diff options
Diffstat (limited to 'arch')
124 files changed, 1290 insertions, 628 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 400b9e1b2f27..a26d6f8ab967 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -234,8 +234,8 @@ config ARCH_HAS_FORTIFY_SOURCE config ARCH_HAS_SET_MEMORY bool -# Select if arch init_task initializer is different to init/init_task.c -config ARCH_INIT_TASK +# Select if arch init_task must go in the __init_task_data section +config ARCH_TASK_STRUCT_ON_STACK bool # Select if arch has its private alloc_task_struct() function diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 8c20c5e35432..807d7b9a1860 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -39,9 +39,6 @@ struct thread_info { .preempt_count = INIT_PREEMPT_COUNT, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* How to get the thread information struct from C. */ register struct thread_info *__current_thread_info __asm__("$8"); #define current_thread_info() __current_thread_info diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c index 37bd6d9b8eb9..a6bdc1da47ad 100644 --- a/arch/alpha/kernel/sys_sio.c +++ b/arch/alpha/kernel/sys_sio.c @@ -102,6 +102,15 @@ sio_pci_route(void) alpha_mv.sys.sio.route_tab); } +static bool sio_pci_dev_irq_needs_level(const struct pci_dev *dev) +{ + if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) && + (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA)) + return false; + + return true; +} + static unsigned int __init sio_collect_irq_levels(void) { @@ -110,8 +119,7 @@ sio_collect_irq_levels(void) /* Iterate through the devices, collecting IRQ levels. */ for_each_pci_dev(dev) { - if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) && - (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA)) + if (!sio_pci_dev_irq_needs_level(dev)) continue; if (dev->irq) @@ -120,8 +128,7 @@ sio_collect_irq_levels(void) return level_bits; } -static void __init -sio_fixup_irq_levels(unsigned int level_bits) +static void __sio_fixup_irq_levels(unsigned int level_bits, bool reset) { unsigned int old_level_bits; @@ -139,12 +146,21 @@ sio_fixup_irq_levels(unsigned int level_bits) */ old_level_bits = inb(0x4d0) | (inb(0x4d1) << 8); - level_bits |= (old_level_bits & 0x71ff); + if (reset) + old_level_bits &= 0x71ff; + + level_bits |= old_level_bits; outb((level_bits >> 0) & 0xff, 0x4d0); outb((level_bits >> 8) & 0xff, 0x4d1); } +static inline void +sio_fixup_irq_levels(unsigned int level_bits) +{ + __sio_fixup_irq_levels(level_bits, true); +} + static inline int noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { @@ -181,7 +197,14 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) const long min_idsel = 6, max_idsel = 14, irqs_per_slot = 5; int irq = COMMON_TABLE_LOOKUP, tmp; tmp = __kernel_extbl(alpha_mv.sys.sio.route_tab, irq); - return irq >= 0 ? tmp : -1; + + irq = irq >= 0 ? tmp : -1; + + /* Fixup IRQ level if an actual IRQ mapping is detected */ + if (sio_pci_dev_irq_needs_level(dev) && irq >= 0) + __sio_fixup_irq_levels(1 << irq, false); + + return irq; } static inline int diff --git a/arch/alpha/lib/ev6-memset.S b/arch/alpha/lib/ev6-memset.S index 316a99aa9efe..1cfcfbbea6f0 100644 --- a/arch/alpha/lib/ev6-memset.S +++ b/arch/alpha/lib/ev6-memset.S @@ -18,7 +18,7 @@ * The algorithm for the leading and trailing quadwords remains the same, * however the loop has been unrolled to enable better memory throughput, * and the code has been replicated for each of the entry points: __memset - * and __memsetw to permit better scheduling to eliminate the stalling + * and __memset16 to permit better scheduling to eliminate the stalling * encountered during the mask replication. * A future enhancement might be to put in a byte store loop for really * small (say < 32 bytes) memset()s. Whether or not that change would be @@ -34,7 +34,7 @@ .globl memset .globl __memset .globl ___memset - .globl __memsetw + .globl __memset16 .globl __constant_c_memset .ent ___memset @@ -415,9 +415,9 @@ end: * to mask stalls. Note that entry point names also had to change */ .align 5 - .ent __memsetw + .ent __memset16 -__memsetw: +__memset16: .frame $30,0,$26,0 .prologue 0 @@ -596,8 +596,8 @@ end_w: nop ret $31,($26),1 # L0 : - .end __memsetw - EXPORT_SYMBOL(__memsetw) + .end __memset16 + EXPORT_SYMBOL(__memset16) memset = ___memset __memset = ___memset diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index 2d79e527fa50..c85947bac5e5 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -62,9 +62,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - static inline __attribute_const__ struct thread_info *current_thread_info(void) { register unsigned long sp asm("sp"); diff --git a/arch/arm/boot/dts/da850-lcdk.dts b/arch/arm/boot/dts/da850-lcdk.dts index eed89e659143..a1f4d6d5a569 100644 --- a/arch/arm/boot/dts/da850-lcdk.dts +++ b/arch/arm/boot/dts/da850-lcdk.dts @@ -293,12 +293,12 @@ label = "u-boot env"; reg = <0 0x020000>; }; - partition@0x020000 { + partition@20000 { /* The LCDK defaults to booting from this partition */ label = "u-boot"; reg = <0x020000 0x080000>; }; - partition@0x0a0000 { + partition@a0000 { label = "free space"; reg = <0x0a0000 0>; }; diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts index cf2f5240e176..27cc913ca0f5 100644 --- a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts +++ b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts @@ -53,7 +53,8 @@ }; pinctrl: pin-controller@10000 { - pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>; + pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header + &pmx_gpio_header_gpo>; pinctrl-names = "default"; pmx_uart0: pmx-uart0 { @@ -85,11 +86,16 @@ * ground. */ pmx_gpio_header: pmx-gpio-header { - marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28", + marvell,pins = "mpp17", "mpp29", "mpp28", "mpp35", "mpp34", "mpp40"; marvell,function = "gpio"; }; + pmx_gpio_header_gpo: pxm-gpio-header-gpo { + marvell,pins = "mpp7"; + marvell,function = "gpo"; + }; + pmx_gpio_init: pmx-init { marvell,pins = "mpp38"; marvell,function = "gpio"; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index 5840f5c75c3b..4f2f2eea0755 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -1104,7 +1104,7 @@ be1_out_tcon0: endpoint@0 { reg = <0>; - remote-endpoint = <&tcon1_in_be0>; + remote-endpoint = <&tcon0_in_be1>; }; be1_out_tcon1: endpoint@1 { diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 59655e42e4b0..bd0cd3204273 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -1354,7 +1354,7 @@ be1_out_tcon0: endpoint@0 { reg = <0>; - remote-endpoint = <&tcon1_in_be0>; + remote-endpoint = <&tcon0_in_be1>; }; be1_out_tcon1: endpoint@1 { diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index 5caaf971fb50..df433abfcb02 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -10,6 +10,7 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 CONFIG_AEABI=y CONFIG_HIGHMEM=y +CONFIG_CMA=y CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CPU_FREQ=y @@ -33,6 +34,7 @@ CONFIG_CAN_SUN4I=y # CONFIG_WIRELESS is not set CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y +CONFIG_DMA_CMA=y CONFIG_BLK_DEV_SD=y CONFIG_ATA=y CONFIG_AHCI_SUNXI=y diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 776757d1604a..e71cc35de163 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -75,9 +75,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* * how to get the current stack pointer in C */ diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index c199990e12b6..323a4df59a6c 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -27,14 +27,58 @@ int bpf_jit_enable __read_mostly; +/* + * eBPF prog stack layout: + * + * high + * original ARM_SP => +-----+ + * | | callee saved registers + * +-----+ <= (BPF_FP + SCRATCH_SIZE) + * | ... | eBPF JIT scratch space + * eBPF fp register => +-----+ + * (BPF_FP) | ... | eBPF prog stack + * +-----+ + * |RSVD | JIT scratchpad + * current ARM_SP => +-----+ <= (BPF_FP - STACK_SIZE + SCRATCH_SIZE) + * | | + * | ... | Function call stack + * | | + * +-----+ + * low + * + * The callee saved registers depends on whether frame pointers are enabled. + * With frame pointers (to be compliant with the ABI): + * + * high + * original ARM_SP => +------------------+ \ + * | pc | | + * current ARM_FP => +------------------+ } callee saved registers + * |r4-r8,r10,fp,ip,lr| | + * +------------------+ / + * low + * + * Without frame pointers: + * + * high + * original ARM_SP => +------------------+ + * | r4-r8,r10,fp,lr | callee saved registers + * current ARM_FP => +------------------+ + * low + * + * When popping registers off the stack at the end of a BPF function, we + * reference them via the current ARM_FP register. + */ +#define CALLEE_MASK (1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \ + 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R10 | \ + 1 << ARM_FP) +#define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR) +#define CALLEE_POP_MASK (CALLEE_MASK | 1 << ARM_PC) + #define STACK_OFFSET(k) (k) #define TMP_REG_1 (MAX_BPF_JIT_REG + 0) /* TEMP Register 1 */ #define TMP_REG_2 (MAX_BPF_JIT_REG + 1) /* TEMP Register 2 */ #define TCALL_CNT (MAX_BPF_JIT_REG + 2) /* Tail Call Count */ -/* Flags used for JIT optimization */ -#define SEEN_CALL (1 << 0) - #define FLAG_IMM_OVERFLOW (1 << 0) /* @@ -95,7 +139,6 @@ static const u8 bpf2a32[][2] = { * idx : index of current last JITed instruction. * prologue_bytes : bytes used in prologue. * epilogue_offset : offset of epilogue starting. - * seen : bit mask used for JIT optimization. * offsets : array of eBPF instruction offsets in * JITed code. * target : final JITed code. @@ -110,7 +153,6 @@ struct jit_ctx { unsigned int idx; unsigned int prologue_bytes; unsigned int epilogue_offset; - u32 seen; u32 flags; u32 *offsets; u32 *target; @@ -179,8 +221,13 @@ static void jit_fill_hole(void *area, unsigned int size) *ptr++ = __opcode_to_mem_arm(ARM_INST_UDF); } -/* Stack must be multiples of 16 Bytes */ -#define STACK_ALIGN(sz) (((sz) + 3) & ~3) +#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) +/* EABI requires the stack to be aligned to 64-bit boundaries */ +#define STACK_ALIGNMENT 8 +#else +/* Stack must be aligned to 32-bit boundaries */ +#define STACK_ALIGNMENT 4 +#endif /* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4, * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9, @@ -194,7 +241,7 @@ static void jit_fill_hole(void *area, unsigned int size) + SCRATCH_SIZE + \ + 4 /* extra for skb_copy_bits buffer */) -#define STACK_SIZE STACK_ALIGN(_STACK_SIZE) +#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT) /* Get the offset of eBPF REGISTERs stored on scratch space. */ #define STACK_VAR(off) (STACK_SIZE-off-4) @@ -285,16 +332,19 @@ static inline void emit_mov_i(const u8 rd, u32 val, struct jit_ctx *ctx) emit_mov_i_no8m(rd, val, ctx); } -static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx) +static void emit_bx_r(u8 tgt_reg, struct jit_ctx *ctx) { - ctx->seen |= SEEN_CALL; -#if __LINUX_ARM_ARCH__ < 5 - emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx); - if (elf_hwcap & HWCAP_THUMB) emit(ARM_BX(tgt_reg), ctx); else emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx); +} + +static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx) +{ +#if __LINUX_ARM_ARCH__ < 5 + emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx); + emit_bx_r(tgt_reg, ctx); #else emit(ARM_BLX_R(tgt_reg), ctx); #endif @@ -354,7 +404,6 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op) } /* Call appropriate function */ - ctx->seen |= SEEN_CALL; emit_mov_i(ARM_IP, op == BPF_DIV ? (u32)jit_udiv32 : (u32)jit_mod32, ctx); emit_blx_r(ARM_IP, ctx); @@ -620,8 +669,6 @@ static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk, /* Do LSH operation */ emit(ARM_SUB_I(ARM_IP, rt, 32), ctx); emit(ARM_RSB_I(tmp2[0], rt, 32), ctx); - /* As we are using ARM_LR */ - ctx->seen |= SEEN_CALL; emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx); emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx); emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx); @@ -656,8 +703,6 @@ static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk, /* Do the ARSH operation */ emit(ARM_RSB_I(ARM_IP, rt, 32), ctx); emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx); - /* As we are using ARM_LR */ - ctx->seen |= SEEN_CALL; emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx); emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx); _emit(ARM_COND_MI, ARM_B(0), ctx); @@ -692,8 +737,6 @@ static inline void emit_a32_lsr_r64(const u8 dst[], const u8 src[], bool dstk, /* Do LSH operation */ emit(ARM_RSB_I(ARM_IP, rt, 32), ctx); emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx); - /* As we are using ARM_LR */ - ctx->seen |= SEEN_CALL; emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx); emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx); emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx); @@ -828,8 +871,6 @@ static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk, /* Do Multiplication */ emit(ARM_MUL(ARM_IP, rd, rn), ctx); emit(ARM_MUL(ARM_LR, rm, rt), ctx); - /* As we are using ARM_LR */ - ctx->seen |= SEEN_CALL; emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx); emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx); @@ -872,33 +913,53 @@ static inline void emit_str_r(const u8 dst, const u8 src, bool dstk, } /* dst = *(size*)(src + off) */ -static inline void emit_ldx_r(const u8 dst, const u8 src, bool dstk, - const s32 off, struct jit_ctx *ctx, const u8 sz){ +static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk, + s32 off, struct jit_ctx *ctx, const u8 sz){ const u8 *tmp = bpf2a32[TMP_REG_1]; - u8 rd = dstk ? tmp[1] : dst; + const u8 *rd = dstk ? tmp : dst; u8 rm = src; + s32 off_max; - if (off) { + if (sz == BPF_H) + off_max = 0xff; + else + off_max = 0xfff; + + if (off < 0 || off > off_max) { emit_a32_mov_i(tmp[0], off, false, ctx); emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx); rm = tmp[0]; + off = 0; + } else if (rd[1] == rm) { + emit(ARM_MOV_R(tmp[0], rm), ctx); + rm = tmp[0]; } switch (sz) { - case BPF_W: - /* Load a Word */ - emit(ARM_LDR_I(rd, rm, 0), ctx); + case BPF_B: + /* Load a Byte */ + emit(ARM_LDRB_I(rd[1], rm, off), ctx); + emit_a32_mov_i(dst[0], 0, dstk, ctx); break; case BPF_H: /* Load a HalfWord */ - emit(ARM_LDRH_I(rd, rm, 0), ctx); + emit(ARM_LDRH_I(rd[1], rm, off), ctx); + emit_a32_mov_i(dst[0], 0, dstk, ctx); break; - case BPF_B: - /* Load a Byte */ - emit(ARM_LDRB_I(rd, rm, 0), ctx); + case BPF_W: + /* Load a Word */ + emit(ARM_LDR_I(rd[1], rm, off), ctx); + emit_a32_mov_i(dst[0], 0, dstk, ctx); + break; + case BPF_DW: + /* Load a Double Word */ + emit(ARM_LDR_I(rd[1], rm, off), ctx); + emit(ARM_LDR_I(rd[0], rm, off + 4), ctx); break; } if (dstk) - emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx); + emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst[1])), ctx); + if (dstk && sz == BPF_DW) + emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst[0])), ctx); } /* Arithmatic Operation */ @@ -906,7 +967,6 @@ static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm, const u8 rn, struct jit_ctx *ctx, u8 op) { switch (op) { case BPF_JSET: - ctx->seen |= SEEN_CALL; emit(ARM_AND_R(ARM_IP, rt, rn), ctx); emit(ARM_AND_R(ARM_LR, rd, rm), ctx); emit(ARM_ORRS_R(ARM_IP, ARM_LR, ARM_IP), ctx); @@ -945,7 +1005,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) const u8 *tcc = bpf2a32[TCALL_CNT]; const int idx0 = ctx->idx; #define cur_offset (ctx->idx - idx0) -#define jmp_offset (out_offset - (cur_offset)) +#define