diff options
189 files changed, 2088 insertions, 1110 deletions
diff --git a/Documentation/devicetree/bindings/misc/arm-charlcd.txt b/Documentation/devicetree/bindings/auxdisplay/arm-charlcd.txt index e28e2aac47f1..e28e2aac47f1 100644 --- a/Documentation/devicetree/bindings/misc/arm-charlcd.txt +++ b/Documentation/devicetree/bindings/auxdisplay/arm-charlcd.txt diff --git a/Documentation/devicetree/bindings/power/wakeup-source.txt b/Documentation/devicetree/bindings/power/wakeup-source.txt index 3c81f78b5c27..5d254ab13ebf 100644 --- a/Documentation/devicetree/bindings/power/wakeup-source.txt +++ b/Documentation/devicetree/bindings/power/wakeup-source.txt @@ -60,7 +60,7 @@ Examples #size-cells = <0>; button@1 { - debounce_interval = <50>; + debounce-interval = <50>; wakeup-source; linux,code = <116>; label = "POWER"; diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.txt b/Documentation/devicetree/bindings/thermal/imx-thermal.txt index 28be51afdb6a..379eb763073e 100644 --- a/Documentation/devicetree/bindings/thermal/imx-thermal.txt +++ b/Documentation/devicetree/bindings/thermal/imx-thermal.txt @@ -22,7 +22,32 @@ Optional properties: - clocks : thermal sensor's clock source. Example: +ocotp: ocotp@21bc000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,imx6sx-ocotp", "syscon"; + reg = <0x021bc000 0x4000>; + clocks = <&clks IMX6SX_CLK_OCOTP>; + tempmon_calib: calib@38 { + reg = <0x38 4>; + }; + + tempmon_temp_grade: temp-grade@20 { + reg = <0x20 4>; + }; +}; + +tempmon: tempmon { + compatible = "fsl,imx6sx-tempmon", "fsl,imx6q-tempmon"; + interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>; + fsl,tempmon = <&anatop>; + nvmem-cells = <&tempmon_calib>, <&tempmon_temp_grade>; + nvmem-cell-names = "calib", "temp_grade"; + clocks = <&clks IMX6SX_CLK_PLL3_USB_OTG>; +}; + +Legacy method (Deprecated): tempmon { compatible = "fsl,imx6q-tempmon"; fsl,tempmon = <&anatop>; diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt index dcab6dc11e3b..87a7506f31c2 100644 --- a/Documentation/virtual/kvm/cpuid.txt +++ b/Documentation/virtual/kvm/cpuid.txt @@ -58,6 +58,10 @@ KVM_FEATURE_PV_TLB_FLUSH || 9 || guest checks this feature bit || || before enabling paravirtualized || || tlb flush. ------------------------------------------------------------------------------ +KVM_FEATURE_ASYNC_PF_VMEXIT || 10 || paravirtualized async PF VM exit + || || can be enabled by setting bit 2 + || || when writing to msr 0x4b564d02 +------------------------------------------------------------------------------ KVM_FEATURE_CLOCKSOURCE_STABLE_BIT || 24 || host will warn if no guest-side || || per-cpu warps are expected in || || kvmclock. diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt index 1ebecc115dc6..f3f0d57ced8e 100644 --- a/Documentation/virtual/kvm/msr.txt +++ b/Documentation/virtual/kvm/msr.txt @@ -170,7 +170,8 @@ MSR_KVM_ASYNC_PF_EN: 0x4b564d02 when asynchronous page faults are enabled on the vcpu 0 when disabled. Bit 1 is 1 if asynchronous page faults can be injected when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults - are delivered to L1 as #PF vmexits. + are delivered to L1 as #PF vmexits. Bit 2 can be set only if + KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID. First 4 byte of 64 byte memory location will be written to by the hypervisor at the time of asynchronous page fault (APF) diff --git a/MAINTAINERS b/MAINTAINERS index 93a12af4f180..1c95c6036098 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1238,7 +1238,7 @@ F: drivers/clk/at91 ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT M: Nicolas Ferre <nicolas.ferre@microchip.com> -M: Alexandre Belloni <alexandre.belloni@free-electrons.com> +M: Alexandre Belloni <alexandre.belloni@bootlin.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) W: http://www.linux4sam.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/nferre/linux-at91.git @@ -1590,7 +1590,7 @@ ARM/Marvell Dove/MV78xx0/Orion SOC support M: Jason Cooper <jason@lakedaemon.net> M: Andrew Lunn <andrew@lunn.ch> M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> -M: Gregory Clement <gregory.clement@free-electrons.com> +M: Gregory Clement <gregory.clement@bootlin.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/soc/dove/ @@ -1604,7 +1604,7 @@ F: arch/arm/boot/dts/orion5x* ARM/Marvell Kirkwood and Armada 370, 375, 38x, 39x, XP, 3700, 7K/8K SOC support M: Jason Cooper <jason@lakedaemon.net> M: Andrew Lunn <andrew@lunn.ch> -M: Gregory Clement <gregory.clement@free-electrons.com> +M: Gregory Clement <gregory.clement@bootlin.com> M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -1999,8 +1999,10 @@ M: Maxime Coquelin <mcoquelin.stm32@gmail.com> M: Alexandre Torgue <alexandre.torgue@st.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/mcoquelin/stm32.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/atorgue/stm32.git stm32-next N: stm32 +F: arch/arm/boot/dts/stm32* +F: arch/arm/mach-stm32/ F: drivers/clocksource/armv7m_systick.c ARM/TANGO ARCHITECTURE @@ -10926,6 +10928,17 @@ L: linux-gpio@vger.kernel.org S: Supported F: drivers/pinctrl/pinctrl-at91-pio4.* +PIN CONTROLLER - FREESCALE +M: Dong Aisheng <aisheng.dong@nxp.com> +M: Fabio Estevam <festevam@gmail.com> +M: Shawn Guo <shawnguo@kernel.org> +M: Stefan Agner <stefan@agner.ch> +R: Pengutronix Kernel Team <kernel@pengutronix.de> +L: linux-gpio@vger.kernel.org +S: Maintained +F: drivers/pinctrl/freescale/ +F: Documentation/devicetree/bindings/pinctrl/fsl,* + PIN CONTROLLER - INTEL M: Mika Westerberg <mika.westerberg@linux.intel.com> M: Heikki Krogerus <heikki.krogerus@linux.intel.com> @@ -489,6 +489,11 @@ KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) endif +RETPOLINE_CFLAGS_GCC := -mindirect-branch=thunk-extern -mindirect-branch-register +RETPOLINE_CFLAGS_CLANG := -mretpoline-external-thunk +RETPOLINE_CFLAGS := $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG))) +export RETPOLINE_CFLAGS + ifeq ($(config-targets),1) # =========================================================================== # *config targets only - make sure prerequisites are updated, and descend diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index f3a80cf164cc..d76bf4a83740 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -484,7 +484,6 @@ config ARC_CURR_IN_REG config ARC_EMUL_UNALIGNED bool "Emulate unaligned memory access (userspace only)" - default N select SYSCTL_ARCH_UNALIGN_NO_WARN select SYSCTL_ARCH_UNALIGN_ALLOW depends on ISA_ARCOMPACT diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts index 70aec7d6ca60..626b694c7be7 100644 --- a/arch/arc/boot/dts/axs101.dts +++ b/arch/arc/boot/dts/axs101.dts @@ -17,6 +17,6 @@ compatible = "snps,axs101", "snps,arc-sdp"; chosen { - bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60"; + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60 print-fatal-signals=1"; }; }; diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 74d070cd3c13..47b74fbc403c 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -214,13 +214,13 @@ }; eeprom@0x54{ - compatible = "24c01"; + compatible = "atmel,24c01"; reg = <0x54>; pagesize = <0x8>; }; eeprom@0x57{ - compatible = "24c04"; + compatible = "atmel,24c04"; reg = <0x57>; pagesize = <0x8>; }; diff --git a/arch/arc/boot/dts/haps_hs_idu.dts b/arch/arc/boot/dts/haps_hs_idu.dts index 215cddd0b63b..0c603308aeb3 100644 --- a/arch/arc/boot/dts/haps_hs_idu.dts +++ b/arch/arc/boot/dts/haps_hs_idu.dts @@ -22,7 +22,7 @@ }; chosen { - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts index 5ee96b067c08..ff2f2c70c545 100644 --- a/arch/arc/boot/dts/nsim_700.dts +++ b/arch/arc/boot/dts/nsim_700.dts @@ -17,7 +17,7 @@ interrupt-parent = <&core_intc>; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts index 8d787b251f73..8e2489b16b0a 100644 --- a/arch/arc/boot/dts/nsim_hs.dts +++ b/arch/arc/boot/dts/nsim_hs.dts @@ -24,7 +24,7 @@ }; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts index 4f98ebf71fd8..ed12f494721d 100644 --- a/arch/arc/boot/dts/nsim_hs_idu.dts +++ b/arch/arc/boot/dts/nsim_hs_idu.dts @@ -15,7 +15,7 @@ interrupt-parent = <&core_intc>; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index 3c391ba565ed..7842e5eb4ab5 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -20,7 +20,7 @@ /* this is for console on PGU */ /* bootargs = "console=tty0 consoleblank=0"; */ /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts index 14a727cbf4c9..b8838cf2b4ec 100644 --- a/arch/arc/boot/dts/nsimosci_hs.dts +++ b/arch/arc/boot/dts/nsimosci_hs.dts @@ -20,7 +20,7 @@ /* this is for console on PGU */ /* bootargs = "console=tty0 consoleblank=0"; */ /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts index 5052917d4a99..72a2c723f1f7 100644 --- a/arch/arc/boot/dts/nsimosci_hs_idu.dts +++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts @@ -18,7 +18,7 @@ chosen { /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h index 257a68f3c2fe..309f4e6721b3 100644 --- a/arch/arc/include/asm/entry-arcv2.h +++ b/arch/arc/include/asm/entry-arcv2.h @@ -184,7 +184,7 @@ .macro FAKE_RET_FROM_EXCPN lr r9, [status32] bic r9, r9, (STATUS_U_MASK|STATUS_DE_MASK|STATUS_AE_MASK) - or r9, r9, (STATUS_L_MASK|STATUS_IE_MASK) + or r9, r9, STATUS_IE_MASK kflag r9 .endm diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index f61a52b01625..5fe84e481654 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -22,10 +22,79 @@ static DEFINE_RAW_SPINLOCK(mcip_lock); static char smp_cpuinfo_buf[128]; +/* + * Set mask to halt GFRC if any online core in SMP cluster is halted. + * Only works for ARC HS v3.0+, on earlier versions has no effect. + */ +static void mcip_update_gfrc_halt_mask(int cpu) +{ + struct bcr_generic gfrc; + unsigned long flags; + u32 gfrc_halt_mask; + + READ_BCR(ARC_REG_GFRC_BUILD, gfrc); + + /* + * CMD_GFRC_SET_CORE and CMD_GFRC_READ_CORE commands were added in + * GFRC 0x3 version. + */ + if (gfrc.ver < 0x3) + return; + + raw_spin_lock_irqsave(&mcip_lock, flags); + + __mcip_cmd(CMD_GFRC_READ_CORE, 0); + gfrc_halt_mask = read_aux_reg(ARC_REG_MCIP_READBACK); + gfrc_halt_mask |= BIT(cpu); + __mcip_cmd_data(CMD_GFRC_SET_CORE, 0, gfrc_halt_mask); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + +static void mcip_update_debug_halt_mask(int cpu) +{ + u32 mcip_mask = 0; + unsigned long flags; + + raw_spin_lock_irqsave(&mcip_lock, flags); + + /* + * mcip_mask is same for CMD_DEBUG_SET_SELECT and CMD_DEBUG_SET_MASK + * commands. So read it once instead of reading both CMD_DEBUG_READ_MASK + * and CMD_DEBUG_READ_SELECT. + */ + __mcip_cmd(CMD_DEBUG_READ_SELECT, 0); + mcip_mask = read_aux_reg(ARC_REG_MCIP_READBACK); + + mcip_mask |= BIT(cpu); + + __mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, mcip_mask); + /* + * Parameter specified halt cause: + * STATUS32[H]/actionpoint/breakpoint/self-halt + * We choose all of them (0xF). + */ + __mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xF, mcip_mask); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + static void mcip_setup_per_cpu(int cpu) { + struct mcip_bcr mp; + + READ_BCR(ARC_REG_MCIP_BCR, mp); + smp_ipi_irq_setup(cpu, IPI_IRQ); smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); + + /* Update GFRC halt mask as new CPU came online */ + if (mp.gfrc) + mcip_update_gfrc_halt_mask(cpu); + + /* Update MCIP debug mask as new CPU came online */ + if (mp.dbg) + mcip_update_debug_halt_mask(cpu); } static void mcip_ipi_send(int cpu) @@ -101,11 +170,6 @@ static void mcip_probe_n_setup(void) IS_AVAIL1(mp.gfrc, "GFRC")); cpuinfo_arc700[0].extn.gfrc = mp.gfrc; - - if (mp.dbg) { - __mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf); - __mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf); - } } struct plat_smp_ops plat_smp_ops = { diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index ec12fe1c2f07..b2cae79a25d7 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -51,7 +51,7 @@ static const struct id_to_str arc_cpu_rel[] = { { 0x51, "R2.0" }, { 0x52, "R2.1" }, { 0x53, "R3.0" }, - { 0x54, "R4.0" }, + { 0x54, "R3.10a" }, #endif { 0x00, NULL } }; diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index efe8b4200a67..21d86c36692b 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -24,6 +24,7 @@ #include <linux/reboot.h> #include <linux/irqdomain.h> #include <linux/export.h> +#include <linux/of_fdt.h> #include <asm/processor.h> #include <asm/setup.h> @@ -47,6 +48,42 @@ void __init smp_prepare_boot_cpu(void) { } +static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask) +{ + unsigned long dt_root = of_get_flat_dt_root(); + const char *buf; + + buf = of_get_flat_dt_prop(dt_root, name, NULL); + if (!buf) + return -EINVAL; + + if (cpulist_parse(buf, cpumask)) + return -EINVAL; + + return 0; +} + +/* + * Read from DeviceTree and setup cpu possible mask. If there is no + * "possible-cpus" property in DeviceTree pretend all [0..NR_CPUS-1] exist. + */ +static void __init arc_init_cpu_possible(void) +{ + struct cpumask cpumask; + + if (arc_get_cpu_map("possible-cpus", &cpumask)) { + pr_warn("Failed to get possible-cpus from dtb, pretending all %u cpus exist\n", + NR_CPUS); + + cpumask_setall(&cpumask); + } + + if (!cpumask_test_cpu(0, &cpumask)) + panic("Master cpu (cpu[0]) is missed in cpu possible mask!"); + + init_cpu_possible(&cpumask); +} + /* * Called from setup_arch() before calling setup_processor() * @@ -58,10 +95,7 @@ void __init smp_prepare_boot_cpu(void) */ void __init smp_init_cpus(void) { - unsigned int i; - - for (i = 0; i < NR_CPUS; i++) - set_cpu_possible(i, true); + arc_init_cpu_possible(); if (plat_smp_ops.init_early_smp) plat_smp_ops.init_early_smp(); @@ -70,16 +104,12 @@ void __init smp_init_cpus(void) /* called from init ( ) => process 1 */ void __init smp_prepare_cpus(unsigned int max_cpus) { - int i; - /* * if platform didn't set the present map already, do it now * boot cpu is set to present already by init/main.c */ - if (num_present_cpus() <= 1) { - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); - } + if (num_present_cpus() <= 1) + init_cpu_present(cpu_possible_mask); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index eee924dfffa6..2072f3451e9c 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -780,7 +780,10 @@ noinline static void slc_entire_op(const int op) write_aux_reg(r, ctrl); - write_aux_reg(ARC_REG_SLC_INVALIDATE, 1); + if (op & OP_INV) /* Inv or flush-n-inv use same cmd reg */ + write_aux_reg(ARC_REG_SLC_INVALIDATE, 0x1); + else + write_aux_reg(ARC_REG_SLC_FLUSH, 0x1); /* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */ read_aux_reg(r); diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi index 18045c38bcf1..db7cded1b7ad 100644 --- a/arch/arm/boot/dts/bcm11351.dtsi +++ b/arch/arm/boot/dts/bcm11351.dtsi @@ -55,7 +55,7 @@ <0x3ff00100 0x100>; }; - smc@0x3404c000 { + smc@3404c000 { compatible = "brcm,bcm11351-smc", "brcm,kona-smc"; reg = <0x3404c000 0x400>; /* 1 KiB in SRAM */ }; diff --git a/arch/arm/boot/dts/bcm21664.dtsi b/arch/arm/boot/dts/bcm21664.dtsi index 6dde95f21cef..266f2611dc22 100644 --- a/arch/arm/boot/dts/bcm21664.dtsi +++ b/arch/arm/boot/dts/bcm21664.dtsi @@ -55,7 +55,7 @@ <0x3ff00100 0x100>; }; - smc@0x3404e000 { + smc@3404e000 { compatible = "brcm,bcm21664-smc", "brcm,kona-smc"; reg = <0x3404e000 0x400>; /* 1 KiB in SRAM */ }; diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi index 0e3d2a5ff208..a5c3824c8056 100644 --- a/arch/arm/boot/dts/bcm2835.dtsi +++ b/arch/arm/boot/dts/bcm2835.dtsi @@ -18,10 +18,10 @@ soc { ranges = <0x7e000000 0x20000000 0x02000000>; dma-ranges = <0x40000000 0x00000000 0x20000000>; + }; - arm-pmu { - compatible = "arm,arm1176-pmu"; - }; + arm-pmu { + compatible = "arm,arm1176-pmu"; }; }; diff --git a/arch/arm/boot/dts/bcm2836.dtsi b/arch/arm/boot/dts/bcm2836.dtsi index 1dfd76442777..c933e8413884 100644 --- a/arch/arm/boot/dts/bcm2836.dtsi +++ b/arch/arm/boot/dts/bcm2836.dtsi @@ -9,19 +9,19 @@ <0x40000000 0x40000000 0x00001000>; dma-ranges = <0xc0000000 0x00000000 0x3f000000>; - local_intc: local_intc { + local_intc: local_intc@40000000 { compatible = "brcm,bcm2836-l1-intc"; reg = <0x40000000 0x100>; interrupt-controller; #interrupt-cells = <2>; interrupt-parent = <&local_intc>; }; + }; - arm-pmu { - compatible = "arm,cortex-a7-pmu"; - interrupt-parent = <&local_intc>; - interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; - }; + arm-pmu { + compatible = "arm,cortex-a7-pmu"; + interrupt-parent = <&local_intc>; + interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; }; timer { diff --git a/arch/arm/boot/dts/bcm2837.dtsi b/arch/arm/boot/dts/bcm2837.dtsi index efa7d3387ab2..7704bb029605 100644 --- a/arch/arm/boot/dts/bcm2837.dtsi +++ b/arch/arm/boot/dts/bcm2837.dtsi @@ -8,7 +8,7 @@ <0x40000000 0x40000000 0x00001000>; dma-ranges = <0xc0000000 0x00000000 0x3f000000>; - local_intc: local_intc { + local_intc: local_intc@40000000 { compatible = "brcm,bcm2836-l1-intc"; reg = <0x40000000 0x100>; interrupt-controller; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 18db25a5a66e..9d293decf8d3 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -465,7 +465,7 @@ status = "disabled"; }; - aux: aux@0x7e215000 { + aux: aux@7e215000 { compatible = "brcm,bcm2835-aux"; #clock-cells = <1>; reg = <0x7e215000 0x8>; diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts index 6a44b8021702..f0e2008f7490 100644 --- a/arch/arm/boot/dts/bcm958625hr.dts +++ b/arch/arm/boot/dts/bcm958625hr.dts @@ -49,7 +49,7 @@ memory { device_type = "memory"; - reg = <0x60000000 0x80000000>; + reg = <0x60000000 0x20000000>; }; gpio-restart { diff --git a/arch/arm/boot/dts/gemini-dlink-dns-313.dts b/arch/arm/boot/dts/gemini-dlink-dns-313.dts index 08568ce24d06..da8bb9d60f99 100644 --- a/arch/arm/boot/dts/gemini-dlink-dns-313.dts +++ b/arch/arm/boot/dts/gemini-dlink-dns-313.dts @@ -269,7 +269,7 @@ sata: sata@46000000 { /* The ROM uses this muxmode */ - cortina,gemini-ata-muxmode = <3>; + cortina,gemini-ata-muxmode = <0>; cortina,gemini-enable-sata-bridge; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6dl-icore-rqs.dts b/arch/arm/boot/dts/imx6dl-icore-rqs.dts index cf42c2f5cdc7..1281bc39b7ab 100644 --- a/arch/arm/boot/dts/imx6dl-icore-rqs.dts +++ b/arch/arm/boot/dts/imx6dl-icore-rqs.dts @@ -42,7 +42,7 @@ /dts-v1/; -#include "imx6q.dtsi" +#include "imx6dl.dtsi" #include "imx6qdl-icore-rqs.dtsi" / { diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index c1aa7a4518fb..a30ee9fcb3ae 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -71,6 +71,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <2600000>; twl: twl@48 { @@ -189,7 +191,12 @@ >; }; - + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */ + >; + }; }; &omap3_pmx_wkup { diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index b50b796e15c7..47915447a826 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -66,6 +66,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <2600000>; twl: twl@48 { @@ -136,6 +138,12 @@ OMAP3_CORE1_IOPAD(0x21b8, PIN_INPUT | MUX_MODE0) /* hsusb0_data7.hsusb0_data7 */ >; }; + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */ + >; + }; }; &uart2 { diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts index ec2c8baef62a..592e17fd4eeb 100644 --- a/arch/arm/boot/dts/omap5-uevm.dts +++ b/arch/arm/boot/dts/omap5-uevm.dts @@ -47,7 +47,7 @@ gpios = <&gpio3 19 GPIO_ACTIVE_LOW>; /* gpio3_83 */ wakeup-source; autorepeat; - debounce_interval = <50>; + debounce-interval = <50>; }; }; diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi index 3b704cfed69a..a97458112ff6 100644 --- a/arch/arm/boot/dts/rk3036.dtsi +++ b/arch/arm/boot/dts/rk3036.dtsi @@ -280,7 +280,7 @@ max-frequency = <37500000>; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>; resets = <&cru SRST_SDIO>; @@ -298,7 +298,7 @@ max-frequency = <37500000>; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; default-sample-phase = <158>; disable-wp; dmas = <&pdma 12>; diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi index 780ec3a99b21..341deaf62ff6 100644 --- a/arch/arm/boot/dts/rk322x.dtsi +++ b/arch/arm/boot/dts/rk322x.dtsi @@ -621,7 +621,7 @@ interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>, <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_bus4>; @@ -634,7 +634,7 @@ interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; pinctrl-names = "default"; pinctrl-0 = <&sdio_clk &sdio_cmd &sdio_bus4>; @@ -649,7 +649,7 @@ max-frequency = <37500000>; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; bus-width = <8>; default-sample-phase = <158>; fifo-depth = <0x100>; diff --git a/arch/arm/boot/dts/rk3288-phycore-som.dtsi b/arch/arm/boot/dts/rk3288-phycore-som.dtsi index 99cfae875e12..5eae4776ffde 100644 --- a/arch/arm/boot/dts/rk3288-phycore-som.dtsi +++ b/arch/arm/boot/dts/rk3288-phycore-som.dtsi @@ -110,26 +110,6 @@ }; }; -&cpu0 { - cpu0-supply = <&vdd_cpu>; - operating-points = < - /* KHz uV */ - 1800000 1400000 - 1608000 1350000 - 1512000 1300000 - 1416000 1200000 - 1200000 1100000 - 1008000 1050000 - 816000 1000000 - 696000 950000 - 600000 900000 - 408000 900000 - 312000 900000 - 216000 900000 - 126000 900000 - >; -}; - &emmc { status = "okay"; bus-width = <8>; diff --git a/arch/arm/boot/dts/zx296702.dtsi b/arch/arm/boot/dts/zx296702.dtsi index 8a74efdb6360..240e7a23d81f 100644 --- a/arch/arm/boot/dts/zx296702.dtsi +++ b/arch/arm/boot/dts/zx296702.dtsi @@ -56,7 +56,7 @@ clocks = <&topclk ZX296702_A9_PERIPHCLK>; }; - l2cc: l2-cache-controller@0x00c00000 { + l2cc: l2-cache-controller@c00000 { compatible = "arm,pl310-cache"; reg = <0x00c00000 0x1000>; cache-unified; @@ -67,30 +67,30 @@ arm,double-linefill-incr = <0>; }; - pcu: pcu@0xa0008000 { + pcu: pcu@a0008000 { compatible = "zte,zx296702-pcu"; reg = <0xa0008000 0x1000>; }; - topclk: topclk@0x09800000 { + topclk: topclk@9800000 { compatible = "zte,zx296702-topcrm-clk"; reg = <0x09800000 0x1000>; #clock-cells = <1>; }; - lsp1clk: lsp1clk@0x09400000 { + lsp1clk: lsp1clk@9400000 { compatible = "zte,zx296702-lsp1crpm-clk"; reg = <0x09400000 0x1000>; #clock-cells = <1>; }; - lsp0clk: lsp0clk@0x0b000000 { + lsp0clk: lsp0clk@b000000 { compatible = "zte,zx296702-lsp0crpm-clk"; reg = <0x0b000000 0x1000>; #clock-cells = <1>; }; - uart0: serial@0x09405000 { + uart0: serial@9405000 { compatible = "zte,zx296702-uart"; reg = <0x09405000 0x1000>; interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; @@ -98,7 +98,7 @@ status = "disabled"; }; - uart1: serial@0x09406000 { + uart1: serial@9406000 { compatible = "zte,zx296702-uart"; reg = <0x09406000 0x1000>; interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; @@ -106,7 +106,7 @@ status = "disabled"; }; - mmc0: mmc@0x09408000 { + mmc0: mmc@9408000 { compatible = "snps,dw-mshc"; #address-cells = <1>; #size-cells = <0>; @@ -119,7 +119,7 @@ status = "disabled"; }; - mmc1: mmc@0x0b003000 { + mmc1: mmc@b003000 { compatible = "snps,dw-mshc"; #address-cells = <1>; #size-cells = <0>; @@ -132,7 +132,7 @@ status = "disabled"; }; - sysctrl: sysctrl@0xa0007000 { + sysctrl: sysctrl@a0007000 { compatible = "zte,sysctrl", "syscon"; reg = <0xa0007000 0x1000>; }; diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 2f145c4af93a..92674f247a12 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -319,7 +319,7 @@ CONFIG_MEDIA_CAMERA_SUPPORT=y CONFIG_RC_CORE=m CONFIG_MEDIA_CONTROLLER=y CONFIG_VIDEO_V4L2_SUBDEV_API=y -CONFIG_LIRC=m +CONFIG_LIRC=y CONFIG_RC_DEVICES=y CONFIG_IR_RX51=m CONFIG_V4L_PLATFORM_DRIVERS=y diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile index 5638ce0c9524..63d6b404d88e 100644 --- a/arch/arm/kvm/hyp/Makefile +++ b/arch/arm/kvm/hyp/Makefile @@ -7,6 +7,8 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING KVM=../../../../virt/kvm +CFLAGS_ARMV7VE :=$(call cc-option, -march=armv7ve) + obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o @@ -15,7 +17,10 @@ obj-$(CONFIG_KVM_ARM_HOST) += tlb.o obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o obj-$(CONFIG_KVM_ARM_HOST) += vfp.o obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o +CFLAGS_banked-sr.o += $(CFLAGS_ARMV7VE) + obj-$(CONFIG_KVM_ARM_HOST) += entry.o obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o obj-$(CONFIG_KVM_ARM_HOST) += switch.o +CFLAGS_switch.o += $(CFLAGS_ARMV7VE) obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c index 111bda8cdebd..be4b8b0a40ad 100644 --- a/arch/arm/kvm/hyp/banked-sr.c +++ b/arch/arm/kvm/hyp/banked-sr.c @@ -20,6 +20,10 @@ #include <asm/kvm_hyp.h> +/* + * gcc before 4.9 doesn't understand -march=armv7ve, so we have to + * trick the assembler. + */ __asm__(".arch_extension virt"); void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt) diff --git a/arch/arm/mach-clps711x/board-dt.c b/arch/arm/mach-clps711x/board-dt.c index ee1f83b1a332..4c89a8e9a2e3 100644 --- a/arch/arm/mach-clps711x/board-dt.c +++ b/arch/arm/mach-clps711x/board-dt.c @@ -69,7 +69,7 @@ static void clps711x_restart(enum reboot_mode mode, const char *cmd) soft_restart(0); } -static const char *clps711x_compat[] __initconst = { +static const char *const clps711x_compat[] __initconst = { "cirrus,ep7209", NULL }; diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c index e457f299cd44..d6b11907380c 100644 --- a/arch/arm/mach-davinci/board-dm355-evm.c +++ b/arch/arm/mach-davinci/board-dm355-evm.c @@ -368,7 +368,7 @@ static struct spi_eeprom at25640a = { .flags = EE_ADDR2, }; -static struct spi_board_info dm355_evm_spi_info[] __initconst = { +static const struct spi_board_info dm355_evm_spi_info[] __initconst = { { .modalias = "at25", .platform_data = &at25640a, diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c index be997243447b..fad9a5611a5d 100644 --- a/arch/arm/mach-davinci/board-dm355-leopard.c +++ b/arch/arm/mach-davinci/board-dm355-leopard.c @@ -217,7 +217,7 @@ static struct spi_eeprom at25640a = { .flags = EE_ADDR2, }; -static struct spi_board_info dm355_leopard_spi_info[] __initconst = { +static const struct spi_board_info dm355_leopard_spi_info[] __initconst = { { .modalias = "at25", .platform_data = &at25640a, diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c index e75741fb2c1d..e3780986d2a3 100644 --- a/arch/arm/mach-davinci/board-dm365-evm.c +++ b/arch/arm/mach-davinci/board-dm365-evm.c @@ -726,7 +726,7 @@ static struct spi_eeprom at25640 = { .flags = EE_ADDR2, }; -static struct spi_board_info dm365_evm_spi_info[] __initconst = { +static const struct spi_board_info dm365_evm_spi_info[] __initconst = { { .modalias = "at25", .platform_data = &at25640, diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig index 6b32dc527edc..2c20599cc350 100644 --- a/arch/arm/mach-mvebu/Kconfig +++ b/arch/arm/mach-mvebu/Kconfig @@ -41,7 +41,7 @@ config MACH_ARMADA_375 depends on ARCH_MULTI_V7 select ARMADA_370_XP_IRQ select ARM_ERRATA_720789 - select ARM_ERRATA_753970 + select PL310_ERRATA_753970 select ARM_GIC select ARMADA_375_CLK select HAVE_ARM_SCU @@ -57,7 +57,7 @@ config MACH_ARMADA_38X bool "Marvell Armada 380/385 boards" depends on ARCH_MULTI_V7 select ARM_ERRATA_720789 - select ARM_ERRATA_753970 + select PL310_ERRATA_753970 select ARM_GIC select ARM_GLOBAL_TIMER select CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c index 43e3e188f521..fa512413a471 100644 --- a/arch/arm/mach-omap1/clock.c +++ b/arch/arm/mach-omap1/clock.c @@ -1011,17 +1011,17 @@ static int clk_debugfs_register_one(struct clk *c) return -ENOMEM; c->dent = d; - d = debugfs_create_u8("usecount", S_IRUGO, c->dent, (u8 *)&c->usecount); + d = debugfs_create_u8("usecount", S_IRUGO, c->dent, &c->usecount); if (!d) { err = -ENOMEM; goto err_out; } - d = debugfs_create_u32("rate", S_IRUGO, c->dent, (u32 *)&c->rate); + d = debugfs_create_ulong("rate", S_IRUGO, c->dent, &c->rate); if (!d) { err = -ENOMEM; goto err_out; } - d = debugfs_create_x32("flags", S_IRUGO, c->dent, (u32 *)&c->flags); + d = debugfs_create_x8("flags", S_IRUGO, c->dent, &c->flags); if (!d) { err = -ENOMEM; goto err_out; diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index 4bb6751864a5..fc5fb776a710 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -299,8 +299,6 @@ static void irq_save_context(void) if (soc_is_dra7xx()) return; - if (!sar_base) - sar_base = omap4_get_sar_ram_base(); if (wakeupgen_ops && wakeupgen_ops->save_context) wakeupgen_ops->save_context(); } @@ -598,6 +596,8 @@ static int __init wakeupgen_init(struct device_node *node, irq_hotplug_init(); irq_pm_init(); + sar_base = omap4_get_sar_ram_base(); + return 0; } IRQCHIP_DECLARE(ti_wakeupgen, "ti,omap4-wugen-mpu", wakeupgen_init); diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 124f9af34a15..34156eca8e23 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -977,6 +977,9 @@ static int _enable_clocks(struct omap_hwmod *oh) pr_debug("omap_hwmod: %s: enabling clocks\n", oh->name); + if (oh->flags & HWMOD_OPT_CLKS_NEEDED) + _enable_optional_clocks(oh); + if (oh->_clk) clk_enable(oh->_clk); @@ -985,9 +988,6 @@ static int _enable_clocks(struct omap_hwmod *oh) clk_enable(os->_clk); } - if (oh->flags & HWMOD_OPT_CLKS_NEEDED) - _enable_optional_clocks(oh); - /* The opt clocks are controlled by the device driver. */ return 0; diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c index 366158a54fcd..6f68576e5695 100644 --- a/arch/arm/mach-omap2/pm.c +++ b/arch/arm/mach-omap2/pm.c @@ -186,7 +186,7 @@ static void omap_pm_end(void) cpu_idle_poll_ctrl(false); } -static void omap_pm_finish(void) +static void omap_pm_wake(void) { if (soc_is_omap34xx()) omap_prcm_irq_complete(); @@ -196,7 +196,7 @@ static const struct platform_suspend_ops omap_pm_ops = { .begin = omap_pm_begin, .end = omap_pm_end, .enter = omap_pm_enter, - .finish = omap_pm_finish, + .wake = omap_pm_wake, .valid = suspend_valid_only_mem, }; diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index ece09c9461f7..d61fbd7a2840 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -156,12 +156,6 @@ static struct clock_event_device clockevent_gpt = { .tick_resume = omap2_gp_timer_shutdown, }; -static struct property device_disabled = { - .name = "status", - .length = sizeof("disabled"), - .value = "disabled", -}; - static const struct of_device_id omap_timer_match[] __initconst = { { .compatible = "ti,omap2420-timer", }, { .compatible = "ti,omap3430-timer", }, @@ -203,8 +197,17 @@ static struct device_node * __init omap_get_timer_dt(const struct of_device_id * of_get_property(np, "ti,timer-secure", NULL))) continue; - if (!of_device_is_compatible(np, "ti,omap-counter32k")) - of_add_property(np, &device_disabled); + if (!of_device_is_compatible(np, "ti,omap-counter32k")) { + struct property *prop; + + prop = kzalloc(sizeof(*prop), GFP_KERNEL); + if (!prop) + return NULL; + prop->name = "status"; + prop->value = "disabled"; + prop->length = strlen(prop->value); + of_add_property(np, prop); + } return np; } diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index aff6994950ba..a2399fd66e97 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -472,28 +472,27 @@ void __init orion_ge11_init(struct mv643xx_eth_platform_data *eth_data, /***************************************************************************** * Ethernet switch ****************************************************************************/ -static __initconst const char *orion_ge00_mvmdio_bus_name = "orion-mii"; -static __initdata struct mdio_board_info - orion_ge00_switch_board_info; +static __initdata struct mdio_board_info orion_ge00_switch_board_info = { + .bus_id = "orion-mii", + .modalias = "mv88e6085", +}; void __init orion_ge00_switch_init(struct dsa_chip_data *d) { - struct mdio_board_info *bd; unsigned int i; if (!IS_BUILTIN(CONFIG_PHYLIB)) return; - for (i = 0; i < ARRAY_SIZE(d->port_names); i++) - if (!strcmp(d->port_names[i], "cpu")) + for (i = 0; i < ARRAY_SIZE(d->port_names); i++) { + if (!strcmp(d->port_names[i], "cpu")) { + d->netdev[i] = &orion_ge00.dev; break; + } + } - bd = &orion_ge00_switch_board_info; - bd->bus_id = orion_ge00_mvmdio_bus_name; - bd->mdio_addr = d->sw_addr; - d->netdev[i] = &orion_ge00.dev; - strcpy(bd->modalias, "mv88e6085"); - bd->platform_data = d; + orion_ge00_switch_board_info.mdio_addr = d->sw_addr; + orion_ge00_switch_board_info.platform_data = d; mdiobus_register_board_info(&orion_ge00_switch_board_info, 1); } diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index a80632641b39..70c776ef7aa7 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -165,14 +165,14 @@ uart_A: serial@24000 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart"; - reg = <0x0 0x24000 0x0 0x14>; + reg = <0x0 0x24000 0x0 0x18>; interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; uart_B: serial@23000 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart"; - reg = <0x0 0x23000 0x0 0x14>; + reg = <0x0 0x23000 0x0 0x18>; interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 6cb3c2a52baf..4ee2e7951482 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -235,14 +235,14 @@ uart_A: serial@84c0 { compatible = "amlogic,meson-gx-uart"; - reg = <0x0 0x84c0 0x0 0x14>; + reg = <0x0 0x84c0 0x0 0x18>; interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; uart_B: serial@84dc { compatible = "amlogic,meson-gx-uart"; - reg = <0x0 0x84dc 0x0 0x14>; + reg = <0x0 0x84dc 0x0 0x18>; interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; @@ -287,7 +287,7 @@ uart_C: serial@8700 { compatible = "amlogic,meson-gx-uart"; - reg = <0x0 0x8700 0x0 0x14>; + reg = <0x0 0x8700 0x0 0x18>; interrupts = <GIC_SPI 93 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; @@ -404,14 +404,14 @@ uart_AO: serial@4c0 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart"; - reg = <0x0 0x004c0 0x0 0x14>; + reg = <0x0 0x004c0 0x0 0x18>; interrupts = <GIC_SPI 193 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; uart_AO_B: serial@4e0 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart"; - reg = <0x0 0x004e0 0x0 0x14>; + reg = <0x0 0x004e0 0x0 0x18>; interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 4f355f17eed6..c8514110b9da 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -631,6 +631,7 @@ internal_phy: ethernet-phy@8 { compatible = "ethernet-phy-id0181.4400", "ethernet-phy-ieee802.3-c22"; + interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>; reg = <8>; max-speed = <100>; }; diff --git a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi index 4220fbdcb24a..ff5c4c47b22b 100644 --- a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi +++ b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi @@ -98,7 +98,7 @@ clock-output-names = "clk125mhz"; }; - pci { + pcie@30000000 { compatible = "pci-host-ecam-generic"; device_type = "pci"; #interrupt-cells = <1>; @@ -118,6 +118,7 @@ ranges = <0x02000000 0 0x40000000 0 0x40000000 0 0x20000000 0x43000000 0x40 0x00000000 0x40 0x00000000 0x20 0x00000000>; + bus-range = <0 0xff>; interrupt-map-mask = <0 0 0 7>; interrupt-map = /* addr pin ic icaddr icintr */ diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts index e94fa1a53192..047641fe294c 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts +++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts @@ -51,7 +51,7 @@ #size-cells = <2>; ranges; - ramoops@0x21f00000 { + ramoops@21f00000 { compatible = "ramoops"; reg = <0x0 0x21f00000 0x0 0x00100000>; record-size = <0x00020000>; diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi index 9fbe4705ee88..94597e33c806 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -341,7 +341,7 @@ reg = <0 0x10005000 0 0x1000>; }; - pio: pinctrl@0x10005000 { + pio: pinctrl@10005000 { compatible = "mediatek,mt8173-pinctrl"; reg = <0 0x1000b000 0 0x1000>; mediatek,pctl-regmap = <&syscfg_pctl_a>; diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi index 492a011f14f6..1c8f1b86472d 100644 --- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi +++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi @@ -140,16 +140,16 @@ }; agnoc@0 { - qcom,pcie@00600000 { + qcom,pcie@600000 { perst-gpio = <&msmgpio 35 GPIO_ACTIVE_LOW>; }; - qcom,pcie@00608000 { + qcom,pcie@608000 { status = "okay"; perst-gpio = <&msmgpio 130 GPIO_ACTIVE_LOW>; }; - qcom,pcie@00610000 { + qcom,pcie@610000 { status = "okay"; perst-gpio = <&msmgpio 114 GPIO_ACTIVE_LOW>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 4b2afcc4fdf4..0a6f7952bbb1 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -840,7 +840,7 @@ #size-cells = <1>; ranges; - pcie0: qcom,pcie@00600000 { + pcie0: qcom,pcie@600000 { compatible = "qcom,pcie-msm8996", "snps,dw-pcie"; status = "disabled"; power-domains = <&gcc PCIE0_GDSC>; @@ -893,7 +893,7 @@ }; - pcie1: qcom,pcie@00608000 { + pcie1: qcom,pcie@608000 { compatible = "qcom,pcie-msm8996", "snps,dw-pcie"; power-domains = <&gcc PCIE1_GDSC>; bus-range = <0x00 0xff>; @@ -946,7 +946,7 @@ "bus_slave"; }; - pcie2: qcom,pcie@00610000 { + pcie2: qcom,pcie@610000 { compatible = "qcom,pcie-msm8996", "snps,dw-pcie"; power-domains = <&gcc PCIE2_GDSC>; bus-range = <0x00 0xff>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index 3890468678ce..28257724a56e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -132,17 +132,16 @@ assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>; assigned-clock-parents = <&gmac_clkin>, <&gmac_clkin>; clock_in_out = "input"; - /* shows instability at 1GBit right now */ - max-speed = <100>; phy-supply = <&vcc_io>; phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&rgmiim1_pins>; + snps,force_thresh_dma_mode; snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; - tx_delay = <0x26>; - rx_delay = <0x11>; + tx_delay = <0x24>; + rx_delay = <0x18>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index a037ee56fead..cae341554486 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -730,7 +730,7 @@ interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>, <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; status = "disabled"; }; @@ -741,7 +741,7 @@ interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; status = "disabled"; }; @@ -752,7 +752,7 @@ interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index aa4d07046a7b..03458ac44201 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -257,7 +257,7 @@ max-frequency = <150000000>; clocks = <&cru HCLK_SDIO0>, <&cru SCLK_SDIO0>, <&cru SCLK_SDIO0_DRV>, <&cru SCLK_SDIO0_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>; resets = <&cru SRST_SDIO0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi index 0f873c897d0d..ce592a4c0c4c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi @@ -457,7 +457,7 @@ assigned-clocks = <&cru SCLK_PCIEPHY_REF>; assigned-clock-parents = <&cru SCLK_PCIEPHY_REF100M>; assigned-clock-rates = <100000000>; - ep-gpios = <&gpio3 RK_PB5 GPIO_ACTIVE_HIGH>; + ep-gpios = <&gpio2 RK_PA4 GPIO_ACTIVE_HIGH>; num-lanes = <4>; pinctrl-names = "default"; pinctrl-0 = <&pcie_clkreqn_cpm>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 7aa2144e0d47..2605118d4b4c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1739,8 +1739,8 @@ compatible = "rockchip,rk3399-edp"; reg = <0x0 0xff970000 0x0 0x8000>; interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH 0>; - clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>; - clock-names = "dp", "pclk"; + clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>, <&cru PCLK_VIO_GRF>; + clock-names = "dp", "pclk", "grf"; pinctrl-names = "default"; pinctrl-0 = <&edp_hpd>; power-domains = <&power RK3399_PD_EDP>; diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index c0319cbf1eec..5510366d169a 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -34,9 +34,9 @@ #define wmb() RISCV_FENCE(ow,ow) /* These barriers do not need to enforce ordering on devices, just memory. */ -#define smp_mb() RISCV_FENCE(rw,rw) -#define smp_rmb() RISCV_FENCE(r,r) -#define smp_wmb() RISCV_FENCE(w,w) +#define __smp_mb() RISCV_FENCE(rw,rw) +#define __smp_rmb() RISCV_FENCE(r,r) +#define __smp_wmb() RISCV_FENCE(w,w) /* * This is a very specific barrier: it's currently only used in two places in diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 9c7d70715862..07c6e81163bf 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -22,22 +22,6 @@ #include "trace.h" #include "trace-s390.h" - -static const intercept_handler_t instruction_handlers[256] = { - [0x01] = kvm_s390_handle_01, - [0x82] = kvm_s390_handle_lpsw, - [0x83] = kvm_s390_handle_diag, - [0xaa] = kvm_s390_handle_aa, - [0xae] = kvm_s390_handle_sigp, - [0xb2] = kvm_s390_handle_b2, - [0xb6] = kvm_s390_handle_stctl, - [0xb7] = kvm_s390_handle_lctl, - [0xb9] = kvm_s390_handle_b9, - [0xe3] = kvm_s390_handle_e3, - [0xe5] = kvm_s390_handle_e5, - [0xeb] = kvm_s390_handle_eb, -}; - u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu) { struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block; @@ -129,16 +113,39 @@ static int handle_validity(struct kvm_vcpu *vcpu) static int handle_instruction(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - vcpu->stat.exit_instruction++; trace_kvm_s390_intercept_instruction(vcpu, vcpu->arch.sie_block->ipa, vcpu->arch.sie_block->ipb); - handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; + + switch (vcpu->arch.sie_block->ipa >> 8) { + case 0x01: + return kvm_s390_handle_01(vcpu); + case 0x82: + return kvm_s390_handle_lpsw(vcpu); + case 0x83: + return kvm_s390_handle_diag(vcpu); + case 0xaa: + return kvm_s390_handle_aa(vcpu); + case 0xae: + return kvm_s390_handle_sigp(vcpu); + case 0xb2: + return kvm_s390_handle_b2(vcpu); + case 0xb6: + return kvm_s390_handle_stctl(vcpu); + case 0xb7: + return kvm_s390_handle_lctl(vcpu); + case 0xb9: + return kvm_s390_handle_b9(vcpu); + case 0xe3: + return kvm_s390_handle_e3(vcpu); + case 0xe5: + return kvm_s390_handle_e5(vcpu); + case 0xeb: + return kvm_s390_handle_eb(vcpu); + default: + return -EOPNOTSUPP; + } } static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index aabf46f5f883..b04616b57a94 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -169,8 +169,15 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu) static int ckc_irq_pending(struct kvm_vcpu *vcpu) { - if (vcpu->arch.sie_block->ckc >= kvm_s390_get_tod_clock_fast(vcpu->kvm)) + const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm); + const u64 ckc = vcpu->arch.sie_block->ckc; + + if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) { + if ((s64)ckc >= (s64)now) + return 0; + } else if (ckc >= now) { return 0; + } return ckc_interrupts_enabled(vcpu); } @@ -187,12 +194,6 @@ static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu) return kvm_s390_get_cpu_timer(vcpu) >> 63; } -static inline int is_ioirq(unsigned long irq_type) -{ - return ((irq_type >= IRQ_PEND_IO_ISC_7) && - (irq_type <= IRQ_PEND_IO_ISC_0)); -} - static uint64_t isc_to_isc_bits(int isc) { return (0x80 >> isc) << 24; @@ -236,10 +237,15 @@ static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gis return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); } -static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) +static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.float_int.pending_irqs | - vcpu->arch.local_int.pending_irqs | + vcpu->arch.local_int.pending_irqs; +} + +static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) +{ + return pending_irqs_no_gisa(vcpu) | kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7; } @@ -337,7 +343,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) { - if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK)) + if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_IO_MASK)) return; else if (psw_ioint_disabled(vcpu)) kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT); @@ -1011,24 +1017,6 @@ out: return rc; } -typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu); - -static const deliver_irq_t deliver_irq_funcs[] = { - [IRQ_PEND_MCHK_EX] = __deliver_machine_check, - [IRQ_PEND_MCHK_REP] = __deliver_machine_check, - [IRQ_PEND_PROG] = __deliver_prog, - [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal, - [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call, - [IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc, - [IRQ_PEND_EXT_CPU_TIMER] = __deliver_cpu_timer, - [IRQ_PEND_RESTART] = __deliver_restart, - [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix, - [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init, - [IRQ_PEND_EXT_SERVICE] = __deliver_service, - [IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done, - [IRQ_PEND_VIRTIO] = __deliver_virtio, -}; - /* Check whether an external call is pending (deliverable or not) */ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) { @@ -1066,13 +1054,19 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) static u64 __calculate_sltime(struct kvm_vcpu *vcpu) { - u64 now, cputm, sltime = 0; + const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm); + const u64 ckc = vcpu->arch.sie_block->ckc; + u64 cputm, sltime = 0; if (ckc_interrupts_enabled(vcpu)) { - now = kvm_s390_get_tod_clock_fast(vcpu->kvm); - sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now); - /* already expired or overflow? */ - if (!sltime || vcpu->arch.sie_block->ckc <= now) + if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) { + if ((s64)now < (s64)ckc) + sltime = tod_to_ns((s64)ckc - (s64)now); + } else if (now < ckc) { + sltime = tod_to_ns(ckc - now); + } + /* already expired */ + if (!sltime) return 0; if (cpu_timer_interrupts_enabled(vcpu)) { cputm = kvm_s390_get_cpu_timer(vcpu); @@ -1192,7 +1186,6 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu) int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - deliver_irq_t func; int rc = 0; unsigned long irq_type; unsigned long irqs; @@ -1212,16 +1205,57 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) while ((irqs = deliverable_irqs(vcpu)) && !rc) { /* bits are in the reverse order of interrupt priority */ irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT); - if (is_ioirq(irq_type)) { + switch (irq_type) { + case IRQ_PEND_IO_ISC_0: + case IRQ_PEND_IO_ISC_1: + case IRQ_PEND_IO_ISC_2: + case IRQ_PEND_IO_ISC_3: + case IRQ_PEND_IO_ISC_4: + case IRQ_PEND_IO_ISC_5: + case IRQ_PEND_IO_ISC_6: + case IRQ_PEND_IO_ISC_7: rc = __deliver_io(vcpu, irq_type); - } else { - func = deliver_irq_funcs[irq_type]; - if (!func) { - WARN_ON_ONCE(func == NULL); - clear_bit(irq_type, &li->pending_irqs); - continue; - } - rc = func(vcpu); + break; + case IRQ_PEND_MCHK_EX: + case IRQ_PEND_MCHK_REP: + rc = __deliver_machine_check(vcpu); + break; + case IRQ_PEND_PROG: + rc = __deliver_prog(vcpu); + break; + case IRQ_PEND_EXT_EMERGENCY: + rc = __deliver_emergency_signal(vcpu); + break; + case IRQ_PEND_EXT_EXTERNAL: + rc = __deliver_external_call(vcpu); + break; + case IRQ_PEND_EXT_CLOCK_COMP: + rc = __deliver_ckc(vcpu); + break; + case IRQ_PEND_EXT_CPU_TIMER: + rc = __deliver_cpu_timer(vcpu); + break; + case IRQ_PEND_RESTART: + rc = __deliver_restart(vcpu); + break; + case IRQ_PEND_SET_PREFIX: + rc = __deliver_set_prefix(vcpu); + break; + case IRQ_PEND_PFAULT_INIT: + rc = __deliver_pfault_init(vcpu); + break; + case IRQ_PEND_EXT_SERVICE: + rc = __deliver_service(vcpu); + break; + case IRQ_PEND_PFAULT_DONE: + rc = __deliver_pfault_done(vcpu); + break; + case IRQ_PEND_VIRTIO: + rc = __deliver_virtio(vcpu); + break; + default: + WARN_ONCE(1, "Unknown pending irq type %ld", irq_type); + clear_bit(irq_type, &li->pending_irqs); } } @@ -1701,7 +1735,8 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT); break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); + if (!