diff options
| author | Thomas Gleixner <tglx@linutronix.de> | 2020-12-15 10:48:07 +0100 |
|---|---|---|
| committer | Thomas Gleixner <tglx@linutronix.de> | 2020-12-15 10:48:07 +0100 |
| commit | 3c41e57a1e168d879e923c5583adeae47eec9f64 (patch) | |
| tree | e6272012c4b766189be2821316a3d23d115f5195 /arch | |
| parent | d14ce74f1fb376ccbbc0b05ded477ada51253729 (diff) | |
| parent | 2f5fbc4305d07725bfebaedb09e57271315691ef (diff) | |
| download | linux-3c41e57a1e168d879e923c5583adeae47eec9f64.tar.bz2 | |
Merge tag 'irqchip-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core
Pull irqchip updates for 5.11 from Marc Zyngier:
- Preliminary support for managed interrupts on platform devices
- Correctly identify allocation of MSIs proxyied by another device
- Remove the fasteoi IPI flow which has been proved useless
- Generalise the Ocelot support to new SoCs
- Improve GICv4.1 vcpu entry, matching the corresponding KVM optimisation
- Work around spurious interrupts on Qualcomm PDC
- Random fixes and cleanups
Link: https://lore.kernel.org/r/20201212135626.1479884-1-maz@kernel.org
Diffstat (limited to 'arch')
239 files changed, 1779 insertions, 1106 deletions
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 7462a7911002..4c7b0414a3ff 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -57,7 +57,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { wtint(0); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_dead(void) diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index c6606f4d20d6..fb98440c0bd4 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -243,10 +243,8 @@ static inline int constant_fls(unsigned int x) x <<= 2; r -= 2; } - if (!(x & 0x80000000u)) { - x <<= 1; + if (!(x & 0x80000000u)) r -= 1; - } return r; } diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index f1ed17edb085..163641726a2b 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -134,8 +134,10 @@ #ifdef CONFIG_ARC_HAS_PAE40 #define PTE_BITS_NON_RWX_IN_PD1 (0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 #else #define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /************************************************************************** diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 17fd1ed700cc..9152782444b5 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -67,7 +67,22 @@ sr r5, [ARC_REG_LPB_CTRL] 1: #endif /* CONFIG_ARC_LPB_DISABLE */ -#endif + + /* On HSDK, CCMs need to remapped super early */ +#ifdef CONFIG_ARC_SOC_HSDK + mov r6, 0x60000000 + lr r5, [ARC_REG_ICCM_BUILD] + breq r5, 0, 1f + sr r6, [ARC_REG_AUX_ICCM] +1: + lr r5, [ARC_REG_DCCM_BUILD] + breq r5, 0, 2f + sr r6, [ARC_REG_AUX_DCCM] +2: +#endif /* CONFIG_ARC_SOC_HSDK */ + +#endif /* CONFIG_ISA_ARCV2 */ + ; Config DSP_CTRL properly, so kernel may use integer multiply, ; multiply-accumulate, and divide operations DSP_EARLY_INIT diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index feba91c9d969..f73da203b170 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -38,15 +38,27 @@ #ifdef CONFIG_ARC_DW2_UNWIND -static void seed_unwind_frame_info(struct task_struct *tsk, - struct pt_regs *regs, - struct unwind_frame_info *frame_info) +static int +seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, + struct unwind_frame_info *frame_info) { - /* - * synchronous unwinding (e.g. dump_stack) - * - uses current values of SP and friends - */ - if (tsk == NULL && regs == NULL) { + if (regs) { + /* + * Asynchronous unwinding of intr/exception + * - Just uses the pt_regs passed + */ + frame_info->task = tsk; + + frame_info->regs.r27 = regs->fp; + frame_info->regs.r28 = regs->sp; + frame_info->regs.r31 = regs->blink; + frame_info->regs.r63 = regs->ret; + frame_info->call_frame = 0; + } else if (tsk == NULL || tsk == current) { + /* + * synchronous unwinding (e.g. dump_stack) + * - uses current values of SP and friends + */ unsigned long fp, sp, blink, ret; frame_info->task = current; @@ -63,13 +75,17 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r31 = blink; frame_info->regs.r63 = ret; frame_info->call_frame = 0; - } else if (regs == NULL) { + } else { /* - * Asynchronous unwinding of sleeping task - * - Gets SP etc from task's pt_regs (saved bottom of kernel - * mode stack of task) + * Asynchronous unwinding of a likely sleeping task + * - first ensure it is actually sleeping + * - if so, it will be in __switch_to, kernel mode SP of task + * is safe-kept and BLINK at a well known location in there */ + if (tsk->state == TASK_RUNNING) + return -1; + frame_info->task = tsk; frame_info->regs.r27 = TSK_K_FP(tsk); @@ -90,19 +106,8 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r28 += 60; frame_info->call_frame = 0; - } else { - /* - * Asynchronous unwinding of intr/exception - * - Just uses the pt_regs passed - */ - frame_info->task = tsk; - - frame_info->regs.r27 = regs->fp; - frame_info->regs.r28 = regs->sp; - frame_info->regs.r31 = regs->blink; - frame_info->regs.r63 = regs->ret; - frame_info->call_frame = 0; } + return 0; } #endif @@ -112,11 +117,12 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, int (*consumer_fn) (unsigned int, void *), void *arg) { #ifdef CONFIG_ARC_DW2_UNWIND - int ret = 0; + int ret = 0, cnt = 0; unsigned int address; struct unwind_frame_info frame_info; - seed_unwind_frame_info(tsk, regs, &frame_info); + if (seed_unwind_frame_info(tsk, regs, &frame_info)) + return 0; while (1) { address = UNW_PC(&frame_info); @@ -132,6 +138,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, break; frame_info.regs.r63 = frame_info.regs.r31; + + if (cnt++ > 128) { + printk("unwinder looping too long, aborting !\n"); + return 0; + } } return address; /* return the last address it saw */ diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index c340acd989a0..9bb3c24f3677 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -30,14 +30,14 @@ * -Changes related to MMU v2 (Rel 4.8) * * Vineetg: Aug 29th 2008 - * -In TLB Flush operations (Metal Fix MMU) there is a explict command to + * -In TLB Flush operations (Metal Fix MMU) there is a explicit command to * flush Micro-TLBS. If TLB Index Reg is invalid prior to TLBIVUTLB cmd, * it fails. Thus need to load it with ANY valid value before invoking * TLBIVUTLB cmd * * Vineetg: Aug 21th 2008: * -Reduced the duration of IRQ lockouts in TLB Flush routines - * -Multiple copies of TLB erase code seperated into a "single" function + * -Multiple copies of TLB erase code separated into a "single" function * -In TLB Flush routines, interrupt disabling moved UP to retrieve ASID * in interrupt-safe region. * @@ -66,7 +66,7 @@ * * Although J-TLB is 2 way set assoc, ARC700 caches J-TLB into uTLBS which has * much higher associativity. u-D-TLB is 8 ways, u-I-TLB is 4 ways. - * Given this, the thrasing problem should never happen because once the 3 + * Given this, the thrashing problem should never happen because once the 3 * J-TLB entries are created (even though 3rd will knock out one of the prev * two), the u-D-TLB and u-I-TLB will have what is required to accomplish memcpy * @@ -127,7 +127,7 @@ static void utlb_invalidate(void) * There was however an obscure hardware bug, where uTLB flush would * fail when a prior probe for J-TLB (both totally unrelated) would * return lkup err - because the entry didn't exist in MMU. - * The Workround was to set Index reg with some valid value, prior to + * The Workaround was to set Index reg with some valid value, prior to * flush. This was fixed in MMU v3 */ unsigned int idx; @@ -272,7 +272,7 @@ noinline void local_flush_tlb_all(void) } /* - * Flush the entrie MM for userland. The fastest way is to move to Next ASID + * Flush the entire MM for userland. The fastest way is to move to Next ASID */ noinline void local_flush_tlb_mm(struct mm_struct *mm) { @@ -303,7 +303,7 @@ noinline void local_flush_tlb_mm(struct mm_struct *mm) * Difference between this and Kernel Range Flush is * -Here the fastest way (if range is too large) is to move to next ASID * without doing any explicit Shootdown - * -In case of kernel Flush, entry has to be shot down explictly + * -In case of kernel Flush, entry has to be shot down explicitly */ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) @@ -620,7 +620,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, * Super Page size is configurable in hardware (4K to 16M), but fixed once * RTL builds. * - * The exact THP size a Linx configuration will support is a function of: + * The exact THP size a Linux configuration will support is a function of: * - MMU page size (typical 8K, RTL fixed) * - software page walker address split between PGD:PTE:PFN (typical * 11:8:13, but can be changed with 1 line) @@ -698,7 +698,7 @@ void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, #endif -/* Read the Cache Build Confuration Registers, Decode them and save into +/* Read the Cache Build Configuration Registers, Decode them and save into * the cpuinfo structure for later use. * No Validation is done here, simply read/convert the BCRs */ @@ -803,13 +803,13 @@ void arc_mmu_init(void) pr_info("%s", arc_mmu_mumbojumbo(0, str, sizeof(str))); /* - * Can't be done in processor.h due to header include depenedencies + * Can't be done in processor.h due to header include dependencies */ BUILD_BUG_ON(!IS_ALIGNED((CONFIG_ARC_KVADDR_SIZE << 20), PMD_SIZE)); /* * stack top size sanity check, - * Can't be done in processor.h due to header include depenedencies + * Can't be done in processor.h due to header include dependencies */ BUILD_BUG_ON(!IS_ALIGNED(STACK_TOP, PMD_SIZE)); @@ -881,7 +881,7 @@ void arc_mmu_init(void) * the duplicate one. * -Knob to be verbose abt it.(TODO: hook them up to debugfs) */ -volatile int dup_pd_silent; /* Be slient abt it or complain (default) */ +volatile int dup_pd_silent; /* Be silent abt it or complain (default) */ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, struct pt_regs *regs) @@ -948,7 +948,7 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, /*********************************************************************** * Diagnostic Routines - * -Called from Low Level TLB Hanlders if things don;t look good + * -Called from Low Level TLB Handlers if things don;t look good **********************************************************************/ #ifdef CONFIG_ARC_DBG_TLB_PARANOIA diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 0b63fc095b99..b3ea1fa11f87 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -17,22 +17,6 @@ int arc_hsdk_axi_dmac_coherent __section(".data") = 0; #define ARC_CCM_UNUSED_ADDR 0x60000000 -static void __init hsdk_init_per_cpu(unsigned int cpu) -{ - /* - * By default ICCM is mapped to 0x7z while this area is used for - * kernel virtual mappings, so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].iccm.sz) - write_aux_reg(ARC_REG_AUX_ICCM, ARC_CCM_UNUSED_ADDR); - - /* - * By default DCCM is mapped to 0x8z while this area is used by kernel, - * so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].dccm.sz) - write_aux_reg(ARC_REG_AUX_DCCM, ARC_CCM_UNUSED_ADDR); -} #define ARC_PERIPHERAL_BASE 0xf0000000 #define CREG_BASE (ARC_PERIPHERAL_BASE + 0x1000) @@ -339,5 +323,4 @@ static const char *hsdk_compat[] __initconst = { MACHINE_START(SIMULATION, "hsdk") .dt_compat = hsdk_compat, .init_early = hsdk_init_early, - .init_per_cpu = hsdk_init_per_cpu, MACHINE_END diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 2e04ec5b5446..caa27322a0ab 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1472,6 +1472,9 @@ ENTRY(efi_enter_kernel) @ issued from HYP mode take us to the correct handler code. We @ will disable the MMU before jumping to the kernel proper. @ + ARM( bic r1, r1, #(1 << 30) ) @ clear HSCTLR.TE + THUMB( orr r1, r1, #(1 << 30) ) @ set HSCTLR.TE + mcr p15, 4, r1, c1, c0, 0 adr r0, __hyp_reentry_vectors mcr p15, 4, r0, c12, c0, 0 @ set HYP vector base (HVBAR) isb diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi index c220dc3c4e0f..243e35f7a56c 100644 --- a/arch/arm/boot/dts/am437x-l4.dtsi +++ b/arch/arm/boot/dts/am437x-l4.dtsi @@ -521,7 +521,7 @@ ranges = <0x0 0x100000 0x8000>; mac_sw: switch@0 { - compatible = "ti,am4372-cpsw","ti,cpsw-switch"; + compatible = "ti,am4372-cpsw-switch", "ti,cpsw-switch"; reg = <0x0 0x4000>; ranges = <0 0 0x4000>; clocks = <&cpsw_125mhz_gclk>, <&dpll_clksel_mac_clk>; diff --git a/arch/arm/boot/dts/dra76x.dtsi b/arch/arm/boot/dts/dra76x.dtsi index b69c7d40f5d8..2f326151116b 100644 --- a/arch/arm/boot/dts/dra76x.dtsi +++ b/arch/arm/boot/dts/dra76x.dtsi @@ -32,8 +32,8 @@ interrupts = <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "int0", "int1"; - clocks = <&mcan_clk>, <&l3_iclk_div>; - clock-names = "cclk", "hclk"; + clocks = <&l3_iclk_div>, <&mcan_clk>; + clock-names = "hclk", "cclk"; bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; }; }; diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi index ab291cec650a..2983e91bc7dd 100644 --- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi +++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi @@ -122,7 +122,6 @@ }; &clock { - clocks = <&clock CLK_XUSBXTI>; assigned-clocks = <&clock CLK_FOUT_EPLL>; assigned-clock-rates = <45158401>; }; diff --git a/arch/arm/boot/dts/imx50-evk.dts b/arch/arm/boot/dts/imx50-evk.dts index 878e89c20190..4ea5c23f181b 100644 --- a/arch/arm/boot/dts/imx50-evk.dts +++ b/arch/arm/boot/dts/imx50-evk.dts @@ -59,7 +59,7 @@ MX50_PAD_CSPI_MISO__CSPI_MISO 0x00 MX50_PAD_CSPI_MOSI__CSPI_MOSI 0x00 MX50_PAD_CSPI_SS0__GPIO4_11 0xc4 - MX50_PAD_ECSPI1_MOSI__CSPI_SS1 0xf4 + MX50_PAD_ECSPI1_MOSI__GPIO4_13 0x84 >; }; diff --git a/arch/arm/boot/dts/imx6q-prti6q.dts b/arch/arm/boot/dts/imx6q-prti6q.dts index d112b50f8c5d..b4605edfd2ab 100644 --- a/arch/arm/boot/dts/imx6q-prti6q.dts +++ b/arch/arm/boot/dts/imx6q-prti6q.dts @@ -213,8 +213,8 @@ #size-cells = <0>; /* Microchip KSZ9031RNX PHY */ - rgmii_phy: ethernet-phy@4 { - reg = <4>; + rgmii_phy: ethernet-phy@0 { + reg = <0>; interrupts-extended = <&gpio1 28 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; diff --git a/arch/arm/boot/dts/imx6qdl-udoo.dtsi b/arch/arm/boot/dts/imx6qdl-udoo.dtsi index 828dd20cd27d..d07d8f83456d 100644 --- a/arch/arm/boot/dts/imx6qdl-udoo.dtsi +++ b/arch/arm/boot/dts/imx6qdl-udoo.dtsi @@ -98,7 +98,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi index 5dff24e39af8..8456f172d4b1 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi @@ -46,6 +46,16 @@ linux,code = <KEY_A>; gpios = <&gpiof 3 GPIO_ACTIVE_LOW>; }; + + /* + * The EXTi IRQ line 0 is shared with PMIC, + * so mark this as polled GPIO key. + */ + button-2 { + label = "TA3-GPIO-C"; + linux,code = <KEY_C>; + gpios = <&gpiog 0 GPIO_ACTIVE_LOW>; + }; }; gpio-keys { @@ -59,13 +69,6 @@ wakeup-source; }; - button-2 { - label = "TA3-GPIO-C"; - linux,code = <KEY_C>; - gpios = <&gpioi 11 GPIO_ACTIVE_LOW>; - wakeup-source; - }; - button-3 { label = "TA4-GPIO-D"; linux,code = <KEY_D>; @@ -79,7 +82,7 @@ led-0 { label = "green:led5"; - gpios = <&gpiog 2 GPIO_ACTIVE_HIGH>; + gpios = <&gpioc 6 GPIO_ACTIVE_HIGH>; default-state = "off"; }; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index b4b52cf634af..f796a6150313 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -68,6 +68,7 @@ gpio = <&gpiog 3 GPIO_ACTIVE_LOW>; regulator-always-on; regulator-boot-on; + vin-supply = <&vdd>; }; }; @@ -202,6 +203,7 @@ vdda: ldo1 { regulator-name = "vdda"; + regulator-always-on; regulator-min-microvolt = <2900000>; regulator-max-microvolt = <2900000>; interrupts = <IT_CURLIM_LDO1 0>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi index 04fbb324a541..803eb8bc9c85 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi @@ -21,6 +21,10 @@ }; }; +&dts { + status = "okay"; +}; + &i2c4 { pinctrl-names = "default"; pinctrl-0 = <&i2c4_pins_a>; diff --git a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts index 049e6ab3cf56..73de34ae37fd 100644 --- a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts +++ b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts @@ -154,7 +154,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts index 32d5d45a35c0..8945dbb114a2 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts @@ -130,7 +130,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_gmac_3v3>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts index 8c8dee6ea461..9109ca0919ad 100644 --- a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts +++ b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts @@ -151,7 +151,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts index 9d34eabba121..431f70234d36 100644 --- a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts +++ b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts @@ -131,7 +131,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_sw>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; allwinner,rx-delay-ps = <700>; allwinner,tx-delay-ps = <700>; status = "okay"; diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts index d9be511f054f..d8326a5c681d 100644 --- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts +++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts @@ -183,7 +183,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_dldo4>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts index 71fb73208939..babf4cf1b2f6 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts @@ -53,11 +53,6 @@ }; }; -&emac { - /* LEDs changed to active high on the plus */ - /delete-property/ allwinner,leds-active-low; -}; - &mmc1 { vmmc-supply = <®_vcc3v3>; bus-width = <4>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts index 6dbf7b2e0c13..b6ca45d18e51 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts @@ -67,7 +67,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts index 2fc62ef0cb3e..a6a1087a0c9b 100644 --- a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts +++ b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts @@ -129,7 +129,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_dc1sw>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts index d3b337b043a1..484b93df20cb 100644 --- a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts +++ b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts @@ -129,7 +129,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_cldo1>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun9i-a80-optimus.dts b/arch/arm/boot/dts/sun9i-a80-optimus.dts index bbc6335e5631..5c3580d712e4 100644 --- a/arch/arm/boot/dts/sun9i-a80-optimus.dts +++ b/arch/arm/boot/dts/sun9i-a80-optimus.dts @@ -124,7 +124,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_cldo1>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi index 39263e74fbb5..8e5cb3b3fd68 100644 --- a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi +++ b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi @@ -126,7 +126,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts index e500911ce0a5..6f1e0f0d4f0a 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts @@ -406,6 +406,9 @@ }; }; +&mdio1 { + clock-frequency = <5000000>; +}; &iomuxc { pinctrl_gpio_e6185_eeprom_sel: pinctrl-gpio-e6185-eeprom-spi0 { diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 213607a1f45c..e26a278d301a 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -44,20 +44,20 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); /* optinsn template addresses */ -extern __visible kprobe_opcode_t optprobe_template_entry; -extern __visible kprobe_opcode_t optprobe_template_val; -extern __visible kprobe_opcode_t optprobe_template_call; -extern __visible kprobe_opcode_t optprobe_template_end; -extern __visible kprobe_opcode_t optprobe_template_sub_sp; -extern __visible kprobe_opcode_t optprobe_template_add_sp; -extern __visible kprobe_opcode_t optprobe_template_restore_begin; -extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn; -extern __visible kprobe_opcode_t optprobe_template_restore_end; +extern __visible kprobe_opcode_t optprobe_template_entry[]; +extern __visible kprobe_opcode_t optprobe_template_val[]; +extern __visible kprobe_opcode_t optprobe_template_call[]; +extern __visible kprobe_opcode_t optprobe_template_end[]; +extern __visible kprobe_opcode_t optprobe_template_sub_sp[]; +extern __visible kprobe_opcode_t optprobe_template_add_sp[]; +extern __visible kprobe_opcode_t optprobe_template_restore_begin[]; +extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn[]; +extern __visible kprobe_opcode_t optprobe_template_restore_end[]; #define MAX_OPTIMIZED_LENGTH 4 #define MAX_OPTINSN_SIZE \ - ((unsigned long)&optprobe_template_end - \ - (unsigned long)&optprobe_template_entry) + ((unsigned long)optprobe_template_end - \ + (unsigned long)optprobe_template_entry) #define RELATIVEJUMP_SIZE 4 struct arch_optimized_insn { diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 3502c2f746ca..baf7d0204eb5 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -75,6 +75,8 @@ #define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) #define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 + /* * PMD_SHIFT determines the size of the area a second-level page table can map * PGDIR_SHIFT determines what a third-level page table entry can map diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index fbb6693c3352..2b85d175e999 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -25,6 +25,8 @@ #define PTE_HWTABLE_OFF (0) #define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u64)) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 + /* * PGDIR_SHIFT determines the size a top-level page table entry can map. */ diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c index 05fe92aa7d98..0529f90395c9 100644 --- a/arch/arm/kernel/perf_regs.c +++ b/arch/arm/kernel/perf_regs.c @@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 8e6ace03e960..9f199b1e8383 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -71,7 +71,7 @@ void arch_cpu_idle(void) arm_pm_idle(); else cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_prepare(void) diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 3ee7bdff86b2..3f62a0c9450d 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -7,7 +7,6 @@ config ARCH_OMAP2 depends on ARCH_MULTI_V6 select ARCH_OMAP2PLUS select CPU_V6 - select PM_GENERIC_DOMAINS if PM select SOC_HAS_OMAP2_SDRC config ARCH_OMAP3 @@ -106,6 +105,8 @@ config ARCH_OMAP2PLUS select OMAP_DM_TIMER select OMAP_GPMC select PINCTRL + select PM_GENERIC_DOMAINS if PM + select PM_GENERIC_DOMAINS_OF if PM select RESET_CONTROLLER select SOC_BUS select TI_SYSC diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index a92d277f81a0..c8d317fafe2e 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -175,8 +175,11 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, if (mpuss_can_lose_context) { error = cpu_cluster_pm_enter(); if (error) { - omap_set_pwrdm_state(mpu_pd, PWRDM_POWER_ON); - goto cpu_cluster_pm_out; + index = 0; + cx = state_ptr + index; + pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state); + omap_set_pwrdm_state(mpu_pd, cx->mpu_state); + mpuss_can_lose_context = 0; } } } @@ -184,7 +187,6 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, omap4_enter_lowpower(dev->cpu, cx->cpu_state); cpu_done[dev->cpu] = true; -cpu_cluster_pm_out: /* Wakeup CPU1 only if it is not offlined */ if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) { diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index d57112a276f5..c23dbf8bebee 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -354,8 +354,8 @@ static void __init free_highpages(void) /* set highmem page free */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &range_start, &range_end, NULL) { - unsigned long start = PHYS_PFN(range_start); - unsigned long end = PHYS_PFN(range_end); + unsigned long start = PFN_UP(range_start); + unsigned long end = PFN_DOWN(range_end); /* Ignore complete lowmem entries */ if (end <= max_low) diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index 7a449df0b359..c78180172120 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -85,21 +85,21 @@ asm ( "optprobe_template_end:\n"); #define TMPL_VAL_IDX \ - ((unsigned long *)&optprobe_template_val - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_val - (unsigned long *)optprobe_template_entry) #define TMPL_CALL_IDX \ - ((unsigned long *)&optprobe_template_call - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_call - (unsigned long *)optprobe_template_entry) #define TMPL_END_IDX \ - ((unsigned long *)&optprobe_template_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_end - (unsigned long *)optprobe_template_entry) #define TMPL_ADD_SP \ - ((unsigned long *)&optprobe_template_add_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_add_sp - (unsigned long *)optprobe_template_entry) #define TMPL_SUB_SP \ - ((unsigned long *)&optprobe_template_sub_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_sub_sp - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_BEGIN \ - ((unsigned long *)&optprobe_template_restore_begin - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_begin - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_ORIGN_INSN \ - ((unsigned long *)&optprobe_template_restore_orig_insn - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_orig_insn - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_END \ - ((unsigned long *)&optprobe_template_restore_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_end - (unsigned long *)optprobe_template_entry) /* * ARM can always optimize an instruction when using ARM ISA, except @@ -234,7 +234,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *or } /* Copy arch-dep-instance from template. */ - memcpy(code, (unsigned long *)&optprobe_template_entry, + memcpy(code, (unsigned long *)optprobe_template_entry, TMPL_END_IDX * sizeof(kprobe_opcode_t)); /* Adjust buffer according to instruction. */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1d466addb078..1515f6f153a0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1002,7 +1002,7 @@ config NUMA config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" range 1 10 - default "2" + default "4" depends on NEED_MULTIPLE_NODES help Specify the maximum number of NUMA Nodes available on the target diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts index 3ea5182ca489..e5e840b9fbb4 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts @@ -105,7 +105,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_dc1sw>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts index d894ec5fa8a1..70e31743f0ba 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts @@ -120,7 +120,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts index b26181cf9095..b54099b654c8 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts @@ -13,7 +13,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-txid"; phy-handle = <&ext_rgmii_phy>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts index 3ab0f0347bc9..0494bfaf2ffa 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts @@ -122,9 +122,6 @@ status = "okay"; port { - #address-cells = <1>; - #size-cells = <0>; - csi_ep: endpoint { remote-endpoint = <&ov5640_ep>; bus-width = <8>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts index df1b9263ad0e..6e30a564c87f 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts @@ -36,7 +36,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; /delete-property/ allwinner,leds-active-low; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts index 7d7aad18f078..8bf2db9dcbda 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts @@ -123,7 +123,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts index cb44bfa5981f..33ab44072e6d 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts @@ -124,7 +124,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 3f7ceeb1a767..7c9dbde645b5 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -97,7 +97,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_aldo2>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts index af85b2074867..961732c52aa0 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts @@ -100,7 +100,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; allwinner,rx-delay-ps = <200>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts index feadd21bc0dc..46e558ab7729 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -159,7 +159,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00a"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts index c07966740e14..f9b4a39683cf 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts @@ -192,7 +192,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00a"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi index 55259f973b5a..aef8f2b00778 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi @@ -5,20 +5,20 @@ usb { compatible = "simple-bus"; dma-ranges; - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x0 0x0 0x68500000 0x00400000>; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0x0 0x0 0x0 0x68500000 0x0 0x00400000>; usbphy0: usb-phy@0 { compatible = "brcm,sr-usb-combo-phy"; - reg = <0x00000000 0x100>; + reg = <0x0 0x00000000 0x0 0x100>; #phy-cells = <1>; status = "disabled"; }; xhci0: usb@1000 { compatible = "generic-xhci"; - reg = <0x00001000 0x1000>; + reg = <0x0 0x00001000 0x0 0x1000>; interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0 1>, <&usbphy0 0>; phy-names = "phy0", "phy1"; @@ -28,7 +28,7 @@ bdc0: usb@2000 { compatible = "brcm,bdc-v0.16"; - reg = <0x00002000 0x1000>; + reg = <0x0 0x00002000 0x0 0x1000>; interrupts = <GIC_SPI 259 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0 0>, <&usbphy0 1>; phy-names = "phy0", "phy1"; @@ -38,21 +38,21 @@ usbphy1: usb-phy@10000 { compatible = "brcm,sr-usb-combo-phy"; - reg = <0x00010000 0x100>; + reg = <0x0 0x00010000 0x0 0x100>; #phy-cells = <1>; status = "disabled"; }; usbphy2: usb-phy@20000 { compatible = "brcm,sr-usb-hs-phy"; - reg = <0x00020000 0x100>; + reg = <0x0 0x00020000 0x0 0x100>; #phy-cells = <0>; status = "disabled"; }; xhci1: usb@11000 { compatible = "generic-xhci"; - reg = <0x00011000 0x1000>; + reg = <0x0 0x00011000 0x0 0x1000>; interrupts = <GIC_SPI 263 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy1 1>, <&usbphy2>, <&usbphy1 0>; phy-names = "phy0", "phy1", "phy2"; @@ -62,7 +62,7 @@ bdc1: usb@21000 { compatible = "brcm,bdc-v0.16"; - reg = <0x00021000 0x1000>; + reg = <0x0 0x00021000 0x0 0x1000>; interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy2>; phy-names = "phy0"; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts index f46eb47cfa4d..8161dd237971 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts @@ -75,6 +75,7 @@ &enetc_port0 { phy-handle = <&phy0>; phy-connection-type = "sgmii"; + managed = "in-band-status"; status = "okay"; mdio { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 73e4f9466887..7a6fb7e1fb82 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -1012,6 +1012,7 @@ compatible = "fsl,ls1028a-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x1c>; #fsl,rcpm-wakeup-cells = <7>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi index ff5805206a28..692d8f4a206d 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi @@ -805,6 +805,7 @@ compatible = "fsl,ls1088a-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x18>; #fsl,rcpm-wakeup-cells = <6>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index bf72918fe545..e7abb74bd816 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -892,6 +892,7 @@ compatible = "fsl,ls208xa-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x18>; #fsl,rcpm-wakeup-cells = <6>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index 6de86a4f0ec4..b88c3c99b007 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -72,6 +72,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; @@ -210,6 +211,7 @@ host-wakeup-gpios = <&gpio2 8 GPIO_ACTIVE_HIGH>; device-wakeup-gpios = <&gpio2 7 GPIO_ACTIVE_HIGH>; clocks = <&osc_32k>; + max-speed = <4000000>; clock-names = "extclk"; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi index f305a530ff6f..521eb3a5a12e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi @@ -121,6 +121,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi index 4107fe914d08..49082529764f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi @@ -135,13 +135,10 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; - /* - * The interrupt is not correct. It should be level low, - * however with internal pull up this causes IRQ storm. - */ - interrupts = <8 IRQ_TYPE_EDGE_RISING>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; #clock-cells = <0>; @@ -398,7 +395,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x41 + MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index b83f400def8b..05ee062548e4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -129,7 +129,7 @@ opp-1600000000 { opp-hz = /bits/ 64 <1600000000>; - opp-microvolt = <900000>; + opp-microvolt = <950000>; opp-supported-hw = <0xc>, <0x7>; clock-latency-ns = <150000>; opp-suspend; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index 46e76cf32b2f..7dfee715a2c4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -53,6 +53,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts index 707d8486b4d8..8311b95dee49 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts @@ -18,6 +18,7 @@ pmic: pmic@25 { compatible = "nxp,pca9450b"; reg = <0x25>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index a2d0190921e4..7f356edf9f91 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -116,13 +116,10 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; - /* - * The interrupt is not correct. It should be level low, - * however with internal pull up this causes IRQ storm. - */ - interrupts = <8 IRQ_TYPE_EDGE_RISING>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; regulators { @@ -388,7 +385,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x101 + MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 746faf1cf2fb..16c7202885d7 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -790,28 +790,6 @@ #index-cells = <1>; reg = <0x32e40200 0x200>; }; - - usbotg2: usb@32e50000 { - compatible = "fsl,imx8mn-usb", "fsl,imx7d-usb"; - reg = <0x32e50000 0x200>; - interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MN_CLK_USB1_CTRL_ROOT>; - clock-names = "usb1_ctrl_root_clk"; - assigned-clocks = <&clk IMX8MN_CLK_USB_BUS>, - <&clk IMX8MN_CLK_USB_CORE_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>, - <&clk IMX8MN_SYS_PLL1_100M>; - fsl,usbphy = <&usbphynop2>; - fsl,usbmisc = <&usbmisc2 0>; - status = "disabled"; - }; - - usbmisc2: usbmisc@32e50200 { - compatible = "fsl,imx8mn-usbmisc", "fsl,imx7d-usbmisc"; - #index-cells = <1>; - reg = <0x32e50200 0x200>; - }; - }; dma_apbh: dma-controller@33000000 { @@ -876,12 +854,4 @@ assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; clock-names = "main_clk"; }; - - usbphynop2: usbphynop2 { - compatible = "usb-nop-xceiv"; - clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; - assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; - clock-names = "main_clk"; - }; }; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi index 8bc6caa9167d..4338db14c5da 100644 --- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi @@ -19,6 +19,7 @@ fman0: fman@1a00000 { clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; ptimer-handle = <&ptp_timer0>; + dma-coherent; muram@0 { compatible = "fsl,fman-muram"; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts index 96c50d48289d..a7a83f29f00b 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts +++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts @@ -110,7 +110,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "mt25qu02g"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts index 381a84912ba8..c28d51cc5797 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts @@ -10,18 +10,6 @@ model = "NVIDIA Jetson TX2 Developer Kit"; compatible = "nvidia,p2771-0000", "nvidia,tegra186"; - aconnect { - status = "okay"; - - dma-controller@2930000 { - status = "okay"; - }; - - interrupt-controller@2a40000 { - status = "okay"; - }; - }; - i2c@3160000 { power-monitor@42 { compatible = "ti,ina3221"; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi index a2893be80507..0dc8304a2edd 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi @@ -54,7 +54,7 @@ status = "okay"; }; - serial@c280000 { + serial@3100000 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index e9c90f0f44ff..93438d2b9469 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -1161,7 +1161,7 @@ hsp_aon: hsp@c150000 { compatible = "nvidia,tegra194-hsp", "nvidia,tegra186-hsp"; - reg = <0x0c150000 0xa0000>; + reg = <0x0c150000 0x90000>; interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi index e18e1a9a3011..a9caaf7c0d67 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi @@ -1663,16 +1663,6 @@ vin-supply = <&vdd_5v0_sys>; }; - vdd_usb_vbus_otg: regulator@11 { - compatible = "regulator-fixed"; - regulator-name = "USB_VBUS_EN0"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>; - enable-active-high; - vin-supply = <&vdd_5v0_sys>; - }; - vdd_hdmi: regulator@10 { compatible = "regulator-fixed"; regulator-name = "VDD_HDMI_5V0"; @@ -1712,4 +1702,14 @@ enable-active-high; vin-supply = <&vdd_3v3_sys>; }; + + vdd_usb_vbus_otg: regulator@14 { + compatible = "regulator-fixed"; + regulator-name = "USB_VBUS_EN0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>; + enable-active-high; + vin-supply = <&vdd_5v0_sys>; + }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts index f6e6a24829af..b5d9a5526272 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts @@ -8,7 +8,7 @@ compatible = "nvidia,tegra234-vdk", "nvidia,tegra234"; aliases { - sdhci3 = "/cbb@0/sdhci@3460000"; + mmc3 = "/bus@0/mmc@3460000"; serial0 = &uarta; }; @@ -17,12 +17,12 @@ stdout-path = "serial0:115200n8"; }; - cbb@0 { + bus@0 { serial@3100000 { status = "okay"; }; - sdhci@3460000 { + mmc@3460000 { status = "okay"; bus-width = <8>; non-removable; diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index a94dac76bf3f..59e0cbfa2214 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -179,22 +179,22 @@ }; soc: soc { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0 0 0 0xffffffff>; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0 0 0 0 0x0 0xffffffff>; dma-ranges; compatible = "simple-bus"; prng: qrng@e1000 { compatible = "qcom,prng-ee"; - reg = <0xe3000 0x1000>; + reg = <0x0 0xe3000 0x0 0x1000>; clocks = <&gcc GCC_PRNG_AHB_CLK>; clock-names = "core"; }; cryptobam: dma@704000 { compatible = "qcom,bam-v1.7.0"; - reg = <0x00704000 0x20000>; + reg = <0x0 0x00704000 0x0 0x20000>; interrupts = <GIC_SPI 207 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_CRYPTO_AHB_CLK>; clock-names = "bam_clk"; @@ -206,7 +206,7 @@ crypto: crypto@73a000 { compatible = "qcom,crypto-v5.1"; - reg = <0x0073a000 0x6000>; + reg = <0x0 0x0073a000 0x0 0x6000>; clocks = <&gcc GCC_CRYPTO_AHB_CLK>, <&gcc GCC_CRYPTO_AXI_CLK>, <&gcc GCC_CRYPTO_CLK>; @@ -217,7 +217,7 @@ tlmm: pinctrl@1000000 { compatible = "qcom,ipq6018-pinctrl"; - reg = <0x01000000 0x300000>; + reg = <0x0 0x01000000 0x0 0x300000>; interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>; gpio-controller; #gpio-cells = <2>; @@ -235,7 +235,7 @@ gcc: gcc@1800000 { compatible = "qcom,gcc-ipq6018"; - reg = <0x01800000 0x80000>; + reg = <0x0 0x01800000 0x0 0x80000>; clocks = <&xo>, <&sleep_clk>; clock-names = "xo", "sleep_clk"; #clock-cells = <1>; @@ -244,17 +244,17 @@ tcsr_mutex_regs: syscon@1905000 { compatible = "syscon"; - reg = <0x01905000 0x8000>; + reg = <0x0 0x01905000 0x0 0x8000>; }; tcsr_q6: syscon@1945000 { compatible = "syscon"; - reg = <0x01945000 0xe000>; + reg = <0x0 0x01945000 0x0 0xe000>; }; blsp_dma: dma@7884000 { compatible = "qcom,bam-v1.7.0"; - reg = <0x07884000 0x2b000>; + reg = <0x0 0x07884000 0x0 0x2b000>; interrupts = <GIC_SPI 238 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_AHB_CLK>; clock-names = "bam_clk"; @@ -264,7 +264,7 @@ blsp1_uart3: serial@78b1000 { compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; - reg = <0x078b1000 0x200>; + reg = <0x0 0x078b1000 0x0 0x200>; interrupts = <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_UART3_APPS_CLK>, <&gcc GCC_BLSP1_AHB_CLK>; @@ -276,7 +276,7 @@ compatible = "qcom,spi-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b5000 0x600>; + reg = <0x0 0x078b5000 0x0 0x600>; interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>, @@ -291,7 +291,7 @@ compatible = "qcom,spi-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b6000 0x600>; + reg = <0x0 0x078b6000 0x0 0x600>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP2_SPI_APPS_CLK>, @@ -306,7 +306,7 @@ compatible = "qcom,i2c-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b6000 0x600>; + reg = <0x0 0x078b6000 0x0 0x600>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_AHB_CLK>, <&gcc GCC_BLSP1_QUP2_I2C_APPS_CLK>; @@ -321,7 +321,7 @@ compatible = "qcom,i2c-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b7000 0x600>; + reg = <0x0 0x078b7000 0x0 0x600>; interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_AHB_CLK>, <&gcc GCC_BLSP1_QUP3_I2C_APPS_CLK>; @@ -336,24 +336,24 @@ compatible = "qcom,msm-qgic2"; interrupt-controller; #interrupt-cells = <0x3>; - reg = <0x0b000000 0x1000>, /*GICD*/ - <0x0b002000 0x1000>, /*GICC*/ - <0x0b001000 0x1000>, /*GICH*/ - <0x0b004000 0x1000>; /*GICV*/ + reg = <0x0 0x0b000000 0x0 0x1000>, /*GICD*/ + <0x0 0x0b002000 0x0 0x1000>, /*GICC*/ + <0x0 0x0b001000 0x0 0x1000>, /*GICH*/ + <0x0 0x0b004000 0x0 0x1000>; /*GICV*/ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>; }; watchdog@b017000 { compatible = "qcom,kpss-wdt"; interrupts = <GIC_SPI 3 IRQ_TYPE_EDGE_RISING>; - reg = <0x0b017000 0x40>; + reg = <0x0 0x0b017000 0x0 0x40>; clocks = <&sleep_clk>; timeout-sec = <10>; }; apcs_glb: mailbox@b111000 { compatible = "qcom,ipq6018-apcs-apps-global"; - reg = <0x0b111000 0x1000>; + reg = <0x0 0x0b111000 0x0 0x1000>; #clock-cells = <1>; clocks = <&a53pll>, <&xo>; clock-names = "pll", "xo"; @@ -362,7 +362,7 @@ a53pll: clock@b116000 { compatible = "qcom,ipq6018-a53pll"; - reg = <0x0b116000 0x40>; + reg = <0x0 0x0b116000 0x0 0x40>; #clock-cells = <0>; clocks = <&xo>; clock-names = "xo"; @@ -377,68 +377,68 @@ }; timer@b120000 { - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; ranges; compatible = "arm,armv7-timer-mem"; - reg = <0x0b120000 0x1000>; + reg = <0x0 0x0b120000 0x0 0x1000>; clock-frequency = <19200000>; frame@b120000 { frame-number = <0>; interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b121000 0x1000>, - <0x0b122000 0x1000>; + reg = <0x0 0x0b121000 0x0 0x1000>, + <0x0 0x0b122000 0x0 0x1000>; }; frame@b123000 { frame-number = <1>; interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>; - reg = <0xb123000 0x1000>; + reg = <0x0 0xb123000 0x0 0x1000>; status = "disabled"; }; frame@b124000 { frame-number = <2>; interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b124000 0x1000>; + reg = <0x0 0x0b124000 0x0 0x1000>; status = "disabled"; }; frame@b125000 { frame-number = <3>; interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b125000 0x1000>; + reg = <0x0 0x0b125000 0x0 0x1000>; status = "disabled"; }; frame@b126000 { frame-number = <4>; interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b126000 0x1000>; + reg = <0x0 0x0b126000 0x0 0x1000>; status = "disabled"; }; frame@b127000 { frame-number = <5>; interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b127000 0x1000>; + reg = <0x0 0x0b127000 0x0 0x1000>; status = "disabled"; }; frame@b128000 { frame-number = <6>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b128000 0x1000>; + reg = <0x0 0x0b128000 0x0 0x1000>; status = "disabled"; }; }; q6v5_wcss: remoteproc@cd00000 { compatible = "qcom,ipq8074-wcss-pil"; - reg = <0x0cd00000 0x4040>, - <0x004ab000 0x20>; + reg = <0x0 0x0cd00000 0x0 0x4040>, + <0x0 0x004ab000 0x0 0x20>; reg-names = "qdsp6", "rmb"; interrupts-extended = <&intc GIC_SPI 325 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi index 9cbf963aa068..c29643442e91 100644 --- a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi @@ -28,6 +28,12 @@ clock-frequency = <0>; }; + audio_clk_b: audio_clk_b { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + audio_clk_c: audio_clk_c { compatible = "fixed-clock"; #clock-cells = <0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts index 35bd6b904b9c..337681038519 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts +++ b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts @@ -243,7 +243,6 @@ interrupts = <RK_PB2 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&pmic_int>; - rockchip,system-power-controller; wakeup-source; #clock-cells = <1>; clock-output-names = "rk808-clkout1", "xin32k"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts index be7a31d81632..2ee07d15a6e3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts @@ -20,7 +20,7 @@ gmac_clk: gmac-clock { compatible = "fixed-clock"; clock-frequency = <125000000>; - clock-output-names = "gmac_clk"; + clock-output-names = "gmac_clkin"; #clock-cells = <0>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi index e7a459fa4322..20309076dbac 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi @@ -74,14 +74,14 @@ label = "red:diy"; gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>; default-state = "off"; - linux,default-trigger = "mmc1"; + linux,default-trigger = "mmc2"; }; yellow_led: led-2 { label = "yellow:yellow-led"; gpios = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>; default-state = "off"; - linux,default-trigger = "mmc0"; + linux,default-trigger = "mmc1"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index ada724b12f01..7a9a7aca86c6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -29,6 +29,9 @@ i2c6 = &i2c6; i2c7 = &i2c7; i2c8 = &i2c8; + mmc0 = &sdio0; + mmc1 = &sdmmc; + mmc2 = &sdhci; serial0 = &uart0; serial1 = &uart1; serial2 = &uart2; diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h index e3d47b52161d..ec7720dbe2c8 100644 --- a/arch/arm64/include/asm/brk-imm.h +++ b/arch/arm64/include/asm/brk-imm.h @@ -10,6 +10,7 @@ * #imm16 values used for BRK instruction generation * 0x004: for installing kprobes * 0x005: for installing uprobes + * 0x006: for kprobe software single-step * Allowed values for kgdb are 0x400 - 0x7ff * 0x100: for triggering a fault on purpose (reserved) * 0x400: for dynamic BRK instruction @@ -19,6 +20,7 @@ */ #define KPROBES_BRK_IMM 0x004 #define UPROBES_BRK_IMM 0x005 +#define KPROBES_BRK_SS_IMM 0x006 #define FAULT_BRK_IMM 0x100 #define KGDB_DYN_DBG_BRK_IMM 0x400 #define KGDB_COMPILED_DBG_BRK_IMM 0x401 diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 97244d4feca9..da250e4741bd 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -268,6 +268,8 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; /* * CPU feature detected at boot time based on feature of one or more CPUs. * All possible conflicts for a late CPU are ignored. + * NOTE: this means that a late CPU with the feature will *not* cause the + * capability to be advertised by cpus_have_*cap()! */ #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 9e2e9a63c7b6..ef5b040dee44 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,8 @@ #define QCOM_CPU_PART_FALKOR_V1 0x800 #define QCOM_CPU_PART_FALKOR 0xC00 #define QCOM_CPU_PART_KRYO 0x200 +#define QCOM_CPU_PART_KRYO_2XX_GOLD 0x800 +#define QCOM_CPU_PART_KRYO_2XX_SILVER 0x801 #define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 #define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804 #define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 @@ -116,6 +118,8 @@ #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) +#define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD) +#define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER) #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD) #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER) diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 0b298f48f5bf..657c921fd784 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -53,6 +53,7 @@ /* kprobes BRK opcodes with ESR encoding */ #define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5)) +#define BRK64_OPCODE_KPROBES_SS (AARCH64_BREAK_MON | (KPROBES_BRK_SS_IMM << 5)) /* uprobes BRK opcodes with ESR encoding */ #define BRK64_OPCODE_UPROBES (AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5)) diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 97e511d645a2..8699ce30f587 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -16,7 +16,7 @@ #include <linux/percpu.h> #define __ARCH_WANT_KPROBES_INSN_SLOT -#define MAX_INSN_SIZE 1 +#define MAX_INSN_SIZE 2 #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 781d029b8aa8..0cd9f0f75c13 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -118,6 +118,8 @@ struct kvm_arch { */ unsigned long *pmu_filter; unsigned int pmuver; + + u8 pfr0_csv2; }; struct kvm_vcpu_fault_info { diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 4ff12a7adcfd..5628289b9d5e 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -115,8 +115,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) -#define pte_valid_young(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) #define pte_valid_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) @@ -124,9 +122,12 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. + * Note that we can't make any assumptions based on the state of the access + * flag, since ptep_clear_flush_young() elides a DSB when invalidating the + * TLB. */ #define pte_accessible(mm, pte) \ - (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (subject to the @@ -164,13 +165,6 @@ static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) return pmd; } -static inline pte_t pte_wrprotect(pte_t pte) -{ - pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); - return pte; -} - static inline pte_t pte_mkwrite(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); @@ -196,6 +190,20 @@ static inline pte_t pte_mkdirty(pte_t pte) return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); + + pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + return pte; +} + static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); @@ -845,12 +853,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres pte = READ_ONCE(*ptep); do { old_pte = pte; - /* - * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY - * clear), set the PTE_DIRTY bit. - */ - if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h index 4266262101fe..006946745352 100644 --- a/arch/arm64/include/asm/probes.h +++ b/arch/arm64/include/asm/probes.h @@ -7,6 +7,8 @@ #ifndef _ARM_PROBES_H #define _ARM_PROBES_H +#include <asm/insn.h> + typedef u32 probe_opcode_t; typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *); diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 174817ba119c..e2ef4c2edf06 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -372,6 +372,8 @@ #define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1) #define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4) +#define SYS_SCXTNUM_EL1 sys_reg(3, 0, 13, 0, 7) + #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0) #define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) @@ -404,6 +406,8 @@ #define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2) #define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3) +#define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7) + /* Definitions for system register interface to AMU for ARMv8.4 onwards */ #define SYS_AM_EL0(crm, op2) sys_reg(3, 3, 13, (crm), (op2)) #define SYS_AMCR_EL0 SYS_AM_EL0(2, 0) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 61314fd70f13..cafaf0da05b7 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -299,6 +299,8 @@ static const struct midr_range erratum_845719_list[] = { MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), /* Brahma-B53 r0p[0] */ MIDR_REV(MIDR_BRAHMA_B53, 0, 0), + /* Kryo2XX Silver rAp4 */ + MIDR_REV(MIDR_QCOM_KRYO_2XX_SILVER, 0xa, 0x4), {}, }; #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index dcc165b3fc04..6f36c4f62f69 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1337,6 +1337,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_GOLD), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index af9987c154ca..9ec34690e255 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -43,7 +43,7 @@ static void *image_load(struct kimage *image, u64 flags, value; bool be_image, be_kernel; struct kexec_buf kbuf; - unsigned long text_offset; + unsigned long text_offset, kernel_segment_number; struct kexec_segment *kernel_segment; int ret; @@ -88,11 +88,37 @@ static void *image_load(struct kimage *image, /* Adjust kernel segment with TEXT_OFFSET */ kbuf.memsz += text_offset; - ret = kexec_add_buffer(&kbuf); - if (ret) + kernel_segment_number = image->nr_segments; + + /* + * The location of the kernel segment may make it impossible to satisfy + * the other segment requirements, so we try repeatedly to find a + * location that will work. + */ + while ((ret = kexec_add_buffer(&kbuf)) == 0) { + /* Try to load additional data */ + kernel_segment = &image->segment[kernel_segment_number]; + ret = load_other_segments(image, kernel_segment->mem, + kernel_segment->memsz, initrd, + initrd_len, cmdline); + if (!ret) + break; + + /* + * We couldn't find space for the other segments; erase the + * kernel segment and try the next available hole. + */ + image->nr_segments -= 1; + kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + } + + if (ret) { + pr_err("Could not find any suitable kernel location!"); return ERR_PTR(ret); + } - kernel_segment = &image->segment[image->nr_segments - 1]; + kernel_segment = &image->segment[kernel_segment_number]; kernel_segment->mem += text_offset; kernel_segment->memsz -= text_offset; image->start = kernel_segment->mem; @@ -101,12 +127,7 @@ static void *image_load(struct kimage *image, kernel_segment->mem, kbuf.bufsz, kernel_segment->memsz); - /* Load additional data */ - ret = load_other_segments(image, - kernel_segment->mem, kernel_segment->memsz, - initrd, initrd_len, cmdline); - - return ERR_PTR(ret); + return NULL; } #ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 5b0e67b93cdc..03210f644790 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -240,6 +240,11 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) return ret; } +/* + * Tries to add the initrd and DTB to the image. If it is not possible to find + * valid locations, this function will undo changes to the image and return non + * zero. + */ int load_other_segments(struct kimage *image, unsigned long kernel_load_addr, unsigned long kernel_size, @@ -248,7 +253,8 @@ int load_other_segments(struct kimage *image, { struct kexec_buf kbuf; void *headers, *dtb = NULL; - unsigned long headers_sz, initrd_load_addr = 0, dtb_len; + unsigned long headers_sz, initrd_load_addr = 0, dtb_len, + orig_segments = image->nr_segments; int ret = 0; kbuf.image = image; @@ -334,6 +340,7 @@ int load_other_segments(struct kimage *image, return 0; out_err: + image->nr_segments = orig_segments; vfree(dtb); return ret; } diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 94e8718e7229..f6f58e6265df 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -73,8 +73,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index deba738142ed..f11a1a1f7026 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -36,25 +36,16 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); static void __kprobes post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); -static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode) -{ - void *addrs[1]; - u32 insns[1]; - - addrs[0] = addr; - insns[0] = opcode; - - return aarch64_insn_patch_text(addrs, insns, 1); -} - static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { + kprobe_opcode_t *addr = p->ainsn.api.insn; + void *addrs[] = {addr, addr + 1}; + u32 insns[] = {p->opcode, BRK64_OPCODE_KPROBES_SS}; + /* prepare insn slot */ - patch_text(p->ainsn.api.insn, p->opcode); + aarch64_insn_patch_text(addrs, insns, 2); - flush_icache_range((uintptr_t) (p->ainsn.api.insn), - (uintptr_t) (p->ainsn.api.insn) + - MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + flush_icache_range((uintptr_t)addr, (uintptr_t)(addr + MAX_INSN_SIZE)); /* * Needs restoring of return address after stepping xol. @@ -128,13 +119,18 @@ void *alloc_insn_page(void) /* arm kprobe: install breakpoint in text */ void __kprobes arch_arm_kprobe(struct kprobe *p) { - patch_text(p->addr, BRK64_OPCODE_KPROBES); + void *addr = p->addr; + u32 insn = BRK64_OPCODE_KPROBES; + + aarch64_insn_patch_text(&addr, &insn, 1); } /* disarm kprobe: remove breakpoint from text */ void __kprobes arch_disarm_kprobe(struct kprobe *p) { - patch_text(p->addr, p->opcode); + void *addr = p->addr; + + aarch64_insn_patch_text(&addr, &p->opcode, 1); } void __kprobes arch_remove_kprobe(struct kprobe *p) @@ -163,20 +159,15 @@ static void __kprobes set_current_kprobe(struct kprobe *p) } /* - * Interrupts need to be disabled before single-step mode is set, and not - * reenabled until after single-step mode ends. - * Without disabling interrupt on local CPU, there is a chance of - * interrupt occurrence in the period of exception return and start of - * out-of-line single-step, that result in wrongly single stepping - * into the interrupt handler. + * Mask all of DAIF while executing the instruction out-of-line, to keep things + * simple and avoid nesting exceptions. Interrupts do have to be disabled since + * the kprobe state is per-CPU and doesn't get migrated. */ static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, struct pt_regs *regs) { kcb->saved_irqflag = regs->pstate & DAIF_MASK; - regs->pstate |= PSR_I_BIT; - /* Unmask PSTATE.D for enabling software step exceptions. */ - regs->pstate &= ~PSR_D_BIT; + regs->pstate |= DAIF_MASK; } static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, @@ -219,10 +210,7 @@ static void __kprobes setup_singlestep(struct kprobe *p, slot = (unsigned long)p->ainsn.api.insn; set_ss_context(kcb, slot); /* mark pending ss */ - - /* IRQs and single stepping do not mix well. */ kprobes_save_local_irqflag(kcb, regs); - kernel_enable_single_step(regs); instruction_pointer_set(regs, slot); } else { /* insn simulation */ @@ -273,12 +261,8 @@ post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs) } /* call post handler */ kcb->kprobe_status = KPROBE_HIT_SSDONE; - if (cur->post_handler) { - /* post_handler can hit breakpoint and single step - * again, so we enable D-flag for recursive exception. - */ + if (cur->post_handler) cur->post_handler(cur, regs, 0); - } reset_current_kprobe(); } @@ -302,8 +286,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr) if (!instruction_pointer(regs)) BUG(); - kernel_disable_single_step(); - if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); else @@ -365,10 +347,6 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) * pre-handler and it returned non-zero, it will * modify the execution path and no need to single * stepping. Let's just reset current kprobe and exit. - * - * pre_handler can hit a breakpoint and can step thru - * before return, keep PSTATE D-flag enabled until - * pre_handler return back. */ if (!p->pre_handler || !p->pre_handler(p, regs)) { setup_singlestep(p, regs, kcb, 0); @@ -399,7 +377,7 @@ kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr) } static int __kprobes -kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr) +kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); int retval; @@ -409,16 +387,15 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr) if (retval == DBG_HOOK_HANDLED) { kprobes_restore_local_irqflag(kcb, regs); - kernel_disable_single_step(); - post_kprobe_handler(kcb, regs); } return retval; } -static struct step_hook kprobes_step_hook = { - .fn = kprobe_single_step_handler, +static struct break_hook kprobes_break_ss_hook = { + .imm = KPROBES_BRK_SS_IMM, + .fn = kprobe_breakpoint_ss_handler, }; static int __kprobes @@ -486,7 +463,7 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p) int __init arch_init_kprobes(void) { register_kernel_break_hook(&kprobes_break_hook); - register_kernel_step_hook(&kprobes_step_hook); + register_kernel_break_hook(&kprobes_break_ss_hook); return 0; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 4784011cecac..7697a4b48b7c 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -126,7 +126,7 @@ void arch_cpu_idle(void) * tricks */ cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_HOTPLUG_CPU @@ -522,14 +522,13 @@ static void erratum_1418040_thread_switch(struct task_struct *prev, bool prev32, next32; u64 val; - if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && - cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040)) return; prev32 = is_compat_thread(task_thread_info(prev)); next32 = is_compat_thread(task_thread_info(next)); - if (prev32 == next32) + if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040)) return; val = read_sysreg(cntkctl_el1); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index c18eb7d41274..f6e4e3737405 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -118,6 +118,7 @@ static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void) MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 43ae4e0c968f..62d2bda7adb8 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -66,7 +66,6 @@ static int cpu_psci_cpu_disable(unsigned int cpu) static void cpu_psci_cpu_die(unsigned int cpu) { - int ret; /* * There are no known implementations of PSCI actually using the * power state field, pass a sensible default for now. @@ -74,9 +73,7 @@ static void cpu_psci_cpu_die(unsigned int cpu) u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT; - ret = psci_ops.cpu_off(state); - - pr_crit("unable to power off CPU%u (%d)\n", cpu, ret); + psci_ops.cpu_off(state); } static int cpu_psci_cpu_kill(unsigned int cpu) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 09c96f57818c..18e9727d3f64 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -413,6 +413,7 @@ void cpu_die_early(void) /* Mark this CPU absent */ set_cpu_present(cpu, 0); + rcu_report_dead(cpu); if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) { update_cpu_boot_status(CPU_KILL_ME); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 5750ec34960e..c0ffb019ca8b 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -102,6 +102,20 @@ static int kvm_arm_default_max_vcpus(void) return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; } +static void set_default_csv2(struct kvm *kvm) +{ + /* + * The default is to expose CSV2 == 1 if the HW isn't affected. + * Although this is a per-CPU feature, we make it global because + * asymmetric systems are just a nuisance. + * + * Userspace can override this as long as it doesn't promise + * the impossible. + */ + if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) + kvm->arch.pfr0_csv2 = 1; +} + /** * kvm_arch_init_vm - initializes a VM data structure * @kvm: pointer to the KVM struct @@ -127,6 +141,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->arch.max_vcpus = kvm_arm_default_max_vcpus(); + set_default_csv2(kvm); + return ret; out_free_stage2_pgd: kvm_free_stage2_pgd(&kvm->arch.mmu); diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S index bb2d986ff696..a797abace13f 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S @@ -13,6 +13,11 @@ SECTIONS { HYP_SECTION(.text) + /* + * .hyp..data..percpu needs to be page aligned to maintain the same + * alignment for when linking into vmlinux. + */ + . = ALIGN(PAGE_SIZE); HYP_SECTION_NAME(.data..percpu) : { PERCPU_INPUT(L1_CACHE_BYTES) } diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 57972bdb213a..1a01da9fdc99 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -788,10 +788,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } switch (vma_shift) { +#ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE)) break; fallthrough; +#endif case CONT_PMD_SHIFT: vma_shift = PMD_SHIFT; fallthrough; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index fb12d3ef423a..c1fac9836af1 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1038,8 +1038,8 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \ access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } -static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, - const struct sys_reg_desc *r) +static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) { kvm_inject_undefined(vcpu); @@ -1047,33 +1047,25 @@ static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, } /* Macro to expand the AMU counter and type registers*/ -#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu } -#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu } -#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu } -#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu } - -static bool trap_ptrauth(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - /* - * If we land here, that is because we didn't fixup the access on exit - * by allowing the PtrAuth sysregs. The only way this happens is when - * the guest does not have PtrAuth support enabled. - */ - kvm_inject_undefined(vcpu); - - return false; -} +#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access } +#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access } +#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access } +#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access } static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN_USER | REG_HIDDEN_GUEST; + return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN; } +/* + * If we land here on a PtrAuth access, that is because we didn't + * fixup the access on exit by allowing the PtrAuth sysregs. The only + * way this happens is when the guest does not have PtrAuth support + * enabled. + */ #define __PTRAUTH_KEY(k) \ - { SYS_DESC(SYS_## k), trap_ptrauth, reset_unknown, k, \ + { SYS_DESC(SYS_## k), undef_access, reset_unknown, k, \ .visibility = ptrauth_visibility} #define PTRAUTH_KEY(k) \ @@ -1128,9 +1120,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, if (!vcpu_has_sve(vcpu)) val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT); val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT); - if (!(val & (0xfUL << ID_AA64PFR0_CSV2_SHIFT)) && - arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) - val |= (1UL << ID_AA64PFR0_CSV2_SHIFT); + val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT); + val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT); } else if (id == SYS_ID_AA64PFR1_EL1) { val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT); } else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) { @@ -1153,6 +1144,22 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, return val; } +static unsigned int id_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, + (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + + switch (id) { + case SYS_ID_AA64ZFR0_EL1: + if (!vcpu_has_sve(vcpu)) + return REG_RAZ; + break; + } + + return 0; +} + /* cpufeature ID register access trap handlers */ static bool __access_id_reg(struct kvm_vcpu *vcpu, @@ -1171,7 +1178,9 @@ static bool access_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - return __access_id_reg(vcpu, p, r, false); + bool raz = sysreg_visible_as_raz(vcpu, r); + + return __access_id_reg(vcpu, p, r, raz); } static bool access_raz_id_reg(struct kvm_vcpu *vcpu, @@ -1192,71 +1201,40 @@ static unsigned int sve_visibility(const struct kvm_vcpu *vcpu, if (vcpu_has_sve(vcpu)) return 0; - return REG_HIDDEN_USER | REG_HIDDEN_GUEST; -} - -/* Visibility overrides for SVE-specific ID registers */ -static unsigned int sve_id_visibility(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) -{ - if (vcpu_has_sve(vcpu)) - return 0; - - return REG_HIDDEN_USER; + return REG_HIDDEN; } -/* Generate the emulated ID_AA64ZFR0_EL1 value exposed to the guest */ -static u64 guest_id_aa64zfr0_el1(const struct kvm_vcpu *vcpu) -{ - if (!vcpu_has_sve(vcpu)) - return 0; - - return read_sanitised_ftr_reg(SYS_ID_AA64ZFR0_EL1); -} - -static bool access_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - if (p->is_write) - return write_to_read_only(vcpu, p, rd); - - p->regval = guest_id_aa64zfr0_el1(vcpu); - return true; -} - -static int get_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd, - const struct kvm_one_reg *reg, void __user *uaddr) -{ - u64 val; - - if (WARN_ON(!vcpu_has_sve(vcpu))) - return -ENOENT; - - val = guest_id_aa64zfr0_el1(vcpu); - return reg_to_user(uaddr, &val, reg->id); -} - -static int set_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd, - const struct kvm_one_reg *reg, void __user *uaddr) +static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) { const u64 id = sys_reg_to_index(rd); int err; u64 val; - - if (WARN_ON(!vcpu_has_sve(vcpu))) - return -ENOENT; + u8 csv2; err = reg_from_user(&val, uaddr, id); if (err) return err; - /* This is what we mean by invariant: you can't change it. */ - if (val != guest_id_aa64zfr0_el1(vcpu)) + /* + * Allow AA64PFR0_EL1.CSV2 to be set from userspace as long as + * it doesn't promise more than what is actually provided (the + * guest could otherwise be covered in ectoplasmic residue). + */ + csv2 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV2_SHIFT); + if (csv2 > 1 || + (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED)) return -EINVAL; + /* We can only differ with CSV2, and anything else is an error */ + val ^= read_id_reg(vcpu, rd, false); + val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT); + if (val) + return -EINVAL; + + vcpu->kvm->arch.pfr0_csv2 = csv2; + return 0; } @@ -1299,13 +1277,17 @@ static int __set_id_reg(const struct kvm_vcpu *vcpu, static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - return __get_id_reg(vcpu, rd, uaddr, false); + bool raz = sysreg_visible_as_raz(vcpu, rd); + + return __get_id_reg(vcpu, rd, uaddr, raz); } static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - return __set_id_reg(vcpu, rd, uaddr, false); + bool raz = sysreg_visible_as_raz(vcpu, rd); + + return __set_id_reg(vcpu, rd, uaddr, raz); } static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, @@ -1384,19 +1366,13 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } -static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ - kvm_inject_undefined(vcpu); - return false; -} - /* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \ SYS_DESC(SYS_##name), \ .access = access_id_reg, \ .get_user = get_id_reg, \ .set_user = set_id_reg, \ + .visibility = id_visibility, \ } /* @@ -1514,11 +1490,12 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* AArch64 ID registers */ /* CRm=4 */ - ID_SANITISED(ID_AA64PFR0_EL1), + { SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg, + .get_user = get_id_reg, .set_user = set_id_aa64pfr0_el1, }, ID_SANITISED(ID_AA64PFR1_EL1), ID_UNALLOCATED(4,2), ID_UNALLOCATED(4,3), - { SYS_DESC(SYS_ID_AA64ZFR0_EL1), access_id_aa64zfr0_el1, .get_user = get_id_aa64zfr0_el1, .set_user = set_id_aa64zfr0_el1, .visibility = sve_id_visibility }, + ID_SANITISED(ID_AA64ZFR0_EL1), ID_UNALLOCATED(4,5), ID_UNALLOCATED(4,6), ID_UNALLOCATED(4,7), @@ -1557,8 +1534,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 }, { SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 }, - { SYS_DESC(SYS_RGSR_EL1), access_mte_regs }, - { SYS_DESC(SYS_GCR_EL1), access_mte_regs }, + { SYS_DESC(SYS_RGSR_EL1), undef_access }, + { SYS_DESC(SYS_GCR_EL1), undef_access }, { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, @@ -1584,8 +1561,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi }, { SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi }, - { SYS_DESC(SYS_TFSR_EL1), access_mte_regs }, - { SYS_DESC(SYS_TFSRE0_EL1), access_mte_regs }, + { SYS_DESC(SYS_TFSR_EL1), undef_access }, + { SYS_DESC(SYS_TFSRE0_EL1), undef_access }, { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 }, { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, @@ -1621,6 +1598,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 }, { SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 }, + { SYS_DESC(SYS_SCXTNUM_EL1), undef_access }, + { SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0}, { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, @@ -1649,14 +1628,16 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, - { SYS_DESC(SYS_AMCR_EL0), access_amu }, - { SYS_DESC(SYS_AMCFGR_EL0), access_amu }, - { SYS_DESC(SYS_AMCGCR_EL0), access_amu }, - { SYS_DESC(SYS_AMUSERENR_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu }, + { SYS_DESC(SYS_SCXTNUM_EL0), undef_access }, + + { SYS_DESC(SYS_AMCR_EL0), undef_access }, + { SYS_DESC(SYS_AMCFGR_EL0), undef_access }, + { SYS_DESC(SYS_AMCGCR_EL0), undef_access }, + { SYS_DESC(SYS_AMUSERENR_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access }, AMU_AMEVCNTR0_EL0(0), AMU_AMEVCNTR0_EL0(1), AMU_AMEVCNTR0_EL0(2), @@ -2185,7 +2166,7 @@ static void perform_access(struct kvm_vcpu *vcpu, trace_kvm_sys_access(*vcpu_pc(vcpu), params, r); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_guest(vcpu, r)) { + if (sysreg_hidden(vcpu, r)) { kvm_inject_undefined(vcpu); return; } @@ -2684,7 +2665,7 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg return get_invariant_sys_reg(reg->id, uaddr); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_user(vcpu, r)) + if (sysreg_hidden(vcpu, r)) return -ENOENT; if (r->get_user) @@ -2709,7 +2690,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg return set_invariant_sys_reg(reg->id, uaddr); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_user(vcpu, r)) + if (sysreg_hidden(vcpu, r)) return -ENOENT; if (r->set_user) @@ -2780,7 +2761,7 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu, if (!