diff options
Diffstat (limited to 'arch')
197 files changed, 1532 insertions, 1394 deletions
diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S index 2efa7dfc798a..2d136c63db16 100644 --- a/arch/alpha/kernel/vmlinux.lds.S +++ b/arch/alpha/kernel/vmlinux.lds.S @@ -71,6 +71,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index 61a1b2b96e1d..6af63084ff28 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -123,6 +123,7 @@ SECTIONS _end = . ; STABS_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S index d411abd4310e..2d916647df03 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.S +++ b/arch/arm/boot/compressed/vmlinux.lds.S @@ -21,6 +21,7 @@ SECTIONS COMMON_DISCARDS *(.ARM.exidx*) *(.ARM.extab*) + *(.modinfo) *(.note.*) *(.rel.*) *(.printk_index) diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index f75d75cf91c8..70d05f74049e 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -279,7 +279,6 @@ CONFIG_TI_CPSW_SWITCHDEV=y CONFIG_TI_CPTS=y CONFIG_TI_KEYSTONE_NETCP=y CONFIG_TI_KEYSTONE_NETCP_ETHSS=y -CONFIG_TI_PRUSS=m CONFIG_TI_PRUETH=m CONFIG_XILINX_EMACLITE=y CONFIG_SFP=m diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index f2e8d4fac068..5afb725998ec 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -154,6 +154,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ARM_DETAILS ARM_ASSERTS diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index d592a203f9c6..c07843c3c53d 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -153,6 +153,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ARM_DETAILS ARM_ASSERTS diff --git a/arch/arm64/boot/dts/renesas/r8a78000.dtsi b/arch/arm64/boot/dts/renesas/r8a78000.dtsi index 4c97298fa763..3e1c98903cea 100644 --- a/arch/arm64/boot/dts/renesas/r8a78000.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a78000.dtsi @@ -698,7 +698,7 @@ compatible = "renesas,scif-r8a78000", "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc0700000 0 0x40>; - interrupts = <GIC_SPI 4074 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 10 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -708,7 +708,7 @@ compatible = "renesas,scif-r8a78000", "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc0704000 0 0x40>; - interrupts = <GIC_SPI 4075 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 11 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -718,7 +718,7 @@ compatible = "renesas,scif-r8a78000", "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc0708000 0 0x40>; - interrupts = <GIC_SPI 4076 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 12 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -728,7 +728,7 @@ compatible = "renesas,scif-r8a78000", "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc070c000 0 0x40>; - interrupts = <GIC_SPI 4077 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 13 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -738,7 +738,7 @@ compatible = "renesas,hscif-r8a78000", "renesas,rcar-gen5-hscif", "renesas,hscif"; reg = <0 0xc0710000 0 0x60>; - interrupts = <GIC_SPI 4078 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 14 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -748,7 +748,7 @@ compatible = "renesas,hscif-r8a78000", "renesas,rcar-gen5-hscif", "renesas,hscif"; reg = <0 0xc0714000 0 0x60>; - interrupts = <GIC_SPI 4079 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 15 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -758,7 +758,7 @@ compatible = "renesas,hscif-r8a78000", "renesas,rcar-gen5-hscif", "renesas,hscif"; reg = <0 0xc0718000 0 0x60>; - interrupts = <GIC_SPI 4080 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 16 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -768,7 +768,7 @@ compatible = "renesas,hscif-r8a78000", "renesas,rcar-gen5-hscif", "renesas,hscif"; reg = <0 0xc071c000 0 0x60>; - interrupts = <GIC_SPI 4081 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 17 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi index 80cba9fcfe7b..504c28386622 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi @@ -581,16 +581,6 @@ status = "disabled"; }; - wdt0: watchdog@11c00400 { - compatible = "renesas,r9a09g057-wdt"; - reg = <0 0x11c00400 0 0x400>; - clocks = <&cpg CPG_MOD 0x4b>, <&cpg CPG_MOD 0x4c>; - clock-names = "pclk", "oscclk"; - resets = <&cpg 0x75>; - power-domains = <&cpg>; - status = "disabled"; - }; - wdt1: watchdog@14400000 { compatible = "renesas,r9a09g057-wdt"; reg = <0 0x14400000 0 0x400>; @@ -601,26 +591,6 @@ status = "disabled"; }; - wdt2: watchdog@13000000 { - compatible = "renesas,r9a09g057-wdt"; - reg = <0 0x13000000 0 0x400>; - clocks = <&cpg CPG_MOD 0x4f>, <&cpg CPG_MOD 0x50>; - clock-names = "pclk", "oscclk"; - resets = <&cpg 0x77>; - power-domains = <&cpg>; - status = "disabled"; - }; - - wdt3: watchdog@13000400 { - compatible = "renesas,r9a09g057-wdt"; - reg = <0 0x13000400 0 0x400>; - clocks = <&cpg CPG_MOD 0x51>, <&cpg CPG_MOD 0x52>; - clock-names = "pclk", "oscclk"; - resets = <&cpg 0x78>; - power-domains = <&cpg>; - status = "disabled"; - }; - rtc: rtc@11c00800 { compatible = "renesas,r9a09g057-rtca3", "renesas,rz-rtca3"; reg = <0 0x11c00800 0 0x400>; diff --git a/arch/arm64/boot/dts/renesas/r9a09g077.dtsi b/arch/arm64/boot/dts/renesas/r9a09g077.dtsi index 14d7fb6f8952..9d0b4d8d3d5b 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g077.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a09g077.dtsi @@ -974,8 +974,8 @@ cpg: clock-controller@80280000 { compatible = "renesas,r9a09g077-cpg-mssr"; - reg = <0 0x80280000 0 0x1000>, - <0 0x81280000 0 0x9000>; + reg = <0 0x80280000 0 0x10000>, + <0 0x81280000 0 0x10000>; clocks = <&extal_clk>; clock-names = "extal"; #clock-cells = <2>; diff --git a/arch/arm64/boot/dts/renesas/r9a09g087.dtsi b/arch/arm64/boot/dts/renesas/r9a09g087.dtsi index 4a1339561332..d407c48f9966 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g087.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a09g087.dtsi @@ -977,8 +977,8 @@ cpg: clock-controller@80280000 { compatible = "renesas,r9a09g087-cpg-mssr"; - reg = <0 0x80280000 0 0x1000>, - <0 0x81280000 0 0x9000>; + reg = <0 0x80280000 0 0x10000>, + <0 0x81280000 0 0x10000>; clocks = <&extal_clk>; clock-names = "extal"; #clock-cells = <2>; diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi index 982f17aafbc5..b45acfe6288a 100644 --- a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi @@ -162,7 +162,7 @@ <100000000>; renesas,settings = [ 80 00 11 19 4c 42 dc 2f 06 7d 20 1a 5f 1e f2 27 - 00 40 00 00 00 00 00 00 06 0c 19 02 3f f0 90 86 + 00 40 00 00 00 00 00 00 06 0c 19 02 3b f0 90 86 a0 80 30 30 9c ]; }; diff --git a/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi b/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi index 510399febf29..f87c2492f414 100644 --- a/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi +++ b/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi @@ -53,6 +53,7 @@ regulator-max-microvolt = <3300000>; gpios-states = <0>; states = <3300000 0>, <1800000 1>; + regulator-ramp-delay = <60>; }; #endif diff --git a/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso b/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso index 0af1e0a6c7f4..fc53c1aae3b5 100644 --- a/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso +++ b/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso @@ -25,6 +25,7 @@ regulator-max-microvolt = <3300000>; gpios-states = <0>; states = <3300000 0>, <1800000 1>; + regulator-ramp-delay = <60>; }; }; diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index cb87c8fc66b3..00530b291010 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -76,19 +76,24 @@ static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm); - struct crypto_aes_ctx rk; + struct crypto_aes_ctx *rk; int err; - err = aes_expandkey(&rk, in_key, key_len); + rk = kmalloc(sizeof(*rk), GFP_KERNEL); + if (!rk) + return -ENOMEM; + + err = aes_expandkey(rk, in_key, key_len); if (err) - return err; + goto out; ctx->rounds = 6 + key_len / 4; scoped_ksimd() - aesbs_convert_key(ctx->rk, rk.key_enc, ctx->rounds); - - return 0; + aesbs_convert_key(ctx->rk, rk->key_enc, ctx->rounds); +out: + kfree_sensitive(rk); + return err; } static int __ecb_crypt(struct skcipher_request *req, @@ -133,22 +138,26 @@ static int aesbs_cbc_ctr_setkey(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm); - struct crypto_aes_ctx rk; + struct crypto_aes_ctx *rk; int err; - err = aes_expandkey(&rk, in_key, key_len); + rk = kmalloc(sizeof(*rk), GFP_KERNEL); + if (!rk) + return -ENOMEM; + + err = aes_expandkey(rk, in_key, key_len); if (err) - return err; + goto out; ctx->key.rounds = 6 + key_len / 4; - memcpy(ctx->enc, rk.key_enc, sizeof(ctx->enc)); + memcpy(ctx->enc, rk->key_enc, sizeof(ctx->enc)); scoped_ksimd() - aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds); - memzero_explicit(&rk, sizeof(rk)); - - return 0; + aesbs_convert_key(ctx->key.rk, rk->key_enc, ctx->key.rounds); +out: + kfree_sensitive(rk); + return err; } static int cbc_encrypt(struct skcipher_request *req) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 5d5a3bbdb95e..70cb9cfd760a 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -784,6 +784,9 @@ struct kvm_host_data { /* Number of debug breakpoints/watchpoints for this CPU (minus 1) */ unsigned int debug_brps; unsigned int debug_wrps; + + /* Last vgic_irq part of the AP list recorded in an LR */ + struct vgic_irq *last_lr_irq; }; struct kvm_host_psci_config { @@ -1616,7 +1619,8 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val); (kvm_has_feat((k), ID_AA64MMFR3_EL1, S1PIE, IMP)) #define kvm_has_s1poe(k) \ - (kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP)) + (system_supports_poe() && \ + kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP)) #define kvm_has_ras(k) \ (kvm_has_feat((k), ID_AA64PFR0_EL1, RAS, IMP)) diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index 905c658057a4..091544e6af44 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -397,6 +397,8 @@ int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu); int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu); void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val); +u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime); + #define vncr_fixmap(c) \ ({ \ u32 __c = (c); \ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index c31f8e17732a..32c2dbcc0c64 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2345,6 +2345,15 @@ static bool can_trap_icv_dir_el1(const struct arm64_cpu_capabilities *entry, !is_midr_in_range_list(has_vgic_v3)) return false; + /* + * pKVM prevents late onlining of CPUs. This means that whatever + * state the capability is in after deprivilege cannot be affected + * by a new CPU booting -- this is garanteed to be a CPU we have + * already seen, and the cap is therefore unchanged. + */ + if (system_capabilities_finalized() && is_protected_kvm_enabled()) + return cpus_have_final_cap(ARM64_HAS_ICH_HCR_EL2_TDIR); + if (is_kernel_in_hyp_mode()) res.a1 = read_sysreg_s(SYS_ICH_VTR_EL2); else diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index ad6133b89e7a..2964aad0362e 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -349,6 +349,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS HEAD_SYMBOLS diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 4f803fd1c99a..7d1f22fd490b 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -21,7 +21,6 @@ menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" select KVM_COMMON select KVM_GENERIC_HARDWARE_ENABLING - select KVM_GENERIC_MMU_NOTIFIER select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_GENERIC_DIRTYLOG_READ_PROTECT diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 29f0326f7e00..410ffd41fd73 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -358,7 +358,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_IOEVENTFD: case KVM_CAP_USER_MEMORY: - case KVM_CAP_SYNC_MMU: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_ONE_REG: case KVM_CAP_ARM_PSCI: diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 885bd5bb2f41..c5c5644b1878 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -540,31 +540,8 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, wr->pa |= va & GENMASK_ULL(va_bottom - 1, 0); wr->nG = (wi->regime != TR_EL2) && (desc & PTE_NG); - if (wr->nG) { - u64 asid_ttbr, tcr; - - switch (wi->regime) { - case TR_EL10: - tcr = vcpu_read_sys_reg(vcpu, TCR_EL1); - asid_ttbr = ((tcr & TCR_A1) ? - vcpu_read_sys_reg(vcpu, TTBR1_EL1) : - vcpu_read_sys_reg(vcpu, TTBR0_EL1)); - break; - case TR_EL20: - tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); - asid_ttbr = ((tcr & TCR_A1) ? - vcpu_read_sys_reg(vcpu, TTBR1_EL2) : - vcpu_read_sys_reg(vcpu, TTBR0_EL2)); - break; - default: - BUG(); - } - - wr->asid = FIELD_GET(TTBR_ASID_MASK, asid_ttbr); - if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || - !(tcr & TCR_ASID16)) - wr->asid &= GENMASK(7, 0); - } + if (wr->nG) + wr->asid = get_asid_by_regime(vcpu, wi->regime); return 0; @@ -1527,8 +1504,6 @@ int __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) fail = true; } - isb(); - if (!fail) par = read_sysreg_par(); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 1c87699fd886..332c453b87cf 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -29,7 +29,7 @@ #include "trace.h" -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; @@ -42,7 +42,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, hvc_exit_stat), STATS_DESC_COUNTER(VCPU, wfe_exit_stat), diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 38f66a56a766..d815265bd374 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -518,7 +518,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) granule = kvm_granule_size(level); cur.start = ALIGN_DOWN(addr, granule); cur.end = cur.start + granule; - if (!range_included(&cur, range)) + if (!range_included(&cur, range) && level < KVM_PGTABLE_LAST_LEVEL) continue; *range = cur; return 0; diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 8e29d7734a15..2f029bfe4755 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -342,6 +342,7 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc /* No restrictions for non-protected VMs. */ if (!kvm_vm_is_protected(kvm)) { hyp_vm->kvm.arch.flags = host_arch_flags; + hyp_vm->kvm.arch.flags &= ~BIT_ULL(KVM_ARCH_FLAG_ID_REGS_INITIALIZED); bitmap_copy(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features, @@ -391,7 +392,7 @@ static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu) if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SVE)) return; - sve_state = kern_hyp_va(hyp_vcpu->vcpu.arch.sve_state); + sve_state = hyp_vcpu->vcpu.arch.sve_state; hyp_unpin_shared_mem(sve_state, sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu)); } @@ -471,6 +472,35 @@ err: return ret; } +static int vm_copy_id_regs(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu); + const struct kvm *host_kvm = hyp_vm->host_kvm; + struct kvm *kvm = &hyp_vm->kvm; + + if (!test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &host_kvm->arch.flags)) + return -EINVAL; + + if (test_and_set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags)) + return 0; + + memcpy(kvm->arch.id_regs, host_kvm->arch.id_regs, sizeof(kvm->arch.id_regs)); + + return 0; +} + +static int pkvm_vcpu_init_sysregs(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + int ret = 0; + + if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + kvm_init_pvm_id_regs(&hyp_vcpu->vcpu); + else + ret = vm_copy_id_regs(hyp_vcpu); + + return ret; +} + static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, struct pkvm_hyp_vm *hyp_vm, struct kvm_vcpu *host_vcpu) @@ -490,8 +520,9 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags); hyp_vcpu->vcpu.arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; - if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) - kvm_init_pvm_id_regs(&hyp_vcpu->vcpu); + ret = pkvm_vcpu_init_sysregs(hyp_vcpu); + if (ret) + goto done; ret = pkvm_vcpu_init_traps(hyp_vcpu); if (ret) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 070a01e53fcb..17d64a1e11e5 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1751,17 +1751,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, force_pte = (max_map_size == PAGE_SIZE); vma_pagesize = min_t(long, vma_pagesize, max_map_size); + vma_shift = __ffs(vma_pagesize); } /* - * Both the canonical IPA and fault IPA must be hugepage-aligned to - * ensure we find the right PFN and lay down the mapping in the right - * place. + * Both the canonical IPA and fault IPA must be aligned to the + * mapping size to ensure we find the right PFN and lay down the + * mapping in the right place. */ - if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) { - fault_ipa &= ~(vma_pagesize - 1); - ipa &= ~(vma_pagesize - 1); - } + fault_ipa = ALIGN_DOWN(fault_ipa, vma_pagesize); + ipa = ALIGN_DOWN(ipa, vma_pagesize); gfn = ipa >> PAGE_SHIFT; mte_allowed = kvm_vma_mte_allowed(vma); @@ -1839,10 +1838,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (exec_fault && s2_force_noncacheable) ret = -ENOEXEC; - if (ret) { - kvm_release_page_unused(page); - return ret; - } + if (ret) + goto out_put_page; /* * Guest performs atomic/exclusive operations on memory with unsupported @@ -1852,7 +1849,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, */ if (esr_fsc_is_excl_atomic_fault(kvm_vcpu_get_esr(vcpu))) { kvm_inject_dabt_excl_atomic(vcpu, kvm_vcpu_get_hfar(vcpu)); - return 1; + ret = 1; + goto out_put_page; } if (nested) @@ -1938,6 +1936,10 @@ out_unlock: mark_page_dirty_in_slot(kvm, memslot, gfn); return ret != -EAGAIN ? ret : 0; + +out_put_page: + kvm_release_page_unused(page); + return ret; } /* Resolve the access fault by making the page young again. */ diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 620126d1f0dc..2c43097248b2 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -152,31 +152,31 @@ static int get_ia_size(struct s2_walk_info *wi) return 64 - wi->t0sz; } -static int check_base_s2_limits(struct s2_walk_info *wi, +static int check_base_s2_limits(struct kvm_vcpu *vcpu, struct s2_walk_info *wi, int level, int input_size, int stride) { - int start_size, ia_size; + int start_size, pa_max; - ia_size = get_ia_size(wi); + pa_max = kvm_get_pa_bits(vcpu->kvm); /* Check translation limits */ switch (BIT(wi->pgshift)) { case SZ_64K: - if (level == 0 || (level == 1 && ia_size <= 42)) + if (level == 0 || (level == 1 && pa_max <= 42)) return -EFAULT; break; case SZ_16K: - if (level == 0 || (level == 1 && ia_size <= 40)) + if (level == 0 || (level == 1 && pa_max <= 40)) return -EFAULT; break; case SZ_4K: - if (level < 0 || (level == 0 && ia_size <= 42)) + if (level < 0 || (level == 0 && pa_max <= 42)) return -EFAULT; break; } /* Check input size limits */ - if (input_size > ia_size) + if (input_size > pa_max) return -EFAULT; /* Check number of entries in starting level table */ @@ -269,16 +269,19 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa, if (input_size > 48 || input_size < 25) return -EFAULT; - ret = check_base_s2_limits(wi, level, input_size, stride); - if (WARN_ON(ret)) + ret = check_base_s2_limits(vcpu, wi, level, input_size, stride); + if (WARN_ON(ret)) { + out->esr = compute_fsc(0, ESR_ELx_FSC_FAULT); return ret; + } base_lower_bound = 3 + input_size - ((3 - level) * stride + wi->pgshift); base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound); if (check_output_size(wi, base_addr)) { - out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); + /* R_BFHQH */ + out->esr = compute_fsc(0, ESR_ELx_FSC_ADDRSZ); return 1; } @@ -293,8 +296,10 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa, paddr = base_addr | index; ret = read_guest_s2_desc(vcpu, paddr, &desc, wi); - if (ret < 0) + if (ret < 0) { + out->esr = ESR_ELx_FSC_SEA_TTW(level); return ret; + } new_desc = desc; @@ -854,6 +859,33 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2) return kvm_inject_nested_sync(vcpu, esr_el2); } +u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime) +{ + enum vcpu_sysreg ttbr_elx; + u64 tcr; + u16 asid; + + switch (regime) { + case TR_EL10: + tcr = vcpu_read_sys_reg(vcpu, TCR_EL1); + ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL1 : TTBR0_EL1; + break; + case TR_EL20: + tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); + ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL2 : TTBR0_EL2; + break; + default: + BUG(); + } + + asid = FIELD_GET(TTBRx_EL1_ASID, vcpu_read_sys_reg(vcpu, ttbr_elx)); + if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || + !(tcr & TCR_ASID16)) + asid &= GENMASK(7, 0); + + return asid; +} + static void invalidate_vncr(struct vncr_tlb *vt) { vt->valid = false; @@ -1154,9 +1186,6 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) { int i; - if (!kvm->arch.nested_mmus_size) - return; - for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; @@ -1336,20 +1365,8 @@ static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu) if (read_vncr_el2(vcpu) != vt->gva) return false; - if (vt->wr.nG) { - u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); - u64 ttbr = ((tcr & TCR_A1) ? - vcpu_read_sys_reg(vcpu, TTBR1_EL2) : - vcpu_read_sys_reg(vcpu, TTBR0_EL2)); - u16 asid; - - asid = FIELD_GET(TTBR_ASID_MASK, ttbr); - if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || - !(tcr & TCR_ASID16)) - asid &= GENMASK(7, 0); - - return asid == vt->wr.asid; - } + if (vt->wr.nG) + return get_asid_by_regime(vcpu, TR_EL20) == vt->wr.asid; return true; } @@ -1452,21 +1469,8 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu) if (read_vncr_el2(vcpu) != vt->gva) return; - if (vt->wr.nG) { - u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); - u64 ttbr = ((tcr & TCR_A1) ? - vcpu_read_sys_reg(vcpu, TTBR1_EL2) : - vcpu_read_sys_reg(vcpu, TTBR0_EL2)); - u16 asid; - - asid = FIELD_GET(TTBR_ASID_MASK, ttbr); - if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || - !(tcr & TCR_ASID16)) - asid &= GENMASK(7, 0); - - if (asid != vt->wr.asid) - return; - } + if (vt->wr.nG && get_asid_by_regime(vcpu, TR_EL20) != vt->wr.asid) + return; vt->cpu = smp_processor_id(); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index a7cd0badc20c..1b4cacb6e918 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1816,6 +1816,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, ID_AA64MMFR3_EL1_SCTLRX | ID_AA64MMFR3_EL1_S1POE | ID_AA64MMFR3_EL1_S1PIE; + + if (!system_supports_poe()) + val &= ~ID_AA64MMFR3_EL1_S1POE; break; case SYS_ID_MMFR4_EL1: val &= ~ID_MMFR4_EL1_CCIDX; diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 9b3091ad868c..e9b8b5fc480c 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -143,6 +143,21 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm->arch.vgic.in_kernel = true; kvm->arch.vgic.vgic_model = type; kvm->arch.vgic.implementation_rev = KVM_VGIC_IMP_REV_LATEST; + kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; + + aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; + pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; + + if (type == KVM_DEV_TYPE_ARM_VGIC_V2) { + kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; + } else { + INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); + aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); + pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3); + } + + kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0); + kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1); kvm_for_each_vcpu(i, vcpu, kvm) { ret = vgic_allocate_private_irqs_locked(vcpu, type); @@ -157,25 +172,10 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) vgic_cpu->private_irqs = NULL; } + kvm->arch.vgic.vgic_model = 0; goto out_unlock; } - kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; - - aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; - pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; - - if (type == KVM_DEV_TYPE_ARM_VGIC_V2) { - kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; - } else { - INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); - aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); - pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3); - } - - kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0); - kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1); - if (type == KVM_DEV_TYPE_ARM_VGIC_V3) kvm->arch.vgic.nassgicap = system_supports_direct_sgis(); diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c index 585491fbda80..cafa3cb32bda 100644 --- a/arch/arm64/kvm/vgic/vgic-v2.c +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -115,7 +115,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2; u32 eoicount = FIELD_GET(GICH_HCR_EOICOUNT, cpuif->vgic_hcr); - struct vgic_irq *irq; + struct vgic_irq *irq = *host_data_ptr(last_lr_irq); DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); @@ -123,7 +123,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) vgic_v2_fold_lr(vcpu, cpuif->vgic_lr[lr]); /* See the GICv3 equivalent for the EOIcount handling rationale */ - list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { + list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) { u32 lr; if (!eoicount) { diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 386ddf69a9c5..6a355eca1934 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -148,7 +148,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3; u32 eoicount = FIELD_GET(ICH_HCR_EL2_EOIcount, cpuif->vgic_hcr); - struct vgic_irq *irq; + struct vgic_irq *irq = *host_data_ptr(last_lr_irq); DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); @@ -158,12 +158,12 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) /* * EOIMode=0: use EOIcount to emulate deactivation. We are * guaranteed to deactivate in reverse order of the activation, so - * just pick one active interrupt after the other in the ap_list, - * and replay the deactivation as if the CPU was doing it. We also - * rely on priority drop to have taken place, and the list to be - * sorted by priority. + * just pick one active interrupt after the other in the tail part + * of the ap_list, past the LRs, and replay the deactivation as if + * the CPU was doing it. We also rely on priority drop to have taken + * place, and the list to be sorted by priority. */ - list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { + list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) { u64 lr; /* diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 430aa98888fd..e22b79cfff96 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -814,6 +814,9 @@ retry: static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) { + if (!*host_data_ptr(last_lr_irq)) + return; + if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_fold_lr_state(vcpu); else @@ -960,10 +963,13 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) if (irqs_outside_lrs(&als)) vgic_sort_ap_list(vcpu); + *host_data_ptr(last_lr_irq) = NULL; + list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { scoped_guard(raw_spinlock, &irq->irq_lock) { if (likely(vgic_target_oracle(irq) == vcpu)) { vgic_populate_lr(vcpu, irq, count++); + *host_data_ptr(last_lr_irq) = irq; } } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 356d33c7a4ae..adf84962d579 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -2119,7 +2119,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) extable_offset = round_up(prog_size + PLT_TARGET_SIZE, extable_align); image_size = extable_offset + extable_size; ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr, - sizeof(u32), &header, &image_ptr, + sizeof(u64), &header, &image_ptr, jit_fill_hole); if (!ro_header) { prog = orig_prog; diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S index d718961786d2..81943981b3af 100644 --- a/arch/csky/kernel/vmlinux.lds.S +++ b/arch/csky/kernel/vmlinux.lds.S @@ -109,6 +109,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 1150b77fa281..aae22283b5e0 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -62,6 +62,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS .hexagon.attributes 0 : { *(.hexagon.attributes) } diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index d211c6572b0a..92068ff38685 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -304,6 +304,9 @@ config AS_HAS_LBT_EXTENSION config AS_HAS_LVZ_EXTENSION def_bool $(as-instr,hvcl 0) +config AS_HAS_SCQ_EXTENSION + def_bool $(as-instr,sc.q \$t0$(comma)\$t1$(comma)\$t2) + config CC_HAS_ANNOTATE_TABLEJUMP def_bool $(cc-option,-mannotate-tablejump) diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h index 58cabab6d90d..909f9274fe71 100644 --- a/arch/loongarch/include/asm/cmpxchg.h +++ b/arch/loongarch/include/asm/cmpxchg.h @@ -238,6 +238,8 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int arch_cmpxchg((ptr), (o), (n)); \ }) +#ifdef CONFIG_AS_HAS_SCQ_EXTENSION + union __u128_halves { u128 full; struct { @@ -290,6 +292,9 @@ union __u128_halves { BUILD_BUG_ON(sizeof(*(ptr)) != 16); \ __arch_cmpxchg128(ptr, o, n, ""); \ }) + +#endif /* CONFIG_AS_HAS_SCQ_EXTENSION */ + #else #include <asm-generic/cmpxchg-local.h> #define arch_cmpxchg64_local(ptr, o, n) __generic_cmpxchg64_local((ptr), (o), (n)) diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h index 4e259d490e45..438269313e78 100644 --- a/arch/loongarch/include/asm/uaccess.h +++ b/arch/loongarch/include/asm/uaccess.h @@ -253,8 +253,13 @@ do { \ \ __get_kernel_common(*((type *)(dst)), sizeof(type), \ (__force type *)(src)); \ - if (unlikely(__gu_err)) \ + if (unlikely(__gu_err)) { \ + pr_info("%s: memory access failed, ecode 0x%x\n", \ + __func__, read_csr_excode()); \ + pr_info("%s: the caller is %pS\n", \ + __func__, __builtin_return_address(0)); \ goto err_label; \ + } \ } while (0) #define __put_kernel_nofault(dst, src, type, err_label) \ @@ -264,8 +269,13 @@ do { \ \ __pu_val = *(__force type *)(src); \ __put_kernel_common(((type *)(dst)), sizeof(type)); \ - if (unlikely(__pu_err)) \ + if (unlikely(__pu_err)) { \ + pr_info("%s: memory access failed, ecode 0x%x\n", \ + __func__, read_csr_excode()); \ + pr_info("%s: the caller is %pS\n", \ + __func__, __builtin_return_address(0)); \ goto err_label; \ + } \ } while (0) extern unsigned long __copy_user(void *to, const void *from, __kernel_size_t n); diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index bf037f0c6b26..1a728082944c 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -246,32 +246,51 @@ static int text_copy_cb(void *data) if (smp_processor_id() == copy->cpu) { ret = copy_to_kernel_nofault(copy->dst, copy->src, copy->len); - if (ret) + if (ret) { pr_err("%s: operation failed\n", __func__); + return ret; + } } flush_icache_range((unsigned long)copy->dst, (unsigned long)copy->dst + copy->len); - return ret; + return 0; } int larch_insn_text_copy(void *dst, void *src, size_t len) { int ret = 0; + int err = 0; size_t start, end; struct insn_copy copy = { .dst = dst, .src = src, .len = len, - .cpu = smp_processor_id(), + .cpu = raw_smp_processor_id(), }; + /* + * Ensure copy.cpu won't be hot removed before stop_machine. + * If it is removed nobody will really update the text. + */ + lockdep_assert_cpus_held(); + start = round_down((size_t)dst, PAGE_SIZE); end = round_up((size_t)dst + len, PAGE_SIZE); - set_memory_rw(start, (end - start) / PAGE_SIZE); - ret = stop_machine(text_copy_cb, ©, cpu_online_mask); - set_memory_rox(start, (end - start) / PAGE_SIZE); + err = set_memory_rw(start, (end - start) / PAGE_SIZE); + if (err) { + pr_info("%s: set_memory_rw() failed\n", __func__); + return err; + } + + ret = stop_machine_cpuslocked(text_copy_cb, ©, cpu_online_mask); + + err = set_memory_rox(start, (end - start) / PAGE_SIZE); + if (err) { + pr_info("%s: set_memory_rox() failed\n", __func__); + return err; + } return ret; } diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index 08ea921cdec1..d0e1377a041d 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -147,6 +147,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS #ifdef CONFIG_EFI_STUB diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig index ed4f724db774..8e5213609975 100644 --- a/arch/loongarch/kvm/Kconfig +++ b/arch/loongarch/kvm/Kconfig @@ -28,7 +28,6 @@ config KVM select KVM_COMMON select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_GENERIC_HARDWARE_ENABLING - select KVM_GENERIC_MMU_NOTIFIER select KVM_MMIO select VIRT_XFER_TO_GUEST_WORK select SCHED_INFO diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 09e137f2f841..8ffd50a470e6 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -14,7 +14,7 @@ #define CREATE_TRACE_POINTS #include "trace.h" -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, int_exits), STATS_DESC_COUNTER(VCPU, idle_exits), diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c index 63fd40530aa9..8cc5ee1c53ef 100644 --- a/arch/loongarch/kvm/vm.c +++ b/arch/loongarch/kvm/vm.c @@ -10,7 +10,7 @@ #include <asm/kvm_eiointc.h> #include <asm/kvm_pch_pic.h> -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, pages), STATS_DESC_ICOUNTER(VM, hugepages), @@ -49,8 +49,8 @@ static void kvm_vm_init_features(struct kvm *kvm) kvm->arch.kvm_features |= BIT(KVM_LOONGARCH_VM_FEAT_PMU); /* Enable all PV features by default */ - kvm->arch.pv_features = BIT(KVM_FEATURE_IPI); - kvm->arch.kvm_features = BIT(KVM_LOONGARCH_VM_FEAT_PV_IPI); + kvm->arch.pv_features |= BIT(KVM_FEATURE_IPI); + kvm->arch.kvm_features |= BIT(KVM_LOONGARCH_VM_FEAT_PV_IPI); if (kvm_pvtime_supported()) { kvm->arch.pv_features |= BIT(KVM_FEATURE_PREEMPT); kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME); @@ -118,7 +118,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ONE_REG: case KVM_CAP_ENABLE_CAP: case KVM_CAP_READONLY_MEM: - case KVM_CAP_SYNC_MMU: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_IOEVENTFD: case KVM_CAP_MP_STATE: diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 3bd89f55960d..9cb796e16379 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1379,9 +1379,11 @@ void *bpf_arch_text_copy(void *dst, void *src, size_t len) { int ret; + cpus_read_lock(); mutex_lock(&text_mutex); ret = larch_insn_text_copy(dst, src, len); mutex_unlock(&text_mutex); + cpus_read_unlock(); return ret ? ERR_PTR(-EINVAL) : dst; } @@ -1429,10 +1431,12 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t, if (ret) return ret; + cpus_read_lock(); mutex_lock(&text_mutex); if (memcmp(ip, new_insns, LOONGARCH_LONG_JUMP_NBYTES)) ret = larch_insn_text_copy(ip, new_insns, LOONGARCH_LONG_JUMP_NBYTES); mutex_unlock(&text_mutex); + cpus_read_unlock(); return ret; } @@ -1450,10 +1454,12 @@ int bpf_arch_text_invalidate(void *dst, size_t len) for (i = 0; i < (len / sizeof(u32)); i++) inst[i] = INSN_BREAK; + cpus_read_lock(); mutex_lock(&text_mutex); if (larch_insn_text_copy(dst, inst, len)) ret = -EINVAL; mutex_unlock(&text_mutex); + cpus_read_unlock(); kvfree(inst); @@ -1568,6 +1574,11 @@ void arch_free_bpf_trampoline(void *image, unsigned int size) bpf_prog_pack_free(image, size); } +int arch_protect_bpf_trampoline(void *image, unsigned int size) +{ + return 0; +} + /* * Sign-extend the register if necessary */ diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds index 2624fc18c131..45d7f4b0177b 100644 --- a/arch/m68k/kernel/vmlinux-nommu.lds +++ b/arch/m68k/kernel/vmlinux-nommu.lds @@ -85,6 +85,7 @@ SECTIONS { _end = .; STABS_DEBUG + MODINFO ELF_DETAILS /* Sections to be discarded */ diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds index 1ccdd04ae462..7326586afe15 100644 --- a/arch/m68k/kernel/vmlinux-std.lds +++ b/arch/m68k/kernel/vmlinux-std.lds @@ -58,6 +58,7 @@ SECTIONS _end = . ; STABS_DEBUG + MODINFO ELF_DETAILS /* Sections to be discarded */ diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds index f13ddcc2af5c..1b19fef201fb 100644 --- a/arch/m68k/kernel/vmlinux-sun3.lds +++ b/arch/m68k/kernel/vmlinux-sun3.lds @@ -51,6 +51,7 @@ __init_begin = .; _end = . ; STABS_DEBUG + MODINFO ELF_DETAILS /* Sections to be discarded */ diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 2b708fac8d2c..579b2cc1995a 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -217,6 +217,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS /* These must appear regardless of . */ diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index cc13cc35f208..b1b9a1d67758 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -23,7 +23,6 @@ config KVM select KVM_COMMON select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_MMIO - select KVM_GENERIC_MMU_NOTIFIER select KVM_GENERIC_HARDWARE_ENABLING select HAVE_KVM_READONLY_MEM help diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b0fb92fda4d4..a53abbba43ea 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -38,7 +38,7 @@ #define VECTORSPACING 0x100 /* for EI/VI mode */ #endif -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; @@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, wait_exits), STATS_DESC_COUNTER(VCPU, cache_exits), @@ -1035,7 +1035,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ONE_REG: case KVM_CAP_ENABLE_CAP: case KVM_CAP_READONLY_MEM: - case KVM_CAP_SYNC_MMU: case KVM_CAP_IMMEDIATE_EXIT: r = 1; break; diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S index 37b958055064..206f92445bfa 100644 --- a/arch/nios2/kernel/vmlinux.lds.S +++ b/arch/nios2/kernel/vmlinux.lds.S @@ -57,6 +57,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index 049bff45f612..9b29c3211774 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -101,6 +101,7 @@ SECTIONS /* Throw in the debugging sections */ STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS /* Sections to be discarded -- must be last */ diff --git a/arch/parisc/boot/compressed/vmlinux.lds.S b/arch/parisc/boot/compressed/vmlinux.lds.S index ab7b43990857..87d24cc824b6 100644 --- a/arch/parisc/boot/compressed/vmlinux.lds.S +++ b/arch/parisc/boot/compressed/vmlinux.lds.S @@ -90,6 +90,7 @@ SECTIONS /* Sections to be discarded */ DISCARDS /DISCARD/ : { + *(.modinfo) #ifdef CONFIG_64BIT /* temporary hack until binutils is fixed to not emit these * for static binaries diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 2c139a4dbf4b..17afe7a59edf 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -85,7 +85,7 @@ extern void __update_cache(pte_t pte); printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e)) /* This is the size of the initially mapped kernel memory */ -#if defined(CONFIG_64BIT) +#if defined(CONFIG_64BIT) || defined(CONFIG_KALLSYMS) #define KERNEL_INITIAL_ORDER 26 /* 1<<26 = 64MB */ #else #define KERNEL_INITIAL_ORDER 25 /* 1<<25 = 32MB */ diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 4c5240d3a3c7..b189265785dc 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -953,7 +953,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes, #else "1: cmpb,<<,n %0,%2,1b\n" #endif - " fic,m %3(%4,%0)\n" + " fdc,m %3(%4,%0)\n" "2: sync\n" ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1") : "+r" (start), "+r" (error) @@ -968,7 +968,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes, #else "1: cmpb,<<,n %0,%2,1b\n" #endif - " fdc,m %3(%4,%0)\n" + " fic,m %3(%4,%0)\n" "2: sync\n" ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1") : "+r" (start), "+r" (error) diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index 96e0264ac961..9188c8d87437 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -56,6 +56,7 @@ ENTRY(parisc_kernel_start) .import __bss_start,data .import __bss_stop,data + .import __end,data load32 PA(__bss_start),%r3 load32 PA(__bss_stop),%r4 @@ -149,7 +150,11 @@ $cpu_ok: * everything ... it will get remapped correctly later */ ldo 0+_PAGE_KERNEL_RWX(%r0),%r3 /* Hardwired 0 phys addr start */ load32 (1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */ - load32 PA(pg0),%r1 + load32 PA(_end),%r1 + SHRREG %r1,PAGE_SHIFT,%r1 /* %r1 is PFN count for _end symbol */ + cmpb,<<,n %r11,%r1,1f + copy %r1,%r11 /* %r1 PFN count smaller than %r11 */ +1: load32 PA(pg0),%r1 $pgt_fill_loop: STREGM %r3,ASM_PTE_ENTRY_SIZE(%r1) diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index ace483b6f19a..d3e17a7a8901 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -120,14 +120,6 @@ void __init setup_arch(char **cmdline_p) #endif printk(KERN_CONT ".\n"); - /* - * Check if initial kernel page mappings are sufficient. - * panic early if not, else we may access kernel functions - * and variables which can't be reached. - */ - if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE) - panic("KERNEL_INITIAL_ORDER too small!"); - #ifdef CONFIG_64BIT if(parisc_narrow_firmware) { printk(KERN_INFO "Kernel is using PDC in 32-bit mode.\n"); @@ -279,6 +271,18 @@ void __init start_parisc(void) int ret, cpunum; struct pdc_coproc_cfg coproc_cfg; + /* + * Check if initial kernel page mapping is sufficient. + * Print warning if not, because we may access kernel functions and + * variables which can't be reached yet through the initial mappings. + * Note that the panic() and printk() functions are not functional + * yet, so we need to use direct iodc() firmware calls instead. + */ + const char warn1[] = "CRITICAL: Kernel may crash because " + "KERNEL_INITIAL_ORDER is too small.\n"; + if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE) + pdc_iodc_print(warn1, sizeof(warn1) - 1); + /* check QEMU/SeaBIOS marker in PAGE0 */ running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0); diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index b445e47903cf..0ca93d6d7235 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -165,6 +165,7 @@ SECTIONS _end = . ; STABS_DEBUG + MODINFO ELF_DETAILS .note 0 : { *(.note) } diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ad7a2fe63a2a..10240cb80904 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -573,8 +573,8 @@ config ARCH_USING_PATCHABLE_FUNCTION_ENTRY depends on FUNCTION_TRACER && (PPC32 || PPC64_ELF_ABI_V2) depends on $(cc-option,-fpatchable-function-entry=2) def_bool y if PPC32 - def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN - def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN + def_bool $(success,$(srctree)/arch/powerpc/tools/check-fpatchable-function-entry.sh $(CC) $(CLANG_FLAGS) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN + def_bool $(success,$(srctree)/arch/powerpc/tools/check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN config PPC_FTRACE_OUT_OF_LINE def_bool PPC64 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY diff --git a/arch/powerpc/boot/dts/asp834x-redboot.dts b/arch/powerpc/boot/dts/asp834x-redboot.dts index 33ddb17d1876..c541bd367983 100644 --- a/arch/powerpc/boot/dts/asp834x-redboot.dts +++ b/arch/powerpc/boot/dts/asp834x-redboot.dts @@ -37,7 +37,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x8000000>; // 128MB at 0 }; diff --git a/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi b/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi deleted file mode 100644 index 9cffccf4e07e..000000000000 --- a/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi +++ /dev/null @@ -1,156 +0,0 @@ -/* T4240 Interlaken LAC Portal device tree stub with 24 portals. - * - * Copyright 2012 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#address-cells = <0x1>; -#size-cells = <0x1>; -compatible = "fsl,interlaken-lac-portals"; - -lportal0: lac-portal@0 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x0 0x1000>; -}; - -lportal1: lac-portal@1000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x1000 0x1000>; -}; - -lportal2: lac-portal@2000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x2000 0x1000>; -}; - -lportal3: lac-portal@3000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x3000 0x1000>; -}; - -lportal4: lac-portal@4000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x4000 0x1000>; -}; - -lportal5: lac-portal@5000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x5000 0x1000>; -}; - -lportal6: lac-portal@6000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x6000 0x1000>; -}; - -lportal7: lac-portal@7000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x7000 0x1000>; -}; - -lportal8: lac-portal@8000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x8000 0x1000>; -}; - -lportal9: lac-portal@9000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x9000 0x1000>; -}; - -lportal10: lac-portal@A000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xA000 0x1000>; -}; - -lportal11: lac-portal@B000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xB000 0x1000>; -}; - -lportal12: lac-portal@C000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xC000 0x1000>; -}; - -lportal13: lac-portal@D000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xD000 0x1000>; -}; - -lportal14: lac-portal@E000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xE000 0x1000>; -}; - -lportal15: lac-portal@F000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xF000 0x1000>; -}; - -lportal16: lac-portal@10000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x10000 0x1000>; -}; - -lportal17: lac-portal@11000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x11000 0x1000>; -}; - -lportal18: lac-portal@1200 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x12000 0x1000>; -}; - -lportal19: lac-portal@13000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x13000 0x1000>; -}; - -lportal20: lac-portal@14000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x14000 0x1000>; -}; - -lportal21: lac-portal@15000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x15000 0x1000>; -}; - -lportal22: lac-portal@16000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x16000 0x1000>; -}; - -lportal23: lac-portal@17000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x17000 0x1000>; -}; diff --git a/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi b/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi deleted file mode 100644 index e8208720ac0e..000000000000 --- a/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi +++ /dev/null @@ -1,45 +0,0 @@ -/* - * T4 Interlaken Look-aside Controller (LAC) device tree stub - * - * Copyright 2012 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -lac: lac@229000 { - compatible = "fsl,interlaken-lac"; - reg = <0x229000 0x1000>; - interrupts = <16 2 1 18>; -}; - -lac-hv@228000 { - compatible = "fsl,interlaken-lac-hv"; - reg = <0x228000 0x1000>; - fsl,non-hv-node = <&lac>; -}; diff --git a/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi b/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi deleted file mode 100644 index 1cf0b77b1efe..000000000000 --- a/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi +++ /dev/null @@ -1,43 +0,0 @@ -/* - * PQ3 MPIC Message (Group B) device tree stub [ controller @ offset 0x42400 ] - * - * Copyright 2012 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -message@42400 { - compatible = "fsl,mpic-v3.1-msgr"; - reg = <0x42400 0x200>; - interrupts = < - 0xb4 2 0 0 - 0xb5 2 0 0 - 0xb6 2 0 0 - 0xb7 2 0 0>; -}; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi deleted file mode 100644 index 71eb75e82c2e..000000000000 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi +++ /dev/null @@ -1,80 +0,0 @@ -/* - * QorIQ FMan v3 1g port #1 device tree stub [ controller @ offset 0x400000 ] - * - * Copyright 2012 - 2015 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -fman@400000 { - fman0_rx_0x09: port@89000 { - cell-index = <0x9>; - compatible = "fsl,fman-v3-port-rx"; - reg = <0x89000 0x1000>; - fsl,fman-10g-port; - fsl,fman-best-effort-port; - }; - - fman0_tx_0x29: port@a9000 { - cell-index = <0x29>; - compatible = "fsl,fman-v3-port-tx"; - reg = <0xa9000 0x1000>; - fsl,fman-10g-port; - fsl,fman-best-effort-port; - }; - - ethernet@e2000 { - cell-index = <1>; - compatible = "fsl,fman-memac"; - reg = <0xe2000 0x1000>; - fsl,fman-ports = <&fman0_rx_0x09 &fman0_tx_0x29>; - ptp-timer = <&ptp_timer0>; - pcsphy-handle = <&pcsphy1>, <&qsgmiia_pcs1>; - pcs-handle-names = "sgmii", "qsgmii"; - }; - - mdio@e1000 { - qsgmiia_pcs1: ethernet-pcs@1 { - compatible = "fsl,lynx-pcs"; - reg = <1>; - }; - }; - - mdio@e3000 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; - reg = <0xe3000 0x1000>; - fsl,erratum-a011043; /* must ignore read errors */ - - pcsphy1: ethernet-phy@0 { - reg = <0x0>; - }; - }; -}; diff --git a/arch/powerpc/boot/dts/mpc8308_p1m.dts b/arch/powerpc/boot/dts/mpc8308_p1m.dts index 2638555afcc4..41f917f97dab 100644 --- a/arch/powerpc/boot/dts/mpc8308_p1m.dts +++ b/arch/powerpc/boot/dts/mpc8308_p1m.dts @@ -37,7 +37,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x08000000>; // 128MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8308rdb.dts b/arch/powerpc/boot/dts/mpc8308rdb.dts index af2ed8380a86..39ed26fba410 100644 --- a/arch/powerpc/boot/dts/mpc8308rdb.dts +++ b/arch/powerpc/boot/dts/mpc8308rdb.dts @@ -38,7 +38,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x08000000>; // 128MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts index 09508b4c8c73..c9fe4dabc80a 100644 --- a/arch/powerpc/boot/dts/mpc8313erdb.dts +++ b/arch/powerpc/boot/dts/mpc8313erdb.dts @@ -6,6 +6,7 @@ */ /dts-v1/; +#include <dt-bindings/interrupt-controller/irq.h> / { model = "MPC8313ERDB"; @@ -38,7 +39,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x08000000>; // 128MB at 0 }; @@ -48,7 +49,7 @@ #size-cells = <1>; compatible = "fsl,mpc8313-elbc", "fsl,elbc", "simple-bus"; reg = <0xe0005000 0x1000>; - interrupts = <77 0x8>; + interrupts = <77 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; // CS0 and CS1 are swapped when @@ -118,7 +119,7 @@ cell-index = <0>; compatible = "fsl-i2c"; reg = <0x3000 0x100>; - interrupts = <14 0x8>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; dfsrr; rtc@68 { @@ -131,7 +132,7 @@ compatible = "fsl,sec2.2", "fsl,sec2.1", "fsl,sec2.0"; reg = <0x30000 0x10000>; - interrupts = <11 0x8>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; fsl,num-channels = <1>; fsl,channel-fifo-len = <24>; @@ -146,7 +147,7 @@ cell-index = <1>; compatible = "fsl-i2c"; reg = <0x3100 0x100>; - interrupts = <15 0x8>; + interrupts = <15 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; dfsrr; }; @@ -155,7 +156,7 @@ cell-index = <0>; compatible = "fsl,spi"; reg = <0x7000 0x1000>; - interrupts = <16 0x8>; + interrupts = <16 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; mode = "cpu"; }; @@ -167,7 +168,7 @@ #address-cells = <1>; #size-cells = <0>; interrupt-parent = <&ipic>; - interrupts = <38 0x8>; + interrupts = <38 IRQ_TYPE_LEVEL_LOW>; phy_type = "utmi_wide"; sleep = <&pmc 0x00300000>; }; @@ -175,7 +176,8 @@ ptp_clock@24E00 { compatible = "fsl,etsec-ptp"; reg = <0x24E00 0xB0>; - interrupts = <12 0x8 13 0x8>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>, + <13 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = < &ipic >; fsl,tclk-period = <10>; fsl,tmr-prsc = <100>; @@ -197,7 +199,9 @@ compatible = "gianfar"; reg = <0x24000 0x1000>; local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <37 0x8 36 0x8 35 0x8>; + interrupts = <37 IRQ_TYPE_LEVEL_LOW>, + <36 IRQ_TYPE_LEVEL_LOW>, + <35 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; tbi-handle = < &tbi0 >; /* Vitesse 7385 isn't on the MDIO bus */ @@ -211,7 +215,7 @@ reg = <0x520 0x20>; phy4: ethernet-phy@4 { interrupt-parent = <&ipic>; - interrupts = <20 0x8>; + interrupts = <20 IRQ_TYPE_LEVEL_LOW>; reg = <0x4>; }; tbi0: tbi-phy@11 { @@ -231,7 +235,9 @@ reg = <0x25000 0x1000>; ranges = <0x0 0x25000 0x1000>; local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <34 0x8 33 0x8 32 0x8>; + interrupts = <34 IRQ_TYPE_LEVEL_LOW>, + <33 IRQ_TYPE_LEVEL_LOW>, + <32 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; tbi-handle = < &tbi1 >; phy-handle = < &phy4 >; @@ -259,7 +265,7 @@ compatible = "fsl,ns16550", "ns16550"; reg = <0x4500 0x100>; clock-frequency = <0>; - interrupts = <9 0x8>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; @@ -269,15 +275,12 @@ compatible = "fsl,ns16550", "ns16550"; reg = <0x4600 0x100>; clock-frequency = <0>; - interrupts = <10 0x8>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; /* IPIC - * interrupts cell = <intr #, sense> - * sense values match linux IORESOURCE_IRQ_* defines: - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change + * interrupts cell = <intr #, type> */ ipic: pic@700 { interrupt-controller; @@ -290,7 +293,7 @@ pmc: power@b00 { compatible = "fsl,mpc8313-pmc", "fsl,mpc8349-pmc"; reg = <0xb00 0x100 0xa00 0x100>; - interrupts = <80 8>; + interrupts = <80 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; fsl,mpc8313-wakeup-timer = <>m1>; @@ -306,14 +309,20 @@ gtm1: timer@500 { compatible = "fsl,mpc8313-gtm", "fsl,gtm"; reg = <0x500 0x100>; - interrupts = <90 8 78 8 84 8 72 8>; + interrupts = <90 IRQ_TYPE_LEVEL_LOW>, + <78 IRQ_TYPE_LEVEL_LOW>, + <84 IRQ_TYPE_LEVEL_LOW>, + <72 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; timer@600 { compatible = "fsl,mpc8313-gtm", "fsl,gtm"; reg = <0x600 0x100>; - interrupts = <91 8 79 8 85 8 73 8>; + interrupts = <91 IRQ_TYPE_LEVEL_LOW>, + <79 IRQ_TYPE_LEVEL_LOW>, + <85 IRQ_TYPE_LEVEL_LOW>, + <73 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; }; @@ -341,7 +350,7 @@ 0x7800 0x0 0x0 0x3 &ipic 17 0x8 0x7800 0x0 0x0 0x4 &ipic 18 0x8>; interrupt-parent = <&ipic>; - interrupts = <66 0x8>; + interrupts = <66 IRQ_TYPE_LEVEL_LOW>; bus-range = <0x0 0x0>; ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000 @@ -363,14 +372,14 @@ reg = <0xe00082a8 4>; ranges = <0 0xe0008100 0x1a8>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; dma-channel@0 { compatible = "fsl,mpc8313-dma-channel", "fsl,elo-dma-channel"; reg = <0 0x28>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <0>; }; @@ -379,7 +388,7 @@ "fsl,elo-dma-channel"; reg = <0x80 0x28>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <1>; }; @@ -388,7 +397,7 @@ "fsl,elo-dma-channel"; reg = <0x100 0x28>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <2>; }; @@ -397,7 +406,7 @@ "fsl,elo-dma-channel"; reg = <0x180 0x28>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <3>; }; }; diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts index a8f68d6e50b0..7ba1159f8803 100644 --- a/arch/powerpc/boot/dts/mpc8315erdb.dts +++ b/arch/powerpc/boot/dts/mpc8315erdb.dts @@ -40,7 +40,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x08000000>; // 128MB at 0 }; @@ -50,7 +50,7 @@ #size-cells = <1>; compatible = "fsl,mpc8315-elbc", "fsl,elbc", "simple-bus"; reg = <0xe0005000 0x1000>; - interrupts = <77 0x8>; + interrupts = <77 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; // CS0 and CS1 are swapped when @@ -112,7 +112,7 @@ cell-index = <0>; compatible = "fsl-i2c"; reg = <0x3000 0x100>; - interrupts = <14 0x8>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; dfsrr; rtc@68 { @@ -133,8 +133,10 @@ cell-index = <0>; compatible = "fsl,spi"; reg = <0x7000 0x1000>; - interrupts = <16 0x8>; + interrupts = <16 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; + #address-cells = <1>; + #size-cells = <0>; mode = "cpu"; }; @@ -145,35 +147,35 @@ reg = <0x82a8 4>; ranges = <0 0x8100 0x1a8>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <0>; dma-channel@0 { compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel"; reg = <0 0x80>; cell-index = <0>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; }; dma-channel@80 { compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel"; reg = <0x80 0x80>; cell-index = <1>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; }; dma-channel@100 { compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel"; reg = <0x100 0x80>; cell-index = <2>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; }; dma-channel@180 { compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel"; reg = <0x180 0x28>; cell-index = <3>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; }; }; @@ -183,7 +185,7 @@ #address-cells = <1>; #size-cells = <0>; interrupt-parent = <&ipic>; - interrupts = <38 0x8>; + interrupts = <38 IRQ_TYPE_LEVEL_LOW>; phy_type = "utmi"; }; @@ -197,7 +199,9 @@ reg = <0x24000 0x1000>; ranges = <0x0 0x24000 0x1000>; local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <32 0x8 33 0x8 34 0x8>; + interrupts = <32 IRQ_TYPE_LEVEL_LOW>, + <33 IRQ_TYPE_LEVEL_LOW>, + <34 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; tbi-handle = <&tbi0>; phy-handle = < &phy0 >; @@ -238,7 +242,9 @@ reg = <0x25000 0x1000>; ranges = <0x0 0x25000 0x1000>; local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <35 0x8 36 0x8 37 0x8>; + interrupts = <35 IRQ_TYPE_LEVEL_LOW>, + <36 IRQ_TYPE_LEVEL_LOW>, + <37 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; tbi-handle = <&tbi1>; phy-handle = < &phy1 >; @@ -263,7 +269,7 @@ compatible = "fsl,ns16550", "ns16550"; reg = <0x4500 0x100>; clock-frequency = <133333333>; - interrupts = <9 0x8>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; @@ -273,7 +279,7 @@ compatible = "fsl,ns16550", "ns16550"; reg = <0x4600 0x100>; clock-frequency = <133333333>; - interrupts = <10 0x8>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; @@ -282,7 +288,7 @@ "fsl,sec2.4", "fsl,sec2.2", "fsl,sec2.1", "fsl,sec2.0"; reg = <0x30000 0x10000>; - interrupts = <11 0x8>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; fsl,num-channels = <4>; fsl,channel-fifo-len = <24>; @@ -294,7 +300,7 @@ compatible = "fsl,mpc8315-sata", "fsl,pq-sata"; reg = <0x18000 0x1000>; cell-index = <1>; - interrupts = <44 0x8>; + interrupts = <44 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; @@ -302,14 +308,17 @@ compatible = "fsl,mpc8315-sata", "fsl,pq-sata"; reg = <0x19000 0x1000>; cell-index = <2>; - interrupts = <45 0x8>; + interrupts = <45 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; gtm1: timer@500 { compatible = "fsl,mpc8315-gtm", "fsl,gtm"; reg = <0x500 0x100>; - interrupts = <90 8 78 8 84 8 72 8>; + interrupts = <90 IRQ_TYPE_LEVEL_LOW>, + <78 IRQ_TYPE_LEVEL_LOW>, + <84 IRQ_TYPE_LEVEL_LOW>, + <72 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; clock-frequency = <133333333>; }; @@ -317,16 +326,16 @@ timer@600 { compatible = "fsl,mpc8315-gtm", "fsl,gtm"; reg = <0x600 0x100>; - interrupts = <91 8 79 8 85 8 73 8>; + interrupts = <91 IRQ_TYPE_LEVEL_LOW>, + <79 IRQ_TYPE_LEVEL_LOW>, + <85 IRQ_TYPE_LEVEL_LOW>, + <73 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; clock-frequency = <133333333>; }; /* IPIC - * interrupts cell = <intr #, sense> - * sense values match linux IORESOURCE_IRQ_* defines: - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change + * interrupts cell = <intr #, type> */ ipic: interrupt-controller@700 { interrupt-controller; @@ -340,14 +349,14 @@ compatible = "fsl,ipic-msi"; reg = <0x7c0 0x40>; msi-available-ranges = <0 0x100>; - interrupts = <0x43 0x8 - 0x4 0x8 - 0x51 0x8 - 0x52 0x8 - 0x56 0x8 - 0x57 0x8 - 0x58 0x8 - 0x59 0x8>; + interrupts = <0x43 IRQ_TYPE_LEVEL_LOW + 0x4 IRQ_TYPE_LEVEL_LOW + 0x51 IRQ_TYPE_LEVEL_LOW + 0x52 IRQ_TYPE_LEVEL_LOW + 0x56 IRQ_TYPE_LEVEL_LOW + 0x57 IRQ_TYPE_LEVEL_LOW + 0x58 IRQ_TYPE_LEVEL_LOW + 0x59 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = < &ipic >; }; @@ -355,7 +364,7 @@ compatible = "fsl,mpc8315-pmc", "fsl,mpc8313-pmc", "fsl,mpc8349-pmc"; reg = <0xb00 0x100 0xa00 0x100>; - interrupts = <80 8>; + interrupts = <80 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; fsl,mpc8313-wakeup-timer = <>m1>; }; @@ -374,24 +383,24 @@ interrupt-map-mask = <0xf800 0x0 0x0 0x7>; interrupt-map = < /* IDSEL 0x0E -mini PCI */ - 0x7000 0x0 0x0 0x1 &ipic 18 0x8 - 0x7000 0x0 0x0 0x2 &ipic 18 0x8 - 0x7000 0x0 0x0 0x3 &ipic 18 0x8 - 0x7000 0x0 0x0 0x4 &ipic 18 0x8 + 0x7000 0x0 0x0 0x1 &ipic 18 IRQ_TYPE_LEVEL_LOW + 0x7000 0x0 0x0 0x2 &ipic 18 IRQ_TYPE_LEVEL_LOW + 0x7000 0x0 0x0 0x3 &ipic 18 IRQ_TYPE_LEVEL_LOW + 0x7000 0x0 0x0 0x4 &ipic 18 IRQ_TYPE_LEVEL_LOW /* IDSEL 0x0F -mini PCI */ - 0x7800 0x0 0x0 0x1 &ipic 17 0x8 - 0x7800 0x0 0x0 0x2 &ipic 17 0x8 - 0x7800 0x0 0x0 0x3 &ipic 17 0x8 - 0x7800 0x0 0x0 0x4 &ipic 17 0x8 + 0x7800 0x0 0x0 0x1 &ipic 17 IRQ_TYPE_LEVEL_LOW + 0x7800 0x0 0x0 0x2 &ipic 17 IRQ_TYPE_LEVEL_LOW + 0x7800 0x0 0x0 0x3 &ipic 17 IRQ_TYPE_LEVEL_LOW + 0x7800 0x0 0x0 0x4 &ipic 17 IRQ_TYPE_LEVEL_LOW /* IDSEL 0x10 - PCI slot */ - 0x8000 0x0 0x0 0x1 &ipic 48 0x8 - 0x8000 0x0 0x0 0x2 &ipic 17 0x8 - 0x8000 0x0 0x0 0x3 &ipic 48 0x8 - 0x8000 0x0 0x0 0x4 &ipic 17 0x8>; + 0x8000 0x0 0x0 0x1 &ipic 48 IRQ_TYPE_LEVEL_LOW + 0x8000 0x0 0x0 0x2 &ipic 17 IRQ_TYPE_LEVEL_LOW + 0x8000 0x0 0x0 0x3 &ipic 48 IRQ_TYPE_LEVEL_LOW + 0x8000 0x0 0x0 0x4 &ipic 17 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; - interrupts = <66 0x8>; + interrupts = <66 IRQ_TYPE_LEVEL_LOW>; bus-range = <0x0 0x0>; ranges = <0x02000000 0 0x90000000 0x90000000 0 0x10000000 0x42000000 0 0x80000000 0x80000000 0 0x10000000 @@ -417,10 +426,10 @@ 0x01000000 0 0x00000000 0xb1000000 0 0x00800000>; bus-range = <0 255>; interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = <0 0 0 1 &ipic 1 8 - 0 0 0 2 &ipic 1 8 - 0 0 0 3 &ipic 1 8 - 0 0 0 4 &ipic 1 8>; + interrupt-map = <0 0 0 1 &ipic 1 IRQ_TYPE_LEVEL_LOW + 0 0 0 2 &ipic 1 IRQ_TYPE_LEVEL_LOW + 0 0 0 3 &ipic 1 IRQ_TYPE_LEVEL_LOW + 0 0 0 4 &ipic 1 IRQ_TYPE_LEVEL_LOW>; clock-frequency = <0>; pcie@0 { @@ -448,10 +457,10 @@ 0x01000000 0 0x00000000 0xd1000000 0 0x00800000>; bus-range = <0 255>; interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = <0 0 0 1 &ipic 2 8 - 0 0 0 2 &ipic 2 8 - 0 0 0 3 &ipic 2 8 - 0 0 0 4 &ipic 2 8>; + interrupt-map = <0 0 0 1 &ipic 2 IRQ_TYPE_LEVEL_LOW + 0 0 0 2 &ipic 2 IRQ_TYPE_LEVEL_LOW + 0 0 0 3 &ipic 2 IRQ_TYPE_LEVEL_LOW + 0 0 0 4 &ipic 2 IRQ_TYPE_LEVEL_LOW>; clock-frequency = <0>; pcie@0 { @@ -471,12 +480,12 @@ leds { compatible = "gpio-leds"; - pwr { + led-pwr { gpios = <&mcu_pio 0 0>; default-state = "on"; }; - hdd { + led-hdd { gpios = <&mcu_pio 1 0>; linux,default-trigger = "disk-activity"; }; diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts index ba7caaf98fd5..06f134490d95 100644 --- a/arch/powerpc/boot/dts/mpc832x_rdb.dts +++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts @@ -38,7 +38,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x04000000>; }; diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts index 13f17232ba83..12d33cb55b72 100644 --- a/arch/powerpc/boot/dts/mpc8349emitx.dts +++ b/arch/powerpc/boot/dts/mpc8349emitx.dts @@ -39,7 +39,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; }; diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts index eae0afd5abbc..2998a233a790 100644 --- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts +++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts @@ -37,7 +37,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; }; diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts index f137ccb8cfde..fb311a7eb9f2 100644 --- a/arch/powerpc/boot/dts/mpc8377_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts @@ -39,7 +39,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; // 256MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8377_wlan.dts b/arch/powerpc/boot/dts/mpc8377_wlan.dts index ce254dd74dd0..f736a15cceff 100644 --- a/arch/powerpc/boot/dts/mpc8377_wlan.dts +++ b/arch/powerpc/boot/dts/mpc8377_wlan.dts @@ -40,7 +40,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x20000000>; // 512MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts index 19e5473d4161..32c49622b404 100644 --- a/arch/powerpc/boot/dts/mpc8378_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts @@ -39,7 +39,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; // 256MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts index 61519acca228..07deb89c5a9b 100644 --- a/arch/powerpc/boot/dts/mpc8379_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts @@ -37,7 +37,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; // 256MB at 0 }; diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 2d71e4b7cd09..496ecc65ac25 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -120,10 +120,8 @@ #if defined(CONFIG_44x) #include <asm/nohash/32/pte-44x.h> -#elif defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT) -#include <asm/nohash/pte-e500.h> #elif defined(CONFIG_PPC_85xx) -#include <asm/nohash/32/pte-85xx.h> +#include <asm/nohash/pte-e500.h> #elif defined(CONFIG_PPC_8xx) #include <asm/nohash/32/pte-8xx.h> #endif diff --git a/arch/powerpc/include/asm/nohash/32/pte-85xx.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h deleted file mode 100644 index 14d64b4f3f14..000000000000 --- a/arch/powerpc/include/asm/nohash/32/pte-85xx.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_32_PTE_85xx_H -#define _ASM_POWERPC_NOHASH_32_PTE_85xx_H -#ifdef __KERNEL__ - -/* PTE bit definitions for Freescale BookE SW loaded TLB MMU based - * processors - * - MMU Assist Register 3: - - 32 33 34 35 36 ... 