(type & KVM_S390_INT_IO_AI_MASK && kvm->arch.gisa)) + kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); break; default: kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_EXT_INT); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ba4c7092335a..77d7818130db 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -179,6 +179,28 @@ int kvm_arch_hardware_enable(void) static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); +static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta) +{ + u8 delta_idx = 0; + + /* + * The TOD jumps by delta, we have to compensate this by adding + * -delta to the epoch. + */ + delta = -delta; + + /* sign-extension - we're adding to signed values below */ + if ((s64)delta < 0) + delta_idx = -1; + + scb->epoch += delta; + if (scb->ecd & ECD_MEF) { + scb->epdx += delta_idx; + if (scb->epoch < delta) + scb->epdx += 1; + } +} + /* * This callback is executed during stop_machine(). All CPUs are therefore * temporarily stopped. In order not to change guest behavior, we have to @@ -194,13 +216,17 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val, unsigned long long *delta = v; list_for_each_entry(kvm, &vm_list, vm_list) { - kvm->arch.epoch -= *delta; kvm_for_each_vcpu(i, vcpu, kvm) { - vcpu->arch.sie_block->epoch -= *delta; + kvm_clock_sync_scb(vcpu->arch.sie_block, *delta); + if (i == 0) { + kvm->arch.epoch = vcpu->arch.sie_block->epoch; + kvm->arch.epdx = vcpu->arch.sie_block->epdx; + } if (vcpu->arch.cputm_enabled) vcpu->arch.cputm_start += *delta; if (vcpu->arch.vsie_block) - vcpu->arch.vsie_block->epoch -= *delta; + kvm_clock_sync_scb(vcpu->arch.vsie_block, + *delta); } } return NOTIFY_OK; @@ -902,12 +928,9 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) if (copy_from_user(>od, (void __user *)attr->addr, sizeof(gtod))) return -EFAULT; - if (test_kvm_facility(kvm, 139)) - kvm_s390_set_tod_clock_ext(kvm, >od); - else if (gtod.epoch_idx == 0) - kvm_s390_set_tod_clock(kvm, gtod.tod); - else + if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx) return -EINVAL; + kvm_s390_set_tod_clock(kvm, >od); VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx", gtod.epoch_idx, gtod.tod); @@ -932,13 +955,14 @@ static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr) static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) { - u64 gtod; + struct kvm_s390_vm_tod_clock gtod = { 0 }; - if (copy_from_user(>od, (void __user *)attr->addr, sizeof(gtod))) + if (copy_from_user(>od.tod, (void __user *)attr->addr, + sizeof(gtod.tod))) return -EFAULT; - kvm_s390_set_tod_clock(kvm, gtod); - VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod); + kvm_s390_set_tod_clock(kvm, >od); + VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod); return 0; } @@ -2389,6 +2413,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) mutex_lock(&vcpu->kvm->lock); preempt_disable(); vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch; + vcpu->arch.sie_block->epdx = vcpu->kvm->arch.epdx; preempt_enable(); mutex_unlock(&vcpu->kvm->lock); if (!kvm_is_ucontrol(vcpu->kvm)) { @@ -3021,8 +3046,8 @@ retry: return 0; } -void kvm_s390_set_tod_clock_ext(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod) +void kvm_s390_set_tod_clock(struct kvm *kvm, + const struct kvm_s390_vm_tod_clock *gtod) { struct kvm_vcpu *vcpu; struct kvm_s390_tod_clock_ext htod; @@ -3034,10 +3059,12 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm, get_tod_clock_ext((char *)&htod); kvm->arch.epoch = gtod->tod - htod.tod; - kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx; - - if (kvm->arch.epoch > gtod->tod) - kvm->arch.epdx -= 1; + kvm->arch.epdx = 0; + if (test_kvm_facility(kvm, 139)) { + kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx; + if (kvm->arch.epoch > gtod->tod) + kvm->arch.epdx -= 1; + } kvm_s390_vcpu_block_all(kvm); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -3050,22 +3077,6 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm, mutex_unlock(&kvm->lock); } -void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod) -{ - struct kvm_vcpu *vcpu; - int i; - - mutex_lock(&kvm->lock); - preempt_disable(); - kvm->arch.epoch = tod - get_tod_clock(); - kvm_s390_vcpu_block_all(kvm); - kvm_for_each_vcpu(i, vcpu, kvm) - vcpu->arch.sie_block->epoch = kvm->arch.epoch; - kvm_s390_vcpu_unblock_all(kvm); - preempt_enable(); - mutex_unlock(&kvm->lock); -} - /** * kvm_arch_fault_in_page - fault-in guest page if necessary * @vcpu: The corresponding virtual cpu diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index bd31b37b0e6f..f55ac0ef99ea 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -19,8 +19,6 @@ #include <asm/processor.h> #include <asm/sclp.h> -typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); - /* Transactional Memory Execution related macros */ #define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & ECB_TE)) #define TDB_FORMAT1 1 @@ -283,9 +281,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ -void kvm_s390_set_tod_clock_ext(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod); -void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod); +void kvm_s390_set_tod_clock(struct kvm *kvm, + const struct kvm_s390_vm_tod_clock *gtod); long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index c4c4e157c036..f0b4185158af 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -85,9 +85,10 @@ int kvm_s390_handle_e3(struct kvm_vcpu *vcpu) /* Handle SCK (SET CLOCK) interception */ static int handle_set_clock(struct kvm_vcpu *vcpu) { + struct kvm_s390_vm_tod_clock gtod = { 0 }; int rc; u8 ar; - u64 op2, val; + u64 op2; vcpu->stat.instruction_sck++; @@ -97,12 +98,12 @@ static int handle_set_clock(struct kvm_vcpu *vcpu) op2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (op2 & 7) /* Operand must be on a doubleword boundary */ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, op2, ar, &val, sizeof(val)); + rc = read_guest(vcpu, op2, ar, >od.tod, sizeof(gtod.tod)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); - VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", val); - kvm_s390_set_tod_clock(vcpu->kvm, val); + VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod); + kvm_s390_set_tod_clock(vcpu->kvm, >od); kvm_s390_set_psw_cc(vcpu, 0); return 0; @@ -795,55 +796,60 @@ out: return rc; } -static const intercept_handler_t b2_handlers[256] = { - [0x02] = handle_stidp, - [0x04] = handle_set_clock, - [0x10] = handle_set_prefix, - [0x11] = handle_store_prefix, - [0x12] = handle_store_cpu_address, - [0x14] = kvm_s390_handle_vsie, - [0x21] = handle_ipte_interlock, - [0x29] = handle_iske, - [0x2a] = handle_rrbe, - [0x2b] = handle_sske, - [0x2c] = handle_test_block, - [0x30] = handle_io_inst, - [0x31] = handle_io_inst, - [0x32] = handle_io_inst, - [0x33] = handle_io_inst, - [0x34] = handle_io_inst, - [0x35] = handle_io_inst, - [0x36] = handle_io_inst, - [0x37] = handle_io_inst, - [0x38] = handle_io_inst, - [0x39] = handle_io_inst, - [0x3a] = handle_io_inst, - [0x3b] = handle_io_inst, - [0x3c] = handle_io_inst, - [0x50] = handle_ipte_interlock, - [0x56] = handle_sthyi, - [0x5f] = handle_io_inst, - [0x74] = handle_io_inst, - [0x76] = handle_io_inst, - [0x7d] = handle_stsi, - [0xb1] = handle_stfl, - [0xb2] = handle_lpswe, -}; - int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - /* - * A lot of B2 instructions are priviledged. Here we check for - * the privileged ones, that we can handle in the kernel. - * Anything else goes to userspace. - */ - handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) - return handler(vcpu); - - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x02: + return handle_stidp(vcpu); + case 0x04: + return handle_set_clock(vcpu); + case 0x10: + return handle_set_prefix(vcpu); + case 0x11: + return handle_store_prefix(vcpu); + case 0x12: + return handle_store_cpu_address(vcpu); + case 0x14: + return kvm_s390_handle_vsie(vcpu); + case 0x21: + case 0x50: + return handle_ipte_interlock(vcpu); + case 0x29: + return handle_iske(vcpu); + case 0x2a: + return handle_rrbe(vcpu); + case 0x2b: + return handle_sske(vcpu); + case 0x2c: + return handle_test_block(vcpu); + case 0x30: + case 0x31: + case 0x32: + case 0x33: + case 0x34: + case 0x35: + case 0x36: + case 0x37: + case 0x38: + case 0x39: + case 0x3a: + case 0x3b: + case 0x3c: + case 0x5f: + case 0x74: + case 0x76: + return handle_io_inst(vcpu); + case 0x56: + return handle_sthyi(vcpu); + case 0x7d: + return handle_stsi(vcpu); + case 0xb1: + return handle_stfl(vcpu); + case 0xb2: + return handle_lpswe(vcpu); + default: + return -EOPNOTSUPP; + } } static int handle_epsw(struct kvm_vcpu *vcpu) @@ -1105,25 +1111,22 @@ static int handle_essa(struct kvm_vcpu *vcpu) return 0; } -static const intercept_handler_t b9_handlers[256] = { - [0x8a] = handle_ipte_interlock, - [0x8d] = handle_epsw, - [0x8e] = handle_ipte_interlock, - [0x8f] = handle_ipte_interlock, - [0xab] = handle_essa, - [0xaf] = handle_pfmf, -}; - int kvm_s390_handle_b9(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - /* This is handled just as for the B2 instructions. */ - handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) - return handler(vcpu); - - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x8a: + case 0x8e: + case 0x8f: + return handle_ipte_interlock(vcpu); + case 0x8d: + return handle_epsw(vcpu); + case 0xab: + return handle_essa(vcpu); + case 0xaf: + return handle_pfmf(vcpu); + default: + return -EOPNOTSUPP; + } } int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) @@ -1271,22 +1274,20 @@ static int handle_stctg(struct kvm_vcpu *vcpu) return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } -static const intercept_handler_t eb_handlers[256] = { - [0x2f] = handle_lctlg, - [0x25] = handle_stctg, - [0x60] = handle_ri, - [0x61] = handle_ri, - [0x62] = handle_ri, -}; - int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipb & 0x000000ff) { + case 0x25: + return handle_stctg(vcpu); + case 0x2f: + return handle_lctlg(vcpu); + case 0x60: + case 0x61: + case 0x62: + return handle_ri(vcpu); + default: + return -EOPNOTSUPP; + } } static int handle_tprot(struct kvm_vcpu *vcpu) @@ -1346,10 +1347,12 @@ out_unlock: int kvm_s390_handle_e5(struct kvm_vcpu *vcpu) { - /* For e5xx... instructions we only handle TPROT */ - if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01) + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x01: return handle_tprot(vcpu); - return -EOPNOTSUPP; + default: + return -EOPNOTSUPP; + } } static int handle_sckpf(struct kvm_vcpu *vcpu) @@ -1380,17 +1383,14 @@ static int handle_ptff(struct kvm_vcpu *vcpu) return 0; } -static const intercept_handler_t x01_handlers[256] = { - [0x04] = handle_ptff, - [0x07] = handle_sckpf, -}; - int kvm_s390_handle_01(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - handler = x01_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x04: + return handle_ptff(vcpu); + case 0x07: + return handle_sckpf(vcpu); + default: + return -EOPNOTSUPP; + } } diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index ec772700ff96..8961e3970901 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -821,6 +821,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; + int guest_bp_isolation; int rc; handle_last_fault(vcpu, vsie_page); @@ -831,6 +832,20 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) s390_handle_mcck(); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + + /* save current guest state of bp isolation override */ + guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST); + + /* + * The guest is running with BPBC, so we have to force it on for our + * nested guest. This is done by enabling BPBC globally, so the BPBC + * control in the SCB (which the nested guest can modify) is simply + * ignored. + */ + if (test_kvm_facility(vcpu->kvm, 82) && + vcpu->arch.sie_block->fpf & FPF_BPBC) + set_thread_flag(TIF_ISOLATE_BP_GUEST); + local_irq_disable(); guest_enter_irqoff(); local_irq_enable(); @@ -840,6 +855,11 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) local_irq_disable(); guest_exit_irqoff(); local_irq_enable(); + + /* restore guest state for bp isolation override */ + if (!guest_bp_isolation) + clear_thread_flag(TIF_ISOLATE_BP_GUEST); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); if (rc == -EINTR) { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c1236b187824..eb7f43f23521 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -430,6 +430,7 @@ config GOLDFISH config RETPOLINE bool "Avoid speculative indirect branches in kernel" default y + select STACK_VALIDATION if HAVE_STACK_VALIDATION help Compile kernel with the retpoline compiler options to guard against kernel-to-user data leaks by avoiding speculative indirect diff --git a/arch/x86/Makefile b/arch/x86/Makefile index fad55160dcb9..498c1b812300 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -232,10 +232,9 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_RETPOLINE - RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) - ifneq ($(RETPOLINE_CFLAGS),) - KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE - endif +ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE +endif endif archscripts: scripts_basic diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index dce7092ab24a..be63330c5511 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,7 +97,7 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 /* * Push registers and sanitize registers of values that a * speculation attack might otherwise want to exploit. The @@ -105,32 +105,41 @@ For 32-bit we have the following conventions - kernel is built with * could be put to use in a speculative execution gadget. * Interleave XOR with PUSH for better uop scheduling: */ + .if \save_ret + pushq %rsi /* pt_regs->si */ + movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ + movq %rdi, 8(%rsp) /* pt_regs->di (overwriting original return address) */ + .else pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ + .endif pushq \rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorq %r11, %r11 /* nospec r11*/ + xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12*/ + xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13*/ + xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14*/ + xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15*/ + xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret + pushq %rsi /* return address on top of stack */ + .endif .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 @@ -172,12 +181,7 @@ For 32-bit we have the following conventions - kernel is built with */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 #ifdef CONFIG_FRAME_POINTER - .if \ptregs_offset - leaq \ptregs_offset(%rsp), %rbp - .else - mov %rsp, %rbp - .endif - orq $0x1, %rbp + leaq 1+\ptregs_offset(%rsp), %rbp #endif .endm diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 16c2c022540d..6ad064c8cf35 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -252,8 +252,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %ebx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 8971bd64d515..d5c7f18f79ac 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -364,8 +364,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %rbx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ @@ -449,9 +448,19 @@ END(irq_entries_start) * * The invariant is that, if irq_count != -1, then the IRQ stack is in use. */ -.macro ENTER_IRQ_STACK regs=1 old_rsp +.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0 DEBUG_ENTRY_ASSERT_IRQS_OFF + + .if \save_ret + /* + * If save_ret is set, the original stack contains one additional + * entry -- the return address. Therefore, move the address one + * entry below %rsp to \old_rsp. + */ + leaq 8(%rsp), \old_rsp + .else movq %rsp, \old_rsp + .endif .if \regs UNWIND_HINT_REGS base=\old_rsp @@ -497,6 +506,15 @@ END(irq_entries_start) .if \regs UNWIND_HINT_REGS indirect=1 .endif + + .if \save_ret + /* + * Push the return address to the stack. This return address can + * be found at the "real" original RSP, which was offset by 8 at + * the beginning of this macro. + */ + pushq -8(\old_rsp) + .endif .endm /* @@ -520,27 +538,65 @@ END(irq_entries_start) .endm /* - * Interrupt entry/exit. - * - * Interrupt entry points save only callee clobbered registers in fast path. + * Interrupt entry helper function. * - * Entry runs with interrupts off. + * Entry runs with interrupts off. Stack layout at entry: + * +----------------------------------------------------+ + * | regs->ss | + * | regs->rsp | + * | regs->eflags | + * | regs->cs | + * | regs->ip | + * +----------------------------------------------------+ + * | regs->orig_ax = ~(interrupt number) | + * +----------------------------------------------------+ + * | return address | + * +----------------------------------------------------+ */ - -/* 0(%rsp): ~(interrupt number) */ - .macro interrupt func +ENTRY(interrupt_entry) + UNWIND_HINT_FUNC + ASM_CLAC cld - testb $3, CS-ORIG_RAX(%rsp) + testb $3, CS-ORIG_RAX+8(%rsp) jz 1f SWAPGS - call switch_to_thread_stack + + /* + * Switch to the thread stack. The IRET frame and orig_ax are + * on the stack, as well as the return address. RDI..R12 are + * not (yet) on the stack and space has not (yet) been + * allocated for them. + */ + pushq %rdi + + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + + /* + * We have RDI, return address, and orig_ax on the stack on + * top of the IRET frame. That means offset=24 + */ + UNWIND_HINT_IRET_REGS base=%rdi offset=24 + + pushq 7*8(%rdi) /* regs->ss */ + pushq 6*8(%rdi) /* regs->rsp */ + pushq 5*8(%rdi) /* regs->eflags */ + pushq 4*8(%rdi) /* regs->cs */ + pushq 3*8(%rdi) /* regs->ip */ + pushq 2*8(%rdi) /* regs->orig_ax */ + pushq 8(%rdi) /* return address */ + UNWIND_HINT_FUNC + + movq (%rdi), %rdi 1: - PUSH_AND_CLEAR_REGS - ENCODE_FRAME_POINTER + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 - testb $3, CS(%rsp) + testb $3, CS+8(%rsp) jz 1f /* @@ -548,7 +604,7 @@ END(irq_entries_start) * * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode - * (which can take locks). Since TRACE_IRQS_OFF idempotent, + * (which can take locks). Since TRACE_IRQS_OFF is idempotent, * the simplest way to handle it is to just call it twice if * we enter from user mode. There's no reason to optimize this since * TRACE_IRQS_OFF is a no-op if lockdep is off. @@ -558,12 +614,15 @@ END(irq_entries_start) CALL_enter_from_user_mode 1: - ENTER_IRQ_STACK old_rsp=%rdi + ENTER_IRQ_STACK old_rsp=%rdi save_ret=1 /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF - call \func /* rdi points to pt_regs */ - .endm + ret +END(interrupt_entry) + + +/* Interrupt entry/exit. */ /* * The interrupt stubs push (~vector+0x80) onto the stack and @@ -571,9 +630,10 @@ END(irq_entries_start) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: - ASM_CLAC addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ - interrupt do_IRQ + call interrupt_entry + UNWIND_HINT_REGS indirect=1 + call do_IRQ /* rdi points to pt_regs */ /* 0(%rsp): old RSP */ ret_from_intr: DISABLE_INTERRUPTS(CLBR_ANY) @@ -766,10 +826,11 @@ END(common_interrupt) .macro apicinterrupt3 num sym do_sym ENTRY(\sym) UNWIND_HINT_IRET_REGS - ASM_CLAC pushq $~(\num) .Lcommon_\sym: - interrupt \do_sym + call interrupt_entry + UNWIND_HINT_REGS indirect=1 + call \do_sym /* rdi points to pt_regs */ jmp ret_from_intr END(\sym) .endm @@ -832,34 +893,6 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt */ #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) -/* - * Switch to the thread stack. This is called with the IRET frame and - * orig_ax on the stack. (That is, RDI..R12 are not on the stack and - * space has not been allocated for them.) - */ -ENTRY(switch_to_thread_stack) - UNWIND_HINT_FUNC - - pushq %rdi - /* Need to switch before accessing the thread stack. */ - SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi - movq %rsp, %rdi - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI - - pushq 7*8(%rdi) /* regs->ss */ - pushq 6*8(%rdi) /* regs->rsp */ - pushq 5*8(%rdi) /* regs->eflags */ - pushq 4*8(%rdi) /* regs->cs */ - pushq 3*8(%rdi) /* regs->ip */ - pushq 2*8(%rdi) /* regs->orig_ax */ - pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC - - movq (%rdi), %rdi - ret -END(switch_to_thread_stack) - .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 @@ -875,12 +908,8 @@ ENTRY(\sym) pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif - /* Save all registers in pt_regs */ - PUSH_AND_CLEAR_REGS - ENCODE_FRAME_POINTER - .if \paranoid < 2 - testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ + testb $3, CS-ORIG_RAX(%rsp) /* If coming from userspace, switch stacks */ jnz .Lfrom_usermode_switch_stack_\@ .endif @@ -1130,13 +1159,15 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* - * Switch gs if needed. + * Save all registers in pt_regs, and switch gs if needed. * Use slow, but surefire "are we in kernel?" check. * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx rdmsr @@ -1181,12 +1212,14 @@ ENTRY(paranoid_exit) END(paranoid_exit) /* - * Switch gs if needed. + * Save all registers in pt_regs, and switch GS if needed. * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - UNWIND_HINT_REGS offset=8 + UNWIND_HINT_FUNC cld + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1577,8 +1610,6 @@ end_repeat_nmi: * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ - PUSH_AND_CLEAR_REGS - ENCODE_FRAME_POINTER /* * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index fd65e016e413..e811dd9c5e99 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -85,25 +85,25 @@ ENTRY(entry_SYSENTER_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ - xorq %r11, %r11 /* nospec r11 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ - xorq %r12, %r12 /* nospec r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ - xorq %r13, %r13 /* nospec r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ - xorq %r14, %r14 /* nospec r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ - xorq %r15, %r15 /* nospec r15 */ + xorl %r15d, %r15d /* nospec r15 */ cld /* @@ -224,25 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ - xorq %r11, %r11 /* nospec r11 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ - xorq %r12, %r12 /* nospec r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ - xorq %r13, %r13 /* nospec r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ - xorq %r14, %r14 /* nospec r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ - xorq %r15, %r15 /* nospec r15 */ + xorl %r15d, %r15d /* nospec r15 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -298,9 +298,9 @@ sysret32_from_system_call: */ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9 - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r10 + xorl %r8d, %r8d + xorl %r9d, %r9d + xorl %r10d, %r10d swapgs sysretl END(entry_SYSCALL_compat) @@ -347,10 +347,23 @@ ENTRY(entry_INT80_compat) */ movl %eax, %eax + /* switch to thread stack expects orig_ax and rdi to be pushed */ pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + + pushq 6*8(%rdi) /* regs->ss */ + pushq 5*8(%rdi) /* regs->rsp */ + pushq 4*8(%rdi) /* regs->eflags */ + pushq 3*8(%rdi) /* regs->cs */ + pushq 2*8(%rdi) /* regs->ip */ + pushq 1*8(%rdi) /* regs->orig_ax */ - /* switch to thread stack expects orig_ax to be pushed */ - call switch_to_thread_stack + movq (%rdi), %rdi /* restore %rdi */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ @@ -358,25 +371,25 @@ ENTRY(entry_INT80_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ - xorq %r11, %r11 /* nospec r11 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15 */ + xorl %r15d, %r15d /* nospec r15 */ cld /* diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index 4d4015ddcf26..c356098b6fb9 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -7,6 +7,8 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H +#include <asm/nospec-branch.h> + #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -32,6 +34,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -44,6 +47,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); } static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -56,6 +60,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -68,6 +73,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 4d111616524b..1908214b9125 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -38,7 +38,4 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -asmlinkage void __fill_rsb(void); -asmlinkage void __clear_rsb(void); - #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0dfe4d3f74e2..f41079da38c5 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -213,6 +213,7 @@ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 85f6ccb80b91..a399c1ebf6f0 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -6,6 +6,7 @@ #include <asm/pgtable.h> #include <asm/processor-flags.h> #include <asm/tlb.h> +#include <asm/nospec-branch.h> /* * We map the EFI regions needed for runtime services non-contiguously, @@ -36,8 +37,18 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...); -#define arch_efi_call_virt_setup() kernel_fpu_begin() -#define arch_efi_call_virt_teardown() kernel_fpu_end() +#define arch_efi_call_virt_setup() \ +({ \ + kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ +}) + +#define arch_efi_call_virt_teardown() \ +({ \ + firmware_restrict_branch_speculation_end(); \ + kernel_fpu_end(); \ +}) + /* * Wrap all the virtual calls in a way that forces the parameters on the stack. @@ -73,6 +84,7 @@ struct efi_scratch { efi_sync_low_kernel_mappings(); \ preempt_disable(); \ __kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ \ if (efi_scratch.use_pgd) { \ efi_scratch.prev_cr3 = __read_cr3(); \ @@ -91,6 +103,7 @@ struct efi_scratch { __flush_tlb_all(); \ } \ \ + firmware_restrict_branch_speculation_end(); \ __kernel_fpu_end(); \ preempt_enable(); \ }) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dd6f57a54a26..0a9e330b34f0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1464,7 +1464,4 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define put_smstate(type, buf, offset, val) \ *(type *)((buf) + (offset) - 0x7e00) = val -void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end); - #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 55520cec8b27..7fb1047d61c7 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -37,7 +37,12 @@ struct cpu_signature { struct device; -enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; +enum ucode_state { + UCODE_OK = 0, + UCODE_UPDATED, + UCODE_NFOUND, + UCODE_ERROR, +}; struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, @@ -54,7 +59,7 @@ struct microcode_ops { * are being called. * See also the "Synchronization" section in microcode_core.c. */ - int (*apply_microcode) (int cpu); + enum ucode_state (*apply_microcode) (int cpu); int (*collect_cpu_info) (int cpu, struct cpu_signature *csig); }; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index c931b88982a0..1de72ce514cd 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -74,6 +74,7 @@ static inline void *ldt_slot_va(int slot) return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); #else BUG(); + return (void *)fix_to_virt(FIX_HOLE); #endif } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 81a1be326571..d0dabeae0505 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -8,6 +8,50 @@ #include <asm/cpufeatures.h> #include <asm/msr-index.h> +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. + */ + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +/* + * Google experimented with loop-unrolling and this turned out to be + * the optimal version — two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr, sp) \ + mov $(nr/2), reg; \ +771: \ + call 772f; \ +773: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 775b; \ +774: \ + dec reg; \ + jnz 771b; \ + add $(BITS_PER_LONG/8) * nr, sp; + #ifdef __ASSEMBLY__ /* @@ -24,6 +68,18 @@ .endm /* + * This should be used immediately before an indirect jump/call. It tells + * objtool the subsequent indirect jump/call is vouched safe for retpoline + * builds. + */ +.macro ANNOTATE_RETPOLINE_SAFE + .Lannotate_\@: + .pushsection .discard.retpoline_safe + _ASM_PTR .Lannotate_\@ + .popsection +.endm + +/* * These are the bare retpoline primitives for indirect jmp and call. * Do not use these directly; they only exist to make the ALTERNATIVE * invocation below less ugly. @@ -59,9 +115,9 @@ .macro JMP_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE_2 __stringify(jmp *\reg), \ + ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg), \ __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD #else jmp *\reg #endif @@ -70,18 +126,25 @@ .macro CALL_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE_2 __stringify(call *\reg), \ + ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg), \ __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ - __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD #else call *\reg #endif .endm -/* This clobbers the BX register */ -.macro FILL_RETURN_BUFFER nr:req ftr:req + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req #ifdef CONFIG_RETPOLINE - ALTERNATIVE "", "call __clear_rsb", \ftr + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ + \ftr +.Lskip_rsb_\@: #endif .endm @@ -93,6 +156,12 @@ ".long 999b - .