diff options
Diffstat (limited to 'arch')
386 files changed, 7478 insertions, 2638 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 29b0167c088b..513a29c62a9b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -35,6 +35,7 @@ config KPROBES depends on MODULES depends on HAVE_KPROBES select KALLSYMS + select TASKS_RCU if PREEMPTION help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes @@ -854,10 +855,8 @@ config HAVE_ARCH_HUGE_VMAP # # Archs that select this would be capable of PMD-sized vmaps (i.e., -# arch_vmap_pmd_supported() returns true), and they must make no assumptions -# that vmalloc memory is mapped with PAGE_SIZE ptes. The VM_NO_HUGE_VMAP flag -# can be used to prohibit arch-specific allocations from using hugepages to -# help with this (e.g., modules may require it). +# arch_vmap_pmd_supported() returns true). The VM_ALLOW_HUGE_VMAP flag +# must be used to enable allocations to use hugepages. # config HAVE_ARCH_HUGE_VMALLOC depends on HAVE_ARCH_HUGE_VMAP diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index dcaa44e408ac..f48ba03e9b5e 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -275,7 +275,7 @@ cs-gpios = <&creg_gpio 0 GPIO_ACTIVE_LOW>, <&creg_gpio 1 GPIO_ACTIVE_LOW>; - spi-flash@0 { + flash@0 { compatible = "sst26wf016b", "jedec,spi-nor"; reg = <0>; #address-cells = <1>; diff --git a/arch/arc/include/asm/atomic-llsc.h b/arch/arc/include/asm/atomic-llsc.h index 088d348781c1..1b0ffaeee16d 100644 --- a/arch/arc/include/asm/atomic-llsc.h +++ b/arch/arc/include/asm/atomic-llsc.h @@ -5,7 +5,7 @@ #define arch_atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#define ATOMIC_OP(op, c_op, asm_op) \ +#define ATOMIC_OP(op, asm_op) \ static inline void arch_atomic_##op(int i, atomic_t *v) \ { \ unsigned int val; \ @@ -21,7 +21,7 @@ static inline void arch_atomic_##op(int i, atomic_t *v) \ : "cc"); \ } \ -#define ATOMIC_OP_RETURN(op, c_op, asm_op) \ +#define ATOMIC_OP_RETURN(op, asm_op) \ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ { \ unsigned int val; \ @@ -42,7 +42,7 @@ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ #define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed #define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed -#define ATOMIC_FETCH_OP(op, c_op, asm_op) \ +#define ATOMIC_FETCH_OP(op, asm_op) \ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ { \ unsigned int val, orig; \ @@ -69,23 +69,23 @@ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ #define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed #define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_OP_RETURN(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_OP_RETURN(op, asm_op) \ + ATOMIC_FETCH_OP(op, asm_op) -ATOMIC_OPS(add, +=, add) -ATOMIC_OPS(sub, -=, sub) +ATOMIC_OPS(add, add) +ATOMIC_OPS(sub, sub) #undef ATOMIC_OPS -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_FETCH_OP(op, asm_op) -ATOMIC_OPS(and, &=, and) -ATOMIC_OPS(andnot, &= ~, bic) -ATOMIC_OPS(or, |=, or) -ATOMIC_OPS(xor, ^=, xor) +ATOMIC_OPS(and, and) +ATOMIC_OPS(andnot, bic) +ATOMIC_OPS(or, or) +ATOMIC_OPS(xor, xor) #define arch_atomic_andnot arch_atomic_andnot diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h index 7848348719b2..64ca25d199be 100644 --- a/arch/arc/include/asm/pgtable-levels.h +++ b/arch/arc/include/asm/pgtable-levels.h @@ -98,9 +98,6 @@ /* * 1st level paging: pgd */ -#define pgd_index(addr) ((addr) >> PGDIR_SHIFT) -#define pgd_offset(mm, addr) (((mm)->pgd) + pgd_index(addr)) -#define pgd_offset_k(addr) pgd_offset(&init_mm, addr) #define pgd_ERROR(e) \ pr_crit("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c index 03f8b1be0c3a..1e1db51b6941 100644 --- a/arch/arc/kernel/disasm.c +++ b/arch/arc/kernel/disasm.c @@ -366,7 +366,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state, case op_SP: /* LD_S|LDB_S b,[sp,u7], ST_S|STB_S b,[sp,u7] */ /* note: we are ignoring possibility of: * ADD_S, SUB_S, PUSH_S, POP_S as these should not - * cause unaliged exception anyway */ + * cause unaligned exception anyway */ state->write = BITS(state->words[0], 6, 6); state->zz = BITS(state->words[0], 5, 5); if (state->zz) @@ -503,7 +503,6 @@ int __kprobes disasm_next_pc(unsigned long pc, struct pt_regs *regs, { struct disasm_state instr; - memset(&instr, 0, sizeof(struct disasm_state)); disasm_instr(pc, &instr, 0, regs, cregs); *next_pc = pc + instr.instr_len; diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index dd77a0c8f740..66ba549b520f 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -196,6 +196,7 @@ tracesys_exit: st r0, [sp, PT_r0] ; sys call return value in pt_regs ;POST Sys Call Ptrace Hook + mov r0, sp ; pt_regs needed bl @syscall_trace_exit b ret_from_exception ; NOT ret_from_system_call at is saves r0 which ; we'd done before calling post hook above diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index f748483628f2..3c1590c27fae 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -319,7 +319,7 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) regs->ret = (unsigned long)ksig->ka.sa.sa_handler; /* - * handler returns using sigreturn stub provided already by userpsace + * handler returns using sigreturn stub provided already by userspace * If not, nuke the process right away */ if(!(ksig->ka.sa.sa_flags & SA_RESTORER)) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 78e6d069b1c1..d947473f1e6d 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -35,7 +35,7 @@ EXPORT_SYMBOL_GPL(smp_atomic_ops_lock); struct plat_smp_ops __weak plat_smp_ops; -/* XXX: per cpu ? Only needed once in early seconday boot */ +/* XXX: per cpu ? Only needed once in early secondary boot */ struct task_struct *secondary_idle_tsk; /* Called from start_kernel */ @@ -274,7 +274,7 @@ static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg) * and read back old value */ do { - new = old = READ_ONCE(*ipi_data_ptr); + new = old = *ipi_data_ptr; new |= 1U << msg; } while (cmpxchg(ipi_data_ptr, old, new) != old); diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index d63ebd81f1c6..99a9b92ed98d 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -237,7 +237,7 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, if (state.fault) goto fault; - /* clear any remanants of delay slot */ + /* clear any remnants of delay slot */ if (delay_mode(regs)) { regs->ret = regs->bta & ~1U; regs->status32 &= ~STATUS_DE_MASK; diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 8aa1231865d1..5446967ea98d 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -401,7 +401,7 @@ static inline void __before_dc_op(const int op) { if (op == OP_FLUSH_N_INV) { /* Dcache provides 2 cmd: FLUSH or INV - * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE + * INV in turn has sub-modes: DISCARD or FLUSH-BEFORE * flush-n-inv is achieved by INV cmd but with IM=1 * So toggle INV sub-mode depending on op request and default */ diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index c9629cb5ccd1..7da42a5b959c 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -263,6 +263,8 @@ compatible = "ti,am3359-tscadc"; reg = <0x0 0x1000>; interrupts = <16>; + clocks = <&adc_tsc_fck>; + clock-names = "fck"; status = "disabled"; dmas = <&edma 53 0>, <&edma 57 0>; dma-names = "fifo0", "fifo1"; diff --git a/arch/arm/boot/dts/am3517-evm.dts b/arch/arm/boot/dts/am3517-evm.dts index 0d2fac98ce7d..c8b80f156ec9 100644 --- a/arch/arm/boot/dts/am3517-evm.dts +++ b/arch/arm/boot/dts/am3517-evm.dts @@ -161,6 +161,8 @@ /* HS USB Host PHY on PORT 1 */ hsusb1_phy: hsusb1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb1_rst_pins>; compatible = "usb-nop-xceiv"; reset-gpios = <&gpio2 25 GPIO_ACTIVE_LOW>; /* gpio_57 */ #phy-cells = <0>; @@ -168,7 +170,9 @@ }; &davinci_emac { - status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <ðernet_pins>; + status = "okay"; }; &davinci_mdio { @@ -193,6 +197,8 @@ }; &i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; clock-frequency = <400000>; /* User DIP swithes [1:8] / User LEDS [1:2] */ tca6416: gpio@21 { @@ -205,6 +211,8 @@ }; &i2c3 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins>; clock-frequency = <400000>; }; @@ -223,6 +231,8 @@ }; &usbhshost { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb1_pins>; port1-mode = "ehci-phy"; }; @@ -231,8 +241,35 @@ }; &omap3_pmx_core { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb1_rst_pins>; + + ethernet_pins: pinmux_ethernet_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21fe, PIN_INPUT | MUX_MODE0) /* rmii_mdio_data */ + OMAP3_CORE1_IOPAD(0x2200, MUX_MODE0) /* rmii_mdio_clk */ + OMAP3_CORE1_IOPAD(0x2202, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_rxd0 */ + OMAP3_CORE1_IOPAD(0x2204, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_rxd1 */ + OMAP3_CORE1_IOPAD(0x2206, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_crs_dv */ + OMAP3_CORE1_IOPAD(0x2208, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_rxer */ + OMAP3_CORE1_IOPAD(0x220a, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_txd0 */ + OMAP3_CORE1_IOPAD(0x220c, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_txd1 */ + OMAP3_CORE1_IOPAD(0x220e, PIN_OUTPUT_PULLDOWN |MUX_MODE0) /* rmii_txen */ + OMAP3_CORE1_IOPAD(0x2210, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_50mhz_clk */ + >; + }; + + i2c2_pins: pinmux_i2c2_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21be, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_scl */ + OMAP3_CORE1_IOPAD(0x21c0, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_sda */ + >; + }; + + i2c3_pins: pinmux_i2c3_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21c2, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_scl */ + OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ + >; + }; leds_pins: pinmux_leds_pins { pinctrl-single,pins = < @@ -300,8 +337,6 @@ }; &omap3_pmx_core2 { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb1_pins>; hsusb1_pins: pinmux_hsusb1_pins { pinctrl-single,pins = < diff --git a/arch/arm/boot/dts/am3517-som.dtsi b/arch/arm/boot/dts/am3517-som.dtsi index 8b669e2eafec..f7b680f6c48a 100644 --- a/arch/arm/boot/dts/am3517-som.dtsi +++ b/arch/arm/boot/dts/am3517-som.dtsi @@ -69,6 +69,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <400000>; s35390a: s35390a@30 { @@ -179,6 +181,13 @@ &omap3_pmx_core { + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_sda */ + >; + }; + wl12xx_buffer_pins: pinmux_wl12xx_buffer_pins { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2156, PIN_OUTPUT | MUX_MODE4) /* mmc1_dat7.gpio_129 */ diff --git a/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts b/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts index e71ccfd1df63..ff4c07c69af1 100644 --- a/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts +++ b/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts @@ -100,12 +100,14 @@ lm25066@40 { compatible = "lm25066"; reg = <0x40>; + shunt-resistor-micro-ohms = <1000>; }; /* 12VSB PMIC */ lm25066@41 { compatible = "lm25066"; reg = <0x41>; + shunt-resistor-micro-ohms = <10000>; }; }; @@ -196,7 +198,7 @@ gpio-line-names = /* A */ "LOCATORLED_STATUS_N", "BMC_MAC2_INTB", "NMI_BTN_N", "BMC_NMI", "", "", "", "", - /* B */ "DDR_MEM_TEMP", "", "", "", "", "", "", "", + /* B */ "POST_COMPLETE_N", "", "", "", "", "", "", "", /* C */ "", "", "", "", "PCIE_HP_SEL_N", "PCIE_SATA_SEL_N", "LOCATORBTN", "", /* D */ "BMC_PSIN", "BMC_PSOUT", "BMC_RESETCON", "RESETCON", "", "", "", "PSU_FAN_FAIL_N", diff --git a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi index e4775bbceecc..7cd4f075e325 100644 --- a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi +++ b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi @@ -117,9 +117,9 @@ groups = "FWSPID"; }; - pinctrl_fwqspid_default: fwqspid_default { - function = "FWSPID"; - groups = "FWQSPID"; + pinctrl_fwqspi_default: fwqspi_default { + function = "FWQSPI"; + groups = "FWQSPI"; }; pinctrl_fwspiwp_default: fwspiwp_default { @@ -653,12 +653,12 @@ }; pinctrl_qspi1_default: qspi1_default { - function = "QSPI1"; + function = "SPI1"; groups = "QSPI1"; }; pinctrl_qspi2_default: qspi2_default { - function = "QSPI2"; + function = "SPI2"; groups = "QSPI2"; }; diff --git a/arch/arm/boot/dts/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed-g6.dtsi index 3d5ce9da42c3..9d2a0ce4ca06 100644 --- a/arch/arm/boot/dts/aspeed-g6.dtsi +++ b/arch/arm/boot/dts/aspeed-g6.dtsi @@ -389,6 +389,16 @@ reg = <0x1e6f2000 0x1000>; }; + video: video@1e700000 { + compatible = "aspeed,ast2600-video-engine"; + reg = <0x1e700000 0x1000>; + clocks = <&syscon ASPEED_CLK_GATE_VCLK>, + <&syscon ASPEED_CLK_GATE_ECLK>; + clock-names = "vclk", "eclk"; + interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + gpio0: gpio@1e780000 { #gpio-cells = <2>; gpio-controller; diff --git a/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi b/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi index c1c8650dafce..3542ad8a243e 100644 --- a/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi +++ b/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi @@ -44,7 +44,7 @@ status = "okay"; /* spi0.0: 4M Flash Macronix MX25R4035FM1IL0 */ - spi-flash@0 { + flash@0 { compatible = "mxicy,mx25u4035", "jedec,spi-nor"; spi-max-frequency = <33000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-q5xr5.dts b/arch/arm/boot/dts/at91-q5xr5.dts index 47a00062f01f..9cf60b6f695c 100644 --- a/arch/arm/boot/dts/at91-q5xr5.dts +++ b/arch/arm/boot/dts/at91-q5xr5.dts @@ -125,7 +125,7 @@ cs-gpios = <&pioA 3 GPIO_ACTIVE_HIGH>, <&pioC 11 GPIO_ACTIVE_LOW>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "jedec,spi-nor"; spi-max-frequency = <20000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sam9_l9260.dts b/arch/arm/boot/dts/at91-sam9_l9260.dts index 1e2a28c2f365..2fb51b9aca2a 100644 --- a/arch/arm/boot/dts/at91-sam9_l9260.dts +++ b/arch/arm/boot/dts/at91-sam9_l9260.dts @@ -101,7 +101,7 @@ nand0: nand@40000000 { nand-bus-width = <8>; nand-ecc-mode = "soft"; - nand-on-flash-bbt = <1>; + nand-on-flash-bbt; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi index 21c86171e462..ba621783acdb 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi @@ -214,7 +214,7 @@ pinctrl-0 = <&pinctrl_qspi1_default>; status = "disabled"; - qspi1_flash: spi_flash@0 { + qspi1_flash: flash@0 { #address-cells = <1>; #size-cells = <1>; compatible = "jedec,spi-nor"; diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts index c145c4e5ef58..5e8755f22784 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts @@ -191,7 +191,7 @@ &qspi1 { status = "okay"; - qspi1_flash: spi_flash@0 { + qspi1_flash: flash@0 { status = "okay"; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index 9bf2ec0ba3e2..cdfe891f9a9e 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -137,7 +137,7 @@ pinctrl-0 = <&pinctrl_spi0_default>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; reg = <0>; spi-max-frequency = <50000000>; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index d72c042f2850..a49c2966b41e 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -57,8 +57,8 @@ }; spi0: spi@f0004000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi0_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi0_cs>; cs-gpios = <&pioD 13 0>, <0>, <0>, <&pioD 16 0>; status = "okay"; }; @@ -171,8 +171,8 @@ }; spi1: spi@f8008000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi1_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi1_cs>; cs-gpios = <&pioC 25 0>; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi index 710cb72bda5a..fd1086f52b40 100644 --- a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi +++ b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi @@ -49,7 +49,7 @@ cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index d241c24f0d83..e519d2747936 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -81,8 +81,8 @@ }; spi1: spi@fc018000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi0_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi1_cs>; cs-gpios = <&pioB 21 0>; status = "okay"; }; @@ -140,7 +140,7 @@ atmel,pins = <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; }; - pinctrl_spi0_cs: spi0_cs_default { + pinctrl_spi1_cs: spi1_cs_default { atmel,pins = <AT91_PIOB 21 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index fe432b6b7e95..7017f626f362 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -65,7 +65,7 @@ spi0: spi@f8010000 { cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sama7g5ek.dts b/arch/arm/boot/dts/at91-sama7g5ek.dts index 08685a10eda1..d83f76a6cd6a 100644 --- a/arch/arm/boot/dts/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/at91-sama7g5ek.dts @@ -495,7 +495,7 @@ pinctrl_flx3_default: flx3_default { pinmux = <PIN_PD16__FLEXCOM3_IO0>, <PIN_PD17__FLEXCOM3_IO1>; - bias-disable; + bias-pull-up; }; pinctrl_flx4_default: flx4_default { @@ -655,7 +655,7 @@ <PIN_PB21__QSPI0_INT>; bias-disable; slew-rate = <0>; - atmel,drive-strength = <ATMEL_PIO_DRVSTR_HI>; + atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>; }; pinctrl_sdmmc0_default: sdmmc0_default { diff --git a/arch/arm/boot/dts/at91-vinco.dts b/arch/arm/boot/dts/at91-vinco.dts index a51a3372afa1..ebeaa6ab500e 100644 --- a/arch/arm/boot/dts/at91-vinco.dts +++ b/arch/arm/boot/dts/at91-vinco.dts @@ -59,7 +59,7 @@ spi0: spi@f8010000 { cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "n25q32b", "jedec,spi-nor"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91rm9200ek.dts b/arch/arm/boot/dts/at91rm9200ek.dts index e1ef4e44e663..4624a6f076f8 100644 --- a/arch/arm/boot/dts/at91rm9200ek.dts +++ b/arch/arm/boot/dts/at91rm9200ek.dts @@ -73,7 +73,7 @@ spi0: spi@fffe0000 { status = "okay"; cs-gpios = <&pioA 3 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <15000000>; reg = <0>; @@ -94,7 +94,7 @@ status = "okay"; }; - nor_flash@10000000 { + flash@10000000 { compatible = "cfi-flash"; reg = <0x10000000 0x800000>; linux,mtd-name = "physmap-flash.0"; diff --git a/arch/arm/boot/dts/at91sam9260ek.dts b/arch/arm/boot/dts/at91sam9260ek.dts index ce96345d28a3..6381088ba24f 100644 --- a/arch/arm/boot/dts/at91sam9260ek.dts +++ b/arch/arm/boot/dts/at91sam9260ek.dts @@ -92,7 +92,7 @@ spi0: spi@fffc8000 { cs-gpios = <0>, <&pioC 11 0>, <0>, <0>; - mtd_dataflash@1 { + flash@1 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <1>; diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts index beed819609e8..8f11c0b7d76d 100644 --- a/arch/arm/boot/dts/at91sam9261ek.dts +++ b/arch/arm/boot/dts/at91sam9261ek.dts @@ -145,7 +145,7 @@ cs-gpios = <&pioA 3 0>, <0>, <&pioA 28 0>, <0>; status = "okay"; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; reg = <0>; spi-max-frequency = <15000000>; diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts index 71f60576761a..42e734020235 100644 --- a/arch/arm/boot/dts/at91sam9263ek.dts +++ b/arch/arm/boot/dts/at91sam9263ek.dts @@ -95,7 +95,7 @@ spi0: spi@fffa4000 { status = "okay"; cs-gpios = <&pioA 5 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi index 87bb39060e8b..85c17dd1c8d5 100644 --- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi +++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi @@ -110,7 +110,7 @@ spi0: spi@fffc8000 { cs-gpios = <0>, <&pioC 11 0>, <0>, <0>; - mtd_dataflash@1 { + flash@1 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <1>; @@ -214,11 +214,23 @@ 24c512@50 { compatible = "atmel,24c512"; reg = <0x50>; + vcc-supply = <®_3v3>; }; wm8731: wm8731@1b { compatible = "wm8731"; reg = <0x1b>; + + /* PCK0 at 12MHz */ + clocks = <&pmc PMC_TYPE_SYSTEM 8>; + clock-names = "mclk"; + assigned-clocks = <&pmc PMC_TYPE_SYSTEM 8>; + assigned-clock-rates = <12000000>; + + HPVDD-supply = <&vcc_dac>; + AVDD-supply = <&vcc_dac>; + DCVDD-supply = <®_3v3>; + DBVDD-supply = <®_3v3>; }; }; @@ -254,4 +266,35 @@ atmel,ssc-controller = <&ssc0>; atmel,audio-codec = <&wm8731>; }; + + reg_5v: fixedregulator0 { + compatible = "regulator-fixed"; + regulator-name = "5V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + reg_3v3: fixedregulator1 { + compatible = "regulator-fixed"; + regulator-name = "3V3"; + vin-supply = <®_5v>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_1v: fixedregulator2 { + compatible = "regulator-fixed"; + regulator-name = "1V"; + vin-supply = <®_5v>; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; + }; + + vcc_dac: fixedregulator3 { + compatible = "regulator-fixed"; + regulator-name = "VCC_DAC"; + vin-supply = <®_3v3>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; }; diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts index b6256a20fbc7..e5db198a87a8 100644 --- a/arch/arm/boot/dts/at91sam9m10g45ek.dts +++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts @@ -167,7 +167,7 @@ spi0: spi@fffa4000{ status = "okay"; cs-gpios = <&pioB 3 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <13000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index 2bc4e6e0a923..c905d7bfc771 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -119,7 +119,7 @@ spi0: spi@f0000000 { status = "okay"; cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts index 62981b39c815..d74b8d9d84aa 100644 --- a/arch/arm/boot/dts/at91sam9rlek.dts +++ b/arch/arm/boot/dts/at91sam9rlek.dts @@ -180,7 +180,7 @@ spi0: spi@fffcc000 { status = "okay"; cs-gpios = <&pioA 28 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <15000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi index 6d1264de6060..5f4eaa618ab4 100644 --- a/arch/arm/boot/dts/at91sam9x5ek.dtsi +++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi @@ -125,7 +125,7 @@ cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; status = "disabled"; /* conflicts with mmc1 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts index 87c517d65f62..e9aecac4f5b5 100644 --- a/arch/arm/boot/dts/da850-evm.dts +++ b/arch/arm/boot/dts/da850-evm.dts @@ -278,7 +278,7 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&spi1_pins &spi1_cs0_pin>; - flash: m25p80@0 { + flash: flash@0 { #address-cells = <1>; #size-cells = <1>; compatible = "jedec,spi-nor"; diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts index 5126e2d72ed7..778796c10af8 100644 --- a/arch/arm/boot/dts/dm8168-evm.dts +++ b/arch/arm/boot/dts/dm8168-evm.dts @@ -177,7 +177,7 @@ pinctrl-names = "default"; pinctrl-0 = <&mcspi1_pins>; - m25p80@0 { + flash@0 { compatible = "w25x32"; spi-max-frequency = <48000000>; reg = <0>; diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index 0a11bacffc1f..5733e3a4ea8e 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -4188,11 +4188,11 @@ reg = <0x1d0010 0x4>; reg-names = "sysc"; ti,sysc-midle = <SYSC_IDLE_FORCE>, - <SYSC_IDLE_NO>, - <SYSC_IDLE_SMART>; + <SYSC_IDLE_NO>; ti,sysc-sidle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>; + power-domains = <&prm_vpe>; clocks = <&vpe_clkctrl DRA7_VPE_VPE_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/imx28-ts4600.dts b/arch/arm/boot/dts/imx28-ts4600.dts index 097ec35c62d8..0d58da1c0cc5 100644 --- a/arch/arm/boot/dts/imx28-ts4600.dts +++ b/arch/arm/boot/dts/imx28-ts4600.dts @@ -26,7 +26,7 @@ pinctrl-0 = <&mmc0_4bit_pins_a &mmc0_sck_cfg &en_sd_pwr>; - broken-cd = <1>; + broken-cd; bus-width = <4>; vmmc-supply = <®_vddio_sd0>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/imx6qdl-apalis.dtsi index ed2739e39085..bd763bae596b 100644 --- a/arch/arm/boot/dts/imx6qdl-apalis.dtsi +++ b/arch/arm/boot/dts/imx6qdl-apalis.dtsi @@ -286,6 +286,8 @@ codec: sgtl5000@a { compatible = "fsl,sgtl5000"; reg = <0x0a>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_sgtl5000>; clocks = <&clks IMX6QDL_CLK_CKO>; VDDA-supply = <®_module_3v3_audio>; VDDIO-supply = <®_module_3v3>; @@ -517,8 +519,6 @@ MX6QDL_PAD_DISP0_DAT21__AUD4_TXD 0x130b0 MX6QDL_PAD_DISP0_DAT22__AUD4_TXFS 0x130b0 MX6QDL_PAD_DISP0_DAT23__AUD4_RXD 0x130b0 - /* SGTL5000 sys_mclk */ - MX6QDL_PAD_GPIO_5__CCM_CLKO1 0x130b0 >; }; @@ -811,6 +811,12 @@ >; }; + pinctrl_sgtl5000: sgtl5000grp { + fsl,pins = < + MX6QDL_PAD_GPIO_5__CCM_CLKO1 0x130b0 + >; + }; + pinctrl_spdif: spdifgrp { fsl,pins = < MX6QDL_PAD_GPIO_16__SPDIF_IN 0x1b0b0 diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi index 563bf9d44fe0..0b90c3f59f89 100644 --- a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi @@ -154,112 +154,112 @@ regulators { bcore1 { regulator-name = "bcore1"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bcore2 { regulator-name = "bcore2"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bpro { regulator-name = "bpro"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bperi { regulator-name = "bperi"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bmem { regulator-name = "bmem"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo2 { regulator-name = "ldo2"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1800000>; }; ldo3 { regulator-name = "ldo3"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo4 { regulator-name = "ldo4"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo5 { regulator-name = "ldo5"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo6 { regulator-name = "ldo6"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo7 { regulator-name = "ldo7"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo8 { regulator-name = "ldo8"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo9 { regulator-name = "ldo9"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo10 { regulator-name = "ldo10"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo11 { regulator-name = "ldo11"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bio { regulator-name = "bio"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; diff --git a/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi b/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi index 7cda6944501d..205e4d462702 100644 --- a/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi +++ b/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi @@ -72,8 +72,8 @@ st,settling = <2>; st,fraction-z = <7>; st,i-drive = <1>; - touchscreen-inverted-x = <1>; - touchscreen-inverted-y = <1>; + touchscreen-inverted-x; + touchscreen-inverted-y; }; }; }; diff --git a/arch/arm/boot/dts/imx6ull-colibri.dtsi b/arch/arm/boot/dts/imx6ull-colibri.dtsi index 7f35a06dff95..951a2a6c5a65 100644 --- a/arch/arm/boot/dts/imx6ull-colibri.dtsi +++ b/arch/arm/boot/dts/imx6ull-colibri.dtsi @@ -37,7 +37,7 @@ reg_sd1_vmmc: regulator-sd1-vmmc { compatible = "regulator-gpio"; - gpio = <&gpio5 9 GPIO_ACTIVE_HIGH>; + gpios = <&gpio5 9 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_snvs_reg_sd>; regulator-always-on; diff --git a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts index 2a0a98fe67f0..3240c67e0c39 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts @@ -11,3 +11,18 @@ model = "LogicPD Zoom OMAP35xx SOM-LV Development Kit"; compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3430", "ti,omap3"; }; + +&omap3_pmx_core2 { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb2_2_pins>; + hsusb2_2_pins: pinmux_hsusb2_2_pins { + pinctrl-single,pins = < + OMAP3430_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ + OMAP3430_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ + OMAP3430_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ + OMAP3430_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ + OMAP3430_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ + OMAP3430_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ + >; + }; +}; diff --git a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts index a604d92221a4..c757f0d7781c 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts @@ -11,3 +11,18 @@ model = "LogicPD Zoom DM3730 SOM-LV Development Kit"; compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3630", "ti,omap3"; }; + +&omap3_pmx_core2 { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb2_2_pins>; + hsusb2_2_pins: pinmux_hsusb2_2_pins { + pinctrl-single,pins = < + OMAP3630_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ + OMAP3630_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ + OMAP3630_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ + OMAP3630_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ + OMAP3630_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ + OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ + >; + }; +}; diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index b56524cc7fe2..55b619c99e24 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -265,21 +265,6 @@ }; }; -&omap3_pmx_core2 { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb2_2_pins>; - hsusb2_2_pins: pinmux_hsusb2_2_pins { - pinctrl-single,pins = < - OMAP3630_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ - OMAP3630_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ - OMAP3630_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ - OMAP3630_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ - OMAP3630_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ - OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ - >; - }; -}; - &uart2 { interrupts-extended = <&intc 73 &omap3_pmx_core OMAP3_UART2_RX>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi index b4664ab00256..d3da8b1b473b 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi @@ -118,8 +118,8 @@ gpmc,device-width = <2>; gpmc,wait-pin = <0>; gpmc,burst-length = <4>; - gpmc,cycle2cycle-samecsen = <1>; - gpmc,cycle2cycle-diffcsen = <1>; + gpmc,cycle2cycle-samecsen; + gpmc,cycle2cycle-diffcsen; gpmc,cs-on-ns = <0>; gpmc,cs-rd-off-ns = <45>; gpmc,cs-wr-off-ns = <45>; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index 7e3d8147e2c1..0365f06165e9 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -31,6 +31,8 @@ aliases { display0 = &lcd; display1 = &tv0; + /delete-property/ mmc2; + /delete-property/ mmc3; }; ldo_3v3: fixedregulator { diff --git a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi index cbe42c4153a0..b4d286a6fab1 100644 --- a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi @@ -76,7 +76,7 @@ pinconf { pins = "gpio20", "gpio21"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -116,7 +116,7 @@ pinconf { pins = "gpio24", "gpio25"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -141,7 +141,7 @@ pinconf { pins = "gpio8", "gpio9"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -166,7 +166,7 @@ pinconf { pins = "gpio12", "gpio13"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -229,7 +229,7 @@ pinconf { pins = "gpio16", "gpio17"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -282,7 +282,7 @@ pinconf { pins = "gpio84", "gpio85"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm/boot/dts/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom-ipq8064.dtsi index 996f4458d9fc..8cb04aa8ed2f 100644 --- a/arch/arm/boot/dts/qcom-ipq8064.dtsi +++ b/arch/arm/boot/dts/qcom-ipq8064.dtsi @@ -972,7 +972,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -996,7 +996,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -1020,7 +1020,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -1044,7 +1044,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; diff --git a/arch/arm/boot/dts/sama5d3xmb.dtsi b/arch/arm/boot/dts/sama5d3xmb.dtsi index a499de8a7a64..3652c9e24124 100644 --- a/arch/arm/boot/dts/sama5d3xmb.dtsi +++ b/arch/arm/boot/dts/sama5d3xmb.dtsi @@ -26,7 +26,7 @@ spi0: spi@f0004000 { dmas = <0>, <0>; /* Do not use DMA for spi0 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi index fa9e5e2a745d..5d9e97fecf83 100644 --- a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi +++ b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi @@ -25,7 +25,7 @@ spi0: spi@f0004000 { dmas = <0>, <0>; /* Do not use DMA for spi0 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/sama7g5.dtsi b/arch/arm/boot/dts/sama7g5.dtsi index 4decd3a91a76..f691c8f08d04 100644 --- a/arch/arm/boot/dts/sama7g5.dtsi +++ b/arch/arm/boot/dts/sama7g5.dtsi @@ -601,9 +601,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 39>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(7)>, - <&dma0 AT91_XDMAC_DT_PERID(8)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(8)>, + <&dma0 AT91_XDMAC_DT_PERID(7)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; @@ -786,9 +786,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 46>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(21)>, - <&dma0 AT91_XDMAC_DT_PERID(22)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(22)>, + <&dma0 AT91_XDMAC_DT_PERID(21)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; @@ -810,9 +810,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 47>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(23)>, - <&dma0 AT91_XDMAC_DT_PERID(24)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(24)>, + <&dma0 AT91_XDMAC_DT_PERID(23)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/spear1310-evb.dts b/arch/arm/boot/dts/spear1310-evb.dts index 4cbadcb41084..ddd1cf4d0554 100644 --- a/arch/arm/boot/dts/spear1310-evb.dts +++ b/arch/arm/boot/dts/spear1310-evb.dts @@ -379,7 +379,7 @@ }; }; - m25p80@1 { + flash@1 { compatible = "st,m25p80"; reg = <1>; spi-max-frequency = <12000000>; diff --git a/arch/arm/boot/dts/spear1340-evb.dts b/arch/arm/boot/dts/spear1340-evb.dts index fd194ebeedc9..3a51a41eb5e4 100644 --- a/arch/arm/boot/dts/spear1340-evb.dts +++ b/arch/arm/boot/dts/spear1340-evb.dts @@ -439,7 +439,7 @@ cs-gpios = <&gpiopinctrl 80 0>, <&gpiopinctrl 24 0>, <&gpiopinctrl 85 0>; - m25p80@0 { + flash@0 { compatible = "m25p80"; reg = <0>; spi-max-frequency = <12000000>; diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index 33ae5e0590df..ac53ee3c496b 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -398,7 +398,7 @@ #size-cells = <0>; status = "okay"; - flash0: is25lp016d@0 { + flash0: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <133000000>; diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts index e222d2d2cb44..d142dd30e16b 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts @@ -262,7 +262,7 @@ #size-cells = <0>; status = "okay"; - flash0: mx66l51235l@0 { + flash0: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-rx-bus-width = <4>; @@ -271,7 +271,7 @@ #size-cells = <1>; }; - flash1: mx66l51235l@1 { + flash1: flash@1 { compatible = "jedec,spi-nor"; reg = <1>; spi-rx-bus-width = <4>; diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts index 8a0cfbfd0c45..b6cb9cdf8197 100644 --- a/arch/arm/boot/dts/usb_a9263.dts +++ b/arch/arm/boot/dts/usb_a9263.dts @@ -60,7 +60,7 @@ spi0: spi@fffa4000 { cs-gpios = <&pioB 15 GPIO_ACTIVE_HIGH>; status = "okay"; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; reg = <0>; spi-max-frequency = <15000000>; diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig index a7acfee11ffc..a80bc8a43091 100644 --- a/arch/arm/configs/gemini_defconfig +++ b/arch/arm/configs/gemini_defconfig @@ -49,11 +49,13 @@ CONFIG_ATA=y CONFIG_PATA_FTIDE010=y CONFIG_NETDEVICES=y CONFIG_TUN=y +CONFIG_NET_DSA_REALTEK=y CONFIG_NET_DSA_REALTEK_SMI=y +CONFIG_NET_DSA_REALTEK_RTL8366RB=y CONFIG_GEMINI_ETHERNET=y +CONFIG_MARVELL_PHY=y CONFIG_MDIO_BITBANG=y CONFIG_MDIO_GPIO=y -CONFIG_MARVELL_PHY=y CONFIG_INPUT_EVDEV=y CONFIG_KEYBOARD_GPIO=y # CONFIG_INPUT_MOUSE is not set @@ -66,6 +68,7 @@ CONFIG_SERIAL_OF_PLATFORM=y CONFIG_I2C_GPIO=y CONFIG_SPI=y CONFIG_SPI_GPIO=y +CONFIG_SENSORS_DRIVETEMP=y CONFIG_SENSORS_GPIO_FAN=y CONFIG_SENSORS_LM75=y CONFIG_THERMAL=y diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig deleted file mode 100644 index 015b7ef237de..000000000000 --- a/arch/arm/configs/imote2_defconfig +++ /dev/null @@ -1,365 +0,0 @@ -# CONFIG_LOCALVERSION_AUTO is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_RD_BZIP2=y -CONFIG_RD_LZMA=y -CONFIG_EXPERT=y -# CONFIG_COMPAT_BRK is not set -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_MODVERSIONS=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_ARCH_PXA=y -CONFIG_MACH_INTELMOTE2=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_PREEMPT=y -CONFIG_AEABI=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="root=/dev/mtdblock2 rootfstype=jffs2 console=ttyS2,115200 mem=32M" -CONFIG_KEXEC=y -CONFIG_FPE_NWFPE=y -CONFIG_BINFMT_AOUT=m -CONFIG_BINFMT_MISC=m -CONFIG_PM=y -CONFIG_APM_EMULATION=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_IP_PNP_RARP=y -CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_DIAG is not set -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_IPV6_MIP6=m -CONFIG_IPV6_TUNNEL=m -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IPV6_SUBTREES=y -CONFIG_NETFILTER=y -CONFIG_NETFILTER_NETLINK_QUEUE=m -CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_SCTP=y -CONFIG_NF_CT_PROTO_UDPLITE=y -CONFIG_NF_CONNTRACK_AMANDA=m -CONFIG_NF_CONNTRACK_FTP=m -CONFIG_NF_CONNTRACK_H323=m -CONFIG_NF_CONNTRACK_IRC=m -CONFIG_NF_CONNTRACK_NETBIOS_NS=m -CONFIG_NF_CONNTRACK_PPTP=m -CONFIG_NF_CONNTRACK_SANE=m -CONFIG_NF_CONNTRACK_SIP=m -CONFIG_NF_CONNTRACK_TFTP=m -CONFIG_NF_CT_NETLINK=m -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m -CONFIG_NETFILTER_XT_TARGET_LED=m -CONFIG_NETFILTER_XT_TARGET_MARK=m -CONFIG_NETFILTER_XT_TARGET_NFLOG=m -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_COMMENT=m -CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m -CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m -CONFIG_NETFILTER_XT_MATCH_CONNMARK=m -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m -CONFIG_NETFILTER_XT_MATCH_DCCP=m -CONFIG_NETFILTER_XT_MATCH_DSCP=m -CONFIG_NETFILTER_XT_MATCH_ESP=m -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m -CONFIG_NETFILTER_XT_MATCH_HELPER=m -CONFIG_NETFILTER_XT_MATCH_LENGTH=m -CONFIG_NETFILTER_XT_MATCH_LIMIT=m -CONFIG_NETFILTER_XT_MATCH_MAC=m -CONFIG_NETFILTER_XT_MATCH_MARK=m -CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m -CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m -CONFIG_NETFILTER_XT_MATCH_QUOTA=m -CONFIG_NETFILTER_XT_MATCH_REALM=m -CONFIG_NETFILTER_XT_MATCH_SCTP=m -CONFIG_NETFILTER_XT_MATCH_STATE=m -CONFIG_NETFILTER_XT_MATCH_STATISTIC=m -CONFIG_NETFILTER_XT_MATCH_STRING=m -CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_TIME=m -CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_ADDRTYPE=m -CONFIG_IP_NF_MATCH_AH=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_LOG=m -CONFIG_NF_NAT=m -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_TARGET_NETMAP=m -CONFIG_IP_NF_TARGET_REDIRECT=m -CONFIG_NF_NAT_SNMP_BASIC=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m -CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_ARPTABLES=m -CONFIG_IP_NF_ARPFILTER=m -CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_MATCH_AH=m -CONFIG_IP6_NF_MATCH_EUI64=m -CONFIG_IP6_NF_MATCH_FRAG=m -CONFIG_IP6_NF_MATCH_OPTS=m -CONFIG_IP6_NF_MATCH_HL=m -CONFIG_IP6_NF_MATCH_IPV6HEADER=m -CONFIG_IP6_NF_MATCH_MH=m -CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_FILTER=m -CONFIG_IP6_NF_TARGET_REJECT=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_RAW=m -CONFIG_BRIDGE=m -# CONFIG_BRIDGE_IGMP_SNOOPING is not set -CONFIG_IEEE802154=y -# CONFIG_WIRELESS is not set -CONFIG_DEVTMPFS=y -CONFIG_DEVTMPFS_MOUNT=y -CONFIG_FW_LOADER=m -CONFIG_CONNECTOR=m -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_AFS_PARTS=y -CONFIG_MTD_AR7_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_ADV_OPTIONS=y -CONFIG_MTD_CFI_GEOMETRY=y -# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_4 is not set -# CONFIG_MTD_CFI_I2 is not set -CONFIG_MTD_OTP=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PXA2XX=y -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y -CONFIG_NETDEVICES=y -CONFIG_DUMMY=y -# CONFIG_WLAN is not set -CONFIG_PPP=m -CONFIG_PPP_MULTILINK=y -CONFIG_PPP_FILTER=y -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPP_BSDCOMP=m -# CONFIG_INPUT_MOUSEDEV is not set -CONFIG_INPUT_EVDEV=y -# CONFIG_KEYBOARD_ATKBD is not set -CONFIG_KEYBOARD_GPIO=y -CONFIG_KEYBOARD_PXA27x=y -# CONFIG_INPUT_MOUSE is not set -CONFIG_INPUT_TOUCHSCREEN=y -CONFIG_INPUT_MISC=y -CONFIG_INPUT_UINPUT=y -# CONFIG_SERIO is not set -CONFIG_SERIAL_PXA=y -CONFIG_SERIAL_PXA_CONSOLE=y -CONFIG_LEGACY_PTY_COUNT=8 -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_PXA=y -CONFIG_SPI=y -CONFIG_SPI_PXA2XX=y -CONFIG_GPIO_SYSFS=y -CONFIG_POWER_SUPPLY=y -# CONFIG_HWMON is not set -CONFIG_PMIC_DA903X=y -CONFIG_REGULATOR=y -CONFIG_REGULATOR_DEBUG=y -CONFIG_REGULATOR_DA903X=y -CONFIG_MEDIA_SUPPORT=y -CONFIG_VIDEO_DEV=y -CONFIG_MEDIA_TUNER_CUSTOMISE=y -# CONFIG_MEDIA_TUNER_SIMPLE is not set -# CONFIG_MEDIA_TUNER_TDA8290 is not set -# CONFIG_MEDIA_TUNER_TDA827X is not set -# CONFIG_MEDIA_TUNER_TDA18271 is not set -# CONFIG_MEDIA_TUNER_TDA9887 is not set -# CONFIG_MEDIA_TUNER_TEA5761 is not set -# CONFIG_MEDIA_TUNER_TEA5767 is not set -# CONFIG_MEDIA_TUNER_MT20XX is not set -# CONFIG_MEDIA_TUNER_MT2060 is not set -# CONFIG_MEDIA_TUNER_MT2266 is not set -# CONFIG_MEDIA_TUNER_MT2131 is not set -# CONFIG_MEDIA_TUNER_QT1010 is not set -# CONFIG_MEDIA_TUNER_XC2028 is not set -# CONFIG_MEDIA_TUNER_XC5000 is not set -# CONFIG_MEDIA_TUNER_MXL5005S is not set -# CONFIG_MEDIA_TUNER_MXL5007T is not set -# CONFIG_MEDIA_TUNER_MC44S803 is not set -# CONFIG_VIDEO_HELPER_CHIPS_AUTO is not set -CONFIG_VIDEO_PXA27x=y -# CONFIG_V4L_USB_DRIVERS is not set -# CONFIG_RADIO_ADAPTERS is not set -CONFIG_FB=y -CONFIG_FB_PXA=y -CONFIG_FB_PXA_OVERLAY=y -CONFIG_FB_PXA_PARAMETERS=y -# CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_BACKLIGHT_CLASS_DEVICE=y -# CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_FONTS=y -CONFIG_FONT_MINI_4x6=y -CONFIG_SOUND=y -CONFIG_SND=y -CONFIG_SND_MIXER_OSS=y -CONFIG_SND_PCM_OSS=y -# CONFIG_SND_DRIVERS is not set -# CONFIG_SND_ARM is not set -# CONFIG_SND_SPI is not set -# CONFIG_SND_USB is not set -CONFIG_SND_SOC=y -CONFIG_SND_PXA2XX_SOC=y -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_GADGET=y -CONFIG_USB_PXA27X=y -CONFIG_USB_ETH=m -# CONFIG_USB_ETH_RNDIS is not set -CONFIG_MMC=y -CONFIG_SDIO_UART=m -CONFIG_MMC_PXA=y -CONFIG_MMC_SPI=y -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=y -CONFIG_LEDS_LP3944=y -CONFIG_LEDS_TRIGGERS=y -CONFIG_LEDS_TRIGGER_TIMER=y -CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_LEDS_TRIGGER_BACKLIGHT=y -CONFIG_LEDS_TRIGGER_GPIO=y -CONFIG_LEDS_TRIGGER_DEFAULT_ON=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_PXA=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=m -CONFIG_AUTOFS4_FS=y -CONFIG_FUSE_FS=m -CONFIG_CUSE=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y -CONFIG_JFFS2_FS_WBUF_VERIFY=y -CONFIG_JFFS2_SUMMARY=y -CONFIG_JFFS2_FS_XATTR=y -CONFIG_JFFS2_COMPRESSION_OPTIONS=y -CONFIG_JFFS2_LZO=y -CONFIG_JFFS2_RUBIN=y -CONFIG_CRAMFS=m -CONFIG_SQUASHFS=m -CONFIG_ROMFS_FS=m -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V3_ACL=y -CONFIG_NFSD=m -CONFIG_NFSD_V3_ACL=y -CONFIG_SMB_FS=m -CONFIG_CIFS=m -CONFIG_CIFS_STATS=y -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_CODEPAGE_737=m -CONFIG_NLS_CODEPAGE_775=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_852=m -CONFIG_NLS_CODEPAGE_855=m -CONFIG_NLS_CODEPAGE_857=m -CONFIG_NLS_CODEPAGE_860=m -CONFIG_NLS_CODEPAGE_861=m -CONFIG_NLS_CODEPAGE_862=m -CONFIG_NLS_CODEPAGE_863=m -CONFIG_NLS_CODEPAGE_864=m -CONFIG_NLS_CODEPAGE_865=m -CONFIG_NLS_CODEPAGE_866=m -CONFIG_NLS_CODEPAGE_869=m -CONFIG_NLS_CODEPAGE_936=m -CONFIG_NLS_CODEPAGE_950=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_CODEPAGE_949=m -CONFIG_NLS_CODEPAGE_874=m -CONFIG_NLS_ISO8859_8=m -CONFIG_NLS_CODEPAGE_1250=m -CONFIG_NLS_CODEPAGE_1251=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_KOI8_R=m -CONFIG_NLS_KOI8_U=m -CONFIG_NLS_UTF8=m -CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y -# CONFIG_SCHED_DEBUG is not set -CONFIG_DEBUG_RT_MUTEXES=y -CONFIG_PROVE_LOCKING=y -# CONFIG_FTRACE is not set -CONFIG_DEBUG_USER=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_XTS=m -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_GHASH=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_AES=m -CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SEED=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRC16=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 6e0c8c19b35c..d6a6811f0539 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -673,6 +673,7 @@ CONFIG_VIDEO_STI_DELTA=m CONFIG_VIDEO_RENESAS_FDP1=m CONFIG_VIDEO_RENESAS_JPU=m CONFIG_VIDEO_RENESAS_VSP1=m +CONFIG_VIDEO_TEGRA_VDE=m CONFIG_V4L_TEST_DRIVERS=y CONFIG_VIDEO_VIVID=m CONFIG_VIDEO_ADV7180=m diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig index 289d022acc4b..c209722399d7 100644 --- a/arch/arm/configs/tegra_defconfig +++ b/arch/arm/configs/tegra_defconfig @@ -286,7 +286,8 @@ CONFIG_SERIO_NVEC_PS2=y CONFIG_NVEC_POWER=y CONFIG_NVEC_PAZ00=y CONFIG_STAGING_MEDIA=y -CONFIG_TEGRA_VDE=y +CONFIG_V4L_MEM2MEM_DRIVERS=y +CONFIG_VIDEO_TEGRA_VDE=y CONFIG_CHROME_PLATFORMS=y CONFIG_CROS_EC=y CONFIG_CROS_EC_I2C=m diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index 3b30913d7d8d..a352207a64d7 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -20,7 +20,6 @@ CONFIG_VFP=y CONFIG_NEON=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y CONFIG_CMA=y CONFIG_NET=y @@ -41,6 +40,8 @@ CONFIG_MAC80211_LEDS=y CONFIG_CAIF=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y +CONFIG_GNSS=y +CONFIG_GNSS_SIRF_SERIAL=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_NETDEVICES=y @@ -83,6 +84,8 @@ CONFIG_SPI_GPIO=y CONFIG_SPI_PL022=y CONFIG_GPIO_STMPE=y CONFIG_GPIO_TC3589X=y +CONFIG_BATTERY_SAMSUNG_SDI=y +CONFIG_AB8500_BM=y CONFIG_SENSORS_IIO_HWMON=y CONFIG_SENSORS_NTC_THERMISTOR=y CONFIG_THERMAL=y @@ -98,10 +101,13 @@ CONFIG_VIDEO_V4L2_SUBDEV_API=y CONFIG_V4L2_FLASH_LED_CLASS=y CONFIG_DRM=y CONFIG_DRM_PANEL_NOVATEK_NT35510=y +CONFIG_DRM_PANEL_NOVATEK_NT35560=y +CONFIG_DRM_PANEL_SAMSUNG_DB7430=y CONFIG_DRM_PANEL_SAMSUNG_S6D16D0=y +CONFIG_DRM_PANEL_SAMSUNG_S6D27A1=y CONFIG_DRM_PANEL_SAMSUNG_S6E63M0=y CONFIG_DRM_PANEL_SAMSUNG_S6E63M0_DSI=y -CONFIG_DRM_PANEL_SONY_ACX424AKP=y +CONFIG_DRM_PANEL_WIDECHIPS_WS2401=y CONFIG_DRM_LIMA=y CONFIG_DRM_MCDE=y CONFIG_FB=y @@ -129,6 +135,7 @@ CONFIG_LEDS_LM3530=y CONFIG_LEDS_GPIO=y CONFIG_LEDS_LP55XX_COMMON=y CONFIG_LEDS_LP5521=y +CONFIG_LEDS_REGULATOR=y CONFIG_LEDS_RT8515=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_RTC_CLASS=y @@ -144,17 +151,22 @@ CONFIG_IIO_SW_TRIGGER=y CONFIG_BMA180=y CONFIG_BMC150_ACCEL=y CONFIG_IIO_ST_ACCEL_3AXIS=y +# CONFIG_IIO_ST_ACCEL_SPI_3AXIS is not set CONFIG_IIO_RESCALE=y CONFIG_MPU3050_I2C=y CONFIG_IIO_ST_GYRO_3AXIS=y +# CONFIG_IIO_ST_GYRO_SPI_3AXIS is not set CONFIG_INV_MPU6050_I2C=y CONFIG_BH1780=y CONFIG_GP2AP002=y +CONFIG_TSL2772=y CONFIG_AK8974=y CONFIG_IIO_ST_MAGN_3AXIS=y +# CONFIG_IIO_ST_MAGN_SPI_3AXIS is not set CONFIG_YAMAHA_YAS530=y CONFIG_IIO_HRTIMER_TRIGGER=y CONFIG_IIO_ST_PRESS=y +# CONFIG_IIO_ST_PRESS_SPI is not set CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -173,10 +185,9 @@ CONFIG_CRYPTO_DEV_UX500_CRYP=y CONFIG_CRYPTO_DEV_UX500_HASH=y CONFIG_CRYPTO_DEV_UX500_DEBUG=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y # CONFIG_SCHED_DEBUG is not set # CONFIG_FTRACE is not set CONFIG_DEBUG_USER=y diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 413abfb42989..f82a819eb0db 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -48,6 +48,7 @@ static inline u32 read_ ## a64(void) \ return read_sysreg(a32); \ } \ +CPUIF_MAP(ICC_EOIR1, ICC_EOIR1_EL1) CPUIF_MAP(ICC_PMR, ICC_PMR_EL1) CPUIF_MAP(ICC_AP0R0, ICC_AP0R0_EL1) CPUIF_MAP(ICC_AP0R1, ICC_AP0R1_EL1) @@ -63,12 +64,6 @@ CPUIF_MAP(ICC_AP1R3, ICC_AP1R3_EL1) /* Low-level accessors */ -static inline void gic_write_eoir(u32 irq) -{ - write_sysreg(irq, ICC_EOIR1); - isb(); -} - static inline void gic_write_dir(u32 val) { write_sysreg(val, ICC_DIR); diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 0c70eb688a00..2a0739a2350b 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -440,6 +440,9 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr); #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap #endif /* diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 06508698abb8..7a8682468a84 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -1145,7 +1145,7 @@ vector_bhb_loop8_\name: @ bhb workaround mov r0, #8 -3: b . + 4 +3: W(b) . + 4 subs r0, r0, #1 bne 3b dsb diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c index 428012687a80..7f7f6bae21c2 100644 --- a/arch/arm/mach-davinci/board-da850-evm.c +++ b/arch/arm/mach-davinci/board-da850-evm.c @@ -1101,11 +1101,13 @@ static int __init da850_evm_config_emac(void) int ret; u32 val; struct davinci_soc_info *soc_info = &davinci_soc_info; - u8 rmii_en = soc_info->emac_pdata->rmii_en; + u8 rmii_en; if (!machine_is_davinci_da850_evm()) return 0; + rmii_en = soc_info->emac_pdata->rmii_en; + cfg_chip3_base = DA8XX_SYSCFG0_VIRT(DA8XX_CFGCHIP3_REG); val = __raw_readl(cfg_chip3_base); diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c index cc75087134d3..4fa6ea5461b7 100644 --- a/arch/arm/mach-ep93xx/clock.c +++ b/arch/arm/mach-ep93xx/clock.c @@ -148,8 +148,10 @@ static struct clk_hw *ep93xx_clk_register_gate(const char *name, psc->lock = &clk_lock; clk = clk_register(NULL, &psc->hw); - if (IS_ERR(clk)) + if (IS_ERR(clk)) { kfree(psc); + return ERR_CAST(clk); + } return &psc->hw; } @@ -207,7 +209,7 @@ static int ep93xx_mux_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { unsigned long rate = req->rate; - struct clk *best_parent = 0; + struct clk *best_parent = NULL; unsigned long __parent_rate; unsigned long best_rate = 0, actual_rate, mclk_rate; unsigned long best_parent_rate; diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index f7d993628cb7..a9c1efcf7c9c 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -17,7 +17,6 @@ menuconfig ARCH_EXYNOS select EXYNOS_PMU select EXYNOS_SROM select EXYNOS_PM_DOMAINS if PM_GENERIC_DOMAINS - select GPIOLIB select HAVE_ARM_ARCH_TIMER if ARCH_EXYNOS5 select HAVE_ARM_SCU if SMP select PINCTRL diff --git a/arch/arm/mach-iop32x/cp6.c b/arch/arm/mach-iop32x/cp6.c index 2882674a1c39..7135a0ac9949 100644 --- a/arch/arm/mach-iop32x/cp6.c +++ b/arch/arm/mach-iop32x/cp6.c @@ -7,6 +7,8 @@ #include <asm/traps.h> #include <asm/ptrace.h> +#include "iop3xx.h" + void iop_enable_cp6(void) { u32 temp; diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c index 5c3845730dbf..0b80f8bcd304 100644 --- a/arch/arm/mach-omap2/omap4-common.c +++ b/arch/arm/mach-omap2/omap4-common.c @@ -314,10 +314,12 @@ void __init omap_gic_of_init(void) np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-gic"); gic_dist_base_addr = of_iomap(np, 0); + of_node_put(np); WARN_ON(!gic_dist_base_addr); np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-twd-timer"); twd_base = of_iomap(np, 0); + of_node_put(np); WARN_ON(!twd_base); skip_errata_init: diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig index e5c2fce281cd..abdb99fe1e97 100644 --- a/arch/arm/mach-sunxi/Kconfig +++ b/arch/arm/mach-sunxi/Kconfig @@ -4,10 +4,7 @@ menuconfig ARCH_SUNXI depends on ARCH_MULTI_V5 || ARCH_MULTI_V7 select ARCH_HAS_RESET_CONTROLLER select CLKSRC_MMIO - select GENERIC_IRQ_CHIP select GPIOLIB - select IRQ_DOMAIN_HIERARCHY - select IRQ_FASTEOI_HIERARCHY_HANDLERS select PINCTRL select PM_OPP select SUN4I_TIMER @@ -22,10 +19,12 @@ if ARCH_MULTI_V7 config MACH_SUN4I bool "Allwinner A10 (sun4i) SoCs support" default ARCH_SUNXI + select SUN4I_INTC config MACH_SUN5I bool "Allwinner A10s / A13 (sun5i) SoCs support" default ARCH_SUNXI + select SUN4I_INTC select SUN5I_HSTIMER config MACH_SUN6I @@ -34,6 +33,8 @@ config MACH_SUN6I select ARM_GIC select MFD_SUN6I_PRCM select SUN5I_HSTIMER + select SUN6I_R_INTC + select SUNXI_NMI_INTC config MACH_SUN7I bool "Allwinner A20 (sun7i) SoCs support" @@ -43,17 +44,21 @@ config MACH_SUN7I select ARCH_SUPPORTS_BIG_ENDIAN select HAVE_ARM_ARCH_TIMER select SUN5I_HSTIMER + select SUNXI_NMI_INTC config MACH_SUN8I bool "Allwinner sun8i Family SoCs support" default ARCH_SUNXI select ARM_GIC select MFD_SUN6I_PRCM + select SUN6I_R_INTC + select SUNXI_NMI_INTC config MACH_SUN9I bool "Allwinner (sun9i) SoCs support" default ARCH_SUNXI select ARM_GIC + select SUNXI_NMI_INTC config ARCH_SUNXI_MC_SMP bool @@ -69,6 +74,7 @@ if ARCH_MULTI_V5 config MACH_SUNIV bool "Allwinner ARMv5 F-series (suniv) SoCs support" default ARCH_SUNXI + select SUN4I_INTC help Support for Allwinner suniv ARMv5 SoCs. (F1C100A, F1C100s, F1C200s, F1C500, F1C600) diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index 1da11bdb1dfb..6e6985e756af 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -122,13 +122,13 @@ static inline bool cluster_is_a15(u32 cluster) } /** - * ve_spc_global_wakeup_irq() + * ve_spc_global_wakeup_irq() - sets/clears global wakeup IRQs + * + * @set: if true, global wake-up IRQs are set, if false they are cleared * * Function to set/clear global wakeup IRQs. Not protected by locking since * it might be used in code paths where normal cacheable locks are not * working. Locking must be provided by the caller to ensure atomicity. - * - * @set: if true, global wake-up IRQs are set, if false they are cleared */ void ve_spc_global_wakeup_irq(bool set) { @@ -145,15 +145,15 @@ void ve_spc_global_wakeup_irq(bool set) } /** - * ve_spc_cpu_wakeup_irq() - * - * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since - * it might be used in code paths where normal cacheable locks are not - * working. Locking must be provided by the caller to ensure atomicity. + * ve_spc_cpu_wakeup_irq() - sets/clears per-CPU wake-up IRQs * * @cluster: mpidr[15:8] bitfield describing cluster affinity level * @cpu: mpidr[7:0] bitfield describing cpu affinity level * @set: if true, wake-up IRQs are set, if false they are cleared + * + * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since + * it might be used in code paths where normal cacheable locks are not + * working. Locking must be provided by the caller to ensure atomicity. */ void ve_spc_cpu_wakeup_irq(u32 cluster, u32 cpu, bool set) { @@ -200,14 +200,14 @@ void ve_spc_set_resume_addr(u32 cluster, u32 cpu, u32 addr) } /** - * ve_spc_powerdown() + * ve_spc_powerdown() - enables/disables cluster powerdown + * + * @cluster: mpidr[15:8] bitfield describing cluster affinity level + * @enable: if true enables powerdown, if false disables it * * Function to enable/disable cluster powerdown. Not protected by locking * since it might be used in code paths where normal cacheable locks are not * working. Locking must be provided by the caller to ensure atomicity. - * - * @cluster: mpidr[15:8] bitfield describing cluster affinity level - * @enable: if true enables powerdown, if false disables it */ void ve_spc_powerdown(u32 cluster, bool enable) { @@ -228,7 +228,7 @@ static u32 standbywfi_cpu_mask(u32 cpu, u32 cluster) } /** - * ve_spc_cpu_in_wfi(u32 cpu, u32 cluster) + * ve_spc_cpu_in_wfi() - Checks if the specified CPU is in WFI or not * * @cpu: mpidr[7:0] bitfield describing CPU affinity level within cluster * @cluster: mpidr[15:8] bitfield describing cluster affinity level @@ -580,7 +580,7 @@ static int __init ve_spc_clk_init(void) } cluster = topology_physical_package_id(cpu_dev->id); - if (init_opp_table[cluster]) + if (cluster < 0 || init_opp_table[cluster]) continue; if (ve_init_opp_table(cpu_dev)) diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index aa08bcb72db9..290702328a33 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -493,3 +493,11 @@ void __init early_ioremap_init(void) { early_ioremap_setup(); } + +bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + return memblock_is_map_memory(pfn); +} diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 06dbfb968182..fb9f3eb6bf48 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -288,6 +288,7 @@ void cpu_v7_ca15_ibe(void) { if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(0))) cpu_v7_spectre_v2_init(); + cpu_v7_spectre_bhb_init(); } void cpu_v7_bugs_init(void) diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index ec5b082f3de6..07eb69f9e7df 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -337,12 +337,15 @@ int __init arch_xen_unpopulated_init(struct resource **res) if (!nr_reg) { pr_err("No extended regions are found\n"); + of_node_put(np); return -EINVAL; } regs = kcalloc(nr_reg, sizeof(*regs), GFP_KERNEL); - if (!regs) + if (!regs) { + of_node_put(np); return -ENOMEM; + } /* * Create resource from extended regions provided by the hypervisor to be @@ -403,8 +406,8 @@ int __init arch_xen_unpopulated_init(struct resource **res) *res = &xen_resource; err: + of_node_put(np); kfree(regs); - return rc; } #endif @@ -424,8 +427,10 @@ static void __init xen_dt_guest_init(void) if (of_address_to_resource(xen_node, GRANT_TABLE_INDEX, &res)) { pr_err("Xen grant table region is not found\n"); + of_node_put(xen_node); return; } + of_node_put(xen_node); xen_grant_frames = res.start; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 57c4c995965f..20ea89d9ac2f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -175,8 +175,6 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_REGS \ - if $(cc-option,-fpatchable-function-entry=2) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -228,6 +226,17 @@ config ARM64 help ARM 64-bit (AArch64) Linux support. +config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS + def_bool CC_IS_CLANG + # https://github.com/ClangBuiltLinux/linux/issues/1507 + depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600)) + select HAVE_DYNAMIC_FTRACE_WITH_REGS + +config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS + def_bool CC_IS_GCC + depends on $(cc-option,-fpatchable-function-entry=2) + select HAVE_DYNAMIC_FTRACE_WITH_REGS + config 64BIT def_bool y @@ -678,7 +687,7 @@ config ARM64_ERRATUM_2051678 default y help This options adds the workaround for ARM Cortex-A510 erratum ARM64_ERRATUM_2051678. - Affected Coretex-A510 might not respect the ordering rules for + Affected Cortex-A510 might not respect the ordering rules for hardware update of the page table's dirty bit. The workaround is to not enable the feature on affected CPUs. diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 30b123cde02c..6a6457fed7b2 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -11,12 +11,11 @@ config ARCH_ACTIONS config ARCH_SUNXI bool "Allwinner sunxi 64-bit SoC Family" select ARCH_HAS_RESET_CONTROLLER - select GENERIC_IRQ_CHIP - select IRQ_DOMAIN_HIERARCHY - select IRQ_FASTEOI_HIERARCHY_HANDLERS select PINCTRL select RESET_CONTROLLER select SUN4I_TIMER + select SUN6I_R_INTC + select SUNXI_NMI_INTC help This enables support for Allwinner sunxi based SoCs like the A64. @@ -253,6 +252,7 @@ config ARCH_INTEL_SOCFPGA config ARCH_SYNQUACER bool "Socionext SynQuacer SoC Family" + select IRQ_FASTEOI_HIERARCHY_HANDLERS config ARCH_TEGRA bool "NVIDIA Tegra SoC Family" diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi index d61f43052a34..8e9ad1e51d66 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi @@ -11,26 +11,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <761000>; @@ -71,26 +51,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <731000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi index 1e5d0ee5d541..44c23c984034 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi @@ -11,26 +11,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <731000>; @@ -76,26 +56,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <751000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <751000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <751000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <751000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <771000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi index bf9ae1e1016b..480afa2cc61f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi @@ -13,28 +13,28 @@ cpu0: cpu@0 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x0>; enable-method = "psci"; }; cpu1: cpu@1 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x1>; enable-method = "psci"; }; cpu2: cpu@2 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x2>; enable-method = "psci"; }; cpu3: cpu@3 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x3>; enable-method = "psci"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts index 5751c48620ed..cadba194b149 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts @@ -437,6 +437,7 @@ "", "eMMC_RST#", /* BOOT_12 */ "eMMC_DS", /* BOOT_13 */ + "", "", /* GPIOC */ "SD_D0_B", /* GPIOC_0 */ "SD_D1_B", /* GPIOC_1 */ diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi index 3c07a89bfd27..80737731af3f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi @@ -95,26 +95,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <730000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <730000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <730000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <666666666>; - opp-microvolt = <750000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <770000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi index 1dc9d187601c..a0bd540f27d3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi @@ -89,12 +89,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi index 73addc0b8e57..cce55c3c5df0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi @@ -146,12 +146,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; status = "okay"; }; @@ -215,7 +217,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi index 1e7badb2a82e..f61e4847fa49 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi @@ -211,12 +211,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; vbus-supply = <®_usb_otg2_vbus>; status = "okay"; }; @@ -309,7 +311,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi index 426483ec1f88..023619648966 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi @@ -238,12 +238,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; vbus-supply = <®_usb_otg2_vbus>; status = "okay"; }; @@ -358,7 +360,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index 7dfee715a2c4..d8ce217c6016 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -59,6 +59,10 @@ interrupts = <3 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; + #clock-cells = <0>; + clocks = <&osc_32k 0>; + clock-output-names = "clk-32k-out"; + regulators { buck1_reg: BUCK1 { regulator-name = "buck1"; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index b16c7caf34c1..87b5e23c766f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -70,12 +70,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 99f0f5026674..5c0ca2490561 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -293,7 +293,7 @@ ranges; sai2: sai@30020000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30020000 0x10000>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI2_IPG>, @@ -307,7 +307,7 @@ }; sai3: sai@30030000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30030000 0x10000>; interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI3_IPG>, @@ -321,7 +321,7 @@ }; sai5: sai@30050000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30050000 0x10000>; interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI5_IPG>, @@ -337,7 +337,7 @@ }; sai6: sai@30060000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30060000 0x10000>; interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI6_IPG>, @@ -394,7 +394,7 @@ }; sai7: sai@300b0000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x300b0000 0x10000>; interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI7_IPG>, diff --git a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi index 38ffcd145b33..899e8e7dbc24 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi @@ -253,7 +253,7 @@ #address-cells = <1>; #size-cells = <1>; spi-max-frequency = <84000000>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm.dtsi b/arch/arm64/boot/dts/freescale/imx8qm.dtsi index be8c76a0554c..4f767012f1f5 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm.dtsi @@ -196,7 +196,7 @@ }; clk: clock-controller { - compatible = "fsl,imx8qxp-clk", "fsl,scu-clk"; + compatible = "fsl,imx8qm-clk", "fsl,scu-clk"; #clock-cells = <2>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index f0f81c23c16f..b9a48cfd760f 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -1249,14 +1249,14 @@ pins = "gpio47", "gpio48"; function = "blsp_i2c3"; drive-strength = <16>; - bias-disable = <0>; + bias-disable; }; blsp1_i2c3_sleep: blsp1-i2c2-sleep { pins = "gpio47", "gpio48"; function = "gpio"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; blsp2_uart3_4pins_default: blsp2-uart2-4pins { diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi index e90f99ef5323..e47c74e513af 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi @@ -33,7 +33,7 @@ ap_h1_spi: &spi0 {}; }; &alc5682 { - realtek,dmic-clk-driving-high = "true"; + realtek,dmic-clk-driving-high; }; &cpu6_alert0 { diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi index 1084d5ce9ac7..07b729f9fec5 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi @@ -630,7 +630,7 @@ pins = "gpio6", "gpio25", "gpio26"; function = "gpio"; drive-strength = <8>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts index 8553c8bf79bd..103cc40816fd 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts @@ -563,7 +563,7 @@ config { pins = "gpio6", "gpio11"; drive-strength = <8>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts index fb99cc2827c7..7ab3627cc347 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts @@ -622,6 +622,10 @@ status = "okay"; }; +&rxmacro { + status = "okay"; +}; + &slpi { status = "okay"; firmware-name = "qcom/sm8250/slpi.mbn"; @@ -773,6 +777,8 @@ }; &swr1 { + status = "okay"; + wcd_rx: wcd9380-rx@0,4 { compatible = "sdw20217010d00"; reg = <0 4>; @@ -781,6 +787,8 @@ }; &swr2 { + status = "okay"; + wcd_tx: wcd9380-tx@0,3 { compatible = "sdw20217010d00"; reg = <0 3>; @@ -819,6 +827,10 @@ }; }; +&txmacro { + status = "okay"; +}; + &uart12 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index af8f22636436..1304b86af1a0 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -2255,6 +2255,7 @@ pinctrl-0 = <&rx_swr_active>; compatible = "qcom,sm8250-lpass-rx-macro"; reg = <0 0x3200000 0 0x1000>; + status = "disabled"; clocks = <&q6afecc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, <&q6afecc LPASS_CLK_ID_TX_CORE_NPL_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, @@ -2273,6 +2274,7 @@ swr1: soundwire-controller@3210000 { reg = <0 0x3210000 0 0x2000>; compatible = "qcom,soundwire-v1.5.1"; + status = "disabled"; interrupts = <GIC_SPI 298 IRQ_TYPE_LEVEL_HIGH>; clocks = <&rxmacro>; clock-names = "iface"; @@ -2300,6 +2302,7 @@ pinctrl-0 = <&tx_swr_active>; compatible = "qcom,sm8250-lpass-tx-macro"; reg = <0 0x3220000 0 0x1000>; + status = "disabled"; clocks = <&q6afecc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, <&q6afecc LPASS_CLK_ID_TX_CORE_NPL_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, @@ -2323,6 +2326,7 @@ compatible = "qcom,soundwire-v1.5.1"; interrupts-extended = <&intc GIC_SPI 297 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "core"; + status = "disabled"; clocks = <&txmacro>; clock-names = "iface"; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index a01886b467ed..067fe4a6b178 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -16,6 +16,7 @@ aliases { ethernet0 = &gmac0; + ethernet1 = &gmac1; mmc0 = &sdmmc0; mmc1 = &sdhci; }; @@ -78,7 +79,6 @@ assigned-clocks = <&cru SCLK_GMAC0_RX_TX>, <&cru SCLK_GMAC0>; assigned-clock-parents = <&cru SCLK_GMAC0_RGMII_SPEED>, <&cru CLK_MAC0_2TOP>; clock_in_out = "input"; - phy-handle = <&rgmii_phy0>; phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&gmac0_miim @@ -90,8 +90,38 @@ snps,reset-active-low; /* Reset time is 20ms, 100ms for rtl8211f */ snps,reset-delays-us = <0 20000 100000>; + tx_delay = <0x4f>; + rx_delay = <0x0f>; + status = "okay"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; +}; + +&gmac1 { + assigned-clocks = <&cru SCLK_GMAC1_RX_TX>, <&cru SCLK_GMAC1>; + assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru CLK_MAC1_2TOP>; + clock_in_out = "output"; + phy-handle = <&rgmii_phy1>; + phy-mode = "rgmii"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1m1_miim + &gmac1m1_tx_bus2 + &gmac1m1_rx_bus2 + &gmac1m1_rgmii_clk + &gmac1m1_rgmii_bus>; + + snps,reset-gpio = <&gpio3 RK_PB0 GPIO_ACTIVE_LOW>; + snps,reset-active-low; + /* Reset time is 20ms, 100ms for rtl8211f */ + snps,reset-delays-us = <0 20000 100000>; + tx_delay = <0x3c>; rx_delay = <0x2f>; + status = "okay"; }; @@ -315,8 +345,8 @@ status = "disabled"; }; -&mdio0 { - rgmii_phy0: ethernet-phy@0 { +&mdio1 { + rgmii_phy1: ethernet-phy@0 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <0x0>; }; @@ -345,9 +375,9 @@ pmuio2-supply = <&vcc3v3_pmu>; vccio1-supply = <&vccio_acodec>; vccio3-supply = <&vccio_sd>; - vccio4-supply = <&vcc_1v8>; + vccio4-supply = <&vcc_3v3>; vccio5-supply = <&vcc_3v3>; - vccio6-supply = <&vcc_3v3>; + vccio6-supply = <&vcc_1v8>; vccio7-supply = <&vcc_3v3>; status = "okay"; }; diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 8bd5afc7b692..48d4473e8eee 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -26,12 +26,6 @@ * sets the GP register's most significant bits to 0 with an explicit cast. */ -static inline void gic_write_eoir(u32 irq) -{ - write_sysreg_s(irq, SYS_ICC_EOIR1_EL1); - isb(); -} - static __always_inline void gic_write_dir(u32 irq) { write_sysreg_s(irq, SYS_ICC_DIR_EL1); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 232b439cbaf3..ff8f4511df71 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 7f3c87f7a0ce..c31be7eda9df 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -107,7 +107,7 @@ isb // Make sure SRE is now set mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks - msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults + msr_s SYS_ICH_HCR_EL2, xzr // Reset ICH_HCR_EL2 to defaults .Lskip_gicv3_\@: .endm diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 7fd836bea7eb..3995652daf81 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -192,4 +192,8 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap + #endif /* __ASM_IO_H */ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index d62405ce3e6d..f71358271b71 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -40,13 +40,26 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_inject_size_fault(struct kvm_vcpu *vcpu); void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); +#if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__) static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); } +#else +static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, + &kvm->arch.flags)); + + return test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); +} +#endif static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) { @@ -72,15 +85,14 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 |= HCR_TVM; } - if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) + if (vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_RW; - - /* - * TID3: trap feature register accesses that we virtualise. - * For now this is conditional, since no AArch32 feature regs - * are currently virtualised. - */ - if (!vcpu_el1_is_32bit(vcpu)) + else + /* + * TID3: trap feature register accesses that we virtualise. + * For now this is conditional, since no AArch32 feature regs + * are currently virtualised. + */ vcpu->arch.hcr_el2 |= HCR_TID3; if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) || diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index e3b25dc6c367..94a27a7520f4 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -127,6 +127,16 @@ struct kvm_arch { #define KVM_ARCH_FLAG_MTE_ENABLED 1 /* At least one vCPU has ran in the VM */ #define KVM_ARCH_FLAG_HAS_RAN_ONCE 2 + /* + * The following two bits are used to indicate the guest's EL1 + * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT + * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set. + * Otherwise, the guest's EL1 register width has not yet been + * determined yet. + */ +#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED 3 +#define KVM_ARCH_FLAG_EL1_32BIT 4 + unsigned long flags; /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 94e147e5456c..dff2b483ea50 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -535,7 +535,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) -#define pmd_leaf(pmd) pmd_sect(pmd) +#define pmd_leaf(pmd) (pmd_present(pmd) && !pmd_table(pmd)) #define pmd_bad(pmd) (!pmd_table(pmd)) #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) @@ -625,7 +625,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) -#define pud_leaf(pud) pud_sect(pud) +#define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) static inline void set_pud(pud_t *pudp, pud_t pud) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 986837d7ec82..fa7981d0d917 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -75,6 +75,10 @@ obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso-wrap.o obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o +# Force dependency (vdso*-wrap.S includes vdso.so through incbin) +$(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so +$(obj)/vdso32-wrap.o: $(obj)/vdso32/vdso.so + obj-y += probes/ head-y := head.o extra-y += $(head-y) vmlinux.lds diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 3fb79b76e9d9..7bbf5104b7b7 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -42,7 +42,7 @@ bool alternative_is_applied(u16 cpufeature) /* * Check if the target PC is within an alternative block. */ -static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) +static __always_inline bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); return !(pc >= replptr && pc <= (replptr + alt->alt_len)); @@ -50,7 +50,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) -static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) +static __always_inline u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) { u32 insn; @@ -95,7 +95,7 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp return insn; } -static void patch_alternative(struct alt_instr *alt, +static noinstr void patch_alternative(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { __le32 *replptr; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 4c9b5b4b7a0b..a0f3d0aaa3c5 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -208,6 +208,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #ifdef CONFIG_ARM64_ERRATUM_1286807 { ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + /* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */ + ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, #endif {}, diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d72c4b4d389c..2cb9cc9e0eff 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -654,7 +654,6 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1, &id_aa64isar1_override), - ARM64_FTR_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2, &id_aa64isar2_override), @@ -810,7 +809,7 @@ static void __init sort_ftr_regs(void) * to sys_id for subsequent binary search in get_arm64_ftr_reg() * to work correctly. */ - BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id); + BUG_ON(arm64_ftr_regs[i].sys_id <= arm64_ftr_regs[i - 1].sys_id); } } diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 3ed39c61a510..98d67444a5b6 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,16 +8,9 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#ifndef VMA_ITERATOR -#define VMA_ITERATOR(name, mm, addr) \ - struct mm_struct *name = mm -#define for_each_vma(vmi, vma) \ - for (vma = vmi->mmap; vma; vma = vma->vm_next) -#endif - -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(tsk, vma) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ + for (vma = tsk->mm->mmap; vma; vma = vma->vm_next) \ if (vma->vm_flags & VM_MTE) static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) @@ -32,10 +25,11 @@ static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) static int mte_dump_tag_range(struct coredump_params *cprm, unsigned long start, unsigned long end) { + int ret = 1; unsigned long addr; + void *tags = NULL; for (addr = start; addr < end; addr += PAGE_SIZE) { - char tags[MTE_PAGE_TAG_STORAGE]; struct page *page = get_dump_page(addr); /* @@ -59,22 +53,36 @@ static int mte_dump_tag_range(struct coredump_params *cprm, continue; } + if (!tags) { + tags = mte_allocate_tag_storage(); + if (!tags) { + put_page(page); + ret = 0; + break; + } + } + mte_save_page_tags(page_address(page), tags); put_page(page); - if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) - return 0; + if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { + mte_free_tag_storage(tags); + ret = 0; + break; + } } - return 1; + if (tags) + mte_free_tag_storage(tags); + + return ret; } Elf_Half elf_core_extra_phdrs(void) { struct vm_area_struct *vma; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) vma_count++; return vma_count; @@ -83,12 +91,11 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { struct elf_phdr phdr; - phdr.p_type = PT_ARM_MEMTAG_MTE; + phdr.p_type = PT_AARCH64_MEMTAG_MTE; phdr.p_offset = offset; phdr.p_vaddr = vma->vm_start; phdr.p_paddr = 0; @@ -109,9 +116,8 @@ size_t elf_core_extra_data_size(void) { struct vm_area_struct *vma; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) data_size += mte_vma_tag_dump_size(vma); return data_size; @@ -120,9 +126,8 @@ size_t elf_core_extra_data_size(void) int elf_core_write_extra_data(struct coredump_params *cprm) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { if (vma->vm_flags & VM_DONTDUMP) continue; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 712e97c03e54..cd868084e724 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -701,7 +701,7 @@ NOKPROBE_SYMBOL(breakpoint_handler); * addresses. There is no straight-forward way, short of disassembling the * offending instruction, to map that address back to the watchpoint. This * function computes the distance of the memory access from the watchpoint as a - * heuristic for the likelyhood that a given access triggered the watchpoint. + * heuristic for the likelihood that a given access triggered the watchpoint. * * See Section D2.10.5 "Determining the memory location that caused a Watchpoint * exception" of ARMv8 Architecture Reference Manual for details. diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index e53493d8b208..a3d0494f25a9 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -220,7 +220,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, * increasing the section's alignment so that the * resulting address of this instruction is guaranteed * to equal the offset in that particular bit (as well - * as all less signficant bits). This ensures that the + * as all less significant bits). This ensures that the * address modulo 4 KB != 0xfff8 or 0xfffc (which would * have all ones in bits [11:3]) */ diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 78b3e0f8e997..d502703e8373 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -76,6 +76,9 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); } + + /* ensure the tags are visible before the PTE is set */ + smp_wmb(); } int memcmp_pages(struct page *page1, struct page *page2) diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index 75fed4460407..57c7c211f8c7 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -35,7 +35,7 @@ static u64 native_steal_clock(int cpu) DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); struct pv_time_stolen_time_region { - struct pvclock_vcpu_stolen_time *kaddr; + struct pvclock_vcpu_stolen_time __rcu *kaddr; }; static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region); @@ -52,7 +52,9 @@ early_param("no-steal-acc", parse_no_stealacc); /* return stolen time in ns by asking the hypervisor */ static u64 para_steal_clock(int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; + u64 ret = 0; reg = per_cpu_ptr(&stolen_time_region, cpu); @@ -61,28 +63,37 @@ static u64 para_steal_clock(int cpu) * online notification callback runs. Until the callback * has run we just return zero. */ - if (!reg->kaddr) + rcu_read_lock(); + kaddr = rcu_dereference(reg->kaddr); + if (!kaddr) { + rcu_read_unlock(); return 0; + } - return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time)); + ret = le64_to_cpu(READ_ONCE(kaddr->stolen_time)); + rcu_read_unlock(); + return ret; } static int stolen_time_cpu_down_prepare(unsigned int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; reg = this_cpu_ptr(&stolen_time_region); if (!reg->kaddr) return 0; - memunmap(reg->kaddr); - memset(reg, 0, sizeof(*reg)); + kaddr = rcu_replace_pointer(reg->kaddr, NULL, true); + synchronize_rcu(); + memunmap(kaddr); return 0; } static int stolen_time_cpu_online(unsigned int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; struct arm_smccc_res res; @@ -93,17 +104,19 @@ static int stolen_time_cpu_online(unsigned int cpu) if (res.a0 == SMCCC_RET_NOT_SUPPORTED) return -EINVAL; - reg->kaddr = memremap(res.a0, + kaddr = memremap(res.a0, sizeof(struct pvclock_vcpu_stolen_time), MEMREMAP_WB); + rcu_assign_pointer(reg->kaddr, kaddr); + if (!reg->kaddr) { pr_warn("Failed to map stolen time data structure\n"); return -ENOMEM; } - if (le32_to_cpu(reg->kaddr->revision) != 0 || - le32_to_cpu(reg->kaddr->attributes) != 0) { + if (le32_to_cpu(kaddr->revision) != 0 || + le32_to_cpu(kaddr->attributes) != 0) { pr_warn_once("Unexpected revision or attributes in stolen time data\n"); return -ENXIO; } diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 771f543464e0..33e0fabc0b79 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) int i, ret = 0; struct aarch64_insn_patch *pp = arg; - /* The first CPU becomes master */ - if (atomic_inc_return(&pp->cpu_count) == 1) { + /* The last CPU becomes master */ + if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) { for (i = 0; ret == 0 && i < pp->insn_cnt; i++) ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i], pp->new_insns[i]); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 5777929d35bf..40be3a7c2c53 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -853,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope) if (scope == SCOPE_LOCAL_CPU) { static const struct midr_range spectre_bhb_k32_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index f0a3df9e18a3..413f899e4ac6 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -37,6 +37,15 @@ * safe memory that has been set up to be preserved during the copy operation. */ SYM_CODE_START(arm64_relocate_new_kernel) + /* + * The kimage structure isn't allocated specially and may be clobbered + * during relocation. We must load any values we need from it prior to + * any relocation occurring. + */ + ldr x28, [x0, #KIMAGE_START] + ldr x27, [x0, #KIMAGE_ARCH_EL2_VECTORS] + ldr x26, [x0, #KIMAGE_ARCH_DTB_MEM] + /* Setup the list loop variables. */ ldr x18, [x0, #KIMAGE_ARCH_ZERO_PAGE] /* x18 = zero page for BBM */ ldr x17, [x0, #KIMAGE_ARCH_TTBR1] /* x17 = linear map copy */ @@ -72,21 +81,20 @@ SYM_CODE_START(arm64_relocate_new_kernel) ic iallu dsb nsh isb - ldr x4, [x0, #KIMAGE_START] /* relocation start */ - ldr x1, [x0, #KIMAGE_ARCH_EL2_VECTORS] /* relocation start */ - ldr x0, [x0, #KIMAGE_ARCH_DTB_MEM] /* dtb address */ turn_off_mmu x12, x13 /* Start new image. */ - cbz x1, .Lel1 - mov x1, x4 /* relocation start */ - mov x2, x0 /* dtb address */ + cbz x27, .Lel1 + mov x1, x28 /* kernel entry point */ + mov x2, x26 /* dtb address */ mov x3, xzr mov x4, xzr mov x0, #HVC_SOFT_RESTART hvc #0 /* Jumps from el2 */ .Lel1: + mov x0, x26 /* dtb address */ + mov x1, xzr mov x2, xzr mov x3, xzr - br x4 /* Jumps from el1 */ + br x28 /* Jumps from el1 */ SYM_CODE_END(arm64_relocate_new_kernel) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 27df5c1e6baa..3b46041f2b97 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void) * Log the CPU info before it is marked online and might get read. */ cpuinfo_store_cpu(); + store_cpu_topology(cpu); /* * Enable GIC and timers. @@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void) ipi_setup(cpu); - store_cpu_topology(cpu); numa_add_cpu(cpu); /* diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 19ee7c33769d..2b0887e58a7c 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -140,7 +140,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully - * renabled if it was enabled when core started shutdown. + * reenabled if it was enabled when core started shutdown. */ local_daif_restore(flags); diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 172452f79e46..ac1964ebed1e 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -52,9 +52,6 @@ GCOV_PROFILE := n targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) -# Force dependency (incbin is bad) -$(obj)/vdso.o : $(obj)/vdso.so - # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold_and_vdso_check) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index ed181bedbffc..05ba1aae1b6f 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -131,9 +131,6 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) -# Force dependency (vdso.s includes vdso.so through incbin) -$(obj)/vdso.o: $(obj)/vdso.so - include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 523bc934fe2f..a66d83540c15 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1436,7 +1436,8 @@ static int kvm_init_vector_slots(void) base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT); - if (kvm_system_needs_idmapped_vectors() && !has_vhe()) { + if (kvm_system_needs_idmapped_vectors() && + !is_protected_kvm_enabled()) { err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs), __BP_HARDEN_HYP_VECS_SZ, &base); if (err) diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 3d613e721a75..727c979b2b69 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -198,15 +198,15 @@ SYM_CODE_START(__kvm_hyp_host_vector) invalid_host_el2_vect // FIQ EL2h invalid_host_el2_vect // Error EL2h - host_el1_sync_vect // Synchronous 64-bit EL1 - invalid_host_el1_vect // IRQ 64-bit EL1 - invalid_host_el1_vect // FIQ 64-bit EL1 - invalid_host_el1_vect // Error 64-bit EL1 - - invalid_host_el1_vect // Synchronous 32-bit EL1 - invalid_host_el1_vect // IRQ 32-bit EL1 - invalid_host_el1_vect // FIQ 32-bit EL1 - invalid_host_el1_vect // Error 32-bit EL1 + host_el1_sync_vect // Synchronous 64-bit EL1/EL0 + invalid_host_el1_vect // IRQ 64-bit EL1/EL0 + invalid_host_el1_vect // FIQ 64-bit EL1/EL0 + invalid_host_el1_vect // Error 64-bit EL1/EL0 + + host_el1_sync_vect // Synchronous 32-bit EL1/EL0 + invalid_host_el1_vect // IRQ 32-bit EL1/EL0 + invalid_host_el1_vect // FIQ 32-bit EL1/EL0 + invalid_host_el1_vect // Error 32-bit EL1/EL0 SYM_CODE_END(__kvm_hyp_host_vector) /* diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index b47df73e98d7..ba20405d2dc2 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -145,6 +145,34 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) inject_abt64(vcpu, true, addr); } +void kvm_inject_size_fault(struct kvm_vcpu *vcpu) +{ + unsigned long addr, esr; + + addr = kvm_vcpu_get_fault_ipa(vcpu); + addr |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); + + if (kvm_vcpu_trap_is_iabt(vcpu)) + kvm_inject_pabt(vcpu, addr); + else + kvm_inject_dabt(vcpu, addr); + + /* + * If AArch64 or LPAE, set FSC to 0 to indicate an Address + * Size Fault at level 0, as if exceeding PARange. + * + * Non-LPAE guests will only get the external abort, as there + * is no way to to describe the ASF. + */ + if (vcpu_el1_is_32bit(vcpu) && + !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) + return; + + esr = vcpu_read_sys_reg(vcpu, ESR_EL1); + esr &= ~GENMASK_ULL(5, 0); + vcpu_write_sys_reg(vcpu, esr, ESR_EL1); +} + /** * kvm_inject_undefined - inject an undefined instruction into the guest * @vcpu: The vCPU in which to inject the exception diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 0d19259454d8..5400fc020164 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1079,7 +1079,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); - bool logging_perm_fault = false; + bool use_read_lock = false; unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu); unsigned long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; @@ -1114,7 +1114,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (logging_active) { force_pte = true; vma_shift = PAGE_SHIFT; - logging_perm_fault = (fault_status == FSC_PERM && write_fault); + use_read_lock = (fault_status == FSC_PERM && write_fault && + fault_granule == PAGE_SIZE); } else { vma_shift = get_vma_page_shift(vma, hva); } @@ -1218,7 +1219,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * logging dirty logging, only acquire read lock for permission * relaxation. */ - if (logging_perm_fault) + if (use_read_lock) read_lock(&kvm->mmu_lock); else write_lock(&kvm->mmu_lock); @@ -1268,6 +1269,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (fault_status == FSC_PERM && vma_pagesize == fault_granule) { ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); } else { + WARN_ONCE(use_read_lock, "Attempted stage-2 map outside of write lock\n"); + ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, memcache); @@ -1280,7 +1283,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } out_unlock: - if (logging_perm_fault) + if (use_read_lock) read_unlock(&kvm->mmu_lock); else write_unlock(&kvm->mmu_lock); @@ -1334,6 +1337,25 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); + if (fault_status == FSC_FAULT) { + /* Beyond sanitised PARange (which is the IPA limit) */ + if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { + kvm_inject_size_fault(vcpu); + return 1; + } + + /* Falls between the IPA range and the PARange? */ + if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) { + fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); + + if (is_iabt) + kvm_inject_pabt(vcpu, fault_ipa); + else + kvm_inject_dabt(vcpu, fault_ipa); + return 1; + } + } + /* Synchronous External Abort? */ if (kvm_vcpu_abt_issea(vcpu)) { /* diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 78fdc443adc7..3dc990ac4f44 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -177,6 +177,9 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc = &pmu->pmc[select_idx]; + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); if (kvm_pmu_pmc_is_chained(pmc) && @@ -198,6 +201,9 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { u64 reg; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + reg = (select_idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx; __vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx); @@ -322,6 +328,9 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val) return; @@ -357,7 +366,7 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc; - if (!val) + if (!kvm_vcpu_has_pmu(vcpu) || !val) return; for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { @@ -527,6 +536,9 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; int i; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) return; @@ -576,6 +588,9 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { int i; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (val & ARMV8_PMU_PMCR_E) { kvm_pmu_enable_counter_mask(vcpu, __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); @@ -739,6 +754,9 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, { u64 reg, mask; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + mask = ARMV8_PMU_EVTYPE_MASK; mask &= ~ARMV8_PMU_EVTYPE_EVENT; mask |= kvm_pmu_event_mask(vcpu->kvm); @@ -827,6 +845,9 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) u64 val, mask = 0; int base, i, nr_events; + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + if (!pmceid1) { val = read_sysreg(pmceid0_el0); base = 0; diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 372da09a2fab..708d80e8e60d 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -181,7 +181,8 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags) memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); vcpu->run->system_event.type = type; - vcpu->run->system_event.flags = flags; + vcpu->run->system_event.ndata = 1; + vcpu->run->system_event.data[0] = flags; vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } @@ -215,15 +216,11 @@ static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn) { - switch(fn) { - case PSCI_0_2_FN64_CPU_SUSPEND: - case PSCI_0_2_FN64_CPU_ON: - case PSCI_0_2_FN64_AFFINITY_INFO: - /* Disallow these functions for 32bit guests */ - if (vcpu_mode_is_32bit(vcpu)) - return PSCI_RET_NOT_SUPPORTED; - break; - } + /* + * Prevent 32 bit guests from calling 64 bit PSCI functions. + */ + if ((fn & PSCI_0_2_64BIT) && vcpu_mode_is_32bit(vcpu)) + return PSCI_RET_NOT_SUPPORTED; return 0; } @@ -235,10 +232,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) unsigned long val; int ret = 1; - val = kvm_psci_check_allowed_function(vcpu, psci_fn); - if (val) - goto out; - switch (psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: /* @@ -306,7 +299,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } -out: smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } @@ -318,9 +310,6 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) unsigned long val; int ret = 1; - if (minor > 1) - return -EINVAL; - switch(psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: val = minor == 0 ? KVM_ARM_PSCI_1_0 : KVM_ARM_PSCI_1_1; @@ -426,6 +415,15 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) */ int kvm_psci_call(struct kvm_vcpu *vcpu) { + u32 psci_fn = smccc_get_function(vcpu); + unsigned long val; + + val = kvm_psci_check_allowed_function(vcpu, psci_fn); + if (val) { + smccc_set_retval(vcpu, val, 0, 0, 0); + return 1; + } + switch (kvm_psci_version(vcpu)) { case KVM_ARM_PSCI_1_1: return kvm_psci_1_x_call(vcpu, 1); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index ecc40c8cd6f6..6c70c6f61c70 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -181,27 +181,51 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) return 0; } -static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) +/** + * kvm_set_vm_width() - set the register width for the guest + * @vcpu: Pointer to the vcpu being configured + * + * Set both KVM_ARCH_FLAG_EL1_32BIT and KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED + * in the VM flags based on the vcpu's requested register width, the HW + * capabilities and other options (such as MTE). + * When REG_WIDTH_CONFIGURED is already set, the vcpu settings must be + * consistent with the value of the FLAG_EL1_32BIT bit in the flags. + * + * Return: 0 on success, negative error code on failure. + */ +static int kvm_set_vm_width(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *tmp; + struct kvm *kvm = vcpu->kvm; bool is32bit; - unsigned long i; is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); + + lockdep_assert_held(&kvm->lock); + + if (test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags)) { + /* + * The guest's register width is already configured. + * Make sure that the vcpu is consistent with it. + */ + if (is32bit == test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags)) + return 0; + + return -EINVAL; + } + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) - return false; + return -EINVAL; /* MTE is incompatible with AArch32 */ - if (kvm_has_mte(vcpu->kvm) && is32bit) - return false; + if (kvm_has_mte(kvm) && is32bit) + return -EINVAL; - /* Check that the vcpus are either all 32bit or all 64bit */ - kvm_for_each_vcpu(i, tmp, vcpu->kvm) { - if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit) - return false; - } + if (is32bit) + set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); - return true; + set_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags); + + return 0; } /** @@ -230,10 +254,16 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) u32 pstate; mutex_lock(&vcpu->kvm->lock); - reset_state = vcpu->arch.reset_state; - WRITE_ONCE(vcpu->arch.reset_state.reset, false); + ret = kvm_set_vm_width(vcpu); + if (!ret) { + reset_state = vcpu->arch.reset_state; + WRITE_ONCE(vcpu->arch.reset_state.reset, false); + } mutex_unlock(&vcpu->kvm->lock); + if (ret) + return ret; + /* Reset PMU outside of the non-preemptible section */ kvm_pmu_vcpu_reset(vcpu); @@ -260,14 +290,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } } - if (!vcpu_allowed_register_width(vcpu)) { - ret = -EINVAL; - goto out; - } - switch (vcpu->arch.target) { default: - if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { + if (vcpu_el1_is_32bit(vcpu)) { pstate = VCPU_RESET_PSTATE_SVC; } else { pstate = VCPU_RESET_PSTATE_EL1; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 7b45c040cc27..adf408c09cdb 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1123,8 +1123,7 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2), (u64)vcpu->kvm->arch.pfr0_csv2); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3), (u64)vcpu->kvm->arch.pfr0_csv3); - if (irqchip_in_kernel(vcpu->kvm) && - vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + if (kvm_vgic_global_state.type == VGIC_V3) { val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_GIC); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_GIC), 1); } diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index f38c40a76251..78cde687383c 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -82,7 +82,7 @@ static bool end_of_vgic(struct vgic_state_iter *iter) static void *vgic_debug_start(struct seq_file *s, loff_t *pos) { - struct kvm *kvm = (struct kvm *)s->private; + struct kvm *kvm = s->private; struct vgic_state_iter *iter; mutex_lock(&kvm->lock); @@ -110,7 +110,7 @@ out: static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) { - struct kvm *kvm = (struct kvm *)s->private; + struct kvm *kvm = s->private; struct vgic_state_iter *iter = kvm->arch.vgic.iter; ++*pos; @@ -122,7 +122,7 @@ static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) static void vgic_debug_stop(struct seq_file *s, void *v) { - struct kvm *kvm = (struct kvm *)s->private; + struct kvm *kvm = s->private; struct vgic_state_iter *iter; /* @@ -229,8 +229,8 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, static int vgic_debug_show(struct seq_file *s, void *v) { - struct kvm *kvm = (struct kvm *)s->private; - struct vgic_state_iter *iter = (struct vgic_state_iter *)v; + struct kvm *kvm = s->private; + struct vgic_state_iter *iter = v; struct vgic_irq *irq; struct kvm_vcpu *vcpu = NULL; unsigned long flags; diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 089fc2ffcb43..2e13402be3bd 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2143,7 +2143,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, void *ptr, void *opaque) { - struct its_device *dev = (struct its_device *)opaque; + struct its_device *dev = opaque; struct its_collection *collection; struct kvm *kvm = its->dev->kvm; struct kvm_vcpu *vcpu = NULL; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 8ac25f19084e..1e7b1550e2fc 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL(memstart_addr); * In this scheme a comparatively quicker boot is observed. * * If ZONE_DMA configs are defined, crash kernel memory reservation - * is delayed until DMA zone memory range size initilazation performed in + * is delayed until DMA zone memory range size initialization performed in * zone_sizes_init(). The defer is necessary to steer clear of DMA zone * memory range to avoid overlap allocation. So crash kernel memory boundaries * are not known when mapping all bank memory ranges, which otherwise means @@ -81,7 +81,7 @@ EXPORT_SYMBOL(memstart_addr); * so page-granularity mappings are created for the entire memory range. * Hence a slightly slower boot is observed. * - * Note: Page-granularity mapppings are necessary for crash kernel memory + * Note: Page-granularity mappings are necessary for crash kernel memory * range for shrinking its size via /sys/kernel/kexec_crash_size interface. */ #if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32) diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index b7c81dacabf0..b21f91cd830d 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -99,3 +99,11 @@ void __init early_ioremap_init(void) { early_ioremap_setup(); } + +bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + return pfn_is_map_memory(pfn); +} diff --git a/arch/mips/include/asm/timex.h b/arch/mips/include/asm/timex.h index b05bb70a2e46..8026baf46e72 100644 --- a/arch/mips/include/asm/timex.h +++ b/arch/mips/include/asm/timex.h @@ -40,9 +40,9 @@ typedef unsigned int cycles_t; /* - * On R4000/R4400 before version 5.0 an erratum exists such that if the - * cycle counter is read in the exact moment that it is matching the - * compare register, no interrupt will be generated. + * On R4000/R4400 an erratum exists such that if the cycle counter is + * read in the exact moment that it is matching the compare register, + * no interrupt will be generated. * * There is a suggested workaround and also the erratum can't strike if * the compare interrupt isn't being used as the clock source device. @@ -63,7 +63,7 @@ static inline int can_use_mips_counter(unsigned int prid) if (!__builtin_constant_p(cpu_has_counter)) asm volatile("" : "=m" (cpu_data[0].options)); if (likely(cpu_has_counter && - prid >= (PRID_IMP_R4000 | PRID_REV_ENCODE_44(5, 0)))) + prid > (PRID_IMP_R4000 | PRID_REV_ENCODE_44(15, 15)))) return 1; else return 0; diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index caa01457dce6..ed339d7979f3 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -141,15 +141,10 @@ static __init int cpu_has_mfc0_count_bug(void) case CPU_R4400MC: /* * The published errata for the R4400 up to 3.0 say the CPU - * has the mfc0 from count bug. + * has the mfc0 from count bug. This seems the last version + * produced. */ - if ((current_cpu_data.processor_id & 0xff) <= 0x30) - return 1; - - /* - * we assume newer revisions are ok - */ - return 0; + return 1; } return 0; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 52e550b45692..bd22578859d0 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -38,6 +38,7 @@ config PARISC select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_SMP_IDLE_THREAD select GENERIC_ARCH_TOPOLOGY if SMP + select GENERIC_CPU_DEVICES if !SMP select GENERIC_LIB_DEVMEM_IS_ALLOWED select SYSCTL_ARCH_UNALIGN_ALLOW select SYSCTL_EXCEPTION_TRACE diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig index a5fee10d76ee..8ce0ae370680 100644 --- a/arch/parisc/configs/generic-32bit_defconfig +++ b/arch/parisc/configs/generic-32bit_defconfig @@ -6,6 +6,9 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=16 +CONFIG_CGROUPS=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_PERF_EVENTS=y @@ -47,7 +50,6 @@ CONFIG_PARPORT=y CONFIG_PARPORT_PC=m CONFIG_PARPORT_1284=y CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_CRYPTOLOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=6144 CONFIG_BLK_DEV_SD=y diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 1b8fd80cbe7f..57501b0aed92 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -16,6 +16,7 @@ CONFIG_CGROUPS=y CONFIG_MEMCG=y CONFIG_CGROUP_PIDS=y CONFIG_CPUSETS=y +CONFIG_USER_NS=y CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -267,9 +268,9 @@ CONFIG_CRYPTO_DEFLATE=m CONFIG_CRC_CCITT=m CONFIG_LIBCRC32C=y CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_KERNEL=y CONFIG_STRIP_ASM_SYMS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index e8b4a03343d3..8d03b3b26229 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -59,20 +59,12 @@ void flush_dcache_page(struct page *page); flush_kernel_icache_range_asm(s,e); \ } while (0) -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ -do { \ - flush_cache_page(vma, vaddr, page_to_pfn(page)); \ - memcpy(dst, src, len); \ - flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); \ -} while (0) - -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ -do { \ - flush_cache_page(vma, vaddr, page_to_pfn(page)); \ - memcpy(dst, src, len); \ -} while (0) - -void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn); +void copy_to_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len); +void copy_from_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len); +void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, + unsigned long pfn); void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -80,16 +72,7 @@ void flush_cache_range(struct vm_area_struct *vma, void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); #define ARCH_HAS_FLUSH_ANON_PAGE -static inline void -flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) -{ - if (PageAnon(page)) { - flush_tlb_page(vma, vmaddr); - preempt_disable(); - flush_dcache_page_asm(page_to_phys(page), vmaddr); - preempt_enable(); - } -} +void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr); #define ARCH_HAS_FLUSH_ON_KUNMAP static inline void kunmap_flush_on_unmap(void *addr) diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index 0561568f7b48..6faaaa3ebe9b 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -26,12 +26,14 @@ #define copy_page(to, from) copy_page_asm((void *)(to), (void *)(from)) struct page; +struct vm_area_struct; void clear_page_asm(void *page); void copy_page_asm(void *to, void *from); #define clear_user_page(vto, vaddr, page) clear_page_asm(vto) -void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, - struct page *pg); +void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, + struct vm_area_struct *vma); +#define __HAVE_ARCH_COPY_USER_HIGHPAGE /* * These are used to make use of C type-checking.. diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 939db6fe620b..69765a6dbe89 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -160,7 +160,7 @@ extern void __update_cache(pte_t pte); #define SPACEID_SHIFT (MAX_ADDRBITS - 32) #else #define MAX_ADDRBITS (BITS_PER_LONG) -#define MAX_ADDRESS (1UL << MAX_ADDRBITS) +#define MAX_ADDRESS (1ULL << MAX_ADDRBITS) #define SPACEID_SHIFT 0 #endif diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 23348199f3f8..0fd04073d4b6 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -27,6 +27,7 @@ #include <asm/processor.h> #include <asm/sections.h> #include <asm/shmparam.h> +#include <asm/mmu_context.h> int split_tlb __ro_after_init; int dcache_stride __ro_after_init; @@ -91,7 +92,7 @@ static inline void flush_data_cache(void) } -/* Virtual address of pfn. */ +/* Kernel virtual address of pfn. */ #define pfn_va(pfn) __va(PFN_PHYS(pfn)) void @@ -124,11 +125,13 @@ show_cache_info(struct seq_file *m) cache_info.ic_size/1024 ); if (cache_info.dc_loop != 1) snprintf(buf, 32, "%lu-way associative", cache_info.dc_loop); - seq_printf(m, "D-cache\t\t: %ld KB (%s%s, %s)\n", + seq_printf(m, "D-cache\t\t: %ld KB (%s%s, %s, alias=%d)\n", cache_info.dc_size/1024, (cache_info.dc_conf.cc_wt ? "WT":"WB"), (cache_info.dc_conf.cc_sh ? ", shared I/D":""), - ((cache_info.dc_loop == 1) ? "direct mapped" : buf)); + ((cache_info.dc_loop == 1) ? "direct mapped" : buf), + cache_info.dc_conf.cc_alias + ); seq_printf(m, "ITLB entries\t: %ld\n" "DTLB entries\t: %ld%s\n", cache_info.it_size, cache_info.dt_size, @@ -324,25 +327,81 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, preempt_enable(); } -static inline void -__purge_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, - unsigned long physaddr) +static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr) { - if (!static_branch_likely(&parisc_has_cache)) - return; + unsigned long flags, space, pgd, prot; +#ifdef CONFIG_TLB_PTLOCK + unsigned long pgd_lock; +#endif + + vmaddr &= PAGE_MASK; + preempt_disable(); - purge_dcache_page_asm(physaddr, vmaddr); + + /* Set context for flush */ + local_irq_save(flags); + prot = mfctl(8); + space = mfsp(SR_USER); + pgd = mfctl(25); +#ifdef CONFIG_TLB_PTLOCK + pgd_lock = mfctl(28); +#endif + switch_mm_irqs_off(NULL, vma->vm_mm, NULL); + local_irq_restore(flags); + + flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE); if (vma->vm_flags & VM_EXEC) - flush_icache_page_asm(physaddr, vmaddr); + flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE); + flush_tlb_page(vma, vmaddr); + + /* Restore previous context */ + local_irq_save(flags); +#ifdef CONFIG_TLB_PTLOCK + mtctl(pgd_lock, 28); +#endif + mtctl(pgd, 25); + mtsp(space, SR_USER); + mtctl(prot, 8); + local_irq_restore(flags); + preempt_enable(); } +static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr) +{ + pte_t *ptep = NULL; + pgd_t *pgd = mm->pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + if (!pgd_none(*pgd)) { + p4d = p4d_offset(pgd, addr); + if (!p4d_none(*p4d)) { + pud = pud_offset(p4d, addr); + if (!pud_none(*pud)) { + pmd = pmd_offset(pud, addr); + if (!pmd_none(*pmd)) + ptep = pte_offset_map(pmd, addr); + } + } + } + return ptep; +} + +static inline bool pte_needs_flush(pte_t pte) +{ + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_NO_CACHE)) + == (_PAGE_PRESENT | _PAGE_ACCESSED); +} + void flush_dcache_page(struct page *page) { struct address_space *mapping = page_mapping_file(page); struct vm_area_struct *mpnt; unsigned long offset; unsigned long addr, old_addr = 0; + unsigned long count = 0; pgoff_t pgoff; if (mapping && !mapping_mapped(mapping)) { @@ -357,33 +416,52 @@ void flush_dcache_page(struct page *page) pgoff = page->index; - /* We have carefully arranged in arch_get_unmapped_area() that + /* + * We have carefully arranged in arch_get_unmapped_area() that * *any* mappings of a file are always congruently mapped (whether * declared as MAP_PRIVATE or MAP_SHARED), so we only need - * to flush one address here for them all to become coherent */ - + * to flush one address here for them all to become coherent + * on machines that support equivalent aliasing + */ flush_dcache_mmap_lock(mapping); vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT; addr = mpnt->vm_start + offset; + if (parisc_requires_coherency()) { + pte_t *ptep; - /* The TLB is the engine of coherence on parisc: The - * CPU is entitled to speculate any page with a TLB - * mapping, so here we kill the mapping then flush the - * page along a special flush only alias mapping. - * This guarantees that the page is no-longer in the - * cache for any process and nor may it be - * speculatively read in (until the user or kernel - * specifically accesses it, of course) */ - - flush_tlb_page(mpnt, addr); - if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) - != (addr & (SHM_COLOUR - 1))) { - __flush_cache_page(mpnt, addr, page_to_phys(page)); - if (parisc_requires_coherency() && old_addr) - printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", old_addr, addr, mpnt->vm_file); - old_addr = addr; + ptep = get_ptep(mpnt->vm_mm, addr); + if (ptep && pte_needs_flush(*ptep)) + flush_user_cache_page(mpnt, addr); + } else { + /* + * The TLB is the engine of coherence on parisc: + * The CPU is entitled to speculate any page + * with a TLB mapping, so here we kill the + * mapping then flush the page along a special + * flush only alias mapping. This guarantees that + * the page is no-longer in the cache for any + * process and nor may it be speculatively read + * in (until the user or kernel specifically + * accesses it, of course) + */ + flush_tlb_page(mpnt, addr); + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { + __flush_cache_page(mpnt, addr, page_to_phys(page)); + /* + * Software is allowed to have any number + * of private mappings to a page. + */ + if (!(mpnt->vm_flags & VM_SHARED)) + continue; + if (old_addr) + pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", + old_addr, addr, mpnt->vm_file); + old_addr = addr; + } } + WARN_ON(++count == 4096); } flush_dcache_mmap_unlock(mapping); } @@ -417,23 +495,16 @@ void __init parisc_setup_cache_timing(void) printk(KERN_DEBUG "Whole cache flush %lu cycles, flushing %lu bytes %lu cycles\n", alltime, size, rangetime); - threshold = L1_CACHE_ALIGN(size * alltime / rangetime); + threshold = L1_CACHE_ALIGN((unsigned long)((uint64_t)size * alltime / rangetime)); + pr_info("Calculated flush threshold is %lu KiB\n", + threshold/1024); /* - * The threshold computed above isn't very reliable since the - * flush times depend greatly on the percentage of dirty lines - * in the flush range. Further, the whole cache time doesn't - * include the time to refill lines that aren't in the mm/vma - * being flushed. By timing glibc build and checks on mako cpus, - * the following formula seems to work reasonably well. The - * value from the timing calculation is too small, and increases - * build and check times by almost a factor two. + * The threshold computed above isn't very reliable. The following + * heuristic works reasonably well on c8000/rp3440. */ threshold2 = cache_info.dc_size * num_online_cpus(); - if (threshold2 > threshold) - threshold = threshold2; - if (threshold) - parisc_cache_flush_threshold = threshold; + parisc_cache_flush_threshold = threshold2; printk(KERN_INFO "Cache flush threshold set to %lu KiB\n", parisc_cache_flush_threshold/1024); @@ -489,19 +560,47 @@ void flush_kernel_dcache_page_addr(void *addr) } EXPORT_SYMBOL(flush_kernel_dcache_page_addr); -void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, - struct page *pg) +static void flush_cache_page_if_present(struct vm_area_struct *vma, + unsigned long vmaddr, unsigned long pfn) { - /* Copy using kernel mapping. No coherency is needed (all in - kunmap) for the `to' page. However, the `from' page needs to - be flushed through a mapping equivalent to the user mapping - before it can be accessed through the kernel mapping. */ - preempt_disable(); - flush_dcache_page_asm(__pa(vfrom), vaddr); - copy_page_asm(vto, vfrom); - preempt_enable(); + pte_t *ptep = get_ptep(vma->vm_mm, vmaddr); + + /* + * The pte check is racy and sometimes the flush will trigger + * a non-access TLB miss. Hopefully, the page has already been + * flushed. + */ + if (ptep && pte_needs_flush(*ptep)) + flush_cache_page(vma, vmaddr, pfn); +} + +void copy_user_highpage(struct page *to, struct page *from, + unsigned long vaddr, struct vm_area_struct *vma) +{ + void *kto, *kfrom; + + kfrom = kmap_local_page(from); + kto = kmap_local_page(to); + flush_cache_page_if_present(vma, vaddr, page_to_pfn(from)); + copy_page_asm(kto, kfrom); + kunmap_local(kto); + kunmap_local(kfrom); +} + +void copy_to_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len) +{ + flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + memcpy(dst, src, len); + flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); +} + +void copy_from_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len) +{ + flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + memcpy(dst, src, len); } -EXPORT_SYMBOL(copy_user_page); /* __flush_tlb_range() * @@ -532,92 +631,105 @@ int __flush_tlb_range(unsigned long sid, unsigned long start, return 0; } -static inline unsigned long mm_total_size(struct mm_struct *mm) +static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - struct vm_area_struct *vma; - unsigned long usize = 0; - - for (vma = mm->mmap; vma; vma = vma->vm_next) - usize += vma->vm_end - vma->vm_start; - return usize; -} - -static inline pte_t *get_ptep(pgd_t *pgd, unsigned long addr) -{ - pte_t *ptep = NULL; + unsigned long addr, pfn; + pte_t *ptep; - if (!pgd_none(*pgd)) { - p4d_t *p4d = p4d_offset(pgd, addr); - if (!p4d_none(*p4d)) { - pud_t *pud = pud_offset(p4d, addr); - if (!pud_none(*pud)) { - pmd_t *pmd = pmd_offset(pud, addr); - if (!pmd_none(*pmd)) - ptep = pte_offset_map(pmd, addr); + for (addr = start; addr < end; addr += PAGE_SIZE) { + /* + * The vma can contain pages that aren't present. Although + * the pte search is expensive, we need the pte to find the + * page pfn and to check whether the page should be flushed. + */ + ptep = get_ptep(vma->vm_mm, addr); + if (ptep && pte_needs_flush(*ptep)) { + if (parisc_requires_coherency()) { + flush_user_cache_page(vma, addr); + } else { + pfn = pte_pfn(*ptep); + if (WARN_ON(!pfn_valid(pfn))) + return; + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); } } } - return ptep; } -static void flush_cache_pages(struct vm_area_struct *vma, struct mm_struct *mm, - unsigned long start, unsigned long end) +static inline unsigned long mm_total_size(struct mm_struct *mm) { - unsigned long addr, pfn; - pte_t *ptep; + struct vm_area_struct *vma; + unsigned long usize = 0; - for (addr = start; addr < end; addr += PAGE_SIZE) { - ptep = get_ptep(mm->pgd, addr); - if (ptep) { - pfn = pte_pfn(*ptep); - flush_cache_page(vma, addr, pfn); - } - } + for (vma = mm->mmap; vma && usize < parisc_cache_flush_threshold; vma = vma->vm_next) + usize += vma->vm_end - vma->vm_start; + return usize; } void flush_cache_mm(struct mm_struct *mm) { struct vm_area_struct *vma; - /* Flushing the whole cache on each cpu takes forever on - rp3440, etc. So, avoid it if the mm isn't too big. */ - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - mm_total_size(mm) >= parisc_cache_flush_threshold) { - if (mm->context.space_id) - flush_tlb_all(); + /* + * Flushing the whole cache on each cpu takes forever on + * rp3440, etc. So, avoid it if the mm isn't too big. + * + * Note that we must flush the entire cache on machines + * with aliasing caches to prevent random segmentation + * faults. + */ + if (!parisc_requires_coherency() + || mm_total_size(mm) >= parisc_cache_flush_threshold) { + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) + return; + flush_tlb_all(); flush_cache_all(); return; } + /* Flush mm */ for (vma = mm->mmap; vma; vma = vma->vm_next) - flush_cache_pages(vma, mm, vma->vm_start, vma->vm_end); + flush_cache_pages(vma, vma->vm_start, vma->vm_end); } -void flush_cache_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) +void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - end - start >= parisc_cache_flush_threshold) { - if (vma->vm_mm->context.space_id) - flush_tlb_range(vma, start, end); + if (!parisc_requires_coherency() + || end - start >= parisc_cache_flush_threshold) { + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) + return; + flush_tlb_range(vma, start, end); flush_cache_all(); return; } - flush_cache_pages(vma, vma->vm_mm, start, end); + flush_cache_pages(vma, start, end); } -void -flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) +void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - if (pfn_valid(pfn)) { - if (likely(vma->vm_mm->context.space_id)) { - flush_tlb_page(vma, vmaddr); - __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); - } else { - __purge_cache_page(vma, vmaddr, PFN_PHYS(pfn)); - } + if (WARN_ON(!pfn_valid(pfn))) + return; + if (parisc_requires_coherency()) + flush_user_cache_page(vma, vmaddr); + else + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); +} + +void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) +{ + if (!PageAnon(page)) + return; + + if (parisc_requires_coherency()) { + flush_user_cache_page(vma, vmaddr); + return; } + + flush_tlb_page(vma, vmaddr); + preempt_disable(); + flush_dcache_page_asm(page_to_phys(page), vmaddr); + preempt_enable(); } void flush_kernel_vmap_range(void *vaddr, int size) diff --git a/arch/parisc/kernel/kprobes.c b/arch/parisc/kernel/kprobes.c index 3343d2fb7889..6e0b86652f30 100644 --- a/arch/parisc/kernel/kprobes.c +++ b/arch/parisc/kernel/kprobes.c @@ -152,7 +152,7 @@ int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs) /* for absolute branch instructions we can copy iaoq_b. for relative * branch instructions we need to calculate the new address based on the * difference between iaoq_f and iaoq_b. We cannot use iaoq_b without - * modificationt because it's based on our ainsn.insn address. + * modifications because it's based on our ainsn.insn address. */ if (p->post_handler) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index d98692115221..26eb568f8b96 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -171,6 +171,7 @@ static int __init processor_probe(struct parisc_device *dev) p->cpu_num = cpu_info.cpu_num; p->cpu_loc = cpu_info.cpu_loc; + set_cpu_possible(cpuid, true); store_cpu_topology(cpuid); #ifdef CONFIG_SMP @@ -419,8 +420,7 @@ show_cpuinfo (struct seq_file *m, void *v) } seq_printf(m, " (0x%02lx)\n", boot_cpu_data.pdc.capabilities); - seq_printf(m, "model\t\t: %s\n" - "model name\t: %s\n", + seq_printf(m, "model\t\t: %s - %s\n", boot_cpu_data.pdc.sys_model_name, cpuinfo->dev ? cpuinfo->dev->name : "Unknown"); @@ -461,6 +461,13 @@ static struct parisc_driver cpu_driver __refdata = { */ void __init processor_init(void) { + unsigned int cpu; + reset_cpu_topology(); + + /* reset possible mask. We will mark those which are possible. */ + for_each_possible_cpu(cpu) + set_cpu_possible(cpu, false); + register_parisc_driver(&cpu_driver); } diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index b91cb45ffd4e..f005ddedb50e 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -161,6 +161,8 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_PA11 dma_ops_init(); #endif + + clear_sched_clock_stable(); } /* diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index bb27dfeeddfc..9714fbd7c42d 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -251,13 +251,9 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs, even if - * they share the same socket. + * The cr16 interval timers are not synchronized across CPUs. */ if (num_online_cpus() > 1 && !running_on_qemu) { - /* mark sched_clock unstable */ - clear_sched_clock_stable(); - clocksource_cr16.name = "cr16_unstable"; clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; clocksource_cr16.rating = 0; diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index a6e61cf2cad0..b78f1b9d45c1 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -469,7 +469,7 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o * panic notifiers, and we should call panic * directly from the location that we wish. * e.g. We should not call panic from - * parisc_terminate, but rather the oter way around. + * parisc_terminate, but rather the other way around. * This hack works, prints the panic message twice, * and it enables reboot timers! */ diff --git a/arch/parisc/math-emu/dfadd.c b/arch/parisc/math-emu/dfadd.c index ec487e07f004..00e561d4aa55 100644 --- a/arch/parisc/math-emu/dfadd.c +++ b/arch/parisc/math-emu/dfadd.c @@ -253,7 +253,7 @@ dbl_fadd( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/dfsub.c b/arch/parisc/math-emu/dfsub.c index c4f30acf2d48..4f03782284bd 100644 --- a/arch/parisc/math-emu/dfsub.c +++ b/arch/parisc/math-emu/dfsub.c @@ -256,7 +256,7 @@ dbl_fsub( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/sfadd.c b/arch/parisc/math-emu/sfadd.c index 838758279d5b..9b98c874dfac 100644 --- a/arch/parisc/math-emu/sfadd.c +++ b/arch/parisc/math-emu/sfadd.c @@ -249,7 +249,7 @@ sgl_fadd( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/sfsub.c b/arch/parisc/math-emu/sfsub.c index 583d3ace4634..29d9eed09d12 100644 --- a/arch/parisc/math-emu/sfsub.c +++ b/arch/parisc/math-emu/sfsub.c @@ -252,7 +252,7 @@ sgl_fsub( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..84bc437be5cd 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -22,6 +22,8 @@ #include <asm/traps.h> +#define DEBUG_NATLB 0 + /* Various important other fields */ #define bit22set(x) (x & 0x00000200) #define bits23_25set(x) (x & 0x000001c0) @@ -450,8 +452,8 @@ handle_nadtlb_fault(struct pt_regs *regs) fallthrough; case 0x380: /* PDC and FIC instructions */ - if (printk_ratelimit()) { - pr_warn("BUG: nullifying cache flush/purge instruction\n"); + if (DEBUG_NATLB && printk_ratelimit()) { + pr_warn("WARNING: nullifying cache flush/purge instruction\n"); show_regs(regs); } if (insn & 0x20) { diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 827038a33064..4def2bd17b9b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -16,18 +16,6 @@ #include <asm/ppc-opcode.h> #include <asm/pte-walk.h> -#ifdef CONFIG_PPC_PSERIES -static inline bool kvmhv_on_pseries(void) -{ - return !cpu_has_feature(CPU_FTR_HVMODE); -} -#else -static inline bool kvmhv_on_pseries(void) -{ - return false; -} -#endif - /* * Structure for a nested guest, that is, for a guest that is managed by * one of our guests. diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c583d0c37f31..838d4cb460b7 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -586,6 +586,18 @@ static inline bool kvm_hv_mode_active(void) { return false; } #endif +#ifdef CONFIG_PPC_PSERIES +static inline bool kvmhv_on_pseries(void) +{ + return !cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool kvmhv_on_pseries(void) +{ + return false; +} +#endif + #ifdef CONFIG_KVM_XICS static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 254687258f42..f2c5c26869f1 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -132,7 +132,11 @@ static inline bool pfn_valid(unsigned long pfn) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \ + pfn_valid(virt_to_pfn(_addr)); \ +}) /* * On Book-E parts we need __va to parse the device tree and we can't diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 049ca26893e6..8fa37ef5da4d 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -28,11 +28,13 @@ void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES +extern bool pseries_reloc_on_exception(void); extern bool pseries_enable_reloc_on_exc(void); extern void pseries_disable_reloc_on_exc(void); extern void pseries_big_endian_exceptions(void); void __init pseries_little_endian_exceptions(void); #else +static inline bool pseries_reloc_on_exception(void) { return false; } static inline bool pseries_enable_reloc_on_exc(void) { return false; } static inline void pseries_disable_reloc_on_exc(void) {} static inline void pseries_big_endian_exceptions(void) {} diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h index 0a0bc79bd1fa..de1018cc522b 100644 --- a/arch/powerpc/include/asm/static_call.h +++ b/arch/powerpc/include/asm/static_call.h @@ -24,5 +24,6 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) __PPC_SCT(name, "b .