b168 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type) case CPU_34K: case CPU_1004K: case CPU_74K: + case CPU_1074K: case CPU_M14KC: case CPU_M14KEC: case CPU_INTERAPTIV: diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h index b6e9c99b85a5..eb181224eb4c 100644 --- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h @@ -26,7 +26,6 @@ #define cpu_has_counter 1 #define cpu_has_dc_aliases (PAGE_SIZE < 0x4000) #define cpu_has_divec 0 -#define cpu_has_ejtag 0 #define cpu_has_inclusive_pcaches 1 #define cpu_has_llsc 1 #define cpu_has_mcheck 0 @@ -42,7 +41,6 @@ #define cpu_has_veic 0 #define cpu_has_vint 0 #define cpu_has_vtag_icache 0 -#define cpu_has_watch 1 #define cpu_has_wsbh 1 #define cpu_has_ic_fills_f_dc 1 #define cpu_hwrena_impl_bits 0xc0000000 diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index f5e362f79701..bf2480923154 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -2,8 +2,6 @@ #ifndef __ASM_MACH_LOONGSON64_IRQ_H_ #define __ASM_MACH_LOONGSON64_IRQ_H_ -#include <boot_param.h> - /* cpu core interrupt numbers */ #define NR_IRQS_LEGACY 16 #define NR_MIPS_CPU_IRQS 8 diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h index 3a25dbd3b3e9..5eaca4fe3f92 100644 --- a/arch/mips/include/asm/mach-loongson64/mmzone.h +++ b/arch/mips/include/asm/mach-loongson64/mmzone.h @@ -9,7 +9,6 @@ #ifndef _ASM_MACH_LOONGSON64_MMZONE_H #define _ASM_MACH_LOONGSON64_MMZONE_H -#include <boot_param.h> #define NODE_ADDRSPACE_SHIFT 44 #define NODE0_ADDRSPACE_OFFSET 0x000000000000UL #define NODE1_ADDRSPACE_OFFSET 0x100000000000UL diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index efce5defcc5c..011eb6bbf81a 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1898,8 +1898,8 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) (base_id >= 64 && base_id < 90) || (base_id >= 128 && base_id < 164) || (base_id >= 192 && base_id < 200) || - (base_id >= 256 && base_id < 274) || - (base_id >= 320 && base_id < 358) || + (base_id >= 256 && base_id < 275) || + (base_id >= 320 && base_id < 361) || (base_id >= 384 && base_id < 574)) break; diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 2f513506a3d5..1dbfb5aadffd 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -239,6 +239,8 @@ static int bmips_boot_secondary(int cpu, struct task_struct *idle) */ static void bmips_init_secondary(void) { + bmips_cpu_setup(); + switch (current_cpu_type()) { case CPU_BMIPS4350: case CPU_BMIPS4380: diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 38aa07ccdbcc..cf788591f091 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1287,6 +1287,18 @@ static int enable_restore_fp_context(int msa) err = own_fpu_inatomic(1); if (msa && !err) { enable_msa(); + /* + * with MSA enabled, userspace can see MSACSR + * and MSA regs, but the values in them are from + * other task before current task, restore them + * from saved fp/msa context + */ + write_msa_csr(current->thread.fpu.msacsr); + /* + * own_fpu_inatomic(1) just restore low 64bit, + * fix the high 64bit + */ + init_msa_upper(); set_thread_flag(TIF_USEDMSA); set_thread_flag(TIF_MSA_CTX_LIVE); } diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 7de85d2253ff..0c50ac444222 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -137,6 +137,8 @@ extern void kvm_init_loongson_ipi(struct kvm *kvm); int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { switch (type) { + case KVM_VM_MIPS_AUTO: + break; #ifdef CONFIG_KVM_MIPS_VZ case KVM_VM_MIPS_VZ: #else diff --git a/arch/mips/loongson2ef/Platform b/arch/mips/loongson2ef/Platform index 4ab55f1123a0..ae023b9a1c51 100644 --- a/arch/mips/loongson2ef/Platform +++ b/arch/mips/loongson2ef/Platform @@ -44,6 +44,10 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS endif endif +# Some -march= flags enable MMI instructions, and GCC complains about that +# support being enabled alongside -msoft-float. Thus explicitly disable MMI. +cflags-y += $(call cc-option,-mno-loongson-mmi) + # # Loongson Machines' Support # diff --git a/arch/mips/loongson64/cop2-ex.c b/arch/mips/loongson64/cop2-ex.c index f130f62129b8..00055d4b6042 100644 --- a/arch/mips/loongson64/cop2-ex.c +++ b/arch/mips/loongson64/cop2-ex.c @@ -95,10 +95,8 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, if (res) goto fault; - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rt, value); - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rq, value_next); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0, value); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0, value_next); compute_return_epc(regs); own_fpu(1); } @@ -130,15 +128,13 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, goto sigbus; lose_fpu(1); - value_next = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rq); + value_next = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0); StoreDW(addr + 8, value_next, res); if (res) goto fault; - value = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rt); + value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0); StoreDW(addr, value, res); if (res) @@ -204,8 +200,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, if (res) goto fault; - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt, value); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value); compute_return_epc(regs); own_fpu(1); @@ -221,8 +216,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, if (res) goto fault; - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt, value); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value); compute_return_epc(regs); own_fpu(1); break; @@ -286,8 +280,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, goto sigbus; lose_fpu(1); - value = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt); + value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0); StoreW(addr, value, res); if (res) @@ -305,8 +298,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, goto sigbus; lose_fpu(1); - value = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt); + value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0); StoreDW(addr, value, res); if (res) diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index fc5a6d25f74f..0ef717093262 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1712,7 +1712,11 @@ static void setup_scache(void) printk("MIPS secondary cache %ldkB, %s, linesize %d bytes.\n", scache_size >> 10, way_string[c->scache.ways], c->scache.linesz); + + if (current_cpu_type() == CPU_BMIPS5000) + c->options |= MIPS_CPU_INCLUSIVE_CACHES; } + #else if (!(c->scache.flags & MIPS_CACHE_NOT_PRESENT)) panic("Dunno how to handle MIPS32 / MIPS64 second level cache"); diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c index 1493c49ca47a..55d7b7fd18b6 100644 --- a/arch/mips/oprofile/op_model_mipsxx.c +++ b/arch/mips/oprofile/op_model_mipsxx.c @@ -245,7 +245,6 @@ static int mipsxx_perfcount_handler(void) switch (counters) { #define HANDLE_COUNTER(n) \ - fallthrough; \ case n + 1: \ control = r_c0_perfctrl ## n(); \ counter = r_c0_perfcntr ## n(); \ @@ -256,8 +255,11 @@ static int mipsxx_perfcount_handler(void) handled = IRQ_HANDLED; \ } HANDLE_COUNTER(3) + fallthrough; HANDLE_COUNTER(2) + fallthrough; HANDLE_COUNTER(1) + fallthrough; HANDLE_COUNTER(0) } diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c index 0ecffb65fd6d..eeeec18c420a 100644 --- a/arch/mips/sni/a20r.c +++ b/arch/mips/sni/a20r.c @@ -143,7 +143,10 @@ static struct platform_device sc26xx_pdev = { }, }; -static u32 a20r_ack_hwint(void) +/* + * Trigger chipset to update CPU's CAUSE IP field + */ +static u32 a20r_update_cause_ip(void) { u32 status = read_c0_status(); @@ -205,12 +208,14 @@ static void a20r_hwint(void) int irq; clear_c0_status(IE_IRQ0); - status = a20r_ack_hwint(); + status = a20r_update_cause_ip(); cause = read_c0_cause(); irq = ffs(((cause & status) >> 8) & 0xf8); if (likely(irq > 0)) do_IRQ(SNI_A20R_IRQ_BASE + irq - 1); + + a20r_update_cause_ip(); set_c0_status(IE_IRQ0); } @@ -222,8 +227,8 @@ void __init sni_a20r_irq_init(void) irq_set_chip_and_handler(i, &a20r_irq_type, handle_level_irq); sni_hwint = a20r_hwint; change_c0_status(ST0_IM, IE_IRQ0); - if (request_irq(SNI_A20R_IRQ_BASE + 3, sni_isa_irq_handler, 0, "ISA", - NULL)) + if (request_irq(SNI_A20R_IRQ_BASE + 3, sni_isa_irq_handler, + IRQF_SHARED, "ISA", sni_isa_irq_handler)) pr_err("Failed to register ISA interrupt\n"); } diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h index f0390211236b..120f5005461b 100644 --- a/arch/openrisc/include/asm/uaccess.h +++ b/arch/openrisc/include/asm/uaccess.h @@ -165,19 +165,19 @@ struct __large_struct { #define __get_user_nocheck(x, ptr, size) \ ({ \ - long __gu_err, __gu_val; \ - __get_user_size(__gu_val, (ptr), (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ + long __gu_err; \ + __get_user_size((x), (ptr), (size), __gu_err); \ __gu_err; \ }) #define __get_user_check(x, ptr, size) \ ({ \ - long __gu_err = -EFAULT, __gu_val = 0; \ + long __gu_err = -EFAULT; \ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ - if (access_ok(__gu_addr, size)) \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ + if (access_ok(__gu_addr, size)) \ + __get_user_size((x), __gu_addr, (size), __gu_err); \ + else \ + (x) = (__typeof__(*(ptr))) 0; \ __gu_err; \ }) @@ -191,11 +191,13 @@ do { \ case 2: __get_user_asm(x, ptr, retval, "l.lhz"); break; \ case 4: __get_user_asm(x, ptr, retval, "l.lwz"); break; \ case 8: __get_user_asm2(x, ptr, retval); break; \ - default: (x) = __get_user_bad(); \ + default: (x) = (__typeof__(*(ptr)))__get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, err, op) \ +{ \ + unsigned long __gu_tmp; \ __asm__ __volatile__( \ "1: "op" %1,0(%2)\n" \ "2:\n" \ @@ -209,10 +211,14 @@ do { \ " .align 2\n" \ " .long 1b,3b\n" \ ".previous" \ - : "=r"(err), "=r"(x) \ - : "r"(addr), "i"(-EFAULT), "0"(err)) + : "=r"(err), "=r"(__gu_tmp) \ + : "r"(addr), "i"(-EFAULT), "0"(err)); \ + (x) = (__typeof__(*(addr)))__gu_tmp; \ +} #define __get_user_asm2(x, addr, err) \ +{ \ + unsigned long long __gu_tmp; \ __asm__ __volatile__( \ "1: l.lwz %1,0(%2)\n" \ "2: l.lwz %H1,4(%2)\n" \ @@ -229,8 +235,11 @@ do { \ " .long 1b,4b\n" \ " .long 2b,4b\n" \ ".previous" \ - : "=r"(err), "=&r"(x) \ - : "r"(addr), "i"(-EFAULT), "0"(err)) + : "=r"(err), "=&r"(__gu_tmp) \ + : "r"(addr), "i"(-EFAULT), "0"(err)); \ + (x) = (__typeof__(*(addr)))( \ + (__typeof__((x)-(x)))__gu_tmp); \ +} /* more complex routines */ diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index b18e775f8be3..13c87f1f872b 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -80,6 +80,16 @@ static void __init setup_memory(void) */ memblock_reserve(__pa(_stext), _end - _stext); +#ifdef CONFIG_BLK_DEV_INITRD + /* Then reserve the initrd, if any */ + if (initrd_start && (initrd_end > initrd_start)) { + unsigned long aligned_start = ALIGN_DOWN(initrd_start, PAGE_SIZE); + unsigned long aligned_end = ALIGN(initrd_end, PAGE_SIZE); + + memblock_reserve(__pa(aligned_start), aligned_end - aligned_start); + } +#endif /* CONFIG_BLK_DEV_INITRD */ + early_init_fdt_reserve_self(); early_init_fdt_scan_reserved_mem(); diff --git a/arch/openrisc/mm/cache.c b/arch/openrisc/mm/cache.c index 08f56af387ac..534a52ec5e66 100644 --- a/arch/openrisc/mm/cache.c +++ b/arch/openrisc/mm/cache.c @@ -16,7 +16,7 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> -static void cache_loop(struct page *page, const unsigned int reg) +static __always_inline void cache_loop(struct page *page, const unsigned int reg) { unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT; unsigned long line = paddr & ~(L1_CACHE_BYTES - 1); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 65bed1fdeaad..787e829b6f25 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -116,7 +116,6 @@ config PPC # select ARCH_32BIT_OFF_T if PPC32 select ARCH_HAS_DEBUG_VIRTUAL - select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index af9af03059e4..15ed8d0aa014 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -108,7 +108,6 @@ CONFIG_FB_NVIDIA=y CONFIG_FB_NVIDIA_I2C=y CONFIG_FB_RADEON=y # CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y CONFIG_SOUND=y CONFIG_SND=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 5e6f92ba3210..66e9a0fd64ff 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -743,7 +743,6 @@ CONFIG_FB_TRIDENT=m CONFIG_FB_SM501=m CONFIG_FB_IBM_GXT4500=y CONFIG_LCD_PLATFORM=m -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 55442d45c597..b392384a3b15 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -239,14 +239,14 @@ static inline void early_init_mmu_secondary(void) extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size); -extern void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size); static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) { - if (early_radix_enabled()) - return radix__setup_initial_memory_limit(first_memblock_base, - first_memblock_size); + /* + * Hash has more strict restrictions. At this point we don't + * know which translations we will pick. Hence go with hash + * restrictions. + */ return hash__setup_initial_memory_limit(first_memblock_base, first_memblock_size); } diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 569fecd7b5b2..9053fc9d20c7 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -120,7 +120,8 @@ u64 dma_iommu_get_required_mask(struct device *dev) if (!tbl) return 0; - mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1); + mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) + + tbl->it_page_shift - 1); mask += mask - 1; return mask; diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 87ab1152d5ce..e147bbdc12cd 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -50,7 +50,7 @@ $(obj-vdso32): %.o: %.S FORCE # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn) -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) + cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 4c985467a668..5206c2eb2a1d 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -111,7 +111,6 @@ SECTIONS *(.note.GNU-stack) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) - *(.glink .iplt .plt .rela*) } } diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 38c317f25141..32ebb3522ea1 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -34,7 +34,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn) + cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index 4e3a8d4ee614..256fb9720298 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -30,7 +30,7 @@ SECTIONS . = ALIGN(16); .text : { *(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*) - *(.sfpr) + *(.sfpr .glink) } :text PROVIDE(__etext = .); PROVIDE(_etext = .); @@ -111,7 +111,6 @@ SECTIONS *(.branch_lt) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) - *(.glink .iplt .plt .rela*) } } diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 28c784976bed..d5f0c10d752a 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -734,21 +734,6 @@ void radix__mmu_cleanup_all(void) } } -void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size) -{ - /* - * We don't currently support the first MEMBLOCK not mapping 0 - * physical on those processors - */ - BUG_ON(first_memblock_base != 0); - - /* - * Radix mode is not limited by RMA / VRMA addressing. - */ - ppc64_rma_size = ULONG_MAX; -} - #ifdef CONFIG_MEMORY_HOTPLUG static void free_pte_table(pte_t *pte_start, pmd_t *pmd) { diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 02e127fa5777..8459056cce67 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -433,9 +433,16 @@ void __init mmu_early_init_devtree(void) if (!