50 51 52 53 54 55 56 57 58 59 60 61 62 63 - RPN...................... 0 0 U0 U1 U2 U3 UX SX UW SW UR SR - - - PRESENT *must* be in the bottom two bits because swap PTEs use - the top 30 bits. - -*/ - -/* Definitions for FSL Book-E Cores */ -#define _PAGE_READ 0x00001 /* H: Read permission (SR) */ -#define _PAGE_PRESENT 0x00002 /* S: PTE contains a translation */ -#define _PAGE_WRITE 0x00004 /* S: Write permission (SW) */ -#define _PAGE_DIRTY 0x00008 /* S: Page dirty */ -#define _PAGE_EXEC 0x00010 /* H: SX permission */ -#define _PAGE_ACCESSED 0x00020 /* S: Page referenced */ - -#define _PAGE_ENDIAN 0x00040 /* H: E bit */ -#define _PAGE_GUARDED 0x00080 /* H: G bit */ -#define _PAGE_COHERENT 0x00100 /* H: M bit */ -#define _PAGE_NO_CACHE 0x00200 /* H: I bit */ -#define _PAGE_WRITETHRU 0x00400 /* H: W bit */ -#define _PAGE_SPECIAL 0x00800 /* S: Special page */ - -#define _PMD_PRESENT 0 -#define _PMD_PRESENT_MASK (PAGE_MASK) -#define _PMD_BAD (~PAGE_MASK) -#define _PMD_USER 0 - -#define _PTE_NONE_MASK 0 - -#define PTE_WIMGE_SHIFT (6) - -/* - * We define 2 sets of base prot bits, one for basic pages (ie, - * cacheable kernel and user pages) and one for non cacheable - * pages. We always set _PAGE_COHERENT when SMP is enabled or - * the processor might need it for DMA coherency. - */ -#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) -#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC) -#define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) -#else -#define _PAGE_BASE (_PAGE_BASE_NC) -#endif - -#include <asm/pgtable-masks.h> - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_85xx_H */ diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h index f3086e39e7d2..e8dec885b6e4 100644 --- a/arch/powerpc/include/asm/pgtable-types.h +++ b/arch/powerpc/include/asm/pgtable-types.h @@ -49,7 +49,7 @@ static inline unsigned long pud_val(pud_t x) #endif /* CONFIG_PPC64 */ /* PGD level */ -#if defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT) +#if defined(CONFIG_PPC_85xx) typedef struct { unsigned long long pgd; } pgd_t; static inline unsigned long long pgd_val(pgd_t x) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index ba1d878c3f40..17e63244e885 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -15,6 +15,9 @@ #define TASK_SIZE_MAX TASK_SIZE_USER64 #endif +/* Threshold above which VMX copy path is used */ +#define VMX_COPY_THRESHOLD 3328 + #include <asm-generic/access_ok.h> /* @@ -255,7 +258,7 @@ __gus_failed: \ ".section .fixup,\"ax\"\n" \ "4: li %0,%3\n" \ " li %1,0\n" \ - " li %1+1,0\n" \ + " li %L1,0\n" \ " b 3b\n" \ ".previous\n" \ EX_TABLE(1b, 4b) \ @@ -326,40 +329,62 @@ do { \ extern unsigned long __copy_tofrom_user(void __user *to, const void __user *from, unsigned long size); -#ifdef __powerpc64__ -static inline unsigned long -raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) +unsigned long __copy_tofrom_user_base(void __user *to, + const void __user *from, unsigned long size); + +unsigned long __copy_tofrom_user_power7_vmx(void __user *to, + const void __user *from, unsigned long size); + +static __always_inline bool will_use_vmx(unsigned long n) +{ + return IS_ENABLED(CONFIG_ALTIVEC) && cpu_has_feature(CPU_FTR_VMX_COPY) && + n > VMX_COPY_THRESHOLD; +} + +static __always_inline unsigned long +raw_copy_tofrom_user(void __user *to, const void __user *from, + unsigned long n, unsigned long dir) { unsigned long ret; - barrier_nospec(); - allow_user_access(to, KUAP_READ_WRITE); + if (will_use_vmx(n) && enter_vmx_usercopy()) { + allow_user_access(to, dir); + ret = __copy_tofrom_user_power7_vmx(to, from, n); + prevent_user_access(dir); + exit_vmx_usercopy(); + + if (unlikely(ret)) { + allow_user_access(to, dir); + ret = __copy_tofrom_user_base(to, from, n); + prevent_user_access(dir); + } + return ret; + } + + allow_user_access(to, dir); ret = __copy_tofrom_user(to, from, n); - prevent_user_access(KUAP_READ_WRITE); + prevent_user_access(dir); return ret; } -#endif /* __powerpc64__ */ -static inline unsigned long raw_copy_from_user(void *to, - const void __user *from, unsigned long n) +#ifdef CONFIG_PPC64 +static inline unsigned long +raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { - unsigned long ret; + barrier_nospec(); + return raw_copy_tofrom_user(to, from, n, KUAP_READ_WRITE); +} +#endif /* CONFIG_PPC64 */ - allow_user_access(NULL, KUAP_READ); - ret = __copy_tofrom_user((__force void __user *)to, from, n); - prevent_user_access(KUAP_READ); - return ret; +static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) +{ + return raw_copy_tofrom_user((__force void __user *)to, from, n, KUAP_READ); } static inline unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n) { - unsigned long ret; - - allow_user_access(to, KUAP_WRITE); - ret = __copy_tofrom_user(to, (__force const void __user *)from, n); - prevent_user_access(KUAP_WRITE); - return ret; + return raw_copy_tofrom_user(to, (__force const void __user *)from, n, KUAP_WRITE); } unsigned long __arch_clear_user(void __user *addr, unsigned long size); diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index f9a73fae6464..8867596d35ad 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -305,7 +305,6 @@ set_ivor: * r12 is pointer to the pte * r10 is the pshift from the PGD, if we're a hugepage */ -#ifdef CONFIG_PTE_64BIT #ifdef CONFIG_HUGETLB_PAGE #define FIND_PTE \ rlwinm r12, r13, 14, 18, 28; /* Compute pgdir/pmd offset */ \ @@ -329,15 +328,6 @@ set_ivor: rlwimi r12, r13, 23, 20, 28; /* Compute pte address */ \ lwz r11, 4(r12); /* Get pte entry */ #endif /* HUGEPAGE */ -#else /* !PTE_64BIT */ -#define FIND_PTE \ - rlwimi r11, r13, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \ - lwz r11, 0(r11); /* Get L1 entry */ \ - rlwinm. r12, r11, 0, 0, 19; /* Extract L2 (pte) base address */ \ - beq 2f; /* Bail if no table */ \ - rlwimi r12, r13, 22, 20, 29; /* Compute PTE address */ \ - lwz r11, 0(r12); /* Get Linux PTE */ -#endif /* * Interrupt vector entry code @@ -473,22 +463,16 @@ END_BTB_FLUSH_SECTION 4: FIND_PTE -#ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT|_PAGE_BAP_SR oris r13,r13,_PAGE_ACCESSED@h -#else - li r13,_PAGE_PRESENT|_PAGE_READ|_PAGE_ACCESSED -#endif andc. r13,r13,r11 /* Check permission */ -#ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP subf r13,r11,r12 /* create false data dep */ lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ #endif -#endif bne 2f /* Bail if permission/valid mismatch */ @@ -552,12 +536,8 @@ END_BTB_FLUSH_SECTION FIND_PTE /* Make up the required permissions for kernel code */ -#ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT | _PAGE_BAP_SX oris r13,r13,_PAGE_ACCESSED@h -#else - li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#endif b 4f /* Get the PGD for the current thread */ @@ -573,24 +553,18 @@ END_BTB_FLUSH_SECTION FIND_PTE /* Make up the required permissions for user code */ -#ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT | _PAGE_BAP_UX oris r13,r13,_PAGE_ACCESSED@h -#else - li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#endif 4: andc. r13,r13,r11 /* Check permission */ -#ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP subf r13,r11,r12 /* create false data dep */ lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ #endif -#endif bne 2f /* Bail if permission mismatch */ @@ -683,7 +657,7 @@ interrupt_end: * r10 - tsize encoding (if HUGETLB_PAGE) or available to use * r11 - TLB (info from Linux PTE) * r12 - available to use - * r13 - upper bits of PTE (if PTE_64BIT) or available to use + * r13 - upper bits of PTE * CR5 - results of addr >= PAGE_OFFSET * MAS0, MAS1 - loaded with proper value when we get here * MAS2, MAS3 - will need additional info from Linux PTE @@ -751,7 +725,6 @@ finish_tlb_load: * here we (properly should) assume have the appropriate value. */ finish_tlb_load_cont: -#ifdef CONFIG_PTE_64BIT rlwinm r12, r11, 32-2, 26, 31 /* Move in perm bits */ andi. r10, r11, _PAGE_DIRTY bne 1f @@ -764,26 +737,9 @@ BEGIN_MMU_FTR_SECTION srwi r10, r13, 12 /* grab RPN[12:31] */ mtspr SPRN_MAS7, r10 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) -#else - li r10, (_PAGE_EXEC | _PAGE_READ) - mr r13, r11 - rlwimi r10, r11, 31, 29, 29 /* extract _PAGE_DIRTY into SW */ - and r12, r11, r10 - mcrf cr0, cr5 /* Test for user page */ - slwi r10, r12, 1 - or r10, r10, r12 - rlwinm r10, r10, 0, ~_PAGE_EXEC /* Clear SX on user pages */ - isellt r12, r10, r12 - rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */ - mtspr SPRN_MAS3, r13 -#endif mfspr r12, SPRN_MAS2 -#ifdef CONFIG_PTE_64BIT rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */ -#else - rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ -#endif #ifdef CONFIG_HUGETLB_PAGE beq 6, 3f /* don't mask if page isn't huge */ li r13, 1 diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0ce71310b7d9..d122e8447831 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1159,7 +1159,7 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain, struct device *dev, struct iommu_domain *old) { - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + struct iommu_domain *domain = iommu_driver_get_domain_for_dev(dev); struct iommu_table_group *table_group; struct iommu_group *grp; diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 756043dd06e9..fb9fbf0d1796 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -212,6 +212,13 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->error_state = pci_channel_io_normal; dev->dma_mask = 0xffffffff; + /* + * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit + * if MSI (rather than MSI-X) capability does not have + * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver. + */ + dev->msi_addr_mask = DMA_BIT_MASK(64); + /* Early fixups, before probing the BARs */ pci_fixup_device(pci_fixup_early, dev); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 827c958677f8..f26e80cbc615 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2893,7 +2893,8 @@ static void __init fixup_device_tree_pmac(void) for (node = 0; prom_next_node(&node); ) { type[0] = '\0'; prom_getprop(node, "device_type", type, sizeof(type)); - if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s")) + if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s") && + prom_strcmp(type, "media-bay")) continue; if (prom_getproplen(node, "#size-cells") != PROM_ERROR) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index cb5b73adc250..b1761909c23f 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -35,7 +35,6 @@ #include <linux/of_irq.h> #include <linux/hugetlb.h> #include <linux/pgtable.h> -#include <asm/kexec.h> #include <asm/io.h> #include <asm/paca.h> #include <asm/processor.h> @@ -995,15 +994,6 @@ void __init setup_arch(char **cmdline_p) initmem_init(); - /* - * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM and - * hugetlb. These must be called after initmem_init(), so that - * pageblock_order is initialised. - */ - fadump_cma_init(); - kdump_cma_reserve(); - kvm_cma_reserve(); - early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); if (ppc_md.setup_arch) diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 841d077e2825..1b2f293e7dcb 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -37,11 +37,29 @@ unsigned long ftrace_call_adjust(unsigned long addr) if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end) return 0; - if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) && - !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { - addr += MCOUNT_INSN_SIZE; - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) { + if (!IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { addr += MCOUNT_INSN_SIZE; + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + addr += MCOUNT_INSN_SIZE; + } else if (IS_ENABLED(CONFIG_CC_IS_CLANG) && IS_ENABLED(CONFIG_PPC64)) { + /* + * addr points to global entry point though the NOP was emitted at local + * entry point due to https://github.com/llvm/llvm-project/issues/163706 + * Handle that here with ppc_function_entry() for kernel symbols while + * adjusting module addresses in the else case, by looking for the below + * module global entry point sequence: + * ld r2, -8(r12) + * add r2, r2, r12 + */ + if (is_kernel_text(addr) || is_kernel_inittext(addr)) + addr = ppc_function_entry((void *)addr); + else if ((ppc_inst_val(ppc_inst_read((u32 *)addr)) == + PPC_RAW_LD(_R2, _R12, -8)) && + (ppc_inst_val(ppc_inst_read((u32 *)(addr+4))) == + PPC_RAW_ADD(_R2, _R2, _R12))) + addr += 8; + } } return addr; diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 15850296c0a9..8fc11d6565bf 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -397,6 +397,7 @@ SECTIONS _end = . ; DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index 104c05520bf0..dc44f11be353 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -23,6 +23,7 @@ #include <asm/firmware.h> #define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG) +#define __be_word __PASTE(__be, BITS_PER_LONG) #ifdef CONFIG_CRASH_DUMP void machine_crash_shutdown(struct pt_regs *regs) @@ -146,25 +147,25 @@ int __init overlaps_crashkernel(unsigned long start, unsigned long size) } /* Values we need to export to the second kernel via the device tree. */ -static phys_addr_t crashk_base; -static phys_addr_t crashk_size; -static unsigned long long mem_limit; +static __be_word crashk_base; +static __be_word crashk_size; +static __be_word mem_limit; static struct property crashk_base_prop = { .name = "linux,crashkernel-base", - .length = sizeof(phys_addr_t), + .length = sizeof(__be_word), .value = &crashk_base }; static struct property crashk_size_prop = { .name = "linux,crashkernel-size", - .length = sizeof(phys_addr_t), + .length = sizeof(__be_word), .value = &crashk_size, }; static struct property memory_limit_prop = { .name = "linux,memory-limit", - .length = sizeof(unsigned long long), + .length = sizeof(__be_word), .value = &mem_limit, }; @@ -193,11 +194,11 @@ static void __init export_crashk_values(struct device_node *node) } #endif /* CONFIG_CRASH_RESERVE */ -static phys_addr_t kernel_end; +static __be_word kernel_end; static struct property kernel_end_prop = { .name = "linux,kernel-end", - .length = sizeof(phys_addr_t), + .length = sizeof(__be_word), .value = &kernel_end, }; diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index e7ef8b2a2554..5f6d50e4c3d4 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -450,6 +450,11 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) kbuf->buffer = headers; kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; kbuf->bufsz = headers_sz; + + /* + * Account for extra space required to accommodate additional memory + * ranges in elfcorehdr due to memory hotplug events. + */ kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem); kbuf->top_down = false; @@ -460,7 +465,14 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) } image->elf_load_addr = kbuf->mem; - image->elf_headers_sz = headers_sz; + + /* + * If CONFIG_CRASH_HOTPLUG is enabled, the elfcorehdr kexec segment + * memsz can be larger than bufsz. Always initialize elf_headers_sz + * with memsz. This ensures the correct size is reserved for elfcorehdr + * memory in the FDT prepared for kdump. + */ + image->elf_headers_sz = kbuf->memsz; image->elf_headers = headers; out: kfree(cmem); diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index c9a2d50ff1b0..9a0d1c1aca6c 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -38,7 +38,6 @@ config KVM_BOOK3S_64_HANDLER config KVM_BOOK3S_PR_POSSIBLE bool select KVM_MMIO - select KVM_GENERIC_MMU_NOTIFIER config KVM_BOOK3S_HV_POSSIBLE bool @@ -81,7 +80,6 @@ config KVM_BOOK3S_64_HV tristate "KVM for POWER7 and later using hypervisor mode in host" depends on KVM_BOOK3S_64 && PPC_POWERNV select KVM_BOOK3S_HV_POSSIBLE - select KVM_GENERIC_MMU_NOTIFIER select KVM_BOOK3S_HV_PMU select CMA help @@ -203,7 +201,6 @@ config KVM_E500V2 depends on !CONTEXT_TRACKING_USER select KVM select KVM_MMIO - select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500 guest kernels in virtual machines on E500v2 host processors. @@ -220,7 +217,6 @@ config KVM_E500MC select KVM select KVM_MMIO select KVM_BOOKE_HV - select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500MC/E5500/E6500 guest kernels in virtual machines on E500MC/E5500/E6500 host processors. diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index d79c5d1098c0..2efbe05caed7 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -38,7 +38,7 @@ /* #define EXIT_DEBUG */ -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) @@ -53,7 +53,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, sum_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 3401b96be475..f3ddb24ece74 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -36,7 +36,7 @@ unsigned long kvmppc_booke_handlers; -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) @@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, sum_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index f9acf866c709..e4469ad73a2e 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -39,15 +39,11 @@ enum vcpu_ftr { /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */ #define E500_TLB_MAS2_ATTR (0x7f) -struct tlbe_ref { +struct tlbe_priv { kvm_pfn_t pfn; /* valid only for TLB0, except briefly */ unsigned int flags; /* E500_TLB_* */ }; -struct tlbe_priv { - struct tlbe_ref ref; -}; - #ifdef CONFIG_KVM_E500V2 struct vcpu_id_table; #endif diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 48580c85f23b..75ed1496ead5 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -920,12 +920,12 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) vcpu_e500->gtlb_offset[0] = 0; vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE; - vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_ref, + vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_priv, vcpu_e500->gtlb_params[0].entries); if (!vcpu_e500->gtlb_priv[0]) goto free_vcpu; - vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_ref, + vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_priv, vcpu_e500->gtlb_params[1].entries); if (!vcpu_e500->gtlb_priv[1]) goto free_vcpu; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 06caf8bbbe2b..37e0d3d9e244 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -189,16 +189,16 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, { struct kvm_book3e_206_tlb_entry *gtlbe = get_entry(vcpu_e500, tlbsel, esel); - struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; + struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[tlbsel][esel]; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) { - WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), - "%s: flags %x\n", __func__, ref->flags); + if (!(tlbe->flags & E500_TLB_VALID)) { + WARN(tlbe->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, tlbe->flags); WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); } - if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { + if (tlbsel == 1 && tlbe->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; int hw_tlb_indx; unsigned long flags; @@ -216,28 +216,28 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, } mb(); vcpu_e500->g2h_tlb1_map[esel] = 0; - ref->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID); + tlbe->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID); local_irq_restore(flags); } - if (tlbsel == 1 && ref->flags & E500_TLB_TLB0) { + if (tlbsel == 1 && tlbe->flags & E500_TLB_TLB0) { /* * TLB1 entry is backed by 4k pages. This should happen * rarely and is not worth optimizing. Invalidate everything. */ kvmppc_e500_tlbil_all(vcpu_e500); - ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID); + tlbe->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID); } /* * If TLB entry is still valid then it's a TLB0 entry, and thus * backed by at most one host tlbe per shadow pid */ - if (ref->flags & E500_TLB_VALID) + if (tlbe->flags & E500_TLB_VALID) kvmppc_e500_tlbil_one(vcpu_e500, gtlbe); /* Mark the TLB as not backed by the host anymore */ - ref->flags = 0; + tlbe->flags = 0; } static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) @@ -245,26 +245,26 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) return tlbe->mas7_3 & (MAS3_SW|MAS3_UW); } -static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, - struct kvm_book3e_206_tlb_entry *gtlbe, - kvm_pfn_t pfn, unsigned int wimg, - bool writable) +static inline void kvmppc_e500_tlbe_setup(struct tlbe_priv *tlbe, + struct kvm_book3e_206_tlb_entry *gtlbe, + kvm_pfn_t pfn, unsigned int wimg, + bool writable) { - ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + tlbe->pfn = pfn; + tlbe->flags = E500_TLB_VALID; if (writable) - ref->flags |= E500_TLB_WRITABLE; + tlbe->flags |= E500_TLB_WRITABLE; /* Use guest supplied MAS2_G and MAS2_E */ - ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; + tlbe->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; } -static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) +static inline void kvmppc_e500_tlbe_release(struct tlbe_priv *tlbe) { - if (ref->flags & E500_TLB_VALID) { + if (tlbe->flags & E500_TLB_VALID) { /* FIXME: don't log bogus pfn for TLB1 */ - trace_kvm_booke206_ref_release(ref->pfn, ref->flags); - ref->flags = 0; + trace_kvm_booke206_ref_release(tlbe->pfn, tlbe->flags); + tlbe->flags = 0; } } @@ -284,11 +284,8 @@ static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) int i; for (tlbsel = 0; tlbsel <= 1; tlbsel++) { - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); - } + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) + kvmppc_e500_tlbe_release(&vcpu_e500->gtlb_priv[tlbsel][i]); } } @@ -304,18 +301,18 @@ void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) static void kvmppc_e500_setup_stlbe( struct kvm_vcpu *vcpu, struct kvm_book3e_206_tlb_entry *gtlbe, - int tsize, struct tlbe_ref *ref, u64 gvaddr, + int tsize, struct tlbe_priv *tlbe, u64 gvaddr, struct kvm_book3e_206_tlb_entry *stlbe) { - kvm_pfn_t pfn = ref->pfn; + kvm_pfn_t pfn = tlbe->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; - bool writable = !!(ref->flags & E500_TLB_WRITABLE); + bool writable = !!(tlbe->flags & E500_TLB_WRITABLE); - BUG_ON(!(ref->flags & E500_TLB_VALID)); + BUG_ON(!(tlbe->flags & E500_TLB_VALID)); /* Force IPROT=0 for all guest mappings. */ stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; - stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR); + stlbe->mas2 = (gvaddr & MAS2_EPN) | (tlbe->flags & E500_TLB_MAS2_ATTR); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr); } @@ -323,7 +320,7 @@ static void kvmppc_e500_setup_stlbe( static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe, - struct tlbe_ref *ref) + struct tlbe_priv *tlbe) { struct kvm_memory_slot *slot; unsigned int psize; @@ -455,9 +452,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, } } - kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable); + kvmppc_e500_tlbe_setup(tlbe, gtlbe, pfn, wimg, writable); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, - ref, gvaddr, stlbe); + tlbe, gvaddr, stlbe); writable = tlbe_is_writable(stlbe); /* Clear i-cache for new pages */ @@ -474,17 +471,17 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel, struct kvm_book3e_206_tlb_entry *stlbe) { struct kvm_book3e_206_tlb_entry *gtlbe; - struct tlbe_ref *ref; + struct tlbe_priv *tlbe; int stlbsel = 0; int sesel = 0; int r; gtlbe = get_entry(vcpu_e500, 0, esel); - ref = &vcpu_e500->gtlb_priv[0][esel].ref; + tlbe = &vcpu_e500->gtlb_priv[0][esel]; r = kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe), get_tlb_raddr(gtlbe) >> PAGE_SHIFT, - gtlbe, 0, stlbe, ref); + gtlbe, 0, stlbe, tlbe); if (r) return r; @@ -494,7 +491,7 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel, } static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, - struct tlbe_ref *ref, + struct tlbe_priv *tlbe, int esel) { unsigned int sesel = vcpu_e500->host_tlb1_nv++; @@ -507,10 +504,10 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_BITMAP; vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; - WARN_ON(!(ref->flags & E500_TLB_VALID)); + WARN_ON(!(tlbe->flags & E500_TLB_VALID)); return sesel; } @@ -522,24 +519,24 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; + struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[1][esel]; int sesel; int r; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - ref); + tlbe); if (r) return r; /* Use TLB0 when we can only map a page with 4k */ if (get_tlb_tsize(stlbe) == BOOK3E_PAGESZ_4K) { - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_TLB0; + vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_TLB0; write_stlbe(vcpu_e500, gtlbe, stlbe, 0, 0); return 0; } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, tlbe, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -561,11 +558,11 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; /* Triggers after clear_tlb_privs or on initial mapping */ - if (!(priv->ref.flags & E500_TLB_VALID)) { + if (!(priv->flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K, - &priv->ref, eaddr, &stlbe); + priv, eaddr, &stlbe); write_stlbe(vcpu_e500, gtlbe, &stlbe, 0, 0); } break; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9a89a6d98f97..00302399fc37 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -623,12 +623,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !!(hv_enabled && kvmppc_hv_ops->enable_nested && !kvmppc_hv_ops->enable_nested(NULL)); break; -#endif - case KVM_CAP_SYNC_MMU: - BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER)); - r = 1; - break; -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_HTAB_FD: r = hv_enabled; break; diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S index 9af969d2cc0c..25a99108caff 100644 --- a/arch/powerpc/lib/copyuser_64.S +++ b/arch/powerpc/lib/copyuser_64.S @@ -562,3 +562,4 @@ exc; std r10,32(3) li r5,4096 b .Ldst_aligned EXPORT_SYMBOL(__copy_tofrom_user) +EXPORT_SYMBOL(__copy_tofrom_user_base) diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 8474c682a178..17dbcfbae25f 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -5,13 +5,9 @@ * * Author: Anton Blanchard <anton@au.ibm.com> */ +#include <linux/export.h> #include <asm/ppc_asm.h> -#ifndef SELFTEST_CASE -/* 0 == don't use VMX, 1 == use VMX */ -#define SELFTEST_CASE 0 -#endif - #ifdef __BIG_ENDIAN__ #define LVS(VRT,RA,RB) lvsl VRT,RA,RB #define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC @@ -47,10 +43,14 @@ ld r15,STK_REG(R15)(r1) ld r14,STK_REG(R14)(r1) .Ldo_err3: - bl CFUNC(exit_vmx_usercopy) + ld r6,STK_REG(R31)(r1) /* original destination pointer */ + ld r5,STK_REG(R29)(r1) /* original number of bytes */ + subf r7,r6,r3 /* #bytes copied */ + subf r3,r7,r5 /* #bytes not copied in r3 */ ld r0,STACKFRAMESIZE+16(r1) mtlr r0 - b .Lexit + addi r1,r1,STACKFRAMESIZE + blr #endif /* CONFIG_ALTIVEC */ .Ldo_err2: @@ -74,7 +74,6 @@ _GLOBAL(__copy_tofrom_user_power7) cmpldi r5,16 - cmpldi cr1,r5,3328 std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) @@ -82,12 +81,6 @@ _GLOBAL(__copy_tofrom_user_power7) blt .Lshort_copy -#ifdef CONFIG_ALTIVEC -test_feature = SELFTEST_CASE -BEGIN_FTR_SECTION - bgt cr1,.Lvmx_copy -END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) -#endif .Lnonvmx_copy: /* Get the source 8B aligned */ @@ -263,23 +256,14 @@ err1; stb r0,0(r3) 15: li r3,0 blr -.Lunwind_stack_nonvmx_copy: - addi r1,r1,STACKFRAMESIZE - b .Lnonvmx_copy - -.Lvmx_copy: #ifdef CONFIG_ALTIVEC +_GLOBAL(__copy_tofrom_user_power7_vmx) mflr r0 std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl CFUNC(enter_vmx_usercopy) - cmpwi cr1,r3,0 - ld r0,STACKFRAMESIZE+16(r1) - ld r3,STK_REG(R31)(r1) - ld r4,STK_REG(R30)(r1) - ld r5,STK_REG(R29)(r1) - mtlr r0 + std r3,STK_REG(R31)(r1) + std r5,STK_REG(R29)(r1) /* * We prefetch both the source and destination using enhanced touch * instructions. We use a stream ID of 0 for the load side and @@ -300,8 +284,6 @@ err1; stb r0,0(r3) DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8) - beq cr1,.Lunwind_stack_nonvmx_copy - /* * If source and destination are not relatively aligned we use a * slower permute loop. @@ -478,7 +460,8 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b CFUNC(exit_vmx_usercopy) /* tail call optimise */ + li r3,0 + blr .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -681,5 +664,7 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b CFUNC(exit_vmx_usercopy) /* tail call optimise */ + li r3,0 + blr +EXPORT_SYMBOL(__copy_tofrom_user_power7_vmx) #endif /* CONFIG_ALTIVEC */ diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index 54340912398f..554b248002b4 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -27,6 +27,7 @@ int enter_vmx_usercopy(void) return 1; } +EXPORT_SYMBOL(enter_vmx_usercopy); /* * This function must return 0 because we tail call optimise when calling @@ -49,6 +50,7 @@ int exit_vmx_usercopy(void) set_dec(1); return 0; } +EXPORT_SYMBOL(exit_vmx_usercopy); int enter_vmx_ops(void) { diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index a985fc96b953..b7982d0243d4 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -30,6 +30,10 @@ #include <asm/setup.h> #include <asm/fixmap.h> +#include <asm/fadump.h> +#include <asm/kexec.h> +#include <asm/kvm_ppc.h> + #include <mm/mmu_decl.h> unsigned long long memory_limit __initdata; @@ -268,6 +272,16 @@ void __init paging_init(void) void __init arch_mm_preinit(void) { + + /* + * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM + * and hugetlb. These must be called after pageblock_order is + * initialised. + */ + fadump_cma_init(); + kdump_cma_reserve(); + kvm_cma_reserve(); + /* * book3s is limited to 16 page sizes due to encoding this in * a 4-bit field for slices. diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 82bbf63f0e57..7354e1d72f79 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -81,9 +81,6 @@ #ifdef CONFIG_PPC64 -/* for gpr non volatile registers BPG_REG_6 to 10 */ -#define BPF_PPC_STACK_SAVE (6 * 8) - /* If dummy pass (!image), account for maximum possible instructions */ #define PPC_LI64(d, i) do { \ if (!image) \ @@ -219,8 +216,6 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass, struct codegen_context *ctx, int insn_idx, int jmp_off, int dst_reg, u32 code); - -int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx); #endif #endif diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 52162e4a7f84..a62a9a92b7b5 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -450,7 +450,7 @@ bool bpf_jit_supports_subprog_tailcalls(void) bool bpf_jit_supports_kfunc_call(void) { - return true; + return IS_ENABLED(CONFIG_PPC64); } bool bpf_jit_supports_arena(void) @@ -638,19 +638,12 @@ static int invoke_bpf_mod_ret(u32 *image, u32 *ro_image, struct codegen_context * for the traced function (BPF subprog/callee) to fetch it. */ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_context *ctx, - int func_frame_offset, - int bpf_dummy_frame_size, int r4_off) + int bpf_frame_size, int r4_off) { if (IS_ENABLED(CONFIG_PPC64)) { - /* See Generated stack layout */ - int tailcallinfo_offset = BPF_PPC_TAILCALL; - - /* - * func_frame_offset = ...(1) - * bpf_dummy_frame_size + trampoline_frame_size - */ - EMIT(PPC_RAW_LD(_R4, _R1, func_frame_offset)); - EMIT(PPC_RAW_LD(_R3, _R4, -tailcallinfo_offset)); + EMIT(PPC_RAW_LD(_R4, _R1, bpf_frame_size)); + /* Refer to trampoline's Generated stack layout */ + EMIT(PPC_RAW_LD(_R3, _R4, -BPF_PPC_TAILCALL)); /* * Setting the tail_call_info in trampoline's frame @@ -658,22 +651,14 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte */ EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT)); PPC_BCC_CONST_SHORT(COND_GT, 8); - EMIT(PPC_RAW_ADDI(_R3, _R4, bpf_jit_stack_tailcallinfo_offset(ctx))); + EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL)); + /* - * From ...(1) above: - * trampoline_frame_bottom = ...(2) - * func_frame_offset - bpf_dummy_frame_size - * - * Using ...(2) derived above: - * trampoline_tail_call_info_offset = ...(3) - * trampoline_frame_bottom - tailcallinfo_offset - * - * From ...(3): - * Use trampoline_tail_call_info_offset to write reference of main's - * tail_call_info in trampoline frame. + * Trampoline's tail_call_info is at the same offset, as that of + * any bpf program, with reference to previous frame. Update the + * address of main's tail_call_info in trampoline frame. */ - EMIT(PPC_RAW_STL(_R3, _R1, (func_frame_offset - bpf_dummy_frame_size) - - tailcallinfo_offset)); + EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size - BPF_PPC_TAILCALL)); } else { /* See bpf_jit_stack_offsetof() and BPF_PPC_TC */ EMIT(PPC_RAW_LL(_R4, _R1, r4_off)); @@ -681,7 +666,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte } static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_context *ctx, - int func_frame_offset, int r4_off) + int bpf_frame_size, int r4_off) { if (IS_ENABLED(CONFIG_PPC32)) { /* @@ -692,12 +677,12 @@ static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_cont } } -static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx, int func_frame_offset, - int nr_regs, int regs_off) +static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx, + int bpf_frame_size, int nr_regs, int regs_off) { int param_save_area_offset; - param_save_area_offset = func_frame_offset; /* the two frames we alloted */ + param_save_area_offset = bpf_frame_size; param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */ for (int i = 0; i < nr_regs; i++) { @@ -720,11 +705,11 @@ static void bpf_trampoline_restore_args_regs(u32 *image, struct codegen_context /* Used when we call into the traced function. Replicate parameter save area */ static void bpf_trampoline_restore_args_stack(u32 *image, struct codegen_context *ctx, - int func_frame_offset, int nr_regs, int regs_off) + int bpf_frame_size, int nr_regs, int regs_off) { int param_save_area_offset; - param_save_area_offset = func_frame_offset; /* the two frames we alloted */ + param_save_area_offset = bpf_frame_size; param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */ for (int i = 8; i < nr_regs; i++) { @@ -741,10 +726,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im void *func_addr) { int regs_off, nregs_off, ip_off, run_ctx_off, retval_off, nvr_off, alt_lr_off, r4_off = 0; - int i, ret, nr_regs, bpf_frame_size = 0, bpf_dummy_frame_size = 0, func_frame_offset; struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; + int i, ret, nr_regs, retaddr_off, bpf_frame_size = 0; struct codegen_context codegen_ctx, *ctx; u32 *image = (u32 *)rw_image; ppc_inst_t branch_insn; @@ -770,24 +755,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im * Generated stack layout: * * func prev back chain [ back chain ] - * [ ] - * bpf prog redzone/tailcallcnt [ ... ] 64 bytes (64-bit powerpc) - * [ ] -- - * LR save area [ r0 save (64-bit) ] | header - * [ r0 save (32-bit) ] | - * dummy frame for unwind [ back chain 1 ] -- * [ tail_call_info ] optional - 64-bit powerpc * [ padding ] align stack frame * r4_off [ r4 (tailcallcnt) ] optional - 32-bit powerpc * alt_lr_off [ real lr (ool stub)] optional - actual lr + * retaddr_off [ return address ] * [ r26 ] * nvr_off [ r25 ] nvr save area * retval_off [ return value ] * [ reg argN ] * [ ... ] - * regs_off [ reg_arg1 ] prog ctx context - * nregs_off [ args count ] - * ip_off [ traced function ] + * regs_off [ reg_arg1 ] prog_ctx + * nregs_off [ args count ] ((u64 *)prog_ctx)[-1] + * ip_off [ traced function ] ((u64 *)prog_ctx)[-2] * [ ... ] * run_ctx_off [ bpf_tramp_run_ctx ] * [ reg argN ] @@ -843,6 +823,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im nvr_off = bpf_frame_size; bpf_frame_size += 2 * SZL; + /* Save area for return address */ + retaddr_off = bpf_frame_size; + bpf_frame_size += SZL; + /* Optional save area for actual LR in case of ool ftrace */ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { alt_lr_off = bpf_frame_size; @@ -869,16 +853,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im /* Padding to align stack frame, if any */ bpf_frame_size = round_up(bpf_frame_size, SZL * 2); - /* Dummy frame size for proper unwind - includes 64-bytes red zone for 64-bit powerpc */ - bpf_dummy_frame_size = STACK_FRAME_MIN_SIZE + 64; - - /* Offset to the traced function's stack frame */ - func_frame_offset = bpf_dummy_frame_size + bpf_frame_size; - - /* Create dummy frame for unwind, store original return value */ + /* Store original return value */ EMIT(PPC_RAW_STL(_R0, _R1, PPC_LR_STKOFF)); - /* Protect red zone where tail call count goes */ - EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_dummy_frame_size)); /* Create our stack frame */ EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_frame_size)); @@ -893,34 +869,44 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im if (IS_ENABLED(CONFIG_PPC32) && nr_regs < 2) EMIT(PPC_RAW_STL(_R4, _R1, r4_off)); - bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off); + bpf_trampoline_save_args(image, ctx, bpf_frame_size, nr_regs, regs_off); - /* Save our return address */ + /* Save our LR/return address */ EMIT(PPC_RAW_MFLR(_R3)); if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off)); else - EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF)); + EMIT(PPC_RAW_STL(_R3, _R1, retaddr_off)); /* - * Save ip address of the traced function. - * We could recover this from LR, but we will need to address for OOL trampoline, - * and optional GEP area. + * Derive IP address of the traced function. + * In case of CONFIG_PPC_FTRACE_OUT_OF_LINE or BPF program, LR points to the instruction + * after the 'bl' instruction in the OOL stub. Refer to ftrace_init_ool_stub() and + * bpf_arch_text_poke() for OOL stub of kernel functions and bpf programs respectively. + * Relevant stub sequence: + * + * bl <tramp> + * LR (R3) => mtlr r0 + * b <func_addr+4> + * + * Recover kernel function/bpf program address from the unconditional + * branch instruction at the end of OOL stub. */ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) || flags & BPF_TRAMP_F_IP_ARG) { EMIT(PPC_RAW_LWZ(_R4, _R3, 4)); EMIT(PPC_RAW_SLWI(_R4, _R4, 6)); EMIT(PPC_RAW_SRAWI(_R4, _R4, 6)); EMIT(PPC_RAW_ADD(_R3, _R3, _R4)); - EMIT(PPC_RAW_ADDI(_R3, _R3, 4)); } if (flags & BPF_TRAMP_F_IP_ARG) EMIT(PPC_RAW_STL(_R3, _R1, ip_off)); - if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) - /* Fake our LR for unwind */ - EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF)); + if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { + /* Fake our LR for BPF_TRAMP_F_CALL_ORIG case */ + EMIT(PPC_RAW_ADDI(_R3, _R3, 4)); + EMIT(PPC_RAW_STL(_R3, _R1, retaddr_off)); + } /* Save function arg count -- see bpf_get_func_arg_cnt() */ EMIT(PPC_RAW_LI(_R3, nr_regs)); @@ -958,20 +944,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im /* Call the traced function */ if (flags & BPF_TRAMP_F_CALL_ORIG) { /* - * The address in LR save area points to the correct point in the original function + * retaddr on trampoline stack points to the correct point in the original function * with both PPC_FTRACE_OUT_OF_LINE as well as with traditional ftrace instruction * sequence */ - EMIT(PPC_RAW_LL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF)); + EMIT(PPC_RAW_LL(_R3, _R1, retaddr_off)); EMIT(PPC_RAW_MTCTR(_R3)); /* Replicate tail_call_cnt before calling the original BPF prog */ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) - bpf_trampoline_setup_tail_call_info(image, ctx, func_frame_offset, - bpf_dummy_frame_size, r4_off); + bpf_trampoline_setup_tail_call_info(image, ctx, bpf_frame_size, r4_off); /* Restore args */ - bpf_trampoline_restore_args_stack(image, ctx, func_frame_offset, nr_regs, regs_off); + bpf_trampoline_restore_args_stack(image, ctx, bpf_frame_size, nr_regs, regs_off); /* Restore TOC for 64-bit */ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) @@ -985,7 +970,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im /* Restore updated tail_call_cnt */ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) - bpf_trampoline_restore_tail_call_cnt(image, ctx, func_frame_offset, r4_off); + bpf_trampoline_restore_tail_call_cnt(image, ctx, bpf_frame_size, r4_off); /* Reserve space to patch branch instruction to skip fexit progs */ if (ro_image) /* image is NULL for dummy pass */ @@ -1037,7 +1022,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im EMIT(PPC_RAW_LD(_R2, _R1, 24)); if (flags & BPF_TRAMP_F_SKIP_FRAME) { /* Skip the traced function and return to parent */ - EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset)); + EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size)); EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF)); EMIT(PPC_RAW_MTLR(_R0)); EMIT(PPC_RAW_BLR()); @@ -1045,13 +1030,13 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { EMIT(PPC_RAW_LL(_R0, _R1, alt_lr_off)); EMIT(PPC_RAW_MTLR(_R0)); - EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset)); + EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size)); EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF)); EMIT(PPC_RAW_BLR()); } else { - EMIT(PPC_RAW_LL(_R0, _R1, bpf_frame_size + PPC_LR_STKOFF)); + EMIT(PPC_RAW_LL(_R0, _R1, retaddr_off)); EMIT(PPC_RAW_MTCTR(_R0)); - EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset)); + EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size)); EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF)); EMIT(PPC_RAW_MTLR(_R0)); EMIT(PPC_RAW_BCTR()); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index b1a3945ccc9f..c5e26d231cd5 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -32,23 +32,27 @@ * * [ prev sp ] <------------- * [ tail_call_info ] 8 | - * [ nv gpr save area ] 6*8 + (12*8) | + * [ nv gpr save area ] (6 * 8) | + * [ addl. nv gpr save area] (12 * 8) | <--- exception boundary/callback program * [ local_tmp_var ] 24 | * fp (r31) --> [ ebpf stack space ] upto 512 | * [ frame header ] 32/112 | * sp (r1) ---> [ stack pointer ] -------------- * - * Additional (12*8) in 'nv gpr save area' only in case of - * exception boundary. + * Additional (12 * 8) in 'nv gpr save area' only in case of + * exception boundary/callback. */ +/* BPF non-volatile registers save area size */ +#define BPF_PPC_STACK_SAVE (6 * 8) + /* for bpf JIT code internal usage */ #define BPF_PPC_STACK_LOCALS 24 /* * for additional non volatile registers(r14-r25) to be saved * at exception boundary */ -#define BPF_PPC_EXC_STACK_SAVE (12*8) +#define BPF_PPC_EXC_STACK_SAVE (12 * 8) /* stack frame excluding BPF stack, ensure this is quadword aligned */ #define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \ @@ -125,12 +129,13 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) * [ ... ] | * sp (r1) ---> [ stack pointer ] -------------- * [ tail_call_info ] 8 - * [ nv gpr save area ] 6*8 + (12*8) + * [ nv gpr save area ] (6 * 8) + * [ addl. nv gpr save area] (12 * 8) <--- exception boundary/callback program * [ local_tmp_var ] 24 * [ unused red zone ] 224 * - * Additional (12*8) in 'nv gpr save area' only in case of - * exception boundary. + * Additional (12 * 8) in 'nv gpr save area' only in case of + * exception boundary/callback. */ static int bpf_jit_stack_local(struct codegen_context *ctx) { @@ -148,7 +153,7 @@ static int bpf_jit_stack_local(struct codegen_context *ctx) } } -int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx) +static int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx) { return bpf_jit_stack_local(ctx) + BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE; } @@ -237,10 +242,6 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) if (bpf_has_stack_frame(ctx) && !ctx->exception_cb) { /* - * exception_cb uses boundary frame after stack walk. - * It can simply use redzone, this optimization reduces - * stack walk loop by one level. - * * We need a stack frame, but we don't necessarily need to * save/restore LR unless we call other functions */ @@ -284,6 +285,22 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) * program(main prog) as third arg */ EMIT(PPC_RAW_MR(_R1, _R5)); + /* + * Exception callback reuses the stack frame of exception boundary. + * But BPF stack depth of exception callback and exception boundary + * don't have to be same. If BPF stack depth is different, adjust the + * stack frame size considering BPF stack depth of exception callback. + * The non-volatile register save area remains unchanged. These non- + * volatile registers are restored in exception callback's epilogue. + */ + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R5, 0)); + EMIT(PPC_RAW_SUB(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_1), _R1)); + EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), + -BPF_PPC_EXC_STACKFRAME)); + EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), ctx->stack_size)); + PPC_BCC_CONST_SHORT(COND_EQ, 12); + EMIT(PPC_RAW_MR(_R1, bpf_to_ppc(TMP_REG_1))); + EMIT(PPC_RAW_STDU(_R1, _R1, -(BPF_PPC_EXC_STACKFRAME + ctx->stack_size))); } /* @@ -482,6 +499,83 @@ int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context * return 0; } +static int zero_extend(u32 *image, struct codegen_context *ctx, u32 src_reg, u32 dst_reg, u32 size) +{ + switch (size) { + case 1: + /* zero-extend 8 bits into 64 bits */ + EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 56)); + return 0; + case 2: + /* zero-extend 16 bits into 64 bits */ + EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 48)); + return 0; + case 4: + /* zero-extend 32 bits into 64 bits */ + EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 32)); + fallthrough; + case 8: + /* Nothing to do */ + return 0; + default: + return -1; + } +} + +static int sign_extend(u32 *image, struct codegen_context *ctx, u32 src_reg, u32 dst_reg, u32 size) +{ + switch (size) { + case 1: + /* sign-extend 8 bits into 64 bits */ + EMIT(PPC_RAW_EXTSB(dst_reg, src_reg)); + return 0; + case 2: + /* sign-extend 16 bits into 64 bits */ + EMIT(PPC_RAW_EXTSH(dst_reg, src_reg)); + return 0; + case 4: + /* sign-extend 32 bits into 64 bits */ + EMIT(PPC_RAW_EXTSW(dst_reg, src_reg)); + fallthrough; + case 8: + /* Nothing to do */ + return 0; + default: + return -1; + } +} + +/* + * Handle powerpc ABI expectations from caller: + * - Unsigned arguments are zero-extended. + * - Signed arguments are sign-extended. + */ +static int prepare_for_kfunc_call(const struct bpf_prog *fp, u32 *image, + struct codegen_context *ctx, + const struct bpf_insn *insn) +{ + const struct btf_func_model *m = bpf_jit_find_kfunc_model(fp, insn); + int i; + + if (!m) + return -1; + + for (i = 0; i < m->nr_args; i++) { + /* Note that BPF ABI only allows up to 5 args for kfuncs */ + u32 reg = bpf_to_ppc(BPF_REG_1 + i), size = m->arg_size[i]; + + if (!