\n\t" \ ".popsection\n\t" +#define ANNOTATE_RETPOLINE_SAFE \ + "999:\n\t" \ + ".pushsection .discard.retpoline_safe\n\t" \ + _ASM_PTR " 999b\n\t" \ + ".popsection\n\t" + #if defined(CONFIG_X86_64) && defined(RETPOLINE) /* @@ -102,6 +171,7 @@ # define CALL_NOSPEC \ ANNOTATE_NOSPEC_ALTERNATIVE \ ALTERNATIVE( \ + ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ "call __x86_indirect_thunk_%V[thunk_target]\n", \ X86_FEATURE_RETPOLINE) @@ -156,26 +226,54 @@ extern char __indirect_thunk_end[]; static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - alternative_input("", - "call __fill_rsb", - X86_FEATURE_RETPOLINE, - ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); + unsigned long loops; + + asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE("jmp 910f", + __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), + X86_FEATURE_RETPOLINE) + "910:" + : "=r" (loops), ASM_CALL_CONSTRAINT + : : "memory" ); #endif } +#define alternative_msr_write(_msr, _val, _feature) \ + asm volatile(ALTERNATIVE("", \ + "movl %[msr], %%ecx\n\t" \ + "movl %[val], %%eax\n\t" \ + "movl $0, %%edx\n\t" \ + "wrmsr", \ + _feature) \ + : : [msr] "i" (_msr), [val] "i" (_val) \ + : "eax", "ecx", "edx", "memory") + static inline void indirect_branch_prediction_barrier(void) { - asm volatile(ALTERNATIVE("", - "movl %[msr], %%ecx\n\t" - "movl %[val], %%eax\n\t" - "movl $0, %%edx\n\t" - "wrmsr", - X86_FEATURE_USE_IBPB) - : : [msr] "i" (MSR_IA32_PRED_CMD), - [val] "i" (PRED_CMD_IBPB) - : "eax", "ecx", "edx", "memory"); + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, + X86_FEATURE_USE_IBPB); } +/* + * With retpoline, we must use IBRS to restrict branch prediction + * before calling into firmware. + * + * (Implemented as CPP macros due to header hell.) + */ +#define firmware_restrict_branch_speculation_start() \ +do { \ + preempt_disable(); \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \ + X86_FEATURE_USE_IBRS_FW); \ +} while (0) + +#define firmware_restrict_branch_speculation_end() \ +do { \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \ + X86_FEATURE_USE_IBRS_FW); \ + preempt_enable(); \ +} while (0) + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 554841fab717..c83a2f418cea 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -7,6 +7,7 @@ #ifdef CONFIG_PARAVIRT #include <asm/pgtable_types.h> #include <asm/asm.h> +#include <asm/nospec-branch.h> #include <asm/paravirt_types.h> @@ -879,23 +880,27 @@ extern void default_banner(void); #define INTERRUPT_RETURN \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret)) + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);) #define DISABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #define ENABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #ifdef CONFIG_X86_32 #define GET_CR0_INTO_EAX \ push %ecx; push %edx; \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx #else /* !CONFIG_X86_32 */ @@ -917,21 +922,25 @@ extern void default_banner(void); */ #define SWAPGS \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ - call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs) \ + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \ ) #define GET_CR2_INTO_RAX \ - call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2) + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2); #define USERGS_SYSRET64 \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);) #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #endif diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index f624f1f10316..180bc0bff0fb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -43,6 +43,7 @@ #include <asm/desc_defs.h> #include <asm/kmap_types.h> #include <asm/pgtable_types.h> +#include <asm/nospec-branch.h> struct page; struct thread_struct; @@ -392,7 +393,9 @@ int paravirt_disable_iospace(void); * offset into the paravirt_patch_template structure, and can therefore be * freely converted back into a structure offset. */ -#define PARAVIRT_CALL "call *%c[paravirt_opptr];" +#define PARAVIRT_CALL \ + ANNOTATE_RETPOLINE_SAFE \ + "call *%c[paravirt_opptr];" /* * These macros are intended to wrap calls through one of the paravirt diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 63c2552b6b65..b444d83cfc95 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -350,14 +350,14 @@ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); - return __pmd(v | set); + return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); - return __pmd(v & ~clear); + return native_make_pmd(v & ~clear); } static inline pmd_t pmd_mkold(pmd_t pmd) @@ -409,14 +409,14 @@ static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); - return __pud(v | set); + return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); - return __pud(v & ~clear); + return native_make_pud(v & ~clear); } static inline pud_t pud_mkold(pud_t pud) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 3696398a9475..246f15b4e64c 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -323,6 +323,11 @@ static inline pudval_t native_pud_val(pud_t pud) #else #include <asm-generic/pgtable-nopud.h> +static inline pud_t native_make_pud(pudval_t val) +{ + return (pud_t) { .p4d.pgd = native_make_pgd(val) }; +} + static inline pudval_t native_pud_val(pud_t pud) { return native_pgd_val(pud.p4d.pgd); @@ -344,6 +349,11 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) #else #include <asm-generic/pgtable-nopmd.h> +static inline pmd_t native_make_pmd(pmdval_t val) +{ + return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) }; +} + static inline pmdval_t native_pmd_val(pmd_t pmd) { return native_pgd_val(pmd.pud.p4d.pgd); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 1bd9ed87606f..b0ccd4847a58 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -977,4 +977,5 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); +void microcode_check(void); #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 4e44250e7d0d..d65171120e90 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -67,13 +67,13 @@ static __always_inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) { GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "er", i, "%0", e); + r->refs.counter, "er", i, "%0", e, "cx"); } static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) { GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "%0", e); + r->refs.counter, "%0", e, "cx"); } static __always_inline __must_check diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index f91c365e57c3..4914a3e7c803 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -2,8 +2,7 @@ #ifndef _ASM_X86_RMWcc #define _ASM_X86_RMWcc -#define __CLOBBERS_MEM "memory" -#define __CLOBBERS_MEM_CC_CX "memory", "cc", "cx" +#define __CLOBBERS_MEM(clb...) "memory", ## clb #if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO) @@ -40,18 +39,19 @@ do { \ #endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ #define GEN_UNARY_RMWcc(op, var, arg0, cc) \ - __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM) + __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) -#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc) \ +#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\ __GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM_CC_CX) + __CLOBBERS_MEM(clobbers)) #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \ __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc, \ - __CLOBBERS_MEM, vcon (val)) + __CLOBBERS_MEM(), vcon (val)) -#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc) \ +#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc, \ + clobbers...) \ __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM_CC_CX, vcon (val)) + __CLOBBERS_MEM(clobbers), vcon (val)) #endif /* _ASM_X86_RMWcc */ diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 7a2ade4aa235..6cfa9c8cb7d6 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -26,6 +26,7 @@ #define KVM_FEATURE_PV_EOI 6 #define KVM_FEATURE_PV_UNHALT 7 #define KVM_FEATURE_PV_TLB_FLUSH 9 +#define KVM_FEATURE_ASYNC_PF_VMEXIT 10 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 8ad2e410974f..7c5538769f7e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1603,7 +1603,7 @@ static void __init delay_with_tsc(void) do { rep_nop(); now = rdtsc(); - } while ((now - start) < 40000000000UL / HZ && + } while ((now - start) < 40000000000ULL / HZ && time_before_eq(jiffies, end)); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d71c8b54b696..bfca937bdcc3 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -300,6 +300,15 @@ retpoline_auto: setup_force_cpu_cap(X86_FEATURE_USE_IBPB); pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } + + /* + * Retpoline means the kernel is safe because it has no indirect + * branches. But firmware isn't, so use IBRS to protect that. + */ + if (boot_cpu_has(X86_FEATURE_IBRS)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); + pr_info("Enabling Restricted Speculation for firmware calls\n"); + } } #undef pr_fmt @@ -326,8 +335,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", spectre_v2_module_string()); } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 824aee0117bb..348cf4821240 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1749,3 +1749,33 @@ static int __init init_cpu_syscore(void) return 0; } core_initcall(init_cpu_syscore); + +/* + * The microcode loader calls this upon late microcode load to recheck features, + * only when microcode has been updated. Caller holds microcode_mutex and CPU + * hotplug lock. + */ +void microcode_check(void) +{ + struct cpuinfo_x86 info; + + perf_check_microcode(); + + /* Reload CPUID max function as it might've changed. */ + info.cpuid_level = cpuid_eax(0); + + /* + * Copy all capability leafs to pick up the synthetic ones so that + * memcmp() below doesn't fail on that. The ones coming from CPUID will + * get overwritten in get_cpu_cap(). + */ + memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)); + + get_cpu_cap(&info); + + if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability))) + return; + + pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n"); + pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); +} diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 330b8462d426..a998e1a7d46f 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -498,7 +498,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, return patch_size; } -static int apply_microcode_amd(int cpu) +static enum ucode_state apply_microcode_amd(int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_amd *mc_amd; @@ -512,7 +512,7 @@ static int apply_microcode_amd(int cpu) p = find_patch(cpu); if (!p) - return 0; + return UCODE_NFOUND; mc_amd = p->data; uci->mc = p->data; @@ -523,13 +523,13 @@ static int apply_microcode_amd(int cpu) if (rev >= mc_amd->hdr.patch_id) { c->microcode = rev; uci->cpu_sig.rev = rev; - return 0; + return UCODE_OK; } if (__apply_microcode_amd(mc_amd)) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); - return -1; + return UCODE_ERROR; } pr_info("CPU%d: new patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); @@ -537,7 +537,7 @@ static int apply_microcode_amd(int cpu) uci->cpu_sig.rev = mc_amd->hdr.patch_id; c->microcode = mc_amd->hdr.patch_id; - return 0; + return UCODE_UPDATED; } static int install_equiv_cpu_table(const u8 *buf) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 319dd65f98a2..aa1b9a422f2b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -374,7 +374,7 @@ static int collect_cpu_info(int cpu) } struct apply_microcode_ctx { - int err; + enum ucode_state err; }; static void apply_microcode_local(void *arg) @@ -489,31 +489,30 @@ static void __exit microcode_dev_exit(void) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; -static int reload_for_cpu(int cpu) +static enum ucode_state reload_for_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; enum ucode_state ustate; - int err = 0; if (!uci->valid) - return err; + return UCODE_OK; ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); - if (ustate == UCODE_OK) - apply_microcode_on_target(cpu); - else - if (ustate == UCODE_ERROR) - err = -EINVAL; - return err; + if (ustate != UCODE_OK) + return ustate; + + return apply_microcode_on_target(cpu); } static ssize_t reload_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { + enum ucode_state tmp_ret = UCODE_OK; + bool do_callback = false; unsigned long val; + ssize_t ret = 0; int cpu; - ssize_t ret = 0, tmp_ret; ret = kstrtoul(buf, 0, &val); if (ret) @@ -526,15 +525,21 @@ static ssize_t reload_store(struct device *dev, mutex_lock(µcode_mutex); for_each_online_cpu(cpu) { tmp_ret = reload_for_cpu(cpu); - if (tmp_ret != 0) + if (tmp_ret > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); - /* save retval of the first encountered reload error */ - if (!ret) - ret = tmp_ret; + /* set retval for the first encountered reload error */ + if (!ret) + ret = -EINVAL; + } + + if (tmp_ret == UCODE_UPDATED) + do_callback = true; } - if (!ret) - perf_check_microcode(); + + if (!ret && do_callback) + microcode_check(); + mutex_unlock(µcode_mutex); put_online_cpus(); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index a15db2b4e0d6..923054a6b760 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -772,7 +772,7 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) return 0; } -static int apply_microcode_intel(int cpu) +static enum ucode_state apply_microcode_intel(int cpu) { struct microcode_intel *mc; struct ucode_cpu_info *uci; @@ -782,7 +782,7 @@ static int apply_microcode_intel(int cpu) /* We should bind the task to the CPU */ if (WARN_ON(raw_smp_processor_id() != cpu)) - return -1; + return UCODE_ERROR; uci = ucode_cpu_info + cpu; mc = uci->mc; @@ -790,7 +790,7 @@ static int apply_microcode_intel(int cpu) /* Look for a newer patch in our cache: */ mc = find_patch(uci); if (!mc) - return 0; + return UCODE_NFOUND; } /* write microcode via MSR 0x79 */ @@ -801,7 +801,7 @@ static int apply_microcode_intel(int cpu) if (rev != mc->hdr.rev) { pr_err("CPU%d update to revision 0x%x failed\n", cpu, mc->hdr.rev); - return -1; + return UCODE_ERROR; } if (rev != prev_rev) { @@ -818,7 +818,7 @@ static int apply_microcode_intel(int cpu) uci->cpu_sig.rev = rev; c->microcode = rev; - return 0; + return UCODE_UPDATED; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 04a625f0fcda..0f545b3cf926 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -23,6 +23,7 @@ #include <asm/nops.h> #include "../entry/calling.h" #include <asm/export.h> +#include <asm/nospec-branch.h> #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -134,6 +135,7 @@ ENTRY(secondary_startup_64) /* Ensure I am executing from virtual addresses */ movq $1f, %rax + ANNOTATE_RETPOLINE_SAFE jmp *%rax 1: UNWIND_HINT_EMPTY diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4e37d1a851a6..bc1a27280c4b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -49,7 +49,7 @@ static int kvmapf = 1; -static int parse_no_kvmapf(char *arg) +static int __init parse_no_kvmapf(char *arg) { kvmapf = 0; return 0; @@ -58,7 +58,7 @@ static int parse_no_kvmapf(char *arg) early_param("no-kvmapf", parse_no_kvmapf); static int steal_acc = 1; -static int parse_no_stealacc(char *arg) +static int __init parse_no_stealacc(char *arg) { steal_acc = 0; return 0; @@ -67,7 +67,7 @@ static int parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); static int kvmclock_vsyscall = 1; -static int parse_no_kvmclock_vsyscall(char *arg) +static int __init parse_no_kvmclock_vsyscall(char *arg) { kvmclock_vsyscall = 0; return 0; @@ -341,10 +341,10 @@ static void kvm_guest_cpu_init(void) #endif pa |= KVM_ASYNC_PF_ENABLED; - /* Async page fault support for L1 hypervisor is optional */ - if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN, - (pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0) - wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); + if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT)) + pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; + + wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); printk(KERN_INFO"KVM setup async PF for cpu %d\n", smp_processor_id()); @@ -545,7 +545,8 @@ static void __init kvm_guest_init(void) pv_time_ops.steal_clock = kvm_steal_clock; } - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -633,7 +634,8 @@ static __init int kvm_setup_pv_tlb_flush(void) { int cpu; - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) { + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), GFP_KERNEL, cpu_to_node(cpu)); diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 1f9188f5357c..feb28fee6cea 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -5,7 +5,6 @@ #include <asm/unwind.h> #include <asm/orc_types.h> #include <asm/orc_lookup.h> -#include <asm/sections.h> #define orc_warn(fmt, ...) \ printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) @@ -148,7 +147,7 @@ static struct orc_entry *orc_find(unsigned long ip) } /* vmlinux .init slow lookup: */ - if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext) + if (init_kernel_text(ip)) return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a0c5a69bc7c4..b671fc2d0422 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -607,7 +607,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | (1 << KVM_FEATURE_PV_UNHALT) | - (1 << KVM_FEATURE_PV_TLB_FLUSH); + (1 << KVM_FEATURE_PV_TLB_FLUSH) | + (1 << KVM_FEATURE_ASYNC_PF_VMEXIT); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 924ac8ce9d50..cc5fe7a50dde 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2165,7 +2165,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) */ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ - kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 46ff304140c7..f551962ac294 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3029,7 +3029,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) return RET_PF_RETRY; } - return -EFAULT; + return RET_PF_EMULATE; } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b3e488a74828..cbd7ab74952e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -49,6 +49,7 @@ #include <asm/debugreg.h> #include <asm/kvm_para.h> #include <asm/irq_remapping.h> +#include <asm/microcode.h> #include <asm/nospec-branch.h> #include <asm/virtext.h> @@ -300,6 +301,8 @@ module_param(vgif, int, 0444); static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); module_param(sev, int, 0444); +static u8 rsm_ins_bytes[] = "\x0f\xaa"; + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -1383,6 +1386,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_SKINIT); set_intercept(svm, INTERCEPT_WBINVD); set_intercept(svm, INTERCEPT_XSETBV); + set_intercept(svm, INTERCEPT_RSM); if (!kvm_mwait_in_guest()) { set_intercept(svm, INTERCEPT_MONITOR); @@ -3699,6 +3703,12 @@ static int emulate_on_interception(struct vcpu_svm *svm) return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } +static int rsm_interception(struct vcpu_svm *svm) +{ + return x86_emulate_instruction(&svm->vcpu, 0, 0, + rsm_ins_bytes, 2) == EMULATE_DONE; +} + static int rdpmc_interception(struct vcpu_svm *svm) { int err; @@ -4541,7 +4551,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = npf_interception, - [SVM_EXIT_RSM] = emulate_on_interception, + [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, }; @@ -5355,7 +5365,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); asm volatile ( "push %%" _ASM_BP "; \n\t" @@ -5464,11 +5474,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -6236,16 +6246,18 @@ e_free: static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) { + void __user *measure = (void __user *)(uintptr_t)argp->data; struct kvm_sev_info *sev = &kvm->arch.sev_info; struct sev_data_launch_measure *data; struct kvm_sev_launch_measure params; + void __user *p = NULL; void *blob = NULL; int ret; if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, measure, sizeof(params))) return -EFAULT; data = kzalloc(sizeof(*data), GFP_KERNEL); @@ -6256,17 +6268,13 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!params.len) goto cmd; - if (params.uaddr) { + p = (void __user *)(uintptr_t)params.uaddr; + if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) { ret = -EINVAL; goto e_free; } - if (!access_ok(VERIFY_WRITE, params.uaddr, params.len)) { - ret = -EFAULT; - goto e_free; - } - ret = -ENOMEM; blob = kmalloc(params.len, GFP_KERNEL); if (!blob) @@ -6290,13 +6298,13 @@ cmd: goto e_free_blob; if (blob) { - if (copy_to_user((void __user *)(uintptr_t)params.uaddr, blob, params.len)) + if (copy_to_user(p, blob, params.len)) ret = -EFAULT; } done: params.len = data->len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + if (copy_to_user(measure, ¶ms, sizeof(params))) ret = -EFAULT; e_free_blob: kfree(blob); @@ -6597,7 +6605,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) struct page **pages; void *blob, *hdr; unsigned long n; - int ret; + int ret, offset; if (!sev_guest(kvm)) return -ENOTTY; @@ -6623,6 +6631,10 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!data) goto e_unpin_memory; + offset = params.guest_uaddr & (PAGE_SIZE - 1); + data->guest_address = __sme_page_pa(pages[0]) + offset; + data->guest_len = params.guest_len; + blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); if (IS_ERR(blob)) { ret = PTR_ERR(blob); @@ -6637,8 +6649,8 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) ret = PTR_ERR(hdr); goto e_free_blob; } - data->trans_address = __psp_pa(blob); - data->trans_len = params.trans_len; + data->hdr_address = __psp_pa(hdr); + data->hdr_len = params.hdr_len; data->handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 3dec126aa302..cab6ea1f8be5 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -51,6 +51,7 @@ #include <asm/apic.h> #include <asm/irq_remapping.h> #include <asm/mmu_context.h> +#include <asm/microcode.h> #include <asm/nospec-branch.h> #include "trace.h" @@ -4485,7 +4486,8 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); hw_cr4 &= ~X86_CR4_UMIP; - } else + } else if (!is_guest_mode(vcpu) || + !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); @@ -9452,7 +9454,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); vmx->__launched = vmx->loaded_vmcs->launched; asm( @@ -9587,11 +9589,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -11199,7 +11201,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (ret) return ret; - if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) + /* + * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken + * by event injection, halt vcpu. + */ + if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && + !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) return kvm_vcpu_halt(vcpu); vmx->nested.nested_run_pending = 1; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8a0b545ac20..96edda878dbf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7975,6 +7975,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); kvm_vcpu_reset(vcpu, false); + kvm_lapic_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); return 0; @@ -8460,10 +8461,8 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) return r; } - if (!size) { - r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); - WARN_ON(r < 0); - } + if (!size) + vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); return 0; } diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 91e9700cc6dc..25a972c61b0a 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -28,7 +28,6 @@ lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_RETPOLINE) += retpoline.o -OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 480edc3a5e03..c909961e678a 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -7,7 +7,6 @@ #include <asm/alternative-asm.h> #include <asm/export.h> #include <asm/nospec-branch.h> -#include <asm/bitsperlong.h> .macro THUNK reg .section .text.