(mfmsr() & MSR_HV)) early_check_vec5(); - if (early_radix_enabled()) + if (early_radix_enabled()) { radix__early_init_devtree(); - else + /* + * We have finalized the translation we are going to use by now. + * Radix mode is not limited by RMA / VRMA addressing. + * Hence don't limit memblock allocations. + */ + ppc64_rma_size = ULONG_MAX; + memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); + } else hash__early_init_devtree(); } #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 78d61f97371e..e809cb5a1631 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -475,7 +475,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: true_cond = COND_NE; - fallthrough; cond_branch: /* same targets, can avoid doing the test :) */ if (filter[i].jt == filter[i].jf) { diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f439f0dfea7d..a88a707a608a 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -822,7 +822,7 @@ free_stats: kfree(stats); return rc ? rc : seq_buf_used(&s); } -DEVICE_ATTR_RO(perf_stats); +DEVICE_ATTR_ADMIN_RO(perf_stats); static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index df18372861d8..7766e1289468 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -32,6 +32,7 @@ config RISCV select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if 64BIT select CLONE_BACKWARDS + select CLINT_TIMER if !MMU select COMMON_CLK select EDAC_SUPPORT select GENERIC_ARCH_TOPOLOGY if SMP diff --git a/arch/riscv/boot/dts/kendryte/k210.dtsi b/arch/riscv/boot/dts/kendryte/k210.dtsi index c1df56ccb8d5..d2d0ff645632 100644 --- a/arch/riscv/boot/dts/kendryte/k210.dtsi +++ b/arch/riscv/boot/dts/kendryte/k210.dtsi @@ -95,10 +95,12 @@ #clock-cells = <1>; }; - clint0: interrupt-controller@2000000 { + clint0: clint@2000000 { + #interrupt-cells = <1>; compatible = "riscv,clint0"; reg = <0x2000000 0xC000>; - interrupts-extended = <&cpu0_intc 3>, <&cpu1_intc 3>; + interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 + &cpu1_intc 3 &cpu1_intc 7>; clocks = <&sysctl K210_CLK_ACLK>; }; diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h new file mode 100644 index 000000000000..0789fd37b40a --- /dev/null +++ b/arch/riscv/include/asm/clint.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Google, Inc + */ + +#ifndef _ASM_RISCV_CLINT_H +#define _ASM_RISCV_CLINT_H + +#include <linux/types.h> +#include <asm/mmio.h> + +#ifdef CONFIG_RISCV_M_MODE +/* + * This lives in the CLINT driver, but is accessed directly by timex.h to avoid + * any overhead when accessing the MMIO timer. + * + * The ISA defines mtime as a 64-bit memory-mapped register that increments at + * a constant frequency, but it doesn't define some other constraints we depend + * on (most notably ordering constraints, but also some simpler stuff like the + * memory layout). Thus, this is called "clint_time_val" instead of something + * like "riscv_mtime", to signify that these non-ISA assumptions must hold. + */ +extern u64 __iomem *clint_time_val; +#endif + +#endif diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index ace8a6e2d11d..845002cc2e57 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -66,6 +66,13 @@ do { \ * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here. */ #define MCOUNT_INSN_SIZE 8 + +#ifndef __ASSEMBLY__ +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #endif #endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/include/asm/stackprotector.h b/arch/riscv/include/asm/stackprotector.h index d95f7b2a7f37..5962f8891f06 100644 --- a/arch/riscv/include/asm/stackprotector.h +++ b/arch/riscv/include/asm/stackprotector.h @@ -5,7 +5,6 @@ #include <linux/random.h> #include <linux/version.h> -#include <asm/timex.h> extern unsigned long __stack_chk_guard; @@ -18,12 +17,9 @@ extern unsigned long __stack_chk_guard; static __always_inline void boot_init_stack_canary(void) { unsigned long canary; - unsigned long tsc; /* Try to get a semi random initial value. */ get_random_bytes(&canary, sizeof(canary)); - tsc = get_cycles(); - canary += tsc + (tsc << BITS_PER_LONG/2); canary ^= LINUX_VERSION_CODE; canary &= CANARY_MASK; diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index a3fb85d505d4..ab104905d4db 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -10,6 +10,44 @@ typedef unsigned long cycles_t; +#ifdef CONFIG_RISCV_M_MODE + +#include <asm/clint.h> + +#ifdef CONFIG_64BIT +static inline cycles_t get_cycles(void) +{ + return readq_relaxed(clint_time_val); +} +#else /* !CONFIG_64BIT */ +static inline u32 get_cycles(void) +{ + return readl_relaxed(((u32 *)clint_time_val)); +} +#define get_cycles get_cycles + +static inline u32 get_cycles_hi(void) +{ + return readl_relaxed(((u32 *)clint_time_val) + 1); +} +#define get_cycles_hi get_cycles_hi +#endif /* CONFIG_64BIT */ + +/* + * Much like MIPS, we may not have a viable counter to use at an early point + * in the boot process. Unfortunately we don't have a fallback, so instead + * we just return 0. + */ +static inline unsigned long random_get_entropy(void) +{ + if (unlikely(clint_time_val == NULL)) + return 0; + return get_cycles(); +} +#define random_get_entropy() random_get_entropy() + +#else /* CONFIG_RISCV_M_MODE */ + static inline cycles_t get_cycles(void) { return csr_read(CSR_TIME); @@ -41,6 +79,8 @@ static inline u64 get_cycles64(void) } #endif /* CONFIG_64BIT */ +#endif /* !CONFIG_RISCV_M_MODE */ + #define ARCH_HAS_READ_CURRENT_TIMER static inline int read_current_timer(unsigned long *timer_val) { diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 2ff63d0cbb50..99e12faa5498 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -97,6 +97,25 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return __ftrace_modify_call(rec->ip, addr, false); } + +/* + * This is called early on, and isn't wrapped by + * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold + * text_mutex, which triggers a lockdep failure. SMP isn't running so we could + * just directly poke the text, but it's simpler to just take the lock + * ourselves. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + int out; + + ftrace_arch_code_modify_prepare(); + out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + ftrace_arch_code_modify_post_process(); + + return out; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { int ret = __ftrace_modify_call((unsigned long)&ftrace_call, diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index f3586e31ed1e..34d00d9e6eac 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -22,13 +22,11 @@ SECTIONS /* Beginning of code and text segment */ . = LOAD_OFFSET; _start = .; - _stext = .; HEAD_TEXT_SECTION . = ALIGN(PAGE_SIZE); __init_begin = .; INIT_TEXT_SECTION(PAGE_SIZE) - INIT_DATA_SECTION(16) . = ALIGN(8); __soc_early_init_table : { __soc_early_init_table_start = .; @@ -55,6 +53,7 @@ SECTIONS . = ALIGN(SECTION_ALIGN); .text : { _text = .; + _stext = .; TEXT_TEXT SCHED_TEXT CPUIDLE_TEXT @@ -67,6 +66,8 @@ SECTIONS _etext = .; } + INIT_DATA_SECTION(16) + /* Start of data section */ _sdata = .; RO_DATA(SECTION_ALIGN) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 787c75f751a5..f750e012dbe5 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -226,12 +226,11 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) ptep = &fixmap_pte[pte_index(addr)]; - if (pgprot_val(prot)) { + if (pgprot_val(prot)) set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, prot)); - } else { + else pte_clear(&init_mm, addr, ptep); - local_flush_tlb_page(addr); - } + local_flush_tlb_page(addr); } static pte_t *__init get_pte_virt(phys_addr_t pa) @@ -516,6 +515,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) #else dtb_early_va = (void *)dtb_pa; #endif + dtb_early_pa = dtb_pa; } static inline void setup_vm_final(void) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 3d86e12e8e3c..b29fcc66ec39 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -30,7 +30,7 @@ config GENERIC_BUG_RELATIVE_POINTERS def_bool y config GENERIC_LOCKBREAK - def_bool y if PREEMPTTION + def_bool y if PREEMPTION config PGSTE def_bool y if KVM diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 0cf9a82326a8..7228aabe9da6 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -626,6 +626,7 @@ CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS_INODE64=y CONFIG_HUGETLBFS=y CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m @@ -807,6 +808,7 @@ CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 # CONFIG_RCU_TRACE is not set CONFIG_LATENCYTOP=y @@ -818,6 +820,7 @@ CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_S390_PTDUMP=y CONFIG_NOTIFIER_ERROR_INJECTION=m @@ -829,6 +832,7 @@ CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y +CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 5df9759e8ff6..fab03b7a6932 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -617,6 +617,7 @@ CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS_INODE64=y CONFIG_HUGETLBFS=y CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m @@ -763,6 +764,7 @@ CONFIG_PANIC_ON_OOPS=y CONFIG_TEST_LOCKUP=m CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y