(m->arg_flags[i] & BTF_FMODEL_SIGNED_ARG)) { + if (zero_extend(image, ctx, reg, reg, size)) + return -1; + } else { + if (sign_extend(image, ctx, reg, reg, size)) + return -1; + } + } + + return 0; +} + static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) { /* @@ -522,9 +616,30 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o /* * tail_call_info++; <- Actual value of tcc here + * Writeback this updated value only if tailcall succeeds. */ EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), 1)); + /* prog = array->ptrs[index]; */ + EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_2), b2p_index, 8)); + EMIT(PPC_RAW_ADD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), b2p_bpf_array)); + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), + offsetof(struct bpf_array, ptrs))); + + /* + * if (prog == NULL) + * goto out; + */ + EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), 0)); + PPC_BCC_SHORT(COND_EQ, out); + + /* goto *(prog->bpf_func + prologue_size); */ + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), + offsetof(struct bpf_prog, bpf_func))); + EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), + FUNCTION_DESCR_SIZE + bpf_tailcall_prologue_size)); + EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_2))); + /* * Before writing updated tail_call_info, distinguish if current frame * is storing a reference to tail_call_info or actual tcc value in @@ -539,24 +654,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o /* Writeback updated value to tail_call_info */ EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), 0)); - /* prog = array->ptrs[index]; */ - EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_1), b2p_index, 8)); - EMIT(PPC_RAW_ADD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), b2p_bpf_array)); - EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_array, ptrs))); - - /* - * if (prog == NULL) - * goto out; - */ - EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), 0)); - PPC_BCC_SHORT(COND_EQ, out); - - /* goto *(prog->bpf_func + prologue_size); */ - EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_prog, bpf_func))); - EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), - FUNCTION_DESCR_SIZE + bpf_tailcall_prologue_size)); - EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_1))); - /* tear down stack, restore NVRs, ... */ bpf_jit_emit_common_epilogue(image, ctx); @@ -1123,14 +1220,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code /* special mov32 for zext */ EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31)); break; - } else if (off == 8) { - EMIT(PPC_RAW_EXTSB(dst_reg, src_reg)); - } else if (off == 16) { - EMIT(PPC_RAW_EXTSH(dst_reg, src_reg)); - } else if (off == 32) { - EMIT(PPC_RAW_EXTSW(dst_reg, src_reg)); - } else if (dst_reg != src_reg) - EMIT(PPC_RAW_MR(dst_reg, src_reg)); + } + if (off == 0) { + /* MOV */ + if (dst_reg != src_reg) + EMIT(PPC_RAW_MR(dst_reg, src_reg)); + } else { + /* MOVSX: dst = (s8,s16,s32)src (off = 8,16,32) */ + if (sign_extend(image, ctx, src_reg, dst_reg, off / 8)) + return -1; + } goto bpf_alu32_trunc; case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */ case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */ @@ -1598,6 +1697,12 @@ emit_clear: if (ret < 0) return ret; + /* Take care of powerpc ABI requirements before kfunc call */ + if (insn[i].src_reg == BPF_PSEUDO_KFUNC_CALL) { + if (prepare_for_kfunc_call(fp, image, ctx, &insn[i])) + return -1; + } + ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr); if (ret) return ret; diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 26aa26482c9a..992cc5c98214 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -103,6 +103,11 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + perf_callchain_store(entry, perf_arch_instruction_pointer(regs)); + + if (!current->mm) + return; + if (!is_32bit_task()) perf_callchain_user_64(entry, regs); else diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c index ddcc2d8aa64a..0de21c5d272c 100644 --- a/arch/powerpc/perf/callchain_32.c +++ b/arch/powerpc/perf/callchain_32.c @@ -142,7 +142,6 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry, next_ip = perf_arch_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; - perf_callchain_store(entry, next_ip); while (entry->nr < entry->max_stack) { fp = (unsigned int __user *) (unsigned long) sp; diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c index 115d1c105e8a..30fb61c5f0cb 100644 --- a/arch/powerpc/perf/callchain_64.c +++ b/arch/powerpc/perf/callchain_64.c @@ -77,7 +77,6 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry, next_ip = perf_arch_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; - perf_callchain_store(entry, next_ip); while (entry->nr < entry->max_stack) { fp = (unsigned long __user *) sp; diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c index 2b5d187d9b62..9ef8fb39dd1b 100644 --- a/arch/powerpc/platforms/83xx/km83xx.c +++ b/arch/powerpc/platforms/83xx/km83xx.c @@ -155,8 +155,8 @@ machine_device_initcall(mpc83xx_km, mpc83xx_declare_of_platform_devices); /* list of the supported boards */ static char *board[] __initdata = { - "Keymile,KMETER1", - "Keymile,kmpbec8321", + "keymile,KMETER1", + "keymile,kmpbec8321", NULL }; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index f399917c17bd..bac02c83bb3e 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -276,7 +276,7 @@ config PPC_BOOK3S config PPC_E500 select FSL_EMB_PERFMON bool - select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64 + select ARCH_SUPPORTS_HUGETLBFS select PPC_SMP_MUXED_IPI select PPC_DOORBELL select PPC_KUEP @@ -337,7 +337,7 @@ config BOOKE config PTE_64BIT bool depends on 44x || PPC_E500 || PPC_86xx - default y if PHYS_64BIT + default y if PPC_E500 || PHYS_64BIT config PHYS_64BIT bool 'Large physical address support' if PPC_E500 || PPC_86xx diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 64ffc6476ad6..8285b9a29fbf 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -605,7 +605,7 @@ static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq &pseries_msi_irq_chip, pseries_dev); } - pseries_dev->msi_used++; + pseries_dev->msi_used += nr_irqs; return 0; out: diff --git a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh b/arch/powerpc/tools/check-fpatchable-function-entry.sh index baed467a016b..baed467a016b 100755 --- a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh +++ b/arch/powerpc/tools/check-fpatchable-function-entry.sh diff --git a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh index bac186bdf64a..9218d43aeb54 100755 --- a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh +++ b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh @@ -15,9 +15,9 @@ if [ -z "$is_64bit" ]; then RELOCATION=R_PPC_ADDR32 fi -num_ool_stubs_total=$($objdump -r -j __patchable_function_entries "$vmlinux_o" | +num_ool_stubs_total=$($objdump -r -j __patchable_function_entries -d "$vmlinux_o" | grep -c "$RELOCATION") -num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries "$vmlinux_o" | +num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries -d "$vmlinux_o" | grep -e ".init.text" -e ".text.startup" | grep -c "$RELOCATION") num_ool_stubs_text=$((num_ool_stubs_total - num_ool_stubs_inittext)) diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 5c2963e269b8..a0ffedc2d344 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -428,6 +428,7 @@ clocks = <&clkcfg CLK_CAN0>, <&clkcfg CLK_MSSPLL3>; interrupt-parent = <&plic>; interrupts = <56>; + resets = <&mss_top_sysreg CLK_CAN0>; status = "disabled"; }; @@ -437,6 +438,7 @@ clocks = <&clkcfg CLK_CAN1>, <&clkcfg CLK_MSSPLL3>; interrupt-parent = <&plic>; interrupts = <57>; + resets = <&mss_top_sysreg CLK_CAN1>; status = "disabled"; }; diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 61bd5ba6680a..997f9eb3b22b 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -170,6 +170,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS .riscv.attributes 0 : { *(.riscv.attributes) } diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index 77379f77840a..ec2cee0a39e0 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -30,7 +30,6 @@ config KVM select KVM_GENERIC_HARDWARE_ENABLING select KVM_MMIO select VIRT_XFER_TO_GUEST_WORK - select KVM_GENERIC_MMU_NOTIFIER select SCHED_INFO select GUEST_PERF_EVENTS if PERF_EVENTS help diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index cac3c2b51d72..5ec503288555 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -13,6 +13,7 @@ #include <linux/irqchip/riscv-imsic.h> #include <linux/irqdomain.h> #include <linux/kvm_host.h> +#include <linux/nospec.h> #include <linux/percpu.h> #include <linux/spinlock.h> #include <asm/cpufeature.h> @@ -182,9 +183,14 @@ int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, unsigned long *out_val) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long)) + if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); *out_val = 0; if (kvm_riscv_aia_available()) @@ -198,9 +204,14 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, unsigned long val) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long)) + if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); if (kvm_riscv_aia_available()) { ((unsigned long *)csr)[reg_num] = val; diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c index d1e50bf5c351..3464f3351df7 100644 --- a/arch/riscv/kvm/aia_aplic.c +++ b/arch/riscv/kvm/aia_aplic.c @@ -10,6 +10,7 @@ #include <linux/irqchip/riscv-aplic.h> #include <linux/kvm_host.h> #include <linux/math.h> +#include <linux/nospec.h> #include <linux/spinlock.h> #include <linux/swab.h> #include <kvm/iodev.h> @@ -45,7 +46,7 @@ static u32 aplic_read_sourcecfg(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return 0; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = irqd->sourcecfg; @@ -61,7 +62,7 @@ static void aplic_write_sourcecfg(struct aplic *aplic, u32 irq, u32 val) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; if (val & APLIC_SOURCECFG_D) val = 0; @@ -81,7 +82,7 @@ static u32 aplic_read_target(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return 0; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = irqd->target; @@ -97,7 +98,7 @@ static void aplic_write_target(struct aplic *aplic, u32 irq, u32 val) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; val &= APLIC_TARGET_EIID_MASK | (APLIC_TARGET_HART_IDX_MASK << APLIC_TARGET_HART_IDX_SHIFT) | @@ -116,7 +117,7 @@ static bool aplic_read_pending(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return false; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = (irqd->state & APLIC_IRQ_STATE_PENDING) ? true : false; @@ -132,7 +133,7 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); @@ -170,7 +171,7 @@ static bool aplic_read_enabled(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return false; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = (irqd->state & APLIC_IRQ_STATE_ENABLED) ? true : false; @@ -186,7 +187,7 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); if (enabled) @@ -205,7 +206,7 @@ static bool aplic_read_input(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return false; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); @@ -254,7 +255,7 @@ static void aplic_update_irq_range(struct kvm *kvm, u32 first, u32 last) for (irq = first; irq <= last; irq++) { if (!irq || aplic->nr_irqs <= irq) continue; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); @@ -283,7 +284,7 @@ int kvm_riscv_aia_aplic_inject(struct kvm *kvm, u32 source, bool level) if (!aplic || !source || (aplic->nr_irqs <= source)) return -ENODEV; - irqd = &aplic->irqs[source]; + irqd = &aplic->irqs[array_index_nospec(source, aplic->nr_irqs)]; ie = (aplic->domaincfg & APLIC_DOMAINCFG_IE) ? true : false; raw_spin_lock_irqsave(&irqd->lock, flags); diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index b195a93add1c..49c71d3cdb00 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -11,6 +11,7 @@ #include <linux/irqchip/riscv-imsic.h> #include <linux/kvm_host.h> #include <linux/uaccess.h> +#include <linux/cpufeature.h> static int aia_create(struct kvm_device *dev, u32 type) { @@ -22,6 +23,9 @@ static int aia_create(struct kvm_device *dev, u32 type) if (irqchip_in_kernel(kvm)) return -EEXIST; + if (!riscv_isa_extension_available(NULL, SSAIA)) + return -ENODEV; + ret = -EBUSY; if (kvm_trylock_all_vcpus(kvm)) return ret; @@ -437,7 +441,7 @@ static int aia_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { - int nr_vcpus; + int nr_vcpus, r = -ENXIO; switch (attr->group) { case KVM_DEV_RISCV_AIA_GRP_CONFIG: @@ -466,12 +470,18 @@ static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) } break; case KVM_DEV_RISCV_AIA_GRP_APLIC: - return kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr); + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr); + mutex_unlock(&dev->kvm->lock); + break; case KVM_DEV_RISCV_AIA_GRP_IMSIC: - return kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr); + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr); + mutex_unlock(&dev->kvm->lock); + break; } - return -ENXIO; + return r; } struct kvm_device_ops kvm_riscv_aia_device_ops = { diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index 06752fa24798..8786f52cf65a 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -908,6 +908,10 @@ int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu, unsigned long isel, int r, rc = KVM_INSN_CONTINUE_NEXT_SEPC; struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + /* If IMSIC vCPU state not initialized then forward to user space */ + if (!imsic) + return KVM_INSN_EXIT_TO_USER_SPACE; + if (isel == KVM_RISCV_AIA_IMSIC_TOPEI) { /* Read pending and enabled interrupt with highest priority */ topei = imsic_mrif_topei(imsic->swfile, imsic->nr_eix, diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 0b75eb2a1820..088d33ba90ed 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -245,6 +245,7 @@ out: bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { struct kvm_gstage gstage; + bool mmu_locked; if (!kvm->arch.pgd) return false; @@ -253,9 +254,12 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) gstage.flags = 0; gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); gstage.pgd = kvm->arch.pgd; + mmu_locked = spin_trylock(&kvm->mmu_lock); kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); + if (mmu_locked) + spin_unlock(&kvm->mmu_lock); return false; } @@ -535,7 +539,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, goto out_unlock; /* Check if we are backed by a THP and thus use block mapping if possible */ - if (vma_pagesize == PAGE_SIZE) + if (!logging && (vma_pagesize == PAGE_SIZE)) vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &hfn, &gpa); if (writable) { diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index a55a95da54d0..fdd99ac1e714 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -24,7 +24,7 @@ #define CREATE_TRACE_POINTS #include "trace.h" -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, ecall_exit_stat), STATS_DESC_COUNTER(VCPU, wfi_exit_stat), diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c index 030904d82b58..bd5a9e7e7165 100644 --- a/arch/riscv/kvm/vcpu_fp.c +++ b/arch/riscv/kvm/vcpu_fp.c @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/cpufeature.h> @@ -93,9 +94,11 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) reg_val = &cntx->fp.f.fcsr; else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && - reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) + reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.f.f)); reg_val = &cntx->fp.f.f[reg_num]; - else + } else return -ENOENT; } else if ((rtype == KVM_REG_RISCV_FP_D) && riscv_isa_extension_available(vcpu->arch.isa, d)) { @@ -107,6 +110,8 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) { if (KVM_REG_SIZE(reg->id) != sizeof(u64)) return -EINVAL; + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.d.f)); reg_val = &cntx->fp.d.f[reg_num]; } else return -ENOENT; @@ -138,9 +143,11 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) reg_val = &cntx->fp.f.fcsr; else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && - reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) + reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.f.f)); reg_val = &cntx->fp.f.f[reg_num]; - else + } else return -ENOENT; } else if ((rtype == KVM_REG_RISCV_FP_D) && riscv_isa_extension_available(vcpu->arch.isa, d)) { @@ -152,6 +159,8 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) { if (KVM_REG_SIZE(reg->id) != sizeof(u64)) return -EINVAL; + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.d.f)); reg_val = &cntx->fp.d.f[reg_num]; } else return -ENOENT; diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index e7ab6cb00646..45ecc0082e90 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -10,6 +10,7 @@ #include <linux/bitops.h> #include <linux/errno.h> #include <linux/err.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <linux/kvm_host.h> #include <asm/cacheflush.h> @@ -127,6 +128,7 @@ static int kvm_riscv_vcpu_isa_check_host(unsigned long kvm_ext, unsigned long *g kvm_ext >= ARRAY_SIZE(kvm_isa_ext_arr)) return -ENOENT; + kvm_ext = array_index_nospec(kvm_ext, ARRAY_SIZE(kvm_isa_ext_arr)); *guest_ext = kvm_isa_ext_arr[kvm_ext]; switch (*guest_ext) { case RISCV_ISA_EXT_SMNPM: @@ -443,13 +445,16 @@ static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu, unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_RISCV_CORE); + unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long); unsigned long reg_val; if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) return -EINVAL; - if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc)) reg_val = cntx->sepc; else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num && @@ -476,13 +481,16 @@ static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu, unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_RISCV_CORE); + unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long); unsigned long reg_val; if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) return -EINVAL; - if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) return -EFAULT; @@ -507,10 +515,13 @@ static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu, unsigned long *out_val) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { kvm_riscv_vcpu_flush_interrupts(vcpu); *out_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK; @@ -526,10 +537,13 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, unsigned long reg_val) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { reg_val &= VSIP_VALID_MASK; reg_val <<= VSIP_TO_HVIP_SHIFT; @@ -548,10 +562,15 @@ static inline int kvm_riscv_vcpu_smstateen_set_csr(struct kvm_vcpu *vcpu, unsigned long reg_val) { struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / + sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) / - sizeof(unsigned long)) - return -EINVAL; + if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); ((unsigned long *)csr)[reg_num] = reg_val; return 0; @@ -562,10 +581,15 @@ static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu, unsigned long *out_val) { struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / + sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) / - sizeof(unsigned long)) - return -EINVAL; + if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); *out_val = ((unsigned long *)csr)[reg_num]; return 0; @@ -595,10 +619,7 @@ static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu, rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, ®_val); break; case KVM_REG_RISCV_CSR_SMSTATEEN: - rc = -EINVAL; - if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) - rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, - ®_val); + rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, ®_val); break; default: rc = -ENOENT; @@ -640,10 +661,7 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu, rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val); break; case KVM_REG_RISCV_CSR_SMSTATEEN: - rc = -EINVAL; - if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) - rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, - reg_val); + rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, reg_val); break; default: rc = -ENOENT; diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index 4d8d5e9aa53d..e873430e596b 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> +#include <linux/nospec.h> #include <linux/perf/riscv_pmu.h> #include <asm/csr.h> #include <asm/kvm_vcpu_sbi.h> @@ -87,7 +88,8 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) static u64 kvm_pmu_get_perf_event_hw_config(u32 sbi_event_code) { - return hw_event_perf_map[sbi_event_code]; + return hw_event_perf_map[array_index_nospec(sbi_event_code, + SBI_PMU_HW_GENERAL_MAX)]; } static u64 kvm_pmu_get_perf_event_cache_config(u32 sbi_event_code) @@ -218,6 +220,7 @@ static int pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx, return -EINVAL; } + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); pmc = &kvpmu->pmc[cidx]; if (pmc->cinfo.type != SBI_PMU_CTR_TYPE_FW) @@ -244,6 +247,7 @@ static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, return -EINVAL; } + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); pmc = &kvpmu->pmc[cidx]; if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { @@ -520,11 +524,12 @@ int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, { struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); - if (cidx > RISCV_KVM_MAX_COUNTERS || cidx == 1) { + if (cidx >= RISCV_KVM_MAX_COUNTERS || cidx == 1) { retdata->err_val = SBI_ERR_INVALID_PARAM; return 0; } + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); retdata->out_val = kvpmu->pmc[cidx].cinfo.value; return 0; @@ -559,7 +564,8 @@ int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, } /* Start the counters that have been configured and requested by the guest */ for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { - pmc_index = i + ctr_base; + pmc_index = array_index_nospec(i + ctr_base, + RISCV_KVM_MAX_COUNTERS); if (!test_bit(pmc_index, kvpmu->pmc_in_use)) continue; /* The guest started the counter again. Reset the overflow status */ @@ -630,7 +636,8 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, /* Stop the counters that have been configured and requested by the guest */ for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { - pmc_index = i + ctr_base; + pmc_index = array_index_nospec(i + ctr_base, + RISCV_KVM_MAX_COUNTERS); if (!test_bit(pmc_index, kvpmu->pmc_in_use)) continue; pmc = &kvpmu->pmc[pmc_index]; @@ -761,6 +768,7 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba } } + ctr_idx = array_index_nospec(ctr_idx, RISCV_KVM_MAX_COUNTERS); pmc = &kvpmu->pmc[ctr_idx]; pmc->idx = ctr_idx; diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 7cbd2340c190..13c63ae1a78b 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -13,7 +13,7 @@ #include <linux/kvm_host.h> #include <asm/kvm_mmu.h> -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == @@ -181,7 +181,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_IOEVENTFD: case KVM_CAP_USER_MEMORY: - case KVM_CAP_SYNC_MMU: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_ONE_REG: case KVM_CAP_READONLY_MEM: diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h index 09f763b9eb40..32536ee34aa0 100644 --- a/arch/s390/include/asm/idle.h +++ b/arch/s390/include/asm/idle.h @@ -19,9 +19,9 @@ struct s390_idle_data { unsigned long mt_cycles_enter[8]; }; +DECLARE_PER_CPU(struct s390_idle_data, s390_idle); + extern struct device_attribute dev_attr_idle_count; extern struct device_attribute dev_attr_idle_time_us; -void psw_idle(struct s390_idle_data *data, unsigned long psw_mask); - #endif /* _S390_IDLE_H */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index cc187afa07b3..78195ee5e99f 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -159,7 +159,7 @@ static __always_inline void __stackleak_poison(unsigned long erase_low, " j 4f\n" "3: mvc 8(1,%[addr]),0(%[addr])\n" "4:" - : [addr] "+&a" (erase_low), [count] "+&d" (count), [tmp] "=&a" (tmp) + : [addr] "+&a" (erase_low), [count] "+&a" (count), [tmp] "=&a" (tmp) : [poison] "d" (poison) : "memory", "cc" ); diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h index 9d25fb35a042..b1db75d14e9d 100644 --- a/arch/s390/include/asm/vtime.h +++ b/arch/s390/include/asm/vtime.h @@ -2,6 +2,12 @@ #ifndef _S390_VTIME_H #define _S390_VTIME_H +#include <asm/lowcore.h> +#include <asm/cpu_mf.h> +#include <asm/idle.h> + +DECLARE_PER_CPU(u64, mt_cycles[8]); + static inline void update_timer_sys(void) { struct lowcore *lc = get_lowcore(); @@ -20,4 +26,32 @@ static inline void update_timer_mcck(void) lc->last_update_timer = lc->mcck_enter_timer; } +static inline void update_timer_idle(void) +{ + struct s390_idle_data *idle = this_cpu_ptr(&s390_idle); + struct lowcore *lc = get_lowcore(); + u64 cycles_new[8]; + int i, mtid; + + mtid = smp_cpu_mtid; + if (mtid) { + stcctm(MT_DIAG, mtid, cycles_new); + for (i = 0; i < mtid; i++) + __this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]); + } + /* + * This is a bit subtle: Forward last_update_clock so it excludes idle + * time. For correct steal time calculation in do_account_vtime() add + * passed wall time before idle_enter to steal_timer: + * During the passed wall time before idle_enter CPU time may have + * been accounted to system, hardirq, softirq, etc. lowcore fields. + * The accounted CPU times will be subtracted again from steal_timer + * when accumulated steal time is calculated in do_account_vtime(). + */ + lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock; + lc->last_update_clock = lc->int_clock; + lc->system_timer += lc->last_update_timer - idle->timer_idle_enter; + lc->last_update_timer = lc->sys_enter_timer; +} + #endif /* _S390_VTIME_H */ diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index dd55cc6bbc28..fb67b4abe68c 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -56,8 +56,6 @@ long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t); long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t); long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user *return_code, unsigned long flags); -DECLARE_PER_CPU(u64, mt_cycles[8]); - unsigned long stack_alloc(void); void stack_free(unsigned long stack); diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 39cb8d0ae348..1f1b06b6b4ef 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -15,37 +15,22 @@ #include <trace/events/power.h> #include <asm/cpu_mf.h> #include <asm/cputime.h> +#include <asm/idle.h> #include <asm/nmi.h> #include <asm/smp.h> -#include "entry.h" -static DEFINE_PER_CPU(struct s390_idle_data, s390_idle); +DEFINE_PER_CPU(struct s390_idle_data, s390_idle); void account_idle_time_irq(void) { struct s390_idle_data *idle = this_cpu_ptr(&s390_idle); - struct lowcore *lc = get_lowcore(); unsigned long idle_time; - u64 cycles_new[8]; - int i; - if (smp_cpu_mtid) { - stcctm(MT_DIAG, smp_cpu_mtid, cycles_new); - for (i = 0; i < smp_cpu_mtid; i++) - this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]); - } - - idle_time = lc->int_clock - idle->clock_idle_enter; - - lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock; - lc->last_update_clock = lc->int_clock; - - lc->system_timer += lc->last_update_timer - idle->timer_idle_enter; - lc->last_update_timer = lc->sys_enter_timer; + idle_time = get_lowcore()->int_clock - idle->clock_idle_enter; /* Account time spent with enabled wait psw loaded as idle time. */ - WRITE_ONCE(idle->idle_time, READ_ONCE(idle->idle_time) + idle_time); - WRITE_ONCE(idle->idle_count, READ_ONCE(idle->idle_count) + 1); + __atomic64_add(idle_time, &idle->idle_time); + __atomic64_add_const(1, &idle->idle_count); account_idle_time(cputime_to_nsecs(idle_time)); } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index dcdc7e274848..049c557c452f 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2377,7 +2377,7 @@ void __init setup_ipl(void) atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb); } -void s390_reset_system(void) +void __no_stack_protector s390_reset_system(void) { /* Disable prefixing */ set_prefix(0); diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index f81723bc8856..d10a17e6531d 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -146,6 +146,10 @@ void noinstr do_io_irq(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); bool from_idle; + from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); + if (from_idle) + update_timer_idle(); + irq_enter_rcu(); if (user_mode(regs)) { @@ -154,7 +158,6 @@ void noinstr do_io_irq(struct pt_regs *regs) current->thread.last_break = regs->last_break; } - from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); if (from_idle) account_idle_time_irq(); @@ -182,6 +185,10 @@ void noinstr do_ext_irq(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); bool from_idle; + from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); + if (from_idle) + update_timer_idle(); + irq_enter_rcu(); if (user_mode(regs)) { @@ -194,7 +201,6 @@ void noinstr do_ext_irq(struct pt_regs *regs) regs->int_parm = get_lowcore()->ext_params; regs->int_parm_long = get_lowcore()->ext_params2; - from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); if (from_idle) account_idle_time_irq(); diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 53bcbb91bb9b..2b62395e35bf 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -221,6 +221,7 @@ SECTIONS /* Debugging sections. */ STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS /* diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 234a0ba30510..bf48744d0912 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -48,8 +48,7 @@ static inline void set_vtimer(u64 expires) static inline int virt_timer_forward(u64 elapsed) { - BUG_ON(!irqs_disabled()); - + lockdep_assert_irqs_disabled(); if (list_empty(&virt_timer_list)) return 0; elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed); @@ -137,23 +136,16 @@ static int do_account_vtime(struct task_struct *tsk) lc->system_timer += timer; /* Update MT utilization calculation */ - if (smp_cpu_mtid && - time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) + if (smp_cpu_mtid && time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) update_mt_scaling(); /* Calculate cputime delta */ - user = update_tsk_timer(&tsk->thread.user_timer, - READ_ONCE(lc->user_timer)); - guest = update_tsk_timer(&tsk->thread.guest_timer, - READ_ONCE(lc->guest_timer)); - system = update_tsk_timer(&tsk->thread.system_timer, - READ_ONCE(lc->system_timer)); - hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, - READ_ONCE(lc->hardirq_timer)); - softirq = update_tsk_timer(&tsk->thread.softirq_timer, - READ_ONCE(lc->softirq_timer)); - lc->steal_timer += - clock - user - guest - system - hardirq - softirq; + user = update_tsk_timer(&tsk->thread.user_timer, lc->user_timer); + guest = update_tsk_timer(&tsk->thread.guest_timer, lc->guest_timer); + system = update_tsk_timer(&tsk->thread.system_timer, lc->system_timer); + hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, lc->hardirq_timer); + softirq = update_tsk_timer(&tsk->thread.softirq_timer, lc->softirq_timer); + lc->steal_timer += clock - user - guest - system - hardirq - softirq; /* Push account value */ if (user) { @@ -225,10 +217,6 @@ static u64 vtime_delta(void) return timer - lc->last_update_timer; } -/* - * Update process times based on virtual cpu times stored by entry.S - * to the lowcore fields user_timer, system_timer & steal_clock. - */ void vtime_account_kernel(struct task_struct *tsk) { struct lowcore *lc = get_lowcore(); @@ -238,27 +226,17 @@ void vtime_account_kernel(struct task_struct *tsk) lc->guest_timer += delta; else lc->system_timer += delta; - - virt_timer_forward(delta); } EXPORT_SYMBOL_GPL(vtime_account_kernel); void vtime_account_softirq(struct task_struct *tsk) { - u64 delta = vtime_delta(); - - get_lowcore()->softirq_timer += delta; - - virt_timer_forward(delta); + get_lowcore()->softirq_timer += vtime_delta(); } void vtime_account_hardirq(struct task_struct *tsk) { - u64 delta = vtime_delta(); - - get_lowcore()->hardirq_timer += delta; - - virt_timer_forward(delta); + get_lowcore()->hardirq_timer += vtime_delta(); } /* diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 917ac740513e..5b835bc6a194 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -28,9 +28,7 @@ config KVM select HAVE_KVM_INVALID_WAKEUPS select HAVE_KVM_NO_POLL select KVM_VFIO - select MMU_NOTIFIER select VIRT_XFER_TO_GUEST_WORK - select KVM_GENERIC_MMU_NOTIFIER select KVM_MMU_LOCKLESS_AGING help Support hosting paravirtualized guest machines using the SIE diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 7a175d86cef0..3eb60aa932ec 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -65,7 +65,7 @@ #define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \ (KVM_MAX_VCPUS + LOCAL_IRQS)) -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, inject_io), STATS_DESC_COUNTER(VM, inject_float_mchk), @@ -91,7 +91,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, exit_userspace), STATS_DESC_COUNTER(VCPU, exit_null), @@ -601,7 +601,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) switch (ext) { case KVM_CAP_S390_PSW: case KVM_CAP_S390_GMAP: - case KVM_CAP_SYNC_MMU: #ifdef CONFIG_KVM_S390_UCONTROL case KVM_CAP_S390_UCONTROL: #endif diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c index 1721b73b7803..5363e4c2462d 100644 --- a/arch/s390/lib/xor.c +++ b/arch/s390/lib/xor.c @@ -28,8 +28,8 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1, " j 3f\n" "2: xc 0(1,%1),0(%2)\n" "3:" - : : "d" (bytes), "a" (p1), "a" (p2) - : "0", "cc", "memory"); + : "+a" (bytes), "+a" (p1), "+a" (p2) + : : "0", "cc", "memory"); } static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, @@ -54,7 +54,7 @@ static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, "2: xc 0(1,%1),0(%2)\n" "3: xc 0(1,%1),0(%3)\n" "4:" - : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3) + : "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3) : : "0", "cc", "memory"); } @@ -85,7 +85,7 @@ static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1, "3: xc 0(1,%1),0(%3)\n" "4: xc 0(1,%1),0(%4)\n" "5:" - : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4) + : "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4) : : "0", "cc", "memory"); } @@ -96,7 +96,6 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p5) { asm volatile( - " larl 1,2f\n" " aghi %0,-1\n" " jm 6f\n" " srlg 0,%0,8\n" @@ -122,7 +121,7 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, "4: xc 0(1,%1),0(%4)\n" "5: xc 0(1,%1),0(%5)\n" "6:" - : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4), + : "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4), "+a" (p5) : : "0", "cc", "memory"); } diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c index 2f829448c719..6ecd6b0a22a8 100644 --- a/arch/s390/mm/pfault.c +++ b/arch/s390/mm/pfault.c @@ -62,7 +62,7 @@ int __pfault_init(void) "0: nopr %%r7\n" EX_TABLE(0b, 0b) : [rc] "+d" (rc) - : [refbk] "a" (&pfault_init_refbk), "m" (pfault_init_refbk) + : [refbk] "a" (virt_to_phys(&pfault_init_refbk)), "m" (pfault_init_refbk) : "cc"); return rc; } @@ -84,7 +84,7 @@ void __pfault_fini(void) "0: nopr %%r7\n" EX_TABLE(0b, 0b) : - : [refbk] "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk) + : [refbk] "a" (virt_to_phys(&pfault_fini_refbk)), "m" (pfault_fini_refbk) : "cc"); } diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 008c30289eaa..169c63fb3c1d 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -89,6 +89,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 46ef88bc9c26..7613ab0ffb89 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -312,6 +312,8 @@ static dma_addr_t dma_4u_map_phys(struct device *dev, phys_addr_t phys, if (direction != DMA_TO_DEVICE) iopte_protection |= IOPTE_WRITE; + phys &= IO_PAGE_MASK; + for (i = 0; i < npages; i++, base++, phys += IO_PAGE_SIZE) iopte_val(*base) = iopte_protection | phys; diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 7e41574634b3..1603d50fdcad 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -355,6 +355,13 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, dev->error_state = pci_channel_io_normal; dev->dma_mask = 0xffffffff; + /* + * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit + * if MSI (rather than MSI-X) capability does not have + * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver. + */ + dev->msi_addr_mask = DMA_BIT_MASK(64); + if (of_node_name_eq(node, "pci")) { /* a PCI-PCI bridge */ dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 440284cc804e..61f14b4c8f90 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -410,6 +410,8 @@ static dma_addr_t dma_4v_map_phys(struct device *dev, phys_addr_t phys, iommu_batch_start(dev, prot, entry); + phys &= IO_PAGE_MASK; + for (i = 0; i < npages; i++, phys += IO_PAGE_SIZE) { long err = iommu_batch_add(phys, mask); if (unlikely(err < 0L)) diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index f1b86eb30340..7ea510d9b42f 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -191,6 +191,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 012b2bcaa8a0..20fc33300a95 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -69,11 +69,11 @@ struct io_thread_req { }; -static struct io_thread_req * (*irq_req_buffer)[]; +static struct io_thread_req **irq_req_buffer; static struct io_thread_req *irq_remainder; static int irq_remainder_size; -static struct io_thread_req * (*io_req_buffer)[]; +static struct io_thread_req **io_req_buffer; static struct io_thread_req *io_remainder; static int io_remainder_size; @@ -398,7 +398,7 @@ static int thread_fd = -1; static int bulk_req_safe_read( int fd, - struct io_thread_req * (*request_buffer)[], + struct io_thread_req **request_buffer, struct io_thread_req **remainder, int *remainder_size, int max_recs @@ -465,7 +465,7 @@ static irqreturn_t ubd_intr(int irq, void *dev) &irq_remainder, &irq_remainder_size, UBD_REQ_BUFFER_SIZE)) >= 0) { for (i = 0; i < len / sizeof(struct io_thread_req *); i++) - ubd_end_request((*irq_req_buffer)[i]); + ubd_end_request(irq_req_buffer[i]); } if (len < 0 && len != -EAGAIN) @@ -1512,7 +1512,7 @@ void *io_thread(void *arg) } for (count = 0; count < n/sizeof(struct io_thread_req *); count++) { - struct io_thread_req *req = (*io_req_buffer)[count]; + struct io_thread_req *req = io_req_buffer[count]; int i; io_count++; diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index a36b7918a011..ad3cefeff2ac 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -172,6 +172,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index a409d4b66114..30aa24348d60 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -113,6 +113,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 68f9d7a1683b..b8b2b7bea1d3 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -113,6 +113,7 @@ vmlinux-objs-$(CONFIG_EFI_SBAT) += $(obj)/sbat.o ifdef CONFIG_EFI_SBAT $(obj)/sbat.o: $(CONFIG_EFI_SBAT_FILE) +AFLAGS_sbat.o += -I $(srctree) endif $(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index c8c1464b3a56..e468476e9e4a 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -28,17 +28,17 @@ #include "sev.h" static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); -struct ghcb *boot_ghcb; +struct ghcb *boot_ghcb __section(".data"); #undef __init #define __init #define __BOOT_COMPRESSED -u8 snp_vmpl; -u16 ghcb_version; +u8 snp_vmpl __section(".data"); +u16 ghcb_version __section(".data"); -u64 boot_svsm_caa_pa; +u64 boot_svsm_caa_pa __section(".data"); /* Include code for early handlers */ #include "../../boot/startup/sev-shared.c" @@ -188,6 +188,7 @@ bool sev_es_check_ghcb_fault(unsigned long address) MSR_AMD64_SNP_RESERVED_BIT13 | \ MSR_AMD64_SNP_RESERVED_BIT15 | \ MSR_AMD64_SNP_SECURE_AVIC | \ + MSR_AMD64_SNP_RESERVED_BITS19_22 | \ MSR_AMD64_SNP_RESERVED_MASK) #ifdef CONFIG_AMD_SECURE_AVIC diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 587ce3e7c504..e0b152715d9c 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -88,7 +88,7 @@ SECTIONS /DISCARD/ : { *(.dynamic) *(.dynsym) *(.dynstr) *(.dynbss) *(.hash) *(.gnu.hash) - *(.note.*) + *(.note.*) *(.modinfo) } .got.plt (INFO) : { diff --git a/arch/x86/boot/startup/sev-shared.c b/arch/x86/boot/startup/sev-shared.c index a0fa8bb2b945..d9ac3a929d33 100644 --- a/arch/x86/boot/startup/sev-shared.c +++ b/arch/x86/boot/startup/sev-shared.c @@ -31,7 +31,7 @@ static u32 cpuid_std_range_max __ro_after_init; static u32 cpuid_hyp_range_max __ro_after_init; static u32 cpuid_ext_range_max __ro_after_init; -bool sev_snp_needs_sfw; +bool sev_snp_needs_sfw __section(".data"); void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index 907981b94c40..7ed3da998489 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -89,6 +89,7 @@ static const char * const sev_status_feat_names[] = { [MSR_AMD64_SNP_VMSA_REG_PROT_BIT] = "VMSARegProt", [MSR_AMD64_SNP_SMT_PROT_BIT] = "SMTProt", [MSR_AMD64_SNP_SECURE_AVIC_BIT] = "SecureAVIC", + [MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT] = "IBPBOnEntry", }; /* diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c index a9b72997103d..88c757ac8ccd 100644 --- a/arch/x86/entry/entry_fred.c +++ b/arch/x86/entry/entry_fred.c @@ -160,8 +160,6 @@ void __init fred_complete_exception_setup(void) static noinstr void fred_extint(struct pt_regs *regs) { unsigned int vector = regs->fred_ss.vector; - unsigned int index = array_index_nospec(vector - FIRST_SYSTEM_VECTOR, - NR_SYSTEM_VECTORS); if (WARN_ON_ONCE(vector < FIRST_EXTERNAL_VECTOR)) return; @@ -170,7 +168,8 @@ static noinstr void fred_extint(struct pt_regs *regs) irqentry_state_t state = irqentry_enter(regs); instrumentation_begin(); - sysvec_table[index](regs); + sysvec_table[array_index_nospec(vector - FIRST_SYSTEM_VECTOR, + NR_SYSTEM_VECTORS)](regs); instrumentation_end(); irqentry_exit(regs, state); } else { diff --git a/arch/x86/entry/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S index b433353bc8e3..b33fcc501ba3 100644 --- a/arch/x86/entry/vdso/vdso32/sigreturn.S +++ b/arch/x86/entry/vdso/vdso32/sigreturn.S @@ -35,9 +35,38 @@ #endif .endm +/* + * WARNING: + * + * A bug in the libgcc unwinder as of at least gcc 15.2 (2026) means that + * the unwinder fails to recognize the signal frame flag. + * + * There is a hacky legacy fallback path in libgcc which ends up + * getting invoked instead. It happens to work as long as BOTH of the + * following conditions are true: + * + * 1. There is at least one byte before the each of the sigreturn + * functions which falls outside any function. This is enforced by + * an explicit nop instruction before the ALIGN. + * 2. The code sequences between the entry point up to and including + * the int $0x80 below need to match EXACTLY. Do not change them + * in any way. The exact byte sequences are: + * + * __kernel_sigreturn: + * 0: 58 pop %eax + * 1: b8 77 00 00 00 mov $0x77,%eax + * 6: cd 80 int $0x80 + * + * __kernel_rt_sigreturn: + * 0: b8 ad 00 00 00 mov $0xad,%eax + * 5: cd 80 int $0x80 + * + * For details, see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124050 + */ .text .globl __kernel_sigreturn .type __kernel_sigreturn,@function + nop /* libgcc hack: see comment above */ ALIGN __kernel_sigreturn: STARTPROC_SIGNAL_FRAME IA32_SIGFRAME_sigcontext @@ -52,6 +81,7 @@ SYM_INNER_LABEL(vdso32_sigreturn_landing_pad, SYM_L_GLOBAL) .globl __kernel_rt_sigreturn .type __kernel_rt_sigreturn,@function + nop /* libgcc hack: see comment above */ ALIGN __kernel_rt_sigreturn: STARTPROC_SIGNAL_FRAME IA32_RT_SIGFRAME_sigcontext diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 5ed6e0b7e715..0a1d08136cc1 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -6497,6 +6497,32 @@ static struct intel_uncore_type gnr_uncore_ubox = { .attr_update = uncore_alias_groups, }; +static struct uncore_event_desc gnr_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x01,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0, "event=0x05,umask=0xcf"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1, "event=0x06,umask=0xcf"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0, "event=0x05,umask=0xf0"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1, "event=0x06,umask=0xf0"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type gnr_uncore_imc = { + SPR_UNCORE_MMIO_COMMON_FORMAT(), + .name = "imc", + .fixed_ctr_bits = 48, + .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, + .