+20") #endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 55caeee37c08..b66dd6f775a4 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -809,6 +809,10 @@ __start_interrupts: * - MSR_EE|MSR_RI is clear (no reentrant exceptions) * - Standard kernel environment is set up (stack, paca, etc) * + * KVM: + * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM + * ensures that FSCR[SCV] is disabled whenever it has to force AIL off. + * * Call convention: * * syscall register convention is in Documentation/powerpc/syscall64-abi.rst diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 40a583e9d3c7..97a76a8619fb 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -101,7 +101,7 @@ __module_alloc(unsigned long size, unsigned long start, unsigned long end, bool * too. */ return __vmalloc_node_range(size, 1, start, end, gfp, prot, - VM_FLUSH_RESET_PERMS | VM_NO_HUGE_VMAP, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e547066a06aa..a96f05063bc9 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -196,6 +196,34 @@ static void __init configure_exceptions(void) /* Under a PAPR hypervisor, we need hypercalls */ if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* + * - PR KVM does not support AIL mode interrupts in the host + * while a PR guest is running. + * + * - SCV system call interrupt vectors are only implemented for + * AIL mode interrupts. + * + * - On pseries, AIL mode can only be enabled and disabled + * system-wide so when a PR VM is created on a pseries host, + * all CPUs of the host are set to AIL=0 mode. + * + * - Therefore host CPUs must not execute scv while a PR VM + * exists. + * + * - SCV support can not be disabled dynamically because the + * feature is advertised to host userspace. Disabling the + * facility and emulating it would be possible but is not + * implemented. + * + * - So SCV support is blanket disabled if PR KVM could possibly + * run. That is, PR support compiled in, booting on pseries + * with hash MMU. + */ + if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) { + init_task.thread.fscr &= ~FSCR_SCV; + cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV; + } + /* Enable AIL if possible */ if (!pseries_enable_reloc_on_exc()) { init_task.thread.fscr &= ~FSCR_SCV; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f5cbfe5efd25..f80cce0e3899 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -615,23 +615,22 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) return; } - /* Conditionally hard-enable interrupts. */ - if (should_hard_irq_enable()) { - /* - * Ensure a positive value is written to the decrementer, or - * else some CPUs will continue to take decrementer exceptions. - * When the PPC_WATCHDOG (decrementer based) is configured, - * keep this at most 31 bits, which is about 4 seconds on most - * systems, which gives the watchdog a chance of catching timer - * interrupt hard lockups. - */ - if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) - set_dec(0x7fffffff); - else - set_dec(decrementer_max); + /* + * Ensure a positive value is written to the decrementer, or + * else some CPUs will continue to take decrementer exceptions. + * When the PPC_WATCHDOG (decrementer based) is configured, + * keep this at most 31 bits, which is about 4 seconds on most + * systems, which gives the watchdog a chance of catching timer + * interrupt hard lockups. + */ + if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) + set_dec(0x7fffffff); + else + set_dec(decrementer_max); + /* Conditionally hard-enable interrupts. */ + if (should_hard_irq_enable()) do_hard_irq_enable(); - } #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index eb9c81e1c218..0c4ecc8fec5a 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -22,12 +22,15 @@ .macro cvdso_call funct call_time=0 .cfi_startproc PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM mflr r0 - .cfi_register lr, r0 PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) + .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF #ifdef __powerpc64__ PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT #endif get_datapage r5 .ifeq \call_time @@ -39,13 +42,15 @@ PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) #ifdef __powerpc64__ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_restore r2 #endif .ifeq \call_time cmpwi r3, 0 .endif mtlr r0 - .cfi_restore lr addi r1, r1, 2 * PPC_MIN_STKFRM + .cfi_restore lr + .cfi_def_cfa_offset 0 crclr so .ifeq \call_time beqlr+ diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 18e58085447c..ddd88179110a 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -112,12 +112,21 @@ config KVM_BOOK3S_64_PR guest in user mode (problem state) and emulating all privileged instructions and registers. + This is only available for hash MMU mode and only supports + guests that use hash MMU mode. + This is not as fast as using hypervisor mode, but works on machines where hypervisor mode is not available or not usable, and can emulate processors that are different from the host processor, including emulating 32-bit processors on a 64-bit host. + Selecting this option will cause the SCV facility to be + disabled when the kernel is booted on the pseries platform in + hash MMU mode (regardless of PR VMs running). When any PR VMs + are running, "AIL" mode is disabled which may slow interrupts + and system calls on the host. + config KVM_BOOK3S_HV_EXIT_TIMING bool "Detailed timing for hypervisor real-mode code" depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS diff --git a/arch/powerpc/kvm/book3s_32_sr.S b/arch/powerpc/kvm/book3s_32_sr.S index e3ab9df6cf19..6cfcd20d4668 100644 --- a/arch/powerpc/kvm/book3s_32_sr.S +++ b/arch/powerpc/kvm/book3s_32_sr.S @@ -122,11 +122,27 @@ /* 0x0 - 0xb */ - /* 'current->mm' needs to be in r4 */ - tophys(r4, r2) - lwz r4, MM(r4) - tophys(r4, r4) - /* This only clobbers r0, r3, r4 and r5 */ + /* switch_mmu_context() needs paging, let's enable it */ + mfmsr r9 + ori r11, r9, MSR_DR + mtmsr r11 + sync + + /* switch_mmu_context() clobbers r12, rescue it */ + SAVE_GPR(12, r1) + + /* Calling switch_mmu_context(<inv>, current->mm, <inv>); */ + lwz r4, MM(r2) bl switch_mmu_context + /* restore r12 */ + REST_GPR(12, r1) + + /* Disable paging again */ + mfmsr r9 + li r6, MSR_DR + andc r9, r9, r6 + mtmsr r9 + sync + .endm diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 05e003eb5d90..e42d1c609e47 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -414,10 +414,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) */ ld r10,HSTATE_SCRATCH0(r13) cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK - beq machine_check_common + beq .Lcall_machine_check_common cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET - beq system_reset_common + beq .Lcall_system_reset_common b . + +.Lcall_machine_check_common: + b machine_check_common + +.Lcall_system_reset_common: + b system_reset_common #endif diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index e4ce2a35483f..42851c32ff3b 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -168,9 +168,10 @@ int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr, return -EINVAL; /* Read the entry from guest memory */ addr = base + (index * sizeof(rpte)); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (ret) { if (pte_ret_p) *pte_ret_p = addr; @@ -246,9 +247,9 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr, /* Read the table to find the root of the radix tree */ ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry)); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (ret) return ret; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d42b4b6d4a79..85cfa6328222 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -420,13 +420,19 @@ static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt, tbl[idx % TCES_PER_PAGE] = tce; } -static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_clear_tce(struct mm_struct *mm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_no_kill(mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill(mm, tbl, io_entry + i, &hpa, &dir); + } } static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm, @@ -485,6 +491,8 @@ static long kvmppc_tce_iommu_unmap(struct kvm *kvm, break; } + iommu_tce_kill(tbl, io_entry, subpages); + return ret; } @@ -544,6 +552,8 @@ static long kvmppc_tce_iommu_map(struct kvm *kvm, break; } + iommu_tce_kill(tbl, io_entry, subpages); + return ret; } @@ -590,10 +600,9 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); - iommu_tce_kill(stit->tbl, entry, 1); if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry); goto unlock_exit; } } @@ -669,13 +678,13 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, */ if (get_user(tce, tces + i)) { ret = H_TOO_HARD; - goto invalidate_exit; + goto unlock_exit; } tce = be64_to_cpu(tce); if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -684,19 +693,15 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce)); if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, + entry + i); + goto unlock_exit; } } kvmppc_tce_put(stt, entry + i, tce); } -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, entry, npages); - unlock_exit: srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -735,20 +740,16 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret; WARN_ON_ONCE(1); - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry + i); } } for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value); -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, ioba >> stt->page_shift, npages); - return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 870b7f0c7ea5..fdeda6a9cff4 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -247,13 +247,19 @@ static void iommu_tce_kill_rm(struct iommu_table *tbl, tbl->it_ops->tce_kill(tbl, entry, pages, true); } -static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_rm_clear_tce(struct kvm *kvm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, io_entry + i, &hpa, &dir); + } } static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -316,6 +322,8 @@ static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm, break; } + iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; } @@ -379,6 +387,8 @@ static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, break; } + iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; } @@ -420,10 +430,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); - iommu_tce_kill_rm(stit->tbl, entry, 1); - if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry); return ret; } } @@ -561,7 +569,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, ua = 0; if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -570,19 +578,15 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce)); if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, + entry + i); + goto unlock_exit; } } kvmppc_rm_tce_put(stt, entry + i, tce); } -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, entry, npages); - unlock_exit: if (!prereg) arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock); @@ -620,20 +624,16 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry + i); } } for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value); -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages); - return ret; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index c886557638a1..6fa518f6501d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -225,6 +225,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) int cpu; struct rcuwait *waitp; + /* + * rcuwait_wake_up contains smp_mb() which orders prior stores that + * create pending work vs below loads of cpu fields. The other side + * is the barrier in vcpu run that orders setting the cpu fields vs + * testing for pending work. + */ + waitp = kvm_arch_vcpu_get_wait(vcpu); if (rcuwait_wake_up(waitp)) ++vcpu->stat.generic.halt_wakeup; @@ -1089,7 +1096,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) break; } tvcpu->arch.prodded = 1; - smp_mb(); + smp_mb(); /* This orders prodded store vs ceded load */ if (tvcpu->arch.ceded) kvmppc_fast_vcpu_kick_hv(tvcpu); break; @@ -3766,6 +3773,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) pvc = core_info.vc[sub]; pvc->pcpu = pcpu + thr; for_each_runnable_thread(i, vcpu, pvc) { + /* + * XXX: is kvmppc_start_thread called too late here? + * It updates vcpu->cpu and vcpu->arch.thread_cpu + * which are used by kvmppc_fast_vcpu_kick_hv(), but + * kick is called after new exceptions become available + * and exceptions are checked earlier than here, by + * kvmppc_core_prepare_to_enter. + */ kvmppc_start_thread(vcpu, pvc); kvmppc_create_dtl_entry(vcpu, pvc); trace_kvm_guest_enter(vcpu); @@ -4487,6 +4502,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, if (need_resched() || !kvm->arch.mmu_ready) goto out; + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + /* + * Orders set cpu/thread_cpu vs testing for pending interrupts and + * doorbells below. The other side is when these fields are set vs + * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to + * kick a vCPU to notice the pending interrupt. + */ + smp_mb(); + if (!nested) { kvmppc_core_prepare_to_enter(vcpu); if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, @@ -4506,13 +4536,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, tb = mftb(); - vcpu->cpu = pcpu; - vcpu->arch.thread_cpu = pcpu; - vc->pcpu = pcpu; - local_paca->kvm_hstate.kvm_vcpu = vcpu; - local_paca->kvm_hstate.ptid = 0; - local_paca->kvm_hstate.fake_suspend = 0; - __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); trace_kvm_guest_enter(vcpu); @@ -4614,6 +4637,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 9d373f8963ee..c943a051c6e7 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -306,10 +306,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* copy parameters in */ hv_ptr = kvmppc_get_gpr(vcpu, 4); regs_ptr = kvmppc_get_gpr(vcpu, 5); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); err = kvmhv_read_guest_state_and_regs(vcpu, &l2_hv, &l2_regs, hv_ptr, regs_ptr); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (err) return H_PARAMETER; @@ -410,10 +410,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) byteswap_hv_regs(&l2_hv); byteswap_pt_regs(&l2_regs); } - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); err = kvmhv_write_guest_state_and_regs(vcpu, &l2_hv, &l2_regs, hv_ptr, regs_ptr); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (err) return H_AUTHORITY; @@ -600,16 +600,16 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) goto not_found; /* Write what was loaded into our buffer back to the L1 guest */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto not_found; } else { /* Load the data to be stored from the L1 guest into our buf */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto not_found; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 34a801c3604a..7bf9e6ca5c2d 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -137,12 +137,15 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max; svcpu->in_use = 0; svcpu_put(svcpu); -#endif /* Disable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) & ~FSCR_SCV); + } +#endif vcpu->cpu = smp_processor_id(); #ifdef CONFIG_PPC_BOOK3S_32 @@ -165,6 +168,14 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb)); to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max; svcpu_put(svcpu); + + /* Enable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) | FSCR_SCV); + } #endif if (kvmppc_is_split_real(vcpu)) @@ -174,11 +185,6 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); kvmppc_save_tm_pr(vcpu); - /* Enable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); - vcpu->cpu = -1; } @@ -1037,6 +1043,8 @@ static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac) void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr) { + if (fscr & FSCR_SCV) + fscr &= ~FSCR_SCV; /* SCV must not be enabled */ if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) { /* TAR got dropped, drop it in shadow too */ kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 1f10e7dfcdd0..dc4f51ac84bc 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -281,6 +281,22 @@ static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +static int kvmppc_h_pr_set_mode(struct kvm_vcpu *vcpu) +{ + unsigned long mflags = kvmppc_get_gpr(vcpu, 4); + unsigned long resource = kvmppc_get_gpr(vcpu, 5); + + if (resource == H_SET_MODE_RESOURCE_ADDR_TRANS_MODE) { + /* KVM PR does not provide AIL!=0 to guests */ + if (mflags == 0) + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + else + kvmppc_set_gpr(vcpu, 3, H_UNSUPPORTED_FLAG_START - 63); + return EMULATE_DONE; + } + return EMULATE_FAIL; +} + #ifdef CONFIG_SPAPR_TCE_IOMMU static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) { @@ -384,6 +400,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_logical_ci_load(vcpu); case H_LOGICAL_CI_STORE: return kvmppc_h_pr_logical_ci_store(vcpu); + case H_SET_MODE: + return kvmppc_h_pr_set_mode(vcpu); case H_XIRR: case H_CPPR: case H_EOI: @@ -421,6 +439,7 @@ int kvmppc_hcall_impl_pr(unsigned long cmd) case H_CEDE: case H_LOGICAL_CI_LOAD: case H_LOGICAL_CI_STORE: + case H_SET_MODE: #ifdef CONFIG_KVM_XICS case H_XIRR: case H_CPPR: @@ -447,6 +466,7 @@ static unsigned int default_hcall_list[] = { H_BULK_REMOVE, H_PUT_TCE, H_CEDE, + H_SET_MODE, #ifdef CONFIG_KVM_XICS H_XIRR, H_CPPR, diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 0f847f1e5ddd..6808bda0dbc1 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -229,9 +229,9 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) */ args_phys = kvmppc_get_gpr(vcpu, 4) & KVM_PAM; - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args)); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto fail; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9772b176e406..533c4232e5ab 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -425,9 +425,9 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, return EMULATE_DONE; } - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) return EMULATE_DO_MMIO; @@ -705,6 +705,23 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; #endif + case KVM_CAP_PPC_AIL_MODE_3: + r = 0; + /* + * KVM PR, POWER7, and some POWER9s don't support AIL=3 mode. + * The POWER9s can support it if the guest runs in hash mode, + * but QEMU doesn't necessarily query the capability in time. + */ + if (hv_enabled) { + if (kvmhv_on_pseries()) { + if (pseries_reloc_on_exception()) + r = 1; + } else if (cpu_has_feature(CPU_FTR_ARCH_207S) && + !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) { + r = 1; + } + } + break; default: r = 0; break; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8e301cd8925b..4d221d033804 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -255,7 +255,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_pfn); kasan_late_init(); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b9b7fefbb64b..13022d734951 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1436,7 +1436,7 @@ int find_and_online_cpu_nid(int cpu) if (new_nid < 0 || !node_possible(new_nid)) new_nid = first_online_node; - if (NODE_DATA(new_nid) == NULL) { + if (!node_online(new_nid)) { #ifdef CONFIG_MEMORY_HOTPLUG /* * Need to ensure that NODE_DATA is initialized for a node from diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile index 2f46e31c7612..4f53d0b97539 100644 --- a/arch/powerpc/perf/Makefile +++ b/arch/powerpc/perf/Makefile @@ -3,11 +3,11 @@ obj-y += callchain.o callchain_$(BITS).o perf_regs.o obj-$(CONFIG_COMPAT) += callchain_32.o -obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o bhrb.o +obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o obj64-$(CONFIG_PPC_PERF_CTRS) += ppc970-pmu.o power5-pmu.o \ power5+-pmu.o power6-pmu.o power7-pmu.o \ isa207-common.o power8-pmu.o power9-pmu.o \ - generic-compat-pmu.o power10-pmu.o + generic-compat-pmu.o power10-pmu.o bhrb.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o obj-$(CONFIG_PPC_POWERNV) += imc-pmu.o diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index d3398100a60f..c6d51e7093cf 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -91,8 +91,8 @@ extern u64 PERF_REG_EXTENDED_MASK; /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { - { PM_CYC_ALT, PM_CYC }, { PM_INST_CMPL_ALT, PM_INST_CMPL }, + { PM_CYC_ALT, PM_CYC }, }; static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[]) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index c9eb5232e68b..c393e837648e 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -133,11 +133,11 @@ int p9_dd22_bl_ev[] = { /* Table of alternatives, sorted by column 0 */ static const unsigned int power9_event_alternatives[][MAX_ALT] = { - { PM_INST_DISP, PM_INST_DISP_ALT }, - { PM_RUN_CYC_ALT, PM_RUN_CYC }, - { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, - { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, { PM_BR_2PATH, PM_BR_2PATH_ALT }, + { PM_INST_DISP, PM_INST_DISP_ALT }, + { PM_RUN_CYC_ALT, PM_RUN_CYC }, + { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, + { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, }; static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[]) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f58728d5f10d..39962c905542 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -462,7 +462,6 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu { struct papr_scm_perf_stat *stat; struct papr_scm_perf_stats *stats; - char *statid; int index, rc, count; u32 available_events; @@ -493,14 +492,12 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu for (index = 0, stat = stats->scm_statistic, count = 0; index < available_events; index++, ++stat) { - statid = kzalloc(strlen(stat->stat_id) + 1, GFP_KERNEL); - if (!statid) { + p->nvdimm_events_map[count] = kmemdup_nul(stat->stat_id, 8, GFP_KERNEL); + if (!p->nvdimm_events_map[count]) { rc = -ENOMEM; goto out_nvdimm_events_map; } - strcpy(statid, stat->stat_id); - p->nvdimm_events_map[count] = statid; count++; } p->nvdimm_events_map[count] = NULL; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 069d7b3bb142..955ff8aa1644 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -353,6 +353,14 @@ static void pseries_lpar_idle(void) pseries_idle_epilog(); } +static bool pseries_reloc_on_exception_enabled; + +bool pseries_reloc_on_exception(void) +{ + return pseries_reloc_on_exception_enabled; +} +EXPORT_SYMBOL_GPL(pseries_reloc_on_exception); + /* * Enable relocation on during exceptions. This has partition wide scope and * may take a while to complete, if it takes longer than one second we will @@ -377,6 +385,7 @@ bool pseries_enable_reloc_on_exc(void) " on exceptions: %ld\n", rc); return false; } + pseries_reloc_on_exception_enabled = true; return true; } @@ -404,7 +413,9 @@ void pseries_disable_reloc_on_exc(void) break; mdelay(get_longbusy_msecs(rc)); } - if (rc != H_SUCCESS) + if (rc == H_SUCCESS) + pseries_reloc_on_exception_enabled = false; + else pr_warn("Warning: Failed to disable relocation on exceptions: %ld\n", rc); } diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c index 4a7fcde5afc0..ec65586cbeb3 100644 --- a/arch/powerpc/platforms/pseries/vas-sysfs.c +++ b/arch/powerpc/platforms/pseries/vas-sysfs.c @@ -27,22 +27,31 @@ struct vas_caps_entry { /* * This function is used to get the notification from the drmgr when - * QoS credits are changed. Though receiving the target total QoS - * credits here, get the official QoS capabilities from the hypervisor. + * QoS credits are changed. */ -static ssize_t update_total_credits_trigger(struct vas_cop_feat_caps *caps, +static ssize_t update_total_credits_store(struct vas_cop_feat_caps *caps, const char *buf, size_t count) { int err; u16 creds; err = kstrtou16(buf, 0, &creds); + /* + * The user space interface from the management console + * notifies OS with the new QoS credits and then the + * hypervisor. So OS has to use this new credits value + * and reconfigure VAS windows (close or reopen depends + * on the credits available) instead of depending on VAS + * QoS capabilities from the hypervisor. + */ if (!err) - err = vas_reconfig_capabilties(caps->win_type); + err = vas_reconfig_capabilties(caps->win_type, creds); if (err) return -EINVAL; + pr_info("Set QoS total credits %u\n", creds); + return count; } @@ -92,13 +101,14 @@ VAS_ATTR_RO(nr_total_credits); VAS_ATTR_RO(nr_used_credits); static struct vas_sysfs_entry update_total_credits_attribute = - __ATTR(update_total_credits, 0200, NULL, update_total_credits_trigger); + __ATTR(update_total_credits, 0200, NULL, update_total_credits_store); static struct attribute *vas_def_capab_attrs[] = { &nr_total_credits_attribute.attr, &nr_used_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_def_capab); static struct attribute *vas_qos_capab_attrs[] = { &nr_total_credits_attribute.attr, @@ -106,6 +116,7 @@ static struct attribute *vas_qos_capab_attrs[] = { &update_total_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_qos_capab); static ssize_t vas_type_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -154,13 +165,13 @@ static const struct sysfs_ops vas_sysfs_ops = { static struct kobj_type vas_def_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_def_capab_attrs, + .default_groups = vas_def_capab_groups, }; static struct kobj_type vas_qos_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_qos_capab_attrs, + .default_groups = vas_qos_capab_groups, }; static char *vas_caps_kobj_name(struct vas_caps_entry *centry, diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 1f59d78c77a1..ec643bbdb67f 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -779,10 +779,10 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds, * changes. Reconfig window configurations based on the credits * availability from this new capabilities. */ -int vas_reconfig_capabilties(u8 type) +int vas_reconfig_capabilties(u8 type, int new_nr_creds) { struct vas_cop_feat_caps *caps; - int old_nr_creds, new_nr_creds; + int old_nr_creds; struct vas_caps *vcaps; int rc = 0, nr_active_wins; @@ -795,12 +795,6 @@ int vas_reconfig_capabilties(u8 type) caps = &vcaps->caps; mutex_lock(&vas_pseries_mutex); - rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, vcaps->feat, - (u64)virt_to_phys(&hv_cop_caps)); - if (rc) - goto out; - - new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); old_nr_creds = atomic_read(&caps->nr_total_credits); @@ -832,7 +826,6 @@ int vas_reconfig_capabilties(u8 type) false); } -out: mutex_unlock(&vas_pseries_mutex); return rc; } @@ -850,7 +843,7 @@ static int pseries_vas_notifier(struct notifier_block *nb, struct of_reconfig_data *rd = data; struct device_node *dn = rd->dn; const __be32 *intserv = NULL; - int len, rc = 0; + int new_nr_creds, len, rc = 0; if ((action == OF_RECONFIG_ATTACH_NODE) || (action == OF_RECONFIG_DETACH_NODE)) @@ -862,7 +855,15 @@ static int pseries_vas_notifier(struct notifier_block *nb, if (!intserv) return NOTIFY_OK; - rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE); + rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, + vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat, + (u64)virt_to_phys(&hv_cop_caps)); + if (!rc) { + new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); + rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, + new_nr_creds); + } + if (rc) pr_err("Failed reconfig VAS capabilities with DLPAR\n"); diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 34177881e998..333ffa2f9f42 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -135,7 +135,7 @@ struct pseries_vas_window { }; int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps); -int vas_reconfig_capabilties(u8 type); +int vas_reconfig_capabilties(u8 type, int new_nr_creds); int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps); #ifdef CONFIG_PPC_VAS diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 34592d00dde8..f6ef358d8a2c 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -38,7 +38,7 @@ config SOC_VIRT select SIFIVE_PLIC select PM_GENERIC_DOMAINS if PM select PM_GENERIC_DOMAINS_OF if PM && OF - select RISCV_SBI_CPUIDLE if CPU_IDLE + select RISCV_SBI_CPUIDLE if CPU_IDLE && RISCV_SBI help This enables support for QEMU Virt Machine. diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi index 854320e17b28..ccaac3371cf9 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi @@ -7,7 +7,7 @@ reg = <0x0 0x41000000 0x0 0xF0>; microchip,sync-update-mask = /bits/ 32 <0>; #pwm-cells = <2>; - clocks = <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk3>; status = "disabled"; }; @@ -16,10 +16,22 @@ reg = <0x0 0x44000000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; - clocks = <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk3>; interrupt-parent = <&plic>; interrupts = <122>; clock-frequency = <100000>; status = "disabled"; }; + + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; }; diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts index cd2fe80fa81a..3392153dd0f1 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts @@ -45,7 +45,7 @@ }; &refclk { - clock-frequency = <600000000>; + clock-frequency = <125000000>; }; &mmuart1 { diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi index c5c9d1360de0..cf2f55e1dcb6 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi @@ -141,7 +141,7 @@ }; }; - refclk: msspllclk { + refclk: mssrefclk { compatible = "fixed-clock"; #clock-cells = <0>; }; @@ -190,7 +190,7 @@ clkcfg: clkcfg@20002000 { compatible = "microchip,mpfs-clkcfg"; - reg = <0x0 0x20002000 0x0 0x1000>; + reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>; clocks = <&refclk>; #clock-cells = <1>; }; @@ -366,7 +366,7 @@ gpio1: gpio@20121000 { compatible = "microchip,mpfs-gpio"; - reg = <000 0x20121000 0x0 0x1000>; + reg = <0x0 0x20121000 0x0 0x1000>; interrupt-parent = <&plic>; interrupt-controller; #interrupt-cells = <1>; @@ -393,8 +393,8 @@ reg = <0x0 0x20124000 0x0 0x1000>; interrupt-parent = <&plic>; interrupts = <80>, <81>; - clocks = <&clkcfg CLK_RTC>; - clock-names = "rtc"; + clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>; + clock-names = "rtc", "rtcref"; status = "disabled"; }; @@ -424,7 +424,7 @@ <0 0 0 3 &pcie_intc 2>, <0 0 0 4 &pcie_intc 3>; interrupt-map-mask = <0 0 0 7>; - clocks = <&clkcfg CLK_FIC0>, <&clkcfg CLK_FIC1>, <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; clock-names = "fic0", "fic1", "fic3"; ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; msi-parent = <&pcie>; diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index aad45d7f498f..5c638fd5b35c 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -167,7 +167,7 @@ clocks = <&prci FU540_PRCI_CLK_TLCLK>; status = "disabled"; }; - dma: dma@3000000 { + dma: dma-controller@3000000 { compatible = "sifive,fu540-c000-pdma"; reg = <0x0 0x3000000 0x0 0x8000>; interrupt-parent = <&plic0>; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 30e3017f22bc..0cc17db8aaba 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -101,6 +101,7 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y CONFIG_RPMSG_CHAR=y +CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 7e5efdc3829d..6cd9d84d3e13 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -93,6 +93,7 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y CONFIG_RPMSG_CHAR=y +CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 78da839657e5..cd4bbcecb0fb 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -193,9 +193,6 @@ struct kvm_vcpu_arch { /* Don't run the VCPU (blocked) */ bool pause; - - /* SRCU lock index for in-kernel run loop */ - int srcu_idx; }; static inline void kvm_arch_hardware_unsetup(void) {} diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 0b552873a577..765004b60513 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -104,7 +104,7 @@ static int patch_text_cb(void *data) struct patch_insn *patch = data; int ret = 0; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { ret = patch_text_nosync(patch->addr, &patch->insn, GET_INSN_LENGTH(patch->insn)); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 624166004e36..7461f964d20a 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -38,14 +38,16 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; -#define KVM_RISCV_ISA_ALLOWED (riscv_isa_extension_mask(a) | \ - riscv_isa_extension_mask(c) | \ - riscv_isa_extension_mask(d) | \ - riscv_isa_extension_mask(f) | \ - riscv_isa_extension_mask(i) | \ - riscv_isa_extension_mask(m) | \ - riscv_isa_extension_mask(s) | \ - riscv_isa_extension_mask(u)) +#define KVM_RISCV_ISA_DISABLE_ALLOWED (riscv_isa_extension_mask(d) | \ + riscv_isa_extension_mask(f)) + +#define KVM_RISCV_ISA_DISABLE_NOT_ALLOWED (riscv_isa_extension_mask(a) | \ + riscv_isa_extension_mask(c) | \ + riscv_isa_extension_mask(i) | \ + riscv_isa_extension_mask(m)) + +#define KVM_RISCV_ISA_ALLOWED (KVM_RISCV_ISA_DISABLE_ALLOWED | \ + KVM_RISCV_ISA_DISABLE_NOT_ALLOWED) static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) { @@ -219,7 +221,8 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu, switch (reg_num) { case KVM_REG_RISCV_CONFIG_REG(isa): if (!vcpu->arch.ran_atleast_once) { - vcpu->arch.isa = reg_val; + /* Ignore the disable request for these extensions */ + vcpu->arch.isa = reg_val | KVM_RISCV_ISA_DISABLE_NOT_ALLOWED; vcpu->arch.isa &= riscv_isa_extension_base(NULL); vcpu->arch.isa &= KVM_RISCV_ISA_ALLOWED; kvm_riscv_vcpu_fp_reset(vcpu); @@ -653,8 +656,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.isa); kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context); - csr_write(CSR_HGATP, 0); - csr->vsstatus = csr_read(CSR_VSSTATUS); csr->vsie = csr_read(CSR_VSIE); csr->vstvec = csr_read(CSR_VSTVEC); @@ -726,13 +727,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) /* Mark this VCPU ran at least once */ vcpu->arch.ran_atleast_once = true; - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); /* Process MMIO value returned from user-space */ if (run->exit_reason == KVM_EXIT_MMIO) { ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run); if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } } @@ -741,13 +742,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) if (run->exit_reason == KVM_EXIT_RISCV_SBI) { ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } } if (run->immediate_exit) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return -EINTR; } @@ -786,7 +787,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ vcpu->mode = IN_GUEST_MODE; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); smp_mb__after_srcu_read_unlock(); /* @@ -804,7 +805,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; local_irq_enable(); preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); continue; } @@ -848,7 +849,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_riscv_vcpu_exit(vcpu, run, &trap); } @@ -857,7 +858,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu_put(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index aa8af129e4bb..a72c15d4b42a 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -456,9 +456,9 @@ static int stage2_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu) { if (!kvm_arch_vcpu_runnable(vcpu)) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_halt(vcpu); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); } } diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c index 4449a976e5a6..d4308c512007 100644 --- a/arch/riscv/kvm/vcpu_fp.c +++ b/arch/riscv/kvm/vcpu_fp.c @@ -11,6 +11,7 @@ #include <linux/err.h> #include <linux/kvm_host.h> #include <linux/uaccess.h> +#include <asm/hwcap.h> #ifdef CONFIG_FPU void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu) diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index a09ecb97b890..d45e7da3f0d3 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -83,7 +83,7 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, struct kvm_run *run, - u32 type, u64 flags) + u32 type, u64 reason) { unsigned long i; struct kvm_vcpu *tmp; @@ -94,7 +94,8 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, memset(&run->system_event, 0, sizeof(run->system_event)); run->system_event.type = type; - run->system_event.flags = flags; + run->system_event.ndata = 1; + run->system_event.data[0] = reason; run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9535bea8688c..05ed641a1134 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -208,8 +208,25 @@ static void __init setup_bootmem(void) * early_init_fdt_reserve_self() since __pa() does * not work for DTB pointers that are fixmap addresses */ - if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) - memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) { + /* + * In case the DTB is not located in a memory region we won't + * be able to locate it later on via the linear mapping and + * get a segfault when accessing it via __va(dtb_early_pa). + * To avoid this situation copy DTB to a memory region. + * Note that memblock_phys_alloc will also reserve DTB region. + */ + if (!memblock_is_memory(dtb_early_pa)) { + size_t fdt_size = fdt_totalsize(dtb_early_va); + phys_addr_t new_dtb_early_pa = memblock_phys_alloc(fdt_size, PAGE_SIZE); + void *new_dtb_early_va = early_memremap(new_dtb_early_pa, fdt_size); + + memcpy(new_dtb_early_va, dtb_early_va, fdt_size); + early_memunmap(new_dtb_early_va, fdt_size); + _dtb_early_pa = new_dtb_early_pa; + } else + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + } early_init_fdt_scan_reserved_mem(); dma_contiguous_reserve(dma32_phys_limit); @@ -718,6 +735,7 @@ retry: if (!check_l4) { disable_pgtable_l5(); check_l4 = true; + memset(early_pg_dir, 0, PAGE_SIZE); goto retry; } disable_pgtable_l4(); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 77b5a03de13a..e084c72104f8 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -255,6 +255,10 @@ config HAVE_MARCH_Z15_FEATURES def_bool n select HAVE_MARCH_Z14_FEATURES +config HAVE_MARCH_Z16_FEATURES + def_bool n + select HAVE_MARCH_Z15_FEATURES + choice prompt "Processor type" default MARCH_Z196 @@ -312,6 +316,14 @@ config MARCH_Z15 and 8561 series). The kernel will be slightly faster but will not work on older machines. +config MARCH_Z16 + bool "IBM z16" + select HAVE_MARCH_Z16_FEATURES + depends on $(cc-option,-march=z16) + help + Select this to enable optimizations for IBM z16 (3931 and + 3932 series). + endchoice config MARCH_Z10_TUNE @@ -332,6 +344,9 @@ config MARCH_Z14_TUNE config MARCH_Z15_TUNE def_bool TUNE_Z15 || MARCH_Z15 && TUNE_DEFAULT +config MARCH_Z16_TUNE + def_bool TUNE_Z16 || MARCH_Z16 && TUNE_DEFAULT + choice prompt "Tune code generation" default TUNE_DEFAULT @@ -372,6 +387,10 @@ config TUNE_Z15 bool "IBM z15" depends on $(cc-option,-mtune=z15) +config TUNE_Z16 + bool "IBM z16" + depends on $(cc-option,-mtune=z16) + endchoice config 64BIT diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 7a65bca1e5af..df325eacf62d 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -30,6 +30,16 @@ KBUILD_CFLAGS_DECOMPRESSOR += -fno-stack-protector KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) + +ifdef CONFIG_CC_IS_GCC + ifeq ($(call cc-ifversion, -ge, 1200, y), y) + ifeq ($(call cc-ifversion, -lt, 1300, y), y) + KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) + KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, array-bounds) + endif + endif +endif + UTS_MACHINE := s390x STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384) CHECKFLAGS += -D__s390__ -D__s390x__ @@ -42,6 +52,7 @@ mflags-$(CONFIG_MARCH_ZEC12) := -march=zEC12 mflags-$(CONFIG_MARCH_Z13) := -march=z13 mflags-$(CONFIG_MARCH_Z14) := -march=z14 mflags-$(CONFIG_MARCH_Z15) := -march=z15 +mflags-$(CONFIG_MARCH_Z16) := -march=z16 export CC_FLAGS_MARCH := $(mflags-y) @@ -54,6 +65,7 @@ cflags-$(CONFIG_MARCH_ZEC12_TUNE) += -mtune=zEC12 cflags-$(CONFIG_MARCH_Z13_TUNE) += -mtune=z13 cflags-$(CONFIG_MARCH_Z14_TUNE) += -mtune=z14 cflags-$(CONFIG_MARCH_Z15_TUNE) += -mtune=z15 +cflags-$(CONFIG_MARCH_Z16_TUNE) += -mtune=z16 cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 498bed9b261b..f6dfde577ce8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -499,11 +499,13 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set # CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DAVICOM is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_FUNGIBLE is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set @@ -588,13 +590,13 @@ CONFIG_MLX5_INFINIBAND=m CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_MLX5_VFIO_PCI=m CONFIG_VFIO_MDEV=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -690,6 +692,7 @@ CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y +CONFIG_HARDENED_USERCOPY=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y @@ -733,6 +736,7 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m @@ -786,7 +790,6 @@ CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y -CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y @@ -814,6 +817,7 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_KFENCE=y +CONFIG_KFENCE_DEFERRABLE=y CONFIG_KFENCE_STATIC_KEYS=y CONFIG_DEBUG_SHIRQ=y CONFIG_PANIC_ON_OOPS=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 61e36b999f67..706df3a4a867 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -490,11 +490,13 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set # CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DAVICOM is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_FUNGIBLE is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set @@ -578,13 +580,13 @@ CONFIG_MLX5_INFINIBAND=m CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_MLX5_VFIO_PCI=m CONFIG_VFIO_MDEV=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -720,6 +722,7 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m @@ -772,7 +775,6 @@ CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y -CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index c55c668dc3c7..a87fcc45e307 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -26,6 +26,7 @@ CONFIG_CRASH_DUMP=y # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set # CONFIG_GCC_PLUGINS is not set +# CONFIG_BLOCK_LEGACY_AUTOLOAD is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_COMPACTION is not set @@ -60,7 +61,6 @@ CONFIG_ZFCP=y # CONFIG_HID is not set # CONFIG_VIRTIO_MENU is not set # CONFIG_VHOST_MENU is not set -# CONFIG_SURFACE_PLATFORMS is not set # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set @@ -71,10 +71,10 @@ CONFIG_LSM="yama,loadpin,safesetid,integrity" CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y # CONFIG_SYMBOLIC_ERRNAME is not set -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h index eabab24b71dd..2f0a1cacdf85 100644 --- a/arch/s390/include/asm/entry-common.h +++ b/arch/s390/include/asm/entry-common.h @@ -58,7 +58,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static inline bool on_thread_stack(void) { - return !(((unsigned long)(current->stack) ^ current_stack_pointer()) & ~(THREAD_SIZE - 1)); + return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); } #endif diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index eee8d96fb38e..ff1e25d515a8 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -200,13 +200,7 @@ unsigned long __get_wchan(struct task_struct *p); /* Has task runtime instrumentation enabled ? */ #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb) -static __always_inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; - - asm volatile("la %0,0(15)" : "=a" (sp)); - return sp; -} +register unsigned long current_stack_pointer asm("r15"); static __always_inline unsigned short stap(void) { diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 275f4258fbd5..f8500191993d 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -46,7 +46,7 @@ struct stack_frame { }; /* - * Unlike current_stack_pointer() which simply returns current value of %r15 + * Unlike current_stack_pointer which simply contains the current value of %r15 * current_frame_address() returns function stack frame address, which matches * %r15 upon function invocation. It may differ from %r15 later if function * allocates stack for local variables or new stack frame to call other diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index b2ef014a9287..6ebf02e15c85 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -54,7 +54,7 @@ static void __do_machine_kdump(void *image) * This need to be done *after* s390_reset_system set the * prefix register of this CPU to zero */ - memcpy((void *) __LC_FPREGS_SAVE_AREA, + memcpy(absolute_pointer(__LC_FPREGS_SAVE_AREA), (void *)(prefix + __LC_FPREGS_SAVE_AREA), 512); __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 7a74ea5f7531..aa0e0e7fc773 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -283,6 +283,10 @@ static int __init setup_elf_platform(void) case 0x8562: strcpy(elf_platform, "z15"); break; + case 0x3931: + case 0x3932: + strcpy(elf_platform, "z16"); + break; } return 0; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 9b30beac904d..af96dc0549a4 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1334,11 +1334,11 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) hrtimer_start(&vcpu->arch.ckc_timer, sltime, HRTIMER_MODE_REL); VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime); no_timer: - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_halt(vcpu); vcpu->valid_wakeup = false; __unset_cpu_idle(vcpu); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); hrtimer_cancel(&vcpu->arch.ckc_timer); return 0; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 156d1c25a3c1..76ad6408cb2c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2384,7 +2384,16 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) return -EINVAL; if (mop->size > MEM_OP_MAX_SIZE) return -E2BIG; - if (kvm_s390_pv_is_protected(kvm)) + /* + * This is technically a heuristic only, if the kvm->lock is not + * taken, it is not guaranteed that the vm is/remains non-protected. + * This is ok from a kernel perspective, wrongdoing is detected + * on the access, -EFAULT is returned and the vm may crash the + * next time it accesses the memory in question. + * There is no sane usecase to do switching and a memop on two + * different CPUs at the same time. + */ + if (kvm_s390_pv_get_handle(kvm)) return -EINVAL; if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) { if (access_key_invalid(mop->key)) @@ -4237,14 +4246,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) * We try to hold kvm->srcu during most of vcpu_run (except when run- * ning the guest), so that memslots (and other stuff) are protected */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); do { rc = vcpu_pre_run(vcpu); if (rc) break; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* * As PF_VCPU will be used in fault handler, between * guest_enter and guest_exit should be no uaccess. @@ -4281,12 +4290,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) __enable_cpu_timer_accounting(vcpu); guest_exit_irqoff(); local_irq_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = vcpu_post_run(vcpu, exit_reason); } while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return rc; } diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 7f7c0d6af2ce..cc7c9599f43e 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -137,12 +137,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) /* Allocate variable storage */ vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE); vlen += uv_info.guest_virt_base_stor_len; - /* - * The Create Secure Configuration Ultravisor Call does not support - * using large pages for the virtual memory area. - * This is a hardware limitation. - */ - kvm->arch.pv.stor_var = vmalloc_no_huge(vlen); + kvm->arch.pv.stor_var = vzalloc(vlen); if (!kvm->arch.pv.stor_var) goto out_err; return 0; diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index acda4b6fc851..dada78b92691 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1091,7 +1091,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) handle_last_fault(vcpu, vsie_page); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* save current guest state of bp isolation override */ guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST); @@ -1133,7 +1133,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (!guest_bp_isolation) clear_thread_flag(TIF_ISOLATE_BP_GUEST); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (rc == -EINTR) { VCPU_EVENT(vcpu, 3, "%s", "machine check"); diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index 9bb067321ab4..5a053b393d5c 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -147,7 +147,7 @@ static __always_inline struct pt_regs fake_pt_regs(void) struct pt_regs regs; memset(®s, 0, sizeof(regs)); - regs.gprs[15] = current_stack_pointer(); + regs.gprs[15] = current_stack_pointer; asm volatile( "basr %[psw_addr],0\n" diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index af03cacf34ec..1ac73917a8d3 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -1183,6 +1183,7 @@ EXPORT_SYMBOL_GPL(gmap_read_table); static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, struct gmap_rmap *rmap) { + struct gmap_rmap *temp; void __rcu **slot; BUG_ON(!gmap_is_shadow(sg)); @@ -1190,6 +1191,12 @@ static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, if (slot) { rmap->next = radix_tree_deref_slot_protected(slot, &sg->guest_table_lock); + for (temp = rmap->next; temp; temp = temp->next) { + if (temp->raddr == rmap->raddr) { + kfree(rmap); + return; + } + } radix_tree_replace_slot(&sg->host_to_rmap, slot, rmap); } else { rmap->next = NULL; diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h index 41c6d734a474..adb6991d0455 100644 --- a/arch/sparc/include/asm/cacheflush_32.h +++ b/arch/sparc/include/asm/cacheflush_32.h @@ -35,6 +35,7 @@ #define flush_page_for_dma(addr) \ sparc32_cachetlb_ops->page_for_dma(addr) +struct page; void sparc_flush_page_to_ram(struct page *page); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index b03269faef71..c4344b67628d 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -483,7 +483,6 @@ static void ubd_handler(void) if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) { blk_queue_max_discard_sectors(io_req->req->q, 0); blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, io_req->req->q); } blk_mq_end_request(io_req->req, io_req->error); kfree(io_req); @@ -800,10 +799,8 @@ static int ubd_open_dev(struct ubd *ubd_dev) } if (ubd_dev->no_trim == 0) { ubd_dev->queue->limits.discard_granularity = SECTOR_SIZE; - ubd_dev->queue->limits.discard_alignment = SECTOR_SIZE; blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST); blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, ubd_dev->queue); } blk_queue_flag_set(QUEUE_FLAG_NONROT, ubd_dev->queue); return 0; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 69231f66a2b5..7fa8bdd0ed7e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -878,6 +878,21 @@ config ACRN_GUEST IOT with small footprint and real-time features. More details can be found in https://projectacrn.org/. +config INTEL_TDX_GUEST + bool "Intel TDX (Trust Domain Extensions) - Guest Support" + depends on X86_64 && CPU_SUP_INTEL + depends on X86_X2APIC + select ARCH_HAS_CC_PLATFORM + select X86_MEM_ENCRYPT + select X86_MCE + help + Support running as a guest under Intel TDX. Without this support, + the guest kernel can not boot or run under TDX. + TDX includes memory encryption and integrity capabilities + which protect the confidentiality and integrity of guest + memory contents and CPU state. TDX guests are protected from + some attacks from the VMM. + endif #HYPERVISOR_GUEST source "arch/x86/Kconfig.cpu" @@ -1816,17 +1831,6 @@ config ARCH_RANDOM If supported, this is a high bandwidth, cryptographically secure hardware random number generator. -config X86_SMAP - def_bool y - prompt "Supervisor Mode Access Prevention" if EXPERT - help - Supervisor Mode Access Prevention (SMAP) is a security - feature in newer Intel processors. There is a small - performance cost if this enabled and turned on; there is - also a small increase in the kernel size if this is enabled. - - If unsure, say Y. - config X86_UMIP def_bool y prompt "User Mode Instruction Prevention" if EXPERT @@ -1866,7 +1870,7 @@ config X86_KERNEL_IBT code with them to make this happen. In addition to building the kernel with IBT, seal all functions that - are not indirect call targets, avoiding them ever becomming one. + are not indirect call targets, avoiding them ever becoming one. This requires LTO like objtool runs and will slow down the build. It does significantly reduce the number of ENDBR instructions in the diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 63d50f65b828..1abd7cc9d6cd 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -313,5 +313,6 @@ define archhelp echo '' echo ' kvm_guest.config - Enable Kconfig items for running this kernel as a KVM guest' echo ' xen.config - Enable Kconfig items for running this kernel as a Xen guest' + echo ' x86_debug.config - Enable tip tree debugging options for testing' endef diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 34c9dbb6a47d..148ba5c5106e 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -26,6 +26,7 @@ #include "bitops.h" #include "ctype.h" #include "cpuflags.h" +#include "io.h" /* Useful macros */ #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) @@ -35,44 +36,10 @@ extern struct boot_params boot_params; #define cpu_relax() asm volatile("rep; nop") -/* Basic port I/O */ -static inline void outb(u8 v, u16 port) -{ - asm volatile("outb %0,%1" : : "a" (v), "dN" (port)); -} -static inline u8 inb(u16 port) -{ - u8 v; - asm volatile("inb %1,%0" : "=a" (v) : "dN" (port)); - return v; -} - -static inline void outw(u16 v, u16 port) -{ - asm volatile("outw %0,%1" : : "a" (v), "dN" (port)); -} -static inline u16 inw(u16 port) -{ - u16 v; - asm volatile("inw %1,%0" : "=a" (v) : "dN" (port)); - return v; -} - -static inline void outl(u32 v, u16 port) -{ - asm volatile("outl %0,%1" : : "a" (v), "dN" (port)); -} -static inline u32 inl(u16 port) -{ - u32 v; - asm volatile("inl %1,%0" : "=a" (v) : "dN" (port)); - return v; -} - static inline void io_delay(void) { const u16 DELAY_PORT = 0x80; - asm volatile("outb %%al,%0" : : "dN" (DELAY_PORT)); + outb(0, DELAY_PORT); } /* These functions are used to reference data in other segments. */ @@ -110,66 +77,78 @@ typedef unsigned int addr_t; static inline u8 rdfs8(addr_t addr) { + u8 *ptr = (u8 *)absolute_pointer(addr); u8 v; - asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr)); + asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*ptr)); return v; } static inline u16 rdfs16(addr_t addr) { + u16 *ptr = (u16 *)absolute_pointer(addr); u16 v; - asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr)); + asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline u32 rdfs32(addr_t addr) { + u32 *ptr = (u32 *)absolute_pointer(addr); u32 v; - asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr)); + asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline void wrfs8(u8 v, addr_t addr) { - asm volatile("movb %1,%%fs:%0" : "+m" (*(u8 *)addr) : "qi" (v)); + u8 *ptr = (u8 *)absolute_pointer(addr); + asm volatile("movb %1,%%fs:%0" : "+m" (*ptr) : "qi" (v)); } static inline void wrfs16(u16 v, addr_t addr) { - asm volatile("movw %1,%%fs:%0" : "+m" (*(u16 *)addr) : "ri" (v)); + u16 *ptr = (u16 *)absolute_pointer(addr); + asm volatile("movw %1,%%fs:%0" : "+m" (*ptr) : "ri" (v)); } static inline void wrfs32(u32 v, addr_t addr) { - asm volatile("movl %1,%%fs:%0" : "+m" (*(u32 *)addr) : "ri" (v)); + u32 *ptr = (u32 *)absolute_pointer(addr); + asm volatile("movl %1,%%fs:%0" : "+m" (*ptr) : "ri" (v)); } static inline u8 rdgs8(addr_t addr) { + u8 *ptr = (u8 *)absolute_pointer(addr); u8 v; - asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr)); + asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*ptr)); return v; } static inline u16 rdgs16(addr_t addr) { + u16 *ptr = (u16 *)absolute_pointer(addr); u16 v; - asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr)); + asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline u32 rdgs32(addr_t addr) { + u32 *ptr = (u32 *)absolute_pointer(addr); u32 v; - asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr)); + asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline void wrgs8(u8 v, addr_t addr) { - asm volatile("movb %1,%%gs:%0" : "+m" (*(u8 *)addr) : "qi" (v)); + u8 *ptr = (u8 *)absolute_pointer(addr); + asm volatile("movb %1,%%gs:%0" : "+m" (*ptr) : "qi" (v)); } static inline void wrgs16(u16 v, addr_t addr) { - asm volatile("movw %1,%%gs:%0" : "+m" (*(u16 *)addr) : "ri" (v)); + u16 *ptr = (u16 *)absolute_pointer(addr); + asm volatile("movw %1,%%gs:%0" : "+m" (*ptr) : "ri" (v)); } static inline void wrgs32(u32 v, addr_t addr) { - asm volatile("movl %1,%%gs:%0" : "+m" (*(u32 *)addr) : "ri" (v)); + u32 *ptr = (u32 *)absolute_pointer(addr); + asm volatile("movl %1,%%gs:%0" : "+m" (*ptr) : "ri" (v)); } /* Note: these only return true/false, not a signed return value! */ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 6115274fe10f..19e1905dcbf6 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -101,8 +101,10 @@ ifdef CONFIG_X86_64 endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o +vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o +vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a $(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 8bcbcee54aa1..9caf89063e77 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -3,10 +3,9 @@ #include "misc.h" #include "error.h" #include "../string.h" +#include "efi.h" #include <linux/numa.h> -#include <linux/efi.h> -#include <asm/efi.h> /* * Longest parameter of 'acpi=' is 'copy_dsdt', plus an extra '\0' @@ -20,153 +19,56 @@ */ struct mem_vector immovable_mem[MAX_NUMNODES*2]; -/* - * Search EFI system tables for RSDP. If both ACPI_20_TABLE_GUID and - * ACPI_TABLE_GUID are found, take the former, which has more features. - */ static acpi_physical_address -__efi_get_rsdp_addr(unsigned long config_tables, unsigned int nr_tables, - bool efi_64) +__efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len) { - acpi_physical_address rsdp_addr = 0; - #ifdef CONFIG_EFI - int i; - - /* Get EFI tables from systab. */ - for (i = 0; i < nr_tables; i++) { - acpi_physical_address table; - efi_guid_t guid; - - if (efi_64) { - efi_config_table_64_t *tbl = (efi_config_table_64_t *)config_tables + i; - - guid = tbl->guid; - table = tbl->table; - - if (!IS_ENABLED(CONFIG_X86_64) && table >> 32) { - debug_putstr("Error getting RSDP address: EFI config table located above 4GB.