jmp_offset (out_offset - (cur_offset) - 2) u32 off, lo, hi; /* if (index >= array->map.max_entries) @@ -956,7 +1016,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit_a32_mov_i(tmp[1], off, false, ctx); emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx); emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx); - /* index (64 bit) */ + /* index is 32-bit for arrays */ emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx); /* index >= array->map.max_entries */ emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx); @@ -997,7 +1057,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit_a32_mov_i(tmp2[1], off, false, ctx); emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx); emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx); - emit(ARM_BX(tmp[1]), ctx); + emit_bx_r(tmp[1], ctx); /* out: */ if (out_offset == -1) @@ -1070,54 +1130,22 @@ static void build_prologue(struct jit_ctx *ctx) const u8 r2 = bpf2a32[BPF_REG_1][1]; const u8 r3 = bpf2a32[BPF_REG_1][0]; const u8 r4 = bpf2a32[BPF_REG_6][1]; - const u8 r5 = bpf2a32[BPF_REG_6][0]; - const u8 r6 = bpf2a32[TMP_REG_1][1]; - const u8 r7 = bpf2a32[TMP_REG_1][0]; - const u8 r8 = bpf2a32[TMP_REG_2][1]; - const u8 r10 = bpf2a32[TMP_REG_2][0]; const u8 fplo = bpf2a32[BPF_REG_FP][1]; const u8 fphi = bpf2a32[BPF_REG_FP][0]; - const u8 sp = ARM_SP; const u8 *tcc = bpf2a32[TCALL_CNT]; - u16 reg_set = 0; - - /* - * eBPF prog stack layout - * - * high - * original ARM_SP => +-----+ eBPF prologue - * |FP/LR| - * current ARM_FP => +-----+ - * | ... | callee saved registers - * eBPF fp register => +-----+ <= (BPF_FP) - * | ... | eBPF JIT scratch space - * | | eBPF prog stack - * +-----+ - * |RSVD | JIT scratchpad - * current A64_SP => +-----+ <= (BPF_FP - STACK_SIZE) - * | | - * | ... | Function call stack - * | | - * +-----+ - * low - */ - /* Save callee saved registers. */ - reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10); #ifdef CONFIG_FRAME_POINTER - reg_set |= (1<<ARM_FP) | (1<<ARM_IP) | (1<<ARM_LR) | (1<<ARM_PC); - emit(ARM_MOV_R(ARM_IP, sp), ctx); + u16 reg_set = CALLEE_PUSH_MASK | 1 << ARM_IP | 1 << ARM_PC; + emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx); emit(ARM_PUSH(reg_set), ctx); emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx); #else - /* Check if call instruction exists in BPF body */ - if (ctx->seen & SEEN_CALL) - reg_set |= (1<<ARM_LR); - emit(ARM_PUSH(reg_set), ctx); + emit(ARM_PUSH(CALLEE_PUSH_MASK), ctx); + emit(ARM_MOV_R(ARM_FP, ARM_SP), ctx); #endif /* Save frame pointer for later */ - emit(ARM_SUB_I(ARM_IP, sp, SCRATCH_SIZE), ctx); + emit(ARM_SUB_I(ARM_IP, ARM_SP, SCRATCH_SIZE), ctx); ctx->stack_size = imm8m(STACK_SIZE); @@ -1140,33 +1168,19 @@ static void build_prologue(struct jit_ctx *ctx) /* end of prologue */ } +/* restore callee saved registers. */ static void build_epilogue(struct jit_ctx *ctx) { - const u8 r4 = bpf2a32[BPF_REG_6][1]; - const u8 r5 = bpf2a32[BPF_REG_6][0]; - const u8 r6 = bpf2a32[TMP_REG_1][1]; - const u8 r7 = bpf2a32[TMP_REG_1][0]; - const u8 r8 = bpf2a32[TMP_REG_2][1]; - const u8 r10 = bpf2a32[TMP_REG_2][0]; - u16 reg_set = 0; - - /* unwind function call stack */ - emit(ARM_ADD_I(ARM_SP, ARM_SP, ctx->stack_size), ctx); - - /* restore callee saved registers. */ - reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10); #ifdef CONFIG_FRAME_POINTER - /* the first instruction of the prologue was: mov ip, sp */ - reg_set |= (1<<ARM_FP) | (1<<ARM_SP) | (1<<ARM_PC); + /* When using frame pointers, some additional registers need to + * be loaded. */ + u16 reg_set = CALLEE_POP_MASK | 1 << ARM_SP; + emit(ARM_SUB_I(ARM_SP, ARM_FP, hweight16(reg_set) * 4), ctx); emit(ARM_LDM(ARM_SP, reg_set), ctx); #else - if (ctx->seen & SEEN_CALL) - reg_set |= (1<<ARM_PC); /* Restore callee saved registers. */ - emit(ARM_POP(reg_set), ctx); - /* Return back to the callee function */ - if (!(ctx->seen & SEEN_CALL)) - emit(ARM_BX(ARM_LR), ctx); + emit(ARM_MOV_R(ARM_SP, ARM_FP), ctx); + emit(ARM_POP(CALLEE_POP_MASK), ctx); #endif } @@ -1394,8 +1408,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) emit_rev32(rt, rt, ctx); goto emit_bswap_uxt; case 64: - /* Because of the usage of ARM_LR */ - ctx->seen |= SEEN_CALL; emit_rev32(ARM_LR, rt, ctx); emit_rev32(rt, rd, ctx); emit(ARM_MOV_R(rd, ARM_LR), ctx); @@ -1448,22 +1460,7 @@ exit: rn = sstk ? tmp2[1] : src_lo; if (sstk) emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx); - switch (BPF_SIZE(code)) { - case BPF_W: - /* Load a Word */ - case BPF_H: - /* Load a Half-Word */ - case BPF_B: - /* Load a Byte */ - emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_SIZE(code)); - emit_a32_mov_i(dst_hi, 0, dstk, ctx); - break; - case BPF_DW: - /* Load a double word */ - emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_W); - emit_ldx_r(dst_hi, rn, dstk, off+4, ctx, BPF_W); - break; - } + emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code)); break; /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */ case BPF_LD | BPF_ABS | BPF_W: diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi index 7c9bdc7ab50b..9db19314c60c 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi @@ -66,6 +66,7 @@ <&cpu1>, <&cpu2>, <&cpu3>; + interrupt-parent = <&intc>; }; psci { diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi index e3b64d03fbd8..9c7724e82aff 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi @@ -63,8 +63,10 @@ cpm_ethernet: ethernet@0 { compatible = "marvell,armada-7k-pp22"; reg = <0x0 0x100000>, <0x129000 0xb000>; - clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>, <&cpm_clk 1 5>; - clock-names = "pp_clk", "gop_clk", "mg_clk"; + clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>, + <&cpm_clk 1 5>, <&cpm_clk 1 18>; + clock-names = "pp_clk", "gop_clk", + "mg_clk","axi_clk"; marvell,system-controller = <&cpm_syscon0>; status = "disabled"; dma-coherent; @@ -155,7 +157,8 @@ #size-cells = <0>; compatible = "marvell,orion-mdio"; reg = <0x12a200 0x10>; - clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>; + clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>, + <&cpm_clk 1 6>, <&cpm_clk 1 18>; status = "disabled"; }; @@ -338,8 +341,8 @@ compatible = "marvell,armada-cp110-sdhci"; reg = <0x780000 0x300>; interrupts = <ICU_GRP_NSR 27 IRQ_TYPE_LEVEL_HIGH>; - clock-names = "core"; - clocks = <&cpm_clk 1 4>; + clock-names = "core","axi"; + clocks = <&cpm_clk 1 4>, <&cpm_clk 1 18>; dma-coherent; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi index 0d51096c69f8..87ac68b2cf37 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi @@ -63,8 +63,10 @@ cps_ethernet: ethernet@0 { compatible = "marvell,armada-7k-pp22"; reg = <0x0 0x100000>, <0x129000 0xb000>; - clocks = <&cps_clk 1 3>, <&cps_clk 1 9>, <&cps_clk 1 5>; - clock-names = "pp_clk", "gop_clk", "mg_clk"; + clocks = <&cps_clk 1 3>, <&cps_clk 1 9>, + <&cps_clk 1 5>, <&cps_clk 1 18>; + clock-names = "pp_clk", "gop_clk", + "mg_clk", "axi_clk"; marvell,system-controller = <&cps_syscon0>; status = "disabled"; dma-coherent; @@ -155,7 +157,8 @@ #size-cells = <0>; compatible = "marvell,orion-mdio"; reg = <0x12a200 0x10>; - clocks = <&cps_clk 1 9>, <&cps_clk 1 5>; + clocks = <&cps_clk 1 9>, <&cps_clk 1 5>, + <&cps_clk 1 6>, <&cps_clk 1 18>; status = "disabled"; }; diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index eb431286bacd..740aa03c5f0d 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -51,8 +51,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_stack (init_thread_union.stack) - #define thread_saved_pc(tsk) \ ((unsigned long)(tsk->thread.cpu_context.pc)) #define thread_saved_sp(tsk) \ diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 304203fa9e33..e60494f1eef9 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -45,7 +45,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_psci_call(vcpu); if (ret < 0) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; } @@ -54,7 +54,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index ba38d403abb2..bb32f7f6dd0f 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -148,7 +148,8 @@ static inline int epilogue_offset(const struct jit_ctx *ctx) /* Stack must be multiples of 16B */ #define STACK_ALIGN(sz) (((sz) + 15) & ~15) -#define PROLOGUE_OFFSET 8 +/* Tail call offset to jump into */ +#define PROLOGUE_OFFSET 7 static int build_prologue(struct jit_ctx *ctx) { @@ -200,19 +201,19 @@ static int build_prologue(struct jit_ctx *ctx) /* Initialize tail_call_cnt */ emit(A64_MOVZ(1, tcc, 0, 0), ctx); - /* 4 byte extra for skb_copy_bits buffer */ - ctx->stack_size = prog->aux->stack_depth + 4; - ctx->stack_size = STACK_ALIGN(ctx->stack_size); - - /* Set up function call stack */ - emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); - cur_offset = ctx->idx - idx0; if (cur_offset != PROLOGUE_OFFSET) { pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n", cur_offset, PROLOGUE_OFFSET); return -1; } + + /* 4 byte extra for skb_copy_bits buffer */ + ctx->stack_size = prog->aux->stack_depth + 4; + ctx->stack_size = STACK_ALIGN(ctx->stack_size); + + /* Set up function call stack */ + emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); return 0; } @@ -260,11 +261,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit(A64_LDR64(prg, tmp, prg), ctx); emit(A64_CBZ(1, prg, jmp_offset), ctx); - /* goto *(prog->bpf_func + prologue_size); */ + /* goto *(prog->bpf_func + prologue_offset); */ off = offsetof(struct bpf_prog, bpf_func); emit_a64_mov_i64(tmp, off, ctx); emit(A64_LDR64(tmp, prg, tmp), ctx); emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx); + emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); emit(A64_BR(tmp), ctx); /* out: */ diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h index 2966b93850a1..a5aeab4e5f2d 100644 --- a/arch/blackfin/include/asm/thread_info.h +++ b/arch/blackfin/include/asm/thread_info.h @@ -56,8 +56,6 @@ struct thread_info { .cpu = 0, \ .preempt_count = INIT_PREEMPT_COUNT, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) /* Given a task stack pointer, you can find its corresponding * thread_info structure just by masking it to the THREAD_SIZE diff --git a/arch/c6x/include/asm/thread_info.h b/arch/c6x/include/asm/thread_info.h index acc70c135ab8..59a5697fe0f3 100644 --- a/arch/c6x/include/asm/thread_info.h +++ b/arch/c6x/include/asm/thread_info.h @@ -60,9 +60,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* get the thread information struct of current task */ static inline __attribute__((const)) struct thread_info *current_thread_info(void) diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h index 124dd5ec7f65..ee4d8b03d048 100644 --- a/arch/cris/include/asm/processor.h +++ b/arch/cris/include/asm/processor.h @@ -26,13 +26,6 @@ struct task_struct; */ #define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3)) -/* THREAD_SIZE is the size of the thread_info/kernel_stack combo. - * normally, the stack is found by doing something like p + THREAD_SIZE - * in CRIS, a page is 8192 bytes, which seems like a sane size - */ -#define THREAD_SIZE PAGE_SIZE -#define THREAD_SIZE_ORDER (0) - /* * At user->kernel entry, the pt_regs struct is stacked on the top of the kernel-stack. * This macro allows us to find those regs for a task. @@ -59,8 +52,6 @@ static inline void release_thread(struct task_struct *dead_task) /* Nothing needs to be done. */ } -#define init_stack (init_thread_union.stack) - #define cpu_relax() barrier() void default_idle(void); diff --git a/arch/cris/include/asm/thread_info.h b/arch/cris/include/asm/thread_info.h index 472830c90997..996fef3be1d5 100644 --- a/arch/cris/include/asm/thread_info.h +++ b/arch/cris/include/asm/thread_info.h @@ -20,6 +20,13 @@ #endif +/* THREAD_SIZE is the size of the thread_info/kernel_stack combo. + * normally, the stack is found by doing something like p + THREAD_SIZE + * in CRIS, a page is 8192 bytes, which seems like a sane size + */ +#define THREAD_SIZE PAGE_SIZE +#define THREAD_SIZE_ORDER (0) + /* * low level task data that entry.S needs immediate access to * - this struct should fit entirely inside of one cache line @@ -56,8 +63,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) - #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S index 6d1dbc1ba767..9b232e0f673e 100644 --- a/arch/cris/kernel/vmlinux.lds.S +++ b/arch/cris/kernel/vmlinux.lds.S @@ -11,6 +11,7 @@ #include <asm-generic/vmlinux.lds.h> #include <asm/page.h> +#include <asm/thread_info.h> #ifdef CONFIG_ETRAX_VMEM_SIZE #define __CONFIG_ETRAX_VMEM_SIZE CONFIG_ETRAX_VMEM_SIZE diff --git a/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h index ccba3b6ce918..0f950845fad9 100644 --- a/arch/frv/include/asm/thread_info.h +++ b/arch/frv/include/asm/thread_info.h @@ -64,9 +64,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the thread information struct from C */ register struct thread_info *__current_thread_info asm("gr15"); diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h index 072b92c0d8b5..0cdaa302d3d2 100644 --- a/arch/h8300/include/asm/thread_info.h +++ b/arch/h8300/include/asm/thread_info.h @@ -46,9 +46,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) { diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h index b80fe1db7b64..f41f9c6f0e31 100644 --- a/arch/hexagon/include/asm/thread_info.h +++ b/arch/hexagon/include/asm/thread_info.h @@ -84,9 +84,6 @@ struct thread_info { .regs = NULL, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* Tacky preprocessor trickery */ #define qqstr(s) qstr(s) #define qstr(s) #s diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index ec87e67feb19..ad69d181c939 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -22,6 +22,8 @@ #include <asm/asm-offsets.h> /* Most of the kernel defines are here */ #include <asm/mem-layout.h> /* except for page_offset */ #include <asm/cache.h> /* and now we're pulling cache line size */ +#include <asm/thread_info.h> /* and we need THREAD_SIZE too */ + OUTPUT_ARCH(hexagon) ENTRY(stext) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 49583c5a5d44..315c51f58811 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -43,7 +43,7 @@ config IA64 select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_IOMAP select GENERIC_SMP_IDLE_THREAD - select ARCH_INIT_TASK + select ARCH_TASK_STRUCT_ON_STACK select ARCH_TASK_STRUCT_ALLOCATOR select ARCH_THREAD_STACK_ALLOCATOR select ARCH_CLOCKSOURCE_DATA diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index c100d780f1eb..2dd7f519ad0b 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -42,7 +42,7 @@ $(error Sorry, you need a newer version of the assember, one that is built from endif KBUILD_CFLAGS += $(cflags-y) -head-y := arch/ia64/kernel/head.o arch/ia64/kernel/init_task.o +head-y := arch/ia64/kernel/head.o libs-y += arch/ia64/lib/ core-y += arch/ia64/kernel/ arch/ia64/mm/ diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 28e02c99be6d..762eeb0fcc1d 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -65,29 +65,30 @@ ia64_atomic_fetch_##op (int i, atomic_t *v) \ ATOMIC_OPS(add, +) ATOMIC_OPS(sub, -) -#define atomic_add_return(i,v) \ +#ifdef __OPTIMIZE__ +#define __ia64_atomic_const(i) __builtin_constant_p(i) ? \ + ((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 || \ + (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0 + +#define atomic_add_return(i, v) \ ({ \ - int __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ - ? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter) \ - : ia64_atomic_add(__ia64_aar_i, v); \ + int __i = (i); \ + static const int __ia64_atomic_p = __ia64_atomic_const(i); \ + __ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) : \ + ia64_atomic_add(__i, v); \ }) -#define atomic_sub_return(i,v) \ +#define atomic_sub_return(i, v) \ ({ \ - int __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ - ? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter) \ - : ia64_atomic_sub(__ia64_asr_i, v); \ + int __i = (i); \ + static const int __ia64_atomic_p = __ia64_atomic_const(i); \ + __ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) : \ + ia64_atomic_sub(__i, v); \ }) +#else +#define atomic_add_return(i, v) ia64_atomic_add(i, v) +#define atomic_sub_return(i, v) ia64_atomic_sub(i, v) +#endif #define atomic_fetch_add(i,v) \ ({ \ diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index 1d172a4119a7..64a1011f6812 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -12,6 +12,8 @@ #include <asm/processor.h> #include <asm/ptrace.h> +#define THREAD_SIZE KERNEL_STACK_SIZE + #ifndef __ASSEMBLY__ /* @@ -41,8 +43,6 @@ struct thread_info { #endif }; -#define THREAD_SIZE KERNEL_STACK_SIZE - #define INIT_THREAD_INFO(tsk) \ { \ .task = &tsk, \ diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 14ad79f394e5..0b4c65a1af25 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -7,7 +7,7 @@ ifdef CONFIG_DYNAMIC_FTRACE CFLAGS_REMOVE_ftrace.o = -pg endif -extra-y := head.o init_task.o vmlinux.lds +extra-y := head.o vmlinux.lds obj-y := entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o \ irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o \ diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c deleted file mode 100644 index 8df9245e29d9..000000000000 --- a/arch/ia64/kernel/init_task.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This is where we statically allocate and initialize the initial - * task. - * - * Copyright (C) 1999, 2002-2003 Hewlett-Packard Co - * David Mosberger-Tang <davidm@hpl.hp.com> - */ - -#include <linux/init.h> -#include <linux/mm.h> -#include <linux/fs.h> -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/init_task.h> -#include <linux/mqueue.h> - -#include <linux/uaccess.h> -#include <asm/pgtable.h> - -static struct signal_struct init_signals = INIT_SIGNALS(init_signals); -static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -/* - * Initial task structure. - * - * We need to make sure that this is properly aligned due to the way process stacks are - * handled. This is done by having a special ".data..init_task" section... - */ -#define init_thread_info init_task_mem.s.thread_info -#define init_stack init_task_mem.stack - -union { - struct { - struct task_struct task; - struct thread_info thread_info; - } s; - unsigned long stack[KERNEL_STACK_SIZE/sizeof (unsigned long)]; -} init_task_mem asm ("init_task") __init_task_data = - {{ - .task = INIT_TASK(init_task_mem.s.task), - .thread_info = INIT_THREAD_INFO(init_task_mem.s.task) -}}; - -EXPORT_SYMBOL(init_task); diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index 58db59da0bd8..b0b2070e0591 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -3,6 +3,7 @@ #include <asm/cache.h> #include <asm/ptrace.h> #include <asm/pgtable.h> +#include <asm/thread_info.h> #include <asm-generic/vmlinux.lds.h> diff --git a/arch/m32r/include/asm/thread_info.h b/arch/m32r/include/asm/thread_info.h index b3a215b0ce0a..ba00f1032587 100644 --- a/arch/m32r/include/asm/thread_info.h +++ b/arch/m32r/include/asm/thread_info.h @@ -56,9 +56,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) { diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h index 928035591f2e..015f1ca38305 100644 --- a/arch/m68k/include/asm/thread_info.h +++ b/arch/m68k/include/asm/thread_info.h @@ -41,8 +41,6 @@ struct thread_info { .preempt_count = INIT_PREEMPT_COUNT, \ } -#define init_stack (init_thread_union.stack) - #ifndef __ASSEMBLY__ /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) @@ -58,8 +56,6 @@ static inline struct thread_info *current_thread_info(void) } #endif -#define init_thread_info (init_thread_union.thread_info) - /* entry.S relies on these definitions! * bits 0-7 are tested at every exception exit * bits 8-15 are also tested at syscall exit diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h index 554f73a77e6e..a1a9c7f5ca8c 100644 --- a/arch/metag/include/asm/thread_info.h +++ b/arch/metag/include/asm/thread_info.h @@ -74,9 +74,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the current stack pointer from C */ register unsigned long current_stack_pointer asm("A0StP") __used; diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h index e7e8954e9815..9afe4b5bd6c8 100644 --- a/arch/microblaze/include/asm/thread_info.h +++ b/arch/microblaze/include/asm/thread_info.h @@ -86,9 +86,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) { diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 350a990fc719..8e0b3702f1c0 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -259,6 +259,7 @@ config BCM47XX select LEDS_GPIO_REGISTER select BCM47XX_NVRAM select BCM47XX_SPROM + select BCM47XX_SSB if !BCM47XX_BCMA help Support for BCM47XX based boards @@ -389,6 +390,7 @@ config LANTIQ select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_MIPS16 select SYS_SUPPORTS_MULTITHREADING + select SYS_SUPPORTS_VPE_LOADER select SYS_HAS_EARLY_PRINTK select GPIOLIB select SWAP_IO_SPACE @@ -516,6 +518,7 @@ config MIPS_MALTA select SYS_SUPPORTS_MIPS16 select SYS_SUPPORTS_MULTITHREADING select SYS_SUPPORTS_SMARTMIPS + select SYS_SUPPORTS_VPE_LOADER select SYS_SUPPORTS_ZBOOT select SYS_SUPPORTS_RELOCATABLE select USE_OF @@ -2281,9 +2284,16 @@ config MIPSR2_TO_R6_EMULATOR The only reason this is a build-time option is to save ~14K from the final kernel image. +config SYS_SUPPORTS_VPE_LOADER + bool + depends on SYS_SUPPORTS_MULTITHREADING + help + Indicates that the platform supports the VPE loader, and provides + physical_memsize. + config MIPS_VPE_LOADER bool "VPE loader support." - depends on SYS_SUPPORTS_MULTITHREADING && MODULES + depends on SYS_SUPPORTS_VPE_LOADER && MODULES select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI select MIPS_MT diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug index 464af5e025d6..0749c3724543 100644 --- a/arch/mips/Kconfig.debug +++ b/arch/mips/Kconfig.debug @@ -124,30 +124,36 @@ config SCACHE_DEBUGFS If unsure, say N. -menuconfig MIPS_CPS_NS16550 +menuconfig MIPS_CPS_NS16550_BOOL bool "CPS SMP NS16550 UART output" depends on MIPS_CPS help Output debug information via an ns16550 compatible UART if exceptions occur early in the boot process of a secondary core. -if MIPS_CPS_NS16550 +if MIPS_CPS_NS16550_BOOL + +config MIPS_CPS_NS16550 + def_bool MIPS_CPS_NS16550_BASE != 0 config MIPS_CPS_NS16550_BASE hex "UART Base Address" default 0x1b0003f8 if MIPS_MALTA + default 0 help The base address of the ns16550 compatible UART on which to output debug information from the early stages of core startup. + This is only used if non-zero. + config MIPS_CPS_NS16550_SHIFT int "UART Register Shift" - default 0 if MIPS_MALTA + default 0 help The number of bits to shift ns16550 register indices by in order to form their addresses. That is, log base 2 of the span between adjacent ns16550 registers in the system. -endif # MIPS_CPS_NS16550 +endif # MIPS_CPS_NS16550_BOOL endmenu diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c index 4674f1efbe7a..e1675c25d5d4 100644 --- a/arch/mips/ar7/platform.c +++ b/arch/mips/ar7/platform.c @@ -575,7 +575,7 @@ static int __init ar7_register_uarts(void) uart_port.type = PORT_AR7; uart_port.uartclk = clk_get_rate(bus_clk) / 2; uart_port.iotype = UPIO_MEM32; - uart_port.flags = UPF_FIXED_TYPE; + uart_port.flags = UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF; uart_port.regshift = 2; uart_port.line = 0; diff --git a/arch/mips/ath25/devices.c b/arch/mips/ath25/devices.c index e1156347da53..301a9028273c 100644 --- a/arch/mips/ath25/devices.c +++ b/arch/mips/ath25/devices.c @@ -73,6 +73,7 @@ const char *get_system_type(void) void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk) { +#ifdef CONFIG_SERIAL_8250_CONSOLE struct uart_port s; memset(&s, 0, sizeof(s)); @@ -85,6 +86,7 @@ void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk) s.uartclk = uartclk; early_serial_setup(&s); +#endif /* CONFIG_SERIAL_8250_CONSOLE */ } int __init ath25_add_wmac(int nr, u32 base, int irq) diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index 5e8927f99a76..4993db40482c 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -49,9 +49,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* How to get the thread information struct from C. */ register struct thread_info *__current_thread_info __asm__("$28"); diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index dd5567b1e305..8f5bd04f320a 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -292,7 +292,6 @@ void mips_cm_lock_other(unsigned int cluster, unsigned int core, *this_cpu_ptr(&cm_core_lock_flags)); } else { WARN_ON(cluster != 0); - WARN_ON(vp != 0); WARN_ON(block != CM_GCR_Cx_OTHER_BLOCK_LOCAL); /* diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile index 78c2affeabf8..e84e12655fa8 100644 --- a/arch/mips/lib/Makefile +++ b/arch/mips/lib/Makefile @@ -16,4 +16,5 @@ obj-$(CONFIG_CPU_R3000) += r3k_dump_tlb.o obj-$(CONFIG_CPU_TX39XX) += r3k_dump_tlb.o # libgcc-style stuff needed in the kernel -obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o ucmpdi2.o +obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o multi3.o \ + ucmpdi2.o diff --git a/arch/mips/lib/libgcc.h b/arch/mips/lib/libgcc.h index 28002ed90c2c..199a7f96282f 100644 --- a/arch/mips/lib/libgcc.h +++ b/arch/mips/lib/libgcc.h @@ -10,10 +10,18 @@ typedef int word_type __attribute__ ((mode (__word__))); struct DWstruct { int high, low; }; + +struct TWstruct { + long long high, low; +}; #elif defined(__LITTLE_ENDIAN) struct DWstruct { int low, high; }; + +struct TWstruct { + long long low, high; +}; #else #error I feel sick. #endif @@ -23,4 +31,13 @@ typedef union { long long ll; } DWunion; +#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) +typedef int ti_type __attribute__((mode(TI))); + +typedef union { + struct TWstruct s; + ti_type ti; +} TWunion; +#endif + #endif /* __ASM_LIBGCC_H */ diff --git a/arch/mips/lib/multi3.c b/arch/mips/lib/multi3.c new file mode 100644 index 000000000000..111ad475aa0c --- /dev/null +++ b/arch/mips/lib/multi3.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/export.h> + +#include "libgcc.h" + +/* + * GCC 7 suboptimally generates __multi3 calls for mips64r6, so for that + * specific case only we'll implement it here. + * + * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981 + */ +#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ == 7) + +/* multiply 64-bit values, low 64-bits returned */ +static inline long long notrace dmulu(long long a, long long b) +{ + long long res; + + asm ("dmulu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +/* multiply 64-bit unsigned values, high 64-bits of 128-bit result returned */ +static inline long long notrace dmuhu(long long a, long long b) +{ + long long res; + + asm ("dmuhu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +/* multiply 128-bit values, low 128-bits returned */ +ti_type notrace __multi3(ti_type a, ti_type b) +{ + TWunion res, aa, bb; + + aa.ti = a; + bb.ti = b; + + /* + * a * b = (a.lo * b.lo) + * + 2^64 * (a.hi * b.lo + a.lo * b.hi) + * [+ 2^128 * (a.hi * b.hi)] + */ + res.s.low = dmulu(aa.s.low, bb.s.low); + res.s.high = dmuhu(aa.s.low, bb.s.low); + res.s.high += dmulu(aa.s.high, bb.s.low); + res.s.high += dmulu(aa.s.low, bb.s.high); + + return res.ti; +} +EXPORT_SYMBOL(__multi3); + +#endif /* 64BIT && CPU_MIPSR6 && GCC7 */ diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c index cdb5a191b9d5..9bb6baa45da3 100644 --- a/arch/mips/mm/uasm-micromips.c +++ b/arch/mips/mm/uasm-micromips.c @@ -40,7 +40,7 @@ #include "uasm.c" -static const struct insn const insn_table_MM[insn_invalid] = { +static const struct insn insn_table_MM[insn_invalid] = { [insn_addu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD}, [insn_addiu] = {M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, [insn_and] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD}, diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c index d4469b20d176..4f46a4509f79 100644 --- a/arch/mips/ralink/timer.c +++ b/arch/mips/ralink/timer.c @@ -109,9 +109,9 @@ static int rt_timer_probe(struct platform_device *pdev) } rt->irq = platform_get_irq(pdev, 0); - if (!rt->irq) { + if (rt->irq < 0) { dev_err(&pdev->dev, "failed to load irq\n"); - return -ENOENT; + return rt->irq; } rt->membase = devm_ioremap_resource(&pdev->dev, res); diff --git a/arch/mips/rb532/Makefile b/arch/mips/rb532/Makefile index efdecdb6e3ea..8186afca2234 100644 --- a/arch/mips/rb532/Makefile +++ b/arch/mips/rb532/Makefile @@ -2,4 +2,6 @@ # Makefile for the RB532 board specific parts of the kernel # -obj-y += irq.o time.o setup.o serial.o prom.o gpio.o devices.o +obj-$(CONFIG_SERIAL_8250_CONSOLE) += serial.o + +obj-y += irq.o time.o setup.o prom.o gpio.o devices.o diff --git a/arch/mips/rb532/devices.c b/arch/mips/rb532/devices.c index 32ea3e6731d6..354d258396ff 100644 --- a/arch/mips/rb532/devices.c +++ b/arch/mips/rb532/devices.c @@ -310,6 +310,8 @@ static int __init plat_setup_devices(void) return platform_add_devices(rb532_devs, ARRAY_SIZE(rb532_devs)); } +#ifdef CONFIG_NET + static int __init setup_kmac(char *s) { printk(KERN_INFO "korina mac = %s\n", s); @@ -322,4 +324,6 @@ static int __init setup_kmac(char *s) __setup("kmac=", setup_kmac); +#endif /* CONFIG_NET */ + arch_initcall(plat_setup_devices); diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h index f5f90bbf019d..1748a7b25bf8 100644 --- a/arch/mn10300/include/asm/thread_info.h +++ b/arch/mn10300/include/asm/thread_info.h @@ -79,8 +79,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) #define init_uregs \ ((struct pt_regs *) \ ((unsigned long) init_stack + THREAD_SIZE - sizeof(struct pt_regs))) diff --git a/arch/nios2/include/asm/thread_info.h b/arch/nios2/include/asm/thread_info.h index d69c338bd19c..7349a4fa635b 100644 --- a/arch/nios2/include/asm/thread_info.h +++ b/arch/nios2/include/asm/thread_info.h @@ -63,9 +63,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) { diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h index 396d8f306c21..af31a9fe736a 100644 --- a/arch/openrisc/include/asm/processor.h +++ b/arch/openrisc/include/asm/processor.h @@ -84,8 +84,6 @@ void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp); void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); -#define init_stack (init_thread_union.stack) - #define cpu_relax() barrier() #endif /* __ASSEMBLY__ */ diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h index c229aa6bb502..5c15dfa2fd4f 100644 --- a/arch/openrisc/include/asm/thread_info.h +++ b/arch/openrisc/include/asm/thread_info.h @@ -79,8 +79,6 @@ struct thread_info { .ksp = 0, \ } -#define init_thread_info (init_thread_union.thread_info) - /* how to get the thread information struct from C */ register struct thread_info *current_thread_info_reg asm("r10"); #define current_thread_info() (current_thread_info_reg) diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index 00ddb7804be4..953bdcd54efe 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -28,6 +28,7 @@ #include <asm/page.h> #include <asm/cache.h> +#include <asm/thread_info.h> #include <asm-generic/vmlinux.lds.h> #ifdef __OR1K__ diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h index 598c8d60fa5e..285757544cca 100644 --- a/arch/parisc/include/asm/thread_info.h +++ b/arch/parisc/include/asm/thread_info.h @@ -25,9 +25,6 @@ struct thread_info { .preempt_count = INIT_PREEMPT_COUNT, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the thread information struct from C */ #define current_thread_info() ((struct thread_info *)mfctl(30)) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index c51e6ce42e7a..2ed525a44734 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -166,6 +166,7 @@ config PPC select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE + select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64 select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_SMP_IDLE_THREAD diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index f0461618bf7b..eca3f9c68907 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -353,6 +353,7 @@ #define PROC_TABLE_GTSE 0x01 #ifndef __ASSEMBLY__ +#include <linux/types.h> /** * plpar_hcall_norets: - Make a pseries hypervisor call with no return arguments diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index a264c3ad366b..4a12c00f8de3 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -58,9 +58,6 @@ struct thread_info { .flags = 0, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - #define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) /* how to get the thread information struct from C */ diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 61d6049f4c1e..637b7263cb86 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info { __u32 ap_encodings[8]; }; +/* For KVM_PPC_GET_CPU_CHAR */ +struct kvm_ppc_cpu_char { + __u64 character; /* characteristics of the CPU */ + __u64 behaviour; /* recommended software behaviour */ + __u64 character_mask; /* valid bits in character */ + __u64 behaviour_mask; /* valid bits in behaviour */ +}; + +/* + * Values for character and character_mask. + * These are identical to the values used by H_GET_CPU_CHARACTERISTICS. + */ +#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 (1ULL << 63) +#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED (1ULL << 62) +#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 (1ULL << 61) +#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 (1ULL << 60) +#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV (1ULL << 59) +#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58) +#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57) +#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56) + +#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63) +#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62) +#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61) + /* Per-vcpu XICS interrupt controller state */ #define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 9d213542a48b..8fd3a70047f1 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -242,14 +242,6 @@ static int show_cpuinfo(struct seq_file *m, void *v) unsigned short maj; unsigned short min; - /* We only show online cpus: disable preempt (overzealous, I - * knew) to prevent cpu going down. */ - preempt_disable(); - if (!cpu_online(cpu_id)) { - preempt_enable(); - return 0; - } - #ifdef CONFIG_SMP pvr = per_cpu(cpu_pvr, cpu_id); #else @@ -358,9 +350,6 @@ static int show_cpuinfo(struct seq_file *m, void *v) #ifdef CONFIG_SMP seq_printf(m, "\n"); #endif - - preempt_enable(); - /* If this is the last cpu, print the summary */ if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids) show_cpuinfo_summary(m); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 491be4179ddd..e67413f4a8f0 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -38,6 +38,7 @@ #include <linux/memory.h> #include <linux/nmi.h> +#include <asm/debugfs.h> #include <asm/io.h> #include <asm/kdump.h> #include <asm/prom.h> @@ -901,4 +902,41 @@ void __init setup_rfi_flush(enum l1d_flush_type types, bool enable) if (!no_rfi_flush) rfi_flush_enable(enable); } + +#ifdef CONFIG_DEBUG_FS +static int rfi_flush_set(void *data, u64 val) +{ + if (val == 1) + rfi_flush_enable(true); + else if (val == 0) + rfi_flush_enable(false); + else + return -EINVAL; + + return 0; +} + +static int rfi_flush_get(void *data, u64 *val) +{ + *val = rfi_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); + +static __init int rfi_flush_debugfs_init(void) +{ + debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + return 0; +} +device_initcall(rfi_flush_debugfs_init); +#endif + +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (rfi_flush) + return sprintf(buf, "Mitigation: RFI Flush\n"); + + return sprintf(buf, "Vulnerable\n"); +} #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 1915e86cef6f..0a7c88786ec0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -39,6 +39,10 @@ #include <asm/iommu.h> #include <asm/switch_to.h> #include <asm/xive.h> +#ifdef CONFIG_PPC_PSERIES +#include <asm/hvcall.h> +#include <asm/plpar_wrappers.h> +#endif #include "timing.h" #include "irq.h" @@ -548,6 +552,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #ifdef CONFIG_KVM_XICS case KVM_CAP_IRQ_XICS: #endif + case KVM_CAP_PPC_GET_CPU_CHAR: r = 1; break; @@ -1759,6 +1764,124 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, return r; } +#ifdef CONFIG_PPC_BOOK3S_64 +/* + * These functions check whether the underlying hardware is safe + * against attacks based on observing the effects of speculatively + * executed instructions, and whether it supplies instructions for + * use in workarounds. The information comes from firmware, either + * via the device tree on powernv platforms or from an hcall on + * pseries platforms. + */ +#ifdef CONFIG_PPC_PSERIES +static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp) +{ + struct h_cpu_char_result c; + unsigned long rc; + + if (!machine_is(pseries)) + return -ENOTTY; + + rc = plpar_get_cpu_characteristics(&c); + if (rc == H_SUCCESS) { + cp->character = c.character; + cp->behaviour = c.behaviour; + cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 | + KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED | + KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 | + KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 | + KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV | + KVM_PPC_CPU_CHAR_BR_HINT_HONOURED | + KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF | + KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS; + cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY | + KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR | + KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR; + } + return 0; +} +#else +static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp) +{ + return -ENOTTY; +} +#endif + +static inline bool have_fw_feat(struct device_node *fw_features, + const char *state, const char *name) +{ + struct device_node *np; + bool r = false; + + np = of_get_child_by_name(fw_features, name); + if (np) { + r = of_property_read_bool(np, state); + of_node_put(np); + } + return r; +} + +static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp) +{ + struct device_node *np, *fw_features; + int r; + + memset(cp, 0, sizeof(*cp)); + r = pseries_get_cpu_char(cp); + if (r != -ENOTTY) + return r; + + np = of_find_node_by_name(NULL, "ibm,opal"); + if (np) { + fw_features = of_get_child_by_name(np, "fw-features"); + of_node_put(np); + if (!fw_features) + return 0; + if (have_fw_feat(fw_features, "enabled", + "inst-spec-barrier-ori31,31,0")) + cp->character |= KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31; + if (have_fw_feat(fw_features, "enabled", + "fw-bcctrl-serialized")) + cp->character |= KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED; + if (have_fw_feat(fw_features, "enabled", + "inst-l1d-flush-ori30,30,0")) + cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30; + if (have_fw_feat(fw_features, "enabled", + "inst-l1d-flush-trig2")) + cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2; + if (have_fw_feat(fw_features, "enabled", + "fw-l1d-thread-split")) + cp->character |= KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV; + if (have_fw_feat(fw_features, "enabled", + "fw-count-cache-disabled")) + cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS; + cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 | + KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED | + KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 | + KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 | + KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV | + KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS; + + if (have_fw_feat(fw_features, "enabled", + "speculation-policy-favor-security")) + cp->behaviour |= KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY; + if (!have_fw_feat(fw_features, "disabled", + "needs-l1d-flush-msr-pr-0-to-1")) + cp->behaviour |= KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR; + if (!have_fw_feat(fw_features, "disabled", + "needs-spec-barrier-for-bound-checks")) + cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR; + cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY | + KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR | + KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR; + + of_node_put(fw_features); + } + + return 0; +} +#endif + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1861,6 +1984,14 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + case KVM_PPC_GET_CPU_CHAR: { + struct kvm_ppc_cpu_char cpuchar; + + r = kvmppc_get_cpu_char(&cpuchar); + if (r >= 0 && copy_to_user(argp, &cpuchar, sizeof(cpuchar))) + r = -EFAULT; + break; + } default: { struct kvm *kvm = filp->private_data; r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index cab24f549e7c..0ddc7ac6c5f1 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2344,10 +2344,10 @@ static void dump_one_paca(int cpu) DUMP(p, kernel_toc, "lx"); DUMP(p, kernelbase, "lx"); DUMP(p, kernel_msr, "lx"); - DUMP(p, emergency_sp, "p"); + DUMP(p, emergency_sp, "px"); #ifdef CONFIG_PPC_BOOK3S_64 - DUMP(p, nmi_emergency_sp, "p"); - DUMP(p, mc_emergency_sp, "p"); + DUMP(p, nmi_emergency_sp, "px"); + DUMP(p, mc_emergency_sp, "px"); DUMP(p, in_nmi, "x"); DUMP(p, in_mce, "x"); DUMP(p, hmi_event_available, "x"); @@ -2375,17 +2375,21 @@ static void dump_one_paca(int cpu) DUMP(p, slb_cache_ptr, "x"); for (i = 0; i < SLB_CACHE_ENTRIES; i++) printf(" slb_cache[%d]: = 0x%016lx\n", i, p->slb_cache[i]); + + DUMP(p, rfi_flush_fallback_area, "px"); + DUMP(p, l1d_flush_congruence, "llx"); + DUMP(p, l1d_flush_sets, "llx"); #endif DUMP(p, dscr_default, "llx"); #ifdef CONFIG_PPC_BOOK3E - DUMP(p, pgd, "p"); - DUMP(p, kernel_pgd, "p"); - DUMP(p, tcd_ptr, "p"); - DUMP(p, mc_kstack, "p"); - DUMP(p, crit_kstack, "p"); - DUMP(p, dbg_kstack, "p"); + DUMP(p, pgd, "px"); + DUMP(p, kernel_pgd, "px"); + DUMP(p, tcd_ptr, "px"); + DUMP(p, mc_kstack, "px"); + DUMP(p, crit_kstack, "px"); + DUMP(p, dbg_kstack, "px"); #endif - DUMP(p, __current, "p"); + DUMP(p, __current, "px"); DUMP(p, kstack, "lx"); printf(" kstack_base = 0x%016lx\n", p->kstack & ~(THREAD_SIZE - 1)); DUMP(p, stab_rr, "lx"); @@ -2403,7 +2407,7 @@ static void dump_one_paca(int cpu) #endif #ifdef CONFIG_PPC_POWERNV - DUMP(p, core_idle_state_ptr, "p"); + DUMP(p, core_idle_state_ptr, "px"); DUMP(p, thread_idle_state, "x"); DUMP(p, thread_mask, "x"); DUMP(p, subcore_sibling_mask, "x"); diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 22c3536ed281..f8fa1cd2dad9 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -64,8 +64,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_stack (init_thread_union.stack) - #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index e14f381757f6..c1b0a9ac1dc8 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -207,7 +207,8 @@ struct kvm_s390_sie_block { __u16 ipa; /* 0x0056 */ __u32 ipb; /* 0x0058 */ __u32 scaoh; /* 0x005c */ - __u8 reserved60; /* 0x0060 */ +#define FPF_BPBC 0x20 + __u8 fpf; /* 0x0060 */ #define ECB_GS 0x40 #define ECB_TE 0x10 #define ECB_SRSI 0x04 diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 0880a37b6d3b..25d6ec3aaddd 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -42,8 +42,6 @@ struct thread_info { .flags = 0, \ } -#define init_stack (init_thread_union.stack) - void arch_release_task_struct(struct task_struct *tsk); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 38535a57fef8..4cdaa55fabfe 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -224,6 +224,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_RICCB (1UL << 7) #define KVM_SYNC_FPRS (1UL << 8) #define KVM_SYNC_GSCB (1UL << 9) +#define KVM_SYNC_BPBC (1UL << 10) /* length and alignment of the sdnx as a power of two */ #define SDNXC 8 #define SDNXL (1UL << SDNXC) @@ -247,7 +248,9 @@ struct kvm_sync_regs { }; __u8 reserved[512]; /* for future vector expansion */ __u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */ - __u8 padding1[52]; /* riccb needs to be 64byte aligned */ + __u8 bpbc : 1; /* bp mode */ + __u8 reserved2 : 7; + __u8 padding1[51]; /* riccb needs to be 64byte aligned */ __u8 riccb[64]; /* runtime instrumentation controls block */ __u8 padding2[192]; /* sdnx needs to be 256byte aligned */ union { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 2c93cbbcd15e..1371dff2b90d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -421,6 +421,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_GS: r = test_facility(133); break; + case KVM_CAP_S390_BPB: + r = test_facility(82); + break; default: r = 0; } @@ -766,7 +769,7 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) /* * Must be called with kvm->srcu held to avoid races on memslots, and with - * kvm->lock to avoid races with ourselves and kvm_s390_vm_stop_migration. + * kvm->slots_lock to avoid races with ourselves and kvm_s390_vm_stop_migration. */ static int kvm_s390_vm_start_migration(struct kvm *kvm) { @@ -822,7 +825,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) } /* - * Must be called with kvm->lock to avoid races with ourselves and + * Must be called with kvm->slots_lock to avoid races with ourselves and * kvm_s390_vm_start_migration. */ static int kvm_s390_vm_stop_migration(struct kvm *kvm) @@ -837,6 +840,8 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm) if (kvm->arch.use_cmma) { kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION); + /* We have to wait for the essa emulation to finish */ + synchronize_srcu(&kvm->srcu); vfree(mgs->pgste_bitmap); } kfree(mgs); @@ -846,14 +851,12 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm) static int kvm_s390_vm_set_migration(struct kvm *kvm, struct kvm_device_attr *attr) { - int idx, res = -ENXIO; + int res = -ENXIO; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->slots_lock); switch (attr->attr) { case KVM_S390_VM_MIGRATION_START: - idx = srcu_read_lock(&kvm->srcu); res = kvm_s390_vm_start_migration(kvm); - srcu_read_unlock(&kvm->srcu, idx); break; case KVM_S390_VM_MIGRATION_STOP: res = kvm_s390_vm_stop_migration(kvm); @@ -861,7 +864,7 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm, default: break; } - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->slots_lock); return res; } @@ -1751,7 +1754,9 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&args, argp, sizeof(args))) break; + mutex_lock(&kvm->slots_lock); r = kvm_s390_get_cmma_bits(kvm, &args); + mutex_unlock(&kvm->slots_lock); if (!r) { r = copy_to_user(argp, &args, sizeof(args)); if (r) @@ -1765,7 +1770,9 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&args, argp, sizeof(args))) break; + mutex_lock(&kvm->slots_lock); r = kvm_s390_set_cmma_bits(kvm, &args); + mutex_unlock(&kvm->slots_lock); break; } default: @@ -2198,6 +2205,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm_s390_set_prefix(vcpu, 0); if (test_kvm_facility(vcpu->kvm, 64)) vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; + if (test_kvm_facility(vcpu->kvm, 82)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; if (test_kvm_facility(vcpu->kvm, 133)) vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB; /* fprs can be synchronized via vrs, even if the guest has no vx. With @@ -2339,6 +2348,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) current->thread.fpu.