__x86.indirect_thunk @@ -47,58 +46,3 @@ GENERATE_THUNK(r13) GENERATE_THUNK(r14) GENERATE_THUNK(r15) #endif - -/* - * Fill the CPU return stack buffer. - * - * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; lfence; jmp' loop to capture speculative execution. - * - * This is required in various cases for retpoline and IBRS-based - * mitigations for the Spectre variant 2 vulnerability. Sometimes to - * eliminate potentially bogus entries from the RSB, and sometimes - * purely to ensure that it doesn't get empty, which on some CPUs would - * allow predictions from other (unwanted!) sources to be used. - * - * Google experimented with loop-unrolling and this turned out to be - * the optimal version - two calls, each with their own speculation - * trap should their return address end up getting used, in a loop. - */ -.macro STUFF_RSB nr:req sp:req - mov $(\nr / 2), %_ASM_BX - .align 16 -771: - call 772f -773: /* speculation trap */ - pause - lfence - jmp 773b - .align 16 -772: - call 774f -775: /* speculation trap */ - pause - lfence - jmp 775b - .align 16 -774: - dec %_ASM_BX - jnz 771b - add $((BITS_PER_LONG/8) * \nr), \sp -.endm - -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ - -ENTRY(__fill_rsb) - STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP - ret -END(__fill_rsb) -EXPORT_SYMBOL_GPL(__fill_rsb) - -#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ - -ENTRY(__clear_rsb) - STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP - ret -END(__clear_rsb) -EXPORT_SYMBOL_GPL(__clear_rsb) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 800de815519c..c88573d90f3e 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1248,10 +1248,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, tsk = current; mm = tsk->mm; - /* - * Detect and handle instructions that would cause a page fault for - * both a tracked kernel page and a userspace page. - */ prefetchw(&mm->mmap_sem); if (unlikely(kmmio_fault(regs, address))) diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 01f682cf77a8..40a6085063d6 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -15,6 +15,7 @@ #include <asm/page.h> #include <asm/processor-flags.h> #include <asm/msr-index.h> +#include <asm/nospec-branch.h> .text .code64 @@ -59,6 +60,7 @@ ENTRY(sme_encrypt_execute) movq %rax, %r8 /* Workarea encryption routine */ addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ + ANNOTATE_RETPOLINE_SAFE call *%rax /* Call the encryption routine */ pop %r12 diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index de53bd15df5a..24bb7598774e 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -102,7 +102,7 @@ ENTRY(startup_32) * don't we'll eventually crash trying to execute encrypted * instructions. */ - bt $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags + btl $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags jnc .Ldone movl $MSR_K8_SYSCFG, %ecx rdmsr diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 4d46003c46cf..cdaeeea7999c 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -630,7 +630,7 @@ static int sysc_init_dts_quirks(struct sysc *ddata) for (i = 0; i < ARRAY_SIZE(sysc_dts_quirks); i++) { prop = of_get_property(np, sysc_dts_quirks[i].name, &len); if (!prop) - break; + continue; ddata->cfg.quirks |= sysc_dts_quirks[i].mask; } diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c index 4d1dc8b46877..f95b9c75175b 100644 --- a/drivers/char/tpm/st33zp24/st33zp24.c +++ b/drivers/char/tpm/st33zp24/st33zp24.c @@ -457,7 +457,7 @@ static int st33zp24_recv(struct tpm_chip *chip, unsigned char *buf, size_t count) { int size = 0; - int expected; + u32 expected; if (!chip) return -EBUSY; @@ -474,7 +474,7 @@ static int st33zp24_recv(struct tpm_chip *chip, unsigned char *buf, } expected = be32_to_cpu(*(__be32 *)(buf + 2)); - if (expected > count) { + if (expected > count || expected < TPM_HEADER_SIZE) { size = -EIO; goto out; } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 76df4fbcf089..9e80a953d693 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -1190,6 +1190,10 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max) break; recd = be32_to_cpu(tpm_cmd.params.getrandom_out.rng_data_len); + if (recd > num_bytes) { + total = -EFAULT; + break; + } rlength = be32_to_cpu(tpm_cmd.header.out.length); if (rlength < offsetof(struct tpm_getrandom_out, rng_data) + diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index c17e75348a99..a700f8f9ead7 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -683,6 +683,10 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, if (!rc) { data_len = be16_to_cpup( (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); + if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) { + rc = -EFAULT; + goto out; + } rlength = be32_to_cpu(((struct tpm2_cmd *)&buf) ->header.out.length); diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c index c1dd39eaaeeb..6116cd05e228 100644 --- a/drivers/char/tpm/tpm_i2c_infineon.c +++ b/drivers/char/tpm/tpm_i2c_infineon.c @@ -473,7 +473,8 @@ static int recv_data(struct tpm_chip *chip, u8 *buf, size_t count) static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count) { int size = 0; - int expected, status; + int status; + u32 expected; if (count < TPM_HEADER_SIZE) { size = -EIO; @@ -488,7 +489,7 @@ static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count) } expected = be32_to_cpu(*(__be32 *)(buf + 2)); - if ((size_t) expected > count) { + if (((size_t) expected > count) || (expected < TPM_HEADER_SIZE)) { size = -EIO; goto out; } diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c index c6428771841f..caa86b19c76d 100644 --- a/drivers/char/tpm/tpm_i2c_nuvoton.c +++ b/drivers/char/tpm/tpm_i2c_nuvoton.c @@ -281,7 +281,11 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count) struct device *dev = chip->dev.parent; struct i2c_client *client = to_i2c_client(dev); s32 rc; - int expected, status, burst_count, retries, size = 0; + int status; + int burst_count; + int retries; + int size = 0; + u32 expected; if (count < TPM_HEADER_SIZE) { i2c_nuvoton_ready(chip); /* return to idle */ @@ -323,7 +327,7 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count) * to machine native */ expected = be32_to_cpu(*(__be32 *) (buf + 2)); - if (expected > count) { + if (expected > count || expected < size) { dev_err(dev, "%s() expected > count\n", __func__); size = -EIO; continue; diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 183a5f54d875..da074e3db19b 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -270,7 +270,8 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count) { struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); int size = 0; - int expected, status; + int status; + u32 expected; if (count < TPM_HEADER_SIZE) { size = -EIO; @@ -285,7 +286,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count) } expected = be32_to_cpu(*(__be32 *) (buf + 2)); - if (expected > count) { + if (expected > count || expected < TPM_HEADER_SIZE) { size = -EIO; goto out; } diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c index fcfa5b1eae61..b3afb6cc9d72 100644 --- a/drivers/crypto/ccp/psp-dev.c +++ b/drivers/crypto/ccp/psp-dev.c @@ -211,7 +211,7 @@ static int __sev_platform_shutdown_locked(int *error) { int ret; - ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, 0, error); + ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); if (ret) return ret; @@ -271,7 +271,7 @@ static int sev_ioctl_do_reset(struct sev_issue_cmd *argp) return rc; } - return __sev_do_cmd_locked(SEV_CMD_FACTORY_RESET, 0, &argp->error); + return __sev_do_cmd_locked(SEV_CMD_FACTORY_RESET, NULL, &argp->error); } static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp) @@ -299,7 +299,7 @@ static int sev_ioctl_do_pek_pdh_gen(int cmd, struct sev_issue_cmd *argp) return rc; } - return __sev_do_cmd_locked(cmd, 0, &argp->error); + return __sev_do_cmd_locked(cmd, NULL, &argp->error); } static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp) @@ -624,7 +624,7 @@ EXPORT_SYMBOL_GPL(sev_guest_decommission); int sev_guest_df_flush(int *error) { - return sev_do_cmd(SEV_CMD_DF_FLUSH, 0, error); + return sev_do_cmd(SEV_CMD_DF_FLUSH, NULL, error); } EXPORT_SYMBOL_GPL(sev_guest_df_flush); diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index f34430f99fd8..872100215ca0 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -279,7 +279,7 @@ static const u32 correrrthrsld[] = { * sbridge structs */ -#define NUM_CHANNELS 4 /* Max channels per MC */ +#define NUM_CHANNELS 6 /* Max channels per MC */ #define MAX_DIMMS 3 /* Max DIMMS per channel */ #define KNL_MAX_CHAS 38 /* KNL max num. of Cache Home Agents */ #define KNL_MAX_CHANNELS 6 /* KNL max num. of PCI channels */ diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 564bb7a31da4..84e5a9df2344 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -241,6 +241,19 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id, desc = of_get_named_gpiod_flags(dev->of_node, prop_name, idx, &of_flags); + /* + * -EPROBE_DEFER in our case means that we found a + * valid GPIO property, but no controller has been + * registered so far. + * + * This means we don't need to look any further for + * alternate name conventions, and we should really + * preserve the return code for our user to be able to + * retry probing later. + */ + if (IS_ERR(desc) && PTR_ERR(desc) == -EPROBE_DEFER) + return desc; + if (!IS_ERR(desc) || (PTR_ERR(desc) != -ENOENT)) break; } @@ -250,7 +263,7 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id, desc = of_find_spi_gpio(dev, con_id, &of_flags); /* Special handling for regulator GPIOs if used */ - if (IS_ERR(desc)) + if (IS_ERR(desc) && PTR_ERR(desc) != -EPROBE_DEFER) desc = of_find_regulator_gpio(dev, con_id, &of_flags); if (IS_ERR(desc)) diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index e40065bdbfc8..0a7e99d62c69 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -157,7 +157,7 @@ static void multipath_status(struct seq_file *seq, struct mddev *mddev) seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); } rcu_read_unlock(); - seq_printf (seq, "]"); + seq_putc(seq, ']'); } static int multipath_congested(struct mddev *mddev, int bits) diff --git a/drivers/md/md.c b/drivers/md/md.c index bc67ab6844f0..254e44e44668 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -801,6 +801,9 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio; int ff = 0; + if (!page) + return; + if (test_bit(Faulty, &rdev->flags)) return; @@ -5452,6 +5455,7 @@ int md_run(struct mddev *mddev) * the only valid external interface is through the md * device. */ + mddev->has_superblocks = false; rdev_for_each(rdev, mddev) { if (test_bit(Faulty, &rdev->flags)) continue; @@ -5465,6 +5469,9 @@ int md_run(struct mddev *mddev) set_disk_ro(mddev->gendisk, 1); } + if (rdev->sb_page) + mddev->has_superblocks = true; + /* perform some consistency tests on the device. * We don't want the data to overlap the metadata, * Internal Bitmap issues have been handled elsewhere. @@ -5497,8 +5504,10 @@ int md_run(struct mddev *mddev) } if (mddev->sync_set == NULL) { mddev->sync_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - if (!mddev->sync_set) - return -ENOMEM; + if (!mddev->sync_set) { + err = -ENOMEM; + goto abort; + } } spin_lock(&pers_lock); @@ -5511,7 +5520,8 @@ int md_run(struct mddev *mddev) else pr_warn("md: personality for level %s is not loaded!\n", mddev->clevel); - return -EINVAL; + err = -EINVAL; + goto abort; } spin_unlock(&pers_lock); if (mddev->level != pers->level) { @@ -5524,7 +5534,8 @@ int md_run(struct mddev *mddev) pers->start_reshape == NULL) { /* This personality cannot handle reshaping... */ module_put(pers->owner); - return -EINVAL; + err = -EINVAL; + goto abort; } if (pers->sync_request) { @@ -5593,7 +5604,7 @@ int md_run(struct mddev *mddev) mddev->private = NULL; module_put(pers->owner); bitmap_destroy(mddev); - return err; + goto abort; } if (mddev->queue) { bool nonrot = true; @@ -5655,6 +5666,18 @@ int md_run(struct mddev *mddev) sysfs_notify_dirent_safe(mddev->sysfs_action); sysfs_notify(&mddev->kobj, NULL, "degraded"); return 0; + +abort: + if (mddev->bio_set) { + bioset_free(mddev->bio_set); + mddev->bio_set = NULL; + } + if (mddev->sync_set) { + bioset_free(mddev->sync_set); + mddev->sync_set = NULL; + } + + return err; } EXPORT_SYMBOL_GPL(md_run); @@ -8049,6 +8072,7 @@ EXPORT_SYMBOL(md_done_sync); bool md_write_start(struct mddev *mddev, struct bio *bi) { int did_change = 0; + if (bio_data_dir(bi) != WRITE) return true; @@ -8081,6 +8105,8 @@ bool md_write_start(struct mddev *mddev, struct bio *bi) rcu_read_unlock(); if (did_change) sysfs_notify_dirent_safe(mddev->sysfs_state); + if (!mddev->has_superblocks) + return true; wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) || mddev->suspended); @@ -8543,6 +8569,19 @@ void md_do_sync(struct md_thread *thread) set_mask_bits(&mddev->sb_flags, 0, BIT(MD_SB_CHANGE_PENDING) | BIT(MD_SB_CHANGE_DEVS)); + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && + !test_bit(MD_RECOVERY_INTR, &mddev->recovery) && + mddev->delta_disks > 0 && + mddev->pers->finish_reshape && + mddev->pers->size && + mddev->queue) { + mddev_lock_nointr(mddev); + md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0)); + mddev_unlock(mddev); + set_capacity(mddev->gendisk, mddev->array_sectors); + revalidate_disk(mddev->gendisk); + } + spin_lock(&mddev->lock); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { /* We completed so min/max setting can be forgotten if used. */ @@ -8569,6 +8608,10 @@ static int remove_and_add_spares(struct mddev *mddev, int removed = 0; bool remove_some = false; + if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + /* Mustn't remove devices when resync thread is running */ + return 0; + rdev_for_each(rdev, mddev) { if ((this == NULL || rdev == this) && rdev->raid_disk >= 0 && diff --git a/drivers/md/md.h b/drivers/md/md.h index 58cd20a5e85e..fbc925cce810 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -468,6 +468,8 @@ struct mddev { void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); struct md_cluster_info *cluster_info; unsigned int good_device_nr; /* good device num within cluster raid */ + + bool has_superblocks:1; }; enum recovery_flags { diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index f978eddc7a21..fe872dc6712e 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1809,6 +1809,17 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct md_rdev *repl = conf->mirrors[conf->raid_disks + number].rdev; freeze_array(conf, 0); + if (atomic_read(&repl->nr_pending)) { + /* It means that some queued IO of retry_list + * hold repl. Thus, we cannot set replacement + * as NULL, avoiding rdev NULL pointer + * dereference in sync_request_write and + * handle_write_finished. + */ + err = -EBUSY; + unfreeze_array(conf); + goto abort; + } clear_bit(Replacement, &repl->flags); p->rdev = repl; conf->mirrors[conf->raid_disks + number].rdev = NULL; diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index c7294e7557e0..eb84bc68e2fd 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -26,6 +26,18 @@ #define BARRIER_BUCKETS_NR_BITS (PAGE_SHIFT - ilog2(sizeof(atomic_t))) #define BARRIER_BUCKETS_NR (1<<BARRIER_BUCKETS_NR_BITS) +/* Note: raid1_info.rdev can be set to NULL asynchronously by raid1_remove_disk. + * There are three safe ways to access raid1_info.rdev. + * 1/ when holding mddev->reconfig_mutex + * 2/ when resync/recovery is known to be happening - i.e. in code that is + * called as part of performing resync/recovery. + * 3/ while holding rcu_read_lock(), use rcu_dereference to get the pointer + * and if it is non-NULL, increment rdev->nr_pending before dropping the + * RCU lock. + * When .rdev is set to NULL, the nr_pending count checked again and if it has + * been incremented, the pointer is put back in .rdev. + */ + struct raid1_info { struct md_rdev *rdev; sector_t head_position; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 99c9207899a7..c5e6c60fc0d4 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -141,7 +141,7 @@ static void r10bio_pool_free(void *r10_bio, void *data) #define RESYNC_WINDOW (1024*1024) /* maximum number of concurrent requests, memory permitting */ #define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE) -#define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW) +#define CLUSTER_RESYNC_WINDOW (32 * RESYNC_WINDOW) #define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9) /* @@ -2655,7 +2655,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) for (m = 0; m < conf->copies; m++) { int dev = r10_bio->devs[m].devnum; rdev = conf->mirrors[dev].rdev; - if (r10_bio->devs[m].bio == NULL) + if (r10_bio->devs[m].bio == NULL || + r10_bio->devs[m].bio->bi_end_io == NULL) continue; if (!r10_bio->devs[m].bio->bi_status) { rdev_clear_badblocks( @@ -2670,7 +2671,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) md_error(conf->mddev, rdev); } rdev = conf->mirrors[dev].replacement; - if (r10_bio->devs[m].repl_bio == NULL) + if (r10_bio->devs[m].repl_bio == NULL || + r10_bio->devs[m].repl_bio->bi_end_io == NULL) continue; if (!r10_bio->devs[m].repl_bio->bi_status) { @@ -3782,7 +3784,7 @@ static int raid10_run(struct mddev *mddev) if (fc > 1 || fo > 0) { pr_err("only near layout is supported by clustered" " raid10\n"); - goto out; + goto out_free_conf; } } @@ -4830,17 +4832,11 @@ static void raid10_finish_reshape(struct mddev *mddev) return; if (mddev->delta_disks > 0) { - sector_t size = raid10_size(mddev, 0, 0); - md_set_array_sectors(mddev, size); if (mddev->recovery_cp > mddev->resync_max_sectors) { mddev->recovery_cp = mddev->resync_max_sectors; set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } - mddev->resync_max_sectors = size; - if (mddev->queue) { - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); - } + mddev->resync_max_sectors = mddev->array_sectors; } else { int d; rcu_read_lock(); diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index db2ac22ac1b4..e2e8840de9bf 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -2,6 +2,19 @@ #ifndef _RAID10_H #define _RAID10_H +/* Note: raid10_info.rdev can be set to NULL asynchronously by + * raid10_remove_disk. + * There are three safe ways to access raid10_info.rdev. + * 1/ when holding mddev->reconfig_mutex + * 2/ when resync/recovery/reshape is known to be happening - i.e. in code + * that is called as part of performing resync/recovery/reshape. + * 3/ while holding rcu_read_lock(), use rcu_dereference to get the pointer + * and if it is non-NULL, increment rdev->nr_pending before dropping the + * RCU lock. + * When .rdev is set to NULL, the nr_pending count checked again and if it has + * been incremented, the pointer is put back in .rdev. + */ + struct raid10_info { struct md_rdev *rdev, *replacement; sector_t head_position; diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h index 0c76bcedfc1c..a001808a2b77 100644 --- a/drivers/md/raid5-log.h +++ b/drivers/md/raid5-log.h @@ -44,6 +44,7 @@ extern void ppl_write_stripe_run(struct r5conf *conf); extern void ppl_stripe_write_finished(struct stripe_head *sh); extern int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add); extern void ppl_quiesce(struct r5conf *conf, int quiesce); +extern int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio); static inline bool raid5_has_ppl(struct r5conf *conf) { @@ -104,7 +105,7 @@ static inline int log_handle_flush_request(struct r5conf *conf, struct bio *bio) if (conf->log) ret = r5l_handle_flush_request(conf->log, bio); else if (raid5_has_ppl(conf)) - ret = 0; + ret = ppl_handle_flush_request(conf->log, bio); return ret; } diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 2764c2290062..42890a08375b 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -693,6 +693,16 @@ void ppl_quiesce(struct r5conf *conf, int quiesce) } } +int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio) +{ + if (bio->bi_iter.bi_size == 0) { + bio_endio(bio); + return 0; + } + bio->bi_opf &= ~REQ_PREFLUSH; + return -EAGAIN; +} + void ppl_stripe_write_finished(struct stripe_head *sh) { struct ppl_io_unit *io; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 50d01144b805..b5d2601483e3 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2196,15 +2196,16 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp) static int grow_stripes(struct r5conf *conf, int num) { struct kmem_cache *sc; + size_t namelen = sizeof(conf->cache_name[0]); int devs = max(conf->raid_disks, conf->previous_raid_disks); if (conf->mddev->gendisk) - sprintf(conf->cache_name[0], + snprintf(conf->cache_name[0], namelen, "raid%d-%s", conf->level, mdname(conf->mddev)); else - sprintf(conf->cache_name[0], + snprintf(conf->cache_name[0], namelen, "raid%d-%p", conf->level, conf->mddev); - sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]); + snprintf(conf->cache_name[1], namelen, "%.27s-alt", conf->cache_name[0]); conf->active_name = 0; sc = kmem_cache_create(conf->cache_name[conf->active_name], @@ -6764,9 +6765,7 @@ static void free_conf(struct r5conf *conf) log_exit(conf); - if (conf->shrinker.nr_deferred) - unregister_shrinker(&conf->shrinker); - + unregister_shrinker(&conf->shrinker); free_thread_groups(conf); shrink_stripes(conf); raid5_free_percpu(conf); @@ -8001,13 +8000,7 @@ static void raid5_finish_reshape(struct mddev *mddev) if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { - if (mddev->delta_disks > 0) { - md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); - if (mddev->queue) { - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); - } - } else { + if (mddev->delta_disks <= 0) { int d; spin_lock_irq(&conf->device_lock); mddev->degraded = raid5_calc_degraded(conf); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 2e6123825095..3f8da26032ac 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -450,6 +450,18 @@ enum { * HANDLE gets cleared if stripe_handle leaves nothing locked. */ +/* Note: disk_info.rdev can be set to NULL asynchronously by raid5_remove_disk. + * There are three safe ways to access disk_info.rdev. + * 1/ when holding mddev->reconfig_mutex + * 2/ when resync/recovery/reshape is known to be happening - i.e. in code that + * is called as part of performing resync/recovery/reshape. + * 3/ while holding rcu_read_lock(), use rcu_dereference to get the pointer + * and if it is non-NULL, increment rdev->nr_pending before dropping the RCU + * lock. + * When .rdev is set to NULL, the nr_pending count checked again and if + * it has been incremented, the pointer is put back in .rdev. + */ + struct disk_info { struct md_rdev *rdev, *replacement; struct page *extra_page; /* extra page to use in prexor */ diff --git a/drivers/memory/brcmstb_dpfe.c b/drivers/memory/brcmstb_dpfe.c index 0a7bdbed3a6f..e9c1485c32b9 100644 --- a/drivers/memory/brcmstb_dpfe.c +++ b/drivers/memory/brcmstb_dpfe.c @@ -45,8 +45,16 @@ #define REG_TO_DCPU_MBOX 0x10 #define REG_TO_HOST_MBOX 0x14 +/* Macros to process offsets returned by the DCPU */ +#define DRAM_MSG_ADDR_OFFSET 0x0 +#define DRAM_MSG_TYPE_OFFSET 0x1c +#define DRAM_MSG_ADDR_MASK ((1UL << DRAM_MSG_TYPE_OFFSET) - 1) +#define DRAM_MSG_TYPE_MASK ((1UL << \ + (BITS_PER_LONG - DRAM_MSG_TYPE_OFFSET)) - 1) + /* Message RAM */ -#define DCPU_MSG_RAM(x) (0x100 + (x) * sizeof(u32)) +#define DCPU_MSG_RAM_START 0x100 +#define DCPU_MSG_RAM(x) (DCPU_MSG_RAM_START + (x) * sizeof(u32)) /* DRAM Info Offsets & Masks */ #define DRAM_INFO_INTERVAL 0x0 @@ -255,6 +263,40 @@ static unsigned int get_msg_chksum(const u32 msg[]) return sum; } +static void __iomem *get_msg_ptr(struct private_data *priv, u32 response, + char *buf, ssize_t *size) +{ + unsigned int msg_type; + unsigned int offset; + void __iomem *ptr = NULL; + + msg_type = (response >> DRAM_MSG_TYPE_OFFSET) & DRAM_MSG_TYPE_MASK; + offset = (response >> DRAM_MSG_ADDR_OFFSET) & DRAM_MSG_ADDR_MASK; + + /* + * msg_type == 1: the offset is relative to the message RAM + * msg_type == 0: the offset is relative to the data RAM (this is the + * previous way of passing data) + * msg_type is anything else: there's critical hardware problem + */ + switch (msg_type) { + case 1: + ptr = priv->regs + DCPU_MSG_RAM_START + offset; + break; + case 0: + ptr = priv->dmem + offset; + break; + default: + dev_emerg(priv->dev, "invalid message reply from DCPU: %#x\n", + response); + if (buf && size) + *size = sprintf(buf, + "FATAL: communication error with DCPU\n"); + } + + return ptr; +} + static int __send_command(struct private_data *priv, unsigned int cmd, u32 result[]) { @@ -507,7 +549,7 @@ static ssize_t show_info(struct device *dev, struct device_attribute *devattr, { u32 response[MSG_FIELD_MAX]; unsigned int info; - int ret; + ssize_t ret; ret = generic_show(DPFE_CMD_GET_INFO, response, dev, buf); if (ret) @@ -528,18 +570,19 @@ static ssize_t show_refresh(struct device *dev, u32 response[MSG_FIELD_MAX]; void __iomem *info; struct private_data *priv; - unsigned int offset; u8 refresh, sr_abort, ppre, thermal_offs, tuf; u32 mr4; - int ret; + ssize_t ret; ret = generic_show(DPFE_CMD_GET_REFRESH, response, dev, buf); if (ret) return ret; priv = dev_get_drvdata(dev); - offset = response[MSG_ARG0]; - info = priv->dmem + offset; + + info = get_msg_ptr(priv, response[MSG_ARG0], buf, &ret); + if (!info) + return ret; mr4 = readl_relaxed(info + DRAM_INFO_MR4) & DRAM_INFO_MR4_MASK; @@ -561,7 +604,6 @@ static ssize_t store_refresh(struct device *dev, struct device_attribute *attr, u32 response[MSG_FIELD_MAX]; struct private_data *priv; void __iomem *info; - unsigned int offset; unsigned long val; int ret; @@ -574,8 +616,10 @@ static ssize_t store_refresh(struct device *dev, struct device_attribute *attr, if (ret) return ret; - offset = response[MSG_ARG0]; - info = priv->dmem + offset; + info = get_msg_ptr(priv, response[MSG_ARG0], NULL, NULL); + if (!info) + return -EIO; + writel_relaxed(val, info + DRAM_INFO_INTERVAL); return count; @@ -587,23 +631,25 @@ static ssize_t show_vendor(struct device *dev, struct device_attribute *devattr, u32 response[MSG_FIELD_MAX]; struct private_data *priv; void __iomem *info; - unsigned int offset; - int ret; + ssize_t ret; ret = generic_show(DPFE_CMD_GET_VENDOR, response, dev, buf); if (ret) return ret; - offset = response[MSG_ARG0]; priv = dev_get_drvdata(dev); - info = priv->dmem + offset; + + info = get_msg_ptr(priv, response[MSG_ARG0], buf, &ret); + if (!info) + return ret; return sprintf(buf, "%#x %#x %#x %#x %#x\n", readl_relaxed(info + DRAM_VENDOR_MR5) & DRAM_VENDOR_MASK, readl_relaxed(info + DRAM_VENDOR_MR6) & DRAM_VENDOR_MASK, readl_relaxed(info + DRAM_VENDOR_MR7) & DRAM_VENDOR_MASK, readl_relaxed(info + DRAM_VENDOR_MR8) & DRAM_VENDOR_MASK, - readl_relaxed(info + DRAM_VENDOR_ERROR)); + readl_relaxed(info + DRAM_VENDOR_ERROR) & + DRAM_VENDOR_MASK); } static int brcmstb_dpfe_resume(struct platform_device *pdev) diff --git a/drivers/pinctrl/meson/pinctrl-meson-axg.c b/drivers/pinctrl/meson/pinctrl-meson-axg.c index 1fda9d6c7ea3..4b91ff74779b 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-axg.c +++ b/drivers/pinctrl/meson/pinctrl-meson-axg.c @@ -716,7 +716,7 @@ static const char * const uart_b_groups[] = { "uart_tx_b_x", "uart_rx_b_x", "uart_cts_b_x", "uart_rts_b_x", }; -static const char * const uart_ao_b_gpioz_groups[] = { +static const char * const uart_ao_b_z_groups[] = { "uart_ao_tx_b_z", "uart_ao_rx_b_z", "uart_ao_cts_b_z", "uart_ao_rts_b_z", }; @@ -855,7 +855,7 @@ static struct meson_pmx_func meson_axg_periphs_functions[] = { FUNCTION(nand), FUNCTION(uart_a), FUNCTION(uart_b), - FUNCTION(uart_ao_b_gpioz), + FUNCTION(uart_ao_b_z), FUNCTION(i2c0), FUNCTION(i2c1), FUNCTION(i2c2), diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index d1a01311c1a2..5e3df194723e 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -376,6 +376,7 @@ static int intel_hid_remove(struct platform_device *device) { acpi_handle handle = ACPI_HANDLE(&device->dev); + device_init_wakeup(&device->dev, false); acpi_remove_notify_handler(handle, ACPI_DEVICE_NOTIFY, notify_handler); intel_hid_set_enable(&device->dev, false); intel_button_array_enable(&device->dev, false); diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index b703d6f5b099..c13780b8dabb 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -7,6 +7,7 @@ */ #include <linux/acpi.h> +#include <linux/dmi.h> #include <linux/input.h> #include <linux/input/sparse-keymap.h> #include <linux/kernel.h> @@ -97,9 +98,35 @@ out_unknown: dev_dbg(&device->dev, "unknown event index 0x%x\n", event); } -static int intel_vbtn_probe(struct platform_device *device) +static void detect_tablet_mode(struct platform_device *device) { + const char *chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE); + struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev); + acpi_handle handle = ACPI_HANDLE(&device->dev); struct acpi_buffer vgbs_output = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *obj; + acpi_status status; + int m; + + if (!