(rd->reg || rd->get_user)) return 0; - if (sysreg_hidden_from_user(vcpu, rd)) + if (sysreg_hidden(vcpu, rd)) return 0; if (!copy_reg_to_user(rd, uind)) diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index 5a6fc30f5989..0f95964339b1 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -59,8 +59,8 @@ struct sys_reg_desc { const struct sys_reg_desc *rd); }; -#define REG_HIDDEN_USER (1 << 0) /* hidden from userspace ioctls */ -#define REG_HIDDEN_GUEST (1 << 1) /* hidden from guest */ +#define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ +#define REG_RAZ (1 << 1) /* RAZ from userspace and guest */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, @@ -111,22 +111,22 @@ static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r __vcpu_sys_reg(vcpu, r->reg) = r->val; } -static inline bool sysreg_hidden_from_guest(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *r) +static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; - return r->visibility(vcpu, r) & REG_HIDDEN_GUEST; + return r->visibility(vcpu, r) & REG_HIDDEN; } -static inline bool sysreg_hidden_from_user(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *r) +static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; - return r->visibility(vcpu, r) & REG_HIDDEN_USER; + return r->visibility(vcpu, r) & REG_RAZ; } static inline int cmp_sys_reg(const struct sys_reg_desc *i1, diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 52d6f24f65dc..15a6c98ee92f 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -273,6 +273,23 @@ static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, return extract_bytes(value, addr & 7, len); } +static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + int target_vcpu_id = vcpu->vcpu_id; + u64 value; + + value = (u64)(mpidr & GENMASK(23, 0)) << 32; + value |= ((target_vcpu_id & 0xffff) << 8); + + if (vgic_has_its(vcpu->kvm)) + value |= GICR_TYPER_PLPIS; + + /* reporting of the Last bit is not supported for userspace */ + return extract_bytes(value, addr & 7, len); +} + static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { @@ -593,8 +610,9 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { REGISTER_DESC_WITH_LENGTH(GICR_IIDR, vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_TYPER, - vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8, + REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER, + vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, + vgic_uaccess_read_v3r_typer, vgic_mmio_uaccess_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_WAKER, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 1c0f3e02f731..ca692a815731 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1444,11 +1444,28 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) free_empty_tables(start, end, PAGE_OFFSET, PAGE_END); } +static bool inside_linear_region(u64 start, u64 size) +{ + /* + * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)] + * accommodating both its ends but excluding PAGE_END. Max physical + * range which can be mapped inside this linear mapping range, must + * also be derived from its end points. + */ + return start >= __pa(_PAGE_OFFSET(vabits_actual)) && + (start + size - 1) <= __pa(PAGE_END - 1); +} + int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) { int ret, flags = 0; + if (!inside_linear_region(start, size)) { + pr_err("[%llx %llx] is outside linear mapping region\n", start, start + size); + return -EINVAL; + } + if (rodata_full || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c index eb32838b8210..09b7f88a2d6a 100644 --- a/arch/csky/kernel/perf_regs.c +++ b/arch/csky/kernel/perf_regs.c @@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index f730869e21ee..69af6bc87e64 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -102,6 +102,6 @@ void arch_cpu_idle(void) #ifdef CONFIG_CPU_PM_STOP asm volatile("stop\n"); #endif - local_irq_enable(); + raw_local_irq_enable(); } #endif diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index aea0a40b77a9..bc1364db58fe 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -57,7 +57,7 @@ asmlinkage void ret_from_kernel_thread(void); */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); __asm__("sleep"); } diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 5a0a95d93ddb..67767c5ed98c 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -44,7 +44,7 @@ void arch_cpu_idle(void) { __vmwait(); /* interrupts wake us up, but irqs are still disabled */ - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index 336d0570e1fa..dd8c166ffd7b 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -18,4 +18,10 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifdef CONFIG_MEMORY_HOTPLUG +int memory_add_physaddr_to_nid(u64 addr); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif + #endif /* _ASM_IA64_SPARSEMEM_H */ diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6b61a703bcf5..c9ff8796b509 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -239,7 +239,7 @@ void arch_cpu_idle(void) if (mark_idle) (*mark_idle)(1); - safe_halt(); + raw_safe_halt(); if (mark_idle) (*mark_idle)(0); diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index a9e46e525cd0..f99860771ff4 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -149,5 +149,5 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpregs) void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c index a95a894aceaf..f0c830337104 100644 --- a/arch/mips/alchemy/common/clock.c +++ b/arch/mips/alchemy/common/clock.c @@ -152,6 +152,7 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, { struct clk_init_data id; struct clk_hw *h; + struct clk *clk; h = kzalloc(sizeof(*h), GFP_KERNEL); if (!h) @@ -164,7 +165,13 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, id.ops = &alchemy_clkops_cpu; h->init = &id; - return clk_register(NULL, h); + clk = clk_register(NULL, h); + if (IS_ERR(clk)) { + pr_err("failed to register clock\n"); + kfree(h); + } + + return clk; } /* AUXPLLs ************************************************************/ diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index a950fc1ddb4d..6c0532d7b211 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -154,6 +154,7 @@ static inline void pmd_clear(pmd_t *pmdp) #if defined(CONFIG_XPA) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 #define pte_pfn(x) (((unsigned long)((x).pte_high >> _PFN_SHIFT)) | (unsigned long)((x).pte_low << _PAGE_PRESENT_SHIFT)) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) @@ -169,6 +170,7 @@ pfn_pte(unsigned long pfn, pgprot_t prot) #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #define pte_pfn(x) ((unsigned long)((x).pte_high >> 6)) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) @@ -183,6 +185,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) #else +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #ifdef CONFIG_CPU_VR41XX #define pte_pfn(x) ((unsigned long)((x).pte >> (PAGE_SHIFT + 2))) #define pfn_pte(pfn, prot) __pte(((pfn) << (PAGE_SHIFT + 2)) | pgprot_val(prot)) diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 5bc3b04693c7..18e69ebf5691 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -33,19 +33,19 @@ static void __cpuidle r3081_wait(void) { unsigned long cfg = read_c0_conf(); write_c0_conf(cfg | R30XX_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } static void __cpuidle r39xx_wait(void) { if (!need_resched()) write_c0_conf(read_c0_conf() | TX39_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } void __cpuidle r4k_wait(void) { - local_irq_enable(); + raw_local_irq_enable(); __r4k_wait(); } @@ -64,7 +64,7 @@ void __cpuidle r4k_wait_irqoff(void) " .set arch=r4000 \n" " wait \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -84,7 +84,7 @@ static void __cpuidle rm7k_wait_irqoff(void) " wait \n" " mtc0 $1, $12 # stalls until W stage \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -257,7 +257,7 @@ void arch_cpu_idle(void) if (cpu_wait) cpu_wait(); else - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_CPU_IDLE diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 0d4253208bde..ca579deef939 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -262,8 +262,8 @@ static void __init bootmem_init(void) static void __init bootmem_init(void) { phys_addr_t ramstart, ramend; - phys_addr_t start, end; - u64 i; + unsigned long start, end; + int i; ramstart = memblock_start_of_DRAM(); ramend = memblock_end_of_DRAM(); @@ -300,7 +300,7 @@ static void __init bootmem_init(void) min_low_pfn = ARCH_PFN_OFFSET; max_pfn = PFN_DOWN(ramend); - for_each_mem_range(i, &start, &end) { + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { /* * Skip highmem here so we get an accurate max_low_pfn if low * memory stops short of high memory. diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 38e2894d5fa3..1b939abbe4ca 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -438,6 +438,7 @@ int has_transparent_hugepage(void) } return mask == PM_HUGE_MASK; } +EXPORT_SYMBOL(has_transparent_hugepage); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 4ffe857e6ada..50b4eb19a6cc 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 0ff391f00334..3c98728cce24 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -79,7 +79,7 @@ void machine_power_off(void) */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); if (mfspr(SPR_UPR) & SPR_UPR_PMP) mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME); } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index f196d96e2f9f..a92a23d6acd9 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -169,7 +169,7 @@ void __cpuidle arch_cpu_idle_dead(void) void __cpuidle arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); /* nop on real hardware, qemu will idle sleep. */ asm volatile("or %%r10,%%r10,%%r10\n":::); diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index a4d56f0a41d9..16b8336f91dd 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -248,7 +248,6 @@ KBUILD_CFLAGS += $(call cc-option,-mno-string) cpu-as-$(CONFIG_40x) += -Wa,-m405 cpu-as-$(CONFIG_44x) += -Wa,-m440 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) -cpu-as-$(CONFIG_E200) += -Wa,-me200 cpu-as-$(CONFIG_E500) += -Wa,-me500 # When using '-many -mpower4' gas will first try and find a matching power4 diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 36443cda8dcf..1376be95e975 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -36,8 +36,10 @@ static inline bool pte_user(pte_t pte) */ #ifdef CONFIG_PTE_64BIT #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index 3ee1ec60be84..a39e2d193fdc 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -27,6 +27,7 @@ #endif .endm +#ifdef CONFIG_PPC_KUAP .macro kuap_check_amr gpr1, gpr2 #ifdef CONFIG_PPC_KUAP_DEBUG BEGIN_MMU_FTR_SECTION_NESTED(67) @@ -38,6 +39,7 @@ END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) #endif .endm +#endif .macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr #ifdef CONFIG_PPC_KUAP @@ -61,6 +63,10 @@ #else /* !__ASSEMBLY__ */ +#include <linux/jump_label.h> + +DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); + #ifdef CONFIG_PPC_KUAP #include <asm/mmu.h> @@ -103,8 +109,16 @@ static inline void kuap_check_amr(void) static inline unsigned long get_kuap(void) { + /* + * We return AMR_KUAP_BLOCKED when we don't support KUAP because + * prevent_user_access_return needs to return AMR_KUAP_BLOCKED to + * cause restore_user_access to do a flush. + * + * This has no effect in terms of actually blocking things on hash, + * so it doesn't break anything. + */ if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP)) - return 0; + return AMR_KUAP_BLOCKED; return mfspr(SPRN_AMR); } @@ -123,6 +137,29 @@ static inline void set_kuap(unsigned long value) isync(); } +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && + (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), + "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); +} +#else /* CONFIG_PPC_KUAP */ +static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) { } + +static inline unsigned long kuap_get_and_check_amr(void) +{ + return 0UL; +} + +static inline unsigned long get_kuap(void) +{ + return AMR_KUAP_BLOCKED; +} + +static inline void set_kuap(unsigned long value) { } +#endif /* !CONFIG_PPC_KUAP */ + static __always_inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { @@ -142,6 +179,8 @@ static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); } static inline unsigned long prevent_user_access_return(void) @@ -149,6 +188,8 @@ static inline unsigned long prevent_user_access_return(void) unsigned long flags = get_kuap(); set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); return flags; } @@ -156,30 +197,9 @@ static inline unsigned long prevent_user_access_return(void) static inline void restore_user_access(unsigned long flags) { set_kuap(flags); + if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED) + do_uaccess_flush(); } - -static inline bool -bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) -{ - return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && - (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), - "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); -} -#else /* CONFIG_PPC_KUAP */ -static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) -{ -} - -static inline void kuap_check_amr(void) -{ -} - -static inline unsigned long kuap_get_and_check_amr(void) -{ - return 0; -} -#endif /* CONFIG_PPC_KUAP */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index ebe95aa04d53..1d32b174ab6a 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -57,11 +57,18 @@ nop; \ nop +#define ENTRY_FLUSH_SLOT \ + ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ #define INTERRUPT_TO_KERNEL \ - STF_ENTRY_BARRIER_SLOT + STF_ENTRY_BARRIER_SLOT; \ + ENTRY_FLUSH_SLOT /* * Macros for annotating the expected destination of (h)rfid @@ -137,6 +144,9 @@ RFSCV; \ b rfscv_flush_fallback +#else /* __ASSEMBLY__ */ +/* Prototype for function defined in exceptions-64s.S */ +void do_uaccess_flush(void); #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_EXCEPTION_H */ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index b0af97add751..fbd406cd6916 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -205,6 +205,22 @@ label##3: \ FTR_ENTRY_OFFSET 955b-956b; \ .popsection; +#define UACCESS_FLUSH_FIXUP_SECTION \ +959: \ + .pushsection __uaccess_flush_fixup,"a"; \ + .align 2; \ +960: \ + FTR_ENTRY_OFFSET 959b-960b; \ + .popsection; + +#define ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -237,8 +253,11 @@ label##3: \ #include <linux/types.h> extern long stf_barrier_fallback; +extern long entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; +extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; +extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 1d0f7d838b2e..0d93331d0fab 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -14,7 +14,7 @@ #define KUAP_CURRENT_WRITE 8 #define KUAP_CURRENT (KUAP_CURRENT_READ | KUAP_CURRENT_WRITE) -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S_64 #include <asm/book3s/64/kup-radix.h> #endif #ifdef CONFIG_PPC_8xx @@ -35,6 +35,9 @@ .macro kuap_check current, gpr .endm +.macro kuap_check_amr gpr1, gpr2 +.endm + #endif #else /* !__ASSEMBLY__ */ @@ -53,17 +56,28 @@ static inline void setup_kuep(bool disabled) { } void setup_kuap(bool disabled); #else static inline void setup_kuap(bool disabled) { } + +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return false; +} + +static inline void kuap_check_amr(void) { } + +/* + * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush + * the L1D cache after user accesses. Only include the empty stubs for other + * platforms. + */ +#ifndef CONFIG_PPC_BOOK3S_64 static inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline unsigned long prevent_user_access_return(void) { return 0UL; } static inline void restore_user_access(unsigned long flags) { } -static inline bool -bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) -{ - return false; -} +#endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* CONFIG_PPC_KUAP */ static inline void allow_read_from_user(const void __user *from, unsigned long size) diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 91c69ff53a8a..6cda76b57c5d 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -46,5 +46,10 @@ u64 memory_hotplug_max(void); #define __HAVE_ARCH_RESERVED_KERNEL_PAGES #endif +#ifdef CONFIG_MEMORY_HOTPLUG +extern int create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index 85ed2390fb99..567cdc557402 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -63,7 +63,7 @@ static inline void restore_user_access(unsigned long flags) static inline bool bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { - return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000), + return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xff000000), "Bug: fault blocked by AP register !"); } diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h index 1d9ac0f9c794..0bd1b144eb76 100644 --- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h @@ -33,19 +33,18 @@ * respectively NA for All or X for Supervisor and no access for User. * Then we use the APG to say whether accesses are according to Page rules or * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * 2-15 => Not Used - */ -#define MI_APG_INIT 0x40000000 - -/* - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 10 (all accesses performed according to swaped page definition) - * 2-15 => Not Used - */ -#define MI_APG_KUEP 0x60000000 + * _PAGE_ACCESSED is also managed via APG. When _PAGE_ACCESSED is not set, say + * "all User" rules, that will lead to NA for all. + * Therefore, we define 4 APG groups. lsb is _PAGE_ACCESSED + * 0 => Kernel => 11 (all accesses performed according as user iaw page definition) + * 1 => Kernel+Accessed => 01 (all accesses performed according to page definition) + * 2 => User => 11 (all accesses performed according as user iaw page definition) + * 3 => User+Accessed => 00 (all accesses performed as supervisor iaw page definition) for INIT + * => 10 (all accesses performed according to swaped page definition) for KUEP + * 4-15 => Not Used + */ +#define MI_APG_INIT 0xdc000000 +#define MI_APG_KUEP 0xde000000 /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MI_RPN is written, bits in @@ -106,25 +105,9 @@ #define MD_Ks 0x80000000 /* Should not be set */ #define MD_Kp 0x40000000 /* Should always be set */ -/* - * All pages' PP data bits are set to either 000 or 011 or 001, which means - * respectively RW for Supervisor and no access for User, or RO for - * Supervisor and no access for user and NA for ALL. - * Then we use the APG to say whether accesses are according to Page rules or - * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * 2-15 => Not Used - */ -#define MD_APG_INIT 0x40000000 - -/* - * 0 => No user => 01 (all accesses performed according to page definition) - * 1 => User => 10 (all accesses performed according to swaped page definition) - * 2-15 => Not Used - */ -#define MD_APG_KUAP 0x60000000 +/* See explanation above at the definition of MI_APG_INIT */ +#define MD_APG_INIT 0xdc000000 +#define MD_APG_KUAP 0xde000000 /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MD_RPN is written, bits in diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index ee2243ba96cf..96522f7f0618 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -153,8 +153,10 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index 66f403a7da44..1581204467e1 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -39,9 +39,9 @@ * into the TLB. */ #define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */ -#define _PAGE_SPECIAL 0x0020 /* SW entry */ +#define _PAGE_ACCESSED 0x0020 /* Copied to L1 APG 1 entry in I/DTLB */ #define _PAGE_EXEC 0x0040 /* Copied to PP (bit 21) in ITLB */ -#define _PAGE_ACCESSED 0x0080 /* software: page referenced */ +#define _PAGE_SPECIAL 0x0080 /* SW entry */ #define _PAGE_NA 0x0200 /* Supervisor NA, User no access */ #define _PAGE_RO 0x0600 /* Supervisor RO, User no access */ @@ -59,11 +59,12 @@ #define _PMD_PRESENT 0x0001 #define _PMD_PRESENT_MASK _PMD_PRESENT -#define _PMD_BAD 0x0fd0 +#define _PMD_BAD 0x0f90 #define _PMD_PAGE_MASK 0x000c #define _PMD_PAGE_8M 0x000c #define _PMD_PAGE_512K 0x0004 -#define _PMD_USER 0x0020 /* APG 1 */ +#define _PMD_ACCESSED 0x0020 /* APG 1 */ +#define _PMD_USER 0x0040 /* APG 2 */ #define _PTE_NONE_MASK 0 diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index fbb8fa32150f..b774a4477d5f 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -86,12 +86,19 @@ static inline bool security_ftr_enabled(u64 feature) // Software required to flush link stack on context switch #define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull +// The L1-D cache should be flushed when entering the kernel +#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull + +// The L1-D cache should be flushed after user accesses from the kernel +#define SEC_FTR_L1D_FLUSH_UACCESS 0x0000000000008000ull // Features enabled by default #define SEC_FTR_DEFAULT \ (SEC_FTR_L1D_FLUSH_HV | \ SEC_FTR_L1D_FLUSH_PR | \ SEC_FTR_BNDS_CHK_SPEC_BAR | \ + SEC_FTR_L1D_FLUSH_ENTRY | \ + SEC_FTR_L1D_FLUSH_UACCESS | \ SEC_FTR_FAVOUR_SECURITY) #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 9efbddee2bca..a466749703f1 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -52,12 +52,16 @@ enum l1d_flush_type { }; void setup_rfi_flush(enum l1d_flush_type, bool enable); +void setup_entry_flush(bool enable); +void setup_uaccess_flush(bool enable); void do_rfi_flush_fixups(enum l1d_flush_type types); #ifdef CONFIG_PPC_BARRIER_NOSPEC void setup_barrier_nospec(void); #else static inline void setup_barrier_nospec(void) { }; #endif +void do_uaccess_flush_fixups(enum l1d_flush_type types); +void do_entry_flush_fixups(enum l1d_flush_type types); void do_barrier_nospec_fixups(bool enable); extern bool barrier_nospec_enabled; diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 1e6fa371cc38..d072866842e4 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -13,9 +13,9 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG -extern int create_section_mapping(unsigned long start, unsigned long end, - int nid, pgprot_t prot); extern int remove_section_mapping(unsigned long start, unsigned long end); +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); @@ -26,6 +26,5 @@ static inline int hot_add_scn_to_nid(unsigned long scn_addr) } #endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_SPARSEMEM_H */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 8728590f514a..3beeb030cd78 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -6,6 +6,7 @@ struct device; struct device_node; +struct drmem_lmb; #ifdef CONFIG_NUMA @@ -61,6 +62,9 @@ static inline int early_cpu_to_node(int cpu) */ return (nid < 0) ? 0 : nid; } + +int of_drconf_to_nid_single(struct drmem_lmb *lmb); + #else static inline int early_cpu_to_node(int cpu) { return 0; } @@ -84,10 +88,12 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) return 0; } -#endif /* CONFIG_NUMA */ +static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb) +{ + return first_online_node; +} -struct drmem_lmb; -int of_drconf_to_nid_single(struct drmem_lmb *lmb); +#endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int find_and_online_cpu_nid(int cpu); diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index ef5bbb705c08..501c9a79038c 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -178,7 +178,7 @@ do { \ * are no aliasing issues. */ #define __put_user_asm_goto(x, addr, label, op) \ - asm volatile goto( \ + asm_volatile_goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -191,7 +191,7 @@ do { \ __put_user_asm_goto(x, ptr, label, "std") #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ - asm volatile goto( \ + asm_volatile_goto( \ "1: stw%X1 %0, %1\n" \ "2: stw%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index 6b50bf15d8c1..bf3270426d82 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -264,8 +264,9 @@ static int eeh_addr_cache_show(struct seq_file *s, void *v) { struct pci_io_addr_range *piar; struct rb_node *n; + unsigned long flags; - spin_lock(&pci_io_addr_cache_root.piar_lock); + spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); for (n = rb_first(&pci_io_addr_cache_root.rb_root); n; n = rb_next(n)) { piar = rb_entry(n, struct pci_io_addr_range, rb_node); @@ -273,7 +274,7 @@ static int eeh_addr_cache_show(struct seq_file *s, void *v) (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev)); } - spin_unlock(&pci_io_addr_cache_root.piar_lock); + spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); return 0; } diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f7d748b88705..4d01f09ecf80 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1000,8 +1000,6 @@ TRAMP_REAL_BEGIN(system_reset_idle_wake) * Vectors for the FWNMI option. Share common code. */ TRAMP_REAL_BEGIN(system_reset_fwnmi) - /* XXX: fwnmi guest could run a nested/PR guest, so why no test? */ - __IKVM_REAL(system_reset)=0 GEN_INT_ENTRY system_reset, virt=0 #endif /* CONFIG_PPC_PSERIES */ @@ -1412,6 +1410,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) * If none is found, do a Linux page fault. Linux page faults can happen in * kernel mode due to user copy operations of course. * + * KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest + * MMU context, which may cause a DSI in the host, which must go to the + * KVM handler. MSR[IR] is not enabled, so the real-mode handler will + * always be used regardless of AIL setting. + * * - Radix MMU * The hardware loads from the Linux page table directly, so a fault goes * immediately to Linux page fault. @@ -1422,10 +1425,8 @@ INT_DEFINE_BEGIN(data_access) IVEC=0x300 IDAR=1 IDSISR=1 -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_SKIP=1 IKVM_REAL=1 -#endif INT_DEFINE_END(data_access) EXC_REAL_BEGIN(data_access, 0x300, 0x80) @@ -1464,6 +1465,8 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) * ppc64_bolted_size (first segment). The kernel handler must avoid stomping * on user-handler data structures. * + * KVM: Same as 0x300, DSLB must test for KVM guest. + * * A dedicated save area EXSLB is used (XXX: but it actually need not be * these days, we could use EXGEN). */ @@ -1472,10 +1475,8 @@ INT_DEFINE_BEGIN(data_access_slb) IAREA=PACA_EXSLB IRECONCILE=0 IDAR=1 -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_SKIP=1 IKVM_REAL=1 -#endif INT_DEFINE_END(data_access_slb) EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) @@ -2951,15 +2952,8 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback) .endr blr -TRAMP_REAL_BEGIN(rfi_flush_fallback) - SET_SCRATCH0(r13); - GET_PACA(r13); - std r1,PACA_EXRFI+EX_R12(r13) - ld r1,PACAKSAVE(r13) - std r9,PACA_EXRFI+EX_R9(r13) - std r10,PACA_EXRFI+EX_R10(r13) - std r11,PACA_EXRFI+EX_R11(r13) - mfctr r9 +/* Clobbers r10, r11, ctr */ +.macro L1D_DISPLACEMENT_FLUSH ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) ld r11,PACA_L1D_FLUSH_SIZE(r13) srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ @@ -2970,7 +2964,7 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) sync /* - * The load adresses are at staggered offsets within cachelines, + * The load addresses are at staggered offsets within cachelines, * which suits some pipelines better (on others it should not * hurt). */ @@ -2985,7 +2979,30 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) ld r11,(0x80 + 8)*7(r10) addi r10,r10,0x80*8 bdnz 1b +.endm +TRAMP_REAL_BEGIN(entry_flush_fallback) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + blr + +TRAMP_REAL_BEGIN(rfi_flush_fallback) + SET_SCRATCH0(r13); + GET_PACA(r13); + std r1,PACA_EXRFI+EX_R12(r13) + ld r1,PACAKSAVE(r13) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -3003,32 +3020,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) mfctr r9 - ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) - ld r11,PACA_L1D_FLUSH_SIZE(r13) - srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ - mtctr r11 - DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ - - /* order ld/st prior to dcbt stop all streams with flushing */ - sync - - /* - * The load adresses are at staggered offsets within cachelines, - * which suits some pipelines better (on others it should not - * hurt). - */ -1: - ld r11,(0x80 + 8)*0(r10) - ld r11,(0x80 + 8)*1(r10) - ld r11,(0x80 + 8)*2(r10) - ld r11,(0x80 + 8)*3(r10) - ld r11,(0x80 + 8)*4(r10) - ld r11,(0x80 + 8)*5(r10) - ld r11,(0x80 + 8)*6(r10) - ld r11,(0x80 + 8)*7(r10) - addi r10,r10,0x80*8 - bdnz 1b - + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -3079,8 +3071,21 @@ TRAMP_REAL_BEGIN(rfscv_flush_fallback) RFSCV USE_TEXT_SECTION() - MASKED_INTERRUPT - MASKED_INTERRUPT hsrr=1 + +_GLOBAL(do_uaccess_flush) + UACCESS_FLUSH_FIXUP_SECTION + nop + nop + nop + blr + L1D_DISPLACEMENT_FLUSH + blr +_ASM_NOKPROBE_SYMBOL(do_uaccess_flush) +EXPORT_SYMBOL(do_uaccess_flush) + + +MASKED_INTERRUPT +MASKED_INTERRUPT hsrr=1 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER kvmppc_skip_interrupt: diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 44c9018aed1b..a1ae00689e0f 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -284,11 +284,7 @@ _ENTRY(saved_ksp_limit) rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */ lwz r11, 0(r11) /* Get Linux PTE */ -#ifdef CONFIG_SWAP li r9, _PAGE_PRESENT | _PAGE_ACCESSED -#else - li r9, _PAGE_PRESENT -#endif andc. r9, r9, r11 /* Check permission */ bne 5f @@ -369,11 +365,7 @@ _ENTRY(saved_ksp_limit) rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */ lwz r11, 0(r11) /* Get Linux PTE */ -#ifdef CONFIG_SWAP li r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#else - li r9, _PAGE_PRESENT | _PAGE_EXEC -#endif andc. r9, r9, r11 /* Check permission */ bne 5f diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 9f359d3fba74..ee0bfebc375f 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -202,9 +202,7 @@ SystemCall: InstructionTLBMiss: mtspr SPRN_SPRG_SCRATCH0, r10 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS) mtspr SPRN_SPRG_SCRATCH1, r11 -#endif /* If we are faulting a kernel address, we have to use the * kernel page tables. @@ -224,25 +222,13 @@ InstructionTLBMiss: 3: mtcr r11 #endif -#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT) lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ mtspr SPRN_MD_TWC, r11 -#else - lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ - mtspr SPRN_MI_TWC, r10 /* Set segment attributes */ - mtspr SPRN_MD_TWC, r10 -#endif mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ -#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT) + rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K mtspr SPRN_MI_TWC, r11 -#endif -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT - and r11, r11, r10 - rlwimi r10, r11, 0, _PAGE_PRESENT -#endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 20 and 23 must be clear. * Software indicator bits 22, 24, 25, 26, and 27 must be @@ -256,9 +242,7 @@ InstructionTLBMiss: /* Restore registers */ 0: mfspr r10, SPRN_SPRG_SCRATCH0 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS) mfspr r11, SPRN_SPRG_SCRATCH1 -#endif rfi patch_site 0b, patch__itlbmiss_exit_1 @@ -268,9 +252,7 @@ InstructionTLBMiss: addi r10, r10, 1 stw r10, (itlb_miss_counter - PAGE_OFFSET)@l(0) mfspr r10, SPRN_SPRG_SCRATCH0 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) mfspr r11, SPRN_SPRG_SCRATCH1 -#endif rfi #endif @@ -297,30 +279,16 @@ DataStoreTLBMiss: mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ - /* Insert the Guarded flag into the TWC from the Linux PTE. + /* Insert Guarded and Accessed flags into the TWC from the Linux PTE. * It is bit 27 of both the Linux PTE and the TWC (at least * I got that right :-). It will be better when we can put * this into the Linux pgd/pmd and load it in the operation * above. */ - rlwimi r11, r10, 0, _PAGE_GUARDED + rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K mtspr SPRN_MD_TWC, r11 - /* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set. - * We also need to know if the insn is a load/store, so: - * Clear _PAGE_PRESENT and load that which will - * trap into DTLB Error with store bit set accordinly. - */ - /* PRESENT=0x1, ACCESSED=0x20 - * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5)); - * r10 = (r10 & ~PRESENT) | r11; - */ -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT - and r11, r11, r10 - rlwimi r10, r11, 0, _PAGE_PRESENT -#endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior @@ -711,7 +679,7 @@ initial_mmu: li r9, 4 /* up to 4 pages of 8M */ mtctr r9 lis r9, KERNELBASE@h /* Create vaddr for TLB */ - li r10, MI_PS8MEG | MI_SVALID /* Set 8M byte page */ + li r10, MI_PS8MEG | _PMD_ACCESSED | MI_SVALID li r11, MI_BOOTINIT /* Create RPN for address 0 */ 1: mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */ @@ -775,7 +743,7 @@ _GLOBAL(mmu_pin_tlb) #ifdef CONFIG_PIN_TLB_TEXT LOAD_REG_IMMEDIATE(r5, 28 << 8) LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET) - LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG) + LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED) LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT) LOAD_REG_ADDR(r9, _sinittext) li r0, 4 @@ -797,7 +765,7 @@ _GLOBAL(mmu_pin_tlb) LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM) #ifdef CONFIG_PIN_TLB_DATA LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET) - LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG) + LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED) #ifdef CONFIG_PIN_TLB_IMMR li r0, 3 #else @@ -834,7 +802,7 @@ _GLOBAL(mmu_pin_tlb) #endif #ifdef CONFIG_PIN_TLB_IMMR LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID) - LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED) + LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED | _PMD_ACCESSED) mfspr r8, SPRN_IMMR rlwinm r8, r8, 0, 0xfff80000 ori r8, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \ diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 5eb9eedac920..a0dda2a1f2df 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -156,6 +156,7 @@ __after_mmu_off: bl initial_bats bl load_segment_registers BEGIN_MMU_FTR_SECTION + bl reloc_offset bl early_hash_table END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) #if defined(CONFIG_BOOTX_TEXT) @@ -457,11 +458,7 @@ InstructionTLBMiss: cmplw 0,r1,r3 #endif mfspr r2, SPRN_SPRG_PGDIR -#ifdef CONFIG_SWAP li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#else - li r1,_PAGE_PRESENT | _PAGE_EXEC -#endif #if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ @@ -523,11 +520,7 @@ DataLoadTLBMiss: lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SPRG_PGDIR -#ifdef CONFIG_SWAP li r1, _PAGE_PRESENT | _PAGE_ACCESSED -#else - li r1, _PAGE_PRESENT -#endif bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ @@ -603,11 +596,7 @@ DataStoreTLBMiss: lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SPRG_PGDIR -#ifdef CONFIG_SWAP li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED -#else - li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT -#endif bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ @@ -932,7 +921,7 @@ early_hash_table: ori r6, r6, 3 /* 256kB table */ mtspr SPRN_SDR1, r6 lis r6, early_hash@h - lis r3, Hash@ha + addis r3, r3, Hash@ha stw r6, Hash@l(r3) blr diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index ae0e2632393d..1f835539fda4 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -52,9 +52,9 @@ void arch_cpu_idle(void) * interrupts enabled, some don't. */ if (irqs_disabled()) - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); /* * Go into low thread priority and possibly * low power mode. diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index bb9cab3641d7..74fd47f46fa5 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -945,7 +945,13 @@ early_initcall(disable_hardlockup_detector); static enum l1d_flush_type enabled_flush_types; static void *l1d_flush_fallback_area; static bool no_rfi_flush; +static bool no_entry_flush; +static bool no_uaccess_flush; bool rfi_flush; +bool entry_flush; +bool uaccess_flush; +DEFINE_STATIC_KEY_FALSE(uaccess_flush_key); +EXPORT_SYMBOL(uaccess_flush_key); static int __init handle_no_rfi_flush(char *p) { @@ -955,6 +961,22 @@ static int __init handle_no_rfi_flush(char *p) } early_param("no_rfi_flush", handle_no_rfi_flush); +static int __init handle_no_entry_flush(char *p) +{ + pr_info("entry-flush: disabled on command line."); + no_entry_flush = true; + return 0; +} +early_param("no_entry_flush", handle_no_entry_flush); + +static int __init handle_no_uaccess_flush(char *p) +{ + pr_info("uaccess-flush: disabled on command line."); + no_uaccess_flush = true; + return 0; +} +early_param("no_uaccess_flush", handle_no_uaccess_flush); + /* * The RFI flush is not KPTI, but because users will see doco that says to use * nopti we hijack that option here to also disable the RFI flush. @@ -986,6 +1008,32 @@ void rfi_flush_enable(bool enable) rfi_flush = enable; } +void entry_flush_enable(bool enable) +{ + if (enable) { + do_entry_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else { + do_entry_flush_fixups(L1D_FLUSH_NONE); + } + + entry_flush = enable; +} + +void uaccess_flush_enable(bool enable) +{ + if (enable) { + do_uaccess_flush_fixups(enabled_flush_types); + static_branch_enable(&uaccess_flush_key); + on_each_cpu(do_nothing, NULL, 1); + } else { + static_branch_disable(&uaccess_flush_key); + do_uaccess_flush_fixups(L1D_FLUSH_NONE); + } + + uaccess_flush = enable; +} + static void __ref init_fallback_flush(void) { u64 l1d_size, limit; @@ -1044,10 +1092,28 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable) enabled_flush_types = types; - if (!no_rfi_flush && !cpu_mitigations_off()) + if (!cpu_mitigations_off() && !no_rfi_flush) rfi_flush_enable(enable); } +void setup_entry_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_entry_flush) + entry_flush_enable(enable); +} + +void setup_uaccess_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_uaccess_flush) + uaccess_flush_enable(enable); +} + #ifdef CONFIG_DEBUG_FS static int rfi_flush_set(void *data, u64 val) { @@ -1075,9 +1141,63 @@ static int rfi_flush_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); +static int entry_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != entry_flush) + entry_flush_enable(enable); + + return 0; +} + +static int entry_flush_get(void *data, u64 *val) +{ + *val = entry_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n"); + +static int uaccess_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != uaccess_flush) + uaccess_flush_enable(enable); + + return 0; +} + +static int uaccess_flush_get(void *data, u64 *val) +{ + *val = uaccess_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n"); + static __init int rfi_flush_debugfs_init(void) { debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush); + debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush); return 0; } device_initcall(rfi_flush_debugfs_init); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 3c6b9822f978..8c2857cbd960 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1393,13 +1393,14 @@ static void add_cpu_to_masks(int cpu) /* Activate a secondary processor. */ void start_secondary(void *unused) { - unsigned int cpu = smp_processor_id(); + unsigned int cpu = raw_smp_processor_id(); mmgrab(&init_mm); current->active_mm = &init_mm; smp_store_cpu_info(cpu); set_dec(tb_ticks_per_jiffy); + rcu_cpu_starting(cpu); preempt_disable(); cpu_callin_map[cpu] = 1; diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c index 8e50818aa50b..310bcd768cd5 100644 --- a/arch/powerpc/kernel/syscall_64.c +++ b/arch/powerpc/kernel/syscall_64.c @@ -2,7 +2,7 @@ #include <linux/err.h> #include <asm/asm-prototypes.h> -#include <asm/book3s/64/kup-radix.h> +#include <asm/kup.h> #include <asm/cputime.h> #include <asm/hw_irq.h> #include <asm/kprobes.h> diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index e0548b4950de..6db90cdf11da 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -132,6 +132,20 @@ SECTIONS } . = ALIGN(8); + __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) { + __start___uaccess_flush_fixup = .; + *(__uaccess_flush_fixup) + __stop___uaccess_flush_fixup = .; + } + + . = ALIGN(8); + __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) { + __start___entry_flush_fixup = .; + *(__entry_flush_fixup) + __stop___entry_flush_fixup = .; + } + + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; *(__stf_exit_barrier_fixup) diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index d0c2db0e07fa..a59a94f02733 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -251,6 +251,13 @@ static vm_fault_t xive_native_esb_fault(struct vm_fault *vmf) } state = &sb->irq_state[src]; + + /* Some sanity checking */ + if (!state->valid) { + pr_devel("%s: source %lx invalid !\n", __func__, irq); + return VM_FAULT_SIGBUS; + } + kvmppc_xive_select_irq(state, &hw_num, &xd); arch_spin_lock(&sb->lock); diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 4c0a7ee9fa00..321c12a9ef6b 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -234,6 +234,110 @@ void do_stf_barrier_fixups(enum stf_barrier_type types) do_stf_exit_barrier_fixups(types); } +void do_uaccess_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[4], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___uaccess_flush_fixup); + end = PTRRELOC(&__stop___uaccess_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + instrs[3] = 0x4e800020; /* blr */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[3] = 0x60000000; /* nop */ + /* fallthrough to fallback flush */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)(dest + 3), ppc_inst(instrs[3])); + } + + printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); +} + +void do_entry_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[3], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[i++] = 0x7d4802a6; /* mflr r10 */ + instrs[i++] = 0x60000000; /* branch patched below */ + instrs[i++] = 0x7d4803a6; /* mtlr r10 */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); +} + void do_rfi_flush_fixups(enum l1d_flush_type types) { unsigned int instrs[3], *dest; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 01ec2a252f09..3fc325bebe4d 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -50,6 +50,7 @@ #include <asm/rtas.h> #include <asm/kasan.h> #include <asm/svm.h> +#include <asm/mmzone.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 9ed4fcccf8a9..7b25548ec42b 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1336,7 +1336,7 @@ static void dump_trace_imc_data(struct perf_event *event) /* If this is a valid record, create the sample */ struct perf_output_handle handle; - if (perf_output_begin(&handle, event, header.size)) + if (perf_output_begin(&handle, &data, event, header.size)) return; perf_output_sample(&handle, &header, &data, event); diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index 8e53f2fc3fe0..6f681b105eec 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -144,8 +144,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) : diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 9acaa0f131b9..46115231a3b2 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -98,7 +98,7 @@ static void init_fw_feat_flags(struct device_node *np) security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR); } -static void pnv_setup_rfi_flush(void) +static void pnv_setup_security_mitigations(void) { struct device_node *np, *fw_features; enum l1d_flush_type type; @@ -122,12 +122,31 @@ static void pnv_setup_rfi_flush(void) type = L1D_FLUSH_ORI; } + /* + * If we are non-Power9 bare metal, we don't need to flush on kernel + * entry or after user access: they fix a P9 specific vulnerability. + */ + if (!pvr_version_is(PVR_POWER9)) { + security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY); + security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS); + } + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \ (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \ security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV)); setup_rfi_flush(type, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); + + setup_stf_barrier(); } static void __init pnv_check_guarded_cores(void) @@ -156,8 +175,7 @@ static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); - pnv_setup_rfi_flush(); - setup_stf_barrier(); + pnv_setup_security_mitigations(); /* Initialize SMP */ pnv_smp_init(); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index d6f4162478a5..2f73cb5bf12d 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -349,8 +349,8 @@ void post_mobility_fixup(void) cpus_read_unlock(); - /* Possibly switch to a new RFI flush type */ - pseries_setup_rfi_flush(); + /* Possibly switch to a new L1 flush type */ + pseries_setup_security_mitigations(); /* Reinitialise system information for hv-24x7 */ read_24x7_sys_info(); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 13fa370a87e4..593840847cd3 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -111,7 +111,7 @@ static inline unsigned long cmo_get_page_size(void) int dlpar_workqueue_init(void); -void pseries_setup_rfi_flush(void); +void pseries_setup_security_mitigations(void); void pseries_lpar_read_hblkrm_characteristics(void); #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 633c45ec406d..090c13f6c881 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -542,7 +542,7 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR); } -void pseries_setup_rfi_flush(void) +void pseries_setup_security_mitigations(void) { struct h_cpu_char_result result; enum l1d_flush_type types; @@ -579,6 +579,16 @@ void pseries_setup_rfi_flush(void) setup_rfi_flush(types, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); + + setup_stf_barrier(); } #ifdef CONFIG_PCI_IOV @@ -768,8 +778,7 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); - pseries_setup_rfi_flush(); - setup_stf_barrier(); + pseries_setup_security_mitigations(); pseries_lpar_read_hblkrm_characteristics(); /* By default, only probe PCI (can be overridden by rtas_pci) */ diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h index b0ab66e5fdb1..5b2e79e5bfa5 100644 --- a/arch/riscv/include/asm/pgtable-32.h +++ b/arch/riscv/include/asm/pgtable-32.h @@ -14,4 +14,6 @@ #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 34 + #endif /* _ASM_RISCV_PGTABLE_32_H */ diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index c47e6b35c551..824b2c9da75b 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -476,7 +476,7 @@ do { \ do { \ long __kr_err; \ \ - __put_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ + __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ goto err_label; \ } while (0) diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index 82a5693b1861..134388cbaaa1 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -4,6 +4,8 @@ #ifndef __ASSEMBLY__ +#include <asm/barrier.h> + static inline void cpu_relax(void) { #ifdef __riscv_muldiv diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 99e12faa5498..765b62434f30 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2013 Linaro Limited * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 11e2a4fe66e0..7e849797c9c3 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -35,6 +35,10 @@ ENTRY(_start) .word 0 #endif .balign 8 +#ifdef CONFIG_RISCV_M_MODE + /* Image load offset (0MB) from start of RAM for M-mode */ + .dword 0 +#else #if __riscv_xlen == 64 /* Image load offset(2MB) from start of RAM */ .dword 0x200000 @@ -42,6 +46,7 @@ ENTRY(_start) /* Image load offset(4MB) from start of RAM */ .dword 0x400000 #endif +#endif /* Effective size of kernel image */ .dword _end - _start .dword __HEAD_FLAGS diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c index 04a38fbeb9c7..fd304a248de6 100644 --- a/arch/riscv/kernel/perf_regs.c +++ b/arch/riscv/kernel/perf_regs.c @@ -36,8 +36,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 19225ec65db6..dd5f985b1f40 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -36,7 +36,7 @@ extern asmlinkage void ret_from_kernel_thread(void); void arch_cpu_idle(void) { wait_for_interrupt(); - local_irq_enable(); + raw_local_irq_enable(); } void show_regs(struct pt_regs *regs) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index c424cc6dd833..117f3212a8e4 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -75,6 +75,7 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; early_ioremap_setup(); + jump_label_init(); parse_early_param(); efi_init(); diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore index 11ebee9e4c1d..3a19def868ec 100644 --- a/arch/riscv/kernel/vdso/.gitignore +++ b/arch/riscv/kernel/vdso/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only vdso.lds *.tmp +vdso-syms.S diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 7d6a94d45ec9..0cfd6da784f8 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -43,19 +43,14 @@ $(obj)/vdso.o: $(obj)/vdso.so SYSCFLAGS_vdso.so.dbg = $(c_flags) $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) +SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ + -Wl,--build-id=sha1 -Wl,--hash-style=both # We also create a special relocatable object that should mirror the symbol # table and layout of the linked DSO. With ld --just-symbols we can then # refer to these symbols in the kernel code rather than hand-coded addresses. - -SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ - -Wl,--build-id=sha1 -Wl,--hash-style=both -$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE - $(call if_changed,vdsold) - -LDFLAGS_vdso-syms.o := -r --just-symbols -$(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE - $(call if_changed,ld) +$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE + $(call if_changed,so2s) # strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -73,6 +68,11 @@ quiet_cmd_vdsold = VDSOLD $@ $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \ rm $@.tmp +# Extracts symbol offsets from the VDSO, converting them into an assembly file +# that contains the same symbols at the same offsets. +quiet_cmd_so2s = SO2S $@ + cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@ + # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ diff --git a/arch/riscv/kernel/vdso/so2s.sh b/arch/riscv/kernel/vdso/so2s.sh new file mode 100755 index 000000000000..e64cb6d9440e --- /dev/null +++ b/arch/riscv/kernel/vdso/so2s.sh @@ -0,0 +1,6 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com> + +sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \ +| grep '^\.' diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 1359e21c0c62..3c8b9e433c67 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -86,6 +86,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a pmd_t *pmd, *pmd_k; pte_t *pte_k; int index; + unsigned long pfn; /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) @@ -100,7 +101,8 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a * of a task switch. */ index = pgd_index(addr); - pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index; + pfn = csr_read(CSR_SATP) & SATP_PPN; + pgd = (pgd_t *)pfn_to_virt(pfn) + index; pgd_k = init_mm.pgd + index; if (!pgd_present(*pgd_k)) { diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ea933b789a88..8e577f14f120 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -154,9 +154,8 @@ disable: void __init setup_bootmem(void) { - phys_addr_t mem_size = 0; - phys_addr_t total_mem = 0; - phys_addr_t mem_start, start, end = 0; + phys_addr_t mem_start = 0; + phys_addr_t start, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); u64 i; @@ -164,21 +163,18 @@ void __init setup_bootmem(void) /* Find the memory region containing the kernel */ for_each_mem_range(i, &start, &end) { phys_addr_t size = end - start; - if (!total_mem) + if (!mem_start) mem_start = start; if (start <= vmlinux_start && vmlinux_end <= end) BUG_ON(size == 0); - total_mem = total_mem + size; } /* - * Remove memblock from the end of usable area to the - * end of region + * The maximal physical memory size is -PAGE_OFFSET. + * Make sure that any memory