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; + vcpu->arch.sie_block->fpf &= ~FPF_BPBC; vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; kvm_clear_async_pf_completion_queue(vcpu); if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) @@ -3298,6 +3308,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT; vcpu->arch.gs_enabled = 1; } + if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) && + test_kvm_facility(vcpu->kvm, 82)) { + vcpu->arch.sie_block->fpf &= ~FPF_BPBC; + vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0; + } save_access_regs(vcpu->arch.host_acrs); restore_access_regs(vcpu->run->s.regs.acrs); /* save host (userspace) fprs/vrs */ @@ -3344,6 +3359,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_run->s.regs.pft = vcpu->arch.pfault_token; kvm_run->s.regs.pfs = vcpu->arch.pfault_select; kvm_run->s.regs.pfc = vcpu->arch.pfault_compare; + kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); /* Save guest register state */ diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 5d6ae0326d9e..751348348477 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -223,6 +223,12 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) memcpy(scb_o->gcr, scb_s->gcr, 128); scb_o->pp = scb_s->pp; + /* branch prediction */ + if (test_kvm_facility(vcpu->kvm, 82)) { + scb_o->fpf &= ~FPF_BPBC; + scb_o->fpf |= scb_s->fpf & FPF_BPBC; + } + /* interrupt intercept */ switch (scb_s->icptcode) { case ICPT_PROGI: @@ -265,6 +271,7 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) scb_s->ecb3 = 0; scb_s->ecd = 0; scb_s->fac = 0; + scb_s->fpf = 0; rc = prepare_cpuflags(vcpu, vsie_page); if (rc) @@ -324,6 +331,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) prefix_unmapped(vsie_page); scb_s->ecb |= scb_o->ecb & ECB_TE; } + /* branch prediction */ + if (test_kvm_facility(vcpu->kvm, 82)) + scb_s->fpf |= scb_o->fpf & FPF_BPBC; /* SIMD */ if (test_kvm_facility(vcpu->kvm, 129)) { scb_s->eca |= scb_o->eca & ECA_VX; diff --git a/arch/score/include/asm/thread_info.h b/arch/score/include/asm/thread_info.h index ad51b56e51bd..bc4c7c90550f 100644 --- a/arch/score/include/asm/thread_info.h +++ b/arch/score/include/asm/thread_info.h @@ -58,9 +58,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* How to get the thread information struct from C. */ register struct thread_info *__current_thread_info __asm__("r28"); #define current_thread_info() __current_thread_info diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h index becb798f1b04..cf5c792bf70b 100644 --- a/arch/sh/include/asm/thread_info.h +++ b/arch/sh/include/asm/thread_info.h @@ -63,9 +63,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the current stack pointer from C */ register unsigned long current_stack_pointer asm("r15") __used; diff --git a/arch/sparc/crypto/Makefile b/arch/sparc/crypto/Makefile index 818d3aa5172e..d257186c27d1 100644 --- a/arch/sparc/crypto/Makefile +++ b/arch/sparc/crypto/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_CRYPTO_MD5_SPARC64) += md5-sparc64.o obj-$(CONFIG_CRYPTO_AES_SPARC64) += aes-sparc64.o obj-$(CONFIG_CRYPTO_DES_SPARC64) += des-sparc64.o -obj-$(CONFIG_CRYPTO_DES_SPARC64) += camellia-sparc64.o +obj-$(CONFIG_CRYPTO_CAMELLIA_SPARC64) += camellia-sparc64.o obj-$(CONFIG_CRYPTO_CRC32C_SPARC64) += crc32c-sparc64.o diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h index febaaeb1a0fe..548b366165dd 100644 --- a/arch/sparc/include/asm/thread_info_32.h +++ b/arch/sparc/include/asm/thread_info_32.h @@ -63,9 +63,6 @@ struct thread_info { .preempt_count = INIT_PREEMPT_COUNT, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the thread information struct from C */ register struct thread_info *current_thread_info_reg asm("g6"); #define current_thread_info() (current_thread_info_reg) diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h index caf915321ba9..f7e7b0baec9f 100644 --- a/arch/sparc/include/asm/thread_info_64.h +++ b/arch/sparc/include/asm/thread_info_64.h @@ -120,9 +120,6 @@ struct thread_info { .preempt_count = INIT_PREEMPT_COUNT, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the thread information struct from C */ register struct thread_info *current_thread_info_reg asm("g6"); #define current_thread_info() (current_thread_info_reg) diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index b7659b8f1117..2adcacd85749 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -59,9 +59,6 @@ struct thread_info { .align_ctl = 0, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - #endif /* !__ASSEMBLY__ */ #if PAGE_SIZE < 8192 diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 86942a492454..b58b746d3f2c 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -58,7 +58,10 @@ static inline void release_thread(struct task_struct *task) { } -#define init_stack (init_thread_union.stack) +static inline void mm_copy_segments(struct mm_struct *from_mm, + struct mm_struct *new_mm) +{ +} /* * User space process size: 3GB (default). diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h index 9300f7630d2a..4eecd960ee8c 100644 --- a/arch/um/include/asm/thread_info.h +++ b/arch/um/include/asm/thread_info.h @@ -6,6 +6,9 @@ #ifndef __UM_THREAD_INFO_H #define __UM_THREAD_INFO_H +#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER +#define THREAD_SIZE ((1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE) + #ifndef __ASSEMBLY__ #include <asm/types.h> @@ -37,10 +40,6 @@ struct thread_info { .real_thread = NULL, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - -#define THREAD_SIZE ((1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE) /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) { @@ -53,8 +52,6 @@ static inline struct thread_info *current_thread_info(void) return ti; } -#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER - #endif #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ diff --git a/arch/um/include/asm/vmlinux.lds.h b/arch/um/include/asm/vmlinux.lds.h new file mode 100644 index 000000000000..149494ae78ea --- /dev/null +++ b/arch/um/include/asm/vmlinux.lds.h @@ -0,0 +1,2 @@ +#include <asm/thread_info.h> +#include <asm-generic/vmlinux.lds.h> diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index d417e3899700..5568cf882371 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -1,5 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm-generic/vmlinux.lds.h> +#include <asm/vmlinux.lds.h> #include <asm/page.h> OUTPUT_FORMAT(ELF_FORMAT) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index f433690b9b37..a818ccef30ca 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -54,7 +54,7 @@ struct cpuinfo_um boot_cpu_data = { union thread_union cpu0_irqstack __attribute__((__section__(".data..init_irqstack"))) = - { INIT_THREAD_INFO(init_task) }; + { .thread_info = INIT_THREAD_INFO(init_task) }; /* Changed in setup_arch, which is called in early boot */ static char host_info[(__NEW_UTS_LEN + 1) * 5]; diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index 3d6ed6ba5b78..36b07ec09742 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#include <asm-generic/vmlinux.lds.h> +#include <asm/vmlinux.lds.h> #include <asm/page.h> OUTPUT_FORMAT(ELF_FORMAT) diff --git a/arch/unicore32/include/asm/thread_info.h b/arch/unicore32/include/asm/thread_info.h index e79ad6d5b5b2..5fb728f3b49a 100644 --- a/arch/unicore32/include/asm/thread_info.h +++ b/arch/unicore32/include/asm/thread_info.h @@ -87,9 +87,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* * how to get the thread information struct from C */ diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index a1f28a54f23a..60c4c342316c 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -244,6 +244,17 @@ ENTRY(__switch_to_asm) movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popl %esi popl %edi diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4f8e1d35a97c..ff6f8022612c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -491,6 +491,17 @@ ENTRY(__switch_to_asm) movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popq %r15 popq %r14 @@ -1253,7 +1264,7 @@ idtentry async_page_fault do_async_page_fault has_error_code=1 #endif #ifdef CONFIG_X86_MCE -idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) +idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c index a6eee5ac4f58..2aefacf5c5b2 100644 --- a/arch/x86/events/amd/power.c +++ b/arch/x86/events/amd/power.c @@ -277,7 +277,7 @@ static int __init amd_power_pmu_init(void) int ret; if (!x86_match_cpu(cpu_match)) - return 0; + return -ENODEV; if (!boot_cpu_has(X86_FEATURE_ACC_POWER)) return -ENODEV; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8156e47da7ba..18c25ab28557 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -372,10 +372,9 @@ static int alloc_pebs_buffer(int cpu) static void release_pebs_buffer(int cpu) { struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); - struct debug_store *ds = hwev->ds; void *cea; - if (!ds || !x86_pmu.pebs) + if (!x86_pmu.pebs) return; kfree(per_cpu(insn_buffer, cpu)); @@ -384,7 +383,6 @@ static void release_pebs_buffer(int cpu) /* Clear the fixmap */ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer; ds_clear_cea(cea, x86_pmu.pebs_buffer_size); - ds->pebs_buffer_base = 0; dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size); hwev->ds_pebs_vaddr = NULL; } @@ -419,16 +417,14 @@ static int alloc_bts_buffer(int cpu) static void release_bts_buffer(int cpu) { struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); - struct debug_store *ds = hwev->ds; void *cea; - if (!ds || !x86_pmu.bts) + if (!x86_pmu.bts) return; /* Clear the fixmap */ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer; ds_clear_cea(cea, BTS_BUFFER_SIZE); - ds->bts_buffer_base = 0; dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE); hwev->ds_bts_vaddr = NULL; } @@ -454,16 +450,22 @@ void release_ds_buffers(void) if (!x86_pmu.bts && !x86_pmu.pebs) return; - get_online_cpus(); - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) + release_ds_buffer(cpu); + + for_each_possible_cpu(cpu) { + /* + * Again, ignore errors from offline CPUs, they will no longer + * observe cpu_hw_events.ds and not program the DS_AREA when + * they come up. + */ fini_debug_store_on_cpu(cpu); + } for_each_possible_cpu(cpu) { release_pebs_buffer(cpu); release_bts_buffer(cpu); - release_ds_buffer(cpu); } - put_online_cpus(); } void reserve_ds_buffers(void) @@ -483,8 +485,6 @@ void reserve_ds_buffers(void) if (!x86_pmu.pebs) pebs_err = 1; - get_online_cpus(); - for_each_possible_cpu(cpu) { if (alloc_ds_buffer(cpu)) { bts_err = 1; @@ -521,11 +521,14 @@ void reserve_ds_buffers(void) if (x86_pmu.pebs && !pebs_err) x86_pmu.pebs_active = 1; - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) { + /* + * Ignores wrmsr_on_cpu() errors for offline CPUs they + * will get this call through intel_pmu_cpu_starting(). + */ init_debug_store_on_cpu(cpu); + } } - - put_online_cpus(); } /* diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 005908ee9333..a2efb490f743 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -755,14 +755,14 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsx_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init), diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a9e57f08bfa6..98722773391d 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -136,6 +136,7 @@ extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void lapic_shutdown(void); extern void sync_Arb_IDs(void); +extern void init_bsp_APIC(void); extern void apic_intr_mode_init(void); extern void setup_local_APIC(void); extern void init_apic_mappings(void); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 0927cdc4f946..1908214b9125 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -38,5 +38,4 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -INDIRECT_THUNK(sp) #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index f275447862f4..25b9375c1484 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -206,11 +206,11 @@ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ #define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -245,6 +245,7 @@ #define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c9459a4c3c68..22c5f3e6f820 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -39,7 +39,7 @@ void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); -void __init sme_encrypt_kernel(void); +void __init sme_encrypt_kernel(struct boot_params *bp); void __init sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); @@ -67,7 +67,7 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } -static inline void __init sme_encrypt_kernel(void) { } +static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } static inline void __init sme_enable(struct boot_params *bp) { } static inline bool sme_active(void) { return false; } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 402a11c803c3..4ad41087ce0e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -11,7 +11,7 @@ * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; jmp' loop to capture speculative execution. + * infinite 'pause; lfence; jmp' loop to capture speculative execution. * * This is required in various cases for retpoline and IBRS-based * mitigations for the Spectre variant 2 vulnerability. Sometimes to @@ -38,11 +38,13 @@ call 772f; \ 773: /* speculation trap */ \ pause; \ + lfence; \ jmp 773b; \ 772: \ call 774f; \ 775: /* speculation trap */ \ pause; \ + lfence; \ jmp 775b; \ 774: \ dec reg; \ @@ -73,6 +75,7 @@ call .Ldo_rop_\@ .Lspec_trap_\@: pause + lfence jmp .Lspec_trap_\@ .Ldo_rop_\@: mov \reg, (%_ASM_SP) @@ -165,6 +168,7 @@ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ + " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: addl $4, %%esp;\n" \ @@ -190,6 +194,9 @@ enum spectre_v2_mitigation { SPECTRE_V2_IBRS, }; +extern char __indirect_thunk_start[]; +extern char __indirect_thunk_end[]; + /* * On VMEXIT we must ensure that no RSB predictions learned in the guest * can be followed in the host, by overwriting the RSB completely. Both @@ -199,16 +206,17 @@ enum spectre_v2_mitigation { static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - unsigned long loops = RSB_CLEAR_LOOPS / 2; + unsigned long loops; asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE ALTERNATIVE("jmp 910f", __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), X86_FEATURE_RETPOLINE) "910:" - : "=&r" (loops), ASM_CALL_CONSTRAINT - : "r" (loops) : "memory" ); + : "=r" (loops), ASM_CALL_CONSTRAINT + : : "memory" ); #endif } + #endif /* __ASSEMBLY__ */ #endif /* __NOSPEC_BRANCH_H__ */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 00223333821a..d25a638a2720 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -62,8 +62,6 @@ struct thread_info { .flags = 0, \ } -#define init_stack (init_thread_union.stack) - #else /* !