\n"); - return 0; - } - } else { - efi_config_table_32_t *tbl = (efi_config_table_32_t *)config_tables + i; - - guid = tbl->guid; - table = tbl->table; - } + unsigned long rsdp_addr; + int ret; - if (!(efi_guidcmp(guid, ACPI_TABLE_GUID))) - rsdp_addr = table; - else if (!(efi_guidcmp(guid, ACPI_20_TABLE_GUID))) - return table; - } + /* + * Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to + * ACPI_TABLE_GUID because it has more features. + */ + rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + ACPI_20_TABLE_GUID); + if (rsdp_addr) + return (acpi_physical_address)rsdp_addr; + + /* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */ + rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + ACPI_TABLE_GUID); + if (rsdp_addr) + return (acpi_physical_address)rsdp_addr; + + debug_putstr("Error getting RSDP address.\n"); #endif - return rsdp_addr; -} - -/* EFI/kexec support is 64-bit only. */ -#ifdef CONFIG_X86_64 -static struct efi_setup_data *get_kexec_setup_data_addr(void) -{ - struct setup_data *data; - u64 pa_data; - - pa_data = boot_params->hdr.setup_data; - while (pa_data) { - data = (struct setup_data *)pa_data; - if (data->type == SETUP_EFI) - return (struct efi_setup_data *)(pa_data + sizeof(struct setup_data)); - - pa_data = data->next; - } - return NULL; -} - -static acpi_physical_address kexec_get_rsdp_addr(void) -{ - efi_system_table_64_t *systab; - struct efi_setup_data *esd; - struct efi_info *ei; - char *sig; - - esd = (struct efi_setup_data *)get_kexec_setup_data_addr(); - if (!esd) - return 0; - - if (!esd->tables) { - debug_putstr("Wrong kexec SETUP_EFI data.\n"); - return 0; - } - - ei = &boot_params->efi_info; - sig = (char *)&ei->efi_loader_signature; - if (strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { - debug_putstr("Wrong kexec EFI loader signature.\n"); - return 0; - } - - /* Get systab from boot params. */ - systab = (efi_system_table_64_t *) (ei->efi_systab | ((__u64)ei->efi_systab_hi << 32)); - if (!systab) - error("EFI system table not found in kexec boot_params."); - - return __efi_get_rsdp_addr((unsigned long)esd->tables, systab->nr_tables, true); + return 0; } -#else -static acpi_physical_address kexec_get_rsdp_addr(void) { return 0; } -#endif /* CONFIG_X86_64 */ static acpi_physical_address efi_get_rsdp_addr(void) { #ifdef CONFIG_EFI - unsigned long systab, config_tables; + unsigned long cfg_tbl_pa = 0; + unsigned int cfg_tbl_len; + unsigned long systab_pa; unsigned int nr_tables; - struct efi_info *ei; - bool efi_64; - char *sig; - - ei = &boot_params->efi_info; - sig = (char *)&ei->efi_loader_signature; - - if (!strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { - efi_64 = true; - } else if (!strncmp(sig, EFI32_LOADER_SIGNATURE, 4)) { - efi_64 = false; - } else { - debug_putstr("Wrong EFI loader signature.\n"); - return 0; - } + enum efi_type et; + int ret; - /* Get systab from boot params. */ -#ifdef CONFIG_X86_64 - systab = ei->efi_systab | ((__u64)ei->efi_systab_hi << 32); -#else - if (ei->efi_systab_hi || ei->efi_memmap_hi) { - debug_putstr("Error getting RSDP address: EFI system table located above 4GB.\n"); + et = efi_get_type(boot_params); + if (et == EFI_TYPE_NONE) return 0; - } - systab = ei->efi_systab; -#endif - if (!systab) - error("EFI system table not found."); - /* Handle EFI bitness properly */ - if (efi_64) { - efi_system_table_64_t *stbl = (efi_system_table_64_t *)systab; + systab_pa = efi_get_system_table(boot_params); + if (!systab_pa) + error("EFI support advertised, but unable to locate system table."); - config_tables = stbl->tables; - nr_tables = stbl->nr_tables; - } else { - efi_system_table_32_t *stbl = (efi_system_table_32_t *)systab; + ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len); + if (ret || !cfg_tbl_pa) + error("EFI config table not found."); - config_tables = stbl->tables; - nr_tables = stbl->nr_tables; - } - - if (!config_tables) - error("EFI config tables not found."); - - return __efi_get_rsdp_addr(config_tables, nr_tables, efi_64); + return __efi_get_rsdp_addr(cfg_tbl_pa, cfg_tbl_len); #else return 0; #endif @@ -256,14 +158,6 @@ acpi_physical_address get_rsdp_addr(void) pa = boot_params->acpi_rsdp_addr; - /* - * Try to get EFI data from setup_data. This can happen when we're a - * kexec'ed kernel and kexec(1) has passed all the required EFI info to - * us. - */ - if (!pa) - pa = kexec_get_rsdp_addr(); - if (!pa) pa = efi_get_rsdp_addr(); diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c index 261e81fb9582..70a8d1706d0f 100644 --- a/arch/x86/boot/compressed/early_serial_console.c +++ b/arch/x86/boot/compressed/early_serial_console.c @@ -1,5 +1,6 @@ #include "misc.h" -int early_serial_base; +/* This might be accessed before .bss is cleared, so use .data instead. */ +int early_serial_base __section(".data"); #include "../early_serial_console.c" diff --git a/arch/x86/boot/compressed/efi.c b/arch/x86/boot/compressed/efi.c new file mode 100644 index 000000000000..6edd034b0b30 --- /dev/null +++ b/arch/x86/boot/compressed/efi.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Helpers for early access to EFI configuration table. + * + * Originally derived from arch/x86/boot/compressed/acpi.c + */ + +#include "misc.h" + +/** + * efi_get_type - Given a pointer to boot_params, determine the type of EFI environment. + * + * @bp: pointer to boot_params + * + * Return: EFI_TYPE_{32,64} for valid EFI environments, EFI_TYPE_NONE otherwise. + */ +enum efi_type efi_get_type(struct boot_params *bp) +{ + struct efi_info *ei; + enum efi_type et; + const char *sig; + + ei = &bp->efi_info; + sig = (char *)&ei->efi_loader_signature; + + if (!strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { + et = EFI_TYPE_64; + } else if (!strncmp(sig, EFI32_LOADER_SIGNATURE, 4)) { + et = EFI_TYPE_32; + } else { + debug_putstr("No EFI environment detected.\n"); + et = EFI_TYPE_NONE; + } + +#ifndef CONFIG_X86_64 + /* + * Existing callers like acpi.c treat this case as an indicator to + * fall-through to non-EFI, rather than an error, so maintain that + * functionality here as well. + */ + if (ei->efi_systab_hi || ei->efi_memmap_hi) { + debug_putstr("EFI system table is located above 4GB and cannot be accessed.\n"); + et = EFI_TYPE_NONE; + } +#endif + + return et; +} + +/** + * efi_get_system_table - Given a pointer to boot_params, retrieve the physical address + * of the EFI system table. + * + * @bp: pointer to boot_params + * + * Return: EFI system table address on success. On error, return 0. + */ +unsigned long efi_get_system_table(struct boot_params *bp) +{ + unsigned long sys_tbl_pa; + struct efi_info *ei; + enum efi_type et; + + /* Get systab from boot params. */ + ei = &bp->efi_info; +#ifdef CONFIG_X86_64 + sys_tbl_pa = ei->efi_systab | ((__u64)ei->efi_systab_hi << 32); +#else + sys_tbl_pa = ei->efi_systab; +#endif + if (!sys_tbl_pa) { + debug_putstr("EFI system table not found."); + return 0; + } + + return sys_tbl_pa; +} + +/* + * EFI config table address changes to virtual address after boot, which may + * not be accessible for the kexec'd kernel. To address this, kexec provides + * the initial physical address via a struct setup_data entry, which is + * checked for here, along with some sanity checks. + */ +static struct efi_setup_data *get_kexec_setup_data(struct boot_params *bp, + enum efi_type et) +{ +#ifdef CONFIG_X86_64 + struct efi_setup_data *esd = NULL; + struct setup_data *data; + u64 pa_data; + + pa_data = bp->hdr.setup_data; + while (pa_data) { + data = (struct setup_data *)pa_data; + if (data->type == SETUP_EFI) { + esd = (struct efi_setup_data *)(pa_data + sizeof(struct setup_data)); + break; + } + + pa_data = data->next; + } + + /* + * Original ACPI code falls back to attempting normal EFI boot in these + * cases, so maintain existing behavior by indicating non-kexec + * environment to the caller, but print them for debugging. + */ + if (esd && !esd->tables) { + debug_putstr("kexec EFI environment missing valid configuration table.\n"); + return NULL; + } + + return esd; +#endif + return NULL; +} + +/** + * efi_get_conf_table - Given a pointer to boot_params, locate and return the physical + * address of EFI configuration table. + * + * @bp: pointer to boot_params + * @cfg_tbl_pa: location to store physical address of config table + * @cfg_tbl_len: location to store number of config table entries + * + * Return: 0 on success. On error, return params are left unchanged. + */ +int efi_get_conf_table(struct boot_params *bp, unsigned long *cfg_tbl_pa, + unsigned int *cfg_tbl_len) +{ + unsigned long sys_tbl_pa; + enum efi_type et; + int ret; + + if (!cfg_tbl_pa || !cfg_tbl_len) + return -EINVAL; + + sys_tbl_pa = efi_get_system_table(bp); + if (!sys_tbl_pa) + return -EINVAL; + + /* Handle EFI bitness properly */ + et = efi_get_type(bp); + if (et == EFI_TYPE_64) { + efi_system_table_64_t *stbl = (efi_system_table_64_t *)sys_tbl_pa; + struct efi_setup_data *esd; + + /* kexec provides an alternative EFI conf table, check for it. */ + esd = get_kexec_setup_data(bp, et); + + *cfg_tbl_pa = esd ? esd->tables : stbl->tables; + *cfg_tbl_len = stbl->nr_tables; + } else if (et == EFI_TYPE_32) { + efi_system_table_32_t *stbl = (efi_system_table_32_t *)sys_tbl_pa; + + *cfg_tbl_pa = stbl->tables; + *cfg_tbl_len = stbl->nr_tables; + } else { + return -EINVAL; + } + + return 0; +} + +/* Get vendor table address/guid from EFI config table at the given index */ +static int get_vendor_table(void *cfg_tbl, unsigned int idx, + unsigned long *vendor_tbl_pa, + efi_guid_t *vendor_tbl_guid, + enum efi_type et) +{ + if (et == EFI_TYPE_64) { + efi_config_table_64_t *tbl_entry = (efi_config_table_64_t *)cfg_tbl + idx; + + if (!IS_ENABLED(CONFIG_X86_64) && tbl_entry->table >> 32) { + debug_putstr("Error: EFI config table entry located above 4GB.\n"); + return -EINVAL; + } + + *vendor_tbl_pa = tbl_entry->table; + *vendor_tbl_guid = tbl_entry->guid; + + } else if (et == EFI_TYPE_32) { + efi_config_table_32_t *tbl_entry = (efi_config_table_32_t *)cfg_tbl + idx; + + *vendor_tbl_pa = tbl_entry->table; + *vendor_tbl_guid = tbl_entry->guid; + } else { + return -EINVAL; + } + + return 0; +} + +/** + * efi_find_vendor_table - Given EFI config table, search it for the physical + * address of the vendor table associated with GUID. + * + * @bp: pointer to boot_params + * @cfg_tbl_pa: pointer to EFI configuration table + * @cfg_tbl_len: number of entries in EFI configuration table + * @guid: GUID of vendor table + * + * Return: vendor table address on success. On error, return 0. + */ +unsigned long efi_find_vendor_table(struct boot_params *bp, + unsigned long cfg_tbl_pa, + unsigned int cfg_tbl_len, + efi_guid_t guid) +{ + enum efi_type et; + unsigned int i; + + et = efi_get_type(bp); + if (et == EFI_TYPE_NONE) + return 0; + + for (i = 0; i < cfg_tbl_len; i++) { + unsigned long vendor_tbl_pa; + efi_guid_t vendor_tbl_guid; + int ret; + + ret = get_vendor_table((void *)cfg_tbl_pa, i, + &vendor_tbl_pa, + &vendor_tbl_guid, et); + if (ret) + return 0; + + if (!efi_guidcmp(guid, vendor_tbl_guid)) + return vendor_tbl_pa; + } + + return 0; +} diff --git a/arch/x86/boot/compressed/efi.h b/arch/x86/boot/compressed/efi.h new file mode 100644 index 000000000000..7db2f41b54cd --- /dev/null +++ b/arch/x86/boot/compressed/efi.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef BOOT_COMPRESSED_EFI_H +#define BOOT_COMPRESSED_EFI_H + +#if defined(_LINUX_EFI_H) || defined(_ASM_X86_EFI_H) +#error Please do not include kernel proper namespace headers +#endif + +typedef guid_t efi_guid_t __aligned(__alignof__(u32)); + +#define EFI_GUID(a, b, c, d...) (efi_guid_t){ { \ + (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ + (b) & 0xff, ((b) >> 8) & 0xff, \ + (c) & 0xff, ((c) >> 8) & 0xff, d } } + +#define ACPI_TABLE_GUID EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) +#define ACPI_20_TABLE_GUID EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) + +#define EFI32_LOADER_SIGNATURE "EL32" +#define EFI64_LOADER_SIGNATURE "EL64" + +/* + * Generic EFI table header + */ +typedef struct { + u64 signature; + u32 revision; + u32 headersize; + u32 crc32; + u32 reserved; +} efi_table_hdr_t; + +#define EFI_CONVENTIONAL_MEMORY 7 + +#define EFI_MEMORY_MORE_RELIABLE \ + ((u64)0x0000000000010000ULL) /* higher reliability */ +#define EFI_MEMORY_SP ((u64)0x0000000000040000ULL) /* soft reserved */ + +#define EFI_PAGE_SHIFT 12 + +typedef struct { + u32 type; + u32 pad; + u64 phys_addr; + u64 virt_addr; + u64 num_pages; + u64 attribute; +} efi_memory_desc_t; + +#define efi_early_memdesc_ptr(map, desc_size, n) \ + (efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size))) + +typedef struct { + efi_guid_t guid; + u64 table; +} efi_config_table_64_t; + +typedef struct { + efi_guid_t guid; + u32 table; +} efi_config_table_32_t; + +typedef struct { + efi_table_hdr_t hdr; + u64 fw_vendor; /* physical addr of CHAR16 vendor string */ + u32 fw_revision; + u32 __pad1; + u64 con_in_handle; + u64 con_in; + u64 con_out_handle; + u64 con_out; + u64 stderr_handle; + u64 stderr; + u64 runtime; + u64 boottime; + u32 nr_tables; + u32 __pad2; + u64 tables; +} efi_system_table_64_t; + +typedef struct { + efi_table_hdr_t hdr; + u32 fw_vendor; /* physical addr of CHAR16 vendor string */ + u32 fw_revision; + u32 con_in_handle; + u32 con_in; + u32 con_out_handle; + u32 con_out; + u32 stderr_handle; + u32 stderr; + u32 runtime; + u32 boottime; + u32 nr_tables; + u32 tables; +} efi_system_table_32_t; + +/* kexec external ABI */ +struct efi_setup_data { + u64 fw_vendor; + u64 __unused; + u64 tables; + u64 smbios; + u64 reserved[8]; +}; + +static inline int efi_guidcmp (efi_guid_t left, efi_guid_t right) +{ + return memcmp(&left, &right, sizeof (efi_guid_t)); +} + +#ifdef CONFIG_EFI +bool __pure __efi_soft_reserve_enabled(void); + +static inline bool __pure efi_soft_reserve_enabled(void) +{ + return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) + && __efi_soft_reserve_enabled(); +} +#else +static inline bool efi_soft_reserve_enabled(void) +{ + return false; +} +#endif /* CONFIG_EFI */ +#endif /* BOOT_COMPRESSED_EFI_H */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index dea95301196b..d33f060900d2 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -189,11 +189,11 @@ SYM_FUNC_START(startup_32) subl $32, %eax /* Encryption bit is always above bit 31 */ bts %eax, %edx /* Set encryption mask for page tables */ /* - * Mark SEV as active in sev_status so that startup32_check_sev_cbit() - * will do a check. The sev_status memory will be fully initialized - * with the contents of MSR_AMD_SEV_STATUS later in - * set_sev_encryption_mask(). For now it is sufficient to know that SEV - * is active. + * Set MSR_AMD64_SEV_ENABLED_BIT in sev_status so that + * startup32_check_sev_cbit() will do a check. sev_enable() will + * initialize sev_status with all the bits reported by + * MSR_AMD_SEV_STATUS later, but only MSR_AMD64_SEV_ENABLED_BIT + * needs to be set for now. */ movl $1, rva(sev_status)(%ebp) 1: @@ -289,7 +289,7 @@ SYM_FUNC_START(startup_32) pushl %eax /* Enter paged protected Mode, activating Long Mode */ - movl $(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */ + movl $CR0_STATE, %eax movl %eax, %cr0 /* Jump from 32bit compatibility mode into 64bit mode. */ @@ -447,6 +447,23 @@ SYM_CODE_START(startup_64) call load_stage1_idt popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* + * Now that the stage1 interrupt handlers are set up, #VC exceptions from + * CPUID instructions can be properly handled for SEV-ES guests. + * + * For SEV-SNP, the CPUID table also needs to be set up in advance of any + * CPUID instructions being issued, so go ahead and do that now via + * sev_enable(), which will also handle the rest of the SEV-related + * detection/setup to ensure that has been done in advance of any dependent + * code. + */ + pushq %rsi + movq %rsi, %rdi /* real mode address */ + call sev_enable + popq %rsi +#endif + /* * paging_prepare() sets up the trampoline and checks if we need to * enable 5-level paging. @@ -558,17 +575,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) shrq $3, %rcx rep stosq -/* - * If running as an SEV guest, the encryption mask is required in the - * page-table setup code below. When the guest also has SEV-ES enabled - * set_sev_encryption_mask() will cause #VC exceptions, but the stage2 - * handler can't map its GHCB because the page-table is not set up yet. - * So set up the encryption mask here while still on the stage1 #VC - * handler. Then load stage2 IDT and switch to the kernel's own - * page-table. - */ pushq %rsi - call set_sev_encryption_mask call load_stage2_idt /* Pass boot_params to initialize_identity_maps() */ @@ -642,12 +649,28 @@ SYM_CODE_START(trampoline_32bit_src) movl $MSR_EFER, %ecx rdmsr btsl $_EFER_LME, %eax + /* Avoid writing EFER if no change was made (for TDX guest) */ + jc 1f wrmsr - popl %edx +1: popl %edx popl %ecx +#ifdef CONFIG_X86_MCE + /* + * Preserve CR4.MCE if the kernel will enable #MC support. + * Clearing MCE may fault in some environments (that also force #MC + * support). Any machine check that occurs before #MC support is fully + * configured will crash the system regardless of the CR4.MCE value set + * here. + */ + movl %cr4, %eax + andl $X86_CR4_MCE, %eax +#else + movl $0, %eax +#endif + /* Enable PAE and LA57 (if required) paging modes */ - movl $X86_CR4_PAE, %eax + orl $X86_CR4_PAE, %eax testl %edx, %edx jz 1f orl $X86_CR4_LA57, %eax @@ -661,8 +684,9 @@ SYM_CODE_START(trampoline_32bit_src) pushl $__KERNEL_CS pushl %eax - /* Enable paging again */ - movl $(X86_CR0_PG | X86_CR0_PE), %eax + /* Enable paging again. */ + movl %cr0, %eax + btsl $X86_CR0_PG_BIT, %eax movl %eax, %cr0 lret diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index f7213d0943b8..44c350d627c7 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -90,7 +90,7 @@ static struct x86_mapping_info mapping_info; /* * Adds the specified range to the identity mappings. */ -static void add_identity_map(unsigned long start, unsigned long end) +void kernel_add_identity_map(unsigned long start, unsigned long end) { int ret; @@ -157,14 +157,15 @@ void initialize_identity_maps(void *rmode) * explicitly here in case the compressed kernel does not touch them, * or does not touch all the pages covering them. */ - add_identity_map((unsigned long)_head, (unsigned long)_end); + kernel_add_identity_map((unsigned long)_head, (unsigned long)_end); boot_params = rmode; - add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); + kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); cmdline = get_cmd_line_ptr(); - add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); + kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); + + sev_prep_identity_maps(top_level_pgt); /* Load the new page-table. */ - sev_verify_cbit(top_level_pgt); write_cr3(top_level_pgt); } @@ -246,10 +247,10 @@ static int set_clr_page_flags(struct x86_mapping_info *info, * It should already exist, but keep things generic. * * To map the page just read from it and fault it in if there is no - * mapping yet. add_identity_map() can't be called here because that - * would unconditionally map the address on PMD level, destroying any - * PTE-level mappings that might already exist. Use assembly here so - * the access won't be optimized away. + * mapping yet. kernel_add_identity_map() can't be called here because + * that would unconditionally map the address on PMD level, destroying + * any PTE-level mappings that might already exist. Use assembly here + * so the access won't be optimized away. */ asm volatile("mov %[address], %%r9" :: [address] "g" (*(unsigned long *)address) @@ -275,15 +276,31 @@ static int set_clr_page_flags(struct x86_mapping_info *info, * Changing encryption attributes of a page requires to flush it from * the caches. */ - if ((set | clr) & _PAGE_ENC) + if ((set | clr) & _PAGE_ENC) { clflush_page(address); + /* + * If the encryption attribute is being cleared, change the page state + * to shared in the RMP table. + */ + if (clr) + snp_set_page_shared(__pa(address & PAGE_MASK)); + } + /* Update PTE */ pte = *ptep; pte = pte_set_flags(pte, set); pte = pte_clear_flags(pte, clr); set_pte(ptep, pte); + /* + * If the encryption attribute is being set, then change the page state to + * private in the RMP entry. The page state change must be done after the PTE + * is updated. + */ + if (set & _PAGE_ENC) + snp_set_page_private(__pa(address & PAGE_MASK)); + /* Flush TLB after changing encryption attribute */ write_cr3(top_level_pgt); @@ -347,5 +364,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) * Error code is sane - now identity map the 2M region around * the faulting address. */ - add_identity_map(address, end); + kernel_add_identity_map(address, end); } diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 9b93567d663a..6debb816e83d 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -39,7 +39,23 @@ void load_stage1_idt(void) load_boot_idt(&boot_idt_desc); } -/* Setup IDT after kernel jumping to .Lrelocated */ +/* + * Setup IDT after kernel jumping to .Lrelocated. + * + * initialize_identity_maps() needs a #PF handler to be setup + * in order to be able to fault-in identity mapping ranges; see + * do_boot_page_fault(). + * + * This #PF handler setup needs to happen in load_stage2_idt() where the + * IDT is loaded and there the #VC IDT entry gets setup too. + * + * In order to be able to handle #VCs, one needs a GHCB which + * gets setup with an already set up pagetable, which is done in + * initialize_identity_maps(). And there's the catch 22: the boot #VC + * handler do_boot_stage2_vc() needs to call early_setup_ghcb() itself + * (and, especially set_page_decrypted()) because the SEV-ES setup code + * cannot initialize a GHCB as there's no #PF handler yet... + */ void load_stage2_idt(void) { boot_idt_desc.address = (unsigned long)boot_idt; diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 411b268bc0a2..4a3f223973f4 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -22,15 +22,14 @@ #include "misc.h" #include "error.h" #include "../string.h" +#include "efi.h" #include <generated/compile.h> #include <linux/module.h> #include <linux/uts.h> #include <linux/utsname.h> #include <linux/ctype.h> -#include <linux/efi.h> #include <generated/utsrelease.h> -#include <asm/efi.h> #define _SETUP #include <asm/setup.h> /* For COMMAND_LINE_SIZE */ diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index a63424d13627..a73e4d783cae 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -187,42 +187,6 @@ SYM_CODE_END(startup32_vc_handler) .code64 #include "../../kernel/sev_verify_cbit.S" -SYM_FUNC_START(set_sev_encryption_mask) -#ifdef CONFIG_AMD_MEM_ENCRYPT - push %rbp - push %rdx - - movq %rsp, %rbp /* Save current stack pointer */ - - call get_sev_encryption_bit /* Get the encryption bit position */ - testl %eax, %eax - jz .Lno_sev_mask - - bts %rax, sme_me_mask(%rip) /* Create the encryption mask */ - - /* - * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in - * get_sev_encryption_bit() because this function is 32-bit code and - * shared between 64-bit and 32-bit boot path. - */ - movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */ - rdmsr - - /* Store MSR value in sev_status */ - shlq $32, %rdx - orq %rdx, %rax - movq %rax, sev_status(%rip) - -.Lno_sev_mask: - movq %rbp, %rsp /* Restore original stack pointer */ - - pop %rdx - pop %rbp -#endif - - xor %rax, %rax - RET -SYM_FUNC_END(set_sev_encryption_mask) .data diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 1cdcaf34ee36..cf690d8712f4 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -48,12 +48,17 @@ void *memmove(void *dest, const void *src, size_t n); */ struct boot_params *boot_params; +struct port_io_ops pio_ops; + memptr free_mem_ptr; memptr free_mem_end_ptr; static char *vidmem; static int vidport; -static int lines, cols; + +/* These might be accessed before .bss is cleared, so use .data instead. */ +static int lines __section(".data"); +static int cols __section(".data"); #ifdef CONFIG_KERNEL_GZIP #include "../../../../lib/decompress_inflate.c" @@ -371,6 +376,16 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, lines = boot_params->screen_info.orig_video_lines; cols = boot_params->screen_info.orig_video_cols; + init_default_io_ops(); + + /* + * Detect TDX guest environment. + * + * It has to be done before console_init() in order to use + * paravirtualized port I/O operations if needed. + */ + early_tdx_detect(); + console_init(); /* diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 16ed360b6692..4910bf230d7b 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -22,17 +22,21 @@ #include <linux/linkage.h> #include <linux/screen_info.h> #include <linux/elf.h> -#include <linux/io.h> #include <asm/page.h> #include <asm/boot.h> #include <asm/bootparam.h> #include <asm/desc_defs.h> +#include "tdx.h" + #define BOOT_CTYPE_H #include <linux/acpi.h> #define BOOT_BOOT_H #include "../ctype.h" +#include "../io.h" + +#include "efi.h" #ifdef CONFIG_X86_64 #define memptr long @@ -120,17 +124,23 @@ static inline void console_init(void) { } #endif -void set_sev_encryption_mask(void); - #ifdef CONFIG_AMD_MEM_ENCRYPT +void sev_enable(struct boot_params *bp); void sev_es_shutdown_ghcb(void); extern bool sev_es_check_ghcb_fault(unsigned long address); +void snp_set_page_private(unsigned long paddr); +void snp_set_page_shared(unsigned long paddr); +void sev_prep_identity_maps(unsigned long top_level_pgt); #else +static inline void sev_enable(struct boot_params *bp) { } static inline void sev_es_shutdown_ghcb(void) { } static inline bool sev_es_check_ghcb_fault(unsigned long address) { return false; } +static inline void snp_set_page_private(unsigned long paddr) { } +static inline void snp_set_page_shared(unsigned long paddr) { } +static inline void sev_prep_identity_maps(unsigned long top_level_pgt) { } #endif /* acpi.c */ @@ -151,6 +161,7 @@ static inline int count_immovable_mem_regions(void) { return 0; } #ifdef CONFIG_X86_5LEVEL extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d; #endif +extern void kernel_add_identity_map(unsigned long start, unsigned long end); /* Used by PAGE_KERN* macros: */ extern pteval_t __default_kernel_pte_mask; @@ -172,4 +183,47 @@ void boot_stage2_vc(void); unsigned long sev_verify_cbit(unsigned long cr3); +enum efi_type { + EFI_TYPE_64, + EFI_TYPE_32, + EFI_TYPE_NONE, +}; + +#ifdef CONFIG_EFI +/* helpers for early EFI config table access */ +enum efi_type efi_get_type(struct boot_params *bp); +unsigned long efi_get_system_table(struct boot_params *bp); +int efi_get_conf_table(struct boot_params *bp, unsigned long *cfg_tbl_pa, + unsigned int *cfg_tbl_len); +unsigned long efi_find_vendor_table(struct boot_params *bp, + unsigned long cfg_tbl_pa, + unsigned int cfg_tbl_len, + efi_guid_t guid); +#else +static inline enum efi_type efi_get_type(struct boot_params *bp) +{ + return EFI_TYPE_NONE; +} + +static inline unsigned long efi_get_system_table(struct boot_params *bp) +{ + return 0; +} + +static inline int efi_get_conf_table(struct boot_params *bp, + unsigned long *cfg_tbl_pa, + unsigned int *cfg_tbl_len) +{ + return -ENOENT; +} + +static inline unsigned long efi_find_vendor_table(struct boot_params *bp, + unsigned long cfg_tbl_pa, + unsigned int cfg_tbl_len, + efi_guid_t guid) +{ + return 0; +} +#endif /* CONFIG_EFI */ + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h index 6ff7e81b5628..cc9b2529a086 100644 --- a/arch/x86/boot/compressed/pgtable.h +++ b/arch/x86/boot/compressed/pgtable.h @@ -6,7 +6,7 @@ #define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 #define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE -#define TRAMPOLINE_32BIT_CODE_SIZE 0x70 +#define TRAMPOLINE_32BIT_CODE_SIZE 0x80 #define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index a1733319a22a..2ac12ff4111b 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,11 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" -#include <linux/efi.h> #include <asm/e820/types.h> #include <asm/processor.h> -#include <asm/efi.h> #include "pgtable.h" #include "../string.h" +#include "efi.h" #define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */ #define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */ diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 28bcf04c022e..52f989f6acc2 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -20,8 +20,10 @@ #include <asm/fpu/xcr.h> #include <asm/ptrace.h> #include <asm/svm.h> +#include <asm/cpuid.h> #include "error.h" +#include "../msr.h" struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); struct ghcb *boot_ghcb; @@ -56,23 +58,19 @@ static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx) static inline u64 sev_es_rd_ghcb_msr(void) { - unsigned long low, high; + struct msr m; - asm volatile("rdmsr" : "=a" (low), "=d" (high) : - "c" (MSR_AMD64_SEV_ES_GHCB)); + boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m); - return ((high << 32) | low); + return m.q; } static inline void sev_es_wr_ghcb_msr(u64 val) { - u32 low, high; + struct msr m; - low = val & 0xffffffffUL; - high = val >> 32; - - asm volatile("wrmsr" : : "c" (MSR_AMD64_SEV_ES_GHCB), - "a"(low), "d" (high) : "memory"); + m.q = val; + boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m); } static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) @@ -119,11 +117,54 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, /* Include code for early handlers */ #include "../../kernel/sev-shared.c" -static bool early_setup_sev_es(void) +static inline bool sev_snp_enabled(void) +{ + return sev_status & MSR_AMD64_SEV_SNP_ENABLED; +} + +static void __page_state_change(unsigned long paddr, enum psc_op op) +{ + u64 val; + + if (!sev_snp_enabled()) + return; + + /* + * If private -> shared then invalidate the page before requesting the + * state change in the RMP table. + */ + if (op == SNP_PAGE_STATE_SHARED && pvalidate(paddr, RMP_PG_SIZE_4K, 0)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); + + /* Issue VMGEXIT to change the page state in RMP table. */ + sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); + VMGEXIT(); + + /* Read the response of the VMGEXIT. */ + val = sev_es_rd_ghcb_msr(); + if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); + + /* + * Now that page state is changed in the RMP table, validate it so that it is + * consistent with the RMP entry. + */ + if (op == SNP_PAGE_STATE_PRIVATE && pvalidate(paddr, RMP_PG_SIZE_4K, 1)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); +} + +void snp_set_page_private(unsigned long paddr) +{ + __page_state_change(paddr, SNP_PAGE_STATE_PRIVATE); +} + +void snp_set_page_shared(unsigned long paddr) { - if (!sev_es_negotiate_protocol()) - sev_es_terminate(GHCB_SEV_ES_PROT_UNSUPPORTED); + __page_state_change(paddr, SNP_PAGE_STATE_SHARED); +} +static bool early_setup_ghcb(void) +{ if (set_page_decrypted((unsigned long)&boot_ghcb_page)) return false; @@ -135,6 +176,10 @@ static bool early_setup_sev_es(void) /* Initialize lookup tables for the instruction decoder */ inat_init_tables(); + /* SNP guest requires the GHCB GPA must be registered */ + if (sev_snp_enabled()) + snp_register_ghcb_early(__pa(&boot_ghcb_page)); + return true; } @@ -174,8 +219,8 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) struct es_em_ctxt ctxt; enum es_result result; - if (!boot_ghcb && !early_setup_sev_es()) - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + if (!boot_ghcb && !early_setup_ghcb()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); vc_ghcb_invalidate(boot_ghcb); result = vc_init_em_ctxt(&ctxt, regs, exit_code); @@ -202,5 +247,191 @@ finish: if (result == ES_OK) vc_finish_insn(&ctxt); else if (result != ES_RETRY) - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); +} + +static void enforce_vmpl0(void) +{ + u64 attrs; + int err; + + /* + * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically + * higher) privilege level. Here, clear the VMPL1 permission mask of the + * GHCB page. If the guest is not running at VMPL0, this will fail. + * + * If the guest is running at VMPL0, it will succeed. Even if that operation + * modifies permission bits, it is still ok to do so currently because Linux + * SNP guests are supported only on VMPL0 so VMPL1 or higher permission masks + * changing is a don't-care. + */ + attrs = 1; + if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, attrs)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); +} + +void sev_enable(struct boot_params *bp) +{ + unsigned int eax, ebx, ecx, edx; + struct msr m; + bool snp; + + /* + * Setup/preliminary detection of SNP. This will be sanity-checked + * against CPUID/MSR values later. + */ + snp = snp_init(bp); + + /* Check for the SME/SEV support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return; + + /* + * Check for the SME/SEV feature: + * CPUID Fn8000_001F[EAX] + * - Bit 0 - Secure Memory Encryption support + * - Bit 1 - Secure Encrypted Virtualization support + * CPUID Fn8000_001F[EBX] + * - Bits 5:0 - Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + /* Check whether SEV is supported */ + if (!(eax & BIT(1))) { + if (snp) + error("SEV-SNP support indicated by CC blob, but not CPUID."); + return; + } + + /* Set the SME mask if this is an SEV guest. */ + boot_rdmsr(MSR_AMD64_SEV, &m); + sev_status = m.q; + if (!(sev_status & MSR_AMD64_SEV_ENABLED)) + return; + + /* Negotiate the GHCB protocol version. */ + if (sev_status & MSR_AMD64_SEV_ES_ENABLED) { + if (!sev_es_negotiate_protocol()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_PROT_UNSUPPORTED); + } + + /* + * SNP is supported in v2 of the GHCB spec which mandates support for HV + * features. + */ + if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { + if (!(get_hv_features() & GHCB_HV_FT_SNP)) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + enforce_vmpl0(); + } + + if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + error("SEV-SNP supported indicated by CC blob, but not SEV status MSR."); + + sme_me_mask = BIT_ULL(ebx & 0x3f); +} + +/* Search for Confidential Computing blob in the EFI config table. */ +static struct cc_blob_sev_info *find_cc_blob_efi(struct boot_params *bp) +{ + unsigned long cfg_table_pa; + unsigned int cfg_table_len; + int ret; + + ret = efi_get_conf_table(bp, &cfg_table_pa, &cfg_table_len); + if (ret) + return NULL; + + return (struct cc_blob_sev_info *)efi_find_vendor_table(bp, cfg_table_pa, + cfg_table_len, + EFI_CC_BLOB_GUID); +} + +/* + * Initial set up of SNP relies on information provided by the + * Confidential Computing blob, which can be passed to the boot kernel + * by firmware/bootloader in the following ways: + * + * - via an entry in the EFI config table + * - via a setup_data structure, as defined by the Linux Boot Protocol + * + * Scan for the blob in that order. + */ +static struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + cc_info = find_cc_blob_efi(bp); + if (cc_info) + goto found_cc_info; + + cc_info = find_cc_blob_setup_data(bp); + if (!cc_info) + return NULL; + +found_cc_info: + if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + return cc_info; +} + +/* + * Indicate SNP based on presence of SNP-specific CC blob. Subsequent checks + * will verify the SNP CPUID/MSR bits. + */ +bool snp_init(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + if (!bp) + return false; + + cc_info = find_cc_blob(bp); + if (!cc_info) + return false; + + /* + * If a SNP-specific Confidential Computing blob is present, then + * firmware/bootloader have indicated SNP support. Verifying this + * involves CPUID checks which will be more reliable if the SNP + * CPUID table is used. See comments over snp_setup_cpuid_table() for + * more details. + */ + setup_cpuid_table(cc_info); + + /* + * Pass run-time kernel a pointer to CC info via boot_params so EFI + * config table doesn't need to be searched again during early startup + * phase. + */ + bp->cc_blob_address = (u32)(unsigned long)cc_info; + + return true; +} + +void sev_prep_identity_maps(unsigned long top_level_pgt) +{ + /* + * The Confidential Computing blob is used very early in uncompressed + * kernel to find the in-memory CPUID table to handle CPUID + * instructions. Make sure an identity-mapping exists so it can be + * accessed after switchover. + */ + if (sev_snp_enabled()) { + unsigned long cc_info_pa = boot_params->cc_blob_address; + struct cc_blob_sev_info *cc_info; + + kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info)); + + cc_info = (struct cc_blob_sev_info *)cc_info_pa; + kernel_add_identity_map(cc_info->cpuid_phys, cc_info->cpuid_phys + cc_info->cpuid_len); + } + + sev_verify_cbit(top_level_pgt); } diff --git a/arch/x86/boot/compressed/tdcall.S b/arch/x86/boot/compressed/tdcall.S new file mode 100644 index 000000000000..46d0495e0d3a --- /dev/null +++ b/arch/x86/boot/compressed/tdcall.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include "../../coco/tdx/tdcall.S" diff --git a/arch/x86/boot/compressed/tdx.c b/arch/x86/boot/compressed/tdx.c new file mode 100644 index 000000000000..918a7606f53c --- /dev/null +++ b/arch/x86/boot/compressed/tdx.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "../cpuflags.h" +#include "../string.h" +#include "../io.h" +#include "error.h" + +#include <vdso/limits.h> +#include <uapi/asm/vmx.h> + +#include <asm/shared/tdx.h> + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __tdx_hypercall_failed(void) +{ + error("TDVMCALL failed. TDX module bug?"); +} + +static inline unsigned int tdx_io_in(int size, u16 port) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = EXIT_REASON_IO_INSTRUCTION, + .r12 = size, + .r13 = 0, + .r14 = port, + }; + + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return UINT_MAX; + + return args.r11; +} + +static inline void tdx_io_out(int size, u16 port, u32 value) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = EXIT_REASON_IO_INSTRUCTION, + .r12 = size, + .r13 = 1, + .r14 = port, + .r15 = value, + }; + + __tdx_hypercall(&args, 0); +} + +static inline u8 tdx_inb(u16 port) +{ + return tdx_io_in(1, port); +} + +static inline void tdx_outb(u8 value, u16 port) +{ + tdx_io_out(1, port, value); +} + +static inline void tdx_outw(u16 value, u16 port) +{ + tdx_io_out(2, port, value); +} + +void early_tdx_detect(void) +{ + u32 eax, sig[3]; + + cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, &sig[0], &sig[2], &sig[1]); + + if (memcmp(TDX_IDENT, sig, sizeof(sig))) + return; + + /* Use hypercalls instead of I/O instructions */ + pio_ops.f_inb = tdx_inb; + pio_ops.f_outb = tdx_outb; + pio_ops.f_outw = tdx_outw; +} diff --git a/arch/x86/boot/compressed/tdx.h b/arch/x86/boot/compressed/tdx.h new file mode 100644 index 000000000000..9055482cd35c --- /dev/null +++ b/arch/x86/boot/compressed/tdx.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef BOOT_COMPRESSED_TDX_H +#define BOOT_COMPRESSED_TDX_H + +#include <linux/types.h> + +#ifdef CONFIG_INTEL_TDX_GUEST +void early_tdx_detect(void); +#else +static inline void early_tdx_detect(void) { }; +#endif + +#endif /* BOOT_COMPRESSED_TDX_H */ diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c index e1478d32de1a..fed8d13ce252 100644 --- a/arch/x86/boot/cpucheck.c +++ b/arch/x86/boot/cpucheck.c @@ -27,6 +27,7 @@ #include <asm/required-features.h> #include <asm/msr-index.h> #include "string.h" +#include "msr.h" static u32 err_flags[NCAPINTS]; @@ -130,12 +131,11 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr) /* If this is an AMD and we're only missing SSE+SSE2, try to turn them on */ - u32 ecx = MSR_K7_HWCR; - u32 eax, edx; + struct msr m; - asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx)); - eax &= ~(1 << 15); - asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); + boot_rdmsr(MSR_K7_HWCR, &m); + m.l &= ~(1 << 15); + boot_wrmsr(MSR_K7_HWCR, &m); get_cpuflags(); /* Make sure it really did something */ err = check_cpuflags(); @@ -145,28 +145,28 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr) /* If this is a VIA C3, we might have to enable CX8 explicitly */ - u32 ecx = MSR_VIA_FCR; - u32 eax, edx; + struct msr m; - asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx)); - eax |= (1<<1)|(1<<7); - asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); + boot_rdmsr(MSR_VIA_FCR, &m); + m.l |= (1 << 1) | (1 << 7); + boot_wrmsr(MSR_VIA_FCR, &m); set_bit(X86_FEATURE_CX8, cpu.flags); err = check_cpuflags(); } else if (err == 0x01 && is_transmeta()) { /* Transmeta might have masked feature bits in word 0 */ - u32 ecx = 0x80860004; - u32 eax, edx; + struct msr m, m_tmp; u32 level = 1; - asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx)); - asm("wrmsr" : : "a" (~0), "d" (edx), "c" (ecx)); + boot_rdmsr(0x80860004, &m); + m_tmp = m; + m_tmp.l = ~0; + boot_wrmsr(0x80860004, &m_tmp); asm("cpuid" : "+a" (level), "=d" (cpu.flags[0]) : : "ecx", "ebx"); - asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); + boot_wrmsr(0x80860004, &m); err = check_cpuflags(); } else if (err == 0x01 && diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index a0b75f73dc63..a83d67ec627d 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -71,8 +71,7 @@ int has_eflag(unsigned long mask) # define EBX_REG "=b" #endif -static inline void cpuid_count(u32 id, u32 count, - u32 *a, u32 *b, u32 *c, u32 *d) +void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d) { asm volatile(".ifnc %%ebx,%3 ; movl %%ebx,%3 ; .endif \n\t" "cpuid \n\t" diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h index 2e20814d3ce3..475b8fde90f7 100644 --- a/arch/x86/boot/cpuflags.h +++ b/arch/x86/boot/cpuflags.h @@ -17,5 +17,6 @@ extern u32 cpu_vendor[3]; int has_eflag(unsigned long mask); void get_cpuflags(void); +void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d); #endif diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 6dbd7e9f74c9..0352e4589efa 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -163,7 +163,11 @@ extra_header_fields: .long 0x200 # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) +#ifdef CONFIG_DXE_MEM_ATTRIBUTES + .word IMAGE_DLL_CHARACTERISTICS_NX_COMPAT # DllCharacteristics +#else .word 0 # DllCharacteristics +#endif #ifdef CONFIG_X86_32 .long 0 # SizeOfStackReserve .long 0 # SizeOfStackCommit diff --git a/arch/x86/boot/io.h b/arch/x86/boot/io.h new file mode 100644 index 000000000000..110880907f87 --- /dev/null +++ b/arch/x86/boot/io.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef BOOT_IO_H +#define BOOT_IO_H + +#include <asm/shared/io.h> + +#undef inb +#undef inw +#undef inl +#undef outb +#undef outw +#undef outl + +struct port_io_ops { + u8 (*f_inb)(u16 port); + void (*f_outb)(u8 v, u16 port); + void (*f_outw)(u16 v, u16 port); +}; + +extern struct port_io_ops pio_ops; + +/* + * Use the normal I/O instructions by default. + * TDX guests override these to use hypercalls. + */ +static inline void init_default_io_ops(void) +{ + pio_ops.f_inb = __inb; + pio_ops.f_outb = __outb; + pio_ops.f_outw = __outw; +} + +/* + * Redirect port I/O operations via pio_ops callbacks. + * TDX guests override these callbacks with TDX-specific helpers. + */ +#define inb pio_ops.f_inb +#define outb pio_ops.f_outb +#define outw pio_ops.f_outw + +#endif diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index e3add857c2c9..c4ea5258ab55 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -17,6 +17,8 @@ struct boot_params boot_params __attribute__((aligned(16))); +struct port_io_ops pio_ops; + char *HEAP = _end; char *heap_end = _end; /* Default end of heap = no heap */ @@ -33,7 +35,7 @@ static void copy_boot_params(void) u16 cl_offset; }; const struct old_cmdline * const oldcmd = - (const struct old_cmdline *)OLD_CL_ADDRESS; + absolute_pointer(OLD_CL_ADDRESS); BUILD_BUG_ON(sizeof(boot_params) != 4096); memcpy(&boot_params.hdr, &hdr, sizeof(hdr)); @@ -133,6 +135,8 @@ static void init_heap(void) void main(void) { + init_default_io_ops(); + /* First, copy the boot header into the "zeropage" */ copy_boot_params(); diff --git a/arch/x86/boot/msr.h b/arch/x86/boot/msr.h new file mode 100644 index 000000000000..aed66f7ae199 --- /dev/null +++ b/arch/x86/boot/msr.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Helpers/definitions related to MSR access. + */ + +#ifndef BOOT_MSR_H +#define BOOT_MSR_H + +#include <asm/shared/msr.h> + +/* + * The kernel proper already defines rdmsr()/wrmsr(), but they are not for the + * boot kernel since they rely on tracepoint/exception handling infrastructure + * that's not available here. + */ +static inline void boot_rdmsr(unsigned int reg, struct msr *m) +{ + asm volatile("rdmsr" : "=a" (m->l), "=d" (m->h) : "c" (reg)); +} + +static inline void boot_wrmsr(unsigned int reg, const struct msr *m) +{ + asm volatile("wrmsr" : : "c" (reg), "a"(m->l), "d" (m->h) : "memory"); +} + +#endif /* BOOT_MSR_H */ diff --git a/arch/x86/coco/Makefile b/arch/x86/coco/Makefile index c1ead00017a7..c816acf78b6a 100644 --- a/arch/x86/coco/Makefile +++ b/arch/x86/coco/Makefile @@ -4,3 +4,5 @@ KASAN_SANITIZE_core.o := n CFLAGS_core.o += -fno-stack-protector obj-y += core.o + +obj-$(CONFIG_INTEL_TDX_GUEST) += tdx/ diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index fc1365dd927e..49b44f881484 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -18,7 +18,15 @@ static u64 cc_mask __ro_after_init; static bool intel_cc_platform_has(enum cc_attr attr) { - return false; + switch (attr) { + case CC_ATTR_GUEST_UNROLL_STRING_IO: + case CC_ATTR_HOTPLUG_DISABLED: + case CC_ATTR_GUEST_MEM_ENCRYPT: + case CC_ATTR_MEM_ENCRYPT: + return true; + default: + return false; + } } /* @@ -57,6 +65,9 @@ static bool amd_cc_platform_has(enum cc_attr attr) return (sev_status & MSR_AMD64_SEV_ENABLED) && !(sev_status & MSR_AMD64_SEV_ES_ENABLED); + case CC_ATTR_GUEST_SEV_SNP: + return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + default: return false; } @@ -87,9 +98,18 @@ EXPORT_SYMBOL_GPL(cc_platform_has); u64 cc_mkenc(u64 val) { + /* + * Both AMD and Intel use a bit in the page table to indicate + * encryption status of the page. + * + * - for AMD, bit *set* means the page is encrypted + * - for Intel *clear* means encrypted. + */ switch (vendor) { case CC_VENDOR_AMD: return val | cc_mask; + case CC_VENDOR_INTEL: + return val & ~cc_mask; default: return val; } @@ -97,9 +117,12 @@ u64 cc_mkenc(u64 val) u64 cc_mkdec(u64 val) { + /* See comment in cc_mkenc() */ switch (vendor) { case CC_VENDOR_AMD: return val & ~cc_mask; + case CC_VENDOR_INTEL: + return val | cc_mask; default: return val; } diff --git a/arch/x86/coco/tdx/Makefile b/arch/x86/coco/tdx/Makefile new file mode 100644 index 000000000000..46c55998557d --- /dev/null +++ b/arch/x86/coco/tdx/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += tdx.o tdcall.o diff --git a/arch/x86/coco/tdx/tdcall.S b/arch/x86/coco/tdx/tdcall.S new file mode 100644 index 000000000000..f9eb1134f22d --- /dev/null +++ b/arch/x86/coco/tdx/tdcall.S @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/asm-offsets.h> +#include <asm/asm.h> +#include <asm/frame.h> +#include <asm/unwind_hints.h> + +#include <linux/linkage.h> +#include <linux/bits.h> +#include <linux/errno.h> + +#include "../../virt/vmx/tdx/tdxcall.S" + +/* + * Bitmasks of exposed registers (with VMM). + */ +#define TDX_R10 BIT(10) +#define TDX_R11 BIT(11) +#define TDX_R12 BIT(12) +#define TDX_R13 BIT(13) +#define TDX_R14 BIT(14) +#define TDX_R15 BIT(15) + +/* + * These registers are clobbered to hold arguments for each + * TDVMCALL. They are safe to expose to the VMM. + * Each bit in this mask represents a register ID. Bit field + * details can be found in TDX GHCI specification, section + * titled "TDCALL [TDG.VP.VMCALL] leaf". + */ +#define TDVMCALL_EXPOSE_REGS_MASK ( TDX_R10 | TDX_R11 | \ + TDX_R12 | TDX_R13 | \ + TDX_R14 | TDX_R15 ) + +/* + * __tdx_module_call() - Used by TDX guests to request services from + * the TDX module (does not include VMM services) using TDCALL instruction. + * + * Transforms function call register arguments into the TDCALL register ABI. + * After TDCALL operation, TDX module output is saved in @out (if it is + * provided by the user). + * + *------------------------------------------------------------------------- + * TDCALL ABI: + *------------------------------------------------------------------------- + * Input Registers: + * + * RAX - TDCALL Leaf number. + * RCX,RDX,R8-R9 - TDCALL Leaf specific input registers. + * + * Output Registers: + * + * RAX - TDCALL instruction error code. + * RCX,RDX,R8-R11 - TDCALL Leaf specific output registers. + * + *------------------------------------------------------------------------- + * + * __tdx_module_call() function ABI: + * + * @fn (RDI) - TDCALL Leaf ID, moved to RAX + * @rcx (RSI) - Input parameter 1, moved to RCX + * @rdx (RDX) - Input parameter 2, moved to RDX + * @r8 (RCX) - Input parameter 3, moved to R8 + * @r9 (R8) - Input parameter 4, moved to R9 + * + * @out (R9) - struct tdx_module_output pointer + * stored temporarily in R12 (not + * shared with the TDX module). It + * can be NULL. + * + * Return status of TDCALL via RAX. + */ +SYM_FUNC_START(__tdx_module_call) + FRAME_BEGIN + TDX_MODULE_CALL host=0 + FRAME_END + RET +SYM_FUNC_END(__tdx_module_call) + +/* + * __tdx_hypercall() - Make hypercalls to a TDX VMM using TDVMCALL leaf + * of TDCALL instruction + * + * Transforms values in function call argument struct tdx_hypercall_args @args + * into the TDCALL register ABI. After TDCALL operation, VMM output is saved + * back in @args. + * + *------------------------------------------------------------------------- + * TD VMCALL ABI: + *------------------------------------------------------------------------- + * + * Input Registers: + * + * RAX - TDCALL instruction leaf number (0 - TDG.VP.VMCALL) + * RCX - BITMAP which controls which part of TD Guest GPR + * is passed as-is to the VMM and back. + * R10 - Set 0 to indicate TDCALL follows standard TDX ABI + * specification. Non zero value indicates vendor + * specific ABI. + * R11 - VMCALL sub function number + * RBX, RBP, RDI, RSI - Used to pass VMCALL sub function specific arguments. + * R8-R9, R12-R15 - Same as above. + * + * Output Registers: + * + * RAX - TDCALL instruction status (Not related to hypercall + * output). + * R10 - Hypercall output error code. + * R11-R15 - Hypercall sub function specific output values. + * + *------------------------------------------------------------------------- + * + * __tdx_hypercall() function ABI: + * + * @args (RDI) - struct tdx_hypercall_args for input and output + * @flags (RSI) - TDX_HCALL_* flags + * + * On successful completion, return the hypercall error code. + */ +SYM_FUNC_START(__tdx_hypercall) + FRAME_BEGIN + + /* Save callee-saved GPRs as mandated by the x86_64 ABI */ + push %r15 + push %r14 + push %r13 + push %r12 + + /* Mangle function call ABI into TDCALL ABI: */ + /* Set TDCALL leaf ID (TDVMCALL (0)) in RAX */ + xor %eax, %eax + + /* Copy hypercall registers from arg struct: */ + movq TDX_HYPERCALL_r10(%rdi), %r10 + movq TDX_HYPERCALL_r11(%rdi), %r11 + movq TDX_HYPERCALL_r12(%rdi), %r12 + movq TDX_HYPERCALL_r13(%rdi), %r13 + movq TDX_HYPERCALL_r14(%rdi), %r14 + movq TDX_HYPERCALL_r15(%rdi), %r15 + + movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx + + /* + * For the idle loop STI needs to be called directly before the TDCALL + * that enters idle (EXIT_REASON_HLT case). STI instruction enables + * interrupts only one instruction later. If there is a window between + * STI and the instruction that emulates the HALT state, there is a + * chance for interrupts to happen in this window, which can delay the + * HLT operation indefinitely. Since this is the not the desired + * result, conditionally call STI before TDCALL. + */ + testq $TDX_HCALL_ISSUE_STI, %rsi + jz .Lskip_sti + sti +.Lskip_sti: + tdcall + + /* + * RAX==0 indicates a failure of the TDVMCALL mechanism itself and that + * something has gone horribly wrong with the TDX module. + * + * The return status of the hypercall operation is in a separate + * register (in R10). Hypercall errors are a part of normal operation + * and are handled by callers. + */ + testq %rax, %rax + jne .Lpanic + + /* TDVMCALL leaf return code is in R10 */ + movq %r10, %rax + + /* Copy hypercall result registers to arg struct if needed */ + testq $TDX_HCALL_HAS_OUTPUT, %rsi + jz .Lout + + movq %r10, TDX_HYPERCALL_r10(%rdi) + movq %r11, TDX_HYPERCALL_r11(%rdi) + movq %r12, TDX_HYPERCALL_r12(%rdi) + movq %r13, TDX_HYPERCALL_r13(%rdi) + movq %r14, TDX_HYPERCALL_r14(%rdi) + movq %r15, TDX_HYPERCALL_r15(%rdi) +.Lout: + /* + * Zero out registers exposed to the VMM to avoid speculative execution + * with VMM-controlled values. This needs to include all registers + * present in TDVMCALL_EXPOSE_REGS_MASK (except R12-R15). R12-R15 + * context will be restored. + */ + xor %r10d, %r10d + xor %r11d, %r11d + + /* Restore callee-saved GPRs as mandated by the x86_64 ABI */ + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + FRAME_END + + RET +.Lpanic: + call __tdx_hypercall_failed + /* __tdx_hypercall_failed never returns */ + REACHABLE + jmp .Lpanic +SYM_FUNC_END(__tdx_hypercall) diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c new file mode 100644 index 000000000000..03deb4d6920d --- /dev/null +++ b/arch/x86/coco/tdx/tdx.c @@ -0,0 +1,692 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021-2022 Intel Corporation */ + +#undef pr_fmt +#define pr_fmt(fmt) "tdx: " fmt + +#include <linux/cpufeature.h> +#include <asm/coco.h> +#include <asm/tdx.h> +#include <asm/vmx.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> +#include <asm/pgtable.h> + +/* TDX module Call Leaf IDs */ +#define TDX_GET_INFO 1 +#define TDX_GET_VEINFO 3 +#define TDX_ACCEPT_PAGE 6 + +/* TDX hypercall Leaf IDs */ +#define TDVMCALL_MAP_GPA 0x10001 + +/* MMIO direction */ +#define EPT_READ 0 +#define EPT_WRITE 1 + +/* Port I/O direction */ +#define PORT_READ 0 +#define PORT_WRITE 1 + +/* See Exit Qualification for I/O Instructions in VMX documentation */ +#define VE_IS_IO_IN(e) ((e) & BIT(3)) +#define VE_GET_IO_SIZE(e) (((e) & GENMASK(2, 0)) + 1) +#define VE_GET_PORT_NUM(e) ((e) >> 16) +#define VE_IS_IO_STRING(e) ((e) & BIT(4)) + +/* + * Wrapper for standard use of __tdx_hypercall with no output aside from + * return code. + */ +static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = fn, + .r12 = r12, + .r13 = r13, + .r14 = r14, + .r15 = r15, + }; + + return __tdx_hypercall(&args, 0); +} + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __tdx_hypercall_failed(void) +{ + panic("TDVMCALL failed. TDX module bug?"); +} + +/* + * The TDG.VP.VMCALL-Instruction-execution sub-functions are defined + * independently from but are currently matched 1:1 with VMX EXIT_REASONs. + * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and + * guest sides of these calls. + */ +static u64 hcall_func(u64 exit_reason) +{ + return exit_reason; +} + +#ifdef CONFIG_KVM_GUEST +long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2, + unsigned long p3, unsigned long p4) +{ + struct tdx_hypercall_args args = { + .r10 = nr, + .r11 = p1, + .r12 = p2, + .r13 = p3, + .r14 = p4, + }; + + return __tdx_hypercall(&args, 0); +} +EXPORT_SYMBOL_GPL(tdx_kvm_hypercall); +#endif + +/* + * Used for TDX guests to make calls directly to the TD module. This + * should only be used for calls that have no legitimate reason to fail + * or where the kernel can not survive the call failing. + */ +static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, + struct tdx_module_output *out) +{ + if (__tdx_module_call(fn, rcx, rdx, r8, r9, out)) + panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); +} + +static u64 get_cc_mask(void) +{ + struct tdx_module_output out; + unsigned int gpa_width; + + /* + * TDINFO TDX module call is used to get the TD execution environment + * information like GPA width, number of available vcpus, debug mode + * information, etc. More details about the ABI can be found in TDX + * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL + * [TDG.VP.INFO]. + * + * The GPA width that comes out of this call is critical. TDX guests + * can not meaningfully run without it. + */ + tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); + + gpa_width = out.rcx & GENMASK(5, 0); + + /* + * The highest bit of a guest physical address is the "sharing" bit. + * Set it for shared pages and clear it for private pages. + */ + return BIT_ULL(gpa_width - 1); +} + +static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_HLT), + .r12 = irq_disabled, + }; + + /* + * Emulate HLT operation via hypercall. More info about ABI + * can be found in TDX Guest-Host-Communication Interface + * (GHCI), section 3.8 TDG.VP.VMCALL<Instruction.HLT>. + * + * The VMM uses the "IRQ disabled" param to understand IRQ + * enabled status (RFLAGS.IF) of the TD guest and to determine + * whether or not it should schedule the halted vCPU if an + * IRQ becomes pending. E.g. if IRQs are disabled, the VMM + * can keep the vCPU in virtual HLT, even if an IRQ is + * pending, without hanging/breaking the guest. + */ + return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0); +} + +static bool handle_halt(void) +{ + /* + * Since non safe halt is mainly used in CPU offlining + * and the guest will always stay in the halt state, don't + * call the STI instruction (set do_sti as false). + */ + const bool irq_disabled = irqs_disabled(); + const bool do_sti = false; + + if (__halt(irq_disabled, do_sti)) + return false; + + return true; +} + +void __cpuidle tdx_safe_halt(void) +{ + /* + * For do_sti=true case, __tdx_hypercall() function enables + * interrupts using the STI instruction before the TDCALL. So + * set irq_disabled as false. + */ + const bool irq_disabled = false; + const bool do_sti = true; + + /* + * Use WARN_ONCE() to report the failure. + */ + if (__halt(irq_disabled, do_sti)) + WARN_ONCE(1, "HLT instruction emulation failed\n"); +} + +static bool read_msr(struct pt_regs *regs) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_MSR_READ), + .r12 = regs->cx, + }; + + /* + * Emulate the MSR read via hypercall. More info about ABI + * can be found in TDX Guest-Host-Communication Interface + * (GHCI), section titled "TDG.VP.VMCALL<Instruction.RDMSR>". + */ + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return false; + + regs->ax = lower_32_bits(args.r11); + regs->dx = upper_32_bits(args.r11); + return true; +} + +static bool write_msr(struct pt_regs *regs) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_MSR_WRITE), + .r12 = regs->cx, + .r13 = (u64)regs->dx << 32 | regs->ax, + }; + + /* + * Emulate the MSR write via hypercall. More info about ABI + * can be found in TDX Guest-Host-Communication Interface + * (GHCI) section titled "TDG.VP.VMCALL<Instruction.WRMSR>". + */ + return !__tdx_hypercall(&args, 0); +} + +static bool handle_cpuid(struct pt_regs *regs) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_CPUID), + .r12 = regs->ax, + .r13 = regs->cx, + }; + + /* + * Only allow VMM to control range reserved for hypervisor + * communication. + * + * Return all-zeros for any CPUID outside the range. It matches CPU + * behaviour for non-supported leaf. + */ + if (regs->ax < 0x40000000 || regs->ax > 0x4FFFFFFF) { + regs->ax = regs->bx = regs->cx = regs->dx = 0; + return true; + } + + /* + * Emulate the CPUID instruction via a hypercall. More info about + * ABI can be found in TDX Guest-Host-Communication Interface + * (GHCI), section titled "VP.VMCALL<Instruction.CPUID>". + */ + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return false; + + /* + * As per TDX GHCI CPUID ABI, r12-r15 registers contain contents of + * EAX, EBX, ECX, EDX registers after the CPUID instruction execution. + * So copy the register contents back to pt_regs. + */ + regs->ax = args.r12; + regs->bx = args.r13; + regs->cx = args.r14; + regs->dx = args.r15; + + return true; +} + +static bool mmio_read(int size, unsigned long addr, unsigned long *val) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_EPT_VIOLATION), + .r12 = size, + .r13 = EPT_READ, + .r14 = addr, + .r15 = *val, + }; + + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return false; + *val = args.r11; + return true; +} + +static bool mmio_write(int size, unsigned long addr, unsigned long val) +{ + return !