CONFIG_BOOTTIME_TRACING=y @@ -771,6 +773,7 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_S390_PTDUMP=y CONFIG_LKDTM=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 4091c50449cd..8f67c55625f9 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -74,5 +74,6 @@ CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 +# CONFIG_RCU_TRACE is not set # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 7eb01a5459cd..b55561cc8786 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1260,26 +1260,44 @@ static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address) #define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address) -static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address) { - if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) - return (p4d_t *) pgd_deref(*pgd) + p4d_index(address); - return (p4d_t *) pgd; + if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) + return (p4d_t *) pgd_deref(pgd) + p4d_index(address); + return (p4d_t *) pgdp; } +#define p4d_offset_lockless p4d_offset_lockless -static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address) { - if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) - return (pud_t *) p4d_deref(*p4d) + pud_index(address); - return (pud_t *) p4d; + return p4d_offset_lockless(pgdp, *pgdp, address); +} + +static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address) +{ + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) + return (pud_t *) p4d_deref(p4d) + pud_index(address); + return (pud_t *) p4dp; +} +#define pud_offset_lockless pud_offset_lockless + +static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address) +{ + return pud_offset_lockless(p4dp, *p4dp, address); } #define pud_offset pud_offset -static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) +static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address) +{ + if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) + return (pmd_t *) pud_deref(pud) + pmd_index(address); + return (pmd_t *) pudp; +} +#define pmd_offset_lockless pmd_offset_lockless + +static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address) { - if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) - return (pmd_t *) pud_deref(*pud) + pmd_index(address); - return (pmd_t *) pud; + return pmd_offset_lockless(pudp, *pudp, address); } #define pmd_offset pmd_offset diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index faca269d5f27..a44ddc2f2dec 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -26,6 +26,7 @@ void do_protection_exception(struct pt_regs *regs); void do_dat_exception(struct pt_regs *regs); void do_secure_storage_access(struct pt_regs *regs); void do_non_secure_storage_access(struct pt_regs *regs); +void do_secure_storage_violation(struct pt_regs *regs); void addressing_exception(struct pt_regs *regs); void data_exception(struct pt_regs *regs); diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index c73f50649e7e..f7f1e64e0d98 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -39,14 +39,13 @@ void enabled_wait(void) local_irq_restore(flags); /* Account time spent with enabled wait psw loaded as idle time. */ - /* XXX seqcount has tracepoints that require RCU */ - write_seqcount_begin(&idle->seqcount); + raw_write_seqcount_begin(&idle->seqcount); idle_time = idle->clock_idle_exit - idle->clock_idle_enter; idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; idle->idle_time += idle_time; idle->idle_count++; account_idle_time(cputime_to_nsecs(idle_time)); - write_seqcount_end(&idle->seqcount); + raw_write_seqcount_end(&idle->seqcount); } NOKPROBE_SYMBOL(enabled_wait); diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S index 2c27907a5ffc..9a92638360ee 100644 --- a/arch/s390/kernel/pgm_check.S +++ b/arch/s390/kernel/pgm_check.S @@ -80,7 +80,7 @@ PGM_CHECK(do_dat_exception) /* 3b */ PGM_CHECK_DEFAULT /* 3c */ PGM_CHECK(do_secure_storage_access) /* 3d */ PGM_CHECK(do_non_secure_storage_access) /* 3e */ -PGM_CHECK_DEFAULT /* 3f */ +PGM_CHECK(do_secure_storage_violation) /* 3f */ PGM_CHECK(monitor_event_exception) /* 40 */ PGM_CHECK_DEFAULT /* 41 */ PGM_CHECK_DEFAULT /* 42 */ diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index e600f6953d7c..c2c1b4e723ea 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -619,7 +619,7 @@ static struct notifier_block kdump_mem_nb = { /* * Make sure that the area behind memory_end is protected */ -static void reserve_memory_end(void) +static void __init reserve_memory_end(void) { if (memory_end_set) memblock_reserve(memory_end, ULONG_MAX); @@ -628,7 +628,7 @@ static void reserve_memory_end(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void reserve_oldmem(void) +static void __init reserve_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) @@ -640,7 +640,7 @@ static void reserve_oldmem(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void remove_oldmem(void) +static void __init remove_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 4c8c063bce5b..996884dcc9fd 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -859,6 +859,21 @@ void do_non_secure_storage_access(struct pt_regs *regs) } NOKPROBE_SYMBOL(do_non_secure_storage_access); +void do_secure_storage_violation(struct pt_regs *regs) +{ + /* + * Either KVM messed up the secure guest mapping or the same + * page is mapped into multiple secure guests. + * + * This exception is only triggered when a guest 2 is running + * and can therefore never occur in kernel context. + */ + printk_ratelimited(KERN_WARNING + "Secure storage violation in task: %s, pid %d\n", + current->comm, current->pid); + send_sig(SIGSEGV, current, 0); +} + #else void do_secure_storage_access(struct pt_regs *regs) { @@ -869,4 +884,9 @@ void do_non_secure_storage_access(struct pt_regs *regs) { default_trap_handler(regs); } + +void do_secure_storage_violation(struct pt_regs *regs) +{ + default_trap_handler(regs); +} #endif diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 4b62d6b55024..1804230dd8d8 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -668,6 +668,10 @@ EXPORT_SYMBOL_GPL(zpci_enable_device); int zpci_disable_device(struct zpci_dev *zdev) { zpci_dma_exit_device(zdev); + /* + * The zPCI function may already be disabled by the platform, this is + * detected in clp_disable_fh() which becomes a no-op. + */ return clp_disable_fh(zdev); } EXPORT_SYMBOL_GPL(zpci_disable_device); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 9a3a291cad43..d9ae7456dd4c 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -143,6 +143,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) zpci_remove_device(zdev); } + zdev->fh = ccdf->fh; + zpci_disable_device(zdev); zdev->state = ZPCI_FN_STATE_STANDBY; if (!clp_get_state(ccdf->fid, &state) && state == ZPCI_FN_STATE_RESERVED) { diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h index 1a0d7cf71c10..100bf241340b 100644 --- a/arch/sh/include/asm/smp.h +++ b/arch/sh/include/asm/smp.h @@ -8,7 +8,6 @@ #ifdef CONFIG_SMP -#include <linux/spinlock.h> #include <linux/atomic.h> #include <asm/current.h> #include <asm/percpu.h> diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index ad963104d22d..91ab2607a1ff 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -370,7 +370,6 @@ syscall_trace_entry: nop cmp/eq #-1, r0 bt syscall_exit - mov.l r0, @(OFF_R0,r15) ! Save return value ! Reload R0-R4 from kernel stack, where the ! parent may have modified them using ! ptrace(POKEUSR). (Note that R0-R2 are diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index b05bf92f9c32..5281685f6ad1 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -455,16 +455,11 @@ long arch_ptrace(struct task_struct *child, long request, asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; - if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - /* - * Tracing decided this syscall should not happen. - * We'll return a bogus call number to get an ENOSYS - * error, but leave the original number in regs->regs[0]. - */ - ret = -1L; + tracehook_report_syscall_entry(regs)) { + regs->regs[0] = -ENOSYS; + return -1; + } if (secure_computing() == -1) return -1; @@ -475,7 +470,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) audit_syscall_entry(regs->regs[3], regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); - return ret ?: regs->regs[0]; + return 0; } asmlinkage void do_syscall_trace_leave(struct pt_regs *regs) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 3962f592633d..ff7894f39e0e 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -43,6 +43,8 @@ KBUILD_CFLAGS += -Wno-pointer-sign KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += -D__DISABLE_EXPORTS +# Disable relocation relaxation in case the link is not PIE. +KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index d7577fece9eb..78210793d357 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -19,6 +19,7 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +# CONFIG_64BIT is not set CONFIG_SMP=y CONFIG_X86_GENERIC=y CONFIG_HPET_TIMER=y @@ -186,7 +187,6 @@ CONFIG_DRM_I915=y CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index f85600143747..9936528e1939 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -181,7 +181,6 @@ CONFIG_DRM_I915=y CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 48512c7944e7..870efeec8bda 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -60,16 +60,10 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs) #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs) { - unsigned int nr = (unsigned int)regs->orig_ax; - if (IS_ENABLED(CONFIG_IA32_EMULATION)) current_thread_info()->status |= TS_COMPAT; - /* - * Subtlety here: if ptrace pokes something larger than 2^32-1 into - * orig_ax, the unsigned int return value truncates it. This may - * or may not be necessary, but it matches the old asm behavior. - */ - return (unsigned int)syscall_enter_from_user_mode(regs, nr); + + return (unsigned int)regs->orig_ax; } /* @@ -91,15 +85,29 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { unsigned int nr = syscall_32_enter(regs); + /* + * Subtlety here: if ptrace pokes something larger than 2^32-1 into + * orig_ax, the unsigned int return value truncates it. This may + * or may not be necessary, but it matches the old asm behavior. + */ + nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + do_syscall_32_irqs_on(regs, nr); syscall_exit_to_user_mode(regs); } static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) { - unsigned int nr = syscall_32_enter(regs); + unsigned int nr = syscall_32_enter(regs); int res; + /* + * This cannot use syscall_enter_from_user_mode() as it has to + * fetch EBP before invoking any of the syscall entry work + * functions. + */ + syscall_enter_from_user_mode_prepare(regs); + instrumentation_begin(); /* Fetch EBP from where the vDSO stashed it. */ if (IS_ENABLED(CONFIG_X86_64)) { @@ -122,6 +130,9 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) return false; } + /* The case truncates any ptrace induced syscall nr > 2^32 -1 */ + nr = (unsigned int)syscall_enter_from_user_mode_work(regs, nr); + /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); syscall_exit_to_user_mode(regs); @@ -288,7 +299,7 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs) old_regs = set_irq_regs(regs); instrumentation_begin(); - run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, NULL, regs); + run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs); instrumentation_begin(); set_irq_regs(old_regs); diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 70dea9337816..d977079a7d02 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -682,6 +682,8 @@ SYM_CODE_END(.Lbad_gs) * rdx: Function argument (can be NULL if none) */ SYM_FUNC_START(asm_call_on_stack) +SYM_INNER_LABEL(asm_call_sysvec_on_stack, SYM_L_GLOBAL) +SYM_INNER_LABEL(asm_call_irq_on_stack, SYM_L_GLOBAL) /* * Save the frame pointer unconditionally. This allows the ORC * unwinder to handle the stack switch. diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index ca0976456a6b..6d2df1ee427b 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -159,8 +159,6 @@ static inline u64 x86_default_get_root_pointer(void) extern int x86_acpi_numa_init(void); #endif /* CONFIG_ACPI_NUMA */ -#define acpi_unlazy_tlb(x) leave_mm(x) - #ifdef CONFIG_ACPI_APEI static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) { diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index a8f9315b9eae..6fe54b2813c1 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -18,8 +18,16 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) * state, not the interrupt state as imagined by Xen. */ unsigned long flags = native_save_fl(); - WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF | - X86_EFLAGS_NT)); + unsigned long mask = X86_EFLAGS_DF | X86_EFLAGS_NT; + + /* + * For !SMAP hardware we patch out CLAC on entry. + */ + if (boot_cpu_has(X86_FEATURE_SMAP) || + (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV))) + mask |= X86_EFLAGS_AC; + + WARN_ON_ONCE(flags & mask); /* We think we came from user mode. Make sure pt_regs agrees. */ WARN_ON_ONCE(!user_mode(regs)); diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h index 296b346184b2..fb42659f6e98 100644 --- a/arch/x86/include/asm/frame.h +++ b/arch/x86/include/asm/frame.h @@ -60,12 +60,26 @@ #define FRAME_END "pop %" _ASM_BP "\n" #ifdef CONFIG_X86_64 + #define ENCODE_FRAME_POINTER \ "lea 1(%rsp), %rbp\n\t" + +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs + 1; +} + #else /* !CONFIG_X86_64 */ + #define ENCODE_FRAME_POINTER \ "movl %esp, %ebp\n\t" \ "andl $0x7fffffff, %ebp\n\t" + +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs & 0x7fffffff; +} + #endif /* CONFIG_X86_64 */ #endif /* __ASSEMBLY__ */ @@ -83,6 +97,11 @@ #define ENCODE_FRAME_POINTER +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return 0; +} + #endif #define FRAME_BEGIN diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index a43366191212..a0638640f1ed 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -242,7 +242,7 @@ __visible noinstr void func(struct pt_regs *regs) \ instrumentation_begin(); \ irq_enter_rcu(); \ kvm_set_cpu_l1tf_flush_l1d(); \ - run_on_irqstack_cond(__##func, regs, regs); \ + run_sysvec_on_irqstack_cond(__##func, regs); \ irq_exit_rcu(); \ instrumentation_end(); \ irqentry_exit(regs, state); \ diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 4ae66f097101..775816965c6a 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -12,20 +12,50 @@ static __always_inline bool irqstack_active(void) return __this_cpu_read(irq_count) != -1; } -void asm_call_on_stack(void *sp, void *func, void *arg); +void asm_call_on_stack(void *sp, void (*func)(void), void *arg); +void asm_call_sysvec_on_stack(void *sp, void (*func)(struct pt_regs *regs), + struct pt_regs *regs); +void asm_call_irq_on_stack(void *sp, void (*func)(struct irq_desc *desc), + struct irq_desc *desc); -static __always_inline void __run_on_irqstack(void *func, void *arg) +static __always_inline void __run_on_irqstack(void (*func)(void)) { void *tos = __this_cpu_read(hardirq_stack_ptr); __this_cpu_add(irq_count, 1); - asm_call_on_stack(tos - 8, func, arg); + asm_call_on_stack(tos - 8, func, NULL); + __this_cpu_sub(irq_count, 1); +} + +static __always_inline void +__run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs), + struct pt_regs *regs) +{ + void *tos = __this_cpu_read(hardirq_stack_ptr); + + __this_cpu_add(irq_count, 1); + asm_call_sysvec_on_stack(tos - 8, func, regs); + __this_cpu_sub(irq_count, 1); +} + +static __always_inline void +__run_irq_on_irqstack(void (*func)(struct irq_desc *desc), + struct irq_desc *desc) +{ + void *tos = __this_cpu_read(hardirq_stack_ptr); + + __this_cpu_add(irq_count, 1); + asm_call_irq_on_stack(tos - 8, func, desc); __this_cpu_sub(irq_count, 1); } #else /* CONFIG_X86_64 */ static inline bool irqstack_active(void) { return false; } -static inline void __run_on_irqstack(void *func, void *arg) { } +static inline void __run_on_irqstack(void (*func)(void)) { } +static inline void __run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs), + struct pt_regs *regs) { } +static inline void __run_irq_on_irqstack(void (*func)(struct irq_desc *desc), + struct irq_desc *desc) { } #endif /* !CONFIG_X86_64 */ static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs) @@ -37,17 +67,40 @@ static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs) return !user_mode(regs) && !irqstack_active(); } -static __always_inline void run_on_irqstack_cond(void *func, void *arg, + +static __always_inline void run_on_irqstack_cond(void (*func)(void), struct pt_regs *regs) { - void (*__func)(void *arg) = func; + lockdep_assert_irqs_disabled(); + + if (irq_needs_irq_stack(regs)) + __run_on_irqstack(func); + else + func(); +} + +static __always_inline void +run_sysvec_on_irqstack_cond(void (*func)(struct pt_regs *regs), + struct pt_regs *regs) +{ + lockdep_assert_irqs_disabled(); + if (irq_needs_irq_stack(regs)) + __run_sysvec_on_irqstack(func, regs); + else + func(regs); +} + +static __always_inline void +run_irq_on_irqstack_cond(void (*func)(struct irq_desc *desc), struct irq_desc *desc, + struct pt_regs *regs) +{ lockdep_assert_irqs_disabled(); if (irq_needs_irq_stack(regs)) - __run_on_irqstack(__func, arg); + __run_irq_on_irqstack(func, desc); else - __func(arg); + func(desc); } #endif diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 40aa69d04862..d8324a236696 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -327,8 +327,8 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, static const unsigned int argument_offs[] = { #ifdef __i386__ offsetof(struct pt_regs, ax), - offsetof(struct pt_regs, cx), offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, cx), #define NR_REG_ARGUMENTS 3 #else offsetof(struct pt_regs, di), diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 779a89e31c4c..21f9c7f11779 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2243,6 +2243,7 @@ static inline void __init check_timer(void) legacy_pic->init(0); legacy_pic->make_irq(0); apic_write(APIC_LVT0, APIC_DM_EXTINT); + legacy_pic->unmask(0); unlock_ExtINT_logic(); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index f43a78bde670..fc4f8c04bdb5 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1904,6 +1904,8 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check; static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) { + bool irq_state; + WARN_ON_ONCE(user_mode(regs)); /* @@ -1914,7 +1916,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) mce_check_crashing_cpu()) return; - nmi_enter(); + irq_state = idtentry_enter_nmi(regs); /* * The call targets are marked noinstr, but objtool can't figure * that out because it's an indirect call. Annotate it. @@ -1925,7 +1927,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) if (regs->flags & X86_EFLAGS_IF) trace_hardirqs_on_prepare(); instrumentation_end(); - nmi_exit(); + idtentry_exit_nmi(regs, irq_state); } static __always_inline void exc_machine_check_user(struct pt_regs *regs) diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 181060247e3c..c5dd50369e2f 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -227,7 +227,7 @@ static __always_inline void handle_irq(struct irq_desc *desc, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_X86_64)) - run_on_irqstack_cond(desc->handle_irq, desc, regs); + run_irq_on_irqstack_cond(desc->handle_irq, desc, regs); else __handle_irq(desc, regs); } diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 1b4fe93a86c5..440eed558558 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -74,5 +74,5 @@ int irq_init_percpu_irqstack(unsigned int cpu) void do_softirq_own_stack(void) { - run_on_irqstack_cond(__do_softirq, NULL, NULL); + run_on_irqstack_cond(__do_softirq, NULL); } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 08320b0b2b27..9663ba31347c 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -270,9 +270,8 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt) { struct pt_regs *old_regs = set_irq_regs(regs); u32 token; - irqentry_state_t state; - state = irqentry_enter(regs); + ack_APIC_irq(); inc_irq_stat(irq_hv_callback_count); @@ -283,7 +282,6 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt) wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1); } - irqentry_exit(regs, state); set_irq_regs(old_regs); } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 13ce616cc7af..ba4593a913fa 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -42,6 +42,7 @@ #include <asm/spec-ctrl.h> #include <asm/io_bitmap.h> #include <asm/proto.h> +#include <asm/frame.h> #include "process.h" @@ -133,7 +134,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, fork_frame = container_of(childregs, struct fork_frame, regs); frame = &fork_frame->frame; - frame->bp = 0; + frame->bp = encode_frame_pointer(childregs); frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap = NULL; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1f66d2d1e998..81a2fb711091 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -729,20 +729,9 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) #endif } -static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7) +static __always_inline unsigned long debug_read_clear_dr6(void) { - /* - * Disable breakpoints during exception handling; recursive exceptions - * are exceedingly 'fun'. - * - * Since this function is NOKPROBE, and that also applies to - * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a - * HW_BREAKPOINT_W on our stack) - * - * Entry text is excluded for HW_BP_X and cpu_entry_area, which - * includes the entry stack is excluded for everything. - */ - *dr7 = local_db_save(); + unsigned long dr6; /* * The Intel SDM says: @@ -755,15 +744,12 @@ static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7) * * Keep it simple: clear DR6 immediately. */ - get_debugreg(*dr6, 6); + get_debugreg(dr6, 6); set_debugreg(0, 6); /* Filter out all the reserved bits which are preset to 1 */ - *dr6 &= ~DR6_RESERVED; -} + dr6 &= ~DR6_RESERVED; -static __always_inline void debug_exit(unsigned long dr7) -{ - local_db_restore(dr7); + return dr6; } /* @@ -863,6 +849,18 @@ out: static __always_inline void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6) { + /* + * Disable breakpoints during exception handling; recursive exceptions + * are exceedingly 'fun'. + * + * Since this function is NOKPROBE, and that also applies to + * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a + * HW_BREAKPOINT_W on our stack) + * + * Entry text is excluded for HW_BP_X and cpu_entry_area, which + * includes the entry stack is excluded for everything. + */ + unsigned long dr7 = local_db_save(); bool irq_state = idtentry_enter_nmi(regs); instrumentation_begin(); @@ -883,6 +881,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, instrumentation_end(); idtentry_exit_nmi(regs, irq_state); + + local_db_restore(dr7); } static __always_inline void exc_debug_user(struct pt_regs *regs, @@ -894,6 +894,15 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, */ WARN_ON_ONCE(!user_mode(regs)); + /* + * NB: We can't easily clear DR7 here because + * idtentry_exit_to_usermode() can invoke ptrace, schedule, access + * user memory, etc. This means that a recursive #DB is possible. If + * this happens, that #DB will hit exc_debug_kernel() and clear DR7. + * Since we're not on the IST stack right now, everything will be + * fine. + */ + irqentry_enter_from_user_mode(regs); instrumentation_begin(); @@ -907,36 +916,24 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, /* IST stack entry */ DEFINE_IDTENTRY_DEBUG(exc_debug) { - unsigned long dr6, dr7; - - debug_enter(&dr6, &dr7); - exc_debug_kernel(regs, dr6); - debug_exit(dr7); + exc_debug_kernel(regs, debug_read_clear_dr6()); } /* User entry, runs on regular task stack */ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) { - unsigned long dr6, dr7; - - debug_enter(&dr6, &dr7); - exc_debug_user(regs, dr6); - debug_exit(dr7); + exc_debug_user(regs, debug_read_clear_dr6()); } #else /* 32 bit does not have separate entry points. */ DEFINE_IDTENTRY_RAW(exc_debug) { - unsigned long dr6, dr7; - - debug_enter(&dr6, &dr7); + unsigned long dr6 = debug_read_clear_dr6(); if (user_mode(regs)) exc_debug_user(regs, dr6); else exc_debug_kernel(regs, dr6); - - debug_exit(dr7); } #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5299ef5ff18d..2f6510de6b0c 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2505,9 +2505,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4); val = GET_SMSTATE(u32, smstate, 