(chassis_type && strcmp(chassis_type, "31") == 0)) + goto out; + + status = acpi_evaluate_object(handle, "VGBS", NULL, &vgbs_output); + if (ACPI_FAILURE(status)) + goto out; + + obj = vgbs_output.pointer; + if (!(obj && obj->type == ACPI_TYPE_INTEGER)) + goto out; + + m = !(obj->integer.value & TABLET_MODE_FLAG); + input_report_switch(priv->input_dev, SW_TABLET_MODE, m); +out: + kfree(vgbs_output.pointer); +} + +static int intel_vbtn_probe(struct platform_device *device) +{ acpi_handle handle = ACPI_HANDLE(&device->dev); struct intel_vbtn_priv *priv; acpi_status status; @@ -122,22 +149,7 @@ static int intel_vbtn_probe(struct platform_device *device) return err; } - /* - * VGBS being present and returning something means we have - * a tablet mode switch. - */ - status = acpi_evaluate_object(handle, "VGBS", NULL, &vgbs_output); - if (ACPI_SUCCESS(status)) { - union acpi_object *obj = vgbs_output.pointer; - - if (obj && obj->type == ACPI_TYPE_INTEGER) { - int m = !(obj->integer.value & TABLET_MODE_FLAG); - - input_report_switch(priv->input_dev, SW_TABLET_MODE, m); - } - } - - kfree(vgbs_output.pointer); + detect_tablet_mode(device); status = acpi_install_notify_handler(handle, ACPI_DEVICE_NOTIFY, @@ -154,6 +166,7 @@ static int intel_vbtn_remove(struct platform_device *device) { acpi_handle handle = ACPI_HANDLE(&device->dev); + device_init_wakeup(&device->dev, false); acpi_remove_notify_handler(handle, ACPI_DEVICE_NOTIFY, notify_handler); /* diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index c0c8945603cb..8796211ef24a 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -945,7 +945,7 @@ static int wmi_dev_probe(struct device *dev) wblock->char_dev.mode = 0444; ret = misc_register(&wblock->char_dev); if (ret) { - dev_warn(dev, "failed to register char dev: %d", ret); + dev_warn(dev, "failed to register char dev: %d\n", ret); ret = -ENOMEM; goto probe_misc_failure; } @@ -1048,7 +1048,7 @@ static int wmi_create_device(struct device *wmi_bus_dev, if (result) { dev_warn(wmi_bus_dev, - "%s data block query control method not found", + "%s data block query control method not found\n", method); return result; } @@ -1198,7 +1198,7 @@ static int parse_wdg(struct device *wmi_bus_dev, struct acpi_device *device) retval = device_add(&wblock->dev.dev); if (retval) { - dev_err(wmi_bus_dev, "failed to register %pULL\n", + dev_err(wmi_bus_dev, "failed to register %pUL\n", wblock->gblock.guid); if (debug_event) wmi_method_enable(wblock, 0); diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c index cfb42f5eccb2..750f93197411 100644 --- a/drivers/soc/imx/gpc.c +++ b/drivers/soc/imx/gpc.c @@ -470,13 +470,21 @@ static int imx_gpc_probe(struct platform_device *pdev) static int imx_gpc_remove(struct platform_device *pdev) { + struct device_node *pgc_node; int ret; + pgc_node = of_get_child_by_name(pdev->dev.of_node, "pgc"); + + /* bail out if DT too old and doesn't provide the necessary info */ + if (!of_property_read_bool(pdev->dev.of_node, "#power-domain-cells") && + !pgc_node) + return 0; + /* * If the old DT binding is used the toplevel driver needs to * de-register the power domains */ - if (!of_get_child_by_name(pdev->dev.of_node, "pgc")) { + if (!pgc_node) { of_genpd_del_provider(pdev->dev.of_node); ret = pm_genpd_remove(&imx_gpc_domains[GPC_PGC_DOMAIN_PU].base); diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index fd975524f460..05c66e05ae20 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -767,7 +767,7 @@ int xfs_scrub_agfl( struct xfs_scrub_context *sc) { - struct xfs_scrub_agfl_info sai = { 0 }; + struct xfs_scrub_agfl_info sai; struct xfs_agf *agf; xfs_agnumber_t agno; unsigned int agflcount; @@ -795,6 +795,7 @@ xfs_scrub_agfl( xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp); goto out; } + memset(&sai, 0, sizeof(sai)); sai.sz_entries = agflcount; sai.entries = kmem_zalloc(sizeof(xfs_agblock_t) * agflcount, KM_NOFS); if (!sai.entries) { diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 3a55d6fc271b..7a39f40645f7 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -23,6 +23,7 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" +#include "xfs_shared.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_trans.h" @@ -456,10 +457,12 @@ xfs_cui_recover( * transaction. Normally, any work that needs to be deferred * gets attached to the same defer_ops that scheduled the * refcount update. However, we're in log recovery here, so we - * we create our own defer_ops and use that to finish up any - * work that doesn't fit. + * we use the passed in defer_ops and to finish up any work that + * doesn't fit. We need to reserve enough blocks to handle a + * full btree split on either end of the refcount range. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, + mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp); if (error) return error; cudp = xfs_trans_get_cud(tp, cuip); diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index f3b139c9aa16..49d3124863a8 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -23,6 +23,7 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" +#include "xfs_shared.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_trans.h" @@ -470,7 +471,8 @@ xfs_rui_recover( } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, + mp->m_rmap_maxlevels, 0, XFS_TRANS_RESERVE, &tp); if (error) return error; rudp = xfs_trans_get_rud(tp, ruip); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 7aba628dc527..93588ea3d3d2 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -250,6 +250,7 @@ xfs_parseargs( return -EINVAL; break; case Opt_logdev: + kfree(mp->m_logname); mp->m_logname = match_strdup(args); if (!mp->m_logname) return -ENOMEM; @@ -258,6 +259,7 @@ xfs_parseargs( xfs_warn(mp, "%s option not allowed on this system", p); return -EINVAL; case Opt_rtdev: + kfree(mp->m_rtname); mp->m_rtname = match_strdup(args); if (!mp->m_rtname) return -ENOMEM; diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d02a4df3f473..d3f264a5b04d 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -27,3 +27,8 @@ #if __has_feature(address_sanitizer) #define __SANITIZE_ADDRESS__ #endif + +/* Clang doesn't have a way to turn it off per-function, yet. */ +#ifdef __noretpoline +#undef __noretpoline +#endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 901c1ccb3374..e2c7f4369eff 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -93,6 +93,10 @@ #define __weak __attribute__((weak)) #define __alias(symbol) __attribute__((alias(#symbol))) +#ifdef RETPOLINE +#define __noretpoline __attribute__((indirect_branch("keep"))) +#endif + /* * it doesn't make sense on ARM (currently the only user of __naked) * to trace naked functions because then mcount is called without diff --git a/include/linux/init.h b/include/linux/init.h index 506a98151131..bc27cf03c41e 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -6,10 +6,10 @@ #include <linux/types.h> /* Built-in __init functions needn't be compiled with retpoline */ -#if defined(RETPOLINE) && !defined(MODULE) -#define __noretpoline __attribute__((indirect_branch("keep"))) +#if defined(__noretpoline) && !defined(MODULE) +#define __noinitretpoline __noretpoline #else -#define __noretpoline +#define __noinitretpoline #endif /* These macros are used to mark some functions or @@ -47,7 +47,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold __latent_entropy __noretpoline +#define __init __section(.init.text) __cold __latent_entropy __noinitretpoline #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index b6a29c126cc4..2168cc6b8b30 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -151,6 +151,7 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); +extern void jump_label_invalidate_init(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -198,6 +199,8 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } +static inline void jump_label_invalidate_init(void) {} + static __always_inline bool static_key_false(struct static_key *key) { if (unlikely(static_key_count(key) > 0)) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index ce51455e2adf..3fd291503576 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -472,6 +472,7 @@ extern bool parse_option_str(const char *str, const char *option); extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); +extern int init_kernel_text(unsigned long addr); extern int core_kernel_data(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ac0062b74aed..6930c63126c7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1105,7 +1105,6 @@ static inline void kvm_irq_routing_update(struct kvm *kvm) { } #endif -void kvm_arch_irq_routing_update(struct kvm *kvm); static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { @@ -1114,6 +1113,8 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) #endif /* CONFIG_HAVE_KVM_EVENTFD */ +void kvm_arch_irq_routing_update(struct kvm *kvm); + static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* @@ -1272,4 +1273,7 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end); + #endif diff --git a/include/linux/nospec.h b/include/linux/nospec.h index fbc98e2c8228..e791ebc65c9c 100644 --- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -5,6 +5,7 @@ #ifndef _LINUX_NOSPEC_H #define _LINUX_NOSPEC_H +#include <asm/barrier.h> /** * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise @@ -30,26 +31,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, #endif /* - * Warn developers about inappropriate array_index_nospec() usage. - * - * Even if the CPU speculates past the WARN_ONCE branch, the - * sign bit of @index is taken into account when generating the - * mask. - * - * This warning is compiled out when the compiler can infer that - * @index and @size are less than LONG_MAX. - */ -#define array_index_mask_nospec_check(index, size) \ -({ \ - if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, \ - "array_index_nospec() limited to range of [0, LONG_MAX]\n")) \ - _mask = 0; \ - else \ - _mask = array_index_mask_nospec(index, size); \ - _mask; \ -}) - -/* * array_index_nospec - sanitize an array index after a bounds check * * For a code sequence like: @@ -67,12 +48,11 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, ({ \ typeof(index) _i = (index); \ typeof(size) _s = (size); \ - unsigned long _mask = array_index_mask_nospec_check(_i, _s); \ + unsigned long _mask = array_index_mask_nospec(_i, _s); \ \ BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ \ - _i &= _mask; \ - _i; \ + (typeof(_i)) (_i & _mask); \ }) #endif /* _LINUX_NOSPEC_H */ diff --git a/include/soc/arc/mcip.h b/include/soc/arc/mcip.h index c2d1b15da136..a91f25151a5b 100644 --- a/include/soc/arc/mcip.h +++ b/include/soc/arc/mcip.h @@ -15,6 +15,7 @@ #define ARC_REG_MCIP_BCR 0x0d0 #define ARC_REG_MCIP_IDU_BCR 0x0D5 +#define ARC_REG_GFRC_BUILD 0x0D6 #define ARC_REG_MCIP_CMD 0x600 #define ARC_REG_MCIP_WDATA 0x601 #define ARC_REG_MCIP_READBACK 0x602 @@ -36,10 +37,14 @@ struct mcip_cmd { #define CMD_SEMA_RELEASE 0x12 #define CMD_DEBUG_SET_MASK 0x34 +#define CMD_DEBUG_READ_MASK 0x35 #define CMD_DEBUG_SET_SELECT 0x36 +#define CMD_DEBUG_READ_SELECT 0x37 #define CMD_GFRC_READ_LO 0x42 #define CMD_GFRC_READ_HI 0x43 +#define CMD_GFRC_SET_CORE 0x47 +#define CMD_GFRC_READ_CORE 0x48 #define CMD_IDU_ENABLE 0x71 #define CMD_IDU_DISABLE 0x72 diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 3d77fe91239a..9008f31c7eb6 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -42,7 +42,7 @@ typedef enum { SEV_RET_INVALID_PLATFORM_STATE, SEV_RET_INVALID_GUEST_STATE, SEV_RET_INAVLID_CONFIG, - SEV_RET_INVALID_len, + SEV_RET_INVALID_LEN, SEV_RET_ALREADY_OWNED, SEV_RET_INVALID_CERTIFICATE, SEV_RET_POLICY_FAILURE, diff --git a/init/main.c b/init/main.c index a8100b954839..969eaf140ef0 100644 --- a/init/main.c +++ b/init/main.c @@ -89,6 +89,7 @@ #include <linux/io.h> #include <linux/cache.h> #include <linux/rodata_test.h> +#include <linux/jump_label.h> #include <asm/io.h> #include <asm/bugs.h> @@ -1000,6 +1001,7 @@ static int __ref kernel_init(void *unused) /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); ftrace_free_init_mem(); + jump_label_invalidate_init(); free_initmem(); mark_readonly(); system_state = SYSTEM_RUNNING; diff --git a/kernel/extable.c b/kernel/extable.c index a17fdb63dc3e..6a5b61ebc66c 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -64,7 +64,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -static inline int init_kernel_text(unsigned long addr) +int init_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_sinittext && addr < (unsigned long)_einittext) diff --git a/kernel/jump_label.c b/kernel/jump_label.c index b4517095db6a..52a0a7af8640 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -366,12 +366,15 @@ static void __jump_label_update(struct static_key *key, { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { /* - * entry->code set to 0 invalidates module init text sections - * kernel_text_address() verifies we are not in core kernel - * init code, see jump_label_invalidate_module_init(). + * An entry->code of 0 indicates an entry which has been + * disabled because it was in an init text area. */ - if (entry->code && kernel_text_address(entry->code)) - arch_jump_label_transform(entry, jump_label_type(entry)); + if (entry->code) { + if (kernel_text_address(entry->code)) + arch_jump_label_transform(entry, jump_label_type(entry)); + else + WARN_ONCE(1, "can't patch jump_label at %pS", (void *)entry->code); + } } } @@ -417,6 +420,19 @@ void __init jump_label_init(void) cpus_read_unlock(); } +/* Disable any jump label entries in __init code */ +void __init jump_label_invalidate_init(void) +{ + struct jump_entry *iter_start = __start___jump_table; + struct jump_entry *iter_stop = __stop___jump_table; + struct jump_entry *iter; + + for (iter = iter_start; iter < iter_stop; iter++) { + if (init_kernel_text(iter->code)) + iter->code = 0; + } +} + #ifdef CONFIG_MODULES static enum jump_label_type jump_label_init_type(struct jump_entry *entry) @@ -633,6 +649,7 @@ static void jump_label_del_module(struct module *mod) } } +/* Disable any jump label entries in module init code */ static void jump_label_invalidate_module_init(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index fc1123583fa6..f274fbef821d 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2397,7 +2397,7 @@ skip: if (console_lock_spinning_disable_and_check()) { printk_safe_exit_irqrestore(flags); - return; + goto out; } printk_safe_exit_irqrestore(flags); @@ -2430,6 +2430,7 @@ skip: if (retry && console_trylock()) goto again; +out: if (wake_klogd) wake_up_klogd(); } diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 1b34d210452c..7f5cdc1e6b29 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1491,12 +1491,12 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size, if (unlikely(virt == NULL)) return; - entry = dma_entry_alloc(); - if (!entry) + /* handle vmalloc and linear addresses */ + if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt)) return; - /* handle vmalloc and linear addresses */ - if (!is_vmalloc_addr(virt) && !virt_to_page(virt)) + entry = dma_entry_alloc(); + if (!entry) return; entry->type = dma_debug_coherent; @@ -1528,7 +1528,7 @@ void debug_dma_free_coherent(struct device *dev, size_t size, }; /* handle vmalloc and linear addresses */ - if (!is_vmalloc_addr(virt) && !virt_to_page(virt)) + if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt)) return; if (is_vmalloc_addr(virt)) diff --git a/lib/idr.c b/lib/idr.c index 99ec5bc89d25..823b813f08f8 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -36,8 +36,8 @@ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, { struct radix_tree_iter iter; void __rcu **slot; - int base = idr->idr_base; - int id = *nextid; + unsigned int base = idr->idr_base; + unsigned int id = *nextid; if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr))) return -EINVAL; @@ -204,10 +204,11 @@ int idr_for_each(const struct idr *idr, radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) { int ret; + unsigned long id = iter.index + base; - if (WARN_ON_ONCE(iter.index > INT_MAX)) + if (WARN_ON_ONCE(id > INT_MAX)) break; - ret = fn(iter.index + base, rcu_dereference_raw(*slot), data); + ret = fn(id, rcu_dereference_raw(*slot), data); if (ret) return ret; } @@ -230,8 +231,8 @@ void *idr_get_next(struct idr *idr, int *nextid) { struct radix_tree_iter iter; void __rcu **slot; - int base = idr->idr_base; - int id = *nextid; + unsigned long base = idr->idr_base; + unsigned long id = *nextid; id = (id < base) ? 0 : id - base; slot = radix_tree_iter_find(&idr->idr_rt, &iter, id); diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile index 0e349b80686e..ba942e3ead89 100644 --- a/samples/seccomp/Makefile +++ b/samples/seccomp/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +ifndef CROSS_COMPILE hostprogs-$(CONFIG_SAMPLE_SECCOMP) := bpf-fancy dropper bpf-direct HOSTCFLAGS_bpf-fancy.o += -I$(objtree)/usr/include @@ -16,7 +17,6 @@ HOSTCFLAGS_bpf-direct.o += -idirafter $(objtree)/include bpf-direct-objs := bpf-direct.o # Try to match the kernel target. -ifndef CROSS_COMPILE ifndef CONFIG_64BIT # s390 has -m31 flag to build 31 bit binaries @@ -35,12 +35,4 @@ HOSTLOADLIBES_bpf-fancy += $(MFLAG) HOSTLOADLIBES_dropper += $(MFLAG) endif always := $(hostprogs-m) -else -# MIPS system calls are defined based on the -mabi that is passed -# to the toolchain which may or may not be a valid option -# for the host toolchain. So disable tests if target architecture -# is MIPS but the host isn't. -ifndef CONFIG_MIPS -always := $(hostprogs-m) -endif endif diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 47cddf32aeba..4f2b25d43ec9 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -256,6 +256,8 @@ __objtool_obj := $(objtree)/tools/objtool/objtool objtool_args = $(if $(CONFIG_UNWINDER_ORC),orc generate,check) +objtool_args += $(if $(part-of-module), --module,) + ifndef CONFIG_FRAME_POINTER objtool_args += --no-fp endif @@ -264,6 +266,12 @@ objtool_args += --no-unreachable else objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable) endif +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_CFLAGS),) + objtool_args += --retpoline +endif +endif + ifdef CONFIG_MODVERSIONS objtool_o = $(@D)/.tmp_$(@F) diff --git a/sound/core/control.c b/sound/core/control.c index 0b3026d937b1..8a77620a3854 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -889,7 +889,7 @@ static int snd_ctl_elem_read(struct snd_card *card, index_offset = snd_ctl_get_ioff(kctl, &control->id); vd = &kctl->vd[index_offset]; - if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) && kctl->get == NULL) + if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL) return -EPERM; snd_ctl_build_ioff(&control->id, kctl, index_offset); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index c71dcacea807..96143df19b21 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -181,7 +181,7 @@ static const struct kernel_param_ops param_ops_xint = { }; #define param_check_xint param_check_int -static int power_save = CONFIG_SND_HDA_POWER_SAVE_DEFAULT; +static int power_save = -1; module_param(power_save, xint, 0644); MODULE_PARM_DESC(power_save, "Automatic power-saving timeout " "(in second, 0 = disable)."); @@ -2186,6 +2186,24 @@ out_free: return err; } +#ifdef CONFIG_PM +/* On some boards setting power_save to a non 0 value leads to clicking / + * popping sounds when ever we enter/leave powersaving mode. Ideally we would + * figure out how to avoid these sounds, but that is not always feasible. + * So we keep a list of devices where we disable powersaving as its known + * to causes problems on these devices. + */ +static struct snd_pci_quirk power_save_blacklist[] = { + /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ + SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0), + /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ + SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0), + /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */ + SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0), + {} +}; +#endif /* CONFIG_PM */ + /* number of codec slots for each chipset: 0 = default slots (i.e. 4) */ static unsigned int azx_max_codecs[AZX_NUM_DRIVERS] = { [AZX_DRIVER_NVIDIA] = 8, @@ -2198,6 +2216,7 @@ static int azx_probe_continue(struct azx *chip) struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; int dev = chip->dev_index; + int val; int err; hda->probe_continued = 1; @@ -2278,7 +2297,22 @@ static int azx_probe_continue(struct azx *chip) chip->running = 1; azx_add_card_list(chip); - snd_hda_set_power_save(&chip->bus, power_save * 1000); + + val = power_save; +#ifdef CONFIG_PM + if (val == -1) { + const struct snd_pci_quirk *q; + + val = CONFIG_SND_HDA_POWER_SAVE_DEFAULT; + q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist); + if (q && val) { + dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n", + q->subvendor, q->subdevice); + val = 0; + } + } +#endif /* CONFIG_PM */ + snd_hda_set_power_save(&chip->bus, val * 1000); if (azx_has_pm_runtime(chip) || hda->use_vga_switcheroo) pm_runtime_put_autosuspend(&pci->dev); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index ce28f7ce64e6..b9c93fa0a51c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4997,13 +4997,14 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec, if (action == HDA_FIXUP_ACT_PRE_PROBE) { spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP; + snd_hda_apply_pincfgs(codec, pincfgs); + } else if (action == HDA_FIXUP_ACT_INIT) { /* Enable DOCK device */ snd_hda_codec_write(codec, 0x17, 0, AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0); /* Enable DOCK device */ snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0); - snd_hda_apply_pincfgs(codec, pincfgs); } } diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 50252046b01d..754e632a27bd 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3325,4 +3325,51 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), } }, +{ + /* + * Bower's & Wilkins PX headphones only support the 48 kHz sample rate + * even though it advertises more. The capture interface doesn't work + * even on windows. + */ + USB_DEVICE(0x19b5, 0x0021), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_MIXER, + }, + /* Capture */ + { + .ifnum = 1, + .type = QUIRK_IGNORE_INTERFACE, + }, + /* Playback */ + { + .ifnum = 2, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels = 2, + .iface = 2, + .altsetting = 1, + .altset_idx = 1, + .attributes = UAC_EP_CS_ATTR_FILL_MAX | + UAC_EP_CS_ATTR_SAMPLE_RATE, + .endpoint = 0x03, + .ep_attr = USB_ENDPOINT_XFER_ISOC, + .rates = SNDRV_PCM_RATE_48000, + .rate_min = 48000, + .rate_max = 48000, + .nr_rates = 1, + .rate_table = (unsigned int[]) { + 48000 + } + } + }, + } + } +}, + #undef USB_DEVICE_VENDOR_SPEC diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c index a0951505c7f5..4ed9d0c41843 100644 --- a/sound/x86/intel_hdmi_audio.c +++ b/sound/x86/intel_hdmi_audio.c @@ -50,6 +50,7 @@ /*standard module options for ALSA. This module supports only one card*/ static int hdmi_card_index = SNDRV_DEFAULT_IDX1; static char *hdmi_card_id = SNDRV_DEFAULT_STR1; +static bool single_port; module_param_named(index, hdmi_card_index, int, 0444); MODULE_PARM_DESC(index, @@ -57,6 +58,9 @@ MODULE_PARM_DESC(index, module_param_named(id, hdmi_card_id, charp, 0444); MODULE_PARM_DESC(id, "ID string for INTEL Intel HDMI Audio controller."); +module_param(single_port, bool, 0444); +MODULE_PARM_DESC(single_port, + "Single-port mode (for compatibility)"); /* * ELD SA bits in the CEA Speaker Allocation data block @@ -1579,7 +1583,11 @@ static irqreturn_t display_pipe_interrupt_handler(int irq, void *dev_id) static void notify_audio_lpe(struct platform_device *pdev, int port) { struct snd_intelhad_card *card_ctx = platform_get_drvdata(pdev); - struct snd_intelhad *ctx = &card_ctx->pcm_ctx[port]; + struct snd_intelhad *ctx; + + ctx = &card_ctx->pcm_ctx[single_port ? 