_tdx_hypercall(hcall_func(EXIT_REASON_EPT_VIOLATION), size, + EPT_WRITE, addr, val); +} + +static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) +{ + char buffer[MAX_INSN_SIZE]; + unsigned long *reg, val; + struct insn insn = {}; + enum mmio_type mmio; + int size, extend_size; + u8 extend_val = 0; + + /* Only in-kernel MMIO is supported */ + if (WARN_ON_ONCE(user_mode(regs))) + return false; + + if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE)) + return false; + + if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64)) + return false; + + mmio = insn_decode_mmio(&insn, &size); + if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED)) + return false; + + if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + reg = insn_get_modrm_reg_ptr(&insn, regs); + if (!reg) + return false; + } + + ve->instr_len = insn.length; + + /* Handle writes first */ + switch (mmio) { + case MMIO_WRITE: + memcpy(&val, reg, size); + return mmio_write(size, ve->gpa, val); + case MMIO_WRITE_IMM: + val = insn.immediate.value; + return mmio_write(size, ve->gpa, val); + case MMIO_READ: + case MMIO_READ_ZERO_EXTEND: + case MMIO_READ_SIGN_EXTEND: + /* Reads are handled below */ + break; + case MMIO_MOVS: + case MMIO_DECODE_FAILED: + /* + * MMIO was accessed with an instruction that could not be + * decoded or handled properly. It was likely not using io.h + * helpers or accessed MMIO accidentally. + */ + return false; + default: + WARN_ONCE(1, "Unknown insn_decode_mmio() decode value?"); + return false; + } + + /* Handle reads */ + if (!mmio_read(size, ve->gpa, &val)) + return false; + + switch (mmio) { + case MMIO_READ: + /* Zero-extend for 32-bit operation */ + extend_size = size == 4 ? sizeof(*reg) : 0; + break; + case MMIO_READ_ZERO_EXTEND: + /* Zero extend based on operand size */ + extend_size = insn.opnd_bytes; + break; + case MMIO_READ_SIGN_EXTEND: + /* Sign extend based on operand size */ + extend_size = insn.opnd_bytes; + if (size == 1 && val & BIT(7)) + extend_val = 0xFF; + else if (size > 1 && val & BIT(15)) + extend_val = 0xFF; + break; + default: + /* All other cases has to be covered with the first switch() */ + WARN_ON_ONCE(1); + return false; + } + + if (extend_size) + memset(reg, extend_val, extend_size); + memcpy(reg, &val, size); + return true; +} + +static bool handle_in(struct pt_regs *regs, int size, int port) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION), + .r12 = size, + .r13 = PORT_READ, + .r14 = port, + }; + u64 mask = GENMASK(BITS_PER_BYTE * size, 0); + bool success; + + /* + * Emulate the I/O read via hypercall. More info about ABI can be found + * in TDX Guest-Host-Communication Interface (GHCI) section titled + * "TDG.VP.VMCALL<Instruction.IO>". + */ + success = !__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT); + + /* Update part of the register affected by the emulated instruction */ + regs->ax &= ~mask; + if (success) + regs->ax |= args.r11 & mask; + + return success; +} + +static bool handle_out(struct pt_regs *regs, int size, int port) +{ + u64 mask = GENMASK(BITS_PER_BYTE * size, 0); + + /* + * Emulate the I/O write via hypercall. More info about ABI can be found + * in TDX Guest-Host-Communication Interface (GHCI) section titled + * "TDG.VP.VMCALL<Instruction.IO>". + */ + return !_tdx_hypercall(hcall_func(EXIT_REASON_IO_INSTRUCTION), size, + PORT_WRITE, port, regs->ax & mask); +} + +/* + * Emulate I/O using hypercall. + * + * Assumes the IO instruction was using ax, which is enforced + * by the standard io.h macros. + * + * Return True on success or False on failure. + */ +static bool handle_io(struct pt_regs *regs, u32 exit_qual) +{ + int size, port; + bool in; + + if (VE_IS_IO_STRING(exit_qual)) + return false; + + in = VE_IS_IO_IN(exit_qual); + size = VE_GET_IO_SIZE(exit_qual); + port = VE_GET_PORT_NUM(exit_qual); + + + if (in) + return handle_in(regs, size, port); + else + return handle_out(regs, size, port); +} + +/* + * Early #VE exception handler. Only handles a subset of port I/O. + * Intended only for earlyprintk. If failed, return false. + */ +__init bool tdx_early_handle_ve(struct pt_regs *regs) +{ + struct ve_info ve; + + tdx_get_ve_info(&ve); + + if (ve.exit_reason != EXIT_REASON_IO_INSTRUCTION) + return false; + + return handle_io(regs, ve.exit_qual); +} + +void tdx_get_ve_info(struct ve_info *ve) +{ + struct tdx_module_output out; + + /* + * Called during #VE handling to retrieve the #VE info from the + * TDX module. + * + * This has to be called early in #VE handling. A "nested" #VE which + * occurs before this will raise a #DF and is not recoverable. + * + * The call retrieves the #VE info from the TDX module, which also + * clears the "#VE valid" flag. This must be done before anything else + * because any #VE that occurs while the valid flag is set will lead to + * #DF. + * + * Note, the TDX module treats virtual NMIs as inhibited if the #VE + * valid flag is set. It means that NMI=>#VE will not result in a #DF. + */ + tdx_module_call(TDX_GET_VEINFO, 0, 0, 0, 0, &out); + + /* Transfer the output parameters */ + ve->exit_reason = out.rcx; + ve->exit_qual = out.rdx; + ve->gla = out.r8; + ve->gpa = out.r9; + ve->instr_len = lower_32_bits(out.r10); + ve->instr_info = upper_32_bits(out.r10); +} + +/* Handle the user initiated #VE */ +static bool virt_exception_user(struct pt_regs *regs, struct ve_info *ve) +{ + switch (ve->exit_reason) { + case EXIT_REASON_CPUID: + return handle_cpuid(regs); + default: + pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); + return false; + } +} + +/* Handle the kernel #VE */ +static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve) +{ + switch (ve->exit_reason) { + case EXIT_REASON_HLT: + return handle_halt(); + case EXIT_REASON_MSR_READ: + return read_msr(regs); + case EXIT_REASON_MSR_WRITE: + return write_msr(regs); + case EXIT_REASON_CPUID: + return handle_cpuid(regs); + case EXIT_REASON_EPT_VIOLATION: + return handle_mmio(regs, ve); + case EXIT_REASON_IO_INSTRUCTION: + return handle_io(regs, ve->exit_qual); + default: + pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); + return false; + } +} + +bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve) +{ + bool ret; + + if (user_mode(regs)) + ret = virt_exception_user(regs, ve); + else + ret = virt_exception_kernel(regs, ve); + + /* After successful #VE handling, move the IP */ + if (ret) + regs->ip += ve->instr_len; + + return ret; +} + +static bool tdx_tlb_flush_required(bool private) +{ + /* + * TDX guest is responsible for flushing TLB on private->shared + * transition. VMM is responsible for flushing on shared->private. + * + * The VMM _can't_ flush private addresses as it can't generate PAs + * with the guest's HKID. Shared memory isn't subject to integrity + * checking, i.e. the VMM doesn't need to flush for its own protection. + * + * There's no need to flush when converting from shared to private, + * as flushing is the VMM's responsibility in this case, e.g. it must + * flush to avoid integrity failures in the face of a buggy or + * malicious guest. + */ + return !private; +} + +static bool tdx_cache_flush_required(void) +{ + /* + * AMD SME/SEV can avoid cache flushing if HW enforces cache coherence. + * TDX doesn't have such capability. + * + * Flush cache unconditionally. + */ + return true; +} + +static bool try_accept_one(phys_addr_t *start, unsigned long len, + enum pg_level pg_level) +{ + unsigned long accept_size = page_level_size(pg_level); + u64 tdcall_rcx; + u8 page_size; + + if (!IS_ALIGNED(*start, accept_size)) + return false; + + if (len < accept_size) + return false; + + /* + * Pass the page physical address to the TDX module to accept the + * pending, private page. + * + * Bits 2:0 of RCX encode page size: 0 - 4K, 1 - 2M, 2 - 1G. + */ + switch (pg_level) { + case PG_LEVEL_4K: + page_size = 0; + break; + case PG_LEVEL_2M: + page_size = 1; + break; + case PG_LEVEL_1G: + page_size = 2; + break; + default: + return false; + } + + tdcall_rcx = *start | page_size; + if (__tdx_module_call(TDX_ACCEPT_PAGE, tdcall_rcx, 0, 0, 0, NULL)) + return false; + + *start += accept_size; + return true; +} + +/* + * Inform the VMM of the guest's intent for this physical page: shared with + * the VMM or private to the guest. The VMM is expected to change its mapping + * of the page in response. + */ +static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc) +{ + phys_addr_t start = __pa(vaddr); + phys_addr_t end = __pa(vaddr + numpages * PAGE_SIZE); + + if (!enc) { + /* Set the shared (decrypted) bits: */ + start |= cc_mkdec(0); + end |= cc_mkdec(0); + } + + /* + * Notify the VMM about page mapping conversion. More info about ABI + * can be found in TDX Guest-Host-Communication Interface (GHCI), + * section "TDG.VP.VMCALL<MapGPA>" + */ + if (_tdx_hypercall(TDVMCALL_MAP_GPA, start, end - start, 0, 0)) + return false; + + /* private->shared conversion requires only MapGPA call */ + if (!enc) + return true; + + /* + * For shared->private conversion, accept the page using + * TDX_ACCEPT_PAGE TDX module call. + */ + while (start < end) { + unsigned long len = end - start; + + /* + * Try larger accepts first. It gives chance to VMM to keep + * 1G/2M SEPT entries where possible and speeds up process by + * cutting number of hypercalls (if successful). + */ + + if (try_accept_one(&start, len, PG_LEVEL_1G)) + continue; + + if (try_accept_one(&start, len, PG_LEVEL_2M)) + continue; + + if (!try_accept_one(&start, len, PG_LEVEL_4K)) + return false; + } + + return true; +} + +void __init tdx_early_init(void) +{ + u64 cc_mask; + u32 eax, sig[3]; + + cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, &sig[0], &sig[2], &sig[1]); + + if (memcmp(TDX_IDENT, sig, sizeof(sig))) + return; + + setup_force_cpu_cap(X86_FEATURE_TDX_GUEST); + + cc_set_vendor(CC_VENDOR_INTEL); + cc_mask = get_cc_mask(); + cc_set_mask(cc_mask); + + /* + * All bits above GPA width are reserved and kernel treats shared bit + * as flag, not as part of physical address. + * + * Adjust physical mask to only cover valid GPA bits. + */ + physical_mask &= cc_mask - 1; + + x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required; + x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required; + x86_platform.guest.enc_status_change_finish = tdx_enc_status_changed; + + pr_info("Guest detected\n"); +} diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index a4c061fb7c6e..29b36e9e4e74 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -63,7 +63,7 @@ For 32-bit we have the following conventions - kernel is built with * for assembly code: */ -.macro PUSH_REGS rdx=%rdx rax=%rax save_ret=0 +.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -73,7 +73,7 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ + pushq \rcx /* pt_regs->cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ pushq %r9 /* pt_regs->r9 */ @@ -99,6 +99,7 @@ For 32-bit we have the following conventions - kernel is built with * well before they could be put to use in a speculative execution * gadget. */ + xorl %esi, %esi /* nospec si */ xorl %edx, %edx /* nospec dx */ xorl %ecx, %ecx /* nospec cx */ xorl %r8d, %r8d /* nospec r8 */ @@ -114,32 +115,24 @@ For 32-bit we have the following conventions - kernel is built with .endm -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - PUSH_REGS rdx=\rdx, rax=\rax, save_ret=\save_ret +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 + PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret CLEAR_REGS .endm -.macro POP_REGS pop_rdi=1 skip_r11rcx=0 +.macro POP_REGS pop_rdi=1 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .if \skip_r11rcx - popq %rsi - .else popq %r11 - .endif popq %r10 popq %r9 popq %r8 popq %rax - .if \skip_r11rcx - popq %rsi - .else popq %rcx - .endif popq %rdx popq %rsi .if \pop_rdi diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4faac48ebec5..4300ba49b5ee 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -191,8 +191,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: - /* rcx and r11 are already restored (see code above) */ - POP_REGS pop_rdi=0 skip_r11rcx=1 + POP_REGS pop_rdi=0 /* * Now all regs are restored except RSP and RDI. @@ -215,8 +214,13 @@ syscall_return_via_sysret: popq %rdi popq %rsp +SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL) + ANNOTATE_NOENDBR swapgs sysretq +SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL) + ANNOTATE_NOENDBR + int3 SYM_CODE_END(entry_SYSCALL_64) /* @@ -318,6 +322,14 @@ SYM_CODE_END(ret_from_fork) #endif .endm +/* Save all registers in pt_regs */ +SYM_CODE_START_LOCAL(push_and_clear_regs) + UNWIND_HINT_FUNC + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 + RET +SYM_CODE_END(push_and_clear_regs) + /** * idtentry_body - Macro to emit code calling the C function * @cfunc: C function to be called @@ -325,7 +337,21 @@ SYM_CODE_END(ret_from_fork) */ .macro idtentry_body cfunc has_error_code:req - call error_entry + call push_and_clear_regs + UNWIND_HINT_REGS + + /* + * Call error_entry() and switch to the task stack if from userspace. + * + * When in XENPV, it is already in the task stack, and it can't fault + * for native_iret() nor native_load_gs_index() since XENPV uses its + * own pvops for IRET and load_gs_index(). And it doesn't need to + * switch the CR3. So it can skip invoking error_entry(). + */ + ALTERNATIVE "call error_entry; movq %rax, %rsp", \ + "", X86_FEATURE_XENPV + + ENCODE_FRAME_POINTER UNWIND_HINT_REGS movq %rsp, %rdi /* pt_regs pointer into 1st argument*/ @@ -337,6 +363,9 @@ SYM_CODE_END(ret_from_fork) call \cfunc + /* For some configurations \cfunc ends up being a noreturn. */ + REACHABLE + jmp error_return .endm @@ -355,6 +384,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 ENDBR ASM_CLAC + cld .if \has_error_code == 0 pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -423,6 +453,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS ENDBR ASM_CLAC + cld pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -479,6 +510,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS ENDBR ASM_CLAC + cld /* * If the entry is from userspace, switch stacks and treat it as @@ -505,6 +537,7 @@ SYM_CODE_START(\asmsym) call vc_switch_off_ist movq %rax, %rsp /* Switch to new stack */ + ENCODE_FRAME_POINTER UNWIND_HINT_REGS /* Update pt_regs */ @@ -541,6 +574,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS offset=8 ENDBR ASM_CLAC + cld /* paranoid_entry returns GS information for paranoid_exit in EBX. */ call paranoid_entry @@ -866,7 +900,6 @@ SYM_CODE_END(xen_failsafe_callback) */ SYM_CODE_START_LOCAL(paranoid_entry) UNWIND_HINT_FUNC - cld PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 @@ -980,13 +1013,10 @@ SYM_CODE_START_LOCAL(paranoid_exit) SYM_CODE_END(paranoid_exit) /* - * Save all registers in pt_regs, and switch GS if needed. + * Switch GS and CR3 if needed. */ SYM_CODE_START_LOCAL(error_entry) UNWIND_HINT_FUNC - cld - PUSH_AND_CLEAR_REGS save_ret=1 - ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -994,19 +1024,15 @@ SYM_CODE_START_LOCAL(error_entry) * We entered from user mode or we're pretending to have entered * from user mode due to an IRET fault. */ - SWAPGS + swapgs FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ .Lerror_entry_from_usermode_after_swapgs: /* Put us onto the real thread stack. */ - popq %r12 /* save return addr in %12 */ - movq %rsp, %rdi /* arg0 = pt_regs pointer */ call sync_regs - movq %rax, %rsp /* switch stack */ - ENCODE_FRAME_POINTER - pushq %r12 RET /* @@ -1030,7 +1056,7 @@ SYM_CODE_START_LOCAL(error_entry) * gsbase and proceed. We'll fix up the exception and land in * .Lgs_change's error handler with kernel gsbase. */ - SWAPGS + swapgs /* * Issue an LFENCE to prevent GS speculation, regardless of whether it is a @@ -1038,6 +1064,7 @@ SYM_CODE_START_LOCAL(error_entry) */ .Lerror_entry_done_lfence: FENCE_SWAPGS_KERNEL_ENTRY + leaq 8(%rsp), %rax /* return pt_regs pointer */ RET .Lbstep_iret: @@ -1050,7 +1077,7 @@ SYM_CODE_START_LOCAL(error_entry) * We came from an IRET to user mode, so we have user * gsbase and CR3. Switch to kernel gsbase and CR3: */ - SWAPGS + swapgs FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -1058,9 +1085,9 @@ SYM_CODE_START_LOCAL(error_entry) * Pretend that the exception came from user mode: set up pt_regs * as if we faulted immediately after IRET. */ - mov %rsp, %rdi + leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ call fixup_bad_iret - mov %rax, %rsp + mov %rax, %rdi jmp .Lerror_entry_from_usermode_after_swapgs SYM_CODE_END(error_entry) @@ -1123,6 +1150,7 @@ SYM_CODE_START(asm_exc_nmi) */ ASM_CLAC + cld /* Use %rdx as our temp variable throughout */ pushq %rdx @@ -1142,7 +1170,6 @@ SYM_CODE_START(asm_exc_nmi) */ swapgs - cld FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4fdb007cddbd..d1052742ad0c 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -50,7 +50,7 @@ SYM_CODE_START(entry_SYSENTER_compat) UNWIND_HINT_EMPTY ENDBR /* Interrupts are off on entry. */ - SWAPGS + swapgs pushq %rax SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -83,32 +83,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) movl %eax, %eax pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq $0 /* pt_regs->r8 = 0 */ - xorl %r8d, %r8d /* nospec r8 */ - pushq $0 /* pt_regs->r9 = 0 */ - xorl %r9d, %r9d /* nospec r9 */ - pushq $0 /* pt_regs->r10 = 0 */ - xorl %r10d, %r10d /* nospec r10 */ - pushq $0 /* pt_regs->r11 = 0 */ - 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 */ - xorl %r12d, %r12d /* nospec r12 */ - pushq $0 /* pt_regs->r13 = 0 */ - xorl %r13d, %r13d /* nospec r13 */ - pushq $0 /* pt_regs->r14 = 0 */ - xorl %r14d, %r14d /* nospec r14 */ - pushq $0 /* pt_regs->r15 = 0 */ - xorl %r15d, %r15d /* nospec r15 */ - + PUSH_AND_CLEAR_REGS rax=$-ENOSYS UNWIND_HINT_REGS cld @@ -225,35 +200,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL) SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) movl %eax, %eax /* discard orig_ax high bits */ pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - xorl %esi, %esi /* nospec si */ - pushq %rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ - pushq %rbp /* pt_regs->cx (stashed in bp) */ - xorl %ecx, %ecx /* nospec cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq $0 /* pt_regs->r8 = 0 */ - xorl %r8d, %r8d /* nospec r8 */ - pushq $0 /* pt_regs->r9 = 0 */ - xorl %r9d, %r9d /* nospec r9 */ - pushq $0 /* pt_regs->r10 = 0 */ - xorl %r10d, %r10d /* nospec r10 */ - pushq $0 /* pt_regs->r11 = 0 */ - 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 */ - xorl %r12d, %r12d /* nospec r12 */ - pushq $0 /* pt_regs->r13 = 0 */ - xorl %r13d, %r13d /* nospec r13 */ - pushq $0 /* pt_regs->r14 = 0 */ - xorl %r14d, %r14d /* nospec r14 */ - pushq $0 /* pt_regs->r15 = 0 */ - xorl %r15d, %r15d /* nospec r15 */ - + PUSH_AND_CLEAR_REGS rcx=%rbp rax=$-ENOSYS UNWIND_HINT_REGS movq %rsp, %rdi @@ -297,6 +244,8 @@ sysret32_from_system_call: * code. We zero R8-R10 to avoid info leaks. */ movq RSP-ORIG_RAX(%rsp), %rsp +SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL) + ANNOTATE_NOENDBR /* * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored @@ -314,6 +263,9 @@ sysret32_from_system_call: xorl %r10d, %r10d swapgs sysretl +SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) + ANNOTATE_NOENDBR + int3 SYM_CODE_END(entry_SYSCALL_compat) /* @@ -362,54 +314,25 @@ SYM_CODE_START(entry_INT80_compat) /* 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 + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* In the Xen PV case we already run on the thread stack. */ ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV - movq %rsp, %rdi + movq %rsp, %rax 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 */ - pushq (%rdi) /* pt_regs->di */ + pushq 5*8(%rax) /* regs->ss */ + pushq 4*8(%rax) /* regs->rsp */ + pushq 3*8(%rax) /* regs->eflags */ + pushq 2*8(%rax) /* regs->cs */ + pushq 1*8(%rax) /* regs->ip */ + pushq 0*8(%rax) /* regs->orig_ax */ .Lint80_keep_stack: - pushq %rsi /* pt_regs->si */ - xorl %esi, %esi /* nospec si */ - pushq %rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ - pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ - pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ - pushq %r10 /* pt_regs->r10*/ - xorl %r10d, %r10d /* nospec r10 */ - pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11 */ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx */ - pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp */ - pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12 */ - pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13 */ - pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14 */ - pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15 */ - + PUSH_AND_CLEAR_REGS rax=$-ENOSYS UNWIND_HINT_REGS cld diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e88791b420ee..fc7f458eb3de 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -302,7 +302,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE), INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), EVENT_EXTRA_END @@ -5536,7 +5536,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con /* Disabled fixed counters which are not in CPUID */ c->idxmsk64 &= intel_ctrl; - if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) + /* + * Don't extend the pseudo-encoding to the + * generic counters + */ + if (!use_fixed_pseudo_encoding(c->code)) c->idxmsk64 |= (1ULL << num_counters) - 1; } c->idxmsk64 &= @@ -6212,6 +6216,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: /* * Alder Lake has 2 types of CPU, core and atom. * diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index c6262b154c3a..48e5db21142c 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,7 +40,7 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL + * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,49 +51,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL,SPR * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL + * ICL,TGL,RKL,ADL,RPL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL + * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, + * RPL,SPR * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL,SPR * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL + * KBL,CML,ICL,TGL,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL + * TNT,RKL,ADL,RPL * Scope: Package (physical package) * */ @@ -674,12 +675,14 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates), + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index e497da9bf427..7695dcae280e 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1828,6 +1828,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index f698a55bde81..4262351f52b6 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -79,6 +79,10 @@ #define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 #define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 #define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 +#define PCI_DEVICE_ID_INTEL_RPL_1_IMC 0xA700 +#define PCI_DEVICE_ID_INTEL_RPL_2_IMC 0xA702 +#define PCI_DEVICE_ID_INTEL_RPL_3_IMC 0xA706 +#define PCI_DEVICE_ID_INTEL_RPL_4_IMC 0xA709 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -1406,6 +1410,22 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_1_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 96c775abe31f..6d759f88315c 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -103,6 +103,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h index 9aff97f0de7f..d937c55e717e 100644 --- a/arch/x86/include/asm/acenv.h +++ b/arch/x86/include/asm/acenv.h @@ -13,7 +13,19 @@ /* Asm macros */ -#define ACPI_FLUSH_CPU_CACHE() wbinvd() +/* + * ACPI_FLUSH_CPU_CACHE() flushes caches on entering sleep states. + * It is required to prevent data loss. + * + * While running inside virtual machine, the kernel can bypass cache flushing. + * Changing sleep state in a virtual machine doesn't affect the host system + * sleep state and cannot lead to data loss. + */ +#define ACPI_FLUSH_CPU_CACHE() \ +do { \ + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) \ + wbinvd(); \ +} while (0) int __acpi_acquire_global_lock(unsigned int *lock); int __acpi_release_global_lock(unsigned int *lock); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 48067af94678..bd8ae0a7010a 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -328,6 +328,8 @@ struct apic { /* wakeup_secondary_cpu */ int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); + /* wakeup secondary CPU using 64-bit wakeup point */ + int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip); void (*inquire_remote_apic)(int apicid); @@ -488,6 +490,11 @@ static inline unsigned int read_apic_id(void) return apic->get_apic_id(reg); } +#ifdef CONFIG_X86_64 +typedef int (*wakeup_cpu_handler)(int apicid, unsigned long start_eip); +extern void acpi_wake_cpu_handler_update(wakeup_cpu_handler handler); +#endif + extern int default_apic_id_valid(u32 apicid); extern int default_acpi_madt_oem_check(char *, char *); extern void default_setup_apic_routing(void); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index c878fed3056f..fbcfec4dc4cc 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -154,24 +154,24 @@ # define DEFINE_EXTABLE_TYPE_REG \ ".macro extable_type_reg type:req reg:req\n" \ - ".set found, 0\n" \ - ".set regnr, 0\n" \ + ".set .Lfound, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".set regnr, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".if (found != 1)\n" \ + ".if (.Lfound != 1)\n" \ ".error \"extable_type_reg: bad register argument\"\n" \ ".endif\n" \ ".endm\n" diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index 981fe923a59f..53e9b0620d96 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -74,6 +74,7 @@ static void sanitize_boot_params(struct boot_params *boot_params) BOOT_PARAM_PRESERVE(hdr), BOOT_PARAM_PRESERVE(e820_table), BOOT_PARAM_PRESERVE(eddbuf), + BOOT_PARAM_PRESERVE(cc_blob_address), }; memset(&scratch, 0, sizeof(scratch)); diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 4d20a293c6fd..aaf0cb0db4ae 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -78,9 +78,9 @@ do { \ */ #define __WARN_FLAGS(flags) \ do { \ - __auto_type f = BUGFLAG_WARNING|(flags); \ + __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 7516e4199b3c..20fd0acd7d80 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -28,15 +28,13 @@ typedef u16 compat_ipc_pid_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { - compat_dev_t st_dev; - u16 __pad1; + u32 st_dev; compat_ino_t st_ino; compat_mode_t st_mode; compat_nlink_t st_nlink; __compat_uid_t st_uid; __compat_gid_t st_gid; - compat_dev_t st_rdev; - u16 __pad2; + u32 st_rdev; u32 st_size; u32 st_blksize; u32 st_blocks; diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 1261842d006c..66d3e3b1d24d 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -34,14 +34,17 @@ enum cpuid_leafs CPUID_8000_001F_EAX, }; +#define X86_CAP_FMT_NUM "%d:%d" +#define x86_cap_flag_num(flag) ((flag) >> 5), ((flag) & 31) + #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; #define X86_CAP_FMT "%s" #define x86_cap_flag(flag) x86_cap_flags[flag] #else -#define X86_CAP_FMT "%d:%d" -#define x86_cap_flag(flag) ((flag) >> 5), ((flag) & 31) +#define X86_CAP_FMT X86_CAP_FMT_NUM +#define x86_cap_flag x86_cap_flag_num #endif /* diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 73e643ae94b6..20df73b51025 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -238,6 +238,7 @@ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ #define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ #define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h new file mode 100644 index 000000000000..70b2db18165e --- /dev/null +++ b/arch/x86/include/asm/cpuid.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * CPUID-related helpers/definitions + * + * Derived from arch/x86/kvm/cpuid.c + */ + +#ifndef _ASM_X86_CPUID_H +#define _ASM_X86_CPUID_H + +static __always_inline bool cpuid_function_is_indexed(u32 function) +{ + switch (function) { + case 4: + case 7: + case 0xb: + case 0xd: + case 0xf: + case 0x10: + case 0x12: + case 0x14: + case 0x17: + case 0x18: + case 0x1d: + case 0x1e: + case 0x1f: + case 0x8000001d: + return true; + } + + return false; +} + +#endif /* _ASM_X86_CPUID_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 1231d63f836d..36369e76cc63 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -10,12 +10,6 @@ * cpu_feature_enabled(). */ -#ifdef CONFIG_X86_SMAP -# define DISABLE_SMAP 0 -#else -# define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31)) -#endif - #ifdef CONFIG_X86_UMIP # define DISABLE_UMIP 0 #else @@ -68,6 +62,12 @@ # define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31)) #endif +#ifdef CONFIG_INTEL_TDX_GUEST +# define DISABLE_TDX_GUEST 0 +#else +# define DISABLE_TDX_GUEST (1 << (X86_FEATURE_TDX_GUEST & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -79,8 +79,8 @@ #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) -#define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX) +#define DISABLED_MASK8 (DISABLE_TDX_GUEST) +#define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 98938a68251c..bed74a0f2932 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -357,6 +357,11 @@ static inline u32 efi64_convert_status(efi_status_t status) runtime), \ func, __VA_ARGS__)) +#define efi_dxe_call(func, ...) \ + (efi_is_native() \ + ? efi_dxe_table->func(__VA_ARGS__) \ + : __efi64_thunk_map(efi_dxe_table, func, __VA_ARGS__)) + #else /* CONFIG_EFI_MIXED */ static inline bool efi_is_64bit(void) diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 7924f27f5c8b..72184b0b2219 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -632,6 +632,10 @@ DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback); DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER, exc_xen_unknown_trap); #endif +#ifdef CONFIG_INTEL_TDX_GUEST +DECLARE_IDTENTRY(X86_TRAP_VE, exc_virtualization_exception); +#endif + /* Device interrupts common/spurious */ DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER, common_interrupt); #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 048b6d5aff50..def6ca121111 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -26,6 +26,7 @@ * _G - parts with extra graphics on * _X - regular server parts * _D - micro server parts + * _N,_P - other mobile parts * * Historical OPTDIFFs: * @@ -107,8 +108,10 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ +#define INTEL_FAM6_ALDERLAKE_N 0xBE #define INTEL_FAM6_RAPTORLAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE_P 0xBA /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index f6d91ecb8026..1870b99c3356 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -44,6 +44,7 @@ #include <asm/page.h> #include <asm/early_ioremap.h> #include <asm/pgtable_types.h> +#include <asm/shared/io.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ @@ -210,8 +211,6 @@ void __iomem *ioremap(resource_size_t offset, unsigned long size); extern void iounmap(volatile void __iomem *addr); #define iounmap iounmap -extern void set_iounmap_nonlazy(void); - #ifdef __KERNEL__ void memcpy_fromio(void *, const volatile void __iomem *, size_t); @@ -258,37 +257,23 @@ static inline void slow_down_io(void) #endif #define BUILDIO(bwl, bw, type) \ -static inline void out##bwl(unsigned type value, int port) \ -{ \ - asm volatile("out" #bwl " %" #bw "0, %w1" \ - : : "a"(value), "Nd"(port)); \ -} \ - \ -static inline unsigned type in##bwl(int port) \ -{ \ - unsigned type value; \ - asm volatile("in" #bwl " %w1, %" #bw "0" \ - : "=a"(value) : "Nd"(port)); \ - return value; \ -} \ - \ -static inline void out##bwl##_p(unsigned type value, int port) \ +static inline void out##bwl##_p(type value, u16 port) \ { \ out##bwl(value, port); \ slow_down_io(); \ } \ \ -static inline unsigned type in##bwl##_p(int port) \ +static inline type in##bwl##_p(u16 port) \ { \ - unsigned type value = in##bwl(port); \ + type value = in##bwl(port); \ slow_down_io(); \ return value; \ } \ \ -static inline void outs##bwl(int port, const void *addr, unsigned long count) \ +static inline void outs##bwl(u16 port, const void *addr, unsigned long count) \ { \ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ - unsigned type *value = (unsigned type *)addr; \ + type *value = (type *)addr; \ while (count) { \ out##bwl(*value, port); \ value++; \ @@ -301,10 +286,10 @@ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ } \ } \ \ -static inline void ins##bwl(int port, void *addr, unsigned long count) \ +static inline void ins##bwl(u16 port, void *addr, unsigned long count) \ { \ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ - unsigned type *value = (unsigned type *)addr; \ + type *value = (type *)addr; \ while (count) { \ *value = in##bwl(port); \ value++; \ @@ -317,13 +302,11 @@ static inline void ins##bwl(int port, void *addr, unsigned long count) \ } \ } -BUILDIO(b, b, char) -BUILDIO(w, w, short) -BUILDIO(l, , int) +BUILDIO(b, b, u8) +BUILDIO(w, w, u16) +BUILDIO(l, , u32) +#undef BUILDIO -#define inb inb -#define inw inw -#define inl inl #define inb_p inb_p #define inw_p inw_p #define inl_p inl_p @@ -331,9 +314,6 @@ BUILDIO(l, , int) #define insw insw #define insl insl -#define outb outb -#define outw outw -#define outl outl #define outb_p outb_p #define outw_p outw_p #define outl_p outl_p diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 111104d1c2cd..7793e52d6237 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -137,14 +137,6 @@ static __always_inline void arch_local_irq_restore(unsigned long flags) if (!arch_irqs_disabled_flags(flags)) arch_local_irq_enable(); } -#else -#ifdef CONFIG_X86_64 -#ifdef CONFIG_XEN_PV -#define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV -#else -#define SWAPGS swapgs -#endif -#endif #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 3c368b639c04..1a6d7e3f6c32 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -118,6 +118,7 @@ KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) +KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) KVM_X86_OP(get_msr_feature) KVM_X86_OP(can_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d23e80a56eb8..4ff36610af6a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -974,12 +974,10 @@ enum hv_tsc_page_status { HV_TSC_PAGE_UNSET = 0, /* TSC page MSR was written by the guest, update pending */ HV_TSC_PAGE_GUEST_CHANGED, - /* TSC page MSR was written by KVM userspace, update pending */ + /* TSC page update was triggered from the host side */ HV_TSC_PAGE_HOST_CHANGED, /* TSC page was properly set up and is currently active */ HV_TSC_PAGE_SET, - /* TSC page is currently being updated and therefore is inactive */ - HV_TSC_PAGE_UPDATING, /* TSC page was set up with an inaccessible GPA */ HV_TSC_PAGE_BROKEN, }; @@ -1052,6 +1050,7 @@ enum kvm_apicv_inhibit { APICV_INHIBIT_REASON_X2APIC, APICV_INHIBIT_REASON_BLOCKIRQ, APICV_INHIBIT_REASON_ABSENT, + APICV_INHIBIT_REASON_SEV, }; struct kvm_arch { @@ -1485,6 +1484,7 @@ struct kvm_x86_ops { int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + void (*guest_memory_reclaimed)(struct kvm *kvm); int (*get_msr_feature)(struct kvm_msr_entry *entry); @@ -1585,8 +1585,9 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) #define kvm_arch_pmi_in_guest(vcpu) \ ((vcpu) && (vcpu)->arch.handling_intr_from_guest) -int kvm_mmu_module_init(void); -void kvm_mmu_module_exit(void); +void kvm_mmu_x86_module_init(void); +int kvm_mmu_vendor_module_init(void); +void kvm_mmu_vendor_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 56935ebb1dfe..57bc74e112f2 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -7,6 +7,8 @@ #include <linux/interrupt.h> #include <uapi/asm/kvm_para.h> +#include <asm/tdx.h> + #ifdef CONFIG_KVM_GUEST bool kvm_check_and_clear_guest_paused(void); #else @@ -32,6 +34,10 @@ static inline bool kvm_check_and_clear_guest_paused(void) static inline long kvm_hypercall0(unsigned int nr) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, 0, 0, 0, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr) @@ -42,6 +48,10 @@ static inline long kvm_hypercall0(unsigned int nr) static inline long kvm_hypercall1(unsigned int nr, unsigned long p1) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, 0, 0, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1) @@ -53,6 +63,10 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1, unsigned long p2) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, 0, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1), "c"(p2) @@ -64,6 +78,10 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1, unsigned long p2, unsigned long p3) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, p3, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1), "c"(p2), "d"(p3) @@ -76,6 +94,10 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, unsigned long p4) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, p3, p4); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index e2c6f433ed10..88ceaf3648b3 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -49,9 +49,6 @@ void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, void __init mem_encrypt_free_decrypted_mem(void); -/* Architecture __weak replacement functions */ -void __init mem_encrypt_init(void); - void __init sev_es_init_vc_handling(void); #define __bss_decrypted __section(".bss..decrypted") @@ -89,6 +86,9 @@ static inline void mem_encrypt_free_decrypted_mem(void) { } #endif /* CONFIG_AMD_MEM_ENCRYPT */ +/* Architecture __weak replacement functions */ +void __init mem_encrypt_init(void); + /* * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when * writing to or comparing values from the cr3 register. Having the diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index d6bfdfb0f0af..0c3d3440fe27 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -131,10 +131,12 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool initrd_gone; +void microcode_bsp_resume(void); #else static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void reload_early_microcode(void) { } +static inline void microcode_bsp_resume(void) { } #endif #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index b85147d75626..d71c7e8b738d 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, /* Structs and defines for the X86 specific MSI message format */ typedef struct x86_msi_data { - u32 vector : 8, - delivery_mode : 3, - dest_mode_logical : 1, - reserved : 2, - active_low : 1, - is_level : 1; - - u32 dmar_subhandle; + union { + struct { + u32 vector : 8, + delivery_mode : 3, + dest_mode_logical : 1, + reserved : 2, + active_low : 1, + is_level : 1; + }; + u32 dmar_subhandle; + }; } __attribute__ ((packed)) arch_msi_msg_data_t; #define arch_msi_msg_data x86_msi_data diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 0eb90d21049e..5555b2f9af46 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -128,9 +128,9 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ -/* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 -#define RNGDS_MITG_DIS BIT(0) +#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ +#define RTM_ALLOW BIT(1) /* TSX development mode */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 @@ -502,8 +502,10 @@ #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 #define MSR_AMD64_SEV_ES_ENABLED_BIT 1 +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index d42e6c6b47b1..65ec1965cd28 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -10,16 +10,7 @@ #include <asm/errno.h> #include <asm/cpumask.h> #include <uapi/asm/msr.h> - -struct msr { - union { - struct { - u32 l; - u32 h; - }; - u64 q; - }; -}; +#include <asm/shared/msr.h> struct msr_info { u32 msr_no; diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index a0627dfae541..1307cd689d2a 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,15 @@ struct irq_routing_table { struct irq_info slots[]; } __attribute__((packed)); +struct irt_routing_table { + u32 signature; /* IRT_SIGNATURE should be here */ + u8 size; /* Number of entries provided */ + u8 used; /* Number of entries actually used */ + u16 exclusive_irqs; /* IRQs devoted exclusively to + PCI usage */ + struct irq_info slots[]; +} __attribute__((packed)); + extern unsigned int pcibios_irq_mask; extern raw_spinlock_t pci_config_lock; diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a3c33b79fb86..13c0d63ed55e 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -38,9 +38,9 @@ #define arch_raw_cpu_ptr(ptr) \ ({ \ unsigned long tcp_ptr__; \ - asm volatile("add " __percpu_arg(1) ", %0" \ - : "=r" (tcp_ptr__) \ - : "m" (this_cpu_off), "0" (ptr)); \ + asm ("add " __percpu_arg(1) ", %0" \ + : "=r" (tcp_ptr__) \ + : "m" (this_cpu_off), "0" (ptr)); \ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) #else diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 58d9e4b1fa0a..b06e4c573add 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -241,6 +241,11 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) #define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) +static inline bool use_fixed_pseudo_encoding(u64 code) +{ + return !(code & 0xff); +} + /* * We model BTS tracing as another fixed-mode PMC. * diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 40497a9020c6..407084d9fd99 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -559,10 +559,6 @@ static inline void update_page_count(int level, unsigned long pages) { } extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); - -struct mm_struct; -extern pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, - unsigned int *level); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 80be803b96d2..12ef86b19910 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -13,6 +13,8 @@ void syscall_init(void); #ifdef CONFIG_X86_64 void entry_SYSCALL_64(void); void entry_SYSCALL_64_safe_stack(void); +void entry_SYSRETQ_unsafe_stack(void); +void entry_SYSRETQ_end(void); long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); #endif @@ -28,6 +30,8 @@ void entry_SYSENTER_compat(void); void __end_entry_SYSENTER_compat(void); void entry_SYSCALL_compat(void); void entry_SYSCALL_compat_safe_stack(void); +void entry_SYSRETL_compat_unsafe_stack(void); +void entry_SYSRETL_compat_end(void); void entry_INT80_compat(void); #ifdef CONFIG_XEN_PV void xen_entry_INT80_compat(void); @@ -35,7 +39,6 @@ void xen_entry_INT80_compat(void); #endif void x86_configure_nx(void); -void x86_report_nx(void); extern int reboot_force; diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 4357e0f2cd5f..f4db78b09c8f 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -186,9 +186,13 @@ static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs) bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); + ret = ret || (regs->ip >= (unsigned long)entry_SYSRETQ_unsafe_stack && + regs->ip < (unsigned long)entry_SYSRETQ_end); #ifdef CONFIG_IA32_EMULATION ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); + ret = ret || (regs->ip >= (unsigned long)entry_SYSRETL_compat_unsafe_stack && + regs->ip < (unsigned long)entry_SYSRETL_compat_end); #endif return ret; diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 331474b150f1..fd6f6e5b755a 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -25,6 +25,7 @@ struct real_mode_header { u32 sev_es_trampoline_start; #endif #ifdef CONFIG_X86_64 + u32 trampoline_start64; u32 trampoline_pgd; #endif /* ACPI S3 wakeup */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 896e48d45828..7590ac2570b9 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -50,7 +50,6 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); -extern unsigned long __startup_secondary_64(void); extern void startup_64_setup_env(unsigned long physbase); extern void early_setup_idt(void); extern void __init do_early_exception(struct pt_regs *regs, int trapnr); @@ -109,27 +108,19 @@ extern unsigned long _brk_end; void *extend_brk(size_t size, size_t align); /* - * Reserve space in the brk section. The name must be unique within - * the file, and somewhat descriptive. The size is in bytes. Must be - * used at file scope. + * Reserve space in the brk section. The name must be unique within the file, + * and somewhat descriptive. The size is in bytes. * - * (This uses a temp function to wrap the asm so we can pass it the - * size parameter; otherwise we wouldn't be able to. We can't use a - * "section" attribute on a normal variable because it always ends up - * being @progbits, which ends up allocating space in the vmlinux - * executable.) + * The allocation is done using inline asm (rather than using a section + * attribute on a normal variable) in order to allow the use of @nobits, so + * that it doesn't take up any space in the vmlinux file. */ -#define RESERVE_BRK(name,sz) \ - static void __section(".discard.text") __noendbr __used notrace \ - __brk_reservation_fn_##name##__(void) { \ - asm volatile ( \ - ".pushsection .brk_reservation,\"aw\",@nobits;" \ - ".brk." #name ":" \ - " 1:.skip %c0;" \ - " .size .brk." #name ", . - 1b;" \ - " .popsection" \ - : : "i" (sz)); \ - } +#define RESERVE_BRK(name, size) \ + asm(".pushsection .brk_reservation,\"aw\",@nobits\n\t" \ + ".brk." #name ":\n\t" \ + ".skip " __stringify(size) "\n\t" \ + ".size .brk." #name ", " __stringify(size) "\n\t" \ + ".popsection\n\t") extern void probe_roms(void); #ifdef __i386__ diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 1b2fd32b42fe..b8357d6ecd47 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -57,9 +57,79 @@ #define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 #define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 +/* GHCB GPA Register */ +#define GHCB_MSR_REG_GPA_REQ 0x012 +#define GHCB_MSR_REG_GPA_REQ_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)((v) & GENMASK_ULL(51, 0)) << 12) | \ + /* GHCBData[11:0] */ \ + GHCB_MSR_REG_GPA_REQ) + +#define GHCB_MSR_REG_GPA_RESP 0x013 +#define GHCB_MSR_REG_GPA_RESP_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) + +/* + * SNP Page State Change Operation + * + * GHCBData[55:52] - Page operation: + * 0x0001 Page assignment, Private + * 0x0002 Page assignment, Shared + */ +enum psc_op { + SNP_PAGE_STATE_PRIVATE = 1, + SNP_PAGE_STATE_SHARED, +}; + +#define GHCB_MSR_PSC_REQ 0x014 +#define GHCB_MSR_PSC_REQ_GFN(gfn, op) \ + /* GHCBData[55:52] */ \ + (((u64)((op) & 0xf) << 52) | \ + /* GHCBData[51:12] */ \ + ((u64)((gfn) & GENMASK_ULL(39, 0)) << 12) | \ + /* GHCBData[11:0] */ \ + GHCB_MSR_PSC_REQ) + +#define GHCB_MSR_PSC_RESP 0x015 +#define GHCB_MSR_PSC_RESP_VAL(val) \ + /* GHCBData[63:32] */ \ + (((u64)(val) & GENMASK_ULL(63, 32)) >> 32) + /* GHCB Hypervisor Feature Request/Response */ #define GHCB_MSR_HV_FT_REQ 0x080 #define GHCB_MSR_HV_FT_RESP 0x081 +#define GHCB_MSR_HV_FT_RESP_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) + +#define GHCB_HV_FT_SNP BIT_ULL(0) +#define GHCB_HV_FT_SNP_AP_CREATION BIT_ULL(1) + +/* SNP Page State Change NAE event */ +#define VMGEXIT_PSC_MAX_ENTRY 253 + +struct psc_hdr { + u16 cur_entry; + u16 end_entry; + u32 reserved; +} __packed; + +struct psc_entry { + u64 cur_page : 12, + gfn : 40, + operation : 4, + pagesize : 1, + reserved : 7; +} __packed; + +struct snp_psc_desc { + struct psc_hdr hdr; + struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY]; +} __packed; + +/* Guest message request error code */ +#define SNP_GUEST_REQ_INVALID_LEN BIT_ULL(32) #define GHCB_MSR_TERM_REQ 0x100 #define GHCB_MSR_TERM_REASON_SET_POS 12 @@ -73,8 +143,20 @@ /* GHCBData[23:16] */ \ ((((u64)reason_val) & 0xff) << 16)) +/* Error codes from reason set 0 */ +#define SEV_TERM_SET_GEN 0 #define GHCB_SEV_ES_GEN_REQ 0 #define GHCB_SEV_ES_PROT_UNSUPPORTED 1 +#define GHCB_SNP_UNSUPPORTED 2 + +/* Linux-specific reason codes (used with reason set 1) */ +#define SEV_TERM_SET_LINUX 1 +#define GHCB_TERM_REGISTER 0 /* GHCB GPA registration failure */ +#define GHCB_TERM_PSC 1 /* Page State Change failure */ +#define GHCB_TERM_PVALIDATE 2 /* Pvalidate failure */ +#define GHCB_TERM_NOT_VMPL0 3 /* SNP guest is not running at VMPL-0 */ +#define GHCB_TERM_CPUID 4 /* CPUID-validation failure */ +#define GHCB_TERM_CPUID_HV 5 /* CPUID failure during hypervisor fallback */ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index ec060c433589..19514524f0f8 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -11,9 +11,10 @@ #include <linux/types.h> #include <asm/insn.h> #include <asm/sev-common.h> +#include <asm/bootparam.h> -#define GHCB_PROTO_OUR 0x0001UL -#define GHCB_PROTOCOL_MAX 1ULL +#define GHCB_PROTOCOL_MIN 1ULL +#define GHCB_PROTOCOL_MAX 2ULL #define GHCB_DEFAULT_USAGE 0ULL #define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } @@ -42,6 +43,24 @@ struct es_em_ctxt { struct es_fault_info fi; }; +/* + * AMD SEV Confidential computing blob structure. The structure is + * defined in OVMF UEFI firmware header: + * https://github.com/tianocore/edk2/blob/master/OvmfPkg/Include/Guid/ConfidentialComputingSevSnpBlob.h + */ +#define CC_BLOB_SEV_HDR_MAGIC 0x45444d41 +struct cc_blob_sev_info { + u32 magic; + u16 version; + u16 reserved; + u64 secrets_phys; + u32 secrets_len; + u32 rsvd1; + u64 cpuid_phys; + u32 cpuid_len; + u32 rsvd2; +} __packed; + void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code); static inline u64 lower_bits(u64 val, unsigned int bits) @@ -60,6 +79,61 @@ extern void vc_no_ghcb(void); extern void vc_boot_ghcb(void); extern bool handle_vc_boot_ghcb(struct pt_regs *regs); +/* Software defined (when rFlags.CF = 1) */ +#define PVALIDATE_FAIL_NOUPDATE 255 + +/* RMP page size */ +#define RMP_PG_SIZE_4K 0 + +#define RMPADJUST_VMSA_PAGE_BIT BIT(16) + +/* SNP Guest message request */ +struct snp_req_data { + unsigned long req_gpa; + unsigned long resp_gpa; + unsigned long data_gpa; + unsigned int data_npages; +}; + +struct sev_guest_platform_data { + u64 secrets_gpa; +}; + +/* + * The secrets page contains 96-bytes of reserved field that can be used by + * the guest OS. The guest OS uses the area to save the message sequence + * number for each VMPCK. + * + * See the GHCB spec section Secret page layout for the format for this area. + */ +struct secrets_os_area { + u32 msg_seqno_0; + u32 msg_seqno_1; + u32 msg_seqno_2; + u32 msg_seqno_3; + u64 ap_jump_table_pa; + u8 rsvd[40]; + u8 guest_usage[32]; +} __packed; + +#define VMPCK_KEY_LEN 32 + +/* See the SNP spec version 0.9 for secrets page format */ +struct snp_secrets_page_layout { + u32 version; + u32 imien : 1, + rsvd1 : 31; + u32 fms; + u32 rsvd2; + u8 gosvw[16]; + u8 vmpck0[VMPCK_KEY_LEN]; + u8 vmpck1[VMPCK_KEY_LEN]; + u8 vmpck2[VMPCK_KEY_LEN]; + u8 vmpck3[VMPCK_KEY_LEN]; + struct secrets_os_area os_area; + u8 rsvd3[3840]; +} __packed; + #ifdef CONFIG_AMD_MEM_ENCRYPT extern struct static_key_false sev_es_enable_key; extern void __sev_es_ist_enter(struct pt_regs *regs); @@ -87,12 +161,71 @@ extern enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, struct es_em_ctxt *ctxt, u64 exit_code, u64 exit_info_1, u64 exit_info_2); +static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) +{ + int rc; + + /* "rmpadjust" mnemonic support in binutils 2.36 and newer */ + asm volatile(".byte 0xF3,0x0F,0x01,0xFE\n\t" + : "=a"(rc) + : "a"(vaddr), "c"(rmp_psize), "d"(attrs) + : "memory", "cc"); + + return rc; +} +static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) +{ + bool no_rmpupdate; + int rc; + + /* "pvalidate" mnemonic support in binutils 2.36 and newer */ + asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFF\n\t" + CC_SET(c) + : CC_OUT(c) (no_rmpupdate), "=a"(rc) + : "a"(vaddr), "c"(rmp_psize), "d"(validate) + : "memory", "cc"); + + if (no_rmpupdate) + return PVALIDATE_FAIL_NOUPDATE; + + return rc; +} +void setup_ghcb(void); +void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned int npages); +void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned int npages); +void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op); +void snp_set_memory_shared(unsigned long vaddr, unsigned int npages); +void snp_set_memory_private(unsigned long vaddr, unsigned int npages); +void snp_set_wakeup_secondary_cpu(void); +bool snp_init(struct boot_params *bp); +void snp_abort(void); +int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } static inline void sev_es_nmi_complete(void) { } static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; } +static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; } +static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; } +static inline void setup_ghcb(void) { } +static inline void __init +early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned int npages) { } +static inline void __init +early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned int npages) { } +static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { } +static inline void snp_set_memory_shared(unsigned long vaddr, unsigned int npages) { } +static inline void snp_set_memory_private(unsigned long vaddr, unsigned int npages) { } +static inline void snp_set_wakeup_secondary_cpu(void) { } +static inline bool snp_init(struct boot_params *bp) { return false; } +static inline void snp_abort(void) { } +static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, + unsigned long *fw_err) +{ + return -ENOTTY; +} #endif #endif diff --git a/arch/x86/include/asm/shared/io.h b/arch/x86/include/asm/shared/io.h new file mode 100644 index 000000000000..c0ef921c0586 --- /dev/null +++ b/arch/x86/include/asm/shared/io.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_IO_H +#define _ASM_X86_SHARED_IO_H + +#include <linux/types.h> + +#define BUILDIO(bwl, bw, type) \ +static inline void __out##bwl(type value, u16 port) \ +{ \ + asm volatile("out" #bwl " %" #bw "0, %w1" \ + : : "a"(value), "Nd"(port)); \ +} \ + \ +static inline type __in##bwl(u16 port) \ +{ \ + type value; \ + asm volatile("in" #bwl " %w1, %" #bw "0" \ + : "=a"(value) : "Nd"(port)); \ + return value; \ +} + +BUILDIO(b, b, u8) +BUILDIO(w, w, u16) +BUILDIO(l, , u32) +#undef BUILDIO + +#define inb __inb +#define inw __inw +#define inl __inl +#define outb __outb +#define outw __outw +#define outl __outl + +#endif diff --git a/arch/x86/include/asm/shared/msr.h b/arch/x86/include/asm/shared/msr.h new file mode 100644 index 000000000000..1e6ec10b3a15 --- /dev/null +++ b/arch/x86/include/asm/shared/msr.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_MSR_H +#define _ASM_X86_SHARED_MSR_H + +struct msr { + union { + struct { + u32 l; + u32 h; + }; + u64 q; + }; +}; + +#endif /* _ASM_X86_SHARED_MSR_H */ diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h new file mode 100644 index 000000000000..e53f26228fbb --- /dev/null +++ b/arch/x86/include/asm/shared/tdx.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_TDX_H +#define _ASM_X86_SHARED_TDX_H + +#include <linux/bits.h> +#include <linux/types.h> + +#define TDX_HYPERCALL_STANDARD 0 + +#define TDX_HCALL_HAS_OUTPUT BIT(0) +#define TDX_HCALL_ISSUE_STI BIT(1) + +#define TDX_CPUID_LEAF_ID 0x21 +#define TDX_IDENT "IntelTDX " + +#ifndef __ASSEMBLY__ + +/* + * Used in __tdx_hypercall() to pass down and get back registers' values of + * the TDCALL instruction when requesting services from the VMM. + * + * This is a software only structure and not part of the TDX module/VMM ABI. + */ +struct tdx_hypercall_args { + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; +}; + +/* Used to request services from the VMM */ +u64 __tdx_hypercall(struct tdx_hypercall_args *args, unsigned long flags); + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __tdx_hypercall_failed(void); + +#endif /* !__ASSEMBLY__ */ +#endif /* _ASM_X86_SHARED_TDX_H */ diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index d17b39893b79..bab490379c65 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -19,25 +19,14 @@ #ifdef __ASSEMBLY__ -#ifdef CONFIG_X86_SMAP - #define ASM_CLAC \ ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP #define ASM_STAC \ ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP -#else /* CONFIG_X86_SMAP */ - -#define ASM_CLAC -#define ASM_STAC - -#endif /* CONFIG_X86_SMAP */ - #else /* __ASSEMBLY__ */ -#ifdef CONFIG_X86_SMAP - static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ @@ -76,19 +65,6 @@ static __always_inline void smap_restore(unsigned long flags) #define ASM_STAC \ ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) -#else /* CONFIG_X86_SMAP */ - -static inline void clac(void) { } -static inline void stac(void) { } - -static inline unsigned long smap_save(void) { return 0; } -static inline void smap_restore(unsigned long flags) { } - -#define ASM_CLAC -#define ASM_STAC - -#endif /* CONFIG_X86_SMAP */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMAP_H */ diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index ed4f8bb6c2d9..2d8dacd02643 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -26,6 +26,7 @@ ".align 4 \n" \ ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ STATIC_CALL_TRAMP_STR(name) ": \n" \ + ANNOTATE_NOENDBR \ insns " \n" \ ".byte 0x53, 0x43, 0x54 \n" \ ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ @@ -38,6 +39,8 @@ #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) #define ARCH_ADD_TRAMP_KEY(name) \ asm(".pushsection .static_call_tramp_key, \"a\" \n" \ diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 7b132d0312eb..a800abb1a992 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -19,7 +19,6 @@ struct saved_context { u16 gs; unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; - bool misc_enable_saved; struct saved_msrs saved_msrs; struct desc_ptr gdt_desc; struct desc_ptr idt; @@ -28,6 +27,7 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + bool misc_enable_saved; } __attribute__((packed)); /* routines for saving/restoring kernel state */ diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 35bb35d28733..54df06687d83 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -14,9 +14,13 @@ * Image of the saved processor state, used by the low level ACPI suspend to * RAM code and by the low level hibernation code. * - * If you modify it, fix arch/x86/kernel/acpi/wakeup_64.S and make sure that - * __save/__restore_processor_state(), defined in arch/x86/kernel/suspend_64.c, - * still work as required. + * If you modify it, check how it is used in arch/x86/kernel/acpi/wakeup_64.S + * and make sure that __save/__restore_processor_state(), defined in + * arch/x86/power/cpu.c, still work as required. + * + * Because the structure is packed, make sure to avoid unaligned members. For + * optimisation purposes but also because tools like kmemleak only search for + * pointers that are aligned. */ struct saved_context { struct pt_regs regs; @@ -36,7 +40,6 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; - bool misc_enable_saved; struct saved_msrs saved_msrs; unsigned long efer; u16 gdt_pad; /* Unused */ @@ -48,6 +51,7 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + bool misc_enable_saved; } __attribute__((packed)); #define loaddebug(thread,register) \ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f70a5108d464..ec623e7da33d 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -271,6 +271,7 @@ struct vmcb_seg { u64 base; } __packed; +/* Save area definition for legacy and SEV-MEM guests */ struct vmcb_save_area { struct vmcb_seg es; struct vmcb_seg cs; @@ -282,12 +283,12 @@ struct vmcb_save_area { struct vmcb_seg ldtr; struct vmcb_seg idtr; struct vmcb_seg tr; - u8 reserved_1[43]; + u8 reserved_1[42]; + u8 vmpl; u8 cpl; u8 reserved_2[4]; u64 efer; - u8 reserved_3[104]; - u64 xss; /* Valid for SEV-ES only */ + u8 reserved_3[112]; u64 cr4; u64 cr3; u64 cr0; @@ -297,7 +298,9 @@ struct vmcb_save_area { u64 rip; u8 reserved_4[88]; u64 rsp; - u8 reserved_5[24]; + u64 s_cet; + u64 ssp; + u64 isst_addr; u64 rax; u64 star; u64 lstar; @@ -308,29 +311,145 @@ struct vmcb_save_area { u64 sysenter_esp; u64 sysenter_eip; u64 cr2; - u8 reserved_6[32]; + u8 reserved_5[32]; u64 g_pat; u64 dbgctl; u64 br_from; u64 br_to; u64 last_excp_from; u64 last_excp_to; - - /* - * The following part of the save area is valid only for - * SEV-ES guests when referenced through the GHCB or for - * saving to the host save area. - */ - u8 reserved_7[72]; + u8 reserved_6[72]; u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */ - u8 reserved_7b[4]; +} __packed; + +/* Save area definition for SEV-ES and SEV-SNP guests */ +struct sev_es_save_area { + struct vmcb_seg es; + struct vmcb_seg cs; + struct vmcb_seg ss; + struct vmcb_seg ds; + struct vmcb_seg fs; + struct vmcb_seg gs; + struct vmcb_seg gdtr; + struct vmcb_seg ldtr; + struct vmcb_seg idtr; + struct vmcb_seg tr; + u64 vmpl0_ssp; + u64 vmpl1_ssp; + u64 vmpl2_ssp; + u64 vmpl3_ssp; + u64 u_cet; + u8 reserved_1[2]; + u8 vmpl; + u8 cpl; + u8 reserved_2[4]; + u64 efer; + u8 reserved_3[104]; + u64 xss; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u64 dr0; + u64 dr1; + u64 dr2; + u64 dr3; + u64 dr0_addr_mask; + u64 dr1_addr_mask; + u64 dr2_addr_mask; + u64 dr3_addr_mask; + u8 reserved_4[24]; + u64 rsp; + u64 s_cet; + u64 ssp; + u64 isst_addr; + u64 rax; + u64 star; + u64 lstar; + u64 cstar; + u64 sfmask; + u64 kernel_gs_base; + u64 sysenter_cs; + u64 sysenter_esp; + u64 sysenter_eip; + u64 cr2; + u8 reserved_5[32]; + u64 g_pat; + u64 dbgctl; + u64 br_from; + u64 br_to; + u64 last_excp_from; + u64 last_excp_to; + u8 reserved_7[80]; u32 pkru; - u8 reserved_7a[20]; - u64 reserved_8; /* rax already available at 0x01f8 */ + u8 reserved_8[20]; + u64 reserved_9; /* rax already available at 0x01f8 */ + u64 rcx; + u64 rdx; + u64 rbx; + u64 reserved_10; /* rsp already available at 0x01d8 */ + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u8 reserved_11[16]; + u64 guest_exit_info_1; + u64 guest_exit_info_2; + u64 guest_exit_int_info; + u64 guest_nrip; + u64 sev_features; + u64 vintr_ctrl; + u64 guest_exit_code; + u64 virtual_tom; + u64 tlb_id; + u64 pcpu_id; + u64 event_inj; + u64 xcr0; + u8 reserved_12[16]; + + /* Floating point area */ + u64 x87_dp; + u32 mxcsr; + u16 x87_ftw; + u16 x87_fsw; + u16 x87_fcw; + u16 x87_fop; + u16 x87_ds; + u16 x87_cs; + u64 x87_rip; + u8 fpreg_x87[80]; + u8 fpreg_xmm[256]; + u8 fpreg_ymm[256]; +} __packed; + +struct ghcb_save_area { + u8 reserved_1[203]; + u8 cpl; + u8 reserved_2[116]; + u64 xss; + u8 reserved_3[24]; + u64 dr7; + u8 reserved_4[16]; + u64 rip; + u8 reserved_5[88]; + u64 rsp; + u8 reserved_6[24]; + u64 rax; + u8 reserved_7[264]; u64 rcx; u64 rdx; u64 rbx; - u64 reserved_9; /* rsp already available at 0x01d8 */ + u8 reserved_8[8]; u64 rbp; u64 rsi; u64 rdi; @@ -342,22 +461,24 @@ struct vmcb_save_area { u64 r13; u64 r14; u64 r15; - u8 reserved_10[16]; + u8 reserved_9[16]; u64 sw_exit_code; u64 sw_exit_info_1; u64 sw_exit_info_2; u64 sw_scratch; - u8 reserved_11[56]; + u8 reserved_10[56]; u64 xcr0; u8 valid_bitmap[16]; u64 x87_state_gpa; } __packed; +#define GHCB_SHARED_BUF_SIZE 2032 + struct ghcb { - struct vmcb_save_area save; - u8 reserved_save[2048 - sizeof(struct vmcb_save_area)]; + struct ghcb_save_area save; + u8 reserved_save[2048 - sizeof(struct ghcb_save_area)]; - u8 shared_buffer[2032]; + u8 shared_buffer[GHCB_SHARED_BUF_SIZE]; u8 reserved_1[10]; u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ @@ -365,13 +486,17 @@ struct ghcb { } __packed; -#define EXPECTED_VMCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_VMCB_SAVE_AREA_SIZE 740 +#define EXPECTED_GHCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_SEV_ES_SAVE_AREA_SIZE 1648 #define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024 #define EXPECTED_GHCB_SIZE PAGE_SIZE static inline void __unused_size_checks(void) { BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct ghcb_save_area) != EXPECTED_GHCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); } @@ -441,7 +566,7 @@ struct vmcb { /* GHCB Accessor functions */ #define GHCB_BITMAP_IDX(field) \ - (offsetof(struct vmcb_save_area, field) / sizeof(u64)) + (offsetof(struct ghcb_save_area, field) / sizeof(u64)) #define DEFINE_GHCB_ACCESSORS(field) \ static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \ diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h new file mode 100644 index 000000000000..020c81a7c729 --- /dev/null +++ b/arch/x86/include/asm/tdx.