__ASSEMBLY__ */ #include <asm/asm-offsets.h> diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 31051f35cbb7..3de69330e6c5 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -88,6 +88,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *, long); #endif +dotraplinkage void do_mce(struct pt_regs *, long); static inline int get_si_code(unsigned long condition) { diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 81bb565f4497..7e2baf7304ae 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -29,10 +29,13 @@ KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y -OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y OBJECT_FILES_NON_STANDARD_paravirt_patch_$(BITS).o := y +ifdef CONFIG_FRAME_POINTER +OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y +endif + # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, # boot, dumpstack/stacktrace, etc are either non-interesting or can lead to diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 880441f24146..25ddf02598d2 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1286,6 +1286,55 @@ static int __init apic_intr_mode_select(void) return APIC_SYMMETRIC_IO; } +/* + * An initial setup of the virtual wire mode. + */ +void __init init_bsp_APIC(void) +{ + unsigned int value; + + /* + * Don't do the setup now if we have a SMP BIOS as the + * through-I/O-APIC virtual wire mode might be active. + */ + if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC)) + return; + + /* + * Do not trust the local APIC being empty at bootup. + */ + clear_local_APIC(); + + /* + * Enable APIC. + */ + value = apic_read(APIC_SPIV); + value &= ~APIC_VECTOR_MASK; + value |= APIC_SPIV_APIC_ENABLED; + +#ifdef CONFIG_X86_32 + /* This bit is reserved on P4/Xeon and should be cleared */ + if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && + (boot_cpu_data.x86 == 15)) + value &= ~APIC_SPIV_FOCUS_DISABLED; + else +#endif + value |= APIC_SPIV_FOCUS_DISABLED; + value |= SPURIOUS_APIC_VECTOR; + apic_write(APIC_SPIV, value); + + /* + * Set up the virtual wire mode. + */ + apic_write(APIC_LVT0, APIC_DM_EXTINT); + value = APIC_DM_NMI; + if (!lapic_is_integrated()) /* 82489DX */ + value |= APIC_LVT_LEVEL_TRIGGER; + if (apic_extnmi == APIC_EXTNMI_NONE) + value |= APIC_LVT_MASKED; + apic_write(APIC_LVT1, value); +} + /* Init the interrupt delivery mode for the BSP */ void __init apic_intr_mode_init(void) { diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f8b03bb8e725..3cc471beb50b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -542,14 +542,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, err = assign_irq_vector_policy(irqd, info); trace_vector_setup(virq + i, false, err); - if (err) + if (err) { + irqd->chip_data = NULL; + free_apic_chip_data(apicd); goto error; + } } return 0; error: - x86_vector_free_irqs(domain, virq, i + 1); + x86_vector_free_irqs(domain, virq, i); return err; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index e4dc26185aa7..390b3dc3d438 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -23,6 +23,7 @@ #include <asm/alternative.h> #include <asm/pgtable.h> #include <asm/set_memory.h> +#include <asm/intel-family.h> static void __init spectre_v2_select_mitigation(void); @@ -155,6 +156,23 @@ disable: return SPECTRE_V2_CMD_NONE; } +/* Check for Skylake-like CPUs (for RSB handling) */ +static bool __init is_skylake_era(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + return true; + } + } + return false; +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -213,6 +231,24 @@ retpoline_auto: spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); + + /* + * If neither SMEP or KPTI are available, there is a risk of + * hitting userspace addresses in the RSB after a context switch + * from a shallow call stack to a deeper one. To prevent this fill + * the entire RSB, even when using IBRS. + * + * Skylake era CPUs have a separate issue with *underflow* of the + * RSB, when they will predict 'ret' targets from the generic BTB. + * The proper mitigation for this is IBRS. If IBRS is not supported + * or deactivated in favour of retpolines the RSB fill on context + * switch is required. + */ + if ((!boot_cpu_has(X86_FEATURE_PTI) && + !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); + pr_info("Filling RSB on context switch\n"); + } } #undef pr_fmt diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 88dcf8479013..99442370de40 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -525,10 +525,6 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) */ if (static_branch_unlikely(&rdt_mon_enable_key)) rmdir_mondata_subdir_allrdtgrp(r, d->id); - kfree(d->ctrl_val); - kfree(d->rmid_busy_llc); - kfree(d->mbm_total); - kfree(d->mbm_local); list_del(&d->list); if (is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); @@ -545,6 +541,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cancel_delayed_work(&d->cqm_limbo); } + kfree(d->ctrl_val); + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); kfree(d); return; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index b1d616d08eee..868e412b4f0c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1785,6 +1785,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code) void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; +dotraplinkage void do_mce(struct pt_regs *regs, long error_code) +{ + machine_check_vector(regs, error_code); +} + /* * Called for each booted CPU to set up machine checks. * Must be called with preempt off: diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index c4fa4a85d4cb..e4fc595cd6ea 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -239,7 +239,7 @@ static int __init save_microcode_in_initrd(void) break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(cpuid_eax(1)); + ret = save_microcode_in_initrd_amd(cpuid_eax(1)); break; default: break; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index d9e460fc7a3b..f7c55b0e753a 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -45,6 +45,9 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; /* Current microcode patch used in early patching on the APs. */ static struct microcode_intel *intel_ucode_patch; +/* last level cache size per core */ +static int llc_size_per_core; + static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, unsigned int s2, unsigned int p2) { @@ -912,12 +915,14 @@ static bool is_blacklisted(unsigned int cpu) /* * Late loading on model 79 with microcode revision less than 0x0b000021 - * may result in a system hang. This behavior is documented in item - * BDF90, #334165 (Intel Xeon Processor E7-8800/4800 v4 Product Family). + * and LLC size per core bigger than 2.5MB may result in a system hang. + * This behavior is documented in item BDF90, #334165 (Intel Xeon + * Processor E7-8800/4800 v4 Product Family). */ if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X && c->x86_mask == 0x01 && + llc_size_per_core > 2621440 && c->microcode < 0x0b000021) { pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); @@ -975,6 +980,15 @@ static struct microcode_ops microcode_intel_ops = { .apply_microcode = apply_microcode_intel, }; +static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) +{ + u64 llc_size = c->x86_cache_size * 1024; + + do_div(llc_size, c->x86_max_cores); + + return (int)llc_size; +} + struct microcode_ops * __init init_intel_microcode(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -985,5 +999,7 @@ struct microcode_ops * __init init_intel_microcode(void) return NULL; } + llc_size_per_core = calc_llc_size_per_core(c); + return µcode_intel_ops; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 05459ad3db46..d0e69769abfd 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -21,7 +21,6 @@ struct cpuid_bit { static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 }, { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 7cb8ba08beb9..91b2cff4b79a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -8,6 +8,7 @@ #include <asm/ftrace.h> #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/unwind_hints.h> .code64 .section .entry.text, "ax" @@ -20,7 +21,6 @@ EXPORT_SYMBOL(__fentry__) EXPORT_SYMBOL(mcount) #endif -/* All cases save the original rbp (8 bytes) */ #ifdef CONFIG_FRAME_POINTER # ifdef CC_USING_FENTRY /* Save parent and function stack frames (rip and rbp) */ @@ -31,7 +31,7 @@ EXPORT_SYMBOL(mcount) # endif #else /* No need to save a stack frame */ -# define MCOUNT_FRAME_SIZE 8 +# define MCOUNT_FRAME_SIZE 0 #endif /* CONFIG_FRAME_POINTER */ /* Size of stack used to save mcount regs in save_mcount_regs */ @@ -64,10 +64,10 @@ EXPORT_SYMBOL(mcount) */ .macro save_mcount_regs added=0 - /* Always save the original rbp */ +#ifdef CONFIG_FRAME_POINTER + /* Save the original rbp */ pushq %rbp -#ifdef CONFIG_FRAME_POINTER /* * Stack traces will stop at the ftrace trampoline if the frame pointer * is not set up properly. If fentry is used, we need to save a frame @@ -105,7 +105,11 @@ EXPORT_SYMBOL(mcount) * Save the original RBP. Even though the mcount ABI does not * require this, it helps out callers. */ +#ifdef CONFIG_FRAME_POINTER movq MCOUNT_REG_SIZE-8(%rsp), %rdx +#else + movq %rbp, %rdx +#endif movq %rdx, RBP(%rsp) /* Copy the parent address into %rsi (second parameter) */ @@ -148,7 +152,7 @@ EXPORT_SYMBOL(mcount) ENTRY(function_hook) retq -END(function_hook) +ENDPROC(function_hook) ENTRY(ftrace_caller) /* save_mcount_regs fills in first two parameters */ @@ -184,7 +188,7 @@ GLOBAL(ftrace_graph_call) /* This is weak to keep gas from relaxing the jumps */ WEAK(ftrace_stub) retq -END(ftrace_caller) +ENDPROC(ftrace_caller) ENTRY(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ @@ -255,7 +259,7 @@ GLOBAL(ftrace_regs_caller_end) jmp ftrace_epilogue -END(ftrace_regs_caller) +ENDPROC(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ @@ -291,7 +295,7 @@ trace: restore_mcount_regs jmp fgraph_trace -END(function_hook) +ENDPROC(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -313,9 +317,10 @@ ENTRY(ftrace_graph_caller) restore_mcount_regs retq -END(ftrace_graph_caller) +ENDPROC(ftrace_graph_caller) -GLOBAL(return_to_handler) +ENTRY(return_to_handler) + UNWIND_HINT_EMPTY subq $24, %rsp /* Save the return values */ @@ -330,4 +335,5 @@ GLOBAL(return_to_handler) movq (%rsp), %rax addq $24, %rsp JMP_NOSPEC %rdi +END(return_to_handler) #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 6a5d757b9cfd..7ba5d819ebe3 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -157,8 +157,8 @@ unsigned long __head __startup_64(unsigned long physaddr, p = fixup_pointer(&phys_base, physaddr); *p += load_delta - sme_get_me_mask(); - /* Encrypt the kernel (if SME is active) */ - sme_encrypt_kernel(); + /* Encrypt the kernel and related (if SME is active) */ + sme_encrypt_kernel(bp); /* * Return the SME encryption mask (if SME is active) to be used as a diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index d985cef3984f..56d99be3706a 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -56,7 +56,7 @@ struct idt_data { * Early traps running on the DEFAULT_STACK because the other interrupt * stacks work only after cpu_init(). */ -static const __initdata struct idt_data early_idts[] = { +static const __initconst struct idt_data early_idts[] = { INTG(X86_TRAP_DB, debug), SYSG(X86_TRAP_BP, int3), #ifdef CONFIG_X86_32 @@ -70,7 +70,7 @@ static const __initdata struct idt_data early_idts[] = { * the traps which use them are reinitialized with IST after cpu_init() has * set up TSS. */ -static const __initdata struct idt_data def_idts[] = { +static const __initconst struct idt_data def_idts[] = { INTG(X86_TRAP_DE, divide_error), INTG(X86_TRAP_NMI, nmi), INTG(X86_TRAP_BR, bounds), @@ -108,7 +108,7 @@ static const __initdata struct idt_data def_idts[] = { /* * The APIC and SMP idt entries */ -static const __initdata struct idt_data apic_idts[] = { +static const __initconst struct idt_data apic_idts[] = { #ifdef CONFIG_SMP INTG(RESCHEDULE_VECTOR, reschedule_interrupt), INTG(CALL_FUNCTION_VECTOR, call_function_interrupt), @@ -150,7 +150,7 @@ static const __initdata struct idt_data apic_idts[] = { * Early traps running on the DEFAULT_STACK because the other interrupt * stacks work only after cpu_init(). */ -static const __initdata struct idt_data early_pf_idts[] = { +static const __initconst struct idt_data early_pf_idts[] = { INTG(X86_TRAP_PF, page_fault), }; @@ -158,7 +158,7 @@ static const __initdata struct idt_data early_pf_idts[] = { * Override for the debug_idt. Same as the default, but with interrupt * stack set to DEFAULT_STACK (0). Required for NMI trap handling. */ -static const __initdata struct idt_data dbg_idts[] = { +static const __initconst struct idt_data dbg_idts[] = { INTG(X86_TRAP_DB, debug), INTG(X86_TRAP_BP, int3), }; @@ -180,7 +180,7 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; * The exceptions which use Interrupt stacks. They are setup after * cpu_init() when the TSS has been initialized. */ -static const __initdata struct idt_data ist_idts[] = { +static const __initconst struct idt_data ist_idts[] = { ISTG(X86_TRAP_DB, debug, DEBUG_STACK), ISTG(X86_TRAP_NMI, nmi, NMI_STACK), SISTG(X86_TRAP_BP, int3, DEBUG_STACK), diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 8da3e909e967..a539410c4ea9 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -61,6 +61,9 @@ void __init init_ISA_irqs(void) struct irq_chip *chip = legacy_pic->chip; int i; +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) + init_bsp_APIC(); +#endif legacy_pic->init(0); for (i = 0; i < nr_legacy_irqs(); i++) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index e941136e24d8..203d398802a3 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -40,6 +40,7 @@ #include <asm/debugreg.h> #include <asm/set_memory.h> #include <asm/sections.h> +#include <asm/nospec-branch.h> #include "common.h" @@ -203,7 +204,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) } /* Check whether insn is indirect jump */ -static int insn_is_indirect_jump(struct insn *insn) +static int __insn_is_indirect_jump(struct insn *insn) { return ((insn->opcode.bytes[0] == 0xff && (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ @@ -237,6 +238,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) return (start <= target && target <= start + len); } +static int insn_is_indirect_jump(struct insn *insn) +{ + int ret = __insn_is_indirect_jump(insn); + +#ifdef CONFIG_RETPOLINE + /* + * Jump to x86_indirect_thunk_* is treated as an indirect jump. + * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with + * older gcc may use indirect jump. So we add this check instead of + * replace indirect-jump check. + */ + if (!ret) + ret = insn_jump_into_range(insn, + (unsigned long)__indirect_thunk_start, + (unsigned long)__indirect_thunk_end - + (unsigned long)__indirect_thunk_start); +#endif + return ret; +} + /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 832a6acd730f..cb368c2a22ab 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -380,19 +380,24 @@ void stop_this_cpu(void *dummy) disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); + /* + * Use wbinvd on processors that support SME. This provides support + * for performing a successful kexec when going from SME inactive + * to SME active (or vice-versa). The cache must be cleared so that + * if there are entries with the same physical address, both with and + * without the encryption bit, they don't race each other when flushed + * and potentially end up with the wrong entry being committed to + * memory. + */ + if (boot_cpu_has(X86_FEATURE_SME)) + native_wbinvd(); for (;;) { /* - * Use wbinvd followed by hlt to stop the processor. This - * provides support for kexec on a processor that supports - * SME. With kexec, going from SME inactive to SME active - * requires clearing cache entries so that addresses without - * the encryption bit set don't corrupt the same physical - * address that has the encryption bit set when caches are - * flushed. To achieve this a wbinvd is performed followed by - * a hlt. Even if the processor is not in the kexec/SME - * scenario this only adds a wbinvd to a halting processor. + * Use native_halt() so that memory contents don't change + * (stack usage and variables) after possibly issuing the + * native_wbinvd() above. */ - asm volatile("wbinvd; hlt" : : : "memory"); + native_halt(); } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 145810b0edf6..68d7ab81c62f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -364,16 +364,6 @@ static void __init reserve_initrd(void) !ramdisk_image || !ramdisk_size) return; /* No initrd provided by bootloader */ - /* - * If SME is active, this memory will be marked encrypted by the - * kernel when it is accessed (including relocation). However, the - * ramdisk image was loaded decrypted by the bootloader, so make - * sure that it is encrypted before accessing it. For SEV the - * ramdisk will already be encrypted, so only do this for SME. - */ - if (sme_active()) - sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image); - initrd_start = 0; mapped_size = memblock_mem_size(max_pfn_mapped); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 8ea117f8142e..e169e85db434 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -602,7 +602,6 @@ unsigned long native_calibrate_tsc(void) case INTEL_FAM6_KABYLAKE_DESKTOP: crystal_khz = 24000; /* 24.0 MHz */ break; - case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_DENVERTON: crystal_khz = 25000; /* 25.0 MHz */ break; @@ -612,6 +611,8 @@ unsigned long native_calibrate_tsc(void) } } + if (crystal_khz == 0) + return 0; /* * TSC frequency determined by CPUID is a "hardware reported" * frequency and is the most accurate one so far we have. This @@ -1315,6 +1316,12 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + if (cpu_khz != tsc_khz) { + pr_info("Detected %lu.