beyond mem_start + (-PAGE_OFFSET) is removed + * as it is unusable by kernel. */ - mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET); - if (mem_start + mem_size < end) - memblock_remove(mem_start + mem_size, - end - mem_start - mem_size); + memblock_enforce_memory_limit(mem_start - PAGE_OFFSET); /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); @@ -297,6 +293,7 @@ pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss; #define NUM_EARLY_PMDS (1UL + MAX_EARLY_MAPPING_SIZE / PGDIR_SIZE) #endif pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE); +pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); static pmd_t *__init get_pmd_virt_early(phys_addr_t pa) { @@ -494,6 +491,18 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) load_pa + (va - PAGE_OFFSET), map_size, PAGE_KERNEL_EXEC); +#ifndef __PAGETABLE_PMD_FOLDED + /* Setup early PMD for DTB */ + create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, + (uintptr_t)early_dtb_pmd, PGDIR_SIZE, PAGE_TABLE); + /* Create two consecutive PMD mappings for FDT early scan */ + pa = dtb_pa & ~(PMD_SIZE - 1); + create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA, + pa, PMD_SIZE, PAGE_KERNEL); + create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE, + pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL); + dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1)); +#else /* Create two consecutive PGD mappings for FDT early scan */ pa = dtb_pa & ~(PGDIR_SIZE - 1); create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, @@ -501,6 +510,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE, pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL); dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1)); +#endif dtb_early_pa = dtb_pa; /* diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 0784bf3caf43..fe6f529ac82c 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -1,3 +1,4 @@ +CONFIG_UAPI_HEADER_TEST=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_WATCH_QUEUE=y @@ -93,9 +94,10 @@ CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y +CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y @@ -378,7 +380,6 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y # CONFIG_PCIEASPM is not set CONFIG_PCI_DEBUG=y @@ -386,7 +387,7 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y -CONFIG_ZRAM=m +CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m @@ -689,6 +690,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m @@ -709,7 +711,6 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m @@ -753,6 +754,7 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_CRC32_SELFTEST=y CONFIG_CRC4=m @@ -829,6 +831,7 @@ CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y CONFIG_FAILSLAB=y CONFIG_FAIL_PAGE_ALLOC=y +CONFIG_FAULT_INJECTION_USERCOPY=y CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 905bc8c4cfaf..17d5df2c1eff 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -87,9 +87,10 @@ CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y +CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y @@ -371,7 +372,6 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y # CONFIG_PCIEASPM is not set CONFIG_HOTPLUG_PCI=y @@ -379,7 +379,7 @@ CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y -CONFIG_ZRAM=m +CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m @@ -680,6 +680,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m @@ -701,7 +702,6 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m @@ -745,6 +745,7 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m CONFIG_CRC4=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 8f67c55625f9..a302630341ef 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -17,11 +17,11 @@ CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y -# CONFIG_SECCOMP is not set # CONFIG_PFAULT is not set # CONFIG_S390_HYPFS_FS is not set # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set +# CONFIG_SECCOMP is not set CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 6b8d8c69b1a1..b5dbae78969b 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -692,16 +692,6 @@ static inline int pud_large(pud_t pud) return !!(pud_val(pud) & _REGION3_ENTRY_LARGE); } -static inline unsigned long pud_pfn(pud_t pud) -{ - unsigned long origin_mask; - - origin_mask = _REGION_ENTRY_ORIGIN; - if (pud_large(pud)) - origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; - return (pud_val(pud) & origin_mask) >> PAGE_SHIFT; -} - #define pmd_leaf pmd_large static inline int pmd_large(pmd_t pmd) { @@ -747,16 +737,6 @@ static inline int pmd_none(pmd_t pmd) return pmd_val(pmd) == _SEGMENT_ENTRY_EMPTY; } -static inline unsigned long pmd_pfn(pmd_t pmd) -{ - unsigned long origin_mask; - - origin_mask = _SEGMENT_ENTRY_ORIGIN; - if (pmd_large(pmd)) - origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE; - return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT; -} - #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { @@ -1238,11 +1218,39 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) -#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN) -#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN) #define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN) #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) +static inline unsigned long pmd_deref(pmd_t pmd) +{ + unsigned long origin_mask; + + origin_mask = _SEGMENT_ENTRY_ORIGIN; + if (pmd_large(pmd)) + origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE; + return pmd_val(pmd) & origin_mask; +} + +static inline unsigned long pmd_pfn(pmd_t pmd) +{ + return pmd_deref(pmd) >> PAGE_SHIFT; +} + +static inline unsigned long pud_deref(pud_t pud) +{ + unsigned long origin_mask; + + origin_mask = _REGION_ENTRY_ORIGIN; + if (pud_large(pud)) + origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; + return pud_val(pud) & origin_mask; +} + +static inline unsigned long pud_pfn(pud_t pud) +{ + return pud_deref(pud) >> PAGE_SHIFT; +} + /* * The pgd_offset function *always* adds the index for the top-level * region/segment table. This is done to get a sequence like the diff --git a/arch/s390/include/asm/vdso/vdso.h b/arch/s390/include/asm/vdso/vdso.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/s390/include/asm/vdso/vdso.h +++ /dev/null diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index ece58f2217cb..483051e10db3 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -53,22 +53,14 @@ int main(void) /* stack_frame offsets */ OFFSET(__SF_BACKCHAIN, stack_frame, back_chain); OFFSET(__SF_GPRS, stack_frame, gprs); - OFFSET(__SF_EMPTY, stack_frame, empty1); - OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]); - OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]); - OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]); - OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[3]); + OFFSET(__SF_EMPTY, stack_frame, empty1[0]); + OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[1]); + OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[2]); + OFFSET(__SF_SIE_REASON, stack_frame, empty1[3]); + OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[4]); BLANK(); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); BLANK(); - /* constants used by the vdso */ - DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME); - DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC); - DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); - DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); - DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID); - DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC); - BLANK(); /* idle data offsets */ OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter); OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 86235919c2d1..26bb0603c5a1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -422,6 +422,7 @@ ENTRY(system_call) #endif LOCKDEP_SYS_EXIT .Lsysc_tif: + DISABLE_INTS TSTMSK __PT_FLAGS(%r11),_PIF_WORK jnz .Lsysc_work TSTMSK __TI_flags(%r12),_TIF_WORK @@ -444,6 +445,7 @@ ENTRY(system_call) # One of the work bits is on. Find out which one. # .Lsysc_work: + ENABLE_INTS TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED jo .Lsysc_reschedule TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART @@ -1066,6 +1068,7 @@ EXPORT_SYMBOL(save_fpu_regs) * %r4 */ load_fpu_regs: + stnsm __SF_EMPTY(%r15),0xfc lg %r4,__LC_CURRENT aghi %r4,__TASK_thread TSTMSK __LC_CPU_FLAGS,_CIF_FPU @@ -1097,6 +1100,7 @@ load_fpu_regs: .Lload_fpu_regs_done: ni __LC_CPU_FLAGS+7,255-_CIF_FPU .Lload_fpu_regs_exit: + ssm __SF_EMPTY(%r15) BR_EX %r14 .Lload_fpu_regs_end: ENDPROC(load_fpu_regs) diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index f7f1e64e0d98..2b85096964f8 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -33,10 +33,10 @@ void enabled_wait(void) PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; clear_cpu_flag(CIF_NOHZ_DELAY); - local_irq_save(flags); + raw_local_irq_save(flags); /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); - local_irq_restore(flags); + raw_local_irq_restore(flags); /* Account time spent with enabled wait psw loaded as idle time. */ raw_write_seqcount_begin(&idle->seqcount); @@ -123,7 +123,7 @@ void arch_cpu_idle_enter(void) void arch_cpu_idle(void) { enabled_wait(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_exit(void) diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 4f9e4626df55..19cd7b961c45 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -672,7 +672,7 @@ static void cpumsf_output_event_pid(struct perf_event *event, rcu_read_lock(); perf_prepare_sample(&header, data, event, regs); - if (perf_output_begin(&handle, event, header.size)) + if (perf_output_begin(&handle, data, event, header.size)) goto out; /* Update the process ID (see also kernel/events/core.c) */ @@ -2228,4 +2228,4 @@ out: } arch_initcall(init_cpum_sampling_pmu); -core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640); +core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644); diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c index 4352a504f235..6e9e5d5e927e 100644 --- a/arch/s390/kernel/perf_regs.c +++ b/arch/s390/kernel/perf_regs.c @@ -53,8 +53,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { /* * Use the regs from the first interruption and let diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index ebfe86d097f0..390d97daa2b3 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -855,13 +855,14 @@ void __init smp_detect_cpus(void) static void smp_init_secondary(void) { - int cpu = smp_processor_id(); + int cpu = raw_smp_processor_id(); S390_lowcore.last_update_clock = get_tod_clock(); restore_access_regs(S390_lowcore.access_regs_save_area); set_cpu_flag(CIF_ASCE_PRIMARY); set_cpu_flag(CIF_ASCE_SECONDARY); cpu_init(); + rcu_cpu_starting(cpu); preempt_disable(); init_cpu_timer(); vtime_init(); diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 14bd9d58edc9..883bfed9f5c2 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -129,8 +129,15 @@ int uv_destroy_page(unsigned long paddr) .paddr = paddr }; - if (uv_call(0, (u64)&uvcb)) + if (uv_call(0, (u64)&uvcb)) { + /* + * Older firmware uses 107/d as an indication of a non secure + * page. Let us emulate the newer variant (no-op). + */ + if (uvcb.header.rc == 0x107 && uvcb.header.rrc == 0xd) + return 0; return -EINVAL; + } return 0; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 6b74b92c1a58..425d3d75320b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2312,7 +2312,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) struct kvm_s390_pv_unp unp = {}; r = -EINVAL; - if (!kvm_s390_pv_is_protected(kvm)) + if (!kvm_s390_pv_is_protected(kvm) || !mm_is_protected(kvm->mm)) break; r = -EFAULT; @@ -3564,7 +3564,6 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->pp = 0; vcpu->arch.sie_block->fpf &= ~FPF_BPBC; vcpu->arch.sie_block->todpr = 0; - vcpu->arch.sie_block->cpnc = 0; } } @@ -3582,7 +3581,6 @@ static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu) regs->etoken = 0; regs->etoken_extension = 0; - regs->diag318 = 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index eb99e2f95ebe..f5847f9dec7c 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -208,7 +208,6 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; - atomic_set(&kvm->mm->context.is_protected, 1); return 0; } @@ -228,6 +227,8 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, *rrc = uvcb.header.rrc; KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x", *rc, *rrc); + if (!cc) + atomic_set(&kvm->mm->context.is_protected, 1); return cc ? -EINVAL : 0; } diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index cfb0017f33a7..64795d034926 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2690,6 +2690,8 @@ static const struct mm_walk_ops reset_acc_walk_ops = { #include <linux/sched/mm.h> void s390_reset_acc(struct mm_struct *mm) { + if (!mm_is_protected(mm)) + return; /* * we might be called during * reset: we walk the pages and clear diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index d33f21545dfd..9a6bae503fe6 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -101,6 +101,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (ret) break; + /* the PCI function will be scanned once function 0 appears */ + if (!zdev->zbus->bus) + break; + pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn); if (!pdev) break; diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 0dc0f52f9bb8..f59814983bd5 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -22,7 +22,7 @@ static void (*sh_idle)(void); void default_idle(void) { set_bl_bit(); - local_irq_enable(); + raw_local_irq_enable(); /* Isn't this racy ? */ cpu_sleep(); clear_bl_bit(); diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c index 065e2d4b7290..396f46bca52e 100644 --- a/arch/sparc/kernel/leon_pmc.c +++ b/arch/sparc/kernel/leon_pmc.c @@ -50,7 +50,7 @@ static void pmc_leon_idle_fixup(void) register unsigned int address = (unsigned int)leon3_irqctrl_regs; /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); __asm__ __volatile__ ( "wr %%g0, %%asr19\n" @@ -66,7 +66,7 @@ static void pmc_leon_idle_fixup(void) static void pmc_leon_idle(void) { /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); /* For systems without power-down, this will be no-op */ __asm__ __volatile__ ("wr %g0, %asr19\n\t"); diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index adfcaeab3ddc..a02363735915 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -74,7 +74,7 @@ void arch_cpu_idle(void) { if (sparc_idle) (*sparc_idle)(); - local_irq_enable(); + raw_local_irq_enable(); } /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */ diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index a75093b993f9..6f8c7822fc06 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -62,11 +62,11 @@ void arch_cpu_idle(void) { if (tlb_type != hypervisor) { touch_nmi_watchdog(); - local_irq_enable(); + raw_local_irq_enable(); } else { unsigned long pstate; - local_irq_enable(); + raw_local_irq_enable(); /* The sun4v sleeping code requires that we have PSTATE.IE cleared over * the cpu sleep hypervisor call. diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 5393e13e07e0..2bbf28cf3aa9 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -33,7 +33,13 @@ do { \ } while (0) #ifdef CONFIG_3_LEVEL_PGTABLES -#define __pmd_free_tlb(tlb,x, address) tlb_remove_page((tlb),virt_to_page(x)) + +#define __pmd_free_tlb(tlb, pmd, address) \ +do { \ + pgtable_pmd_page_dtor(virt_to_page(pmd)); \ + tlb_remove_page((tlb),virt_to_page(pmd)); \ +} while (0) \ + #endif #endif diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 3bed09538dd9..9505a7e87396 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -217,7 +217,7 @@ void arch_cpu_idle(void) { cpu_tasks[current_thread_info()->cpu].pid = os_getpid(); um_idle_sleep(); - local_irq_enable(); + raw_local_irq_enable(); } int __cant_sleep(void) { diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index a5e5db6ada3c..39b2eded7bc2 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -164,6 +164,7 @@ void initialize_identity_maps(void *rmode) add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); /* Load the new page-table. */ + sev_verify_cbit(top_level_pgt); write_cr3(top_level_pgt); } diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index dd07e7b41b11..aa561795efd1 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -68,6 +68,9 @@ SYM_FUNC_START(get_sev_encryption_bit) SYM_FUNC_END(get_sev_encryption_bit) .code64 + +#include "../../kernel/sev_verify_cbit.S" + SYM_FUNC_START(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT push %rbp @@ -81,6 +84,19 @@ SYM_FUNC_START(set_sev_encryption_mask) bts %rax, sme_me_mask(%rip) /* Create the encryption mask */ + /* + * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in + * get_sev_encryption_bit() because this function is 32-bit code and + * shared between 64-bit and 32-bit boot path. + */ + movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */ + rdmsr + + /* Store MSR value in sev_status */ + shlq $32, %rdx + orq %rdx, %rax + movq %rax, sev_status(%rip) + .Lno_sev_mask: movq %rbp, %rsp /* Restore original stack pointer */ @@ -96,5 +112,7 @@ SYM_FUNC_END(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 -SYM_DATA(sme_me_mask, .quad 0) +SYM_DATA(sme_me_mask, .quad 0) +SYM_DATA(sev_status, .quad 0) +SYM_DATA(sev_check_data, .quad 0) #endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 6d31f1b4c4d1..d9a631c5973c 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -159,4 +159,6 @@ void boot_page_fault(void); void boot_stage1_vc(void); void boot_stage2_vc(void); +unsigned long sev_verify_cbit(unsigned long cr3); + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index f1926e9f2143..af457f8cb29d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2630,7 +2630,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) u64 pebs_enabled = cpuc->pebs_enabled; handled++; - x86_pmu.drain_pebs(regs); + x86_pmu.drain_pebs(regs, &data); status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; /* @@ -4987,6 +4987,12 @@ __init int intel_pmu_init(void) x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */ + if (version >= 5) { + x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated; + if (x86_pmu.intel_cap.anythread_deprecated) + pr_cont(" AnyThread deprecated, "); + } + /* * Install the hw-cache-events table: */ @@ -5512,6 +5518,10 @@ __init int intel_pmu_init(void) x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED; + /* AnyThread may be deprecated on arch perfmon v5 or later */ + if (x86_pmu.intel_cap.anythread_deprecated) + x86_pmu.format_attrs = intel_arch_formats_attr; + if (x86_pmu.event_constraints) { /* * event on fixed counter2 (REF_CYCLES) only works on this diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 442e1ed4acd4..4eb7ee5fed72 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -107,14 +107,14 @@ MODULE_LICENSE("GPL"); #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __cstate_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __cstate_##_var##_show, NULL) static ssize_t cstate_get_attr_cpumask(struct device *dev, diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 404315df1e16..b47cc4226934 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -642,8 +642,8 @@ int intel_pmu_drain_bts_buffer(void) rcu_read_lock(); perf_prepare_sample(&header, &data, event, ®s); - if (perf_output_begin(&handle, event, header.size * - (top - base - skip))) + if (perf_output_begin(&handle, &data, event, + header.size * (top - base - skip))) goto unlock; for (at = base; at < top; at++) { @@ -670,7 +670,9 @@ unlock: static inline void intel_pmu_drain_pebs_buffer(void) { - x86_pmu.drain_pebs(NULL); + struct perf_sample_data data; + + x86_pmu.drain_pebs(NULL, &data); } /* @@ -1719,23 +1721,24 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) return 0; } -static void __intel_pmu_pebs_event(struct perf_event *event, - struct pt_regs *iregs, - void *base, void *top, - int bit, int count, - void (*setup_sample)(struct perf_event *, - struct pt_regs *, - void *, - struct perf_sample_data *, - struct pt_regs *)) +static __always_inline void +__intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, + struct perf_sample_data *data, + void *base, void *top, + int bit, int count, + void (*setup_sample)(struct perf_event *, + struct pt_regs *, + void *, + struct perf_sample_data *, + struct pt_regs *)) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - struct perf_sample_data data; struct x86_perf_regs perf_regs; struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); - struct pt_regs dummy_iregs; + static struct pt_regs dummy_iregs; if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { /* @@ -1752,14 +1755,14 @@ static void __intel_pmu_pebs_event(struct perf_event *event, iregs = &dummy_iregs; while (count > 1) { - setup_sample(event, iregs, at, &data, regs); - perf_event_output(event, &data, regs); + setup_sample(event, iregs, at, data, regs); + perf_event_output(event, data, regs); at += cpuc->pebs_record_size; at = get_next_pebs_record_by_bit(at, top, bit); count--; } - setup_sample(event, iregs, at, &data, regs); + setup_sample(event, iregs, at, data, regs); if (iregs == &dummy_iregs) { /* * The PEBS records may be drained in the non-overflow context, @@ -1767,18 +1770,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * last record the same as other PEBS records, and doesn't * invoke the generic overflow handler. */ - perf_event_output(event, &data, regs); + perf_event_output(event, data, regs); } else { /* * All but the last records are processed. * The last one is left to be able to call the overflow handler. */ - if (perf_event_overflow(event, &data, regs)) + if (perf_event_overflow(event, data, regs)) x86_pmu_stop(event, 0); } } -static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -1812,7 +1815,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) return; } - __intel_pmu_pebs_event(event, iregs, at, top, 0, n, + __intel_pmu_pebs_event(event, iregs, data, at, top, 0, n, setup_pebs_fixed_sample_data); } @@ -1835,7 +1838,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int } } -static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_data *data) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -1942,14 +1945,14 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) } if (counts[bit]) { - __intel_pmu_pebs_event(event, iregs, base, + __intel_pmu_pebs_event(event, iregs, data, base, top, bit, counts[bit], setup_pebs_fixed_sample_data); } } } -static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data) { short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1997,7 +2000,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) if (WARN_ON_ONCE(!event->attr.precise_ip)) continue; - __intel_pmu_pebs_event(event, iregs, base, + __intel_pmu_pebs_event(event, iregs, data, base, top, bit, counts[bit], setup_pebs_adaptive_sample_data); } diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 86d012b3e0b4..80d52cbe2fde 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -94,8 +94,8 @@ end: return map; } -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct uncore_event_desc *event = container_of(attr, struct uncore_event_desc, attr); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 83d2a7d490e0..9efea154349d 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -157,7 +157,7 @@ struct intel_uncore_box { #define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS 2 struct uncore_event_desc { - struct kobj_attribute attr; + struct device_attribute attr; const char *config; }; @@ -179,8 +179,8 @@ struct pci2phy_map { struct pci2phy_map *__find_pci2phy_map(int segment); int uncore_pcibus_to_physid(struct pci_bus *bus); -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf); +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf); static inline struct intel_uncore_pmu *dev_to_uncore_pmu(struct device *dev) { @@ -201,14 +201,14 @@ extern int __uncore_max_dies; } #define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __uncore_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __uncore_##_var##_show, NULL) static inline bool uncore_pmc_fixed(int idx) diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 39e632ed6ca9..bbd1120ae161 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -475,7 +475,7 @@ enum perf_snb_uncore_imc_freerunning_types { static struct freerunning_counters snb_uncore_imc_freerunning[] = { [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x0, 0x0, 1, 32 }, - [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + [SNB_PCI_UNCORE_IMC_DATA_WRITES] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, 0x0, 0x0, 1, 32 }, [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, 0x0, 0x0, 1, 32 }, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ee2b9b9fc2a5..6a8edfe59b09 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -585,6 +585,7 @@ union perf_capabilities { u64 pebs_baseline:1; u64 perf_metrics:1; u64 pebs_output_pt_available:1; + u64 anythread_deprecated:1; }; u64 capabilities; }; @@ -727,7 +728,7 @@ struct x86_pmu { int pebs_record_size; int pebs_buffer_size; int