0 : port]; + if (single_port) + ctx->port = port; schedule_work(&ctx->hdmi_audio_wq); } @@ -1743,6 +1751,7 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) { struct snd_card *card; struct snd_intelhad_card *card_ctx; + struct snd_intelhad *ctx; struct snd_pcm *pcm; struct intel_hdmi_lpe_audio_pdata *pdata; int irq; @@ -1787,6 +1796,21 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) platform_set_drvdata(pdev, card_ctx); + card_ctx->num_pipes = pdata->num_pipes; + card_ctx->num_ports = single_port ? 1 : pdata->num_ports; + + for_each_port(card_ctx, port) { + ctx = &card_ctx->pcm_ctx[port]; + ctx->card_ctx = card_ctx; + ctx->dev = card_ctx->dev; + ctx->port = single_port ? -1 : port; + ctx->pipe = -1; + + spin_lock_init(&ctx->had_spinlock); + mutex_init(&ctx->mutex); + INIT_WORK(&ctx->hdmi_audio_wq, had_audio_wq); + } + dev_dbg(&pdev->dev, "%s: mmio_start = 0x%x, mmio_end = 0x%x\n", __func__, (unsigned int)res_mmio->start, (unsigned int)res_mmio->end); @@ -1816,19 +1840,12 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) init_channel_allocations(); card_ctx->num_pipes = pdata->num_pipes; - card_ctx->num_ports = pdata->num_ports; + card_ctx->num_ports = single_port ? 1 : pdata->num_ports; for_each_port(card_ctx, port) { - struct snd_intelhad *ctx = &card_ctx->pcm_ctx[port]; int i; - ctx->card_ctx = card_ctx; - ctx->dev = card_ctx->dev; - ctx->port = port; - ctx->pipe = -1; - - INIT_WORK(&ctx->hdmi_audio_wq, had_audio_wq); - + ctx = &card_ctx->pcm_ctx[port]; ret = snd_pcm_new(card, INTEL_HAD, port, MAX_PB_STREAMS, MAX_CAP_STREAMS, &pcm); if (ret) diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index a5684d0968b4..5898c22ba310 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -33,7 +33,7 @@ import resource import struct import re import subprocess -from collections import defaultdict +from collections import defaultdict, namedtuple VMX_EXIT_REASONS = { 'EXCEPTION_NMI': 0, @@ -228,6 +228,7 @@ IOCTL_NUMBERS = { } ENCODING = locale.getpreferredencoding(False) +TRACE_FILTER = re.compile(r'^[^\(]*$') class Arch(object): @@ -260,6 +261,11 @@ class Arch(object): return ArchX86(SVM_EXIT_REASONS) return + def tracepoint_is_child(self, field): + if (TRACE_FILTER.match(field)): + return None + return field.split('(', 1)[0] + class ArchX86(Arch): def __init__(self, exit_reasons): @@ -267,6 +273,10 @@ class ArchX86(Arch): self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = exit_reasons + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + return None + class ArchPPC(Arch): def __init__(self): @@ -282,6 +292,10 @@ class ArchPPC(Arch): self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16 self.exit_reasons = {} + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + return None + class ArchA64(Arch): def __init__(self): @@ -289,6 +303,10 @@ class ArchA64(Arch): self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = AARCH64_EXIT_REASONS + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + return None + class ArchS390(Arch): def __init__(self): @@ -296,6 +314,12 @@ class ArchS390(Arch): self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = None + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + if field.startswith('instruction_'): + return 'exit_instruction' + + ARCH = Arch.get_arch() @@ -331,9 +355,6 @@ class perf_event_attr(ctypes.Structure): PERF_TYPE_TRACEPOINT = 2 PERF_FORMAT_GROUP = 1 << 3 -PATH_DEBUGFS_TRACING = '/sys/kernel/debug/tracing' -PATH_DEBUGFS_KVM = '/sys/kernel/debug/kvm' - class Group(object): """Represents a perf event group.""" @@ -376,8 +397,8 @@ class Event(object): self.syscall = self.libc.syscall self.name = name self.fd = None - self.setup_event(group, trace_cpu, trace_pid, trace_point, - trace_filter, trace_set) + self._setup_event(group, trace_cpu, trace_pid, trace_point, + trace_filter, trace_set) def __del__(self): """Closes the event's file descriptor. @@ -390,7 +411,7 @@ class Event(object): if self.fd: os.close(self.fd) - def perf_event_open(self, attr, pid, cpu, group_fd, flags): + def _perf_event_open(self, attr, pid, cpu, group_fd, flags): """Wrapper for the sys_perf_evt_open() syscall. Used to set up performance events, returns a file descriptor or -1 @@ -409,7 +430,7 @@ class Event(object): ctypes.c_int(pid), ctypes.c_int(cpu), ctypes.c_int(group_fd), ctypes.c_long(flags)) - def setup_event_attribute(self, trace_set, trace_point): + def _setup_event_attribute(self, trace_set, trace_point): """Returns an initialized ctype perf_event_attr struct.""" id_path = os.path.join(PATH_DEBUGFS_TRACING, 'events', trace_set, @@ -419,8 +440,8 @@ class Event(object): event_attr.config = int(open(id_path).read()) return event_attr - def setup_event(self, group, trace_cpu, trace_pid, trace_point, - trace_filter, trace_set): + def _setup_event(self, group, trace_cpu, trace_pid, trace_point, + trace_filter, trace_set): """Sets up the perf event in Linux. Issues the syscall to register the event in the kernel and @@ -428,7 +449,7 @@ class Event(object): """ - event_attr = self.setup_event_attribute(trace_set, trace_point) + event_attr = self._setup_event_attribute(trace_set, trace_point) # First event will be group leader. group_leader = -1 @@ -437,8 +458,8 @@ class Event(object): if group.events: group_leader = group.events[0].fd - fd = self.perf_event_open(event_attr, trace_pid, - trace_cpu, group_leader, 0) + fd = self._perf_event_open(event_attr, trace_pid, + trace_cpu, group_leader, 0) if fd == -1: err = ctypes.get_errno() raise OSError(err, os.strerror(err), @@ -475,6 +496,10 @@ class Event(object): class Provider(object): """Encapsulates functionalities used by all providers.""" + def __init__(self, pid): + self.child_events = False + self.pid = pid + @staticmethod def is_field_wanted(fields_filter, field): """Indicate whether field is valid according to fields_filter.""" @@ -500,12 +525,12 @@ class TracepointProvider(Provider): """ def __init__(self, pid, fields_filter): self.group_leaders = [] - self.filters = self.get_filters() + self.filters = self._get_filters() self.update_fields(fields_filter) - self.pid = pid + super(TracepointProvider, self).__init__(pid) @staticmethod - def get_filters(): + def _get_filters(): """Returns a dict of trace events, their filter ids and the values that can be filtered. @@ -521,8 +546,8 @@ class TracepointProvider(Provider): filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons) return filters - def get_available_fields(self): - """Returns a list of available event's of format 'event name(filter + def _get_available_fields(self): + """Returns a list of available events of format 'event name(filter name)'. All available events have directories under @@ -549,11 +574,12 @@ class TracepointProvider(Provider): def update_fields(self, fields_filter): """Refresh fields, applying fields_filter""" - self.fields = [field for field in self.get_available_fields() - if self.is_field_wanted(fields_filter, field)] + self.fields = [field for field in self._get_available_fields() + if self.is_field_wanted(fields_filter, field) or + ARCH.tracepoint_is_child(field)] @staticmethod - def get_online_cpus(): + def _get_online_cpus(): """Returns a list of cpu id integers.""" def parse_int_list(list_string): """Returns an int list from a string of comma separated integers and @@ -575,17 +601,17 @@ class TracepointProvider(Provider): cpu_string = cpu_list.readline() return parse_int_list(cpu_string) - def setup_traces(self): + def _setup_traces(self): """Creates all event and group objects needed to be able to retrieve data.""" - fields = self.get_available_fields() + fields = self._get_available_fields() if self._pid > 0: # Fetch list of all threads of the monitored pid, as qemu # starts a thread for each vcpu. path = os.path.join('/proc', str(self._pid), 'task') groupids = self.walkdir(path)[1] else: - groupids = self.get_online_cpus() + groupids = self._get_online_cpus() # The constant is needed as a buffer for python libs, std # streams and other files that the script opens. @@ -663,7 +689,7 @@ class TracepointProvider(Provider): # The garbage collector will get rid of all Event/Group # objects and open files after removing the references. self.group_leaders = [] - self.setup_traces() + self._setup_traces() self.fields = self._fields def read(self, by_guest=0): @@ -671,8 +697,12 @@ class TracepointProvider(Provider): ret = defaultdict(int) for group in self.group_leaders: for name, val in group.read().items(): - if name in self._fields: - ret[name] += val + if name not in self._fields: + continue + parent = ARCH.tracepoint_is_child(name) + if parent: + name += ' ' + parent + ret[name] += val return ret def reset(self): @@ -690,11 +720,11 @@ class DebugfsProvider(Provider): self._baseline = {} self.do_read = True self.paths = [] - self.pid = pid + super(DebugfsProvider, self).__init__(pid) if include_past: - self.restore() + self._restore() - def get_available_fields(self): + def _get_available_fields(self): """"Returns a list of available fields. The fields are all available KVM debugfs files @@ -704,8 +734,9 @@ class DebugfsProvider(Provider): def update_fields(self, fields_filter): """Refresh fields, applying fields_filter""" - self._fields = [field for field in self.get_available_fields() - if self.is_field_wanted(fields_filter, field)] + self._fields = [field for field in self._get_available_fields() + if self.is_field_wanted(fields_filter, field) or + ARCH.debugfs_is_child(field)] @property def fields(self): @@ -758,7 +789,7 @@ class DebugfsProvider(Provider): paths.append(dir) for path in paths: for field in self._fields: - value = self.read_field(field, path) + value = self._read_field(field, path) key = path + field if reset == 1: self._baseline[key] = value @@ -766,20 +797,21 @@ class DebugfsProvider(Provider): self._baseline[key] = 0 if self._baseline.get(key, -1) == -1: self._baseline[key] = value - increment = (results.get(field, 0) + value - - self._baseline.get(key, 0)) - if by_guest: - pid = key.split('-')[0] - if pid in results: - results[pid] += increment - else: - results[pid] = increment + parent = ARCH.debugfs_is_child(field) + if parent: + field = field + ' ' + parent + else: + if by_guest: + field = key.split('-')[0] # set 'field' to 'pid' + increment = value - self._baseline.get(key, 0) + if field in results: + results[field] += increment else: results[field] = increment return results - def read_field(self, field, path): + def _read_field(self, field, path): """Returns the value of a single field from a specific VM.""" try: return int(open(os.path.join(PATH_DEBUGFS_KVM, @@ -794,12 +826,15 @@ class DebugfsProvider(Provider): self._baseline = {} self.read(1) - def restore(self): + def _restore(self): """Reset field counters""" self._baseline = {} self.read(2) +EventStat = namedtuple('EventStat', ['value', 'delta']) + + class Stats(object): """Manages the data providers and the data they provide. @@ -808,13 +843,13 @@ class Stats(object): """ def __init__(self, options): - self.providers = self.get_providers(options) + self.providers = self._get_providers(options) self._pid_filter = options.pid self._fields_filter = options.fields self.values = {} + self._child_events = False - @staticmethod - def get_providers(options): + def _get_providers(self, options): """Returns a list of data providers depending on the passed options.""" providers = [] @@ -826,7 +861,7 @@ class Stats(object): return providers - def update_provider_filters(self): + def _update_provider_filters(self): """Propagates fields filters to providers.""" # As we reset the counters when updating the fields we can # also clear the cache of old values. @@ -847,7 +882,7 @@ class Stats(object): def fields_filter(self, fields_filter): if fields_filter != self._fields_filter: self._fields_filter = fields_filter - self.update_provider_filters() + self._update_provider_filters() @property def pid_filter(self): @@ -861,16 +896,33 @@ class Stats(object): for provider in self.providers: provider.pid = self._pid_filter + @property + def child_events(self): + return self._child_events + + @child_events.setter + def child_events(self, val): + self._child_events = val + for provider in self.providers: + provider.child_events = val + def get(self, by_guest=0): """Returns a dict with field -> (value, delta to last value) of all - provider data.""" + provider data. + Key formats: + * plain: 'key' is event name + * child-parent: 'key' is in format '<child> <parent>' + * pid: 'key' is the pid of the guest, and the record contains the + aggregated event data + These formats are generated by the providers, and handled in class TUI. + """ for provider in self.providers: new = provider.read(by_guest=by_guest) - for key in new if by_guest else provider.fields: - oldval = self.values.get(key, (0, 0))[0] + for key in new: + oldval = self.values.get(key, EventStat(0, 0)).value newval = new.get(key, 0) newdelta = newval - oldval - self.values[key] = (newval, newdelta) + self.values[key] = EventStat(newval, newdelta) return self.values def toggle_display_guests(self, to_pid): @@ -899,10 +951,10 @@ class Stats(object): self.get(to_pid) return 0 + DELAY_DEFAULT = 3.0 MAX_GUEST_NAME_LEN = 48 MAX_REGEX_LEN = 44 -DEFAULT_REGEX = r'^[^\(]*$' SORT_DEFAULT = 0 @@ -969,7 +1021,7 @@ class Tui(object): return res - def print_all_gnames(self, row): + def _print_all_gnames(self, row): """Print a list of all running guests along with their pids.""" self.screen.addstr(row, 2, '%8s %-60s' % ('Pid', 'Guest Name (fuzzy list, might be ' @@ -1032,19 +1084,13 @@ class Tui(object): return name - def update_drilldown(self): - """Sets or removes a filter that only allows fields without braces.""" - if not self.stats.fields_filter: - self.stats.fields_filter = DEFAULT_REGEX - - elif self.stats.fields_filter == DEFAULT_REGEX: - self.stats.fields_filter = None - - def update_pid(self, pid): + def _update_pid(self, pid): """Propagates pid selection to stats object.""" + self.screen.addstr(4, 1, 'Updating pid filter...') + self.screen.refresh() self.stats.pid_filter = pid - def refresh_header(self, pid=None): + def _refresh_header(self, pid=None): """Refreshes the header.""" if pid is None: pid = self.stats.pid_filter @@ -1059,8 +1105,7 @@ class Tui(object): .format(pid, gname), curses.A_BOLD) else: self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD) - if self.stats.fields_filter and self.stats.fields_filter \ - != DEFAULT_REGEX: + if self.stats.fields_filter: regex = self.stats.fields_filter if len(regex) > MAX_REGEX_LEN: regex = regex[:MAX_REGEX_LEN] + '...' @@ -1075,56 +1120,99 @@ class Tui(object): self.screen.addstr(4, 1, 'Collecting data...') self.screen.refresh() - def refresh_body(self, sleeptime): + def _refresh_body(self, sleeptime): + def is_child_field(field): + return field.find('(') != -1 + + def insert_child(sorted_items, child, values, parent): + num = len(sorted_items) + for i in range(0, num): + # only add child if parent is present + if parent.startswith(sorted_items[i][0]): + sorted_items.insert(i + 1, (' ' + child, values)) + + def get_sorted_events(self, stats): + """ separate parent and child events """ + if self._sorting == SORT_DEFAULT: + def sortkey((_k, v)): + # sort by (delta value, overall value) + return (v.delta, v.value) + else: + def sortkey((_k, v)): + # sort by overall value + return v.value + + childs = [] + sorted_items = [] + # we can't rule out child events to appear prior to parents even + # when sorted - separate out all children first, and add in later + for key, values in sorted(stats.items(), key=sortkey, + reverse=True): + if values == (0, 0): + continue + if key.find(' ') != -1: + if not self.stats.child_events: + continue + childs.insert(0, (key, values)) + else: + sorted_items.append((key, values)) + if self.stats.child_events: + for key, values in childs: + (child, parent) = key.split(' ') + insert_child(sorted_items, child, values, parent) + + return sorted_items + row = 3 self.screen.move(row, 0) self.screen.clrtobot() stats = self.stats.get(self._display_guests) - - def sortCurAvg(x): - # sort by current events if available - if stats[x][1]: - return (-stats[x][1], -stats[x][0]) + total = 0. + ctotal = 0. + for key, values in stats.items(): + if self._display_guests: + if self.get_gname_from_pid(key): + total += values.value + continue + if not key.find(' ') != -1: + total += values.value else: - return (0, -stats[x][0]) + ctotal += values.value + if total == 0.: + # we don't have any fields, or all non-child events are filtered + total = ctotal - def sortTotal(x): - # sort by totals - return (0, -stats[x][0]) - total = 0. - for key in stats.keys(): - if key.find('(') is -1: - total += stats[key][0] - if self._sorting == SORT_DEFAULT: - sortkey = sortCurAvg - else: - sortkey = sortTotal + # print events tavg = 0 - for key in sorted(stats.keys(), key=sortkey): - if row >= self.screen.getmaxyx()[0] - 1: - break - values = stats[key] - if not values[0] and not values[1]: + tcur = 0 + for key, values in get_sorted_events(self, stats): + if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0): break - if values[0] is not None: - cur = int(round(values[1] / sleeptime)) if values[1] else '' - if self._display_guests: - key = self.get_gname_from_pid(key) - self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % - (key, values[0], values[0] * 100 / total, - cur)) - if cur is not '' and key.find('(') is -1: - tavg += cur + if self._display_guests: + key = self.get_gname_from_pid(key) + if not key: + continue + cur = int(round(values.delta / sleeptime)) if values.delta else '' + if key[0] != ' ': + if values.delta: + tcur += values.delta + ptotal = values.value + ltotal = total + else: + ltotal = ptotal + self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % (key, + values.value, + values.value * 100 / float(ltotal), cur)) row += 1 if row == 3: self.screen.addstr(4, 1, 'No matching events reported yet') - else: + if row > 4: + tavg = int(round(tcur / sleeptime)) if tcur > 0 else '' self.screen.addstr(row, 1, '%-40s %10d %8s' % - ('Total', total, tavg if tavg else ''), - curses.A_BOLD) + ('Total', total, tavg), curses.A_BOLD) self.screen.refresh() - def show_msg(self, text): + def _show_msg(self, text): """Display message centered text and exit on key press""" hint = 'Press any key to continue' curses.cbreak() @@ -1139,16 +1227,16 @@ class Tui(object): curses.A_STANDOUT) self.screen.getkey() - def show_help_interactive(self): + def _show_help_interactive(self): """Display help with list of interactive commands""" msg = (' b toggle events by guests (debugfs only, honors' ' filters)', ' c clear filter', ' f filter by regular expression', - ' g filter by guest name', + ' g filter by guest name/PID', ' h display interactive commands reference', ' o toggle sorting order (Total vs CurAvg/s)', - ' p filter by PID', + ' p filter by guest name/PID', ' q quit', ' r reset stats', ' s set update interval', @@ -1165,14 +1253,15 @@ class Tui(object): self.screen.addstr(row, 0, line) row += 1 self.screen.getkey() - self.refresh_header() + self._refresh_header() - def show_filter_selection(self): + def _show_filter_selection(self): """Draws filter selection mask. Asks for a valid regex and sets the fields filter accordingly. """ + msg = '' while True: self.screen.erase() self.screen.addstr(0, 0, @@ -1181,61 +1270,25 @@ class Tui(object): self.screen.addstr(2, 0, "Current regex: {0}" .format(self.stats.fields_filter)) + self.screen.addstr(5, 0, msg) self.screen.addstr(3, 0, "New regex: ") curses.echo() regex = self.screen.getstr().decode(ENCODING) curses.noecho() if len(regex) == 0: - self.stats.fields_filter = DEFAULT_REGEX - self.refresh_header() + self.stats.fields_filter = '' + self._refresh_header() return try: re.compile(regex) self.stats.fields_filter = regex - self.refresh_header() + self._refresh_header() return except re.error: + msg = '"' + regex + '": Not a valid regular expression' continue - def show_vm_selection_by_pid(self): - """Draws PID selection mask. - - Asks for a pid until a valid pid or 0 has been entered. - - """ - msg = '' - while True: - self.screen.erase() - self.screen.addstr(0, 0, - 'Show statistics for specific pid.', - curses.A_BOLD) - self.screen.addstr(1, 0, - 'This might limit the shown data to the trace ' - 'statistics.') - self.screen.addstr(5, 0, msg) - self.print_all_gnames(7) - - curses.echo() - self.screen.addstr(3, 0, "Pid [0 or pid]: ") - pid = self.screen.getstr().decode(ENCODING) - curses.noecho() - - try: - if len(pid) > 0: - pid = int(pid) - if pid != 0 and not os.path.isdir(os.path.join('/proc/', - str(pid))): - msg = '"' + str(pid) + '": Not a running process' - continue - else: - pid = 0 - self.refresh_header(pid) - self.update_pid(pid) - break - except ValueError: - msg = '"' + str(pid) + '": Not a valid pid' - - def show_set_update_interval(self): + def _show_set_update_interval(self): """Draws update interval selection mask.""" msg = '' while True: @@ -1265,60 +1318,67 @@ class Tui(object): except ValueError: msg = '"' + str(val) + '": Invalid value' - self.refresh_header() + self._refresh_header() - def show_vm_selection_by_guest_name(self): + def _show_vm_selection_by_guest(self): """Draws guest selection mask. - Asks for a guest name until a valid guest name or '' is entered. + Asks for a guest name or pid until a valid guest name or '' is entered. """ msg = '' while True: self.screen.erase() self.screen.addstr(0, 0, - 'Show statistics for specific guest.', + 'Show statistics for specific guest or pid.', curses.A_BOLD) self.screen.addstr(1, 0, 'This might limit the shown data to the trace ' 'statistics.') self.screen.addstr(5, 0, msg) - self.print_all_gnames(7) + self._print_all_gnames(7) curses.echo() - self.screen.addstr(3, 0, "Guest [ENTER or guest]: ") - gname = self.screen.getstr().decode(ENCODING) + curses.curs_set(1) + self.screen.addstr(3, 0, "Guest or pid [ENTER exits]: ") + guest = self.screen.getstr().decode(ENCODING) curses.noecho() - if not gname: - self.refresh_header(0) - self.update_pid(0) + pid = 0 + if not guest or guest == '0': break - else: - pids = [] - try: - pids = self.get_pid_from_gname(gname) - except: - msg = '"' + gname + '": Internal error while searching, ' \ - 'use pid filter instead' - continue - if len(pids) == 0: - msg = '"' + gname + '": Not an active guest' + if guest.isdigit(): + if not os.path.isdir(os.path.join('/proc/', guest)): + msg = '"' + guest + '": Not a running process' continue - if len(pids) > 1: - msg = '"' + gname + '": Multiple matches found, use pid ' \ - 'filter instead' - continue - self.refresh_header(pids[0]) - self.update_pid(pids[0]) + pid = int(guest) break + pids = [] + try: + pids = self.get_pid_from_gname(guest) + except: + msg = '"' + guest + '": Internal error while searching, ' \ + 'use pid filter instead' + continue + if len(pids) == 0: + msg = '"' + guest + '": Not an active guest' + continue + if len(pids) > 1: + msg = '"' + guest + '": Multiple matches found, use pid ' \ + 'filter instead' + continue + pid = pids[0] + break + curses.curs_set(0) + self._refresh_header(pid) + self._update_pid(pid) def show_stats(self): """Refreshes the screen and processes user input.""" sleeptime = self._delay_initial - self.refresh_header() + self._refresh_header() start = 0.0 # result based on init value never appears on screen while True: - self.refresh_body(time.time() - start) + self._refresh_body(time.time() - start) curses.halfdelay(int(sleeptime * 10)) start = time.time() sleeptime = self._delay_regular @@ -1327,47 +1387,39 @@ class Tui(object): if char == 'b': self._display_guests = not self._display_guests if self.stats.toggle_display_guests(self._display_guests): - self.show_msg(['Command not available with tracepoints' - ' enabled', 'Restart with debugfs only ' - '(see option \'-d\') and try again!']) + self._show_msg(['Command not available with ' + 'tracepoints enabled', 'Restart with ' + 'debugfs only (see option \'-d\') and ' + 'try again!']) self._display_guests = not self._display_guests - self.refresh_header() + self._refresh_header() if char == 'c': - self.stats.fields_filter = DEFAULT_REGEX - self.refresh_header(0) - self.update_pid(0) + self.stats.fields_filter = '' + self._refresh_header(0) + self._update_pid(0) if char == 'f': curses.curs_set(1) - self.show_filter_selection() + self._show_filter_selection() curses.curs_set(0) sleeptime = self._delay_initial - if char == 'g': - curses.curs_set(1) - self.show_vm_selection_by_guest_name() - curses.curs_set(0) + if char == 'g' or char == 'p': + self._show_vm_selection_by_guest() sleeptime = self._delay_initial if char == 'h': - self.show_help_interactive() + self._show_help_interactive() if char == 'o': self._sorting = not self._sorting - if char == 'p': - curses.curs_set(1) - self.show_vm_selection_by_pid() - curses.curs_set(0) - sleeptime = self._delay_initial if char == 'q': break if char == 'r': self.stats.reset() if char == 's': curses.curs_set(1) - self.show_set_update_interval() + self._show_set_update_interval() curses.curs_set(0) sleeptime = self._delay_initial if char == 'x': - self.update_drilldown() - # prevents display of current values on next refresh - self.stats.get(self._display_guests) + self.stats.child_events = not self.stats.child_events except KeyboardInterrupt: break except curses.error: @@ -1380,9 +1432,9 @@ def batch(stats): s = stats.get() time.sleep(1) s = stats.get() - for key in sorted(s.keys()): - values = s[key] - print('%-42s%10d%10d' % (key, values[0], values[1])) + for key, values in sorted(s.items()): + print('%-42s%10d%10d' % (key.split(' ')[0], values.value, + values.delta)) except KeyboardInterrupt: pass @@ -1392,14 +1444,14 @@ def log(stats): keys = sorted(stats.get().keys()) def banner(): - for k in keys: - print(k, end=' ') + for key in keys: + print(key.split(' ')[0], end=' ') print() def statline(): s = stats.get() - for k in keys: - print(' %9d' % s[k][1], end=' ') + for key in keys: + print(' %9d' % s[key].delta, end=' ') print() line = 0 banner_repeat = 20 @@ -1504,7 +1556,7 @@ Press any other key to refresh statistics immediately. ) optparser.add_option('-f', '--fields', action='store', - default=DEFAULT_REGEX, + default='', dest='fields', help='''fields to display (regex) "-f help" for a list of available events''', @@ -1539,17 +1591,6 @@ Press any other key to refresh statistics immediately. def check_access(options): """Exits if the current user can't access all needed directories.""" - if not os.path.exists('/sys/kernel/debug'): - sys.stderr.write('Please enable CONFIG_DEBUG_FS in your kernel.') - sys.exit(1) - - if not os.path.exists(PATH_DEBUGFS_KVM): - sys.stderr.write("Please make sure, that debugfs is mounted and " - "readable by the current user:\n" - "('mount -t debugfs debugfs /sys/kernel/debug')\n" - "Also ensure, that the kvm modules are loaded.