0x7fcc); - ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + + if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1)) + return X86EMUL_UNHANDLEABLE; + val = GET_SMSTATE(u32, smstate, 0x7fc8); - ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1)) + return X86EMUL_UNHANDLEABLE; selector = GET_SMSTATE(u32, smstate, 0x7fc4); set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64)); @@ -2560,16 +2565,23 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED; val = GET_SMSTATE(u32, smstate, 0x7f68); - ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + + if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1)) + return X86EMUL_UNHANDLEABLE; + val = GET_SMSTATE(u32, smstate, 0x7f60); - ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1)) + return X86EMUL_UNHANDLEABLE; cr0 = GET_SMSTATE(u64, smstate, 0x7f58); cr3 = GET_SMSTATE(u64, smstate, 0x7f50); cr4 = GET_SMSTATE(u64, smstate, 0x7f48); ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00)); val = GET_SMSTATE(u64, smstate, 0x7ed0); - ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA); + + if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA)) + return X86EMUL_UNHANDLEABLE; selector = GET_SMSTATE(u32, smstate, 0x7e90); rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 43fdb0c12a5d..71aa3da2a0b7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2469,7 +2469,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, } if (sp->unsync_children) - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); __clear_sp_write_flooding_count(sp); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index fb68467e6049..e90bc436f584 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -586,7 +586,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE; /* Give the current vmcb to the guest */ - svm_set_gif(svm, false); nested_vmcb->save.es = vmcb->save.es; nested_vmcb->save.cs = vmcb->save.cs; @@ -632,6 +631,9 @@ int nested_svm_vmexit(struct vcpu_svm *svm) /* Restore the original control entries */ copy_vmcb_control_area(&vmcb->control, &hsave->control); + /* On vmexit the GIF is set to false */ + svm_set_gif(svm, false); + svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset = svm->vcpu.arch.l1_tsc_offset; @@ -1132,6 +1134,9 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, load_nested_vmcb_control(svm, &ctl); nested_prepare_vmcb_control(svm); + if (!nested_svm_vmrun_msrpm(svm)) + return -EINVAL; + out_set_gif: svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); return 0; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 402dc4234e39..7bf7bf734979 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1106,6 +1106,7 @@ void sev_vm_destroy(struct kvm *kvm) list_for_each_safe(pos, q, head) { __unregister_enc_region_locked(kvm, list_entry(pos, struct enc_region, list)); + cond_resched(); } } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 0194336b64a4..91ea74ae71b8 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2183,6 +2183,12 @@ static int iret_interception(struct vcpu_svm *svm) return 1; } +static int invd_interception(struct vcpu_svm *svm) +{ + /* Treat an INVD instruction as a NOP and just skip it. */ + return kvm_skip_emulated_instruction(&svm->vcpu); +} + static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) @@ -2774,7 +2780,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, - [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_INVD] = invd_interception, [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, @@ -2938,8 +2944,6 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (npt_enabled) vcpu->arch.cr3 = svm->vmcb->save.cr3; - svm_complete_interrupts(svm); - if (is_guest_mode(vcpu)) { int vmexit; @@ -3504,7 +3508,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) stgi(); /* Any pending NMI will happen here */ - exit_fastpath = svm_exit_handlers_fastpath(vcpu); if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_after_interrupt(&svm->vcpu); @@ -3518,6 +3521,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) } svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; + vmcb_mark_all_clean(svm->vmcb); /* if exit due to PF check for async PF */ if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) @@ -3537,7 +3541,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) SVM_EXIT_EXCP_BASE + MC_VECTOR)) svm_handle_mce(svm); - vmcb_mark_all_clean(svm->vmcb); + svm_complete_interrupts(svm); + exit_fastpath = svm_exit_handlers_fastpath(vcpu); return exit_fastpath; } @@ -3900,21 +3905,28 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *nested_vmcb; struct kvm_host_map map; - u64 guest; - u64 vmcb; int ret = 0; - guest = GET_SMSTATE(u64, smstate, 0x7ed8); - vmcb = GET_SMSTATE(u64, smstate, 0x7ee0); + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); + u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); + u64 vmcb = GET_SMSTATE(u64, smstate, 0x7ee0); - if (guest) { - if (kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb), &map) == -EINVAL) - return 1; - nested_vmcb = map.hva; - ret = enter_svm_guest_mode(svm, vmcb, nested_vmcb); - kvm_vcpu_unmap(&svm->vcpu, &map, true); + if (guest) { + if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + return 1; + + if (!(saved_efer & EFER_SVME)) + return 1; + + if (kvm_vcpu_map(&svm->vcpu, + gpa_to_gfn(vmcb), &map) == -EINVAL) + return 1; + + ret = enter_svm_guest_mode(svm, vmcb, map.hva); + kvm_vcpu_unmap(&svm->vcpu, &map, true); + } } return ret; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 23b58c28a1c9..1bb6b31eb646 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4404,6 +4404,14 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); + /* + * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between + * now and the new vmentry. Ensure that the VMCS02 PDPTR fields are + * up-to-date before switching to L1. + */ + if (enable_ept && is_pae_paging(vcpu)) + vmx_ept_load_pdptrs(vcpu); + leave_guest_mode(vcpu); if (nested_cpu_has_preemption_timer(vmcs12)) @@ -4668,7 +4676,7 @@ void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu) vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; vmx->nested.msrs.exit_ctls_high &= - ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; } } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 819c185adf09..96979c09ebd1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -129,6 +129,9 @@ static bool __read_mostly enable_preemption_timer = 1; module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #endif +extern bool __read_mostly allow_smaller_maxphyaddr; +module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); + #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE #define KVM_VM_CR0_ALWAYS_ON \ @@ -791,6 +794,18 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu) */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; + else { + /* + * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched + * between guest and host. In that case we only care about present + * faults. For vmcs02, however, PFEC_MASK and PFEC_MATCH are set in + * prepare_vmcs02_rare. + */ + bool selective_pf_trap = enable_ept && (eb & (1u << PF_VECTOR)); + int mask = selective_pf_trap ? PFERR_PRESENT_MASK : 0; + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, mask); + } vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -2971,7 +2986,7 @@ static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) vpid_sync_context(to_vmx(vcpu)->vpid); } -static void ept_load_pdptrs(struct kvm_vcpu *vcpu) +void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; @@ -3114,7 +3129,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd, guest_cr3 = vcpu->arch.cr3; else /* vmcs01.GUEST_CR3 is already up-to-date. */ update_guest_cr3 = false; - ept_load_pdptrs(vcpu); + vmx_ept_load_pdptrs(vcpu); } else { guest_cr3 = pgd; } @@ -4352,16 +4367,6 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmx->pt_desc.guest.output_mask = 0x7F; vmcs_write64(GUEST_IA32_RTIT_CTL, 0); } - - /* - * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched - * between guest and host. In that case we only care about present - * faults. - */ - if (enable_ept) { - vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, PFERR_PRESENT_MASK); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, PFERR_PRESENT_MASK); - } } static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -4803,6 +4808,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) * EPT will cause page fault only if we need to * detect illegal GPAs. */ + WARN_ON_ONCE(!allow_smaller_maxphyaddr); kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code); return 1; } else @@ -5331,7 +5337,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ - if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa))) + if (unlikely(allow_smaller_maxphyaddr && kvm_mmu_is_illegal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -6054,6 +6060,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) (exit_reason != EXIT_REASON_EXCEPTION_NMI && exit_reason != EXIT_REASON_EPT_VIOLATION && exit_reason != EXIT_REASON_PML_FULL && + exit_reason != EXIT_REASON_APIC_ACCESS && exit_reason != EXIT_REASON_TASK_SWITCH)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; @@ -8304,11 +8311,12 @@ static int __init vmx_init(void) vmx_check_vmcs12_offsets(); /* - * Intel processors don't have problems with - * GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable - * it for VMX by default + * Shadow paging doesn't have a (further) performance penalty + * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it + * by default */ - allow_smaller_maxphyaddr = true; + if (!enable_ept) + allow_smaller_maxphyaddr = true; return 0; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 26175a4759fa..a0e47720f60c 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -356,6 +356,7 @@ void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); int vmx_find_msr_index(struct vmx_msrs *m, u32 msr); int vmx_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e); +void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); #define POSTED_INTR_ON 0 #define POSTED_INTR_SN 1 @@ -551,7 +552,10 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) { - return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; + if (!enable_ept) + return true; + + return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; } void dump_vmcs(void); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d39d6cf1d473..ce856e0ece84 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -188,7 +188,7 @@ static struct kvm_shared_msrs __percpu *shared_msrs; u64 __read_mostly host_efer; EXPORT_SYMBOL_GPL(host_efer); -bool __read_mostly allow_smaller_maxphyaddr; +bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); static u64 __read_mostly host_xss; @@ -976,6 +976,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP; + unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -1003,7 +1004,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (kvm_x86_ops.set_cr4(vcpu, cr4)) return 1; - if (((cr4 ^ old_cr4) & pdptr_bits) || + if (((cr4 ^ old_cr4) & mmu_role_bits) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); @@ -2731,7 +2732,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 1; if (!lapic_in_kernel(vcpu)) - return 1; + return data ? 1 : 0; vcpu->arch.apf.msr_en_val = data; @@ -3221,9 +3222,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_POWER_CTL: msr_info->data = vcpu->arch.msr_ia32_power_ctl; break; - case MSR_IA32_TSC: - msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; + case MSR_IA32_TSC: { + /* + * Intel SDM states that MSR_IA32_TSC read adds the TSC offset + * even when not intercepted. AMD manual doesn't explicitly + * state this but appears to behave the same. + * + * On userspace reads and writes, however, we unconditionally + * operate L1's TSC value to ensure backwards-compatible + * behavior for migration. + */ + u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset : + vcpu->arch.tsc_offset; + + msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset; break; + } case MSR_MTRRcap: case 0x200 ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); @@ -3578,6 +3592,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SMALLER_MAXPHYADDR: r = (int) allow_smaller_maxphyaddr; break; + case KVM_CAP_STEAL_TIME: + r = sched_info_on(); + break; default: break; } diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index d46fff11f06f..aa067859a70b 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -24,7 +24,7 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_cmdline.o = -pg endif -CFLAGS_cmdline.o := -fno-stack-protector +CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables endif inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index b0dfac3d3df7..1847e993ac63 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size) */ if (size < 8) { if (!IS_ALIGNED(dest, 4) || size != 4) - clean_cache_range(dst, 1); + clean_cache_range(dst, size); } else { if (!IS_ALIGNED(dest, 8)) { dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 35f1498e9832..6e3e8a124903 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -190,6 +190,53 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) return pmd_k; } +/* + * Handle a fault on the vmalloc or module mapping area + * + * This is needed because there is a race condition between the time + * when the vmalloc mapping code updates the PMD to the point in time + * where it synchronizes this update with the other page-tables in the + * system. + * + * In this race window another thread/CPU can map an area on the same + * PMD, finds it already present and does not synchronize it with the + * rest of the system yet. As a result v[mz]alloc might return areas + * which are not mapped in every page-table in the system, causing an + * unhandled page-fault when they are accessed. + */ +static noinline int vmalloc_fault(unsigned long address) +{ + unsigned long pgd_paddr; + pmd_t *pmd_k; + pte_t *pte_k; + + /* Make sure we are in vmalloc area: */ + if (!(address >= VMALLOC_START && address < VMALLOC_END)) + return -1; + + /* + * Synchronize this task's top level page-table + * with the 'reference' page table. + * + * Do _not_ use "current" here. We might be inside + * an interrupt in the middle of a task switch.. + */ + pgd_paddr = read_cr3_pa(); + pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); + if (!pmd_k) + return -1; + + if (pmd_large(*pmd_k)) + return 0; + + pte_k = pte_offset_kernel(pmd_k, address); + if (!pte_present(*pte_k)) + return -1; + + return 0; +} +NOKPROBE_SYMBOL(vmalloc_fault); + void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; @@ -1110,6 +1157,37 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, */ WARN_ON_ONCE(hw_error_code & X86_PF_PK); +#ifdef CONFIG_X86_32 + /* + * We can fault-in kernel-space virtual memory on-demand. The + * 'reference' page table is init_mm.pgd. + * + * NOTE! We MUST NOT take any locks for this case. We may + * be in an interrupt or a critical region, and should + * only copy the information from the master page table, + * nothing more. + * + * Before doing this on-demand faulting, ensure that the + * fault is not any of the following: + * 1. A fault on a PTE with a reserved bit set. + * 2. A fault caused by a user-mode access. (Do not demand- + * fault kernel memory due to user-mode accesses). + * 3. A fault caused by a page-level protection violation. + * (A demand fault would be on a non-present page which + * would have X86_PF_PROT==0). + * + * This is only needed to close a race condition on x86-32 in + * the vmalloc mapping/unmapping code. See the comment above + * vmalloc_fault() for details. On x86-64 the race does not + * exist as the vmalloc mappings don't need to be synchronized + * there. + */ + if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { + if (vmalloc_fault(address) >= 0) + return; + } +#endif + /* Was the fault spurious, caused by lazy TLB invalidation? */ if (spurious_kernel_fault(hw_error_code, address)) return; diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index c5174b4e318b..683cd12f4793 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -321,7 +321,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, u64 addr, u64 max_addr, u64 size) { return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, - 0, NULL, NUMA_NO_NODE); + 0, NULL, 0); } static int __init setup_emu2phys_nid(int *dfl_phys_nid) |