max_pebs_events; - void (*drain_pebs)(struct pt_regs *regs); + void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); unsigned long large_pebs_flags; diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 7c0120e2e957..7dbbeaacd995 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -93,18 +93,6 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { * any other bit is reserved */ #define RAPL_EVENT_MASK 0xFFULL - -#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ - char *page) \ -{ \ - BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ - return sprintf(page, _format "\n"); \ -} \ -static struct kobj_attribute format_attr_##_var = \ - __ATTR(_name, 0444, __rapl_##_var##_show, NULL) - #define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ @@ -441,7 +429,7 @@ static struct attribute_group rapl_pmu_events_group = { .attrs = attrs_empty, }; -DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7"); +PMU_FORMAT_ATTR(event, "config:0-7"); static struct attribute *rapl_formats_attr[] = { &format_attr_event.attr, NULL, diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 40e0e322161d..284e73661a18 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -273,11 +273,15 @@ void __init hv_apic_init(void) pr_info("Hyper-V: Using enlightened APIC (%s mode)", x2apic_enabled() ? "x2apic" : "xapic"); /* - * With x2apic, architectural x2apic MSRs are equivalent to the - * respective synthetic MSRs, so there's no need to override - * the apic accessors. The only exception is - * hv_apic_eoi_write, because it benefits from lazy EOI when - * available, but it works for both xapic and x2apic modes. + * When in x2apic mode, don't use the Hyper-V specific APIC + * accessors since the field layout in the ICR register is + * different in x2apic mode. Furthermore, the architectural + * x2apic MSRs function just as well as the Hyper-V + * synthetic APIC MSRs, so there's no benefit in having + * separate Hyper-V accessors for x2apic mode. The only + * exception is hv_apic_eoi_write, because it benefits from + * lazy EOI when available, but the same accessor works for + * both xapic and x2apic because the field layout is the same. */ apic_set_eoi_write(hv_apic_eoi_write); if (!x2apic_enabled()) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d44858b69353..7e5f33a0d0e2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -639,6 +639,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; + unsigned long cr3_lm_rsvd_bits; int maxphyaddr; int max_tdp_level; @@ -1655,6 +1656,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index e039a933aca3..29dd27b5a339 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -88,8 +88,6 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx, static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { - trace_hardirqs_on(); - mds_idle_clear_cpu_buffers(); /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 6960cd6d1f23..b9a7fd0a27e2 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -137,7 +137,9 @@ union cpuid10_edx { struct { unsigned int num_counters_fixed:5; unsigned int bit_width_fixed:8; - unsigned int reserved:19; + unsigned int reserved1:2; + unsigned int anythread_deprecated:1; + unsigned int reserved2:16; } split; unsigned int full; }; diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 6bfc878f6771..6a9ccc1b2be5 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -28,4 +28,14 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_NUMA_KEEP_MEMINFO +extern int phys_to_target_node(phys_addr_t start); +#define phys_to_target_node phys_to_target_node +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_SPARSEMEM_H */ diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 172d3e4a9e4b..648eb23fe7f0 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -2,14 +2,8 @@ #ifndef _ASM_X86_UV_UV_H #define _ASM_X86_UV_UV_H -#include <asm/tlbflush.h> - enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC}; -struct cpumask; -struct mm_struct; -struct flush_tlb_info; - #ifdef CONFIG_X86_UV #include <linux/efi.h> @@ -44,10 +38,6 @@ static inline int is_uv_system(void) { return 0; } static inline int is_uv_hubbed(int uv) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } -static inline const struct cpumask * -uv_flush_tlb_others(const struct cpumask *cpumask, - const struct flush_tlb_info *info) -{ return cpumask; } #endif /* X86_UV */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 714233cee0b5..1b98f8c12b96 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -33,7 +33,7 @@ static union uvh_apicid uvh_apicid; static int uv_node_id; /* Unpack AT/OEM/TABLE ID's to be NULL terminated strings */ -static u8 uv_archtype[UV_AT_SIZE]; +static u8 uv_archtype[UV_AT_SIZE + 1]; static u8 oem_id[ACPI_OEM_ID_SIZE + 1]; static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; @@ -290,6 +290,9 @@ static void __init uv_stringify(int len, char *to, char *from) { /* Relies on 'to' being NULL chars so result will be NULL terminated */ strncpy(to, from, len-1); + + /* Trim trailing spaces */ + (void)strim(to); } /* Find UV arch type entry in UVsystab */ @@ -317,7 +320,7 @@ static int __init decode_arch_type(unsigned long ptr) if (n > 0 && n < sizeof(uv_ate->archtype)) { pr_info("UV: UVarchtype received from BIOS\n"); - uv_stringify(UV_AT_SIZE, uv_archtype, uv_ate->archtype); + uv_stringify(sizeof(uv_archtype), uv_archtype, uv_ate->archtype); return 1; } return 0; @@ -366,7 +369,7 @@ static int __init early_get_arch_type(void) return ret; } -static int __init uv_set_system_type(char *_oem_id) +static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id) { /* Save OEM_ID passed from ACPI MADT */ uv_stringify(sizeof(oem_id), oem_id, _oem_id); @@ -375,7 +378,7 @@ static int __init uv_set_system_type(char *_oem_id) if (!early_get_arch_type()) /* If not use OEM ID for UVarchtype */ - uv_stringify(UV_AT_SIZE, uv_archtype, _oem_id); + uv_stringify(sizeof(uv_archtype), uv_archtype, oem_id); /* Check if not hubbed */ if (strncmp(uv_archtype, "SGI", 3) != 0) { @@ -386,13 +389,23 @@ static int __init uv_set_system_type(char *_oem_id) /* (Not hubless), not a UV */ return 0; + /* Is UV hubless system */ + uv_hubless_system = 0x01; + + /* UV5 Hubless */ + if (strncmp(uv_archtype, "NSGI5", 5) == 0) + uv_hubless_system |= 0x20; + /* UV4 Hubless: CH */ - if (strncmp(uv_archtype, "NSGI4", 5) == 0) - uv_hubless_system = 0x11; + else if (strncmp(uv_archtype, "NSGI4", 5) == 0) + uv_hubless_system |= 0x10; /* UV3 Hubless: UV300/MC990X w/o hub */ else - uv_hubless_system = 0x9; + uv_hubless_system |= 0x8; + + /* Copy APIC type */ + uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id); pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n", oem_id, oem_table_id, uv_system_type, uv_hubless_system); @@ -456,7 +469,7 @@ static int __init uv_acpi_madt_oem_check(char *_oem_id, char *_oem_table_id) uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0; /* If not UV, return. */ - if (likely(uv_set_system_type(_oem_id) == 0)) + if (uv_set_system_type(_oem_id, _oem_table_id) == 0) return 0; /* Save and Decode OEM Table ID */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d3f0db463f96..d41b70fe4918 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -739,11 +739,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + spectre_v2_user_ibpb = mode; switch (cmd) { case SPECTRE_V2_USER_CMD_FORCE: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: static_branch_enable(&switch_mm_always_ibpb); + spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT; break; case SPECTRE_V2_USER_CMD_PRCTL: case SPECTRE_V2_USER_CMD_AUTO: @@ -757,8 +759,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", static_key_enabled(&switch_mm_always_ibpb) ? "always-on" : "conditional"); - - spectre_v2_user_ibpb = mode; } /* @@ -1254,6 +1254,14 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) return 0; } +static bool is_spec_ib_user_controlled(void) +{ + return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP; +} + static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { @@ -1261,16 +1269,26 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return 0; + /* - * Indirect branch speculation is always disabled in strict - * mode. It can neither be enabled if it was force-disabled - * by a previous prctl call. + * With strict mode for both IBPB and STIBP, the instruction + * code paths avoid checking this task flag and instead, + * unconditionally run the instruction. However, STIBP and IBPB + * are independent and either can be set to conditionally + * enabled regardless of the mode of the other. + * + * If either is set to conditional, allow the task flag to be + * updated, unless it was force-disabled by a previous prctl + * call. Currently, this is possible on an AMD CPU which has the + * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the + * kernel is booted with 'spectre_v2_user=seccomp', then + * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and + * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED. */ - if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED || + if (!is_spec_ib_user_controlled() || task_spec_ib_force_disable(task)) return -EPERM; + task_clear_spec_ib_disable(task); task_update_spec_tif(task); break; @@ -1283,10 +1301,10 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return -EPERM; - if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + + if (!is_spec_ib_user_controlled()) return 0; + task_set_spec_ib_disable(task); if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); @@ -1351,20 +1369,17 @@ static int ib_prctl_get(struct task_struct *task) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return PR_SPEC_ENABLE; - else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) - return PR_SPEC_DISABLE; - else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || - spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || - spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || - spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) { + else if (is_spec_ib_user_controlled()) { if (task_spec_ib_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ib_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; - } else + } else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + return PR_SPEC_DISABLE; + else return PR_SPEC_NOT_AFFECTED; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 4102b866e7c0..32b7099e3511 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1384,8 +1384,10 @@ noinstr void do_machine_check(struct pt_regs *regs) * When there's any problem use only local no_way_out state. */ if (!lmce) { - if (mce_end(order) < 0) - no_way_out = worst >= MCE_PANIC_SEVERITY; + if (mce_end(order) < 0) { + if (!no_way_out) + no_way_out = worst >= MCE_PANIC_SEVERITY; + } } else { /* * If there was a fatal machine check we should have diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 6a99535d7f37..7e8e07bddd5f 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -100,53 +100,6 @@ static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev return find_matching_signature(mc, csig, cpf); } -/* - * Given CPU signature and a microcode patch, this function finds if the - * microcode patch has matching family and model with the CPU. - * - * %true - if there's a match - * %false - otherwise - */ -static bool microcode_matches(struct microcode_header_intel *mc_header, - unsigned long sig) -{ - unsigned long total_size = get_totalsize(mc_header); - unsigned long data_size = get_datasize(mc_header); - struct extended_sigtable *ext_header; - unsigned int fam_ucode, model_ucode; - struct extended_signature *ext_sig; - unsigned int fam, model; - int ext_sigcount, i; - - fam = x86_family(sig); - model = x86_model(sig); - - fam_ucode = x86_family(mc_header->sig); - model_ucode = x86_model(mc_header->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - return false; - - ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - ext_sigcount = ext_header->count; - - for (i = 0; i < ext_sigcount; i++) { - fam_ucode = x86_family(ext_sig->sig); - model_ucode = x86_model(ext_sig->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - ext_sig++; - } - return false; -} - static struct ucode_patch *memdup_patch(void *data, unsigned int size) { struct ucode_patch *p; @@ -164,7 +117,7 @@ static struct ucode_patch *memdup_patch(void *data, unsigned int size) return p; } -static void save_microcode_patch(void *data, unsigned int size) +static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; struct ucode_patch *iter, *tmp, *p = NULL; @@ -210,6 +163,9 @@ static void save_microcode_patch(void *data, unsigned int size) if (!p) return; + if (!find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) + return; + /* * Save for early loading. On 32-bit, that needs to be a physical * address as the APs are running from physical addresses, before @@ -344,13 +300,14 @@ scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save) size -= mc_size; - if (!microcode_matches(mc_header, uci->cpu_sig.sig)) { + if (!find_matching_signature(data, uci->cpu_sig.sig, + uci->cpu_sig.pf)) { data += mc_size; continue; } if (save) { - save_microcode_patch(data, mc_size); + save_microcode_patch(uci, data, mc_size); goto next; } @@ -483,14 +440,14 @@ static void show_saved_mc(void) * Save this microcode patch. It will be loaded early when a CPU is * hot-added or resumes. */ -static void save_mc_for_early(u8 *mc, unsigned int size) +static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size) { /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); mutex_lock(&x86_cpu_microcode_mutex); - save_microcode_patch(mc, size); + save_microcode_patch(uci, mc, size); show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); @@ -935,7 +892,7 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) * permanent memory. So it will be loaded early when a CPU is hot added * or resumes. */ - save_mc_for_early(new_mc, new_mc_size); + save_mc_for_early(uci, new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index af323e2e3100..6f4ca4bea625 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -507,6 +507,24 @@ unlock: return ret ?: nbytes; } +/** + * rdtgroup_remove - the helper to remove resource group safely + * @rdtgrp: resource group to remove + * + * On resource group creation via a mkdir, an extra kernfs_node reference is + * taken to ensure that the rdtgroup structure remains accessible for the + * rdtgroup_kn_unlock() calls where it is removed. + * + * Drop the extra reference here, then free the rdtgroup structure. + * + * Return: void + */ +static void rdtgroup_remove(struct rdtgroup *rdtgrp) +{ + kernfs_put(rdtgrp->kn); + kfree(rdtgrp); +} + struct task_move_callback { struct callback_head work; struct rdtgroup *rdtgrp; @@ -529,7 +547,7 @@ static void move_myself(struct callback_head *head) (rdtgrp->flags & RDT_DELETED)) { current->closid = 0; current->rmid = 0; - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } if (unlikely(current->flags & PF_EXITING)) @@ -1769,7 +1787,6 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, if (IS_ERR(kn_subdir)) return PTR_ERR(kn_subdir); - kernfs_get(kn_subdir); ret = rdtgroup_kn_set_ugid(kn_subdir); if (ret) return ret; @@ -1792,7 +1809,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); if (IS_ERR(kn_info)) return PTR_ERR(kn_info); - kernfs_get(kn_info); ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); if (ret) @@ -1813,12 +1829,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) goto out_destroy; } - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn_info); - ret = rdtgroup_kn_set_ugid(kn_info); if (ret) goto out_destroy; @@ -1847,12 +1857,6 @@ mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, if (dest_kn) *dest_kn = kn; - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn); - ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -2079,8 +2083,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); - kernfs_put(rdtgrp->kn); - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } else { kernfs_unbreak_active_protection(kn); } @@ -2139,13 +2142,11 @@ static int rdt_get_tree(struct fs_context *fc) &kn_mongrp); if (ret < 0) goto out_info; - kernfs_get(kn_mongrp); ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); if (ret < 0) goto out_mongrp; - kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; } @@ -2357,7 +2358,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) if (atomic_read(&sentry->waitcount) != 0) sentry->flags = RDT_DELETED; else - kfree(sentry); + rdtgroup_remove(sentry); } } @@ -2399,7 +2400,7 @@ static void rmdir_all_sub(void) if (atomic_read(&rdtgrp->waitcount) != 0) rdtgrp->flags = RDT_DELETED; else - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); @@ -2499,11 +2500,6 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, if (IS_ERR(kn)) return PTR_ERR(kn); - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that kn is always accessible. - */ - kernfs_get(kn); ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -2838,8 +2834,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, /* * kernfs_remove() will drop the reference count on "kn" which * will free it. But we still need it to stick around for the - * rdtgroup_kn_unlock(kn} call below. Take one extra reference - * here, which will be dropped inside rdtgroup_kn_unlock(). + * rdtgroup_kn_unlock(kn) call. Take one extra reference here, + * which will be dropped by kernfs_put() in rdtgroup_remove(). */ kernfs_get(kn); @@ -2880,6 +2876,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, out_idfree: free_rmid(rdtgrp->mon.rmid); out_destroy: + kernfs_put(rdtgrp->kn); kernfs_remove(rdtgrp->kn); out_free_rgrp: kfree(rdtgrp); @@ -2892,7 +2889,7 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) { kernfs_remove(rgrp->kn); free_rmid(rgrp->mon.rmid); - kfree(rgrp); + rdtgroup_remove(rgrp); } /* @@ -3049,11 +3046,6 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); list_del(&rdtgrp->mon.crdtgrp_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; @@ -3065,11 +3057,6 @@ static int rdtgroup_ctrl_remove(struct kernfs_node *kn, rdtgrp->flags = RDT_DELETED; list_del(&rdtgrp->rdtgroup_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 25c06b67e7e0..97aa900386cb 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -78,6 +78,9 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (!user_mode(regs)) return copy_from_kernel_nofault(buf, (u8 *)src, nbytes); + /* The user space code from other tasks cannot be accessed. */ + if (regs != task_pt_regs(current)) + return -EPERM; /* * Make sure userspace isn't trying to trick us into dumping kernel * memory by pointing the userspace instruction pointer at it. @@ -85,6 +88,12 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX)) return -EINVAL; + /* + * Even if named copy_from_user_nmi() this can be invoked from + * other contexts and will not try to resolve a pagefault, which is + * the correct thing to do here as this code can be called from any + * context. + */ return copy_from_user_nmi(buf, (void __user *)src, nbytes); } @@ -115,13 +124,19 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) u8 opcodes[OPCODE_BUFSIZE]; unsigned long prologue = regs->ip - PROLOGUE_SIZE; - if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { - printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", - loglvl, prologue); - } else { + switch (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { + case 0: printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1); + break; + case -EPERM: + /* No access to the user space stack of other tasks. Ignore. */ + break; + default: + printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + loglvl, prologue); + break; } } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 7eb2a1c87969..3c417734790f 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -161,6 +161,21 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax + + /* + * For SEV guests: Verify that the C-bit is correct. A malicious + * hypervisor could lie about the C-bit position to perform a ROP + * attack on the guest by writing to the unencrypted stack and wait for + * the next RET instruction. + * %rsi carries pointer to realmode data and is callee-clobbered. Save + * and restore it. + */ + pushq %rsi + movq %rax, %rdi + call sev_verify_cbit + popq %rsi + + /* Switch to new page-table */ movq %rax, %cr3 /* Ensure I am executing from virtual addresses */ @@ -279,6 +294,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" +#include "sev_verify_cbit.S" #ifdef CONFIG_HOTPLUG_CPU /* diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index bb7e1132290b..f9e5352b3bef 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -101,8 +101,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); @@ -129,12 +128,20 @@ u64 perf_reg_abi(struct task_struct *task) return PERF_SAMPLE_REGS_ABI_64; } +static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs); + void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { + struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs); struct pt_regs *user_regs = task_pt_regs(current); + if (!in_nmi()) { + regs_user->regs = user_regs; + regs_user->abi = perf_reg_abi(current); + return; + } + /* * If we're in an NMI that interrupted task_pt_regs setup, then * we can't sample user regs at all. This check isn't really diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ba4593a913fa..145a7ac0c19a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -685,7 +685,7 @@ void arch_cpu_idle(void) */ void __cpuidle default_idle(void) { - safe_halt(); + raw_safe_halt(); } #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); @@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy) /* * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power * states (local apic timer and TSC stop). + * + * XXX this function is completely buggered vs RCU and tracing. */ static void amd_e400_idle(void) { @@ -757,9 +759,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be called with * interrupts disabled. */ - local_irq_disable(); + raw_local_irq_disable(); tick_broadcast_exit(); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void) if (!need_resched()) __sti_mwait(0, 0); else - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); } __current_clr_polling(); } diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 5f83ccaab877..7d04b356d44d 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -178,6 +178,32 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) goto fail; regs->dx = val >> 32; + /* + * This is a VC handler and the #VC is only raised when SEV-ES is + * active, which means SEV must be active too. Do sanity checks on the + * CPUID results to make sure the hypervisor does not trick the kernel + * into the no-sev path. This could map sensitive data unencrypted and + * make it accessible to the hypervisor. + * + * In particular, check for: + * - Hypervisor CPUID bit + * - Availability of CPUID leaf 0x8000001f + * - SEV CPUID bit. + * + * The hypervisor might still report the wrong C-bit position, but this + * can't be checked here. + */ + + if ((fn == 1 && !(regs->cx & BIT(31)))) + /* Hypervisor bit */ + goto fail; + else if (fn == 0x80000000 && (regs->ax < 0x8000001f)) + /* SEV leaf check */ + goto fail; + else if ((fn == 0x8000001f && !