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021-2022 Intel Corporation */ +#ifndef _ASM_X86_TDX_H +#define _ASM_X86_TDX_H + +#include <linux/init.h> +#include <linux/bits.h> +#include <asm/ptrace.h> +#include <asm/shared/tdx.h> + +/* + * SW-defined error codes. + * + * Bits 47:40 == 0xFF indicate Reserved status code class that never used by + * TDX module. + */ +#define TDX_ERROR _BITUL(63) +#define TDX_SW_ERROR (TDX_ERROR | GENMASK_ULL(47, 40)) +#define TDX_SEAMCALL_VMFAILINVALID (TDX_SW_ERROR | _UL(0xFFFF0000)) + +#ifndef __ASSEMBLY__ + +/* + * Used to gather the output registers values of the TDCALL and SEAMCALL + * instructions when requesting services from the TDX module. + * + * This is a software only structure and not part of the TDX module/VMM ABI. + */ +struct tdx_module_output { + u64 rcx; + u64 rdx; + u64 r8; + u64 r9; + u64 r10; + u64 r11; +}; + +/* + * Used by the #VE exception handler to gather the #VE exception + * info from the TDX module. This is a software only structure + * and not part of the TDX module/VMM ABI. + */ +struct ve_info { + u64 exit_reason; + u64 exit_qual; + /* Guest Linear (virtual) Address */ + u64 gla; + /* Guest Physical Address */ + u64 gpa; + u32 instr_len; + u32 instr_info; +}; + +#ifdef CONFIG_INTEL_TDX_GUEST + +void __init tdx_early_init(void); + +/* Used to communicate with the TDX module */ +u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, + struct tdx_module_output *out); + +void tdx_get_ve_info(struct ve_info *ve); + +bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve); + +void tdx_safe_halt(void); + +bool tdx_early_handle_ve(struct pt_regs *regs); + +#else + +static inline void tdx_early_init(void) { }; +static inline void tdx_safe_halt(void) { }; + +static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; } + +#endif /* CONFIG_INTEL_TDX_GUEST */ + +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_INTEL_TDX_GUEST) +long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2, + unsigned long p3, unsigned long p4); +#else +static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4) +{ + return -ENODEV; +} +#endif /* CONFIG_INTEL_TDX_GUEST && CONFIG_KVM_GUEST */ +#endif /* !__ASSEMBLY__ */ +#endif /* _ASM_X86_TDX_H */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 35317c5c551d..47ecfff2c83d 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -13,7 +13,7 @@ #ifdef CONFIG_X86_64 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); asmlinkage __visible notrace -struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); +struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs); void __init trap_init(void); asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); #endif diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index b25d3f82c2f3..bea5cdcdf532 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -10,6 +10,7 @@ #define SETUP_EFI 4 #define SETUP_APPLE_PROPERTIES 5 #define SETUP_JAILHOUSE 6 +#define SETUP_CC_BLOB 7 #define SETUP_INDIRECT (1<<31) @@ -187,7 +188,8 @@ struct boot_params { __u32 ext_ramdisk_image; /* 0x0c0 */ __u32 ext_ramdisk_size; /* 0x0c4 */ __u32 ext_cmd_line_ptr; /* 0x0c8 */ - __u8 _pad4[116]; /* 0x0cc */ + __u8 _pad4[112]; /* 0x0cc */ + __u32 cc_blob_address; /* 0x13c */ struct edid_info edid_info; /* 0x140 */ struct efi_info efi_info; /* 0x1c0 */ __u32 alt_mem_k; /* 0x1e0 */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index efa969325ede..f69c168391aa 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -108,6 +108,14 @@ #define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 +#define SVM_VMGEXIT_PSC 0x80000010 +#define SVM_VMGEXIT_GUEST_REQUEST 0x80000011 +#define SVM_VMGEXIT_EXT_GUEST_REQUEST 0x80000012 +#define SVM_VMGEXIT_AP_CREATION 0x80000013 +#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0 +#define SVM_VMGEXIT_AP_CREATE 1 +#define SVM_VMGEXIT_AP_DESTROY 2 +#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ @@ -218,6 +226,11 @@ { SVM_VMGEXIT_NMI_COMPLETE, "vmgexit_nmi_complete" }, \ { SVM_VMGEXIT_AP_HLT_LOOP, "vmgexit_ap_hlt_loop" }, \ { SVM_VMGEXIT_AP_JUMP_TABLE, "vmgexit_ap_jump_table" }, \ + { SVM_VMGEXIT_PSC, "vmgexit_page_state_change" }, \ + { SVM_VMGEXIT_GUEST_REQUEST, "vmgexit_guest_request" }, \ + { SVM_VMGEXIT_EXT_GUEST_REQUEST, "vmgexit_ext_guest_request" }, \ + { SVM_VMGEXIT_AP_CREATION, "vmgexit_ap_creation" }, \ + { SVM_VMGEXIT_HV_FEATURES, "vmgexit_hypervisor_feature" }, \ { SVM_EXIT_ERR, "invalid_guest_state" } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index c41ef42adbe8..1a2dc328cb5e 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -46,8 +46,6 @@ endif # non-deterministic coverage. KCOV_INSTRUMENT := n -CFLAGS_head$(BITS).o += -fno-stack-protector - CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 0d01e7f5078c..6d2c50819501 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -65,6 +65,13 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; static bool acpi_support_online_capable; #endif +#ifdef CONFIG_X86_64 +/* Physical address of the Multiprocessor Wakeup Structure mailbox */ +static u64 acpi_mp_wake_mailbox_paddr; +/* Virtual address of the Multiprocessor Wakeup Structure mailbox */ +static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox; +#endif + #ifdef CONFIG_X86_IO_APIC /* * Locks related to IOAPIC hotplug @@ -336,7 +343,60 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e return 0; } -#endif /*CONFIG_X86_LOCAL_APIC */ +#ifdef CONFIG_X86_64 +static int acpi_wakeup_cpu(int apicid, unsigned long start_ip) +{ + /* + * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). + * + * Wakeup of secondary CPUs is fully serialized in the core code. + * No need to protect acpi_mp_wake_mailbox from concurrent accesses. + */ + if (!acpi_mp_wake_mailbox) { + acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr, + sizeof(*acpi_mp_wake_mailbox), + MEMREMAP_WB); + } + + /* + * Mailbox memory is shared between the firmware and OS. Firmware will + * listen on mailbox command address, and once it receives the wakeup + * command, the CPU associated with the given apicid will be booted. + * + * The value of 'apic_id' and 'wakeup_vector' must be visible to the + * firmware before the wakeup command is visible. smp_store_release() + * ensures ordering and visibility. + */ + acpi_mp_wake_mailbox->apic_id = apicid; + acpi_mp_wake_mailbox->wakeup_vector = start_ip; + smp_store_release(&acpi_mp_wake_mailbox->command, + ACPI_MP_WAKE_COMMAND_WAKEUP); + + /* + * Wait for the CPU to wake up. + * + * The CPU being woken up is essentially in a spin loop waiting to be + * woken up. It should not take long for it wake up and acknowledge by + * zeroing out ->command. + * + * ACPI specification doesn't provide any guidance on how long kernel + * has to wait for a wake up acknowledgement. It also doesn't provide + * a way to cancel a wake up request if it takes too long. + * + * In TDX environment, the VMM has control over how long it takes to + * wake up secondary. It can postpone scheduling secondary vCPU + * indefinitely. Giving up on wake up request and reporting error opens + * possible attack vector for VMM: it can wake up a secondary CPU when + * kernel doesn't expect it. Wait until positive result of the wake up + * request. + */ + while (READ_ONCE(acpi_mp_wake_mailbox->command)) + cpu_relax(); + + return 0; +} +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC #define MP_ISA_BUS 0 @@ -1083,6 +1143,29 @@ static int __init acpi_parse_madt_lapic_entries(void) } return 0; } + +#ifdef CONFIG_X86_64 +static int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_multiproc_wakeup *mp_wake; + + if (!IS_ENABLED(CONFIG_SMP)) + return -ENODEV; + + mp_wake = (struct acpi_madt_multiproc_wakeup *)header; + if (BAD_MADT_ENTRY(mp_wake, end)) + return -EINVAL; + + acpi_table_print_madt_entry(&header->common); + + acpi_mp_wake_mailbox_paddr = mp_wake->base_address; + + acpi_wake_cpu_handler_update(acpi_wakeup_cpu); + + return 0; +} +#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -1278,6 +1361,14 @@ static void __init acpi_process_madt(void) smp_found_config = 1; } + +#ifdef CONFIG_X86_64 + /* + * Parse MADT MP Wake entry. + */ + acpi_table_parse_madt(ACPI_MADT_TYPE_MULTIPROC_WAKEUP, + acpi_parse_mp_wake, 1); +#endif } if (error == -EINVAL) { /* diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b70344bf6600..3c8f2c797a98 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2551,6 +2551,16 @@ u32 x86_msi_msg_get_destid(struct msi_msg *msg, bool extid) } EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid); +#ifdef CONFIG_X86_64 +void __init acpi_wake_cpu_handler_update(wakeup_cpu_handler handler) +{ + struct apic **drv; + + for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) + (*drv)->wakeup_secondary_cpu_64 = handler; +} +#endif + /* * Override the generic EOI implementation with an optimized version. * Only called during early boot when only one CPU is active and with diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c1bb384935b0..a868b76cd3d4 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -65,6 +65,7 @@ #include <asm/irq_remapping.h> #include <asm/hw_irq.h> #include <asm/apic.h> +#include <asm/pgtable.h> #define for_each_ioapic(idx) \ for ((idx) = 0; (idx) < nr_ioapics; (idx)++) @@ -2677,6 +2678,19 @@ static struct resource * __init ioapic_setup_resources(void) return res; } +static void io_apic_set_fixmap(enum fixed_addresses idx, phys_addr_t phys) +{ + pgprot_t flags = FIXMAP_PAGE_NOCACHE; + + /* + * Ensure fixmaps for IOAPIC MMIO respect memory encryption pgprot + * bits, just like normal ioremap(): + */ + flags = pgprot_decrypted(flags); + + __set_fixmap(idx, phys, flags); +} + void __init io_apic_init_mappings(void) { unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; @@ -2709,7 +2723,7 @@ fake_ioapic_page: __func__, PAGE_SIZE, PAGE_SIZE); ioapic_phys = __pa(ioapic_phys); } - set_fixmap_nocache(idx, ioapic_phys); + io_apic_set_fixmap(idx, ioapic_phys); apic_printk(APIC_VERBOSE, "mapped IOAPIC to %08lx (%08lx)\n", __fix_to_virt(idx) + (ioapic_phys & ~PAGE_MASK), ioapic_phys); @@ -2838,7 +2852,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base, ioapics[idx].mp_config.flags = MPC_APIC_USABLE; ioapics[idx].mp_config.apicaddr = address; - set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); + io_apic_set_fixmap(FIX_IO_APIC_BASE_0 + idx, address); if (bad_ioapic_register(idx)) { clear_fixmap(FIX_IO_APIC_BASE_0 + idx); return -ENODEV; diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 9fb0a2f8b62a..437308004ef2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -18,6 +18,7 @@ #include <asm/bootparam.h> #include <asm/suspend.h> #include <asm/tlbflush.h> +#include <asm/tdx.h> #ifdef CONFIG_XEN #include <xen/interface/xen.h> @@ -66,6 +67,22 @@ static void __used common(void) #endif BLANK(); + OFFSET(TDX_MODULE_rcx, tdx_module_output, rcx); + OFFSET(TDX_MODULE_rdx, tdx_module_output, rdx); + OFFSET(TDX_MODULE_r8, tdx_module_output, r8); + OFFSET(TDX_MODULE_r9, tdx_module_output, r9); + OFFSET(TDX_MODULE_r10, tdx_module_output, r10); + OFFSET(TDX_MODULE_r11, tdx_module_output, r11); + + BLANK(); + OFFSET(TDX_HYPERCALL_r10, tdx_hypercall_args, r10); + OFFSET(TDX_HYPERCALL_r11, tdx_hypercall_args, r11); + OFFSET(TDX_HYPERCALL_r12, tdx_hypercall_args, r12); + OFFSET(TDX_HYPERCALL_r13, tdx_hypercall_args, r13); + OFFSET(TDX_HYPERCALL_r14, tdx_hypercall_args, r14); + OFFSET(TDX_HYPERCALL_r15, tdx_hypercall_args, r15); + + BLANK(); OFFSET(BP_scratch, boot_params, scratch); OFFSET(BP_secure_boot, boot_params, secure_boot); OFFSET(BP_loadflags, boot_params, hdr.loadflags); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 6296e1ebed1d..d879a6c93609 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -446,6 +446,13 @@ void update_srbds_msr(void) if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED) return; + /* + * A MDS_NO CPU for which SRBDS mitigation is not needed due to TSX + * being disabled and it hasn't received the SRBDS MSR microcode. + */ + if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) + return; + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); switch (srbds_mitigation) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ed4417500700..2e9142797c99 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -60,6 +60,7 @@ #include <asm/uv/uv.h> #include <asm/sigframe.h> #include <asm/traps.h> +#include <asm/sev.h> #include "cpu.h" @@ -298,13 +299,6 @@ static int __init cachesize_setup(char *str) } __setup("cachesize=", cachesize_setup); -static int __init x86_sep_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_SEP); - return 1; -} -__setup("nosep", x86_sep_setup); - /* Standard macro to see if a specific flag is changeable */ static inline int flag_is_changeable_p(u32 flag) { @@ -376,26 +370,12 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) } #endif -static __init int setup_disable_smep(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_SMEP); - return 1; -} -__setup("nosmep", setup_disable_smep); - static __always_inline void setup_smep(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_SMEP)) cr4_set_bits(X86_CR4_SMEP); } -static __init int setup_disable_smap(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_SMAP); - return 1; -} -__setup("nosmap", setup_disable_smap); - static __always_inline void setup_smap(struct cpuinfo_x86 *c) { unsigned long eflags = native_save_fl(); @@ -403,14 +383,8 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) /* This should have been cleared long ago */ BUG_ON(eflags & X86_EFLAGS_AC); - if (cpu_has(c, X86_FEATURE_SMAP)) { -#ifdef CONFIG_X86_SMAP + if (cpu_has(c, X86_FEATURE_SMAP)) cr4_set_bits(X86_CR4_SMAP); -#else - clear_cpu_cap(c, X86_FEATURE_SMAP); - cr4_clear_bits(X86_CR4_SMAP); -#endif - } } static __always_inline void setup_umip(struct cpuinfo_x86 *c) @@ -1368,8 +1342,8 @@ static void detect_nopl(void) static void __init cpu_parse_early_param(void) { char arg[128]; - char *argptr = arg; - int arglen, res, bit; + char *argptr = arg, *opt; + int arglen, taint = 0; #ifdef CONFIG_X86_32 if (cmdline_find_option_bool(boot_command_line, "no387")) @@ -1397,21 +1371,61 @@ static void __init cpu_parse_early_param(void) return; pr_info("Clearing CPUID bits:"); - do { - res = get_option(&argptr, &bit); - if (res == 0 || res == 3) - break; - /* If the argument was too long, the last bit may be cut off */ - if (res == 1 && arglen >= sizeof(arg)) - break; + while (argptr) { + bool found __maybe_unused = false; + unsigned int bit; - if (bit >= 0 && bit < NCAPINTS * 32) { - pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + opt = strsep(&argptr, ","); + + /* + * Handle naked numbers first for feature flags which don't + * have names. + */ + if (!kstrtouint(opt, 10, &bit)) { + if (bit < NCAPINTS * 32) { + +#ifdef CONFIG_X86_FEATURE_NAMES + /* empty-string, i.e., ""-defined feature flags */ + if (!x86_cap_flags[bit]) + pr_cont(" " X86_CAP_FMT_NUM, x86_cap_flag_num(bit)); + else +#endif + pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + + setup_clear_cpu_cap(bit); + taint++; + } + /* + * The assumption is that there are no feature names with only + * numbers in the name thus go to the next argument. + */ + continue; + } + +#ifdef CONFIG_X86_FEATURE_NAMES + for (bit = 0; bit < 32 * NCAPINTS; bit++) { + if (!x86_cap_flag(bit)) + continue; + + if (strcmp(x86_cap_flag(bit), opt)) + continue; + + pr_cont(" %s", opt); setup_clear_cpu_cap(bit); + taint++; + found = true; + break; } - } while (res == 2); + + if (!found) + pr_cont(" (unknown: %s)", opt); +#endif + } pr_cont("\n"); + + if (taint) + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); } /* @@ -1855,15 +1869,9 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); -} -static __init int setup_noclflush(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_CLFLUSH); - setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT); - return 1; + tsx_ap_init(); } -__setup("noclflush", setup_noclflush); void print_cpu_info(struct cpuinfo_x86 *c) { @@ -2124,6 +2132,9 @@ void cpu_init_exception_handling(void) load_TR_desc(); + /* GHCB needs to be setup to handle #VC. */ + setup_ghcb(); + /* Finally load the IDT */ load_current_idt(); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index ee6f23f7587d..2a8e584fc991 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -55,11 +55,10 @@ enum tsx_ctrl_states { extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; extern void __init tsx_init(void); -extern void tsx_enable(void); -extern void tsx_disable(void); -extern void tsx_clear_cpuid(void); +void tsx_ap_init(void); #else static inline void tsx_init(void) { } +static inline void tsx_ap_init(void) { } #endif /* CONFIG_CPU_SUP_INTEL */ extern void get_cpu_cap(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 8321c43554a1..f7a5370a9b3b 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -717,13 +717,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_misc_features(c); - if (tsx_ctrl_state == TSX_CTRL_ENABLE) - tsx_enable(); - else if (tsx_ctrl_state == TSX_CTRL_DISABLE) - tsx_disable(); - else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT) - tsx_clear_cpuid(); - split_lock_init(); bus_lock_init(); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 1940d305db1c..1c87501e0fa3 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1294,10 +1294,23 @@ out_free: kfree(bank); } +static void __threshold_remove_device(struct threshold_bank **bp) +{ + unsigned int bank, numbanks = this_cpu_read(mce_num_banks); + + for (bank = 0; bank < numbanks; bank++) { + if (!bp[bank]) + continue; + + threshold_remove_bank(bp[bank]); + bp[bank] = NULL; + } + kfree(bp); +} + int mce_threshold_remove_device(unsigned int cpu) { struct threshold_bank **bp = this_cpu_read(threshold_banks); - unsigned int bank, numbanks = this_cpu_read(mce_num_banks); if (!bp) return 0; @@ -1308,13 +1321,7 @@ int mce_threshold_remove_device(unsigned int cpu) */ this_cpu_write(threshold_banks, NULL); - for (bank = 0; bank < numbanks; bank++) { - if (bp[bank]) { - threshold_remove_bank(bp[bank]); - bp[bank] = NULL; - } - } - kfree(bp); + __threshold_remove_device(bp); return 0; } @@ -1351,15 +1358,14 @@ int mce_threshold_create_device(unsigned int cpu) if (!(this_cpu_read(bank_map) & (1 << bank))) continue; err = threshold_create_bank(bp, cpu, bank); - if (err) - goto out_err; + if (err) { + __threshold_remove_device(bp); + return err; + } } this_cpu_write(threshold_banks, bp); if (thresholding_irq_en) mce_threshold_vector = amd_threshold_interrupt; return 0; -out_err: - mce_threshold_remove_device(cpu); - return err; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 981496e6bc0e..d775fcd74e98 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -69,7 +69,9 @@ DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks); struct mce_bank { u64 ctl; /* subevents to enable */ - bool init; /* initialise bank? */ + + __u64 init : 1, /* initialise bank? */ + __reserved_1 : 63; }; static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 1add86935349..00483d1c27e4 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -301,85 +301,65 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) } } -static __always_inline int mce_severity_amd_smca(struct mce *m, enum context err_ctx) +/* See AMD PPR(s) section Machine Check Error Handling. */ +static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) { - u64 mcx_cfg; + char *panic_msg = NULL; + int ret; /* - * We need to look at the following bits: - * - "succor" bit (data poisoning support), and - * - TCC bit (Task Context Corrupt) - * in MCi_STATUS to determine error severity. + * Default return value: Action required, the error must be handled + * immediately. */ - if (!mce_flags.succor) - return MCE_PANIC_SEVERITY; - - mcx_cfg = mce_rdmsrl(MSR_AMD64_SMCA_MCx_CONFIG(m->bank)); - - /* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */ - if ((mcx_cfg & MCI_CONFIG_MCAX) && - (m->status & MCI_STATUS_TCC) && - (err_ctx == IN_KERNEL)) - return MCE_PANIC_SEVERITY; - - /* ...otherwise invoke hwpoison handler. */ - return MCE_AR_SEVERITY; -} - -/* - * See AMD Error Scope Hierarchy table in a newer BKDG. For example - * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" - */ -static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) -{ - enum context ctx = error_context(m, regs); + ret = MCE_AR_SEVERITY; /* Processor Context Corrupt, no need to fumble too much, die! */ - if (m->status & MCI_STATUS_PCC) - return MCE_PANIC_SEVERITY; - - if (m->status & MCI_STATUS_UC) { - - if (ctx == IN_KERNEL) - return MCE_PANIC_SEVERITY; + if (m->status & MCI_STATUS_PCC) { + panic_msg = "Processor Context Corrupt"; + ret = MCE_PANIC_SEVERITY; + goto out; + } - /* - * On older systems where overflow_recov flag is not present, we - * should simply panic if an error overflow occurs. If - * overflow_recov flag is present and set, then software can try - * to at least kill process to prolong system operation. - */ - if (mce_flags.overflow_recov) { - if (mce_flags.smca) - return mce_severity_amd_smca(m, ctx); - - /* kill current process */ - return MCE_AR_SEVERITY; - } else { - /* at least one error was not logged */ - if (m->status & MCI_STATUS_OVER) - return MCE_PANIC_SEVERITY; - } - - /* - * For any other case, return MCE_UC_SEVERITY so that we log the - * error and exit #MC handler. - */ - return MCE_UC_SEVERITY; + if (m->status & MCI_STATUS_DEFERRED) { + ret = MCE_DEFERRED_SEVERITY; + goto out; } /* - * deferred error: poll handler catches these and adds to mce_ring so - * memory-failure can take recovery actions. + * If the UC bit is not set, the system either corrected or deferred + * the error. No action will be required after logging the error. */ - if (m->status & MCI_STATUS_DEFERRED) - return MCE_DEFERRED_SEVERITY; + if (!(m->status & MCI_STATUS_UC)) { + ret = MCE_KEEP_SEVERITY; + goto out; + } /* - * corrected error: poll handler catches these and passes responsibility - * of decoding the error to EDAC + * On MCA overflow, without the MCA overflow recovery feature the + * system will not be able to recover, panic. */ - return MCE_KEEP_SEVERITY; + if ((m->status & MCI_STATUS_OVER) && !mce_flags.overflow_recov) { + panic_msg = "Overflowed uncorrected error without MCA Overflow Recovery"; + ret = MCE_PANIC_SEVERITY; + goto out; + } + + if (!mce_flags.succor) { + panic_msg = "Uncorrected error without MCA Recovery"; + ret = MCE_PANIC_SEVERITY; + goto out; + } + + if (error_context(m, regs) == IN_KERNEL) { + panic_msg = "Uncorrected unrecoverable error in kernel context"; + ret = MCE_PANIC_SEVERITY; + } + +out: + if (msg && panic_msg) + *msg = panic_msg; + + return ret; } static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index f955d25076ba..239ff5fcec6a 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -758,9 +758,9 @@ static struct subsys_interface mc_cpu_interface = { }; /** - * mc_bp_resume - Update boot CPU microcode during resume. + * microcode_bsp_resume - Update boot CPU microcode during resume. */ -static void mc_bp_resume(void) +void microcode_bsp_resume(void) { int cpu = smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; @@ -772,7 +772,7 @@ static void mc_bp_resume(void) } static struct syscore_ops mc_syscore_ops = { - .resume = mc_bp_resume, + .resume = microcode_bsp_resume, }; static int mc_cpu_starting(unsigned int cpu) diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index 9c7a5f049292..ec7bbac3a9f2 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -19,7 +19,7 @@ enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; -void tsx_disable(void) +static void tsx_disable(void) { u64 tsx; @@ -39,7 +39,7 @@ void tsx_disable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -void tsx_enable(void) +static void tsx_enable(void) { u64 tsx; @@ -58,7 +58,7 @@ void tsx_enable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -static bool __init tsx_ctrl_is_supported(void) +static bool tsx_ctrl_is_supported(void) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -84,7 +84,45 @@ static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) return TSX_CTRL_ENABLE; } -void tsx_clear_cpuid(void) +/* + * Disabling TSX is not a trivial business. + * + * First of all, there's a CPUID bit: X86_FEATURE_RTM_ALWAYS_ABORT + * which says that TSX is practically disabled (all transactions are + * aborted by default). When that bit is set, the kernel unconditionally + * disables TSX. + * + * In order to do that, however, it needs to dance a bit: + * + * 1. The first method to disable it is through MSR_TSX_FORCE_ABORT and + * the MSR is present only when *two* CPUID bits are set: + * + * - X86_FEATURE_RTM_ALWAYS_ABORT + * - X86_FEATURE_TSX_FORCE_ABORT + * + * 2. The second method is for CPUs which do not have the above-mentioned + * MSR: those use a different MSR - MSR_IA32_TSX_CTRL and disable TSX + * through that one. Those CPUs can also have the initially mentioned + * CPUID bit X86_FEATURE_RTM_ALWAYS_ABORT set and for those the same strategy + * applies: TSX gets disabled unconditionally. + * + * When either of the two methods are present, the kernel disables TSX and + * clears the respective RTM and HLE feature flags. + * + * An additional twist in the whole thing presents late microcode loading + * which, when done, may cause for the X86_FEATURE_RTM_ALWAYS_ABORT CPUID + * bit to be set after the update. + * + * A subsequent hotplug operation on any logical CPU except the BSP will + * cause for the supported CPUID feature bits to get re-detected and, if + * RTM and HLE get cleared all of a sudden, but, userspace did consult + * them before the update, then funny explosions will happen. Long story + * short: the kernel doesn't modify CPUID feature bits after booting. + * + * That's why, this function's call in init_intel() doesn't clear the + * feature flags. + */ +static void tsx_clear_cpuid(void) { u64 msr; @@ -97,6 +135,39 @@ void tsx_clear_cpuid(void) rdmsrl(MSR_TSX_FORCE_ABORT, msr); msr |= MSR_TFA_TSX_CPUID_CLEAR; wrmsrl(MSR_TSX_FORCE_ABORT, msr); + } else if (tsx_ctrl_is_supported()) { + rdmsrl(MSR_IA32_TSX_CTRL, msr); + msr |= TSX_CTRL_CPUID_CLEAR; + wrmsrl(MSR_IA32_TSX_CTRL, msr); + } +} + +/* + * Disable TSX development mode + * + * When the microcode released in Feb 2022 is applied, TSX will be disabled by + * default on some processors. MSR 0x122 (TSX_CTRL) and MSR 0x123 + * (IA32_MCU_OPT_CTRL) can be used to re-enable TSX for development, doing so is + * not recommended for production deployments. In particular, applying MD_CLEAR + * flows for mitigation of the Intel TSX Asynchronous Abort (TAA) transient + * execution attack may not be effective on these processors when Intel TSX is + * enabled with updated microcode. + */ +static void tsx_dev_mode_disable(void) +{ + u64 mcu_opt_ctrl; + + /* Check if RTM_ALLOW exists */ + if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() || + !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL)) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl); + + if (mcu_opt_ctrl & RTM_ALLOW) { + mcu_opt_ctrl &= ~RTM_ALLOW; + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl); + setup_force_cpu_cap(X86_FEATURE_RTM_ALWAYS_ABORT); } } @@ -105,14 +176,14 @@ void __init tsx_init(void) char arg[5] = {}; int ret; + tsx_dev_mode_disable(); + /* - * Hardware will always abort a TSX transaction if both CPUID bits - * RTM_ALWAYS_ABORT and TSX_FORCE_ABORT are set. In this case, it is - * better not to enumerate CPUID.RTM and CPUID.HLE bits. Clear them - * here. + * Hardware will always abort a TSX transaction when the CPUID bit + * RTM_ALWAYS_ABORT is set. In this case, it is better not to enumerate + * CPUID.RTM and CPUID.HLE bits. Clear them here. */ - if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT) && - boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) { + if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT)) { tsx_ctrl_state = TSX_CTRL_RTM_ALWAYS_ABORT; tsx_clear_cpuid(); setup_clear_cpu_cap(X86_FEATURE_RTM); @@ -175,3 +246,16 @@ void __init tsx_init(void) setup_force_cpu_cap(X86_FEATURE_HLE); } } + +void tsx_ap_init(void) +{ + tsx_dev_mode_disable(); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + else if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); + else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT) + /* See comment over that function for more details. */ + tsx_clear_cpuid(); +} diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index a7f617a3981d..97529552dd24 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -37,7 +37,6 @@ static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, } else memcpy(buf, vaddr + offset, csize); - set_iounmap_nonlazy(); iounmap((void __iomem *)vaddr); return csize; } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index c049561f373a..e28ab0ecc537 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -41,17 +41,7 @@ struct fpu_state_config fpu_user_cfg __ro_after_init; */ struct fpstate init_fpstate __ro_after_init; -/* - * Track whether the kernel is using the FPU state - * currently. - * - * This flag is used: - * - * - by IRQ context code to potentially use the FPU - * if it's unused. - * - * - to debug kernel_fpu_begin()/end() correctness - */ +/* Track in-kernel FPU usage */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* @@ -59,42 +49,37 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu); */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); -static bool kernel_fpu_disabled(void) -{ - return this_cpu_read(in_kernel_fpu); -} - -static bool interrupted_kernel_fpu_idle(void) -{ - return !kernel_fpu_disabled(); -} - -/* - * Were we in user mode (or vm86 mode) when we were - * interrupted? - * - * Doing kernel_fpu_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - return regs && user_mode(regs); -} - /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. */ bool irq_fpu_usable(void) { - return !in_interrupt() || - interrupted_user_mode() || - interrupted_kernel_fpu_idle(); + if (WARN_ON_ONCE(in_nmi())) + return false; + + /* In kernel FPU usage already active? */ + if (this_cpu_read(in_kernel_fpu)) + return false; + + /* + * When not in NMI or hard interrupt context, FPU can be used in: + * + * - Task context except from within fpregs_lock()'ed critical + * regions. + * + * - Soft interrupt processing context which cannot happen + * while in a fpregs_lock()'ed critical region. + */ + if (!in_hardirq()) + return true; + + /* + * In hard interrupt context it's safe when soft interrupts + * are enabled, which means the interrupt did not hit in + * a fpregs_lock()'ed critical region. + */ + return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 4f5ecbbaae77..bd4a34100ed0 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -40,6 +40,7 @@ #include <asm/extable.h> #include <asm/trapnr.h> #include <asm/sev.h> +#include <asm/tdx.h> /* * Manage page tables very early on. @@ -143,7 +144,20 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv if (sme_get_me_mask()) { vaddr = (unsigned long)__start_bss_decrypted; vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + /* + * On SNP, transition the page to shared in the RMP table so that + * it is consistent with the page table attribute change. + * + * __start_bss_decrypted has a virtual address in the high range + * mapping (kernel .text). PVALIDATE, by way of + * early_snp_set_memory_shared(), requires a valid virtual + * address but the kernel is currently running off of the identity + * mapping so use __pa() to get a *currently* valid virtual address. + */ + early_snp_set_memory_shared(__pa(vaddr), __pa(vaddr), PTRS_PER_PMD); + i = pmd_index(vaddr); pmd[i] -= sme_get_me_mask(); } @@ -192,9 +206,6 @@ unsigned long __head __startup_64(unsigned long physaddr, if (load_delta & ~PMD_PAGE_MASK) for (;;); - /* Activate Secure Memory Encryption (SME) if supported and enabled */ - sme_enable(bp); - /* Include the SME encryption mask in the fixup value */ load_delta += sme_get_me_mask(); @@ -308,15 +319,6 @@ unsigned long __head __startup_64(unsigned long physaddr, return sme_postprocess_startup(bp, pmd); } -unsigned long __startup_secondary_64(void) -{ - /* - * Return the SME encryption mask (if SME is active) to be used as a - * modifier for the initial pgdir entry programmed into CR3. - */ - return sme_get_me_mask(); -} - /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { @@ -416,6 +418,9 @@ void __init do_early_exception(struct pt_regs *regs, int trapnr) trapnr == X86_TRAP_VC && handle_vc_boot_ghcb(regs)) return; + if (trapnr == X86_TRAP_VE && tdx_early_handle_ve(regs)) + return; + early_fixup_exception(regs, trapnr); } @@ -514,6 +519,9 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) idt_setup_early_handler(); + /* Needed before cc_platform_has() can be used for TDX */ + tdx_early_init(); + copy_bootdata(__va(real_mode_data)); /* @@ -600,8 +608,10 @@ static void startup_64_load_idt(unsigned long physbase) void early_setup_idt(void) { /* VMM Communication Exception */ - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { + setup_ghcb(); set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb); + } bringup_idt_descr.address = (unsigned long)bringup_idt_table; native_load_idt(&bringup_idt_descr); diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index b8e3019547a5..92c4afa2b729 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -65,10 +65,39 @@ SYM_CODE_START_NOALIGN(startup_64) leaq (__end_init_task - FRAME_SIZE)(%rip), %rsp leaq _text(%rip), %rdi + + /* + * initial_gs points to initial fixed_percpu_data struct with storage for + * the stack protector canary. Global pointer fixups are needed at this + * stage, so apply them as is done in fixup_pointer(), and initialize %gs + * such that the canary can be accessed at %gs:40 for subsequent C calls. + */ + movl $MSR_GS_BASE, %ecx + movq initial_gs(%rip), %rax + movq $_text, %rdx + subq %rdx, %rax + addq %rdi, %rax + movq %rax, %rdx + shrq $32, %rdx + wrmsr + pushq %rsi call startup_64_setup_env popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* + * Activate SEV/SME memory encryption if supported/enabled. This needs to + * be done now, since this also includes setup of the SEV-SNP CPUID table, + * which needs to be done before any CPUID instructions are executed in + * subsequent code. + */ + movq %rsi, %rdi + pushq %rsi + call sme_enable + popq %rsi +#endif + /* Now switch to __KERNEL_CS so IRET works reliably */ pushq $__KERNEL_CS leaq .Lon_kernel_cs(%rip), %rax @@ -134,16 +163,32 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. */ - pushq %rsi - call __startup_secondary_64 - popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + movq sme_me_mask, %rax +#else + xorq %rax, %rax +#endif /* Form the CR3 value being sure to include the CR3 modifier */ addq $(init_top_pgt - __START_KERNEL_map), %rax 1: +#ifdef CONFIG_X86_MCE + /* + * Preserve CR4.MCE if the kernel will enable #MC support. + * Clearing MCE may fault in some environments (that also force #MC + * support). Any machine check that occurs before #MC support is fully + * configured will crash the system regardless of the CR4.MCE value set + * here. + */ + movq %cr4, %rcx + andl $X86_CR4_MCE, %ecx +#else + movl $0, %ecx +#endif + /* Enable PAE mode, PGE and LA57 */ - movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx + orl $(X86_CR4_PAE | X86_CR4_PGE), %ecx #ifdef CONFIG_X86_5LEVEL testl $1, __pgtable_l5_enabled(%rip) jz 1f @@ -249,13 +294,23 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Setup EFER (Extended Feature Enable Register) */ movl $MSR_EFER, %ecx rdmsr + /* + * Preserve current value of EFER for comparison and to skip + * EFER writes if no change was made (for TDX guest) + */ + movl %eax, %edx btsl $_EFER_SCE, %eax /* Enable System Call */ btl $20,%edi /* No Execute supported? */ jnc 1f btsl $_EFER_NX, %eax btsq $_PAGE_BIT_NX,early_pmd_flags(%rip) -1: wrmsr /* Make changes effective */ + /* Avoid writing EFER if no change was made (for TDX guest) */ +1: cmpl %edx, %eax + je 1f + xor %edx, %edx + wrmsr /* Make changes effective */ +1: /* Setup cr0 */ movl $CR0_STATE, %eax /* Make changes effective */ diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 608eb63bf044..a58c6bc1cd68 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -69,6 +69,9 @@ static const __initconst struct idt_data early_idts[] = { */ INTG(X86_TRAP_PF, asm_exc_page_fault), #endif +#ifdef CONFIG_INTEL_TDX_GUEST + INTG(X86_TRAP_VE, asm_exc_virtualization_exception), +#endif }; /* diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a22deb58f86d..8b1c45c9cda8 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -69,6 +69,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible; static int has_steal_clock = 0; +static int has_guest_poll = 0; /* * No need for any "IO delay" on KVM */ @@ -706,14 +707,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu) static int kvm_suspend(void) { + u64 val = 0; + kvm_guest_cpu_offline(false); +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) + rdmsrl(MSR_KVM_POLL_CONTROL, val); + has_guest_poll = !(val & 1); +#endif return 0; } static void kvm_resume(void) { kvm_cpu_online(raw_smp_processor_id()); + +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll) + wrmsrl(MSR_KVM_POLL_CONTROL, 0); +#endif } static struct syscore_ops kvm_syscore_ops = { diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 36e84d904260..319fef37d9dc 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -21,6 +21,7 @@ #include <asm/sections.h> #include <asm/io.h> #include <asm/setup_arch.h> +#include <asm/sev.h> static struct resource system_rom_resource = { .name = "System ROM", @@ -197,11 +198,21 @@ static int __init romchecksum(const unsigned char *rom, unsigned long length) void __init probe_roms(void) { - const unsigned char *rom; unsigned long start, length, upper; + const unsigned char *rom; unsigned char c; int i; + /* + * The ROM memory range is not part of the e820 table and is therefore not + * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted + * memory, and SNP requires encrypted memory to be validated before access. + * Do that here. + */ + snp_prep_memory(video_rom_resource.start, + ((system_rom_resource.end + 1) - video_rom_resource.start), + SNP_PAGE_STATE_PRIVATE); + /* video rom */ upper = adapter_rom_resources[0].start; for (start = video_rom_resource.start; start < upper; start += 2048) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e86d09a6aac7..d5275ecb1e92 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -46,6 +46,7 @@ #include <asm/proto.h> #include <asm/frame.h> #include <asm/unwind.h> +#include <asm/tdx.h> #include "process.h" @@ -873,6 +874,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c) } else if (prefer_mwait_c1_over_halt(c)) { pr_info("using mwait in idle threads\n"); x86_idle = mwait_idle; + } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + pr_info("using TDX aware idle routine\n"); + x86_idle = tdx_safe_halt; } else x86_idle = default_idle; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c95b9ac5a457..249981bf3d8a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -756,6 +756,30 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } +void x86_configure_nx(void) +{ + if (boot_cpu_has(X86_FEATURE_NX)) + __supported_pte_mask |= _PAGE_NX; + else + __supported_pte_mask &= ~_PAGE_NX; +} + +static void __init x86_report_nx(void) +{ + if (!boot_cpu_has(X86_FEATURE_NX)) { + printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " + "missing in CPU!\n"); + } else { +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) + printk(KERN_INFO "NX (Execute Disable) protection: active\n"); +#else + /* 32bit non-PAE kernel, NX cannot be used */ + printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " + "cannot be enabled: non-PAE kernel!\n"); +#endif + } +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -896,9 +920,7 @@ void __init setup_arch(char **cmdline_p) /* * x86_configure_nx() is called before parse_early_param() to detect * whether hardware doesn't support NX (so that the early EHCI debug - * console setup can safely call set_fixmap()). It may then be called - * again from within noexec_setup() during parsing early parameters - * to honor the respective command line option. + * console setup can safely call set_fixmap()). */ x86_configure_nx(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index ce987688bbc0..b478edf43bec 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -14,6 +14,68 @@ #define has_cpuflag(f) boot_cpu_has(f) #endif +/* I/O parameters for CPUID-related helpers */ +struct cpuid_leaf { + u32 fn; + u32 subfn; + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; +}; + +/* + * Individual entries of the SNP CPUID table, as defined by the SNP + * Firmware ABI, Revision 0.9, Section 7.1, Table 14. + */ +struct snp_cpuid_fn { + u32 eax_in; + u32 ecx_in; + u64 xcr0_in; + u64 xss_in; + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; + u64 __reserved; +} __packed; + +/* + * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9, + * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit + * of 64 entries per CPUID table. + */ +#define SNP_CPUID_COUNT_MAX 64 + +struct snp_cpuid_table { + u32 count; + u32 __reserved1; + u64 __reserved2; + struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX]; +} __packed; + +/* + * Since feature negotiation related variables are set early in the boot + * process they must reside in the .data section so as not to be zeroed + * out when the .bss section is later cleared. + * + * GHCB protocol version negotiated with the hypervisor. + */ +static u16 ghcb_version __ro_after_init; + +/* Copy of the SNP firmware's CPUID page. */ +static struct snp_cpuid_table cpuid_table_copy __ro_after_init; + +/* + * These will be initialized based on CPUID table so that non-present + * all-zero leaves (for sparse tables) can be differentiated from + * invalid/out-of-range leaves. This is needed since all-zero leaves + * still need to be post-processed. + */ +static u32 cpuid_std_range_max __ro_after_init; +static u32 cpuid_hyp_range_max __ro_after_init; +static u32 cpuid_ext_range_max __ro_after_init; + static bool __init sev_es_check_cpu_features(void) { if (!has_cpuflag(X86_FEATURE_RDRAND)) { @@ -24,15 +86,12 @@ static bool __init sev_es_check_cpu_features(void) return true; } -static void __noreturn sev_es_terminate(unsigned int reason) +static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) { u64 val = GHCB_MSR_TERM_REQ; - /* - * Tell the hypervisor what went wrong - only reason-set 0 is - * currently supported. - */ - val |= GHCB_SEV_TERM_REASON(0, reason); + /* Tell the hypervisor what went wrong. */ + val |= GHCB_SEV_TERM_REASON(set, reason); /* Request Guest Termination from Hypvervisor */ sev_es_wr_ghcb_msr(val); @@ -42,6 +101,42 @@ static void __noreturn sev_es_terminate(unsigned int reason) asm volatile("hlt\n" : : : "memory"); } +/* + * The hypervisor features are available from GHCB version 2 onward. + */ +static u64 get_hv_features(void) +{ + u64 val; + + if (ghcb_version < 2) + return 0; + + sev_es_wr_ghcb_msr(GHCB_MSR_HV_FT_REQ); + VMGEXIT(); + + val = sev_es_rd_ghcb_msr(); + if (GHCB_RESP_CODE(val) != GHCB_MSR_HV_FT_RESP) + return 0; + + return GHCB_MSR_HV_FT_RESP_VAL(val); +} + +static void snp_register_ghcb_early(unsigned long paddr) +{ + unsigned long pfn = paddr >> PAGE_SHIFT; + u64 val; + + sev_es_wr_ghcb_msr(GHCB_MSR_REG_GPA_REQ_VAL(pfn)); + VMGEXIT(); + + val = sev_es_rd_ghcb_msr(); + + /* If the response GPA is not ours then abort the guest */ + if ((GHCB_RESP_CODE(val) != GHCB_MSR_REG_GPA_RESP) || + (GHCB_MSR_REG_GPA_RESP_VAL(val) != pfn)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_REGISTER); +} + static bool sev_es_negotiate_protocol(void) { u64 val; @@ -54,10 +149,12 @@ static bool sev_es_negotiate_protocol(void) if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP) return false; - if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTO_OUR || - GHCB_MSR_PROTO_MIN(val) > GHCB_PROTO_OUR) + if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTOCOL_MIN || + GHCB_MSR_PROTO_MIN(val) > GHCB_PROTOCOL_MAX) return false; + ghcb_version = min_t(size_t, GHCB_MSR_PROTO_MAX(val), GHCB_PROTOCOL_MAX); + return true; } @@ -104,10 +201,7 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt if (ret == 1) { u64 info = ghcb->save.sw_exit_info_2; - unsigned long v; - - info = ghcb->save.sw_exit_info_2; - v = info & SVM_EVTINJ_VEC_MASK; + unsigned long v = info & SVM_EVTINJ_VEC_MASK; /* Check if exception information from hypervisor is sane. */ if ((info & SVM_EVTINJ_VALID) && @@ -130,7 +224,7 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, u64 exit_info_1, u64 exit_info_2) { /* Fill in protocol and format specifiers */ - ghcb->protocol_version = GHCB_PROTOCOL_MAX; + ghcb->protocol_version = ghcb_version; ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; ghcb_set_sw_exit_code(ghcb, exit_code); @@ -150,6 +244,290 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, return verify_exception_info(ghcb, ctxt); } +static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg) +{ + u64 val; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, reg_idx)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) + return -EIO; + + *reg = (val >> 32); + + return 0; +} + +static int sev_cpuid_hv(struct cpuid_leaf *leaf) +{ + int ret; + + /* + * MSR protocol does not support fetching non-zero subfunctions, but is + * sufficient to handle current early-boot cases. Should that change, + * make sure to report an error rather than ignoring the index and + * grabbing random values. If this issue arises in the future, handling + * can be added here to use GHCB-page protocol for cases that occur late + * enough in boot that GHCB page is available. + */ + if (cpuid_function_is_indexed(leaf->fn) && leaf->subfn) + return -EINVAL; + + ret = __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EAX, &leaf->eax); + ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EBX, &leaf->ebx); + ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_ECX, &leaf->ecx); + ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EDX, &leaf->edx); + + return ret; +} + +/* + * This may be called early while still running on the initial identity + * mapping. Use RIP-relative addressing to obtain the correct address + * while running with the initial identity mapping as well as the + * switch-over to kernel virtual addresses later. + */ +static const struct snp_cpuid_table *snp_cpuid_get_table(void) +{ + void *ptr; + + asm ("lea cpuid_table_copy(%%rip), %0" + : "=r" (ptr) + : "p" (&cpuid_table_copy)); + + return ptr; +} + +/* + * The SNP Firmware ABI, Revision 0.9, Section 7.1, details the use of + * XCR0_IN and XSS_IN to encode multiple versions of 0xD subfunctions 0 + * and 1 based on the corresponding features enabled by a particular + * combination of XCR0 and XSS registers so that a guest can look up the + * version corresponding to the features currently enabled in its XCR0/XSS + * registers. The only values that differ between these versions/table + * entries is the enabled XSAVE area size advertised via EBX. + * + * While hypervisors may choose to make use of this support, it is more + * robust/secure for a guest to simply find the entry corresponding to the + * base/legacy XSAVE area size (XCR0=1 or XCR0=3), and then calculate the + * XSAVE area size using subfunctions 2 through 64, as documented in APM + * Volume 3, Rev 3.31, Appendix E.3.8, which is what is done here. + * + * Since base/legacy XSAVE area size is documented as 0x240, use that value + * directly rather than relying on the base size in the CPUID table. + * + * Return: XSAVE area size on success, 0 otherwise. + */ +static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + u64 xfeatures_found = 0; + u32 xsave_size = 0x240; + int i; + + for (i = 0; i < cpuid_table->count; i++) { + const struct snp_cpuid_fn *e = &cpuid_table->fn[i]; + + if (!(e->eax_in == 0xD && e->ecx_in > 1 && e->ecx_in < 64)) + continue; + if (!(xfeatures_en & (BIT_ULL(e->ecx_in)))) + continue; + if (xfeatures_found & (BIT_ULL(e->ecx_in))) + continue; + + xfeatures_found |= (BIT_ULL(e->ecx_in)); + + if (compacted) + xsave_size += e->eax; + else + xsave_size = max(xsave_size, e->eax + e->ebx); + } + + /* + * Either the guest set unsupported XCR0/XSS bits, or the corresponding + * entries in the CPUID table were not present. This is not a valid + * state to be in. + */ + if (xfeatures_found != (xfeatures_en & GENMASK_ULL(63, 2))) + return 0; + + return xsave_size; +} + +static bool +snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + int i; + + for (i = 0; i < cpuid_table->count; i++) { + const struct snp_cpuid_fn *e = &cpuid_table->fn[i]; + + if (e->eax_in != leaf->fn) + continue; + + if (cpuid_function_is_indexed(leaf->fn) && e->ecx_in != leaf->subfn) + continue; + + /* + * For 0xD subfunctions 0 and 1, only use the entry corresponding + * to the base/legacy XSAVE area size (XCR0=1 or XCR0=3, XSS=0). + * See the comments above snp_cpuid_calc_xsave_size() for more + * details. + */ + if (e->eax_in == 0xD && (e->ecx_in == 0 || e->ecx_in == 1)) + if (!(e->xcr0_in == 1 || e->xcr0_in == 3) || e->xss_in) + continue; + + leaf->eax = e->eax; + leaf->ebx = e->ebx; + leaf->ecx = e->ecx; + leaf->edx = e->edx; + + return true; + } + + return false; +} + +static void snp_cpuid_hv(struct cpuid_leaf *leaf) +{ + if (sev_cpuid_hv(leaf)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV); +} + +static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) +{ + struct cpuid_leaf leaf_hv = *leaf; + + switch (leaf->fn) { + case 0x1: + snp_cpuid_hv(&leaf_hv); + + /* initial APIC ID */ + leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0)); + /* APIC enabled bit */ + leaf->edx = (leaf_hv.edx & BIT(9)) | (leaf->edx & ~BIT(9)); + + /* OSXSAVE enabled bit */ + if (native_read_cr4() & X86_CR4_OSXSAVE) + leaf->ecx |= BIT(27); + break; + case 0x7: + /* OSPKE enabled bit */ + leaf->ecx &= ~BIT(4); + if (native_read_cr4() & X86_CR4_PKE) + leaf->ecx |= BIT(4); + break; + case 0xB: + leaf_hv.subfn = 0; + snp_cpuid_hv(&leaf_hv); + + /* extended APIC ID */ + leaf->edx = leaf_hv.edx; + break; + case 0xD: { + bool compacted = false; + u64 xcr0 = 1, xss = 0; + u32 xsave_size; + + if (leaf->subfn != 0 && leaf->subfn != 1) + return 0; + + if (native_read_cr4() & X86_CR4_OSXSAVE) + xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + if (leaf->subfn == 1) { + /* Get XSS value if XSAVES is enabled. */ + if (leaf->eax & BIT(3)) { + unsigned long lo, hi; + + asm volatile("rdmsr" : "=a" (lo), "=d" (hi) + : "c" (MSR_IA32_XSS)); + xss = (hi << 32) | lo; + } + + /* + * The PPR and APM aren't clear on what size should be + * encoded in 0xD:0x1:EBX when compaction is not enabled + * by either XSAVEC (feature bit 1) or XSAVES (feature + * bit 3) since SNP-capable hardware has these feature + * bits fixed as 1. KVM sets it to 0 in this case, but + * to avoid this becoming an issue it's safer to simply + * treat this as unsupported for SNP guests. + */ + if (!(leaf->eax & (BIT(1) | BIT(3)))) + return -EINVAL; + + compacted = true; + } + + xsave_size = snp_cpuid_calc_xsave_size(xcr0 | xss, compacted); + if (!xsave_size) + return -EINVAL; + + leaf->ebx = xsave_size; + } + break; + case 0x8000001E: + snp_cpuid_hv(&leaf_hv); + + /* extended APIC ID */ + leaf->eax = leaf_hv.eax; + /* compute ID */ + leaf->ebx = (leaf->ebx & GENMASK(31, 8)) | (leaf_hv.ebx & GENMASK(7, 0)); + /* node ID */ + leaf->ecx = (leaf->ecx & GENMASK(31, 8)) | (leaf_hv.ecx & GENMASK(7, 0)); + break; + default: + /* No fix-ups needed, use values as-is. */ + break; + } + + return 0; +} + +/* + * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value + * should be treated as fatal by caller. + */ +static int snp_cpuid(struct cpuid_leaf *leaf) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + + if (!cpuid_table->count) + return -EOPNOTSUPP; + + if (!snp_cpuid_get_validated_func(leaf)) { + /* + * Some hypervisors will avoid keeping track of CPUID entries + * where all values are zero, since they can be handled the + * same as out-of-range values (all-zero). This is useful here + * as well as it allows virtually all guest configurations to + * work using a single SNP CPUID table. + * + * To allow for this, there is a need to distinguish between + * out-of-range entries and in-range zero entries, since the + * CPUID table entries are only a template that may need to be + * augmented with additional values for things like + * CPU-specific information during post-processing. So if it's + * not in the table, set the values to zero. Then, if they are + * within a valid CPUID range, proceed with post-processing + * using zeros as the initial values. Otherwise, skip + * post-processing and just return zeros immediately. + */ + leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0; + + /* Skip post-processing for out-of-range zero leafs. */ + if (!(leaf->fn <= cpuid_std_range_max || + (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) || + (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max))) + return 0; + } + + return snp_cpuid_postprocess(leaf); +} + /* * Boot VC Handler - This is the first VC handler during boot, there is no GHCB * page yet, so it only supports the MSR based communication with the @@ -157,40 +535,33 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, */ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { + unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); - unsigned long val; + struct cpuid_leaf leaf; + int ret; /* Only CPUID is supported via MSR protocol */ if (exit_code != SVM_EXIT_CPUID) goto fail; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) - goto fail; - regs->ax = val >> 32; + leaf.fn = fn; + leaf.subfn = subfn; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) - goto fail; - regs->bx = val >> 32; + ret = snp_cpuid(&leaf); + if (!ret) + goto cpuid_done; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) + if (ret != -EOPNOTSUPP) goto fail; - regs->cx = val >> 32; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) + if (sev_cpuid_hv(&leaf)) goto fail; - regs->dx = val >> 32; + +cpuid_done: + regs->ax = leaf.eax; + regs->bx = leaf.ebx; + regs->cx = leaf.ecx; + regs->dx = leaf.edx; /* * This is a VC handler and the #VC is only raised when SEV-ES is @@ -221,7 +592,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) fail: /* Terminate the guest */ - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); } static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, @@ -481,12 +852,37 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } +static int vc_handle_cpuid_snp(struct pt_regs *regs) +{ + struct cpuid_leaf leaf; + int ret; + + leaf.fn = regs->ax; + leaf.subfn = regs->cx; + ret = snp_cpuid(&leaf); + if (!ret) { + regs->ax = leaf.eax; + regs->bx = leaf.ebx; + regs->cx = leaf.ecx; + regs->dx = leaf.edx; + } + + return ret; +} + static enum es_result vc_handle_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u32 cr4 = native_read_cr4(); enum es_result ret; + int snp_cpuid_ret; + + snp_cpuid_ret = vc_handle_cpuid_snp(regs); + if (!snp_cpuid_ret) + return ES_OK; + if (snp_cpuid_ret != -EOPNOTSUPP) + return ES_VMM_ERROR; ghcb_set_rax(ghcb, regs->ax); ghcb_set_rcx(ghcb, regs->cx); @@ -538,3 +934,67 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, return ES_OK; } + +struct cc_setup_data { + struct setup_data header; + u32 cc_blob_address; +}; + +/* + * Search for a Confidential Computing blob passed in as a setup_data entry + * via the Linux Boot Protocol. + */ +static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) +{ + struct cc_setup_data *sd = NULL; + struct setup_data *hdr; + + hdr = (struct setup_data *)bp->hdr.setup_data; + + while (hdr) { + if (hdr->type == SETUP_CC_BLOB) { + sd = (struct cc_setup_data *)hdr; + return (struct cc_blob_sev_info *)(unsigned long)sd->cc_blob_address; + } + hdr = (struct setup_data *)hdr->next; + } + + return NULL; +} + +/* + * Initialize the kernel's copy of the SNP CPUID table, and set up the + * pointer that will be used to access it. + * + * Maintaining a direct mapping of the SNP CPUID table used by firmware would + * be possible as an alternative, but the approach is brittle since the + * mapping needs to be updated in sync with all the changes to virtual memory + * layout and related mapping facilities throughout the boot process. + */ +static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) +{ + const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table; + int i; + + if (!cc_info || !cc_info->cpuid_phys || cc_info->cpuid_len < PAGE_SIZE) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID); + + cpuid_table_fw = (const struct snp_cpuid_table *)cc_info->cpuid_phys; + if (!cpuid_table_fw->count || cpuid_table_fw->count > SNP_CPUID_COUNT_MAX) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID); + + cpuid_table = snp_cpuid_get_table(); + memcpy((void *)cpuid_table, cpuid_table_fw, sizeof(*cpuid_table)); + + /* Initialize CPUID ranges for range-checking. */ + for (i = 0; i < cpuid_table->count; i++) { + const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; + + if (fn->eax_in == 0x0) + cpuid_std_range_max = fn->eax; + else if (fn->eax_in == 0x40000000) + cpuid_hyp_range_max = fn->eax; + else if (fn->eax_in == 0x80000000) + cpuid_ext_range_max = fn->eax; + } +} diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index e6d316a01fdd..c05f0124c410 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -18,6 +18,10 @@ #include <linux/memblock.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/cpumask.h> +#include <linux/efi.h> +#include <linux/platform_device.h> +#include <linux/io.h> #include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> @@ -31,9 +35,28 @@ #include <asm/svm.h> #include <asm/smp.h> #include <asm/cpu.h> +#include <asm/apic.h> +#include <asm/cpuid.h> +#include <asm/cmdline.h> #define DR7_RESET_VALUE 0x400 +/* AP INIT values as documented in the APM2 section "Processor Initialization State" */ +#define AP_INIT_CS_LIMIT 0xffff +#define AP_INIT_DS_LIMIT 0xffff +#define AP_INIT_LDTR_LIMIT 0xffff +#define AP_INIT_GDTR_LIMIT 0xffff +#define AP_INIT_IDTR_LIMIT 0xffff +#define AP_INIT_TR_LIMIT 0xffff +#define AP_INIT_RFLAGS_DEFAULT 0x2 +#define AP_INIT_DR6_DEFAULT 0xffff0ff0 +#define AP_INIT_GPAT_DEFAULT 0x0007040600070406ULL +#define AP_INIT_XCR0_DEFAULT 0x1 +#define AP_INIT_X87_FTW_DEFAULT 0x5555 +#define AP_INIT_X87_FCW_DEFAULT 0x0040 +#define AP_INIT_CR0_DEFAULT 0x60000010 +#define AP_INIT_MXCSR_DEFAULT 0x1f80 + /* For early boot hypervisor communication in SEV-ES enabled guests */ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); @@ -41,7 +64,10 @@ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); * Needs to be in the .data section because we need it NULL before bss is * cleared */ -static struct ghcb __initdata *boot_ghcb; +static struct ghcb *boot_ghcb __section(".data"); + +/* Bitmap of SEV features supported by the hypervisor */ +static u64 sev_hv_features __ro_after_init; /* #VC handler runtime per-CPU data */ struct sev_es_runtime_data { @@ -87,6 +113,15 @@ struct ghcb_state { static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); +static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa); + +struct sev_config { + __u64 debug : 1, + __reserved : 63; +}; + +static struct sev_config sev_cfg __read_mostly; + static __always_inline bool on_vc_stack(struct pt_regs *regs) { unsigned long sp = regs->sp; @@ -523,13 +558,68 @@ void noinstr __sev_es_nmi_complete(void) __sev_put_ghcb(&state); } -static u64 get_jump_table_addr(void) +static u64 __init get_secrets_page(void) +{ + u64 pa_data = boot_params.cc_blob_address; + struct cc_blob_sev_info info; + void *map; + + /* + * The CC blob contains the address of the secrets page, check if the + * blob is present. + */ + if (!pa_data) + return 0; + + map = early_memremap(pa_data, sizeof(info)); + if (!map) { + pr_err("Unable to locate SNP secrets page: failed to map the Confidential Computing blob.