%03lu MHz TSC", + (unsigned long)tsc_khz / 1000, + (unsigned long)tsc_khz % 1000); + } + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ tsc_store_and_check_tsc_adjust(true); diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index be86a865087a..1f9188f5357c 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -74,8 +74,50 @@ static struct orc_entry *orc_module_find(unsigned long ip) } #endif +#ifdef CONFIG_DYNAMIC_FTRACE +static struct orc_entry *orc_find(unsigned long ip); + +/* + * Ftrace dynamic trampolines do not have orc entries of their own. + * But they are copies of the ftrace entries that are static and + * defined in ftrace_*.S, which do have orc entries. + * + * If the undwinder comes across a ftrace trampoline, then find the + * ftrace function that was used to create it, and use that ftrace + * function's orc entrie, as the placement of the return code in + * the stack will be identical. + */ +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + struct ftrace_ops *ops; + unsigned long caller; + + ops = ftrace_ops_trampoline(ip); + if (!ops) + return NULL; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + caller = (unsigned long)ftrace_regs_call; + else + caller = (unsigned long)ftrace_call; + + /* Prevent unlikely recursion */ + if (ip == caller) + return NULL; + + return orc_find(caller); +} +#else +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + return NULL; +} +#endif + static struct orc_entry *orc_find(unsigned long ip) { + static struct orc_entry *orc; + if (!orc_init) return NULL; @@ -111,7 +153,11 @@ static struct orc_entry *orc_find(unsigned long ip) __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); /* Module lookup: */ - return orc_module_find(ip); + orc = orc_module_find(ip); + if (orc) + return orc; + + return orc_ftrace_find(ip); } static void orc_sort_swap(void *_a, void *_b, int size) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 1e413a9326aa..9b138a06c1a4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -124,6 +124,12 @@ SECTIONS ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); #endif +#ifdef CONFIG_RETPOLINE + __indirect_thunk_start = .; + *(.text.__x86.indirect_thunk) + __indirect_thunk_end = .; +#endif + /* End of text section */ _etext = .; } :text = 0x9090 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1cec2c62a0b0..c53298dfbf50 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7496,13 +7496,13 @@ EXPORT_SYMBOL_GPL(kvm_task_switch); int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) { + if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in * 64-bit mode (though maybe in a 32-bit code segment). * CR4.PAE and EFER.LMA must be set. */ - if (!(sregs->cr4 & X86_CR4_PAE_BIT) + if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return -EINVAL; } else { diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index cb45c6cb465f..c909961e678a 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -9,7 +9,7 @@ #include <asm/nospec-branch.h> .macro THUNK reg - .section .text.__x86.indirect_thunk.\reg + .section .text.__x86.indirect_thunk ENTRY(__x86_indirect_thunk_\reg) CFI_STARTPROC @@ -25,7 +25,8 @@ ENDPROC(__x86_indirect_thunk_\reg) * than one per register with the correct names. So we do it * the simple and nasty way... */ -#define EXPORT_THUNK(reg) EXPORT_SYMBOL(__x86_indirect_thunk_ ## reg) +#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym) +#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) #define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) GENERATE_THUNK(_ASM_AX) @@ -35,7 +36,6 @@ GENERATE_THUNK(_ASM_DX) GENERATE_THUNK(_ASM_SI) GENERATE_THUNK(_ASM_DI) GENERATE_THUNK(_ASM_BP) -GENERATE_THUNK(_ASM_SP) #ifdef CONFIG_64BIT GENERATE_THUNK(r8) GENERATE_THUNK(r9) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 06fe3d51d385..800de815519c 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -172,14 +172,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) +static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info, + u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return; /* Fault not from Protection Keys: nothing to do */ - if (si_code != SEGV_PKUERR) + if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV)) return; /* * force_sig_info_fault() is called from a number of @@ -218,7 +219,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, pkey); + fill_sig_info_pkey(si_signo, si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } @@ -438,18 +439,13 @@ static noinline int vmalloc_fault(unsigned long address) if (pgd_none(*pgd_ref)) return -1; - if (pgd_none(*pgd)) { - set_pgd(pgd, *pgd_ref); - arch_flush_lazy_mmu_mode(); - } else if (CONFIG_PGTABLE_LEVELS > 4) { - /* - * With folded p4d, pgd_none() is always false, so the pgd may - * point to an empty page table entry and pgd_page_vaddr() - * will return garbage. - * - * We will do the correct sanity check on the p4d level. - */ - BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + if (CONFIG_PGTABLE_LEVELS > 4) { + if (pgd_none(*pgd)) { + set_pgd(pgd, *pgd_ref); + arch_flush_lazy_mmu_mode(); + } else { + BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + } } /* With 4-level paging, copying happens on the p4d level. */ @@ -458,7 +454,7 @@ static noinline int vmalloc_fault(unsigned long address) if (p4d_none(*p4d_ref)) return -1; - if (p4d_none(*p4d)) { + if (p4d_none(*p4d) && CONFIG_PGTABLE_LEVELS == 4) { set_p4d(p4d, *p4d_ref); arch_flush_lazy_mmu_mode(); } else { @@ -469,6 +465,7 @@ static noinline int vmalloc_fault(unsigned long address) * Below here mismatches are bugs because these lower tables * are shared: */ + BUILD_BUG_ON(CONFIG_PGTABLE_LEVELS < 4); pud = pud_offset(p4d, address); pud_ref = pud_offset(p4d_ref, address); diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 47388f0c0e59..af6f2f9c6a26 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -21,10 +21,14 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES]; static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -static __init void *early_alloc(size_t size, int nid) +static __init void *early_alloc(size_t size, int nid, bool panic) { - return memblock_virt_alloc_try_nid_nopanic(size, size, - __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + if (panic) + return memblock_virt_alloc_try_nid(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + else + return memblock_virt_alloc_try_nid_nopanic(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); } static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, @@ -38,14 +42,14 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (boot_cpu_has(X86_FEATURE_PSE) && ((end - addr) == PMD_SIZE) && IS_ALIGNED(addr, PMD_SIZE)) { - p = early_alloc(PMD_SIZE, nid); + p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PMD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pmd_populate_kernel(&init_mm, pmd, p); } @@ -57,7 +61,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (!pte_none(*pte)) continue; - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL); set_pte_at(&init_mm, addr, pte, entry); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -75,14 +79,14 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, if (boot_cpu_has(X86_FEATURE_GBPAGES) && ((end - addr) == PUD_SIZE) && IS_ALIGNED(addr, PUD_SIZE)) { - p = early_alloc(PUD_SIZE, nid); + p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PUD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pud_populate(&init_mm, pud, p); } @@ -101,7 +105,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, unsigned long next; if (p4d_none(*p4d)) { - void *p = early_alloc(PAGE_SIZE, nid); + void *p = early_alloc(PAGE_SIZE, nid, true); p4d_populate(&init_mm, p4d, p); } @@ -122,7 +126,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr, unsigned long next; if (pgd_none(*pgd)) { - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pgd_populate(&init_mm, pgd, p); } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 391b13402e40..e1d61e8500f9 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -464,37 +464,62 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size) set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT); } -static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start, - unsigned long end) +struct sme_populate_pgd_data { + void *pgtable_area; + pgd_t *pgd; + + pmdval_t pmd_flags; + pteval_t pte_flags; + unsigned long paddr; + + unsigned long vaddr; + unsigned long vaddr_end; +}; + +static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; - pgd_start = start & PGDIR_MASK; - pgd_end = end & PGDIR_MASK; + pgd_start = ppd->vaddr & PGDIR_MASK; + pgd_end = ppd->vaddr_end & PGDIR_MASK; - pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1); - pgd_size *= sizeof(pgd_t); + pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t); - pgd_p = pgd_base + pgd_index(start); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); memset(pgd_p, 0, pgd_size); } -#define PGD_FLAGS _KERNPG_TABLE_NOENC -#define P4D_FLAGS _KERNPG_TABLE_NOENC -#define PUD_FLAGS _KERNPG_TABLE_NOENC -#define PMD_FLAGS (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) +#define PGD_FLAGS _KERNPG_TABLE_NOENC +#define P4D_FLAGS _KERNPG_TABLE_NOENC +#define PUD_FLAGS _KERNPG_TABLE_NOENC +#define PMD_FLAGS _KERNPG_TABLE_NOENC + +#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) + +#define PMD_FLAGS_DEC PMD_FLAGS_LARGE +#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) + +#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL) + +#define PTE_FLAGS_DEC PTE_FLAGS +#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC) -static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, - unsigned long vaddr, pmdval_t pmd_val) +static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd_p; p4d_t *p4d_p; pud_t *pud_p; pmd_t *pmd_p; - pgd_p = pgd_base + pgd_index(vaddr); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); if (native_pgd_val(*pgd_p)) { if (IS_ENABLED(CONFIG_X86_5LEVEL)) p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); @@ -504,15 +529,15 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, pgd_t pgd; if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p = pgtable_area; + p4d_p = ppd->pgtable_area; memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); - pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; + ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS); } else { - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS); } @@ -520,58 +545,160 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, } if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p += p4d_index(vaddr); + p4d_p += p4d_index(ppd->vaddr); if (native_p4d_val(*p4d_p)) { pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK); } else { p4d_t p4d; - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS); native_set_p4d(p4d_p, p4d); } } - pud_p += pud_index(vaddr); + pud_p += pud_index(ppd->vaddr); if (native_pud_val(*pud_p)) { if (native_pud_val(*pud_p) & _PAGE_PSE) - goto out; + return NULL; pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK); } else { pud_t pud; - pmd_p = pgtable_area; + pmd_p = ppd->pgtable_area; memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); - pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; + ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS); native_set_pud(pud_p, pud); } - pmd_p += pmd_index(vaddr); + return pmd_p; +} + +static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE)) - native_set_pmd(pmd_p, native_make_pmd(pmd_val)); + native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags)); +} -out: - return pgtable_area; +static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + pte_t *pte_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); + if (native_pmd_val(*pmd_p)) { + if (native_pmd_val(*pmd_p) & _PAGE_PSE) + return; + + pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK); + } else { + pmd_t pmd; + + pte_p = ppd->pgtable_area; + memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE); + ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE; + + pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS); + native_set_pmd(pmd_p, pmd); + } + + pte_p += pte_index(ppd->vaddr); + if (!native_pte_val(*pte_p)) + native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags)); +} + +static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd_large(ppd); + + ppd->vaddr += PMD_PAGE_SIZE; + ppd->paddr += PMD_PAGE_SIZE; + } +} + +static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd(ppd); + + ppd->vaddr += PAGE_SIZE; + ppd->paddr += PAGE_SIZE; + } +} + +static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, + pmdval_t pmd_flags, pteval_t pte_flags) +{ + unsigned long vaddr_end; + + ppd->pmd_flags = pmd_flags; + ppd->pte_flags = pte_flags; + + /* Save original end value since we modify the struct value */ + vaddr_end = ppd->vaddr_end; + + /* If start is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE); + __sme_map_range_pte(ppd); + + /* Create PMD entries */ + ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK; + __sme_map_range_pmd(ppd); + + /* If end is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = vaddr_end; + __sme_map_range_pte(ppd); +} + +static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); +} + +static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); +} + +static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } static unsigned long __init sme_pgtable_calc(unsigned long len) { - unsigned long p4d_size, pud_size, pmd_size; + unsigned long p4d_size, pud_size, pmd_size, pte_size; unsigned long total; /* * Perform a relatively simplistic calculation of the pagetable - * entries that are needed. That mappings will be covered by 2MB - * PMD entries so we