(regs->ax & BIT(1)))) + /* SEV bit */ + goto fail; + /* Skip over the CPUID two-byte opcode */ regs->ip += 2; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 4a96726fbaf8..0bd1a0fc587e 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -374,8 +374,8 @@ fault: return ES_EXCEPTION; } -static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, - unsigned long vaddr, phys_addr_t *paddr) +static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned long vaddr, phys_addr_t *paddr) { unsigned long va = (unsigned long)vaddr; unsigned int level; @@ -394,15 +394,19 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, if (user_mode(ctxt->regs)) ctxt->fi.error_code |= X86_PF_USER; - return false; + return ES_EXCEPTION; } + if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC)) + /* Emulated MMIO to/from encrypted memory not supported */ + return ES_UNSUPPORTED; + pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; pa |= va & ~page_level_mask(level); *paddr = pa; - return true; + return ES_OK; } /* Include code shared with pre-decompression boot stage */ @@ -731,6 +735,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, { u64 exit_code, exit_info_1, exit_info_2; unsigned long ghcb_pa = __pa(ghcb); + enum es_result res; phys_addr_t paddr; void __user *ref; @@ -740,11 +745,12 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE; - if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) { - if (!read) + res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr); + if (res != ES_OK) { + if (res == ES_EXCEPTION && !read) ctxt->fi.error_code |= X86_PF_WRITE; - return ES_EXCEPTION; + return res; } exit_info_1 = paddr; diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S new file mode 100644 index 000000000000..ee04941a6546 --- /dev/null +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * sev_verify_cbit.S - Code for verification of the C-bit position reported + * by the Hypervisor when running with SEV enabled. + * + * Copyright (c) 2020 Joerg Roedel (jroedel@suse.de) + * + * sev_verify_cbit() is called before switching to a new long-mode page-table + * at boot. + * + * Verify that the C-bit position is correct by writing a random value to + * an encrypted memory location while on the current page-table. Then it + * switches to the new page-table to verify the memory content is still the + * same. After that it switches back to the current page-table and when the + * check succeeded it returns. If the check failed the code invalidates the + * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to + * make sure no interrupt or exception can get the CPU out of the hlt loop. + * + * New page-table pointer is expected in %rdi (first parameter) + * + */ +SYM_FUNC_START(sev_verify_cbit) +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* First check if a C-bit was detected */ + movq sme_me_mask(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */ + movq sev_status(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* Save CR4 in %rsi */ + movq %cr4, %rsi + + /* Disable Global Pages */ + movq %rsi, %rdx + andq $(~X86_CR4_PGE), %rdx + movq %rdx, %cr4 + + /* + * Verified that running under SEV - now get a random value using + * RDRAND. This instruction is mandatory when running as an SEV guest. + * + * Don't bail out of the loop if RDRAND returns errors. It is better to + * prevent forward progress than to work with a non-random value here. + */ +1: rdrand %rdx + jnc 1b + + /* Store value to memory and keep it in %rdx */ + movq %rdx, sev_check_data(%rip) + + /* Backup current %cr3 value to restore it later */ + movq %cr3, %rcx + + /* Switch to new %cr3 - This might unmap the stack */ + movq %rdi, %cr3 + + /* + * Compare value in %rdx with memory location. If C-bit is incorrect + * this would read the encrypted data and make the check fail. + */ + cmpq %rdx, sev_check_data(%rip) + + /* Restore old %cr3 */ + movq %rcx, %cr3 + + /* Restore previous CR4 */ + movq %rsi, %cr4 + + /* Check CMPQ result */ + je 3f + + /* + * The check failed, prevent any forward progress to prevent ROP + * attacks, invalidate the stack and go into a hlt loop. + */ + xorq %rsp, %rsp + subq $0x1000, %rsp +2: hlt + jmp 2b +3: +#endif + /* Return page-table pointer */ + movq %rdi, %rax + ret +SYM_FUNC_END(sev_verify_cbit) diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 992fb1415c0f..ae64f98ec2ab 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -514,16 +514,10 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (intel_iommu_tboot_noforce) - return 1; - - if (no_iommu || swiotlb || dmar_disabled) + if (no_iommu || dmar_disabled) pr_warn("Forcing Intel-IOMMU to enabled\n"); dmar_disabled = 0; -#ifdef CONFIG_SWIOTLB - swiotlb = 0; -#endif no_iommu = 0; return 1; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 06a278b3701d..83637a2ff605 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -90,6 +90,20 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent) return 0; } +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + + /* + * save the feature bitmap to avoid cpuid lookup for every PV + * operation + */ + if (best) + vcpu->arch.pv_cpuid.features = best->eax; +} + void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -124,13 +138,6 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); - /* - * save the feature bitmap to avoid cpuid lookup for every PV - * operation - */ - if (best) - vcpu->arch.pv_cpuid.features = best->eax; - if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = kvm_find_cpuid_entry(vcpu, 0x1, 0); if (best) @@ -162,6 +169,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = (best->eax | ((u64)best->edx << 32)) & supported_xcr0; + kvm_update_pv_runtime(vcpu); + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); kvm_mmu_reset_context(vcpu); @@ -169,6 +178,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); + vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + /* Invoke the vendor callback only after the above state is updated. */ kvm_x86_ops.vcpu_after_set_cpuid(vcpu); } @@ -672,7 +683,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS); edx.split.bit_width_fixed = cap.bit_width_fixed; - edx.split.reserved = 0; + edx.split.anythread_deprecated = 1; + edx.split.reserved1 = 0; + edx.split.reserved2 = 0; entry->eax = eax.full; entry->ebx = cap.events_mask; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index bf8577947ed2..f7a6e8f83783 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -11,6 +11,7 @@ extern u32 kvm_cpu_caps[NCAPINTS] __read_mostly; void kvm_set_cpu_caps(void); void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu); +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0d917eb70319..56cae1ff9e3f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4046,6 +4046,12 @@ static int em_clflush(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_clflushopt(struct x86_emulate_ctxt *ctxt) +{ + /* emulating clflushopt regardless of cpuid */ + return X86EMUL_CONTINUE; +} + static int em_movsxd(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = (s32) ctxt->src.val; @@ -4585,7 +4591,7 @@ static const struct opcode group11[] = { }; static const struct gprefix pfx_0f_ae_7 = { - I(SrcMem | ByteOp, em_clflush), N, N, N, + I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N, }; static const struct group_dual group15 = { { diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 99d118ffc67d..814698e5b152 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -40,29 +40,10 @@ static int pending_userspace_extint(struct kvm_vcpu *v) * check if there is pending interrupt from * non-APIC source without intack. */ -static int kvm_cpu_has_extint(struct kvm_vcpu *v) -{ - u8 accept = kvm_apic_accept_pic_intr(v); - - if (accept) { - if (irqchip_split(v->kvm)) - return pending_userspace_extint(v); - else - return v->kvm->arch.vpic->output; - } else - return 0; -} - -/* - * check if there is injectable interrupt: - * when virtual interrupt delivery enabled, - * interrupt from apic will handled by hardware, - * we don't need to check it here. - */ -int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +int kvm_cpu_has_extint(struct kvm_vcpu *v) { /* - * FIXME: interrupt.injected represents an interrupt that it's + * FIXME: interrupt.injected represents an interrupt whose * side-effects have already been applied (e.g. bit from IRR * already moved to ISR). Therefore, it is incorrect to rely * on interrupt.injected to know if there is a pending @@ -75,6 +56,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.injected; + if (!kvm_apic_accept_pic_intr(v)) + return 0; + + if (irqchip_split(v->kvm)) + return pending_userspace_extint(v); + else + return v->kvm->arch.vpic->output; +} + +/* + * check if there is injectable interrupt: + * when virtual interrupt delivery enabled, + * interrupt from apic will handled by hardware, + * we don't need to check it here. + */ +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +{ if (kvm_cpu_has_extint(v)) return 1; @@ -91,20 +89,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr); */ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) { - /* - * FIXME: interrupt.injected represents an interrupt that it's - * side-effects have already been applied (e.g. bit from IRR - * already moved to ISR). Therefore, it is incorrect to rely - * on interrupt.injected to know if there is a pending - * interrupt in the user-mode LAPIC. - * This leads to nVMX/nSVM not be able to distinguish - * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on - * pending interrupt or should re-inject an injected - * interrupt. - */ - if (!lapic_in_kernel(v)) - return v->arch.interrupt.injected; - if (kvm_cpu_has_extint(v)) return 1; @@ -118,16 +102,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); */ static int kvm_cpu_get_extint(struct kvm_vcpu *v) { - if (kvm_cpu_has_extint(v)) { - if (irqchip_split(v->kvm)) { - int vector = v->arch.pending_external_vector; - - v->arch.pending_external_vector = -1; - return vector; - } else - return kvm_pic_read_irq(v->kvm); /* PIC */ - } else + if (!kvm_cpu_has_extint(v)) { + WARN_ON(!lapic_in_kernel(v)); return -1; + } + + if (!lapic_in_kernel(v)) + return v->arch.interrupt.nr; + + if (irqchip_split(v->kvm)) { + int vector = v->arch.pending_external_vector; + + v->arch.pending_external_vector = -1; + return vector; + } else + return kvm_pic_read_irq(v->kvm); /* PIC */ } /* @@ -135,13 +124,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) */ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) { - int vector; - - if (!lapic_in_kernel(v)) - return v->arch.interrupt.nr; - - vector = kvm_cpu_get_extint(v); - + int vector = kvm_cpu_get_extint(v); if (vector != -1) return vector; /* PIC */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 105e7859d1f2..86c33d53c90a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2465,7 +2465,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (!kvm_apic_hw_enabled(apic)) + if (!kvm_apic_present(vcpu)) return -1; __apic_update_ppr(apic, &ppr); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1f96adff8dc4..7a6ae9e90bd7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -856,12 +856,14 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, } else { rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - while (desc->sptes[PTE_LIST_EXT-1] && desc->more) { - desc = desc->more; + while (desc->sptes[PTE_LIST_EXT-1]) { count += PTE_LIST_EXT; - } - if (desc->sptes[PTE_LIST_EXT-1]) { - desc->more = mmu_alloc_pte_list_desc(vcpu); + + if (!desc->more) { + desc->more = mmu_alloc_pte_list_desc(vcpu); + desc = desc->more; + break; + } desc = desc->more; } for (i = 0; desc->sptes[i]; ++i) @@ -3515,7 +3517,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { u64 sptes[PT64_ROOT_MAX_LEVEL]; struct rsvd_bits_validate *rsvd_check; - int root = vcpu->arch.mmu->root_level; + int root = vcpu->arch.mmu->shadow_root_level; int leaf; int level; bool reserved = false; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 27e381c9da6c..ff28a5c6abd6 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -49,7 +49,14 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) { struct kvm_mmu_page *sp; + if (!kvm->arch.tdp_mmu_enabled) + return false; + if (WARN_ON(!VALID_PAGE(hpa))) + return false; + sp = to_shadow_page(hpa); + if (WARN_ON(!sp)) + return false; return sp->tdp_mmu_page && sp->root_count; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c0b14106258a..566f4d18185b 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -642,8 +642,8 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, * Its safe to read more than we are asked, caller should ensure that * destination has enough space. */ - src_paddr = round_down(src_paddr, 16); offset = src_paddr & 15; + src_paddr = round_down(src_paddr, 16); sz = round_up(sz + offset, 16); return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2f32fd09e259..79b3a564f1c9 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1309,8 +1309,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm->avic_is_running = true; svm->msrpm = svm_vcpu_alloc_msrpm(); - if (!svm->msrpm) + if (!svm->msrpm) { + err = -ENOMEM; goto error_free_vmcb_page; + } svm_vcpu_init_msrpm(vcpu, svm->msrpm); @@ -3741,6 +3743,7 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_cpuid_entry2 *best; vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && boot_cpu_has(X86_FEATURE_XSAVE) && @@ -3753,6 +3756,13 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) /* Check again if INVPCID interception if required */ svm_check_invpcid(svm); + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + if (sev_guest(vcpu->kvm)) { + best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0); + if (best) + vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f)); + } + if (!kvm_vcpu_apicv_active(vcpu)) return; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f5ede41bf9e6..e545a8a613b1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -255,11 +255,10 @@ static struct kmem_cache *x86_emulator_cache; /* * When called, it means the previous get/set msr reached an invalid msr. - * Return 0 if we want to ignore/silent this failed msr access, or 1 if we want - * to fail the caller. + * Return true if we want to ignore/silent this failed msr access. */ -static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, - u64 data, bool write) +static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, + u64 data, bool write) { const char *op = write ? "wrmsr" : "rdmsr"; @@ -268,11 +267,11 @@ static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, data); /* Mask the error */ - return 0; + return true; } else { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", op, msr, data); - return -ENOENT; + return false; } } @@ -1042,7 +1041,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu) && - (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63))) + (cr3 & vcpu->arch.cr3_lm_rsvd_bits)) return 1; else if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) @@ -1416,7 +1415,8 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) if (r == KVM_MSR_RET_INVALID) { /* Unconditionally clear the output for simplicity */ *data = 0; - r = kvm_msr_ignored_check(vcpu, index, 0, false); + if (kvm_msr_ignored_check(vcpu, index, 0, false)) + r = 0; } if (r) @@ -1540,7 +1540,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, struct msr_data msr; if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) - return -EPERM; + return KVM_MSR_RET_FILTERED; switch (index) { case MSR_FS_BASE: @@ -1581,7 +1581,8 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, int ret = __kvm_set_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) - ret = kvm_msr_ignored_check(vcpu, index, data, true); + if (kvm_msr_ignored_check(vcpu, index, data, true)) + ret = 0; return ret; } @@ -1599,7 +1600,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, int ret; if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) - return -EPERM; + return KVM_MSR_RET_FILTERED; msr.index = index; msr.host_initiated = host_initiated; @@ -1618,7 +1619,8 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, if (ret == KVM_MSR_RET_INVALID) { /* Unconditionally clear *data for simplicity */ *data = 0; - ret = kvm_msr_ignored_check(vcpu, index, 0, false); + if (kvm_msr_ignored_check(vcpu, index, 0, false)) + ret = 0; } return ret; @@ -1662,9 +1664,9 @@ static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) static u64 kvm_msr_reason(int r) { switch (r) { - case -ENOENT: + case KVM_MSR_RET_INVALID: return KVM_MSR_EXIT_REASON_UNKNOWN; - case -EPERM: + case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; default: return KVM_MSR_EXIT_REASON_INVAL; @@ -1965,7 +1967,7 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, struct kvm_arch *ka = &vcpu->kvm->arch; if (vcpu->vcpu_id == 0 && !host_initiated) { - if (ka->boot_vcpu_runs_old_kvmclock && old_msr) + if (ka->boot_vcpu_runs_old_kvmclock != old_msr) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); ka->boot_vcpu_runs_old_kvmclock = old_msr; @@ -3063,9 +3065,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Values other than LBR and BTF are vendor-specific, thus reserved and should throw a #GP */ return 1; - } - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + } else if (report_ignored_msrs) + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); break; case 0x200 ... 0x2ff: return kvm_mtrr_set_msr(vcpu, msr, data); @@ -3463,29 +3465,63 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->kvm->arch.wall_clock; + break; case MSR_KVM_WALL_CLOCK_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->arch.time; + break; case MSR_KVM_SYSTEM_TIME_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + msr_info->data = vcpu->arch.apf.msr_en_val; break; case MSR_KVM_ASYNC_PF_INT: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) + return 1; + msr_info->data = vcpu->arch.apf.msr_int_val; break; case MSR_KVM_ASYNC_PF_ACK: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + msr_info->data = 0; break; case MSR_KVM_STEAL_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) + return 1; + msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) + return 1; + msr_info->data = vcpu->arch.pv_eoi.msr_val; break; case MSR_KVM_POLL_CONTROL: + if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) + return 1; + msr_info->data = vcpu->arch.msr_kvm_poll_control; break; case MSR_IA32_P5_MC_ADDR: @@ -4015,21 +4051,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) { + /* + * We can accept userspace's request for interrupt injection + * as long as we have a place to store the interrupt number. + * The actual injection will happen when the CPU is able to + * deliver the interrupt. + */ + if (kvm_cpu_has_extint(vcpu)) + return false; + + /* Acknowledging ExtINT does not happen if LINT0 is masked. */ return (!lapic_in_kernel(vcpu) || kvm_apic_accept_pic_intr(vcpu)); } -/* - * if userspace requested an interrupt window, check that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { return kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); } @@ -4575,6 +4613,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; + if (vcpu->arch.pv_cpuid.enforce) + kvm_update_pv_runtime(vcpu); return 0; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 3900ab0c6004..e7ca622a468f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -376,7 +376,13 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); -#define KVM_MSR_RET_INVALID 2 +/* + * Internal error codes that are used to indicate that MSR emulation encountered + * an error that should result in #GP in the guest, unless userspace + * handles it. + */ +#define KVM_MSR_RET_INVALID 2 /* in-kernel MSR emulation #GP condition */ +#define KVM_MSR_RET_FILTERED 3 /* #GP due to userspace MSR filter */ #define __cr4_reserved_bits(__cpu_has, __c) \ ({ \ diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 037faac46b0c..1e299ac73c86 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -16,8 +16,6 @@ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. */ -.weak memcpy - /* * memcpy - Copy a memory block. * @@ -30,7 +28,7 @@ * rax original destination */ SYM_FUNC_START_ALIAS(__memcpy) -SYM_FUNC_START_LOCAL(memcpy) +SYM_FUNC_START_WEAK(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 7ff00ea64e4f..41902fe8b859 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -24,9 +24,7 @@ * Output: * rax: dest */ -.weak memmove - -SYM_FUNC_START_ALIAS(memmove) +SYM_FUNC_START_WEAK(memmove) SYM_FUNC_START(__memmove) mov %rdi, %rax diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 9ff15ee404a4..0bfd26e4ca9e 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -6,8 +6,6 @@ #include <asm/alternative-asm.h> #include <asm/export.h> -.weak memset - /* * ISO C memset - set a memory block to a byte value. This function uses fast * string to get better performance than the original function. The code is @@ -19,7 +17,7 @@ * * rax original destination */ -SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START_WEAK(memset) SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index efbb3de472df..bc0833713be9 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -39,6 +39,7 @@ */ u64 sme_me_mask __section(".data") = 0; u64 sev_status __section(".data") = 0; +u64 sev_check_data __section(".data") = 0; EXPORT_SYMBOL(sme_me_mask); DEFINE_STATIC_KEY_FALSE(sev_enable_key); EXPORT_SYMBOL_GPL(sev_enable_key); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 44148691d78b..5eb4dc2b97da 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -938,6 +938,7 @@ int phys_to_target_node(phys_addr_t start) return meminfo_to_nid(&numa_reserved_meminfo, start); } +EXPORT_SYMBOL_GPL(phys_to_target_node); int memory_add_physaddr_to_nid(u64 start) { @@ -947,4 +948,5 @@ int memory_add_physaddr_to_nid(u64 start) nid = numa_meminfo.blk[0].nid; return nid; } +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 8f5759df7776..e1e8d4e3a213 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -78,28 +78,30 @@ int __init efi_alloc_page_tables(void) gfp_mask = GFP_KERNEL | __GFP_ZERO; efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); if (!efi_pgd) - return -ENOMEM; + goto fail; pgd = efi_pgd + pgd_index(EFI_VA_END); p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END); - if (!p4d) { - free_page((unsigned long)efi_pgd); - return -ENOMEM; - } + if (!p4d) + goto free_pgd; pud = pud_alloc(&init_mm, p4d, EFI_VA_END); - if (!pud) { - if (pgtable_l5_enabled()) - free_page((unsigned long) pgd_page_vaddr(*pgd)); - free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); - return -ENOMEM; - } + if (!pud) + goto free_p4d; efi_mm.pgd = efi_pgd; mm_init_cpumask(&efi_mm); init_new_context(NULL, &efi_mm); return 0; + +free_p4d: + if (pgtable_l5_enabled()) + free_page((unsigned long)pgd_page_vaddr(*pgd)); +free_pgd: + free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); +fail: + return -ENOMEM; } /* diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 799f4eba0a62..043c73dfd2c9 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -93,10 +93,20 @@ void xen_init_lock_cpu(int cpu) void xen_uninit_lock_cpu(int cpu) { + int irq; + if (!xen_pvspin) return; - unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); + /* + * When booting the kernel with 'mitigations=auto,nosmt', the secondary + * CPUs are not activated, and lock_kicker_irq is not initialized. + */ + irq = per_cpu(lock_kicker_irq, cpu); + if (irq == -1) + return; + + unbind_from_irqhandler(irq, NULL); per_cpu(lock_kicker_irq, cpu) = -1; kfree(per_cpu(irq_name, cpu)); per_cpu(irq_name, cpu) = NULL; diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index fa054a1772e1..4dc04e6c01d7 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -69,7 +69,7 @@ */ #define VMALLOC_START (XCHAL_KSEG_CACHED_VADDR - 0x10000000) #define VMALLOC_END (VMALLOC_START + 0x07FEFFFF) -#define TLBTEMP_BASE_1 (VMALLOC_END + 1) +#define TLBTEMP_BASE_1 (VMALLOC_START + 0x08000000) #define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE) #if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE #define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE) diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index b9758119feca..5c9fb8005aa8 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -302,7 +302,7 @@ strncpy_from_user(char *dst, const char __user *src, long count) return -EFAULT; } #else -long strncpy_from_user(char *dst, const char *src, long count); +long strncpy_from_user(char *dst, const char __user *src, long count); #endif /* diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 5835406b3cec..085b8c77b9d9 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -70,8 +70,10 @@ static inline void kmap_invalidate_coherent(struct page *page, kvaddr = TLBTEMP_BASE_1 + (page_to_phys(page) & DCACHE_ALIAS_MASK); + preempt_disable(); __invalidate_dcache_page_alias(kvaddr, page_to_phys(page)); + preempt_enable(); } } } @@ -156,6 +158,7 @@ void flush_dcache_page(struct page *page) if (!alias && !mapping) return; + preempt_disable(); virt = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(virt, phys); @@ -166,6 +169,7 @@ void flush_dcache_page(struct page *page) if (mapping) __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } /* There shouldn't be an entry in the cache for this page anymore. */ @@ -199,8 +203,10 @@ void local_flush_cache_page(struct vm_area_struct *vma, unsigned long address, unsigned long phys = page_to_phys(pfn_to_page(pfn)); unsigned long virt = TLBTEMP_BASE_1 + (address & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(virt, phys); __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } EXPORT_SYMBOL(local_flush_cache_page); @@ -227,11 +233,13 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep) unsigned long phys = page_to_phys(page); unsigned long tmp; + preempt_disable(); tmp = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); tmp = TLBTEMP_BASE_1 + (addr & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); __invalidate_icache_page_alias(tmp, phys); + preempt_enable(); clear_bit(PG_arch_1, &page->flags); } @@ -265,7 +273,9 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } /* Copy data */ @@ -280,9 +290,11 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_range((unsigned long) dst, len); if ((vma->vm_flags & VM_EXEC) != 0) __invalidate_icache_page_alias(t, phys); + preempt_enable(); } else if ((vma->vm_flags & VM_EXEC) != 0) { __flush_dcache_range((unsigned long)dst,len); @@ -304,7 +316,9 @@ extern void copy_from_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } memcpy(dst, src, len); diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index c6fc83efee0c..8731b7ad9308 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -89,8 +89,8 @@ static void __init free_highpages(void) /* set highmem page free */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &range_start, &range_end, NULL) { - unsigned long start = PHYS_PFN(range_start); - unsigned long end = PHYS_PFN(range_end); + unsigned long start = PFN_UP(range_start); + unsigned long end = PFN_DOWN(range_end); /* Ignore complete lowmem entries */ if (end <= max_low) |