\n"); + return 0; + } + memcpy(&info, map, sizeof(info)); + early_memunmap(map, sizeof(info)); + + /* smoke-test the secrets page passed */ + if (!info.secrets_phys || info.secrets_len != PAGE_SIZE) + return 0; + + return info.secrets_phys; +} + +static u64 __init get_snp_jump_table_addr(void) +{ + struct snp_secrets_page_layout *layout; + void __iomem *mem; + u64 pa, addr; + + pa = get_secrets_page(); + if (!pa) + return 0; + + mem = ioremap_encrypted(pa, PAGE_SIZE); + if (!mem) { + pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n"); + return 0; + } + + layout = (__force struct snp_secrets_page_layout *)mem; + + addr = layout->os_area.ap_jump_table_pa; + iounmap(mem); + + return addr; +} + +static u64 __init get_jump_table_addr(void) { struct ghcb_state state; unsigned long flags; struct ghcb *ghcb; u64 ret = 0; + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return get_snp_jump_table_addr(); + local_irq_save(flags); ghcb = __sev_get_ghcb(&state); @@ -553,7 +643,496 @@ static u64 get_jump_table_addr(void) return ret; } -int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) +static void pvalidate_pages(unsigned long vaddr, unsigned int npages, bool validate) +{ + unsigned long vaddr_end; + int rc; + + vaddr = vaddr & PAGE_MASK; + vaddr_end = vaddr + (npages << PAGE_SHIFT); + + while (vaddr < vaddr_end) { + rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate); + if (WARN(rc, "Failed to validate address 0x%lx ret %d", vaddr, rc)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); + + vaddr = vaddr + PAGE_SIZE; + } +} + +static void __init early_set_pages_state(unsigned long paddr, unsigned int npages, enum psc_op op) +{ + unsigned long paddr_end; + u64 val; + + paddr = paddr & PAGE_MASK; + paddr_end = paddr + (npages << PAGE_SHIFT); + + while (paddr < paddr_end) { + /* + * Use the MSR protocol because this function can be called before + * the GHCB is established. + */ + sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); + VMGEXIT(); + + val = sev_es_rd_ghcb_msr(); + + if (WARN(GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP, + "Wrong PSC response code: 0x%x\n", + (unsigned int)GHCB_RESP_CODE(val))) + goto e_term; + + if (WARN(GHCB_MSR_PSC_RESP_VAL(val), + "Failed to change page state to '%s' paddr 0x%lx error 0x%llx\n", + op == SNP_PAGE_STATE_PRIVATE ? "private" : "shared", + paddr, GHCB_MSR_PSC_RESP_VAL(val))) + goto e_term; + + paddr = paddr + PAGE_SIZE; + } + + return; + +e_term: + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); +} + +void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + /* + * Ask the hypervisor to mark the memory pages as private in the RMP + * table. + */ + early_set_pages_state(paddr, npages, SNP_PAGE_STATE_PRIVATE); + + /* Validate the memory pages after they've been added in the RMP table. */ + pvalidate_pages(vaddr, npages, true); +} + +void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + /* Invalidate the memory pages before they are marked shared in the RMP table. */ + pvalidate_pages(vaddr, npages, false); + + /* Ask hypervisor to mark the memory pages shared in the RMP table. */ + early_set_pages_state(paddr, npages, SNP_PAGE_STATE_SHARED); +} + +void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) +{ + unsigned long vaddr, npages; + + vaddr = (unsigned long)__va(paddr); + npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + + if (op == SNP_PAGE_STATE_PRIVATE) + early_snp_set_memory_private(vaddr, paddr, npages); + else if (op == SNP_PAGE_STATE_SHARED) + early_snp_set_memory_shared(vaddr, paddr, npages); + else + WARN(1, "invalid memory op %d\n", op); +} + +static int vmgexit_psc(struct snp_psc_desc *desc) +{ + int cur_entry, end_entry, ret = 0; + struct snp_psc_desc *data; + struct ghcb_state state; + struct es_em_ctxt ctxt; + unsigned long flags; + struct ghcb *ghcb; + + /* + * __sev_get_ghcb() needs to run with IRQs disabled because it is using + * a per-CPU GHCB. + */ + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + if (!ghcb) { + ret = 1; + goto out_unlock; + } + + /* Copy the input desc into GHCB shared buffer */ + data = (struct snp_psc_desc *)ghcb->shared_buffer; + memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc))); + + /* + * As per the GHCB specification, the hypervisor can resume the guest + * before processing all the entries. Check whether all the entries + * are processed. If not, then keep retrying. Note, the hypervisor + * will update the data memory directly to indicate the status, so + * reference the data->hdr everywhere. + * + * The strategy here is to wait for the hypervisor to change the page + * state in the RMP table before guest accesses the memory pages. If the + * page state change was not successful, then later memory access will + * result in a crash. + */ + cur_entry = data->hdr.cur_entry; + end_entry = data->hdr.end_entry; + + while (data->hdr.cur_entry <= data->hdr.end_entry) { + ghcb_set_sw_scratch(ghcb, (u64)__pa(data)); + + /* This will advance the shared buffer data points to. */ + ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, SVM_VMGEXIT_PSC, 0, 0); + + /* + * Page State Change VMGEXIT can pass error code through + * exit_info_2. + */ + if (WARN(ret || ghcb->save.sw_exit_info_2, + "SNP: PSC failed ret=%d exit_info_2=%llx\n", + ret, ghcb->save.sw_exit_info_2)) { + ret = 1; + goto out; + } + + /* Verify that reserved bit is not set */ + if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) { + ret = 1; + goto out; + } + + /* + * Sanity check that entry processing is not going backwards. + * This will happen only if hypervisor is tricking us. + */ + if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry, +"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n", + end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) { + ret = 1; + goto out; + } + } + +out: + __sev_put_ghcb(&state); + +out_unlock: + local_irq_restore(flags); + + return ret; +} + +static void __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr, + unsigned long vaddr_end, int op) +{ + struct psc_hdr *hdr; + struct psc_entry *e; + unsigned long pfn; + int i; + + hdr = &data->hdr; + e = data->entries; + + memset(data, 0, sizeof(*data)); + i = 0; + + while (vaddr < vaddr_end) { + if (is_vmalloc_addr((void *)vaddr)) + pfn = vmalloc_to_pfn((void *)vaddr); + else + pfn = __pa(vaddr) >> PAGE_SHIFT; + + e->gfn = pfn; + e->operation = op; + hdr->end_entry = i; + + /* + * Current SNP implementation doesn't keep track of the RMP page + * size so use 4K for simplicity. + */ + e->pagesize = RMP_PG_SIZE_4K; + + vaddr = vaddr + PAGE_SIZE; + e++; + i++; + } + + if (vmgexit_psc(data)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); +} + +static void set_pages_state(unsigned long vaddr, unsigned int npages, int op) +{ + unsigned long vaddr_end, next_vaddr; + struct snp_psc_desc *desc; + + desc = kmalloc(sizeof(*desc), GFP_KERNEL_ACCOUNT); + if (!desc) + panic("SNP: failed to allocate memory for PSC descriptor\n"); + + vaddr = vaddr & PAGE_MASK; + vaddr_end = vaddr + (npages << PAGE_SHIFT); + + while (vaddr < vaddr_end) { + /* Calculate the last vaddr that fits in one struct snp_psc_desc. */ + next_vaddr = min_t(unsigned long, vaddr_end, + (VMGEXIT_PSC_MAX_ENTRY * PAGE_SIZE) + vaddr); + + __set_pages_state(desc, vaddr, next_vaddr, op); + + vaddr = next_vaddr; + } + + kfree(desc); +} + +void snp_set_memory_shared(unsigned long vaddr, unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + pvalidate_pages(vaddr, npages, false); + + set_pages_state(vaddr, npages, SNP_PAGE_STATE_SHARED); +} + +void snp_set_memory_private(unsigned long vaddr, unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE); + + pvalidate_pages(vaddr, npages, true); +} + +static int snp_set_vmsa(void *va, bool vmsa) +{ + u64 attrs; + + /* + * Running at VMPL0 allows the kernel to change the VMSA bit for a page + * using the RMPADJUST instruction. However, for the instruction to + * succeed it must target the permissions of a lesser privileged + * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST + * instruction in the AMD64 APM Volume 3). + */ + attrs = 1; + if (vmsa) + attrs |= RMPADJUST_VMSA_PAGE_BIT; + + return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); +} + +#define __ATTR_BASE (SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK) +#define INIT_CS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_READ_MASK | SVM_SELECTOR_CODE_MASK) +#define INIT_DS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_WRITE_MASK) + +#define INIT_LDTR_ATTRIBS (SVM_SELECTOR_P_MASK | 2) +#define INIT_TR_ATTRIBS (SVM_SELECTOR_P_MASK | 3) + +static void *snp_alloc_vmsa_page(void) +{ + struct page *p; + + /* + * Allocate VMSA page to work around the SNP erratum where the CPU will + * incorrectly signal an RMP violation #PF if a large page (2MB or 1GB) + * collides with the RMP entry of VMSA page. The recommended workaround + * is to not use a large page. + * + * Allocate an 8k page which is also 8k-aligned. + */ + p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1); + if (!p) + return NULL; + + split_page(p, 1); + + /* Free the first 4k. This page may be 2M/1G aligned and cannot be used. */ + __free_page(p); + + return page_address(p + 1); +} + +static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) +{ + int err; + + err = snp_set_vmsa(vmsa, false); + if (err) + pr_err("clear VMSA page failed (%u), leaking page\n", err); + else + free_page((unsigned long)vmsa); +} + +static int wakeup_cpu_via_vmgexit(int apic_id, unsigned long start_ip) +{ + struct sev_es_save_area *cur_vmsa, *vmsa; + struct ghcb_state state; + unsigned long flags; + struct ghcb *ghcb; + u8 sipi_vector; + int cpu, ret; + u64 cr4; + + /* + * The hypervisor SNP feature support check has happened earlier, just check + * the AP_CREATION one here. + */ + if (!(sev_hv_features & GHCB_HV_FT_SNP_AP_CREATION)) + return -EOPNOTSUPP; + + /* + * Verify the desired start IP against the known trampoline start IP + * to catch any future new trampolines that may be introduced that + * would require a new protected guest entry point. + */ + if (WARN_ONCE(start_ip != real_mode_header->trampoline_start, + "Unsupported SNP start_ip: %lx\n", start_ip)) + return -EINVAL; + + /* Override start_ip with known protected guest start IP */ + start_ip = real_mode_header->sev_es_trampoline_start; + + /* Find the logical CPU for the APIC ID */ + for_each_present_cpu(cpu) { + if (arch_match_cpu_phys_id(cpu, apic_id)) + break; + } + if (cpu >= nr_cpu_ids) + return -EINVAL; + + cur_vmsa = per_cpu(sev_vmsa, cpu); + + /* + * A new VMSA is created each time because there is no guarantee that + * the current VMSA is the kernels or that the vCPU is not running. If + * an attempt was done to use the current VMSA with a running vCPU, a + * #VMEXIT of that vCPU would wipe out all of the settings being done + * here. + */ + vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page(); + if (!vmsa) + return -ENOMEM; + + /* CR4 should maintain the MCE value */ + cr4 = native_read_cr4() & X86_CR4_MCE; + + /* Set the CS value based on the start_ip converted to a SIPI vector */ + sipi_vector = (start_ip >> 12); + vmsa->cs.base = sipi_vector << 12; + vmsa->cs.limit = AP_INIT_CS_LIMIT; + vmsa->cs.attrib = INIT_CS_ATTRIBS; + vmsa->cs.selector = sipi_vector << 8; + + /* Set the RIP value based on start_ip */ + vmsa->rip = start_ip & 0xfff; + + /* Set AP INIT defaults as documented in the APM */ + vmsa->ds.limit = AP_INIT_DS_LIMIT; + vmsa->ds.attrib = INIT_DS_ATTRIBS; + vmsa->es = vmsa->ds; + vmsa->fs = vmsa->ds; + vmsa->gs = vmsa->ds; + vmsa->ss = vmsa->ds; + + vmsa->gdtr.limit = AP_INIT_GDTR_LIMIT; + vmsa->ldtr.limit = AP_INIT_LDTR_LIMIT; + vmsa->ldtr.attrib = INIT_LDTR_ATTRIBS; + vmsa->idtr.limit = AP_INIT_IDTR_LIMIT; + vmsa->tr.limit = AP_INIT_TR_LIMIT; + vmsa->tr.attrib = INIT_TR_ATTRIBS; + + vmsa->cr4 = cr4; + vmsa->cr0 = AP_INIT_CR0_DEFAULT; + vmsa->dr7 = DR7_RESET_VALUE; + vmsa->dr6 = AP_INIT_DR6_DEFAULT; + vmsa->rflags = AP_INIT_RFLAGS_DEFAULT; + vmsa->g_pat = AP_INIT_GPAT_DEFAULT; + vmsa->xcr0 = AP_INIT_XCR0_DEFAULT; + vmsa->mxcsr = AP_INIT_MXCSR_DEFAULT; + vmsa->x87_ftw = AP_INIT_X87_FTW_DEFAULT; + vmsa->x87_fcw = AP_INIT_X87_FCW_DEFAULT; + + /* SVME must be set. */ + vmsa->efer = EFER_SVME; + + /* + * Set the SNP-specific fields for this VMSA: + * VMPL level + * SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits) + */ + vmsa->vmpl = 0; + vmsa->sev_features = sev_status >> 2; + + /* Switch the page over to a VMSA page now that it is initialized */ + ret = snp_set_vmsa(vmsa, true); + if (ret) { + pr_err("set VMSA page failed (%u)\n", ret); + free_page((unsigned long)vmsa); + + return -EINVAL; + } + + /* Issue VMGEXIT AP Creation NAE event */ + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + + vc_ghcb_invalidate(ghcb); + ghcb_set_rax(ghcb, vmsa->sev_features); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION); + ghcb_set_sw_exit_info_1(ghcb, ((u64)apic_id << 32) | SVM_VMGEXIT_AP_CREATE); + ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa)); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if (!ghcb_sw_exit_info_1_is_valid(ghcb) || + lower_32_bits(ghcb->save.sw_exit_info_1)) { + pr_err("SNP AP Creation error\n"); + ret = -EINVAL; + } + + __sev_put_ghcb(&state); + + local_irq_restore(flags); + + /* Perform cleanup if there was an error */ + if (ret) { + snp_cleanup_vmsa(vmsa); + vmsa = NULL; + } + + /* Free up any previous VMSA page */ + if (cur_vmsa) + snp_cleanup_vmsa(cur_vmsa); + + /* Record the current VMSA page */ + per_cpu(sev_vmsa, cpu) = vmsa; + + return ret; +} + +void snp_set_wakeup_secondary_cpu(void) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + /* + * Always set this override if SNP is enabled. This makes it the + * required method to start APs under SNP. If the hypervisor does + * not support AP creation, then no APs will be started. + */ + apic->wakeup_secondary_cpu = wakeup_cpu_via_vmgexit; +} + +int __init sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { u16 startup_cs, startup_ip; phys_addr_t jump_table_pa; @@ -644,15 +1223,39 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -/* - * This function runs on the first #VC exception after the kernel - * switched to virtual addresses. - */ -static bool __init sev_es_setup_ghcb(void) +static void snp_register_per_cpu_ghcb(void) +{ + struct sev_es_runtime_data *data; + struct ghcb *ghcb; + + data = this_cpu_read(runtime_data); + ghcb = &data->ghcb_page; + + snp_register_ghcb_early(__pa(ghcb)); +} + +void setup_ghcb(void) { + if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + return; + /* First make sure the hypervisor talks a supported protocol. */ if (!sev_es_negotiate_protocol()) - return false; + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); + + /* + * Check whether the runtime #VC exception handler is active. It uses + * the per-CPU GHCB page which is set up by sev_es_init_vc_handling(). + * + * If SNP is active, register the per-CPU GHCB page so that the runtime + * exception handler can use it. + */ + if (initial_vc_handler == (unsigned long)kernel_exc_vmm_communication) { + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + snp_register_per_cpu_ghcb(); + + return; + } /* * Clear the boot_ghcb. The first exception comes in before the bss @@ -663,7 +1266,9 @@ static bool __init sev_es_setup_ghcb(void) /* Alright - Make the boot-ghcb public */ boot_ghcb = &boot_ghcb_page; - return true; + /* SNP guest requires that GHCB GPA must be registered. */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + snp_register_ghcb_early(__pa(&boot_ghcb_page)); } #ifdef CONFIG_HOTPLUG_CPU @@ -766,6 +1371,17 @@ void __init sev_es_init_vc_handling(void) if (!sev_es_check_cpu_features()) panic("SEV-ES CPU Features missing"); + /* + * SNP is supported in v2 of the GHCB spec which mandates support for HV + * features. + */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) { + sev_hv_features = get_hv_features(); + + if (!(sev_hv_features & GHCB_HV_FT_SNP)) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + } + /* Enable SEV-ES special handling */ static_branch_enable(&sev_es_enable_key); @@ -1337,7 +1953,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication) show_regs(regs); /* Ask hypervisor to sev_es_terminate */ - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); /* If that fails and we get here - just panic */ panic("Returned from Terminate-Request to Hypervisor\n"); @@ -1383,10 +1999,6 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) struct es_em_ctxt ctxt; enum es_result result; - /* Do initial setup or terminate the guest */ - if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb())) - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); - vc_ghcb_invalidate(boot_ghcb); result = vc_init_em_ctxt(&ctxt, regs, exit_code); @@ -1425,6 +2037,215 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) fail: show_regs(regs); - while (true) - halt(); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); +} + +/* + * Initial set up of SNP relies on information provided by the + * Confidential Computing blob, which can be passed to the kernel + * in the following ways, depending on how it is booted: + * + * - when booted via the boot/decompress kernel: + * - via boot_params + * + * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH): + * - via a setup_data entry, as defined by the Linux Boot Protocol + * + * Scan for the blob in that order. + */ +static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + /* Boot kernel would have passed the CC blob via boot_params. */ + if (bp->cc_blob_address) { + cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address; + goto found_cc_info; + } + + /* + * If kernel was booted directly, without the use of the + * boot/decompression kernel, the CC blob may have been passed via + * setup_data instead. + */ + cc_info = find_cc_blob_setup_data(bp); + if (!cc_info) + return NULL; + +found_cc_info: + if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC) + snp_abort(); + + return cc_info; +} + +bool __init snp_init(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + if (!bp) + return false; + + cc_info = find_cc_blob(bp); + if (!cc_info) + return false; + + setup_cpuid_table(cc_info); + + /* + * The CC blob will be used later to access the secrets page. Cache + * it here like the boot kernel does. + */ + bp->cc_blob_address = (u32)(unsigned long)cc_info; + + return true; +} + +void __init snp_abort(void) +{ + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); +} + +static void dump_cpuid_table(void) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + int i = 0; + + pr_info("count=%d reserved=0x%x reserved2=0x%llx\n", + cpuid_table->count, cpuid_table->__reserved1, cpuid_table->__reserved2); + + for (i = 0; i < SNP_CPUID_COUNT_MAX; i++) { + const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; + + pr_info("index=%3d fn=0x%08x subfn=0x%08x: eax=0x%08x ebx=0x%08x ecx=0x%08x edx=0x%08x xcr0_in=0x%016llx xss_in=0x%016llx reserved=0x%016llx\n", + i, fn->eax_in, fn->ecx_in, fn->eax, fn->ebx, fn->ecx, + fn->edx, fn->xcr0_in, fn->xss_in, fn->__reserved); + } +} + +/* + * It is useful from an auditing/testing perspective to provide an easy way + * for the guest owner to know that the CPUID table has been initialized as + * expected, but that initialization happens too early in boot to print any + * sort of indicator, and there's not really any other good place to do it, + * so do it here. + */ +static int __init report_cpuid_table(void) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + + if (!cpuid_table->count) + return 0; + + pr_info("Using SNP CPUID table, %d entries present.\n", + cpuid_table->count); + + if (sev_cfg.debug) + dump_cpuid_table(); + + return 0; +} +arch_initcall(report_cpuid_table); + +static int __init init_sev_config(char *str) +{ + char *s; + + while ((s = strsep(&str, ","))) { + if (!strcmp(s, "debug")) { + sev_cfg.debug = true; + continue; + } + + pr_info("SEV command-line option '%s' was not recognized\n", s); + } + + return 1; +} +__setup("sev=", init_sev_config); + +int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err) +{ + struct ghcb_state state; + struct es_em_ctxt ctxt; + unsigned long flags; + struct ghcb *ghcb; + int ret; + + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return -ENODEV; + + if (!fw_err) + return -EINVAL; + + /* + * __sev_get_ghcb() needs to run with IRQs disabled because it is using + * a per-CPU GHCB. + */ + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + if (!ghcb) { + ret = -EIO; + goto e_restore_irq; + } + + vc_ghcb_invalidate(ghcb); + + if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) { + ghcb_set_rax(ghcb, input->data_gpa); + ghcb_set_rbx(ghcb, input->data_npages); + } + + ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, exit_code, input->req_gpa, input->resp_gpa); + if (ret) + goto e_put; + + if (ghcb->save.sw_exit_info_2) { + /* Number of expected pages are returned in RBX */ + if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST && + ghcb->save.sw_exit_info_2 == SNP_GUEST_REQ_INVALID_LEN) + input->data_npages = ghcb_get_rbx(ghcb); + + *fw_err = ghcb->save.sw_exit_info_2; + + ret = -EIO; + } + +e_put: + __sev_put_ghcb(&state); +e_restore_irq: + local_irq_restore(flags); + + return ret; +} +EXPORT_SYMBOL_GPL(snp_issue_guest_request); + +static struct platform_device sev_guest_device = { + .name = "sev-guest", + .id = -1, +}; + +static int __init snp_init_platform_device(void) +{ + struct sev_guest_platform_data data; + u64 gpa; + + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return -ENODEV; + + gpa = get_secrets_page(); + if (!gpa) + return -ENODEV; + + data.secrets_gpa = gpa; + if (platform_device_add_data(&sev_guest_device, &data, sizeof(data))) + return -ENODEV; + + if (platform_device_register(&sev_guest_device)) + return -ENODEV; + + pr_info("SNP guest platform device initialized.\n"); + return 0; } +device_initcall(snp_init_platform_device); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index eb7de776a2a6..5e7f9532a10d 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -81,6 +81,7 @@ #include <asm/spec-ctrl.h> #include <asm/hw_irq.h> #include <asm/stackprotector.h> +#include <asm/sev.h> /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); @@ -1081,6 +1082,11 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, unsigned long boot_error = 0; unsigned long timeout; +#ifdef CONFIG_X86_64 + /* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */ + if (apic->wakeup_secondary_cpu_64) + start_ip = real_mode_header->trampoline_start64; +#endif idle->thread.sp = (unsigned long)task_pt_regs(idle); early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); initial_code = (unsigned long)start_secondary; @@ -1122,11 +1128,14 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, /* * Wake up a CPU in difference cases: - * - Use the method in the APIC driver if it's defined + * - Use a method from the APIC driver if one defined, with wakeup + * straight to 64-bit mode preferred over wakeup to RM. * Otherwise, * - Use an INIT boot APIC message for APs or NMI for BSP. */ - if (apic->wakeup_secondary_cpu) + if (apic->wakeup_secondary_cpu_64) + boot_error = apic->wakeup_secondary_cpu_64(apicid, start_ip); + else if (apic->wakeup_secondary_cpu) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, @@ -1428,6 +1437,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) smp_quirk_init_udelay(); speculative_store_bypass_ht_init(); + + snp_set_wakeup_secondary_cpu(); } void arch_thaw_secondary_cpus_begin(void) diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 531fb4cbb63f..aa72cefdd5be 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,10 +12,9 @@ enum insn_type { }; /* - * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax - * The REX.W cancels the effect of any data16. + * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ -static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; +static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1563fb995005..d62b2cb85cea 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -62,6 +62,7 @@ #include <asm/insn.h> #include <asm/insn-eval.h> #include <asm/vdso.h> +#include <asm/tdx.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -686,13 +687,40 @@ static bool try_fixup_enqcmd_gp(void) #endif } +static bool gp_try_fixup_and_notify(struct pt_regs *regs, int trapnr, + unsigned long error_code, const char *str) +{ + if (fixup_exception(regs, trapnr, error_code, 0)) + return true; + + current->thread.error_code = error_code; + current->thread.trap_nr = trapnr; + + /* + * To be potentially processing a kprobe fault and to trust the result + * from kprobe_running(), we have to be non-preemptible. + */ + if (!preemptible() && kprobe_running() && + kprobe_fault_handler(regs, trapnr)) + return true; + + return notify_die(DIE_GPF, str, regs, error_code, trapnr, SIGSEGV) == NOTIFY_STOP; +} + +static void gp_user_force_sig_segv(struct pt_regs *regs, int trapnr, + unsigned long error_code, const char *str) +{ + current->thread.error_code = error_code; + current->thread.trap_nr = trapnr; + show_signal(current, SIGSEGV, "", str, regs, error_code); + force_sig(SIGSEGV); +} + DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) { char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR; enum kernel_gp_hint hint = GP_NO_HINT; - struct task_struct *tsk; unsigned long gp_addr; - int ret; if (user_mode(regs) && try_fixup_enqcmd_gp()) return; @@ -711,40 +739,18 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) return; } - tsk = current; - if (user_mode(regs)) { if (fixup_iopl_exception(regs)) goto exit; - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0)) goto exit; - show_signal(tsk, SIGSEGV, "", desc, regs, error_code); - force_sig(SIGSEGV); + gp_user_force_sig_segv(regs, X86_TRAP_GP, error_code, desc); goto exit; } - if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) - goto exit; - - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - - /* - * To be potentially processing a kprobe fault and to trust the result - * from kprobe_running(), we have to be non-preemptible. - */ - if (!preemptible() && - kprobe_running() && - kprobe_fault_handler(regs, X86_TRAP_GP)) - goto exit; - - ret = notify_die(DIE_GPF, desc, regs, error_code, X86_TRAP_GP, SIGSEGV); - if (ret == NOTIFY_STOP) + if (gp_try_fixup_and_notify(regs, X86_TRAP_GP, error_code, desc)) goto exit; if (error_code) @@ -892,14 +898,10 @@ sync: } #endif -struct bad_iret_stack { - void *error_entry_ret; - struct pt_regs regs; -}; - -asmlinkage __visible noinstr -struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) +asmlinkage __visible noinstr struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs) { + struct pt_regs tmp, *new_stack; + /* * This is called from entry_64.S early in handling a fault * caused by a bad iret to user mode. To handle the fault @@ -908,19 +910,18 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) * just below the IRET frame) and we want to pretend that the * exception came from the IRET target. */ - struct bad_iret_stack tmp, *new_stack = - (struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; + new_stack = (struct pt_regs *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the temporary storage. */ - __memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); + __memcpy(&tmp.ip, (void *)bad_regs->sp, 5*8); /* Copy the remainder of the stack from the current stack. */ - __memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); + __memcpy(&tmp, bad_regs, offsetof(struct pt_regs, ip)); /* Update the entry stack */ __memcpy(new_stack, &tmp, sizeof(tmp)); - BUG_ON(!user_mode(&new_stack->regs)); + BUG_ON(!user_mode(new_stack)); return new_stack; } #endif @@ -1343,6 +1344,91 @@ DEFINE_IDTENTRY(exc_device_not_available) } } +#ifdef CONFIG_INTEL_TDX_GUEST + +#define VE_FAULT_STR "VE fault" + +static void ve_raise_fault(struct pt_regs *regs, long error_code) +{ + if (user_mode(regs)) { + gp_user_force_sig_segv(regs, X86_TRAP_VE, error_code, VE_FAULT_STR); + return; + } + + if (gp_try_fixup_and_notify(regs, X86_TRAP_VE, error_code, VE_FAULT_STR)) + return; + + die_addr(VE_FAULT_STR, regs, error_code, 0); +} + +/* + * Virtualization Exceptions (#VE) are delivered to TDX guests due to + * specific guest actions which may happen in either user space or the + * kernel: + * + * * Specific instructions (WBINVD, for example) + * * Specific MSR accesses + * * Specific CPUID leaf accesses + * * Access to specific guest physical addresses + * + * In the settings that Linux will run in, virtualization exceptions are + * never generated on accesses to normal, TD-private memory that has been + * accepted (by BIOS or with tdx_enc_status_changed()). + * + * Syscall entry code has a critical window where the kernel stack is not + * yet set up. Any exception in this window leads to hard to debug issues + * and can be exploited for privilege escalation. Exceptions in the NMI + * entry code also cause issues. Returning from the exception handler with + * IRET will re-enable NMIs and nested NMI will corrupt the NMI stack. + * + * For these reasons, the kernel avoids #VEs during the syscall gap and + * the NMI entry code. Entry code paths do not access TD-shared memory, + * MMIO regions, use #VE triggering MSRs, instructions, or CPUID leaves + * that might generate #VE. VMM can remove memory from TD at any point, + * but access to unaccepted (or missing) private memory leads to VM + * termination, not to #VE. + * + * Similarly to page faults and breakpoints, #VEs are allowed in NMI + * handlers once the kernel is ready to deal with nested NMIs. + * + * During #VE delivery, all interrupts, including NMIs, are blocked until + * TDGETVEINFO is called. It prevents #VE nesting until the kernel reads + * the VE info. + * + * If a guest kernel action which would normally cause a #VE occurs in + * the interrupt-disabled region before TDGETVEINFO, a #DF (fault + * exception) is delivered to the guest which will result in an oops. + * + * The entry code has been audited carefully for following these expectations. + * Changes in the entry code have to be audited for correctness vs. this + * aspect. Similarly to #PF, #VE in these places will expose kernel to + * privilege escalation or may lead to random crashes. + */ +DEFINE_IDTENTRY(exc_virtualization_exception) +{ + struct ve_info ve; + + /* + * NMIs/Machine-checks/Interrupts will be in a disabled state + * till TDGETVEINFO TDCALL is executed. This ensures that VE + * info cannot be overwritten by a nested #VE. + */ + tdx_get_ve_info(&ve); + + cond_local_irq_enable(regs); + + /* + * If tdx_handle_virt_exception() could not process + * it successfully, treat it as #GP(0) and handle it. + */ + if (!tdx_handle_virt_exception(regs, &ve)) + ve_raise_fault(regs, 0); + + cond_local_irq_disable(regs); +} + +#endif + #ifdef CONFIG_X86_32 DEFINE_IDTENTRY_SW(iret_error) { diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 794fdef2501a..38185aedf7d1 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -339,11 +339,11 @@ static bool stack_access_ok(struct unwind_state *state, unsigned long _addr, struct stack_info *info = &state->stack_info; void *addr = (void *)_addr; - if (!on_stack(info, addr, len) && - (get_stack_info(addr, state->task, info, &state->stack_mask))) - return false; + if (on_stack(info, addr, len)) + return true; - return true; + return !get_stack_info(addr, state->task, info, &state->stack_mask) && + on_stack(info, addr, len); } static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b24ca7f4ed7c..de6d44e07e34 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -19,6 +19,7 @@ #include <asm/user.h> #include <asm/fpu/xstate.h> #include <asm/sgx.h> +#include <asm/cpuid.h> #include "cpuid.h" #include "lapic.h" #include "mmu.h" @@ -744,24 +745,8 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - switch (function) { - case 4: - case 7: - case 0xb: - case 0xd: - case 0xf: - case 0x10: - case 0x12: - case 0x14: - case 0x17: - case 0x18: - case 0x1d: - case 0x1e: - case 0x1f: - case 0x8000001d: + if (cpuid_function_is_indexed(function)) entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - break; - } return entry; } @@ -887,6 +872,11 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) union cpuid10_eax eax; union cpuid10_edx edx; + if (!static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + perf_get_x86_pmu_capability(&cap); /* @@ -1085,12 +1075,21 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) case 0x80000000: entry->eax = min(entry->eax, 0x80000021); /* - * Serializing LFENCE is reported in a multitude of ways, - * and NullSegClearsBase is not reported in CPUID on Zen2; - * help userspace by providing the CPUID leaf ourselves. + * Serializing LFENCE is reported in a multitude of ways, and + * NullSegClearsBase is not reported in CPUID on Zen2; help + * userspace by providing the CPUID leaf ourselves. + * + * However, only do it if the host has CPUID leaf 0x8000001d. + * QEMU thinks that it can query the host blindly for that + * CPUID leaf if KVM reports that it supports 0x8000001d or + * above. The processor merrily returns values from the + * highest Intel leaf which QEMU tries to use as the guest's + * 0x8000001d. Even worse, this can result in an infinite + * loop if said highest leaf has no subleaves indexed by ECX. */ - if (static_cpu_has(X86_FEATURE_LFENCE_RDTSC) - || !static_cpu_has_bug(X86_BUG_NULL_SEG)) + if (entry->eax >= 0x8000001d && + (static_cpu_has(X86_FEATURE_LFENCE_RDTSC) + || !static_cpu_has_bug(X86_BUG_NULL_SEG))) entry->eax = max(entry->eax, 0x80000021); break; case 0x80000001: diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 123b677111c5..a0702b6be3e8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1135,11 +1135,13 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence)); BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0); + mutex_lock(&hv->hv_lock); + if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || + hv->hv_tsc_page_status == HV_TSC_PAGE_SET || hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET) - return; + goto out_unlock; - mutex_lock(&hv->hv_lock); if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) goto out_unlock; @@ -1201,45 +1203,19 @@ out_unlock: mutex_unlock(&hv->hv_lock); } -void kvm_hv_invalidate_tsc_page(struct kvm *kvm) +void kvm_hv_request_tsc_page_update(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); - u64 gfn; - int idx; - - if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || - hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET || - tsc_page_update_unsafe(hv)) - return; mutex_lock(&hv->hv_lock); - if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) - goto out_unlock; - - /* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */ - if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET) - hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING; + if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET && + !tsc_page_update_unsafe(hv)) + hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED; - gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; - - hv->tsc_ref.tsc_sequence = 0; - - /* - * Take the srcu lock as memslots will be accessed to check the gfn - * cache generation against the memslots generation. - */ - idx = srcu_read_lock(&kvm->srcu); - if (kvm_write_guest(kvm, gfn_to_gpa(gfn), - &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) - hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; - srcu_read_unlock(&kvm->srcu, idx); - -out_unlock: mutex_unlock(&hv->hv_lock); } - static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) { if (!hv_vcpu->enforce_cpuid) @@ -1938,7 +1914,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) struct hv_send_ipi_ex send_ipi_ex; struct hv_send_ipi send_ipi; DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); - unsigned long valid_bank_mask; + u64 valid_bank_mask; u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; u32 vector; bool all_cpus; @@ -1980,7 +1956,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask; all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; - if (hc->var_cnt != bitmap_weight(&valid_bank_mask, 64)) + if (hc->var_cnt != bitmap_weight((unsigned long *)&valid_bank_mask, 64)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (all_cpus) diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index e19c00ee9ab3..da2737f2a956 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -137,7 +137,7 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock); -void kvm_hv_invalidate_tsc_page(struct kvm *kvm); +void kvm_hv_request_tsc_page_update(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e6cae6f22683..a335e7f1f69e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -65,6 +65,30 @@ static __always_inline u64 rsvd_bits(int s, int e) return ((2ULL << (e - s)) - 1) << s; } +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +extern u8 __read_mostly shadow_phys_bits; + +static inline gfn_t kvm_mmu_max_gfn(void) +{ + /* + * Note that this uses the host MAXPHYADDR, not the guest's. + * EPT/NPT cannot support GPAs that would exceed host.MAXPHYADDR; + * assuming KVM is running on bare metal, guest accesses beyond + * host.MAXPHYADDR will hit a #PF(RSVD) and never cause a vmexit + * (either EPT Violation/Misconfig or #NPF), and so KVM will never + * install a SPTE for such addresses. If KVM is running as a VM + * itself, on the other hand, it might see a MAXPHYADDR that is less + * than hardware's real MAXPHYADDR. Using the host MAXPHYADDR + * disallows such SPTEs entirely and simplifies the TDP MMU. + */ + int max_gpa_bits = likely(tdp_enabled) ? shadow_phys_bits : 52; + + return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1; +} + void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 8f19ea752704..45e1573f8f1d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -473,30 +473,6 @@ retry: } #endif -static bool spte_has_volatile_bits(u64 spte) -{ - if (!is_shadow_present_pte(spte)) - return false; - - /* - * Always atomically update spte if it can be updated - * out of mmu-lock, it can ensure dirty bit is not lost, - * also, it can help us to get a stable is_writable_pte() - * to ensure tlb flush is not missed. - */ - if (spte_can_locklessly_be_made_writable(spte) || - is_access_track_spte(spte)) - return true; - - if (spte_ad_enabled(spte)) { - if ((spte & shadow_accessed_mask) == 0 || - (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0)) - return true; - } - - return false; -} - /* Rules for using mmu_spte_set: * Set the sptep from nonpresent to present. * Note: the sptep being assigned *must* be either not present @@ -557,7 +533,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) * we always atomically update it, see the comments in * spte_has_volatile_bits(). */ - if (spte_can_locklessly_be_made_writable(old_spte) && + if (is_mmu_writable_spte(old_spte) && !is_writable_pte(new_spte)) flush = true; @@ -591,7 +567,8 @@ static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) u64 old_spte = *sptep; int level = sptep_to_sp(sptep)->role.level; - if (!spte_has_volatile_bits(old_spte)) + if (!is_shadow_present_pte(old_spte) || + !spte_has_volatile_bits(old_spte)) __update_clear_spte_fast(sptep, 0ull); else old_spte = __update_clear_spte_slow(sptep, 0ull); @@ -1187,7 +1164,7 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) u64 spte = *sptep; if (!is_writable_pte(spte) && - !(pt_protect && spte_can_locklessly_be_made_writable(spte))) + !(pt_protect && is_mmu_writable_spte(spte))) return false; rmap_printk("spte %p %llx\n", sptep, *sptep); @@ -2804,8 +2781,12 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, const struct kvm_memory_slot *slot) { unsigned long hva; - pte_t *pte; - int level; + unsigned long flags; + int level = PG_LEVEL_4K; + pgd_t pgd; + p4d_t p4d; + pud_t pud; + pmd_t pmd; if (!PageCompound(pfn_to_page(pfn)) && !kvm_is_zone_device_pfn(pfn)) return PG_LEVEL_4K; @@ -2820,10 +2801,43 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, */ hva = __gfn_to_hva_memslot(slot, gfn); - pte = lookup_address_in_mm(kvm->mm, hva, &level); - if (unlikely(!pte)) - return PG_LEVEL_4K; + /* + * Lookup the mapping level in the current mm. The information + * may become stale soon, but it is safe to use as long as + * 1) mmu_notifier_retry was checked after taking mmu_lock, and + * 2) mmu_lock is taken now. + * + * We still need to disable IRQs to prevent concurrent tear down + * of page tables. + */ + local_irq_save(flags); + + pgd = READ_ONCE(*pgd_offset(kvm->mm, hva)); + if (pgd_none(pgd)) + goto out; + p4d = READ_ONCE(*p4d_offset(&pgd, hva)); + if (p4d_none(p4d) || !p4d_present(p4d)) + goto out; + + pud = READ_ONCE(*pud_offset(&p4d, hva)); + if (pud_none(pud) || !pud_present(pud)) + goto out; + + if (pud_large(pud)) { + level = PG_LEVEL_1G; + goto out; + } + + pmd = READ_ONCE(*pmd_offset(&pud, hva)); + if (pmd_none(pmd) || !pmd_present(pmd)) + goto out; + + if (pmd_large(pmd)) + level = PG_LEVEL_2M; + +out: + local_irq_restore(flags); return level; } @@ -2992,9 +3006,15 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fa /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an - * MMIO SPTE will just be an expensive nop. + * MMIO SPTE will just be an expensive nop. Do not cache MMIO + * whose gfn is greater than host.MAXPHYADDR, any guest that + * generates such gfns is running nested and is being tricked + * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if + * and only if L1's MAXPHYADDR is inaccurate with respect to + * the hardware's). */ - if (unlikely(!shadow_mmio_value)) { + if (unlikely(!shadow_mmio_value) || + unlikely(fault->gfn > kvm_mmu_max_gfn())) { *ret_val = RET_PF_EMULATE; return true; } @@ -3153,8 +3173,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * be removed in the fast path only if the SPTE was * write-protected for dirty-logging or access tracking. */ - if (fault->write && - spte_can_locklessly_be_made_writable(spte)) { + if (fault->write && is_mmu_writable_spte(spte)) { new_spte |= PT_WRITABLE_MASK; /* @@ -5451,14 +5470,16 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) uint i; if (pcid == kvm_get_active_pcid(vcpu)) { - mmu->invlpg(vcpu, gva, mmu->root.hpa); + if (mmu->invlpg) + mmu->invlpg(vcpu, gva, mmu->root.hpa); tlb_flush = true; } for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (VALID_PAGE(mmu->prev_roots[i].hpa) && pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) { - mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); + if (mmu->invlpg) + mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); tlb_flush = true; } } @@ -5646,6 +5667,7 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; int nr_zapped, batch = 0; + bool unstable; restart: list_for_each_entry_safe_reverse(sp, node, @@ -5677,11 +5699,12 @@ restart: goto restart; } - if (__kvm_mmu_prepare_zap_page(kvm, sp, - &kvm->arch.zapped_obsolete_pages, &nr_zapped)) { - batch += nr_zapped; + unstable = __kvm_mmu_prepare_zap_page(kvm, sp, + &kvm->arch.zapped_obsolete_pages, &nr_zapped); + batch += nr_zapped; + + if (unstable) goto restart; - } } /* @@ -6237,12 +6260,24 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) return 0; } -int kvm_mmu_module_init(void) +/* + * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as + * its default value of -1 is technically undefined behavior for a boolean. + */ +void kvm_mmu_x86_module_init(void) { - int ret = -ENOMEM; - if (nx_huge_pages == -1) __set_nx_huge_pages(get_nx_auto_mode()); +} + +/* + * The bulk of the MMU initialization is deferred until the vendor module is + * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need + * to be reset when a potentially different vendor module is loaded. + */ +int kvm_mmu_vendor_module_init(void) +{ + int ret = -ENOMEM; /* * MMU roles use union aliasing which is, generally speaking, an @@ -6290,7 +6325,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu) mmu_free_memory_caches(vcpu); } -void kvm_mmu_module_exit(void) +void kvm_mmu_vendor_module_exit(void) { mmu_destroy_caches(); percpu_counter_destroy(&kvm_total_used_mmu_pages); diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 4739b53c9734..e5c0b6db6f2c 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -90,6 +90,34 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) E820_TYPE_RAM); } +/* + * Returns true if the SPTE has bits that may be set without holding mmu_lock. + * The caller is responsible for checking if the SPTE is shadow-present, and + * for determining whether or not the caller cares about non-leaf SPTEs. + */ +bool spte_has_volatile_bits(u64 spte) +{ + /* + * Always atomically update spte if it can be updated + * out of mmu-lock, it can ensure dirty bit is not lost, + * also, it can help us to get a stable is_writable_pte() + * to ensure tlb flush is not missed. + */ + if (!is_writable_pte(spte) && is_mmu_writable_spte(spte)) + return true; + + if (is_access_track_spte(spte)) + return true; + + if (spte_ad_enabled(spte)) { + if (!(spte & shadow_accessed_mask) || + (is_writable_pte(spte) && !(spte & shadow_dirty_mask))) + return true; + } + + return false; +} + bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 73f12615416f..80ab0f5cff01 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -201,12 +201,6 @@ static inline bool is_removed_spte(u64 spte) */ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; -/* - * The number of non-reserved physical address bits irrespective of features - * that repurpose legal bits, e.g. MKTME. - */ -extern u8 __read_mostly shadow_phys_bits; - static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && @@ -396,7 +390,7 @@ static inline void check_spte_writable_invariants(u64 spte) "kvm: Writable SPTE is not MMU-writable: %llx", spte); } -static inline bool spte_can_locklessly_be_made_writable(u64 spte) +static inline bool is_mmu_writable_spte(u64 spte) { return spte & shadow_mmu_writable_mask; } @@ -410,6 +404,8 @@ static inline u64 get_mmio_spte_generation(u64 spte) return gen; } +bool spte_has_volatile_bits(u64 spte); + bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index b1eaf6ec0e0b..f0af385c56e0 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -6,6 +6,7 @@ #include <linux/kvm_host.h> #include "mmu.h" +#include "spte.h" /* * TDP MMU SPTEs are RCU protected to allow paging structures (non-leaf SPTEs) @@ -17,9 +18,38 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep) { return READ_ONCE(*rcu_dereference(sptep)); } -static inline void kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 val) + +static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte) +{ + return xchg(rcu_dereference(sptep), new_spte); +} + +static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte) +{ + WRITE_ONCE(*rcu_dereference(sptep), new_spte); +} + +static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte, + u64 new_spte, int level) { - WRITE_ONCE(*rcu_dereference(sptep), val); + /* + * Atomically write the SPTE if it is a shadow-present, leaf SPTE with + * volatile bits, i.e. has bits that can be set outside of mmu_lock. + * The Writable bit can be set by KVM's fast page fault handler, and + * Accessed and Dirty bits can be set by the CPU. + * + * Note, non-leaf SPTEs do have Accessed bits and those bits are + * technically volatile, but KVM doesn't consume the Accessed bit of + * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit. This + * logic needs to be reassessed if KVM were to use non-leaf Accessed + * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs. + */ + if (is_shadow_present_pte(old_spte) && is_last_spte(old_spte, level) && + spte_has_volatile_bits(old_spte)) + return kvm_tdp_mmu_write_spte_atomic(sptep, new_spte); + + __kvm_tdp_mmu_write_spte(sptep, new_spte); + return old_spte; } /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d71d177ae6b8..922b06bf4b94 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -51,7 +51,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return; - flush_workqueue(kvm->arch.tdp_mmu_zap_wq); + /* Also waits for any queued work items. */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); @@ -426,9 +426,9 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) tdp_mmu_unlink_sp(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - u64 *sptep = rcu_dereference(pt) + i; + tdp_ptep_t sptep = pt + i; gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); - u64 old_child_spte; + u64 old_spte; if (shared) { /* @@ -440,8 +440,8 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * value to the removed SPTE value. */ for (;;) { - old_child_spte = xchg(sptep, REMOVED_SPTE); - if (!is_removed_spte(old_child_spte)) + old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, REMOVED_SPTE); + if (!is_removed_spte(old_spte)) break; cpu_relax(); } @@ -455,23 +455,43 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * are guarded by the memslots generation, not by being * unreachable. */ - old_child_spte = READ_ONCE(*sptep); - if (!is_shadow_present_pte(old_child_spte)) + old_spte = kvm_tdp_mmu_read_spte(sptep); + if (!is_shadow_present_pte(old_spte)) continue; /* - * Marking the SPTE as a removed SPTE is not - * strictly necessary here as the MMU lock will - * stop other threads from concurrently modifying - * this SPTE. Using the removed SPTE value keeps - * the two branches consistent and simplifies - * the function. + * Use the common helper instead of a raw WRITE_ONCE as + * the SPTE needs to be updated atomically if it can be + * modified by a different vCPU outside of mmu_lock. + * Even though the parent SPTE is !PRESENT, the TLB + * hasn't yet been flushed, and both Intel and AMD + * document that A/D assists can use upper-level PxE + * entries that are cached in the TLB, i.e. the CPU can + * still access the page and mark it dirty. + * + * No retry is needed in the atomic update path as the + * sole concern is dropping a Dirty bit, i.e. no other + * task can zap/remove the SPTE as mmu_lock is held for + * write. Marking the SPTE as a removed SPTE is not + * strictly necessary for the same reason, but using + * the remove SPTE value keeps the shared/exclusive + * paths consistent and allows the handle_changed_spte() + * call below to hardcode the new value to REMOVED_SPTE. + * + * Note, even though dropping a Dirty bit is the only + * scenario where a non-atomic update could result in a + * functional bug, simply checking the Dirty bit isn't + * sufficient as a fast page fault could read the upper + * level SPTE before it is zapped, and then make this + * target SPTE writable, resume the guest, and set the + * Dirty bit between reading the SPTE above and writing + * it here. */ - WRITE_ONCE(*sptep, REMOVED_SPTE); + old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, + REMOVED_SPTE, level); } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, - old_child_spte, REMOVED_SPTE, level, - shared); + old_spte, REMOVED_SPTE, level, shared); } call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -667,14 +687,13 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, KVM_PAGES_PER_HPAGE(iter->level)); /* - * No other thread can overwrite the removed SPTE as they - * must either wait on the MMU lock or use - * tdp_mmu_set_spte_atomic which will not overwrite the - * special removed SPTE value. No bookkeeping is needed - * here since the SPTE is going from non-present - * to non-present. + * No other thread can overwrite the removed SPTE as they must either + * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not + * overwrite the special removed SPTE value. No bookkeeping is needed + * here since the SPTE is going from non-present to non-present. Use + * the raw write helper to avoid an unnecessary check on volatile bits. */ - kvm_tdp_mmu_write_spte(iter->sptep, 0); + __kvm_tdp_mmu_write_spte(iter->sptep, 0); return 0; } @@ -699,10 +718,13 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, * unless performing certain dirty logging operations. * Leaving record_dirty_log unset in that case prevents page * writes from being double counted. + * + * Returns the old SPTE value, which _may_ be different than @old_spte if the + * SPTE had voldatile bits. */ -static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, - u64 old_spte, u64 new_spte, gfn_t gfn, int level, - bool record_acc_track, bool record_dirty_log) +static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, + u64 old_spte, u64 new_spte, gfn_t gfn, int level, + bool record_acc_track, bool record_dirty_log) { lockdep_assert_held_write(&kvm->mmu_lock); @@ -715,7 +737,7 @@ static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, */ WARN_ON(is_removed_spte(old_spte) || is_removed_spte(new_spte)); - kvm_tdp_mmu_write_spte(sptep, new_spte); + old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); @@ -724,6 +746,7 @@ static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, if (record_dirty_log) handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, new_spte, level); + return old_spte; } static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, @@ -732,9 +755,10 @@ static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, { WARN_ON_ONCE(iter->yielded); - __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, iter->old_spte, - new_spte, iter->gfn, iter->level, - record_acc_track, record_dirty_log); + iter->old_spte = __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, + iter->old_spte, new_spte, + iter->gfn, iter->level, + record_acc_track, record_dirty_log); } static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, @@ -815,14 +839,15 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, return iter->yielded; } -static inline gfn_t tdp_mmu_max_gfn_host(void) +static inline gfn_t tdp_mmu_max_gfn_exclusive(void) { /* - * Bound TDP MMU walks at host.MAXPHYADDR, guest accesses beyond that - * will hit a #PF(RSVD) and never hit an EPT Violation/Misconfig / #NPF, - * and so KVM will never install a SPTE for such addresses. + * Bound TDP MMU walks at host.MAXPHYADDR. KVM disallows memslots with + * a gpa range that would exceed the max gfn, and KVM does not create + * MMIO SPTEs for "impossible" gfns, instead sending such accesses down + * the slow emulation path every time. */ - return 1ULL << (shadow_phys_bits - PAGE_SHIFT); + return kvm_mmu_max_gfn() + 1; } static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, @@ -830,7 +855,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - gfn_t end = tdp_mmu_max_gfn_host(); + gfn_t end = tdp_mmu_max_gfn_exclusive(); gfn_t start = 0; for_each_tdp_pte_min_level(iter, root, zap_level, start, end) { @@ -923,7 +948,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - end = min(end, tdp_mmu_max_gfn_host()); + end = min(end, tdp_mmu_max_gfn_exclusive()); lockdep_assert_held_write(&kvm->mmu_lock); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index eca39f56c231..0604bc29f0b8 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -171,9 +171,12 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } -static int cmp_u64(const void *a, const void *b) +static int cmp_u64(const void *pa, const void *pb) { - return *(__u64 *)a - *(__u64 *)b; + u64 a = *(u64 *)pa; + u64 b = *(u64 *)pb; + + return (a > b) - (a < b); } void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 9e66fba1d6a3..22992b049d38 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -138,6 +138,15 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) return sample_period; } +static inline void pmc_update_sample_period(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event || pmc->is_paused) + return; + + perf_event_period(pmc->perf_event, + get_sample_period(pmc, pmc->counter)); +} + void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index a1cf9c31273b..421619540ff9 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -837,7 +837,8 @@ bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) BIT(APICV_INHIBIT_REASON_IRQWIN) | BIT(APICV_INHIBIT_REASON_PIT_REINJ) | BIT(APICV_INHIBIT_REASON_X2APIC) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ); + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | + BIT(APICV_INHIBIT_REASON_SEV); return supported & BIT(reason); } diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 24eb935b6f85..16a5ebb420cf 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -45,6 +45,22 @@ static struct kvm_event_hw_type_mapping amd_event_mapping[] = { [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, }; +/* duplicated from amd_f17h_perfmon_event_map. */ +static struct kvm_event_hw_type_mapping amd_f17h_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x60, 0xff, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x64, 0x09, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0x87, 0x02, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0x87, 0x01, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + +/* amd_pmc_perf_hw_id depends on these being the same size */ +static_assert(ARRAY_SIZE(amd_event_mapping) == + ARRAY_SIZE(amd_f17h_event_mapping)); + static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type) { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); @@ -140,6 +156,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) { + struct kvm_event_hw_type_mapping *event_mapping; u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; @@ -148,15 +165,20 @@ static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) if (WARN_ON(pmc_is_fixed(pmc))) return PERF_COUNT_HW_MAX; + if (guest_cpuid_family(pmc->vcpu) >= 0x17) + event_mapping = amd_f17h_event_mapping; + else + event_mapping = amd_event_mapping; + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) - if (amd_event_mapping[i].eventsel == event_select - && amd_event_mapping[i].unit_mask == unit_mask) + if (event_mapping[i].eventsel == event_select + && event_mapping[i].unit_mask == unit_mask) break; if (i == ARRAY_SIZE(amd_event_mapping)) return PERF_COUNT_HW_MAX; - return amd_event_mapping[i].event_type; + return event_mapping[i].event_type; } /* check if a PMC is enabled by comparing it against global_ctrl bits. Because @@ -257,6 +279,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { pmc->counter += data - pmc_read_counter(pmc); + pmc_update_sample_period(pmc); return 0; } /* MSR_EVNTSELn */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 75fa6dd268f0..636c77ef55fc 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -260,6 +260,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->mirror_vms); + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV); + return 0; e_free: @@ -465,6 +467,7 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages) page_virtual = kmap_atomic(pages[i]); clflush_cache_range(page_virtual, PAGE_SIZE); kunmap_atomic(page_virtual); + cond_resched(); } } @@ -559,12 +562,20 @@ e_unpin: static int sev_es_sync_vmsa(struct vcpu_svm *svm) { - struct vmcb_save_area *save = &svm->vmcb->save; + struct sev_es_save_area *save = svm->sev_es.vmsa; /* Check some debug related fields before encrypting the VMSA */ - if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1)) + if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1)) return -EINVAL; + /* + * SEV-ES will use a VMSA that is pointed to by the VMCB, not + * the traditional VMSA that is part of the VMCB. Copy the + * traditional VMSA as it has been built so far (in prep + * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. + */ + memcpy(save, &svm->vmcb->save, sizeof(svm->vmcb->save)); + /* Sync registgers */ save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX]; save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX]; @@ -592,14 +603,6 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; - /* - * SEV-ES will use a VMSA that is pointed to by the VMCB, not - * the traditional VMSA that is part of the VMCB. Copy the - * traditional VMSA as it has been built so far (in prep - * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. - */ - memcpy(svm->sev_es.vmsa, save, sizeof(*save)); - return 0; } @@ -1591,24 +1594,51 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) atomic_set_release(&src_sev->migration_in_progress, 0); } +/* vCPU mutex subclasses. */ +enum sev_migration_role { + SEV_MIGRATION_SOURCE = 0, + SEV_MIGRATION_TARGET, + SEV_NR_MIGRATION_ROLES, +}; -static int sev_lock_vcpus_for_migration(struct kvm *kvm) +static int sev_lock_vcpus_for_migration(struct kvm *kvm, + enum sev_migration_role role) { struct kvm_vcpu *vcpu; unsigned long i, j; + bool first = true; kvm_for_each_vcpu(i, vcpu, kvm) { - if (mutex_lock_killable(&vcpu->mutex)) + if (mutex_lock_killable_nested(&vcpu->mutex, role)) goto out_unlock; + + if (first) { + /* + * Reset the role to one that avoids colliding with + * the role used for the first vcpu mutex. + */ + role = SEV_NR_MIGRATION_ROLES; + first = false; + } else { + mutex_release(&vcpu->mutex.dep_map, _THIS_IP_); + } } return 0; out_unlock: + + first = true; kvm_for_each_vcpu(j, vcpu, kvm) { if (i == j) break; + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_); + + mutex_unlock(&vcpu->mutex); } return -EINTR; @@ -1618,8 +1648,15 @@ static void sev_unlock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; + bool first = true; kvm_for_each_vcpu(i, vcpu, kvm) { + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, + SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_); + mutex_unlock(&vcpu->mutex); } } @@ -1745,10 +1782,10 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) charged = true; } - ret = sev_lock_vcpus_for_migration(kvm); + ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE); if (ret) goto out_dst_cgroup; - ret = sev_lock_vcpus_for_migration(source_kvm); + ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET); if (ret) goto out_dst_vcpu; @@ -2223,51 +2260,47 @@ int sev_cpu_init(struct svm_cpu_data *sd) * Pages used by hardware to hold guest encrypted state must be flushed before * returning them to the system. */ -static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va, - unsigned long len) +static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { + int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + /* - * If hardware enforced cache coherency for encrypted mappings of the - * same physical page is supported, nothing to do. + * Note! The address must be a kernel address, as regular page walk + * checks are performed by VM_PAGE_FLUSH, i.e. operating on a user + * address is non-deterministic and unsafe. This function deliberately + * takes a pointer to deter passing in a user address. */ - if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) - return; + unsigned long addr = (unsigned long)va; /* - * If the VM Page Flush MSR is supported, use it to flush the page - * (using the page virtual address and the guest ASID). + * If CPU enforced cache coherency for encrypted mappings of the + * same physical page is supported, use CLFLUSHOPT instead. NOTE: cache + * flush is still needed in order to work properly with DMA devices. */ - if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) { - struct kvm_sev_info *sev; - unsigned long va_start; - u64 start, stop; - - /* Align start and stop to page boundaries. */ - va_start = (unsigned long)va; - start = (u64)va_start & PAGE_MASK; - stop = PAGE_ALIGN((u64)va_start + len); - - if (start < stop) { - sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; + if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) { + clflush_cache_range(va, PAGE_SIZE); + return; + } - while (start < stop) { - wrmsrl(MSR_AMD64_VM_PAGE_FLUSH, - start | sev->asid); + /* + * VM Page Flush takes a host virtual address and a guest ASID. Fall + * back to WBINVD if this faults so as not to make any problems worse + * by leaving stale encrypted data in the cache. + */ + if (WARN_ON_ONCE(wrmsrl_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid))) + goto do_wbinvd; - start += PAGE_SIZE; - } + return; - return; - } +do_wbinvd: + wbinvd_on_all_cpus(); +} - WARN(1, "Address overflow, using WBINVD\n"); - } +void sev_guest_memory_reclaimed(struct kvm *kvm) +{ + if (!sev_guest(kvm)) + return; - /* - * Hardware should always have one of the above features, - * but if not, use WBINVD and issue a warning. - */ - WARN_ONCE(1, "Using WBINVD to flush guest memory\n"); wbinvd_on_all_cpus(); } @@ -2281,7 +2314,8 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); if (vcpu->arch.guest_state_protected) - sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE); + sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa); + __free_page(virt_to_page(svm->sev_es.vmsa)); if (svm->sev_es.ghcb_sa_free) @@ -2932,7 +2966,7 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm) sev_enc_bit)); } -void sev_es_prepare_switch_to_guest(struct vmcb_save_area *hostsa) +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) { /* * As an SEV-ES guest, hardware will restore the host state on VMEXIT, diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index bd4c64b362d2..17d334ef5430 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1270,8 +1270,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) */ vmsave(__sme_page_pa(sd->save_area)); if (sev_es_guest(vcpu->kvm)) { - struct vmcb_save_area *hostsa; - hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400); + struct sev_es_save_area *hostsa; + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); sev_es_prepare_switch_to_guest(hostsa); } @@ -3117,8 +3117,8 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) "tr:", save01->tr.selector, save01->tr.attrib, save01->tr.limit, save01->tr.base); - pr_err("cpl: %d efer: %016llx\n", - save->cpl, save->efer); + pr_err("vmpl: %d cpl: %d efer: %016llx\n", + save->vmpl, save->cpl, save->efer); pr_err("%-15s %016llx %-13s %016llx\n", "cr0:", save->cr0, "cr2:", save->cr2); pr_err("%-15s %016llx %-13s %016llx\n", @@ -4620,6 +4620,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_ioctl = sev_mem_enc_ioctl, .mem_enc_register_region = sev_mem_enc_register_region, .mem_enc_unregister_region = sev_mem_enc_unregister_region, + .guest_memory_reclaimed = sev_guest_memory_reclaimed, .