can conservatively calculate the required + * entries that are needed. Those mappings will be covered mostly + * by 2MB PMD entries so we can conservatively calculate the required * number of P4D, PUD and PMD structures needed to perform the - * mappings. Incrementing the count for each covers the case where - * the addresses cross entries. + * mappings. For mappings that are not 2MB aligned, PTE mappings + * would be needed for the start and end portion of the address range + * that fall outside of the 2MB alignment. This results in, at most, + * two extra pages to hold PTE entries for each range that is mapped. + * Incrementing the count for each covers the case where the addresses + * cross entries. */ if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; @@ -585,8 +712,9 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) } pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1; pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; + pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE; - total = p4d_size + pud_size + pmd_size; + total = p4d_size + pud_size + pmd_size + pte_size; /* * Now calculate the added pagetable structures needed to populate @@ -610,29 +738,29 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return total; } -void __init sme_encrypt_kernel(void) +void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; unsigned long kernel_start, kernel_end, kernel_len; + unsigned long initrd_start, initrd_end, initrd_len; + struct sme_populate_pgd_data ppd; unsigned long pgtable_area_len; - unsigned long paddr, pmd_flags; unsigned long decrypted_base; - void *pgtable_area; - pgd_t *pgd; if (!sme_active()) return; /* - * Prepare for encrypting the kernel by building new pagetables with - * the necessary attributes needed to encrypt the kernel in place. + * Prepare for encrypting the kernel and initrd by building new + * pagetables with the necessary attributes needed to encrypt the + * kernel in place. * * One range of virtual addresses will map the memory occupied - * by the kernel as encrypted. + * by the kernel and initrd as encrypted. * * Another range of virtual addresses will map the memory occupied - * by the kernel as decrypted and write-protected. + * by the kernel and initrd as decrypted and write-protected. * * The use of write-protect attribute will prevent any of the * memory from being cached. @@ -643,6 +771,20 @@ void __init sme_encrypt_kernel(void) kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); kernel_len = kernel_end - kernel_start; + initrd_start = 0; + initrd_end = 0; + initrd_len = 0; +#ifdef CONFIG_BLK_DEV_INITRD + initrd_len = (unsigned long)bp->hdr.ramdisk_size | + ((unsigned long)bp->ext_ramdisk_size << 32); + if (initrd_len) { + initrd_start = (unsigned long)bp->hdr.ramdisk_image | + ((unsigned long)bp->ext_ramdisk_image << 32); + initrd_end = PAGE_ALIGN(initrd_start + initrd_len); + initrd_len = initrd_end - initrd_start; + } +#endif + /* Set the encryption workarea to be immediately after the kernel */ workarea_start = kernel_end; @@ -665,16 +807,21 @@ void __init sme_encrypt_kernel(void) */ pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD; pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2; + if (initrd_len) + pgtable_area_len += sme_pgtable_calc(initrd_len) * 2; /* PUDs and PMDs needed in the current pagetables for the workarea */ pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len); /* * The total workarea includes the executable encryption area and - * the pagetable area. + * the pagetable area. The start of the workarea is already 2MB + * aligned, align the end of the workarea on a 2MB boundary so that + * we don't try to create/allocate PTE entries from the workarea + * before it is mapped. */ workarea_len = execute_len + pgtable_area_len; - workarea_end = workarea_start + workarea_len; + workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE); /* * Set the address to the start of where newly created pagetable @@ -683,45 +830,30 @@ void __init sme_encrypt_kernel(void) * pagetables and when the new encrypted and decrypted kernel * mappings are populated. */ - pgtable_area = (void *)execute_end; + ppd.pgtable_area = (void *)execute_end; /* * Make sure the current pagetable structure has entries for * addressing the workarea. */ - pgd = (pgd_t *)native_read_cr3_pa(); - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = (pgd_t *)native_read_cr3_pa(); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); /* * A new pagetable structure is being built to allow for the kernel - * to be encrypted. It starts with an empty PGD that will then be - * populated with new PUDs and PMDs as the encrypted and decrypted - * kernel mappings are created. + * and initrd to be encrypted. It starts with an empty PGD that will + * then be populated with new PUDs and PMDs as the encrypted and + * decrypted kernel mappings are created. */ - pgd = pgtable_area; - memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD); - pgtable_area += sizeof(*pgd) * PTRS_PER_PGD; - - /* Add encrypted kernel (identity) mappings */ - pmd_flags = PMD_FLAGS | _PAGE_ENC; - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = ppd.pgtable_area; + memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD); + ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD; /* * A different PGD index/entry must be used to get different @@ -730,47 +862,79 @@ void __init sme_encrypt_kernel(void) * the base of the mapping. */ decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1); + if (initrd_len) { + unsigned long check_base; + + check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1); + decrypted_base = max(decrypted_base, check_base); + } decrypted_base <<= PGDIR_SHIFT; + /* Add encrypted kernel (identity) mappings */ + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start; + ppd.vaddr_end = kernel_end; + sme_map_range_encrypted(&ppd); + /* Add decrypted, write-protected kernel (non-identity) mappings */ - pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT); - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); + + if (initrd_len) { + /* Add encrypted initrd (identity) mappings */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start; + ppd.vaddr_end = initrd_end; + sme_map_range_encrypted(&ppd); + /* + * Add decrypted, write-protected initrd (non-identity) mappings + */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); } /* Add decrypted workarea mappings to both kernel mappings */ - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_map_range_decrypted(&ppd); /* Perform the encryption */ sme_encrypt_execute(kernel_start, kernel_start + decrypted_base, - kernel_len, workarea_start, (unsigned long)pgd); + kernel_len, workarea_start, (unsigned long)ppd.pgd); + + if (initrd_len) + sme_encrypt_execute(initrd_start, initrd_start + decrypted_base, + initrd_len, workarea_start, + (unsigned long)ppd.pgd); /* * At this point we are running encrypted. Remove the mappings for * the decrypted areas - all that is needed for this is to remove * the PGD entry/entries. */ - sme_clear_pgd(pgd, kernel_start + decrypted_base, - kernel_end + decrypted_base); + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_clear_pgd(&ppd); + + if (initrd_len) { + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_clear_pgd(&ppd); + } - sme_clear_pgd(pgd, workarea_start + decrypted_base, - workarea_end + decrypted_base); + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_clear_pgd(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 730e6d541df1..01f682cf77a8 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -22,9 +22,9 @@ ENTRY(sme_encrypt_execute) /* * Entry parameters: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping - * RDX - length of kernel + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping + * RDX - length to encrypt * RCX - virtual address of the encryption workarea, including: * - stack page (PAGE_SIZE) * - encryption routine page (PAGE_SIZE) @@ -41,9 +41,9 @@ ENTRY(sme_encrypt_execute) addq $PAGE_SIZE, %rax /* Workarea encryption routine */ push %r12 - movq %rdi, %r10 /* Encrypted kernel */ - movq %rsi, %r11 /* Decrypted kernel */ - movq %rdx, %r12 /* Kernel length */ + movq %rdi, %r10 /* Encrypted area */ + movq %rsi, %r11 /* Decrypted area */ + movq %rdx, %r12 /* Area length */ /* Copy encryption routine into the workarea */ movq %rax, %rdi /* Workarea encryption routine */ @@ -52,10 +52,10 @@ ENTRY(sme_encrypt_execute) rep movsb /* Setup registers for call */ - movq %r10, %rdi /* Encrypted kernel */ - movq %r11, %rsi /* Decrypted kernel */ + movq %r10, %rdi /* Encrypted area */ + movq %r11, %rsi /* Decrypted area */ movq %r8, %rdx /* Pagetables used for encryption */ - movq %r12, %rcx /* Kernel length */ + movq %r12, %rcx /* Area length */ movq %rax, %r8 /* Workarea encryption routine */ addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ @@ -71,7 +71,7 @@ ENDPROC(sme_encrypt_execute) ENTRY(__enc_copy) /* - * Routine used to encrypt kernel. + * Routine used to encrypt memory in place. * This routine must be run outside of the kernel proper since * the kernel will be encrypted during the process. So this * routine is defined here and then copied to an area outside @@ -79,19 +79,19 @@ ENTRY(__enc_copy) * during execution. * * On entry the registers must be: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping * RDX - address of the pagetables to use for encryption - * RCX - length of kernel + * RCX - length of area * R8 - intermediate copy buffer * * RAX - points to this routine * - * The kernel will be encrypted by copying from the non-encrypted - * kernel space to an intermediate buffer and then copying from the - * intermediate buffer back to the encrypted kernel space. The physical - * addresses of the two kernel space mappings are the same which - * results in the kernel being encrypted "in place". + * The area will be encrypted by copying from the non-encrypted + * memory space to an intermediate buffer and then copying from the + * intermediate buffer back to the encrypted memory space. The physical + * addresses of the two mappings are the same which results in the area + * being encrypted "in place". */ /* Enable the new page tables */ mov %rdx, %cr3 @@ -103,47 +103,55 @@ ENTRY(__enc_copy) orq $X86_CR4_PGE, %rdx mov %rdx, %cr4 + push %r15 + push %r12 + + movq %rcx, %r9 /* Save area length */ + movq %rdi, %r10 /* Save encrypted area address */ + movq %rsi, %r11 /* Save decrypted area address */ + /* Set the PAT register PA5 entry to write-protect */ - push %rcx movl $MSR_IA32_CR_PAT, %ecx rdmsr - push %rdx /* Save original PAT value */ + mov %rdx, %r15 /* Save original PAT value */ andl $0xffff00ff, %edx /* Clear PA5 */ orl $0x00000500, %edx /* Set PA5 to WP */ wrmsr - pop %rdx /* RDX contains original PAT value */ - pop %rcx - - movq %rcx, %r9 /* Save kernel length */ - movq %rdi, %r10 /* Save encrypted kernel address */ - movq %rsi, %r11 /* Save decrypted kernel address */ wbinvd /* Invalidate any cache entries */ - /* Copy/encrypt 2MB at a time */ + /* Copy/encrypt up to 2MB at a time */ + movq $PMD_PAGE_SIZE, %r12 1: - movq %r11, %rsi /* Source - decrypted kernel */ + cmpq %r12, %r9 + jnb 2f + movq %r9, %r12 + +2: + movq %r11, %rsi /* Source - decrypted area */ movq %r8, %rdi /* Dest - intermediate copy buffer */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r12, %rcx rep movsb movq %r8, %rsi /* Source - intermediate copy buffer */ - movq %r10, %rdi /* Dest - encrypted kernel */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r10, %rdi /* Dest - encrypted area */ + movq %r12, %rcx rep movsb - addq $PMD_PAGE_SIZE, %r11 - addq $PMD_PAGE_SIZE, %r10 - subq $PMD_PAGE_SIZE, %r9 /* Kernel length decrement */ + addq %r12, %r11 + addq %r12, %r10 + subq %r12, %r9 /* Kernel length decrement */ jnz 1b /* Kernel length not zero? */ /* Restore PAT register */ - push %rdx /* Save original PAT value */ movl $MSR_IA32_CR_PAT, %ecx rdmsr - pop %rdx /* Restore original PAT value */ + mov %r15, %rdx /* Restore original PAT value */ wrmsr + pop %r12 + pop %r15 + ret .L__enc_copy_end: ENDPROC(__enc_copy) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index a1561957dccb..5bfe61a5e8e3 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -151,6 +151,34 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, local_irq_restore(flags); } +static void sync_current_stack_to_mm(struct mm_struct *mm) +{ + unsigned long sp = current_stack_pointer; + pgd_t *pgd = pgd_offset(mm, sp); + + if (CONFIG_PGTABLE_LEVELS > 4) { + if (unlikely(pgd_none(*pgd))) { + pgd_t *pgd_ref = pgd_offset_k(sp); + + set_pgd(pgd, *pgd_ref); + } + } else { + /* + * "pgd" is faked. The top level entries are "p4d"s, so sync + * the p4d. This compiles to approximately the same code as + * the 5-level case. + */ + p4d_t *p4d = p4d_offset(pgd, sp); + + if (unlikely(p4d_none(*p4d))) { + pgd_t *pgd_ref = pgd_offset_k(sp); + p4d_t *p4d_ref = p4d_offset(pgd_ref, sp); + + set_p4d(p4d, *p4d_ref); + } + } +} + void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { @@ -226,11 +254,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int index = pgd_index(current_stack_pointer); - pgd_t *pgd = next->pgd + index; - - if (unlikely(pgd_none(*pgd))) - set_pgd(pgd, init_mm.pgd[index]); + sync_current_stack_to_mm(next); } /* Stop remote flushes for the previous mm */ diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index f6a26e3cb476..54ef19e90705 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -662,11 +662,11 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid); */ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) { + static const char *name = "PCI Bus 0000:00"; + struct resource *res, *conflict; u32 base, limit, high; struct pci_dev *other; - struct resource *res; unsigned i; - int r; if (!(pci_probe & PCI_BIG_ROOT_WINDOW)) return; @@ -707,21 +707,26 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) * Allocate a 256GB window directly below the 0xfd00000000 hardware * limit (see AMD Family 15h Models 30h-3Fh BKDG, sec 2.4.6). */ - res->name = "PCI Bus 0000:00"; + res->name = name; res->flags = IORESOURCE_PREFETCH | IORESOURCE_MEM | IORESOURCE_MEM_64 | IORESOURCE_WINDOW; res->start = 0xbd00000000ull; res->end = 0xfd00000000ull - 1; - r = request_resource(&iomem_resource, res); - if (r) { + conflict = request_resource_conflict(&iomem_resource, res); + if (conflict) { kfree(res); - return; - } + if (conflict->name != name) + return; - dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n", - res); - add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + /* We are resuming from suspend; just reenable the window */ + res = conflict; + } else { + dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n", + res); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + pci_bus_add_resource(dev->bus, res, 0); + } base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) | AMD_141b_MMIO_BASE_RE_MASK | AMD_141b_MMIO_BASE_WE_MASK; @@ -733,13 +738,16 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) pci_write_config_dword(dev, AMD_141b_MMIO_HIGH(i), high); pci_write_config_dword(dev, AMD_141b_MMIO_LIMIT(i), limit); pci_write_config_dword(dev, AMD_141b_MMIO_BASE(i), base); - - pci_bus_add_resource(dev->bus, res, 0); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); #endif diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h index 7be2400f745a..2ccd37510aaa 100644 --- a/arch/xtensa/include/asm/thread_info.h +++ b/arch/xtensa/include/asm/thread_info.h @@ -77,9 +77,6 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) { |