\n") - sys.exit(1) - if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints or not options.debugfs): sys.stderr.write("Please enable CONFIG_TRACING in your kernel " @@ -1567,7 +1608,33 @@ def check_access(options): return options +def assign_globals(): + global PATH_DEBUGFS_KVM + global PATH_DEBUGFS_TRACING + + debugfs = '' + for line in file('/proc/mounts'): + if line.split(' ')[0] == 'debugfs': + debugfs = line.split(' ')[1] + break + if debugfs == '': + sys.stderr.write("Please make sure that CONFIG_DEBUG_FS is enabled in " + "your kernel, mounted and\nreadable by the current " + "user:\n" + "('mount -t debugfs debugfs /sys/kernel/debug')\n") + sys.exit(1) + + PATH_DEBUGFS_KVM = os.path.join(debugfs, 'kvm') + PATH_DEBUGFS_TRACING = os.path.join(debugfs, 'tracing') + + if not os.path.exists(PATH_DEBUGFS_KVM): + sys.stderr.write("Please make sure that CONFIG_KVM is enabled in " + "your kernel and that the modules are loaded.\n") + sys.exit(1) + + def main(): + assign_globals() options = get_options() options = check_access(options) diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index b5b3810c9e94..0811d860fe75 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -35,13 +35,13 @@ INTERACTIVE COMMANDS *f*:: filter by regular expression -*g*:: filter by guest name +*g*:: filter by guest name/PID *h*:: display interactive commands reference *o*:: toggle sorting order (Total vs CurAvg/s) -*p*:: filter by PID +*p*:: filter by guest name/PID *q*:: quit diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 57254f5b2779..694abc628e9b 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -29,7 +29,7 @@ #include "builtin.h" #include "check.h" -bool no_fp, no_unreachable; +bool no_fp, no_unreachable, retpoline, module; static const char * const check_usage[] = { "objtool check [<options>] file.o", @@ -39,6 +39,8 @@ static const char * const check_usage[] = { const struct option check_options[] = { OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"), OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"), + OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"), + OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"), OPT_END(), }; @@ -53,5 +55,5 @@ int cmd_check(int argc, const char **argv) objname = argv[0]; - return check(objname, no_fp, no_unreachable, false); + return check(objname, false); } diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c index 91e8e19ff5e0..77ea2b97117d 100644 --- a/tools/objtool/builtin-orc.c +++ b/tools/objtool/builtin-orc.c @@ -25,7 +25,6 @@ */ #include <string.h> -#include <subcmd/parse-options.h> #include "builtin.h" #include "check.h" @@ -36,9 +35,6 @@ static const char *orc_usage[] = { NULL, }; -extern const struct option check_options[]; -extern bool no_fp, no_unreachable; - int cmd_orc(int argc, const char **argv) { const char *objname; @@ -54,7 +50,7 @@ int cmd_orc(int argc, const char **argv) objname = argv[0]; - return check(objname, no_fp, no_unreachable, true); + return check(objname, true); } if (!strcmp(argv[0], "dump")) { diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h index dd526067fed5..28ff40e19a14 100644 --- a/tools/objtool/builtin.h +++ b/tools/objtool/builtin.h @@ -17,6 +17,11 @@ #ifndef _BUILTIN_H #define _BUILTIN_H +#include <subcmd/parse-options.h> + +extern const struct option check_options[]; +extern bool no_fp, no_unreachable, retpoline, module; + extern int cmd_check(int argc, const char **argv); extern int cmd_orc(int argc, const char **argv); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a8cb69a26576..472e64e95891 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -18,6 +18,7 @@ #include <string.h> #include <stdlib.h> +#include "builtin.h" #include "check.h" #include "elf.h" #include "special.h" @@ -33,7 +34,6 @@ struct alternative { }; const char *objname; -static bool no_fp; struct cfi_state initial_func_cfi; struct instruction *find_insn(struct objtool_file *file, @@ -497,6 +497,7 @@ static int add_jump_destinations(struct objtool_file *file) * disguise, so convert them accordingly. */ insn->type = INSN_JUMP_DYNAMIC; + insn->retpoline_safe = true; continue; } else { /* sibling call */ @@ -548,7 +549,8 @@ static int add_call_destinations(struct objtool_file *file) if (!insn->call_dest && !insn->ignore) { WARN_FUNC("unsupported intra-function call", insn->sec, insn->offset); - WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."); + if (retpoline) + WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."); return -1; } @@ -1108,6 +1110,54 @@ static int read_unwind_hints(struct objtool_file *file) return 0; } +static int read_retpoline_hints(struct objtool_file *file) +{ + struct section *sec, *relasec; + struct instruction *insn; + struct rela *rela; + int i; + + sec = find_section_by_name(file->elf, ".discard.retpoline_safe"); + if (!sec) + return 0; + + relasec = sec->rela; + if (!relasec) { + WARN("missing .rela.discard.retpoline_safe section"); + return -1; + } + + if (sec->len % sizeof(unsigned long)) { + WARN("retpoline_safe size mismatch: %d %ld", sec->len, sizeof(unsigned long)); + return -1; + } + + for (i = 0; i < sec->len / sizeof(unsigned long); i++) { + rela = find_rela_by_dest(sec, i * sizeof(unsigned long)); + if (!rela) { + WARN("can't find rela for retpoline_safe[%d]", i); + return -1; + } + + insn = find_insn(file, rela->sym->sec, rela->addend); + if (!insn) { + WARN("can't find insn for retpoline_safe[%d]", i); + return -1; + } + + if (insn->type != INSN_JUMP_DYNAMIC && + insn->type != INSN_CALL_DYNAMIC) { + WARN_FUNC("retpoline_safe hint not a indirect jump/call", + insn->sec, insn->offset); + return -1; + } + + insn->retpoline_safe = true; + } + + return 0; +} + static int decode_sections(struct objtool_file *file) { int ret; @@ -1146,6 +1196,10 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; + ret = read_retpoline_hints(file); + if (ret) + return ret; + return 0; } @@ -1891,6 +1945,38 @@ static int validate_unwind_hints(struct objtool_file *file) return warnings; } +static int validate_retpoline(struct objtool_file *file) +{ + struct instruction *insn; + int warnings = 0; + + for_each_insn(file, insn) { + if (insn->type != INSN_JUMP_DYNAMIC && + insn->type != INSN_CALL_DYNAMIC) + continue; + + if (insn->retpoline_safe) + continue; + + /* + * .init.text code is ran before userspace and thus doesn't + * strictly need retpolines, except for modules which are + * loaded late, they very much do need retpoline in their + * .init.text + */ + if (!strcmp(insn->sec->name, ".init.text") && !module) + continue; + + WARN_FUNC("indirect %s found in RETPOLINE build", + insn->sec, insn->offset, + insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); + + warnings++; + } + + return warnings; +} + static bool is_kasan_insn(struct instruction *insn) { return (insn->type == INSN_CALL && @@ -2022,13 +2108,12 @@ static void cleanup(struct objtool_file *file) elf_close(file->elf); } -int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc) +int check(const char *_objname, bool orc) { struct objtool_file file; int ret, warnings = 0; objname = _objname; - no_fp = _no_fp; file.elf = elf_open(objname, orc ? O_RDWR : O_RDONLY); if (!file.elf) @@ -2052,6 +2137,13 @@ int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc) if (list_empty(&file.insn_list)) goto out; + if (retpoline) { + ret = validate_retpoline(&file); + if (ret < 0) + return ret; + warnings += ret; + } + ret = validate_functions(&file); if (ret < 0) goto out; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 23a1d065cae1..c6b68fcb926f 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -45,6 +45,7 @@ struct instruction { unsigned char type; unsigned long immediate; bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; + bool retpoline_safe; struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; @@ -63,7 +64,7 @@ struct objtool_file { bool ignore_unreachables, c_file, hints; }; -int check(const char *objname, bool no_fp, bool no_unreachable, bool orc); +int check(const char *objname, bool orc); struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset); diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 44ef9eba5a7a..6c645eb77d42 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -178,6 +178,55 @@ void idr_get_next_test(int base) idr_destroy(&idr); } +int idr_u32_cb(int id, void *ptr, void *data) +{ + BUG_ON(id < 0); + BUG_ON(ptr != DUMMY_PTR); + return 0; +} + +void idr_u32_test1(struct idr *idr, u32 handle) +{ + static bool warned = false; + u32 id = handle; + int sid = 0; + void *ptr; + + BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL)); + BUG_ON(id != handle); + BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL) != -ENOSPC); + BUG_ON(id != handle); + if (!warned && id > INT_MAX) + printk("vvv Ignore these warnings\n"); + ptr = idr_get_next(idr, &sid); + if (id > INT_MAX) { + BUG_ON(ptr != NULL); + BUG_ON(sid != 0); + } else { + BUG_ON(ptr != DUMMY_PTR); + BUG_ON(sid != id); + } + idr_for_each(idr, idr_u32_cb, NULL); + if (!warned && id > INT_MAX) { + printk("^^^ Warnings over\n"); + warned = true; + } + BUG_ON(idr_remove(idr, id) != DUMMY_PTR); + BUG_ON(!idr_is_empty(idr)); +} + +void idr_u32_test(int base) +{ + DEFINE_IDR(idr); + idr_init_base(&idr, base); + idr_u32_test1(&idr, 10); + idr_u32_test1(&idr, 0x7fffffff); + idr_u32_test1(&idr, 0x80000000); + idr_u32_test1(&idr, 0x80000001); + idr_u32_test1(&idr, 0xffe00000); + idr_u32_test1(&idr, 0xffffffff); +} + void idr_checks(void) { unsigned long i; @@ -248,6 +297,9 @@ void idr_checks(void) idr_get_next_test(0); idr_get_next_test(1); idr_get_next_test(4); + idr_u32_test(4); + idr_u32_test(1); + idr_u32_test(0); } /* diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index 6903ccf35595..44a0d1ad4408 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -29,7 +29,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) { struct radix_tree_node *node; - if (flags & __GFP_NOWARN) + if (!(flags & __GFP_DIRECT_RECLAIM)) return NULL; pthread_mutex_lock(&cachep->lock); @@ -73,10 +73,17 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) void *kmalloc(size_t size, gfp_t gfp) { - void *ret = malloc(size); + void *ret; + + if (!(gfp & __GFP_DIRECT_RECLAIM)) + return NULL; + + ret = malloc(size); uatomic_inc(&nr_allocated); if (kmalloc_verbose) printf("Allocating %p from malloc\n", ret); + if (gfp & __GFP_ZERO) + memset(ret, 0, size); return ret; } diff --git a/tools/testing/radix-tree/linux/compiler_types.h b/tools/testing/radix-tree/linux/compiler_types.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/radix-tree/linux/compiler_types.h diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h index e9fff59dfd8a..e3201ccf54c3 100644 --- a/tools/testing/radix-tree/linux/gfp.h +++ b/tools/testing/radix-tree/linux/gfp.h @@ -11,6 +11,7 @@ #define __GFP_IO 0x40u #define __GFP_FS 0x80u #define __GFP_NOWARN 0x200u +#define __GFP_ZERO 0x8000u #define __GFP_ATOMIC 0x80000u #define __GFP_ACCOUNT 0x100000u #define __GFP_DIRECT_RECLAIM 0x400000u diff --git a/tools/testing/radix-tree/linux/slab.h b/tools/testing/radix-tree/linux/slab.h index 979baeec7e70..a037def0dec6 100644 --- a/tools/testing/radix-tree/linux/slab.h +++ b/tools/testing/radix-tree/linux/slab.h @@ -3,6 +3,7 @@ #define SLAB_H #include <linux/types.h> +#include <linux/gfp.h> #define SLAB_HWCACHE_ALIGN 1 #define SLAB_PANIC 2 @@ -11,6 +12,11 @@ void *kmalloc(size_t size, gfp_t); void kfree(void *); +static inline void *kzalloc(size_t size, gfp_t gfp) +{ + return kmalloc(size, gfp | __GFP_ZERO); +} + void *kmem_cache_alloc(struct kmem_cache *cachep, int flags); void kmem_cache_free(struct kmem_cache *cachep, void *objp); diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile index 1a7492268993..f6304d2be90c 100644 --- a/tools/testing/selftests/android/Makefile +++ b/tools/testing/selftests/android/Makefile @@ -11,11 +11,11 @@ all: BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ - #SUBDIR test prog name should be in the form: SUBDIR_test.sh + #SUBDIR test prog name should be in the form: SUBDIR_test.sh \ TEST=$$DIR"_test.sh"; \ - if [ -e $$DIR/$$TEST ]; then - rsync -a $$DIR/$$TEST $$BUILD_TARGET/; - fi + if [ -e $$DIR/$$TEST ]; then \ + rsync -a $$DIR/$$TEST $$BUILD_TARGET/; \ + fi \ done override define RUN_TESTS diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index cea4adcd42b8..a63e8453984d 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -12,9 +12,9 @@ all: BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ - if [ -e $$DIR/$(TEST_PROGS) ]; then - rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; - fi + if [ -e $$DIR/$(TEST_PROGS) ]; then \ + rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \ + fi \ done override define RUN_TESTS diff --git a/tools/testing/selftests/memfd/config b/tools/testing/selftests/memfd/config new file mode 100644 index 000000000000..835c7f4dadcd --- /dev/null +++ b/tools/testing/selftests/memfd/config @@ -0,0 +1 @@ +CONFIG_FUSE_FS=m diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile index 86636d207adf..183b46883875 100644 --- a/tools/testing/selftests/memory-hotplug/Makefile +++ b/tools/testing/selftests/memory-hotplug/Makefile @@ -4,7 +4,7 @@ all: include ../lib.mk TEST_PROGS := mem-on-off-test.sh -override RUN_TESTS := ./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]" +override RUN_TESTS := @./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]" override EMIT_TESTS := echo "$(RUN_TESTS)" run_full_test: diff --git a/tools/testing/selftests/pstore/config b/tools/testing/selftests/pstore/config index 6a8e5a9bfc10..d148f9f89fb6 100644 --- a/tools/testing/selftests/pstore/config +++ b/tools/testing/selftests/pstore/config @@ -2,3 +2,4 @@ CONFIG_MISC_FILESYSTEMS=y CONFIG_PSTORE=y CONFIG_PSTORE_PMSG=y CONFIG_PSTORE_CONSOLE=y +CONFIG_PSTORE_RAM=m diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index b3c8ba3cb668..d0121a8a3523 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -30,7 +30,7 @@ $(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS) $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS) $(OBJS): $(OUTPUT)/%.o: %.c - $(CC) -c $^ -o $@ + $(CC) -c $^ -o $@ $(CFLAGS) $(TESTS): $(OUTPUT)/%.o: %.c $(CC) -c $^ -o $@ diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index 3d5a62ff7d31..f5d7a7851e21 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +include ../lib.mk + ifndef CROSS_COMPILE CFLAGS := -std=gnu99 CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector @@ -6,16 +8,14 @@ ifeq ($(CONFIG_X86_32),y) LDLIBS += -lgcc_s endif -TEST_PROGS := vdso_test vdso_standalone_test_x86 +TEST_PROGS := $(OUTPUT)/vdso_test $(OUTPUT)/vdso_standalone_test_x86 all: $(TEST_PROGS) -vdso_test: parse_vdso.c vdso_test.c -vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c +$(OUTPUT)/vdso_test: parse_vdso.c vdso_test.c +$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c $(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \ vdso_standalone_test_x86.c parse_vdso.c \ - -o vdso_standalone_test_x86 + -o $@ -include ../lib.mk -clean: - rm -fr $(TEST_PROGS) +EXTRA_CLEAN := $(TEST_PROGS) endif diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 63c94d776e89..342c7bc9dc8c 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -11,3 +11,4 @@ mlock-intersect-test mlock-random-test virtual_address_range gup_benchmark +va_128TBswitch diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 70268c0bec79..70f4c30918eb 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -36,6 +36,8 @@ static struct timecounter *timecounter; static unsigned int host_vtimer_irq; static u32 host_vtimer_irq_flags; +static DEFINE_STATIC_KEY_FALSE(has_gic_active_state); + static const struct kvm_irq_level default_ptimer_irq = { .irq = 30, .level = 1, @@ -56,6 +58,12 @@ u64 kvm_phys_timer_read(void) return timecounter->cc->read(timecounter->cc); } +static inline bool userspace_irqchip(struct kvm *kvm) +{ + return static_branch_unlikely(&userspace_irqchip_in_use) && + unlikely(!irqchip_in_kernel(kvm)); +} + static void soft_timer_start(struct hrtimer *hrt, u64 ns) { hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns), @@ -69,25 +77,6 @@ static void soft_timer_cancel(struct hrtimer *hrt, struct work_struct *work) cancel_work_sync(work); } -static void kvm_vtimer_update_mask_user(struct kvm_vcpu *vcpu) -{ - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - - /* - * When using a userspace irqchip with the architected timers, we must - * prevent continuously exiting from the guest, and therefore mask the - * physical interrupt by disabling it on the host interrupt controller - * when the virtual level is high, such that the guest can make - * forward progress. Once we detect the output level being - * de-asserted, we unmask the interrupt again so that we exit from the - * guest when the timer fires. - */ - if (vtimer->irq.level) - disable_percpu_irq(host_vtimer_irq); - else - enable_percpu_irq(host_vtimer_irq, 0); -} - static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) { struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; @@ -106,9 +95,9 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) if (kvm_timer_should_fire(vtimer)) kvm_timer_update_irq(vcpu, true, vtimer); - if (static_branch_unlikely(&userspace_irqchip_in_use) && - unlikely(!irqchip_in_kernel(vcpu->kvm))) - kvm_vtimer_update_mask_user(vcpu); + if (userspace_irqchip(vcpu->kvm) && + !static_branch_unlikely(&has_gic_active_state)) + disable_percpu_irq(host_vtimer_irq); return IRQ_HANDLED; } @@ -290,8 +279,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq, timer_ctx->irq.level); - if (!static_branch_unlikely(&userspace_irqchip_in_use) || - likely(irqchip_in_kernel(vcpu->kvm))) { + if (!userspace_irqchip(vcpu->kvm)) { ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, timer_ctx->irq.irq, timer_ctx->irq.level, @@ -350,12 +338,6 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) phys_timer_emulate(vcpu); } -static void __timer_snapshot_state(struct arch_timer_context *timer) -{ - timer->cnt_ctl = read_sysreg_el0(cntv_ctl); - timer->cnt_cval = read_sysreg_el0(cntv_cval); -} - static void vtimer_save_state(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; @@ -367,8 +349,10 @@ static void vtimer_save_state(struct kvm_vcpu *vcpu) if (!vtimer->loaded) goto out; - if (timer->enabled) - __timer_snapshot_state(vtimer); + if (timer->enabled) { + vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl); + vtimer->cnt_cval = read_sysreg_el0(cntv_cval); + } /* Disable the virtual timer */ write_sysreg_el0(0, cntv_ctl); @@ -460,23 +444,43 @@ static void set_cntvoff(u64 cntvoff) kvm_call_hyp(__kvm_timer_set_cntvoff, low, high); } -static void kvm_timer_vcpu_load_vgic(struct kvm_vcpu *vcpu) +static inline void set_vtimer_irq_phys_active(struct kvm_vcpu *vcpu, bool active) +{ + int r; + r = irq_set_irqchip_state(host_vtimer_irq, IRQCHIP_STATE_ACTIVE, active); + WARN_ON(r); +} + +static void kvm_timer_vcpu_load_gic(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); bool phys_active; - int ret; - phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq); - - ret = irq_set_irqchip_state(host_vtimer_irq, - IRQCHIP_STATE_ACTIVE, - phys_active); - WARN_ON(ret); + if (irqchip_in_kernel(vcpu->kvm)) + phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq); + else + phys_active = vtimer->irq.level; + set_vtimer_irq_phys_active(vcpu, phys_active); } -static void kvm_timer_vcpu_load_user(struct kvm_vcpu *vcpu) +static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) { - kvm_vtimer_update_mask_user(vcpu); + struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + + /* + * When using a userspace irqchip with the architected timers and a + * host interrupt controller that doesn't support an active state, we + * must still prevent continuously exiting from the guest, and + * therefore mask the physical interrupt by disabling it on the host + * interrupt controller when the virtual level is high, such that the + * guest can make forward progress. Once we detect the output level + * being de-asserted, we unmask the interrupt again so that we exit + * from the guest when the timer fires. + */ + if (vtimer->irq.level) + disable_percpu_irq(host_vtimer_irq); + else + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) @@ -487,10 +491,10 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) if (unlikely(!timer->enabled)) return; - if (unlikely(!irqchip_in_kernel(vcpu->kvm))) - kvm_timer_vcpu_load_user(vcpu); + if (static_branch_likely(&has_gic_active_state)) + kvm_timer_vcpu_load_gic(vcpu); else - kvm_timer_vcpu_load_vgic(vcpu); + kvm_timer_vcpu_load_nogic(vcpu); set_cntvoff(vtimer->cntvoff); @@ -555,18 +559,24 @@ static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { - __timer_snapshot_state(vtimer); - if (!kvm_timer_should_fire(vtimer)) { - kvm_timer_update_irq(vcpu, false, vtimer); - kvm_vtimer_update_mask_user(vcpu); - } + if (!kvm_timer_should_fire(vtimer)) { + kvm_timer_update_irq(vcpu, false, vtimer); + if (static_branch_likely(&has_gic_active_state)) + set_vtimer_irq_phys_active(vcpu, false); + else + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } } void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) { - unmask_vtimer_irq_user(vcpu); + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + if (unlikely(!timer->enabled)) + return; + + if (unlikely(!irqchip_in_kernel(vcpu->kvm))) + unmask_vtimer_irq_user(vcpu); } int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) @@ -753,6 +763,8 @@ int kvm_timer_hyp_init(bool has_gic) kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); goto out_free_irq; } + + static_branch_enable(&has_gic_active_state); } kvm_info("virtual timer IRQ%d\n", host_vtimer_irq); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4501e658e8d6..65dea3ffef68 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -969,8 +969,7 @@ int __kvm_set_memory_region(struct kvm *kvm, /* Check for overlaps */ r = -EEXIST; kvm_for_each_memslot(slot, __kvm_memslots(kvm, as_id)) { - if ((slot->id >= KVM_USER_MEM_SLOTS) || - (slot->id == id)) + if (slot->id == id) continue; if (!((base_gfn + npages <= slot->base_gfn) || (base_gfn >= slot->base_gfn + slot->npages))) |