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f77a7d2d39dd..2d83845b9032 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -181,7 +181,7 @@ struct svm_nested_state { struct vcpu_sev_es_state { /* SEV-ES support */ - struct vmcb_save_area *vmsa; + struct sev_es_save_area *vmsa; struct ghcb *ghcb; struct kvm_host_map ghcb_map; bool received_first_sipi; @@ -609,6 +609,8 @@ int sev_mem_enc_unregister_region(struct kvm *kvm, struct kvm_enc_region *range); int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd); int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd); +void sev_guest_memory_reclaimed(struct kvm *kvm); + void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); @@ -620,7 +622,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_vcpu_reset(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); -void sev_es_prepare_switch_to_guest(struct vmcb_save_area *hostsa); +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); void sev_es_unmap_ghcb(struct vcpu_svm *svm); /* vmenter.S */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f18744f7ff82..856c87563883 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4618,6 +4618,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); } + if (vmx->nested.update_vmcs01_apicv_status) { + vmx->nested.update_vmcs01_apicv_status = false; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } + if ((vm_exit_reason != -1) && (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) vmx->nested.need_vmcs12_to_shadow_sync = true; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index bc3f8512bb64..b82b6709d7a8 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -431,15 +431,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 04d170c4b61e..610355b9ccce 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4174,6 +4174,11 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (is_guest_mode(vcpu)) { + vmx->nested.update_vmcs01_apicv_status = true; + return; + } + pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); if (cpu_has_secondary_exec_ctrls()) { if (kvm_vcpu_apicv_active(vcpu)) @@ -5467,7 +5472,7 @@ static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); return vmx->emulation_required && !vmx->rmode.vm86_active && - vcpu->arch.exception.pending; + (vcpu->arch.exception.pending || vcpu->arch.exception.injected); } static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 9c6bfcd84008..b98c7e96697a 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -183,6 +183,7 @@ struct nested_vmx { bool change_vmcs01_virtual_apic_mode; bool reload_vmcs01_apic_access_page; bool update_vmcs01_cpu_dirty_logging; + bool update_vmcs01_apicv_status; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0c0ca599a353..4790f0d7d40b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2901,7 +2901,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) static void kvm_update_masterclock(struct kvm *kvm) { - kvm_hv_invalidate_tsc_page(kvm); + kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); kvm_end_pvclock_update(kvm); @@ -3113,8 +3113,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_set) kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); - if (!v->vcpu_idx) - kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); + kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } @@ -6241,7 +6240,7 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) if (data.flags & ~KVM_CLOCK_VALID_FLAGS) return -EINVAL; - kvm_hv_invalidate_tsc_page(kvm); + kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); @@ -8926,7 +8925,7 @@ int kvm_arch_init(void *opaque) } kvm_nr_uret_msrs = 0; - r = kvm_mmu_module_init(); + r = kvm_mmu_vendor_module_init(); if (r) goto out_free_percpu; @@ -8974,7 +8973,7 @@ void kvm_arch_exit(void) cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops.hardware_enable = NULL; - kvm_mmu_module_exit(); + kvm_mmu_vendor_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); #ifdef CONFIG_KVM_XEN @@ -9112,7 +9111,7 @@ static void kvm_apicv_init(struct kvm *kvm) if (!enable_apicv) set_or_clear_apicv_inhibit(inhibits, - APICV_INHIBIT_REASON_ABSENT, true); + APICV_INHIBIT_REASON_DISABLE, true); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) @@ -9890,6 +9889,11 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); } +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) +{ + static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm); +} + static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) @@ -10016,12 +10020,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; + vcpu->run->system_event.ndata = 0; r = 0; goto out; } if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET; + vcpu->run->system_event.ndata = 0; r = 0; goto out; } @@ -10098,7 +10104,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* Store vcpu->apicv_active before vcpu->mode. */ smp_store_release(&vcpu->mode, IN_GUEST_MODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* * 1) We should set ->mode before checking ->requests. Please see @@ -10129,7 +10135,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) smp_wmb(); local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); r = 1; goto cancel_injection; } @@ -10255,7 +10261,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); /* * Profile KVM exit RIPs: @@ -10285,7 +10291,7 @@ out: } /* Called within kvm->srcu read side. */ -static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) +static inline int vcpu_block(struct kvm_vcpu *vcpu) { bool hv_timer; @@ -10301,12 +10307,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) if (hv_timer) kvm_lapic_switch_to_sw_timer(vcpu); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) kvm_vcpu_halt(vcpu); else kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); @@ -10348,7 +10354,6 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) static int vcpu_run(struct kvm_vcpu *vcpu) { int r; - struct kvm *kvm = vcpu->kvm; vcpu->arch.l1tf_flush_l1d = true; @@ -10356,7 +10361,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { - r = vcpu_block(kvm, vcpu); + r = vcpu_block(vcpu); } if (r <= 0) @@ -10375,9 +10380,9 @@ static int vcpu_run(struct kvm_vcpu *vcpu) } if (__xfer_to_guest_mode_work_pending()) { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); r = xfer_to_guest_mode_handle_work(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (r) return r; } @@ -10388,12 +10393,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { - int r; - - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - return r; + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); } static int complete_emulated_pio(struct kvm_vcpu *vcpu) @@ -10485,7 +10485,6 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - struct kvm *kvm = vcpu->kvm; int r; vcpu_load(vcpu); @@ -10493,7 +10492,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -10505,9 +10504,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (kvm_apic_accept_events(vcpu) < 0) { r = 0; @@ -10568,7 +10567,7 @@ out: if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); @@ -10986,6 +10985,9 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) struct kvm_vcpu *vcpu; unsigned long i; + if (!enable_apicv) + return; + down_write(&kvm->arch.apicv_update_lock); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -11197,8 +11199,21 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; - if (kvm_apicv_activated(vcpu->kvm)) + + /* + * Defer evaluating inhibits until the vCPU is first run, as + * this vCPU will not get notified of any changes until this + * vCPU is visible to other vCPUs (marked online and added to + * the set of vCPUs). Opportunistically mark APICv active as + * VMX in particularly is highly unlikely to have inhibits. + * Ignore the current per-VM APICv state so that vCPU creation + * is guaranteed to run with a deterministic value, the request + * will ensure the vCPU gets the correct state before VM-Entry. + */ + if (enable_apicv) { vcpu->arch.apicv_active = true; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } } else static_branch_inc(&kvm_has_noapic_vcpu); @@ -11996,8 +12011,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { + if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); + } if (change == KVM_MR_FLAGS_ONLY) memcpy(&new->arch, &old->arch, sizeof(old->arch)); @@ -12986,3 +13005,19 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); + +static int __init kvm_x86_init(void) +{ + kvm_mmu_x86_module_init(); + return 0; +} +module_init(kvm_x86_init); + +static void __exit kvm_x86_exit(void) +{ + /* + * If module_init() is implemented, module_exit() must also be + * implemented to allow module unload. + */ +} +module_exit(kvm_x86_exit); diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 8ca5ecf16dc4..9dec1b38a98f 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -53,12 +53,12 @@ SYM_FUNC_START(copy_user_generic_unrolled) ASM_STAC cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .Lcopy_user_short_string_bytes ALIGN_DESTINATION movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz .L_copy_short_string + jz copy_user_short_string 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -79,37 +79,11 @@ SYM_FUNC_START(copy_user_generic_unrolled) leaq 64(%rdi),%rdi decl %ecx jnz 1b -.L_copy_short_string: - movl %edx,%ecx - andl $7,%edx - shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movq %r8,(%rdi) - leaq 8(%rsi),%rsi - leaq 8(%rdi),%rdi - decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f - movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 21b -23: xor %eax,%eax - ASM_CLAC - RET + jmp copy_user_short_string 30: shll $6,%ecx addl %ecx,%edx - jmp 60f -40: leal (%rdx,%rcx,8),%edx - jmp 60f -50: movl %ecx,%edx -60: jmp .Lcopy_user_handle_tail /* ecx is zerorest also */ + jmp .Lcopy_user_handle_tail _ASM_EXTABLE_CPY(1b, 30b) _ASM_EXTABLE_CPY(2b, 30b) @@ -127,10 +101,6 @@ SYM_FUNC_START(copy_user_generic_unrolled) _ASM_EXTABLE_CPY(14b, 30b) _ASM_EXTABLE_CPY(15b, 30b) _ASM_EXTABLE_CPY(16b, 30b) - _ASM_EXTABLE_CPY(18b, 40b) - _ASM_EXTABLE_CPY(19b, 40b) - _ASM_EXTABLE_CPY(21b, 50b) - _ASM_EXTABLE_CPY(22b, 50b) SYM_FUNC_END(copy_user_generic_unrolled) EXPORT_SYMBOL(copy_user_generic_unrolled) @@ -191,7 +161,7 @@ EXPORT_SYMBOL(copy_user_generic_string) SYM_FUNC_START(copy_user_enhanced_fast_string) ASM_STAC /* CPUs without FSRM should avoid rep movsb for short copies */ - ALTERNATIVE "cmpl $64, %edx; jb .L_copy_short_string", "", X86_FEATURE_FSRM + ALTERNATIVE "cmpl $64, %edx; jb copy_user_short_string", "", X86_FEATURE_FSRM movl %edx,%ecx 1: rep movsb xorl %eax,%eax @@ -244,6 +214,53 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) SYM_CODE_END(.Lcopy_user_handle_tail) /* + * Finish memcpy of less than 64 bytes. #AC should already be set. + * + * Input: + * rdi destination + * rsi source + * rdx count (< 64) + * + * Output: + * eax uncopied bytes or 0 if successful. + */ +SYM_CODE_START_LOCAL(copy_user_short_string) + movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz .Lcopy_user_short_string_bytes +18: movq (%rsi),%r8 +19: movq %r8,(%rdi) + leaq 8(%rsi),%rsi + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +.Lcopy_user_short_string_bytes: + andl %edx,%edx + jz 23f + movl %edx,%ecx +21: movb (%rsi),%al +22: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 21b +23: xor %eax,%eax + ASM_CLAC + RET + +40: leal (%rdx,%rcx,8),%edx + jmp 60f +50: movl %ecx,%edx /* ecx is zerorest also */ +60: jmp .Lcopy_user_handle_tail + + _ASM_EXTABLE_CPY(18b, 40b) + _ASM_EXTABLE_CPY(19b, 40b) + _ASM_EXTABLE_CPY(21b, 50b) + _ASM_EXTABLE_CPY(22b, 50b) +SYM_CODE_END(copy_user_short_string) + +/* * copy_user_nocache - Uncached memory copy with exception handling * This will force destination out of cache for more performance. * diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index 2b3eb8c948a3..a58f451a7dd3 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -11,7 +11,7 @@ #include <asm/msr.h> #include <asm/archrandom.h> #include <asm/e820/api.h> -#include <asm/io.h> +#include <asm/shared/io.h> /* * When built for the regular kernel, several functions need to be stubbed out diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index ecb2049c1273..b7dfd60243b7 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -48,6 +48,7 @@ SYM_FUNC_START(__put_user_1) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL) + ENDBR ASM_STAC 1: movb %al,(%_ASM_CX) xor %ecx,%ecx @@ -62,6 +63,7 @@ SYM_FUNC_START(__put_user_2) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL) + ENDBR ASM_STAC 2: movw %ax,(%_ASM_CX) xor %ecx,%ecx @@ -76,6 +78,7 @@ SYM_FUNC_START(__put_user_4) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL) + ENDBR ASM_STAC 3: movl %eax,(%_ASM_CX) xor %ecx,%ecx @@ -90,6 +93,7 @@ SYM_FUNC_START(__put_user_8) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL) + ENDBR ASM_STAC 4: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 5f87bab4fb8d..b2b2366885a2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -31,6 +31,7 @@ .align RETPOLINE_THUNK_SIZE SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ @@ -55,7 +56,6 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) .align RETPOLINE_THUNK_SIZE SYM_CODE_START(__x86_indirect_thunk_array) - ANNOTATE_NOENDBR // apply_retpolines #define GEN(reg) THUNK reg #include <asm/GEN-for-each-reg.h> diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0402a749f3a0..0ae6cf804197 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -119,7 +119,7 @@ void __memcpy_flushcache(void *_dst, const void *_src, size_t size) /* cache copy and flush to align dest */ if (!IS_ALIGNED(dest, 8)) { - unsigned len = min_t(unsigned, size, ALIGN(dest, 8) - dest); + size_t len = min_t(size_t, size, ALIGN(dest, 8) - dest); memcpy((void *) dest, (void *) source, len); clean_cache_range((void *) dest, len); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index fe3d3061fc11..d957dc15b371 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -20,13 +20,12 @@ CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ - pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o + pgtable.o physaddr.o tlb.o cpu_entry_area.o maccess.o obj-y += pat/ # Make sure __phys_addr has no stackprotector CFLAGS_physaddr.o := -fno-stack-protector -CFLAGS_setup_nx.o := -fno-stack-protector CFLAGS_mem_encrypt_identity.o := -fno-stack-protector CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 96d34ebb20a9..61d0ab154f96 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -110,7 +110,6 @@ int force_personality32; /* * noexec32=on|off * Control non executable heap for 32bit processes. - * To control the stack too use noexec=off * * on PROT_READ does not imply PROT_EXEC for 32-bit processes (default) * off PROT_READ implies PROT_EXEC @@ -902,6 +901,8 @@ static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end) { + const unsigned long page = ALIGN_DOWN(start, PMD_SIZE); + vmemmap_flush_unused_pmd(); /* @@ -914,8 +915,7 @@ static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long * Mark with PAGE_UNUSED the unused parts of the new memmap range */ if (!IS_ALIGNED(start, PMD_SIZE)) - memset((void *)start, PAGE_UNUSED, - start - ALIGN_DOWN(start, PMD_SIZE)); + memset((void *)page, PAGE_UNUSED, start - page); /* * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 17a492c27306..1ad0228f8ceb 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -242,10 +242,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, * If the page being mapped is in memory and SEV is active then * make sure the memory encryption attribute is enabled in the * resulting mapping. + * In TDX guests, memory is marked private by default. If encryption + * is not requested (using encrypted), explicitly set decrypt + * attribute in all IOREMAPPED memory. */ prot = PAGE_KERNEL_IO; if ((io_desc.flags & IORES_MAP_ENCRYPTED) || encrypted) prot = pgprot_encrypted(prot); + else + prot = pgprot_decrypted(prot); switch (pcm) { case _PAGE_CACHE_MODE_UC: diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 50d209939c66..11350e2fd736 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -42,7 +42,14 @@ bool force_dma_unencrypted(struct device *dev) static void print_mem_encrypt_feature_info(void) { - pr_info("AMD Memory Encryption Features active:"); + pr_info("Memory Encryption Features active:"); + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + pr_cont(" Intel TDX\n"); + return; + } + + pr_cont(" AMD"); /* Secure Memory Encryption */ if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { @@ -62,6 +69,10 @@ static void print_mem_encrypt_feature_info(void) if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) pr_cont(" SEV-ES"); + /* Secure Nested Paging */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + pr_cont(" SEV-SNP"); + pr_cont("\n"); } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 6169053c2854..d3c88d9ef8d6 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -31,6 +31,7 @@ #include <asm/processor-flags.h> #include <asm/msr.h> #include <asm/cmdline.h> +#include <asm/sev.h> #include "mm_internal.h" @@ -48,6 +49,36 @@ EXPORT_SYMBOL(sme_me_mask); static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE); /* + * SNP-specific routine which needs to additionally change the page state from + * private to shared before copying the data from the source to destination and + * restore after the copy. + */ +static inline void __init snp_memcpy(void *dst, void *src, size_t sz, + unsigned long paddr, bool decrypt) +{ + unsigned long npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + + if (decrypt) { + /* + * @paddr needs to be accessed decrypted, mark the page shared in + * the RMP table before copying it. + */ + early_snp_set_memory_shared((unsigned long)__va(paddr), paddr, npages); + + memcpy(dst, src, sz); + + /* Restore the page state after the memcpy. */ + early_snp_set_memory_private((unsigned long)__va(paddr), paddr, npages); + } else { + /* + * @paddr need to be accessed encrypted, no need for the page state + * change. + */ + memcpy(dst, src, sz); + } +} + +/* * This routine does not change the underlying encryption setting of the * page(s) that map this memory. It assumes that eventually the memory is * meant to be accessed as either encrypted or decrypted but the contents @@ -95,8 +126,13 @@ static void __init __sme_early_enc_dec(resource_size_t paddr, * Use a temporary buffer, of cache-line multiple size, to * avoid data corruption as documented in the APM. */ - memcpy(sme_early_buffer, src, len); - memcpy(dst, sme_early_buffer, len); + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) { + snp_memcpy(sme_early_buffer, src, len, paddr, enc); + snp_memcpy(dst, sme_early_buffer, len, paddr, !enc); + } else { + memcpy(sme_early_buffer, src, len); + memcpy(dst, sme_early_buffer, len); + } early_memunmap(dst, len); early_memunmap(src, len); @@ -280,11 +316,24 @@ static void enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) static void amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc) { + /* + * To maintain the security guarantees of SEV-SNP guests, make sure + * to invalidate the memory before encryption attribute is cleared. + */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc) + snp_set_memory_shared(vaddr, npages); } /* Return true unconditionally: return value doesn't matter for the SEV side */ static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc) { + /* + * After memory is mapped encrypted in the page table, validate it + * so that it is consistent with the page table updates. + */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && enc) + snp_set_memory_private(vaddr, npages); + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) enc_dec_hypercall(vaddr, npages, enc); @@ -322,14 +371,28 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) clflush_cache_range(__va(pa), size); /* Encrypt/decrypt the contents in-place */ - if (enc) + if (enc) { sme_early_encrypt(pa, size); - else + } else { sme_early_decrypt(pa, size); + /* + * ON SNP, the page state in the RMP table must happen + * before the page table updates. + */ + early_snp_set_memory_shared((unsigned long)__va(pa), pa, 1); + } + /* Change the page encryption mask. */ new_pte = pfn_pte(pfn, new_prot); set_pte_atomic(kpte, new_pte); + + /* + * If page is set encrypted in the page table, then update the RMP table to + * add this page as private. + */ + if (enc) + early_snp_set_memory_private((unsigned long)__va(pa), pa, 1); } static int __init early_set_memory_enc_dec(unsigned long vaddr, diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index b43bc24d2bb6..f415498d3175 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -45,6 +45,7 @@ #include <asm/sections.h> #include <asm/cmdline.h> #include <asm/coco.h> +#include <asm/sev.h> #include "mm_internal.h" @@ -509,8 +510,11 @@ void __init sme_enable(struct boot_params *bp) bool active_by_default; unsigned long me_mask; char buffer[16]; + bool snp; u64 msr; + snp = snp_init(bp); + /* Check for the SME/SEV support leaf */ eax = 0x80000000; ecx = 0; @@ -542,6 +546,10 @@ void __init sme_enable(struct boot_params *bp) sev_status = __rdmsr(MSR_AMD64_SEV); feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ + if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + snp_abort(); + /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { /* diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index abf5ed76e4b7..0656db33574d 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -638,17 +638,6 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) } EXPORT_SYMBOL_GPL(lookup_address); -/* - * Lookup the page table entry for a virtual address in a given mm. Return a - * pointer to the entry and the level of the mapping. - */ -pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, - unsigned int *level) -{ - return lookup_address_in_pgd(pgd_offset(mm, address), address, level); -} -EXPORT_SYMBOL_GPL(lookup_address_in_mm); - static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, unsigned int *level) { diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c deleted file mode 100644 index ed5667f5169f..000000000000 --- a/arch/x86/mm/setup_nx.c +++ /dev/null @@ -1,62 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/spinlock.h> -#include <linux/errno.h> -#include <linux/init.h> -#include <linux/pgtable.h> - -#include <asm/proto.h> -#include <asm/cpufeature.h> - -static int disable_nx; - -/* - * noexec = on|off - * - * Control non-executable mappings for processes. - * - * on Enable - * off Disable - */ -static int __init noexec_setup(char *str) -{ - if (!str) - return -EINVAL; - if (!strncmp(str, "on", 2)) { - disable_nx = 0; - } else if (!strncmp(str, "off", 3)) { - disable_nx = 1; - } - x86_configure_nx(); - return 0; -} -early_param("noexec", noexec_setup); - -void x86_configure_nx(void) -{ - if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) - __supported_pte_mask |= _PAGE_NX; - else - __supported_pte_mask &= ~_PAGE_NX; -} - -void __init x86_report_nx(void) -{ - if (!boot_cpu_has(X86_FEATURE_NX)) { - printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " - "missing in CPU!\n"); - } else { -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) - if (disable_nx) { - printk(KERN_INFO "NX (Execute Disable) protection: " - "disabled by kernel command line option\n"); - } else { - printk(KERN_INFO "NX (Execute Disable) protection: " - "active\n"); - } -#else - /* 32bit non-PAE kernel, NX cannot be used */ - printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " - "cannot be enabled: non-PAE kernel!\n"); -#endif - } -} diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6eb4d91d5365..d400b6d9d246 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -855,13 +855,11 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu) +static bool tlb_is_not_lazy(int cpu, void *data) { return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); } -static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared); @@ -890,36 +888,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, * up on the new contents of what used to be page tables, while * doing a speculative memory access. */ - if (info->freed_tables) { + if (info->freed_tables) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); - } else { - /* - * Although we could have used on_each_cpu_cond_mask(), - * open-coding it has performance advantages, as it eliminates - * the need for indirect calls or retpolines. In addition, it - * allows to use a designated cpumask for evaluating the - * condition, instead of allocating one. - * - * This code works under the assumption that there are no nested - * TLB flushes, an assumption that is already made in - * flush_tlb_mm_range(). - * - * cond_cpumask is logically a stack-local variable, but it is - * more efficient to have it off the stack and not to allocate - * it on demand. Preemption is disabled and this code is - * non-reentrant. - */ - struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask); - int cpu; - - cpumask_clear(cond_cpumask); - - for_each_cpu(cpu, cpumask) { - if (tlb_is_not_lazy(cpu)) - __cpumask_set_cpu(cpu, cond_cpumask); - } - on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true); - } + else + on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + (void *)info, 1, cpumask); } void flush_tlb_multi(const struct cpumask *cpumask, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8fe35ed11fd6..16b6efacf7c6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,6 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else #endif diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 97b63e35e152..a498b847d740 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -25,6 +25,8 @@ #define PIRQ_SIGNATURE (('$' << 0) + ('P' << 8) + ('I' << 16) + ('R' << 24)) #define PIRQ_VERSION 0x0100 +#define IRT_SIGNATURE (('$' << 0) + ('I' << 8) + ('R' << 16) + ('T' << 24)) + static int broken_hp_bios_irq9; static int acer_tm360_irqrouting; @@ -68,30 +70,99 @@ void (*pcibios_disable_irq)(struct pci_dev *dev) = pirq_disable_irq; * and perform checksum verification. */ -static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr) +static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr, + u8 *limit) { struct irq_routing_table *rt; int i; u8 sum; - rt = (struct irq_routing_table *) addr; + rt = (struct irq_routing_table *)addr; if (rt->signature != PIRQ_SIGNATURE || rt->version != PIRQ_VERSION || rt->size % 16 || - rt->size < sizeof(struct irq_routing_table)) + rt->size < sizeof(struct irq_routing_table) || + (limit && rt->size > limit - addr)) return NULL; sum = 0; for (i = 0; i < rt->size; i++) sum += addr[i]; if (!sum) { - DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%p\n", - rt); + DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%lx\n", + __pa(rt)); return rt; } return NULL; } +/* + * Handle the $IRT PCI IRQ Routing Table format used by AMI for its BCP + * (BIOS Configuration Program) external tool meant for tweaking BIOS + * structures without the need to rebuild it from sources. The $IRT + * format has been invented by AMI before Microsoft has come up with its + * $PIR format and a $IRT table is therefore there in some systems that + * lack a $PIR table. + * + * It uses the same PCI BIOS 2.1 format for interrupt routing entries + * themselves but has a different simpler header prepended instead, + * occupying 8 bytes, where a `$IRT' signature is followed by one byte + * specifying the total number of interrupt routing entries allocated in + * the table, then one byte specifying the actual number of entries used + * (which the BCP tool can take advantage of when modifying the table), + * and finally a 16-bit word giving the IRQs devoted exclusively to PCI. + * Unlike with the $PIR table there is no alignment guarantee. + * + * Given the similarity of the two formats the $IRT one is trivial to + * convert to the $PIR one, which we do here, except that obviously we + * have no information as to the router device to use, but we can handle + * it by matching PCI device IDs actually seen on the bus against ones + * that our individual routers recognise. + * + * Reportedly there is another $IRT table format where a 16-bit word + * follows the header instead that points to interrupt routing entries + * in a $PIR table provided elsewhere. In that case this code will not + * be reached though as the $PIR table will have been chosen instead. + */ +static inline struct irq_routing_table *pirq_convert_irt_table(u8 *addr, + u8 *limit) +{ + struct irt_routing_table *ir; + struct irq_routing_table *rt; + u16 size; + u8 sum; + int i; + + ir = (struct irt_routing_table *)addr; + if (ir->signature != IRT_SIGNATURE || !ir->used || ir->size < ir->used) + return NULL; + + size = sizeof(*ir) + ir->used * sizeof(ir->slots[0]); + if (size > limit - addr) + return NULL; + + DBG(KERN_DEBUG "PCI: $IRT Interrupt Routing Table found at 0x%lx\n", + __pa(ir)); + size = sizeof(*rt) + ir->used * sizeof(rt->slots[0]); + rt = kzalloc(size, GFP_KERNEL); + if (!rt) + return NULL; + + rt->signature = PIRQ_SIGNATURE; + rt->version = PIRQ_VERSION; + rt->size = size; + rt->exclusive_irqs = ir->exclusive_irqs; + for (i = 0; i < ir->used; i++) + rt->slots[i] = ir->slots[i]; + + addr = (u8 *)rt; + sum = 0; + for (i = 0; i < size; i++) + sum += addr[i]; + rt->checksum = -sum; + + return rt; +} /* * Search 0xf0000 -- 0xfffff for the PCI IRQ Routing Table. @@ -99,17 +170,29 @@ static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr) static struct irq_routing_table * __init pirq_find_routing_table(void) { + u8 * const bios_start = (u8 *)__va(0xf0000); + u8 * const bios_end = (u8 *)__va(0x100000); u8 *addr; struct irq_routing_table *rt; if (pirq_table_addr) { - rt = pirq_check_routing_table((u8 *) __va(pirq_table_addr)); + rt = pirq_check_routing_table((u8 *)__va(pirq_table_addr), + NULL); if (rt) return rt; printk(KERN_WARNING "PCI: PIRQ table NOT found at pirqaddr\n"); } - for (addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) { - rt = pirq_check_routing_table(addr); + for (addr = bios_start; + addr < bios_end - sizeof(struct irq_routing_table); + addr += 16) { + rt = pirq_check_routing_table(addr, bios_end); + if (rt) + return rt; + } + for (addr = bios_start; + addr < bios_end - sizeof(struct irt_routing_table); + addr++) { + rt = pirq_convert_irt_table(addr, bios_end); if (rt) return rt; } @@ -135,7 +218,8 @@ static void __init pirq_peer_trick(void) #ifdef DEBUG { int j; - DBG(KERN_DEBUG "%02x:%02x slot=%02x", e->bus, e->devfn/8, e->slot); + DBG(KERN_DEBUG "%02x:%02x.%x slot=%02x", + e->bus, e->devfn / 8, e->devfn % 8, e->slot); for (j = 0; j < 4; j++) DBG(" %d:%02x/%04x", j, e->irq[j].link, e->irq[j].bitmap); DBG("\n"); @@ -253,6 +337,15 @@ static void write_pc_conf_nybble(u8 base, u8 index, u8 val) pc_conf_set(reg, x); } +/* + * FinALi pirq rules are as follows: + * + * - bit 0 selects between INTx Routing Table Mapping Registers, + * + * - bit 3 selects the nibble within the INTx Routing Table Mapping Register, + * + * - bits 7:4 map to bits 3:0 of the PCI INTx Sensitivity Register. + */ static int pirq_finali_get(struct pci_dev *router, struct pci_dev *dev, int pirq) { @@ -260,11 +353,13 @@ static int pirq_finali_get(struct pci_dev *router, struct pci_dev *dev, 0, 9, 3, 10, 4, 5, 7, 6, 0, 11, 0, 12, 0, 14, 0, 15 }; unsigned long flags; + u8 index; u8 x; + index = (pirq & 1) << 1 | (pirq & 8) >> 3; raw_spin_lock_irqsave(&pc_conf_lock, flags); pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); - x = irqmap[read_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1)]; + x = irqmap[read_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, index)]; pc_conf_set(PC_CONF_FINALI_LOCK, 0); raw_spin_unlock_irqrestore(&pc_conf_lock, flags); return x; @@ -278,13 +373,15 @@ static int pirq_finali_set(struct pci_dev *router, struct pci_dev *dev, }; u8 val = irqmap[irq]; unsigned long flags; + u8 index; if (!val) return 0; + index = (pirq & 1) << 1 | (pirq & 8) >> 3; raw_spin_lock_irqsave(&pc_conf_lock, flags); pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); - write_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1, val); + write_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, index, val); pc_conf_set(PC_CONF_FINALI_LOCK, 0); raw_spin_unlock_irqrestore(&pc_conf_lock, flags); return 1; @@ -293,7 +390,7 @@ static int pirq_finali_set(struct pci_dev *router, struct pci_dev *dev, static int pirq_finali_lvl(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { - u8 mask = ~(1u << (pirq - 1)); + u8 mask = ~((pirq & 0xf0u) >> 4); unsigned long flags; u8 trig; @@ -579,6 +676,81 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, return 1; } + +/* + * PIRQ routing for the SiS85C497 AT Bus Controller & Megacell (ATM) + * ISA bridge used with the SiS 85C496/497 486 Green PC VESA/ISA/PCI + * Chipset. + * + * There are four PCI INTx#-to-IRQ Link registers provided in the + * SiS85C497 part of the peculiar combined 85C496/497 configuration + * space decoded by the SiS85C496 PCI & CPU Memory Controller (PCM) + * host bridge, at 0xc0/0xc1/0xc2/0xc3 respectively for the PCI INT + * A/B/C/D lines. Bit 7 enables the respective link if set and bits + * 3:0 select the 8259A IRQ line as follows: + * + * 0000 : Reserved + * 0001 : Reserved + * 0010 : Reserved + * 0011 : IRQ3 + * 0100 : IRQ4 + * 0101 : IRQ5 + * 0110 : IRQ6 + * 0111 : IRQ7 + * 1000 : Reserved + * 1001 : IRQ9 + * 1010 : IRQ10 + * 1011 : IRQ11 + * 1100 : IRQ12 + * 1101 : Reserved + * 1110 : IRQ14 + * 1111 : IRQ15 + * + * We avoid using a reserved value for disabled links, hence the + * choice of IRQ15 for that case. + * + * References: + * + * "486 Green PC VESA/ISA/PCI Chipset, SiS 85C496/497", Rev 3.0, + * Silicon Integrated Systems Corp., July 1995 + */ + +#define PCI_SIS497_INTA_TO_IRQ_LINK 0xc0u + +#define PIRQ_SIS497_IRQ_MASK 0x0fu +#define PIRQ_SIS497_IRQ_ENABLE 0x80u + +static int pirq_sis497_get(struct pci_dev *router, struct pci_dev *dev, + int pirq) +{ + int reg; + u8 x; + + reg = pirq; + if (reg >= 1 && reg <= 4) + reg += PCI_SIS497_INTA_TO_IRQ_LINK - 1; + + pci_read_config_byte(router, reg, &x); + return (x & PIRQ_SIS497_IRQ_ENABLE) ? (x & PIRQ_SIS497_IRQ_MASK) : 0; +} + +static int pirq_sis497_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) +{ + int reg; + u8 x; + + reg = pirq; + if (reg >= 1 && reg <= 4) + reg += PCI_SIS497_INTA_TO_IRQ_LINK - 1; + + pci_read_config_byte(router, reg, &x); + x &= ~(PIRQ_SIS497_IRQ_MASK | PIRQ_SIS497_IRQ_ENABLE); + x |= irq ? (PIRQ_SIS497_IRQ_ENABLE | irq) : PIRQ_SIS497_IRQ_MASK; + pci_write_config_byte(router, reg, x); + return 1; +} + /* * PIRQ routing for SiS 85C503 router used in several SiS chipsets. * We have to deal with the following issues here: @@ -640,11 +812,12 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, * bit 6-4 are probably unused, not like 5595 */ -#define PIRQ_SIS_IRQ_MASK 0x0f -#define PIRQ_SIS_IRQ_DISABLE 0x80 -#define PIRQ_SIS_USB_ENABLE 0x40 +#define PIRQ_SIS503_IRQ_MASK 0x0f +#define PIRQ_SIS503_IRQ_DISABLE 0x80 +#define PIRQ_SIS503_USB_ENABLE 0x40 -static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +static int pirq_sis503_get(struct pci_dev *router, struct pci_dev *dev, + int pirq) { u8 x; int reg; @@ -653,10 +826,11 @@ static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq) if (reg >= 0x01 && reg <= 0x04) reg += 0x40; pci_read_config_byte(router, reg, &x); - return (x & PIRQ_SIS_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS_IRQ_MASK); + return (x & PIRQ_SIS503_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS503_IRQ_MASK); } -static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int pirq_sis503_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) { u8 x; int reg; @@ -665,8 +839,8 @@ static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, i if (reg >= 0x01 && reg <= 0x04) reg += 0x40; pci_read_config_byte(router, reg, &x); - x &= ~(PIRQ_SIS_IRQ_MASK | PIRQ_SIS_IRQ_DISABLE); - x |= irq ? irq: PIRQ_SIS_IRQ_DISABLE; + x &= ~(PIRQ_SIS503_IRQ_MASK | PIRQ_SIS503_IRQ_DISABLE); + x |= irq ? irq : PIRQ_SIS503_IRQ_DISABLE; pci_write_config_byte(router, reg, x); return 1; } @@ -958,13 +1132,19 @@ static __init int serverworks_router_probe(struct irq_router *r, static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - if (device != PCI_DEVICE_ID_SI_503) - return 0; - - r->name = "SIS"; - r->get = pirq_sis_get; - r->set = pirq_sis_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_SI_496: + r->name = "SiS85C497"; + r->get = pirq_sis497_get; + r->set = pirq_sis497_set; + return 1; + case PCI_DEVICE_ID_SI_503: + r->name = "SiS85C503"; + r->get = pirq_sis503_get; + r->set = pirq_sis503_set; + return 1; + } + return 0; } static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) @@ -1084,10 +1264,32 @@ static struct pci_dev *pirq_router_dev; * chipset" ? */ +static bool __init pirq_try_router(struct irq_router *r, + struct irq_routing_table *rt, + struct pci_dev *dev) +{ + struct irq_router_handler *h; + + DBG(KERN_DEBUG "PCI: Trying IRQ router for [%04x:%04x]\n", + dev->vendor, dev->device); + + for (h = pirq_routers; h->vendor; h++) { + /* First look for a router match */ + if (rt->rtr_vendor == h->vendor && + h->probe(r, dev, rt->rtr_device)) + return true; + /* Fall back to a device match */ + if (dev->vendor == h->vendor && + h->probe(r, dev, dev->device)) + return true; + } + return false; +} + static void __init pirq_find_router(struct irq_router *r) { struct irq_routing_table *rt = pirq_table; - struct irq_router_handler *h; + struct pci_dev *dev; #ifdef CONFIG_PCI_BIOS if (!rt->signature) { @@ -1106,50 +1308,94 @@ static void __init pirq_find_router(struct irq_router *r) DBG(KERN_DEBUG "PCI: Attempting to find IRQ router for [%04x:%04x]\n", rt->rtr_vendor, rt->rtr_device); - pirq_router_dev = pci_get_domain_bus_and_slot(0, rt->rtr_bus, - rt->rtr_devfn); - if (!pirq_router_dev) { - DBG(KERN_DEBUG "PCI: Interrupt router not found at " - "%02x:%02x\n", rt->rtr_bus, rt->rtr_devfn); - return; + /* Use any vendor:device provided by the routing table or try all. */ + if (rt->rtr_vendor) { + dev = pci_get_domain_bus_and_slot(0, rt->rtr_bus, + rt->rtr_devfn); + if (dev && pirq_try_router(r, rt, dev)) + pirq_router_dev = dev; + } else { + dev = NULL; + for_each_pci_dev(dev) { + if (pirq_try_router(r, rt, dev)) { + pirq_router_dev = dev; + break; + } + } } - for (h = pirq_routers; h->vendor; h++) { - /* First look for a router match */ - if (rt->rtr_vendor == h->vendor && - h->probe(r, pirq_router_dev, rt->rtr_device)) - break; - /* Fall back to a device match */ - if (pirq_router_dev->vendor == h->vendor && - h->probe(r, pirq_router_dev, pirq_router_dev->device)) - break; - } - dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x:%04x]\n", - pirq_router.name, - pirq_router_dev->vendor, pirq_router_dev->device); + if (pirq_router_dev) + dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x:%04x]\n", + pirq_router.name, + pirq_router_dev->vendor, pirq_router_dev->device); + else + DBG(KERN_DEBUG "PCI: Interrupt router not found at " + "%02x:%02x\n", rt->rtr_bus, rt->rtr_devfn); /* The device remains referenced for the kernel lifetime */ } -static struct irq_info *pirq_get_info(struct pci_dev *dev) +/* + * We're supposed to match on the PCI device only and not the function, + * but some BIOSes build their tables with the PCI function included + * for motherboard devices, so if a complete match is found, then give + * it precedence over a slot match. + */ +static struct irq_info *pirq_get_dev_info(struct pci_dev *dev) { struct irq_routing_table *rt = pirq_table; int entries = (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); + struct irq_info *slotinfo = NULL; struct irq_info *info; for (info = rt->slots; entries--; info++) - if (info->bus == dev->bus->number && - PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) - return info; - return NULL; + if (info->bus == dev->bus->number) { + if (info->devfn == dev->devfn) + return info; + if (!slotinfo && + PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) + slotinfo = info; + } + return slotinfo; +} + +/* + * Buses behind bridges are typically not listed in the PIRQ routing table. + * Do the usual dance then and walk the tree of bridges up adjusting the + * pin number accordingly on the way until the originating root bus device + * has been reached and then use its routing information. + */ +static struct irq_info *pirq_get_info(struct pci_dev *dev, u8 *pin) +{ + struct pci_dev *temp_dev = dev; + struct irq_info *info; + u8 temp_pin = *pin; + u8 dpin = temp_pin; + + info = pirq_get_dev_info(dev); + while (!info && temp_dev->bus->parent) { + struct pci_dev *bridge = temp_dev->bus->self; + + temp_pin = pci_swizzle_interrupt_pin(temp_dev, temp_pin); + info = pirq_get_dev_info(bridge); + if (info) + dev_warn(&dev->dev, + "using bridge %s INT %c to get INT %c\n", + pci_name(bridge), + 'A' + temp_pin - 1, 'A' + dpin - 1); + + temp_dev = bridge; + } + *pin = temp_pin; + return info; } static int pcibios_lookup_irq(struct pci_dev *dev, int assign) { - u8 pin; struct irq_info *info; int i, pirq, newirq; + u8 dpin, pin; int irq = 0; u32 mask; struct irq_router *r = &pirq_router; @@ -1157,8 +1403,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) char *msg = NULL; /* Find IRQ pin */ - pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); - if (!pin) { + pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &dpin); + if (!dpin) { dev_dbg(&dev->dev, "no interrupt pin\n"); return 0; } @@ -1171,20 +1417,21 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) if (!pirq_table) return 0; - info = pirq_get_info(dev); + pin = dpin; + info = pirq_get_info(dev, &pin); if (!info) { dev_dbg(&dev->dev, "PCI INT %c not found in routing table\n", - 'A' + pin - 1); + 'A' + dpin - 1); return 0; } pirq = info->irq[pin - 1].link; mask = info->irq[pin - 1].bitmap; if (!pirq) { - dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin - 1); + dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + dpin - 1); return 0; } dev_dbg(&dev->dev, "PCI INT %c -> PIRQ %02x, mask %04x, excl %04x", - 'A' + pin - 1, pirq, mask, pirq_table->exclusive_irqs); + 'A' + dpin - 1, pirq, mask, pirq_table->exclusive_irqs); mask &= pcibios_irq_mask; /* Work around broken HP Pavilion Notebooks which assign USB to @@ -1226,7 +1473,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) newirq = i; } } - dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin - 1, newirq); + dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + dpin - 1, newirq); /* Check if it is hardcoded */ if ((pirq & 0xf0) == 0xf0) { @@ -1260,15 +1507,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) return 0; } } - dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin - 1, irq); + dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", + msg, 'A' + dpin - 1, irq); /* Update IRQ for all devices with the same pirq value */ for_each_pci_dev(dev2) { - pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &pin); - if (!pin) + pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &dpin); + if (!dpin) continue; - info = pirq_get_info(dev2); + pin = dpin; + info = pirq_get_info(dev2, &pin); if (!info) continue; if (info->irq[pin - 1].link == pirq) { diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9bb1e2941179..b94f727251b6 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -467,7 +467,6 @@ static __init void xen_setup_pci_msi(void) else xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs; - pci_msi_ignore_mask = 1; } else if (xen_hvm_domain()) { xen_msi_ops.setup_msi_irqs = xen_hvm_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_teardown_msi_irqs; @@ -481,6 +480,11 @@ static __init void xen_setup_pci_msi(void) * in allocating the native domain and never use it. */ x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain; + /* + * With XEN PIRQ/Eventchannels in use PCI/MSI[-X] masking is solely + * controlled by the hypervisor. + */ + pci_msi_ignore_mask = 1; } #else /* CONFIG_PCI_MSI */ diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 147c30a81f15..1591d67e0bcd 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -93,6 +93,9 @@ static const unsigned long * const efi_tables[] = { #ifdef CONFIG_LOAD_UEFI_KEYS &efi.mokvar_table, #endif +#ifdef CONFIG_EFI_COCO_SECRET + &efi.coco_secret, +#endif }; u64 efi_setup; /* efi setup_data physical address */ diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index 72c1e42d121d..7fe564eaf228 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -50,6 +50,7 @@ #define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) SYM_CODE_START_LOCAL(pvh_start_xen) + UNWIND_HINT_EMPTY cld lgdt (_pa(gdt)) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9f2b251e83c5..bb176c72891c 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -25,6 +25,7 @@ #include <asm/cpu.h> #include <asm/mmu_context.h> #include <asm/cpu_device_id.h> +#include <asm/microcode.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -40,7 +41,8 @@ static void msr_save_context(struct saved_context *ctxt) struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { - msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + if (msr->valid) + rdmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } @@ -261,11 +263,18 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); perf_restore_debug_store(); - msr_restore_context(ctxt); c = &cpu_data(smp_processor_id()); if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) init_ia32_feat_ctl(c); + + microcode_bsp_resume(); + + /* + * This needs to happen after the microcode has been updated upon resume + * because some of the MSRs are "emulated" in microcode. + */ + msr_restore_context(ctxt); } /* Needed by apm.c */ @@ -424,8 +433,10 @@ static int msr_build_context(const u32 *msr_id, const int num) } for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + u64 dummy; + msr_array[i].info.msr_no = msr_id[j]; - msr_array[i].valid = false; + msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy); msr_array[i].info.reg.q = 0; } saved_msrs->num = total_num; @@ -500,10 +511,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c) return ret; } +static void pm_save_spec_msr(void) +{ + u32 spec_msr_id[] = { + MSR_IA32_SPEC_CTRL, + MSR_IA32_TSX_CTRL, + MSR_TSX_FORCE_ABORT, + MSR_IA32_MCU_OPT_CTRL, + MSR_AMD64_LS_CFG, + }; + + msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); pm_cpu_check(msr_save_cpu_table); + pm_save_spec_msr(); return 0; } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index c5e29db02a46..41d7669a97ad 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -67,7 +67,7 @@ void __init reserve_real_mode(void) memblock_reserve(0, SZ_1M); } -static void sme_sev_setup_real_mode(struct trampoline_header *th) +static void __init sme_sev_setup_real_mode(struct trampoline_header *th) { #ifdef CONFIG_AMD_MEM_ENCRYPT if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index 8c1db5bf5d78..2eb62be6d256 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -24,6 +24,7 @@ SYM_DATA_START(real_mode_header) .long pa_sev_es_trampoline_start #endif #ifdef CONFIG_X86_64 + .long pa_trampoline_start64 .long pa_trampoline_pgd; #endif /* ACPI S3 wakeup */ diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index cc8391f86cdb..e38d61d6562e 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -70,7 +70,7 @@ SYM_CODE_START(trampoline_start) movw $__KERNEL_DS, %dx # Data segment descriptor # Enable protected mode - movl $X86_CR0_PE, %eax # protected mode (PE) bit + movl $(CR0_STATE & ~X86_CR0_PG), %eax movl %eax, %cr0 # into protected mode # flush prefetch and jump to startup_32 @@ -143,13 +143,24 @@ SYM_CODE_START(startup_32) movl %eax, %cr3 # Set up EFER + movl $MSR_EFER, %ecx + rdmsr + /* + * Skip writing to EFER if the register already has desired + * value (to avoid #VE for the TDX guest). + */ + cmp pa_tr_efer, %eax + jne .Lwrite_efer + cmp pa_tr_efer + 4, %edx + je .Ldone_efer +.Lwrite_efer: movl pa_tr_efer, %eax movl pa_tr_efer + 4, %edx - movl $MSR_EFER, %ecx wrmsr - # Enable paging and in turn activate Long Mode - movl $(X86_CR0_PG | X86_CR0_WP | X86_CR0_PE), %eax +.Ldone_efer: + # Enable paging and in turn activate Long Mode. + movl $CR0_STATE, %eax movl %eax, %cr0 /* @@ -161,6 +172,19 @@ SYM_CODE_START(startup_32) ljmpl $__KERNEL_CS, $pa_startup_64 SYM_CODE_END(startup_32) +SYM_CODE_START(pa_trampoline_compat) + /* + * In compatibility mode. Prep ESP and DX for startup_32, then disable + * paging and complete the switch to legacy 32-bit mode. + */ + movl $rm_stack_end, %esp + movw $__KERNEL_DS, %dx + + movl $(CR0_STATE & ~X86_CR0_PG), %eax + movl %eax, %cr0 + ljmpl $__KERNEL32_CS, $pa_startup_32 +SYM_CODE_END(pa_trampoline_compat) + .section ".text64","ax" .code64 .balign 4 @@ -169,6 +193,20 @@ SYM_CODE_START(startup_64) jmpq *tr_start(%rip) SYM_CODE_END(startup_64) +SYM_CODE_START(trampoline_start64) + /* + * APs start here on a direct transfer from 64-bit BIOS with identity + * mapped page tables. Load the kernel's GDT in order to gear down to + * 32-bit mode (to handle 4-level vs. 5-level paging), and to (re)load + * segment registers. Load the zero IDT so any fault triggers a + * shutdown instead of jumping back into BIOS. + */ + lidt tr_idt(%rip) + lgdt tr_gdt64(%rip) + + ljmpl *tr_compat(%rip) +SYM_CODE_END(trampoline_start64) + .section ".rodata","a" # Duplicate the global descriptor table # so the kernel can live anywhere @@ -182,6 +220,17 @@ SYM_DATA_START(tr_gdt) .quad 0x00cf93000000ffff # __KERNEL_DS SYM_DATA_END_LABEL(tr_gdt, SYM_L_LOCAL, tr_gdt_end) +SYM_DATA_START(tr_gdt64) + .short tr_gdt_end - tr_gdt - 1 # gdt limit + .long pa_tr_gdt + .long 0 +SYM_DATA_END(tr_gdt64) + +SYM_DATA_START(tr_compat) + .long pa_trampoline_compat + .short __KERNEL32_CS +SYM_DATA_END(tr_compat) + .bss .balign PAGE_SIZE SYM_DATA(trampoline_pgd, .space PAGE_SIZE) diff --git a/arch/x86/realmode/rm/trampoline_common.S b/arch/x86/realmode/rm/trampoline_common.S index 5033e640f957..4331c32c47f8 100644 --- a/arch/x86/realmode/rm/trampoline_common.S +++ b/arch/x86/realmode/rm/trampoline_common.S @@ -1,4 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0 */ .section ".rodata","a" .balign 16 -SYM_DATA_LOCAL(tr_idt, .fill 1, 6, 0) + +/* + * When a bootloader hands off to the kernel in 32-bit mode an + * IDT with a 2-byte limit and 4-byte base is needed. When a boot + * loader hands off to a kernel 64-bit mode the base address + * extends to 8-bytes. Reserve enough space for either scenario. + */ +SYM_DATA_START_LOCAL(tr_idt) + .short 0 + .quad 0 +SYM_DATA_END(tr_idt) diff --git a/arch/x86/realmode/rm/wakemain.c b/arch/x86/realmode/rm/wakemain.c index 1d6437e6d2ba..a6f4d8388ad8 100644 --- a/arch/x86/realmode/rm/wakemain.c +++ b/arch/x86/realmode/rm/wakemain.c @@ -62,8 +62,12 @@ static void send_morse(const char *pattern) } } +struct port_io_ops pio_ops; + void main(void) { + init_default_io_ops(); + /* Kill machine if structures are wrong */ if (wakeup_header.real_magic != 0x12345678) while (1) diff --git a/arch/x86/virt/vmx/tdx/tdxcall.S b/arch/x86/virt/vmx/tdx/tdxcall.S new file mode 100644 index 000000000000..49a54356ae99 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdxcall.S @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/asm-offsets.h> +#include <asm/tdx.h> + +/* + * TDCALL and SEAMCALL are supported in Binutils >= 2.36. + */ +#define tdcall .byte 0x66,0x0f,0x01,0xcc +#define seamcall .byte 0x66,0x0f,0x01,0xcf + +/* + * TDX_MODULE_CALL - common helper macro for both + * TDCALL and SEAMCALL instructions. + * + * TDCALL - used by TDX guests to make requests to the + * TDX module and hypercalls to the VMM. + * SEAMCALL - used by TDX hosts to make requests to the + * TDX module. + */ +.macro TDX_MODULE_CALL host:req + /* + * R12 will be used as temporary storage for struct tdx_module_output + * pointer. Since R12-R15 registers are not used by TDCALL/SEAMCALL + * services supported by this function, it can be reused. + */ + + /* Callee saved, so preserve it */ + push %r12 + + /* + * Push output pointer to stack. + * After the operation, it will be fetched into R12 register. + */ + push %r9 + + /* Mangle function call ABI into TDCALL/SEAMCALL ABI: */ + /* Move Leaf ID to RAX */ + mov %rdi, %rax + /* Move input 4 to R9 */ + mov %r8, %r9 + /* Move input 3 to R8 */ + mov %rcx, %r8 + /* Move input 1 to RCX */ + mov %rsi, %rcx + /* Leave input param 2 in RDX */ + + .if \host + seamcall + /* + * SEAMCALL instruction is essentially a VMExit from VMX root + * mode to SEAM VMX root mode. VMfailInvalid (CF=1) indicates + * that the targeted SEAM firmware is not loaded or disabled, + * or P-SEAMLDR is busy with another SEAMCALL. %rax is not + * changed in this case. + * + * Set %rax to TDX_SEAMCALL_VMFAILINVALID for VMfailInvalid. + * This value will never be used as actual SEAMCALL error code as + * it is from the Reserved status code class. + */ + jnc .Lno_vmfailinvalid + mov $TDX_SEAMCALL_VMFAILINVALID, %rax +.Lno_vmfailinvalid: + + .else + tdcall + .endif + + /* + * Fetch output pointer from stack to R12 (It is used + * as temporary storage) + */ + pop %r12 + + /* + * Since this macro can be invoked with NULL as an output pointer, + * check if caller provided an output struct before storing output + * registers. + * + * Update output registers, even if the call failed (RAX != 0). + * Other registers may contain details of the failure. + */ + test %r12, %r12 + jz .Lno_output_struct + + /* Copy result registers to output struct: */ + movq %rcx, TDX_MODULE_rcx(%r12) + movq %rdx, TDX_MODULE_rdx(%r12) + movq %r8, TDX_MODULE_r8(%r12) + movq %r9, TDX_MODULE_r9(%r12) + movq %r10, TDX_MODULE_r10(%r12) + movq %r11, TDX_MODULE_r11(%r12) + +.Lno_output_struct: + /* Restore the state of R12 register */ + pop %r12 +.endm diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 688aa8b6ae29..ba7af2eca755 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -260,8 +260,11 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) return 0; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (ctxt == NULL) + if (ctxt == NULL) { + cpumask_clear_cpu(cpu, xen_cpu_initialized_map); + cpumask_clear_cpu(cpu, cpu_callout_mask); return -ENOMEM; + } gdt = get_cpu_gdt_rw(cpu); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index ac17196e2518..3a2cd93bf059 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -45,6 +45,7 @@ SYM_CODE_END(hypercall_page) __INIT SYM_CODE_START(startup_xen) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR cld /* Clear .bss */ diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index 45cc0ae0af6f..c7b9f12896f2 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -29,7 +29,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lsave_cp_regs_cp##x: \ - xchal_cp##x##_store a2 a4 a5 a6 a7; \ + xchal_cp##x##_store a2 a3 a4 a5 a6; \ jx a0; \ .endif @@ -46,7 +46,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lload_cp_regs_cp##x: \ - xchal_cp##x##_load a2 a4 a5 a6 a7; \ + xchal_cp##x##_load a2 a3 a4 a5 a6; \ jx a0; \ .endif diff --git a/arch/xtensa/kernel/jump_label.c b/arch/xtensa/kernel/jump_label.c index 0dde21e0d3de..ad1841cecdfb 100644 --- a/arch/xtensa/kernel/jump_label.c +++ b/arch/xtensa/kernel/jump_label.c @@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) { struct patch *patch = data; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { local_patch_text(patch->addr, patch->data, patch->sz); atomic_inc(&patch->cpu_count); } else { diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 81d7c7e8f7e9..10b79d3c74e0 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -36,24 +36,19 @@ static void rs_poll(struct timer_list *); static struct tty_driver *serial_driver; static struct tty_port serial_port; static DEFINE_TIMER(serial_timer, rs_poll); -static DEFINE_SPINLOCK(timer_lock); static int rs_open(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock_bh(&timer_lock); return 0; } static void rs_close(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) del_timer_sync(&serial_timer); - spin_unlock_bh(&timer_lock); } @@ -73,8 +68,6 @@ static void rs_poll(struct timer_list *unused) int rd = 1; unsigned char c; - spin_lock(&timer_lock); - while (simc_poll(0)) { rd = simc_read(0, &c, 1); if (rd <= 0) @@ -87,7 +80,6 @@ static void rs_poll(struct timer_list *unused) tty_flip_buffer_push(port); if (rd) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock(&timer_lock); } |