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, + .event_descs = gnr_uncore_imc_events, +}; + static struct intel_uncore_type gnr_uncore_pciex8 = { SPR_UNCORE_PCI_COMMON_FORMAT(), .name = "pciex8", @@ -6544,7 +6570,7 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = { NULL, &spr_uncore_pcu, &gnr_uncore_ubox, - &spr_uncore_imc, + &gnr_uncore_imc, NULL, &gnr_uncore_upi, NULL, diff --git a/arch/x86/hyperv/hv_crash.c b/arch/x86/hyperv/hv_crash.c index 92da1b4f2e73..5ffcc23255de 100644 --- a/arch/x86/hyperv/hv_crash.c +++ b/arch/x86/hyperv/hv_crash.c @@ -107,14 +107,12 @@ static void __noreturn hv_panic_timeout_reboot(void) cpu_relax(); } -/* This cannot be inlined as it needs stack */ -static noinline __noclone void hv_crash_restore_tss(void) +static void hv_crash_restore_tss(void) { load_TR_desc(); } -/* This cannot be inlined as it needs stack */ -static noinline void hv_crash_clear_kernpt(void) +static void hv_crash_clear_kernpt(void) { pgd_t *pgd; p4d_t *p4d; @@ -125,6 +123,25 @@ static noinline void hv_crash_clear_kernpt(void) native_p4d_clear(p4d); } + +static void __noreturn hv_crash_handle(void) +{ + hv_crash_restore_tss(); + hv_crash_clear_kernpt(); + + /* we are now fully in devirtualized normal kernel mode */ + __crash_kexec(NULL); + + hv_panic_timeout_reboot(); +} + +/* + * __naked functions do not permit function calls, not even to __always_inline + * functions that only contain asm() blocks themselves. So use a macro instead. + */ +#define hv_wrmsr(msr, val) \ + asm volatile("wrmsr" :: "c"(msr), "a"((u32)val), "d"((u32)(val >> 32)) : "memory") + /* * This is the C entry point from the asm glue code after the disable hypercall. * We enter here in IA32-e long mode, ie, full 64bit mode running on kernel @@ -133,51 +150,38 @@ static noinline void hv_crash_clear_kernpt(void) * available. We restore kernel GDT, and rest of the context, and continue * to kexec. */ -static asmlinkage void __noreturn hv_crash_c_entry(void) +static void __naked hv_crash_c_entry(void) { - struct hv_crash_ctxt *ctxt = &hv_crash_ctxt; - /* first thing, restore kernel gdt */ - native_load_gdt(&ctxt->gdtr); + asm volatile("lgdt %0" : : "m" (hv_crash_ctxt.gdtr)); - asm volatile("movw %%ax, %%ss" : : "a"(ctxt->ss)); - asm volatile("movq %0, %%rsp" : : "m"(ctxt->rsp)); + asm volatile("movw %0, %%ss\n\t" + "movq %1, %%rsp" + :: "m"(hv_crash_ctxt.ss), "m"(hv_crash_ctxt.rsp)); - asm volatile("movw %%ax, %%ds" : : "a"(ctxt->ds)); - asm volatile("movw %%ax, %%es" : : "a"(ctxt->es)); - asm volatile("movw %%ax, %%fs" : : "a"(ctxt->fs)); - asm volatile("movw %%ax, %%gs" : : "a"(ctxt->gs)); + asm volatile("movw %0, %%ds" : : "m"(hv_crash_ctxt.ds)); + asm volatile("movw %0, %%es" : : "m"(hv_crash_ctxt.es)); + asm volatile("movw %0, %%fs" : : "m"(hv_crash_ctxt.fs)); + asm volatile("movw %0, %%gs" : : "m"(hv_crash_ctxt.gs)); - native_wrmsrq(MSR_IA32_CR_PAT, ctxt->pat); - asm volatile("movq %0, %%cr0" : : "r"(ctxt->cr0)); + hv_wrmsr(MSR_IA32_CR_PAT, hv_crash_ctxt.pat); + asm volatile("movq %0, %%cr0" : : "r"(hv_crash_ctxt.cr0)); - asm volatile("movq %0, %%cr8" : : "r"(ctxt->cr8)); - asm volatile("movq %0, %%cr4" : : "r"(ctxt->cr4)); - asm volatile("movq %0, %%cr2" : : "r"(ctxt->cr4)); + asm volatile("movq %0, %%cr8" : : "r"(hv_crash_ctxt.cr8)); + asm volatile("movq %0, %%cr4" : : "r"(hv_crash_ctxt.cr4)); + asm volatile("movq %0, %%cr2" : : "r"(hv_crash_ctxt.cr2)); - native_load_idt(&ctxt->idtr); - native_wrmsrq(MSR_GS_BASE, ctxt->gsbase); - native_wrmsrq(MSR_EFER, ctxt->efer); + asm volatile("lidt %0" : : "m" (hv_crash_ctxt.idtr)); + hv_wrmsr(MSR_GS_BASE, hv_crash_ctxt.gsbase); + hv_wrmsr(MSR_EFER, hv_crash_ctxt.efer); /* restore the original kernel CS now via far return */ - asm volatile("movzwq %0, %%rax\n\t" - "pushq %%rax\n\t" - "pushq $1f\n\t" - "lretq\n\t" - "1:nop\n\t" : : "m"(ctxt->cs) : "rax"); - - /* We are in asmlinkage without stack frame, hence make C function - * calls which will buy stack frames. - */ - hv_crash_restore_tss(); - hv_crash_clear_kernpt(); - - /* we are now fully in devirtualized normal kernel mode */ - __crash_kexec(NULL); - - hv_panic_timeout_reboot(); + asm volatile("pushq %q0\n\t" + "pushq %q1\n\t" + "lretq" + :: "r"(hv_crash_ctxt.cs), "r"(hv_crash_handle)); } -/* Tell gcc we are using lretq long jump in the above function intentionally */ +/* Tell objtool we are using lretq long jump in the above function intentionally */ STACK_FRAME_NON_STANDARD(hv_crash_c_entry); static void hv_mark_tss_not_busy(void) @@ -195,20 +199,20 @@ static void hv_hvcrash_ctxt_save(void) { struct hv_crash_ctxt *ctxt = &hv_crash_ctxt; - asm volatile("movq %%rsp,%0" : "=m"(ctxt->rsp)); + ctxt->rsp = current_stack_pointer; ctxt->cr0 = native_read_cr0(); ctxt->cr4 = native_read_cr4(); - asm volatile("movq %%cr2, %0" : "=a"(ctxt->cr2)); - asm volatile("movq %%cr8, %0" : "=a"(ctxt->cr8)); + asm volatile("movq %%cr2, %0" : "=r"(ctxt->cr2)); + asm volatile("movq %%cr8, %0" : "=r"(ctxt->cr8)); - asm volatile("movl %%cs, %%eax" : "=a"(ctxt->cs)); - asm volatile("movl %%ss, %%eax" : "=a"(ctxt->ss)); - asm volatile("movl %%ds, %%eax" : "=a"(ctxt->ds)); - asm volatile("movl %%es, %%eax" : "=a"(ctxt->es)); - asm volatile("movl %%fs, %%eax" : "=a"(ctxt->fs)); - asm volatile("movl %%gs, %%eax" : "=a"(ctxt->gs)); + asm volatile("movw %%cs, %0" : "=m"(ctxt->cs)); + asm volatile("movw %%ss, %0" : "=m"(ctxt->ss)); + asm volatile("movw %%ds, %0" : "=m"(ctxt->ds)); + asm volatile("movw %%es, %0" : "=m"(ctxt->es)); + asm volatile("movw %%fs, %0" : "=m"(ctxt->fs)); + asm volatile("movw %%gs, %0" : "=m"(ctxt->gs)); native_store_gdt(&ctxt->gdtr); store_idt(&ctxt->idtr); diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 9b4e04690e1a..80c1696d8d59 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -7,7 +7,7 @@ #include <linux/objtool.h> #include <asm/asm.h> -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ struct bug_entry; extern void __WARN_trap(struct bug_entry *bug, ...); #endif @@ -137,7 +137,7 @@ do { \ #ifdef HAVE_ARCH_BUG_FORMAT_ARGS -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/static_call_types.h> DECLARE_STATIC_CALL(WARN_trap, __WARN_trap); @@ -153,7 +153,7 @@ struct arch_va_list { struct sysv_va_list args; }; extern void *__warn_args(struct arch_va_list *args, struct pt_regs *regs); -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #define __WARN_bug_entry(flags, format) ({ \ struct bug_entry *bug; \ diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h index c40b9ebc1fb4..ab3fbbd947ed 100644 --- a/arch/x86/include/asm/cfi.h +++ b/arch/x86/include/asm/cfi.h @@ -111,6 +111,12 @@ extern bhi_thunk __bhi_args_end[]; struct pt_regs; +#ifdef CONFIG_CALL_PADDING +#define CFI_OFFSET (CONFIG_FUNCTION_PADDING_CFI+5) +#else +#define CFI_OFFSET 5 +#endif + #ifdef CONFIG_CFI enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); #define __bpfcall @@ -119,11 +125,9 @@ static inline int cfi_get_offset(void) { switch (cfi_mode) { case CFI_FINEIBT: - return 16; + return /* fineibt_prefix_size */ 16; case CFI_KCFI: - if (IS_ENABLED(CONFIG_CALL_PADDING)) - return 16; - return 5; + return CFI_OFFSET; default: return 0; } diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index f227a70ac91f..51b4cdbea061 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -138,7 +138,7 @@ extern void __init efi_apply_memmap_quirks(void); extern int __init efi_reuse_config(u64 tables, int nr_tables); extern void efi_delete_dummy_variable(void); extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr); -extern void efi_free_boot_services(void); +extern void efi_unmap_boot_services(void); void arch_efi_call_virt_setup(void); void arch_efi_call_virt_teardown(void); diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index a1193e9d65f2..462754b0bf8a 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -77,7 +77,7 @@ static __always_inline void native_local_irq_restore(unsigned long flags) #endif #ifndef CONFIG_PARAVIRT -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* * Used in the idle loop; sti takes one instruction cycle * to complete: @@ -95,7 +95,7 @@ static __always_inline void halt(void) { native_halt(); } -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* CONFIG_PARAVIRT */ #ifdef CONFIG_PARAVIRT_XXL diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ff07c45e3c73..6e4e3ef9b8c7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2485,7 +2485,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS | \ KVM_X86_QUIRK_SLOT_ZAP_ALL | \ KVM_X86_QUIRK_STUFF_FEATURE_MSRS | \ - KVM_X86_QUIRK_IGNORE_GUEST_PAT) + KVM_X86_QUIRK_IGNORE_GUEST_PAT | \ + KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM) #define KVM_X86_CONDITIONAL_QUIRKS \ (KVM_X86_QUIRK_CD_NW_CLEARED | \ diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 9d38ae744a2e..a7294656ad90 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -68,7 +68,7 @@ * Depending on -fpatchable-function-entry=N,N usage (CONFIG_CALL_PADDING) the * CFI symbol layout changes. * - * Without CALL_THUNKS: + * Without CALL_PADDING: * * .align FUNCTION_ALIGNMENT * __cfi_##name: @@ -77,7 +77,7 @@ * .long __kcfi_typeid_##name * name: * - * With CALL_THUNKS: + * With CALL_PADDING: * * .align FUNCTION_ALIGNMENT * __cfi_##name: diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index da5275d8eda6..6673601246b3 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -740,7 +740,10 @@ #define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) #define MSR_AMD64_SNP_SECURE_AVIC_BIT 18 #define MSR_AMD64_SNP_SECURE_AVIC BIT_ULL(MSR_AMD64_SNP_SECURE_AVIC_BIT) -#define MSR_AMD64_SNP_RESV_BIT 19 +#define MSR_AMD64_SNP_RESERVED_BITS19_22 GENMASK_ULL(22, 19) +#define MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT 23 +#define MSR_AMD64_SNP_IBPB_ON_ENTRY BIT_ULL(MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT) +#define MSR_AMD64_SNP_RESV_BIT 24 #define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) #define MSR_AMD64_SAVIC_CONTROL 0xc0010138 #define MSR_AMD64_SAVIC_EN_BIT 0 diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 53ba39ce010c..a9063f332fa6 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -22,6 +22,7 @@ extern int numa_off; */ extern s16 __apicid_to_node[MAX_LOCAL_APIC]; extern nodemask_t numa_nodes_parsed __initdata; +extern nodemask_t numa_phys_nodes_parsed __initdata; static inline void set_apicid_to_node(int apicid, s16 node) { @@ -48,6 +49,7 @@ extern void __init init_cpu_to_node(void); extern void numa_add_cpu(unsigned int cpu); extern void numa_remove_cpu(unsigned int cpu); extern void init_gi_nodes(void); +extern int num_phys_nodes(void); #else /* CONFIG_NUMA */ static inline void numa_set_node(int cpu, int node) { } static inline void numa_clear_node(int cpu) { } @@ -55,6 +57,10 @@ static inline void init_cpu_to_node(void) { } static inline void numa_add_cpu(unsigned int cpu) { } static inline void numa_remove_cpu(unsigned int cpu) { } static inline void init_gi_nodes(void) { } +static inline int num_phys_nodes(void) +{ + return 1; +} #endif /* CONFIG_NUMA */ #ifdef CONFIG_DEBUG_PER_CPU_MAPS diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index c55058f3d75e..409981468cba 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -20,7 +20,7 @@ #define PER_CPU_VAR(var) __percpu(var)__percpu_rel -#else /* !__ASSEMBLY__: */ +#else /* !__ASSEMBLER__: */ #include <linux/args.h> #include <linux/bits.h> diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index f06e5d6a2747..ce45882ccd07 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -19,10 +19,8 @@ extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; -extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; -extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h index e5a13dc8816e..4cd94fdcb45e 100644 --- a/arch/x86/include/asm/runtime-const.h +++ b/arch/x86/include/asm/runtime-const.h @@ -6,7 +6,7 @@ #error "Cannot use runtime-const infrastructure from modules" #endif -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ .macro RUNTIME_CONST_PTR sym reg movq $0x0123456789abcdef, %\reg @@ -16,7 +16,7 @@ .popsection .endm -#else /* __ASSEMBLY__ */ +#else /* __ASSEMBLER__ */ #define runtime_const_ptr(sym) ({ \ typeof(sym) __ret; \ @@ -74,5 +74,5 @@ static inline void runtime_const_fixup(void (*fn)(void *, unsigned long), } } -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 1fadf0cf520c..0ba9bdb99871 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -155,6 +155,7 @@ extern unsigned int __max_logical_packages; extern unsigned int __max_threads_per_core; extern unsigned int __num_threads_per_package; extern unsigned int __num_cores_per_package; +extern unsigned int __num_nodes_per_package; const char *get_topology_cpu_type_name(struct cpuinfo_x86 *c); enum x86_topology_cpu_type get_topology_cpu_type(struct cpuinfo_x86 *c); @@ -179,6 +180,11 @@ static inline unsigned int topology_num_threads_per_package(void) return __num_threads_per_package; } +static inline unsigned int topology_num_nodes_per_package(void) +{ + return __num_nodes_per_package; +} + #ifdef CONFIG_X86_LOCAL_APIC int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level); #else diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 869b88061801..3f24cc472ce9 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -25,6 +25,8 @@ extern int ibt_selftest_noendbr(void); void handle_invalid_op(struct pt_regs *regs); #endif +noinstr bool handle_bug(struct pt_regs *regs); + static inline int get_si_code(unsigned long condition) { if (condition & DR_STEP) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 846a63215ce1..0d4538fa6c31 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -476,6 +476,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8) #define KVM_X86_QUIRK_IGNORE_GUEST_PAT (1 << 9) +#define KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM (1 << 10) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a888ae0f01fb..e87da25d1236 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1182,7 +1182,7 @@ void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end) poison_endbr(addr); if (IS_ENABLED(CONFIG_FINEIBT)) - poison_cfi(addr - 16); + poison_cfi(addr - CFI_OFFSET); } } @@ -1389,6 +1389,8 @@ extern u8 fineibt_preamble_end[]; #define fineibt_preamble_ud 0x13 #define fineibt_preamble_hash 5 +#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE) + /* * <fineibt_caller_start>: * 0: b8 78 56 34 12 mov $0x12345678, %eax @@ -1634,7 +1636,7 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end) * have determined there are no indirect calls to it and we * don't need no CFI either. */ - if (!is_endbr(addr + 16)) + if (!is_endbr(addr + CFI_OFFSET)) continue; hash = decode_preamble_hash(addr, &arity); @@ -1642,6 +1644,15 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end) addr, addr, 5, addr)) return -EINVAL; + /* + * FineIBT relies on being at func-16, so if the preamble is + * actually larger than that, place it the tail end. + * + * NOTE: this is possible with things like DEBUG_CALL_THUNKS + * and DEBUG_FORCE_FUNCTION_ALIGN_64B. + */ + addr += CFI_OFFSET - fineibt_prefix_size; + text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size); WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678); text_poke_early(addr + fineibt_preamble_hash, &hash, 4); @@ -1664,10 +1675,10 @@ static void cfi_rewrite_endbr(s32 *start, s32 *end) for (s = start; s < end; s++) { void *addr = (void *)s + *s; - if (!exact_endbr(addr + 16)) + if (!exact_endbr(addr + CFI_OFFSET)) continue; - poison_endbr(addr + 16); + poison_endbr(addr + CFI_OFFSET); } } @@ -1772,7 +1783,8 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, if (FINEIBT_WARN(fineibt_preamble_size, 20) || FINEIBT_WARN(fineibt_preamble_bhi + fineibt_bhi1_size, 20) || FINEIBT_WARN(fineibt_caller_size, 14) || - FINEIBT_WARN(fineibt_paranoid_size, 20)) + FINEIBT_WARN(fineibt_paranoid_size, 20) || + WARN_ON_ONCE(CFI_OFFSET < fineibt_prefix_size)) return; if (cfi_mode == CFI_AUTO) { @@ -1886,6 +1898,11 @@ static void poison_cfi(void *addr) switch (cfi_mode) { case CFI_FINEIBT: /* + * FineIBT preamble is at func-16. + */ + addr += CFI_OFFSET - fineibt_prefix_size; + + /* * FineIBT prefix should start with an ENDBR. */ if (!is_endbr(addr)) @@ -1923,8 +1940,6 @@ static void poison_cfi(void *addr) } } -#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE) - /* * When regs->ip points to a 0xD6 byte in the FineIBT preamble, * return true and fill out target and type. diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d93f87f29d03..961714e6adae 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1894,6 +1894,7 @@ void __init check_x2apic(void) static inline void try_to_enable_x2apic(int remap_mode) { } static inline void __x2apic_enable(void) { } +static inline void __x2apic_disable(void) { } #endif /* !CONFIG_X86_X2APIC */ void __init enable_IR_x2apic(void) @@ -2456,6 +2457,11 @@ static void lapic_resume(void *data) if (x2apic_mode) { __x2apic_enable(); } else { + if (x2apic_enabled()) { + pr_warn_once("x2apic: re-enabled by firmware during resume. Disabling\n"); + __x2apic_disable(); + } + /* * Make sure the APICBASE points to the right address * diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 1c3261cae40c..a8ff4376c286 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -95,6 +95,9 @@ EXPORT_SYMBOL(__max_dies_per_package); unsigned int __max_logical_packages __ro_after_init = 1; EXPORT_SYMBOL(__max_logical_packages); +unsigned int __num_nodes_per_package __ro_after_init = 1; +EXPORT_SYMBOL(__num_nodes_per_package); + unsigned int __num_cores_per_package __ro_after_init = 1; EXPORT_SYMBOL(__num_cores_per_package); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 89a2eb8a0722..9befdc557d9e 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -496,8 +496,9 @@ static void hv_reserve_irq_vectors(void) test_and_set_bit(HYPERV_DBG_FASTFAIL_VECTOR, system_vectors)) BUG(); - pr_info("Hyper-V: reserve vectors: %d %d %d\n", HYPERV_DBG_ASSERT_VECTOR, - HYPERV_DBG_SERVICE_VECTOR, HYPERV_DBG_FASTFAIL_VECTOR); + pr_info("Hyper-V: reserve vectors: 0x%x 0x%x 0x%x\n", + HYPERV_DBG_ASSERT_VECTOR, HYPERV_DBG_SERVICE_VECTOR, + HYPERV_DBG_FASTFAIL_VECTOR); } static void __init ms_hyperv_init_platform(void) diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index e6a154240b8d..9bd87bae4983 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -364,7 +364,7 @@ void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d) msr_clear_bit(MSR_RMID_SNC_CONFIG, 0); } -/* CPU models that support MSR_RMID_SNC_CONFIG */ +/* CPU models that support SNC and MSR_RMID_SNC_CONFIG */ static const struct x86_cpu_id snc_cpu_ids[] __initconst = { X86_MATCH_VFM(INTEL_ICELAKE_X, 0), X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, 0), @@ -375,40 +375,14 @@ static const struct x86_cpu_id snc_cpu_ids[] __initconst = { {} }; -/* - * There isn't a simple hardware bit that indicates whether a CPU is running - * in Sub-NUMA Cluster (SNC) mode. Infer the state by comparing the - * number of CPUs sharing the L3 cache with CPU0 to the number of CPUs in - * the same NUMA node as CPU0. - * It is not possible to accurately determine SNC state if the system is - * booted with a maxcpus=N parameter. That distorts the ratio of SNC nodes - * to L3 caches. It will be OK if system is booted with hyperthreading - * disabled (since this doesn't affect the ratio). - */ static __init int snc_get_config(void) { - struct cacheinfo *ci = get_cpu_cacheinfo_level(0, RESCTRL_L3_CACHE); - const cpumask_t *node0_cpumask; - int cpus_per_node, cpus_per_l3; - int ret; - - if (!x86_match_cpu(snc_cpu_ids) || !ci) - return 1; + int ret = topology_num_nodes_per_package(); - cpus_read_lock(); - if (num_online_cpus() != num_present_cpus()) - pr_warn("Some CPUs offline, SNC detection may be incorrect\n"); - cpus_read_unlock(); - - node0_cpumask = cpumask_of_node(cpu_to_node(0)); - - cpus_per_node = cpumask_weight(node0_cpumask); - cpus_per_l3 = cpumask_weight(&ci->shared_cpu_map); - - if (!cpus_per_node || !cpus_per_l3) + if (ret > 1 && !x86_match_cpu(snc_cpu_ids)) { + pr_warn("CoD enabled system? Resctrl not supported\n"); return 1; - - ret = cpus_per_l3 / cpus_per_node; + } /* sanity check: Only valid results are 1, 2, 3, 4, 6 */ switch (ret) { diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 23190a786d31..eafcb1fc185a 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -31,6 +31,7 @@ #include <asm/mpspec.h> #include <asm/msr.h> #include <asm/smp.h> +#include <asm/numa.h> #include "cpu.h" @@ -492,11 +493,19 @@ void __init topology_init_possible_cpus(void) set_nr_cpu_ids(allowed); cnta = domain_weight(TOPO_PKG_DOMAIN); - cntb = domain_weight(TOPO_DIE_DOMAIN); __max_logical_packages = cnta; + + pr_info("Max. logical packages: %3u\n", __max_logical_packages); + + cntb = num_phys_nodes(); + __num_nodes_per_package = DIV_ROUND_UP(cntb, cnta); + + pr_info("Max. logical nodes: %3u\n", cntb); + pr_info("Num. nodes per package:%3u\n", __num_nodes_per_package); + + cntb = domain_weight(TOPO_DIE_DOMAIN); __max_dies_per_package = 1U << (get_count_order(cntb) - get_count_order(cnta)); - pr_info("Max. logical packages: %3u\n", cnta); pr_info("Max. logical dies: %3u\n", cntb); pr_info("Max. dies per package: %3u\n", __max_dies_per_package); diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 21816b48537c..85d4a5094f6b 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -616,38 +616,10 @@ SYM_DATA(early_recursion_flag, .long 0) .data -#if defined(CONFIG_XEN_PV) || defined(CONFIG_PVH) -SYM_DATA_START_PTI_ALIGNED(init_top_pgt) - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC - .org init_top_pgt + L4_PAGE_OFFSET*8, 0 - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC - .org init_top_pgt + L4_START_KERNEL*8, 0 - /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC - .fill PTI_USER_PGD_FILL,8,0 -SYM_DATA_END(init_top_pgt) - -SYM_DATA_START_PAGE_ALIGNED(level3_ident_pgt) - .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC - .fill 511, 8, 0 -SYM_DATA_END(level3_ident_pgt) -SYM_DATA_START_PAGE_ALIGNED(level2_ident_pgt) - /* - * Since I easily can, map the first 1G. - * Don't set NX because code runs from these pages. - * - * Note: This sets _PAGE_GLOBAL despite whether - * the CPU supports it or it is enabled. But, - * the CPU should ignore the bit. - */ - PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) -SYM_DATA_END(level2_ident_pgt) -#else SYM_DATA_START_PTI_ALIGNED(init_top_pgt) .fill 512,8,0 .fill PTI_USER_PGD_FILL,8,0 SYM_DATA_END(init_top_pgt) -#endif SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt) .fill 511,8,0 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 5cd6950ab672..294a8ea60298 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -468,13 +468,6 @@ static int x86_cluster_flags(void) } #endif -/* - * Set if a package/die has multiple NUMA nodes inside. - * AMD Magny-Cours, Intel Cluster-on-Die, and Intel - * Sub-NUMA Clustering have this. - */ -static bool x86_has_numa_in_package; - static struct sched_domain_topology_level x86_topology[] = { SDTL_INIT(tl_smt_mask, cpu_smt_flags, SMT), #ifdef CONFIG_SCHED_CLUSTER @@ -496,7 +489,7 @@ static void __init build_sched_topology(void) * PKG domain since the NUMA domains will auto-magically create the * right spanning domains based on the SLIT. */ - if (x86_has_numa_in_package) { + if (topology_num_nodes_per_package() > 1) { unsigned int pkgdom = ARRAY_SIZE(x86_topology) - 2; memset(&x86_topology[pkgdom], 0, sizeof(x86_topology[pkgdom])); @@ -513,33 +506,149 @@ static void __init build_sched_topology(void) } #ifdef CONFIG_NUMA -static int sched_avg_remote_distance; -static int avg_remote_numa_distance(void) +/* + * Test if the on-trace cluster at (N,N) is symmetric. + * Uses upper triangle iteration to avoid obvious duplicates. + */ +static bool slit_cluster_symmetric(int N) { - int i, j; - int distance, nr_remote, total_distance; - - if (sched_avg_remote_distance > 0) - return sched_avg_remote_distance; - - nr_remote = 0; - total_distance = 0; - for_each_node_state(i, N_CPU) { - for_each_node_state(j, N_CPU) { - distance = node_distance(i, j); - - if (distance >= REMOTE_DISTANCE) { - nr_remote++; - total_distance += distance; - } + int u = topology_num_nodes_per_package(); + + for (int k = 0; k < u; k++) { + for (int l = k; l < u; l++) { + if (node_distance(N + k, N + l) != + node_distance(N + l, N + k)) + return false; } } - if (nr_remote) - sched_avg_remote_distance = total_distance / nr_remote; - else - sched_avg_remote_distance = REMOTE_DISTANCE; - return sched_avg_remote_distance; + return true; +} + +/* + * Return the package-id of the cluster, or ~0 if indeterminate. + * Each node in the on-trace cluster should have the same package-id. + */ +static u32 slit_cluster_package(int N) +{ + int u = topology_num_nodes_per_package(); + u32 pkg_id = ~0; + + for (int n = 0; n < u; n++) { + const struct cpumask *cpus = cpumask_of_node(N + n); + int cpu; + + for_each_cpu(cpu, cpus) { + u32 id = topology_logical_package_id(cpu); + + if (pkg_id == ~0) + pkg_id = id; + if (pkg_id != id) + return ~0; + } + } + + return pkg_id; +} + +/* + * Validate the SLIT table is of the form expected for SNC, specifically: + * + * - each on-trace cluster should be symmetric, + * - each on-trace cluster should have a unique package-id. + * + * If you NUMA_EMU on top of SNC, you get to keep the pieces. + */ +static bool slit_validate(void) +{ + int u = topology_num_nodes_per_package(); + u32 pkg_id, prev_pkg_id = ~0; + + for (int pkg = 0; pkg < topology_max_packages(); pkg++) { + int n = pkg * u; + + /* + * Ensure the on-trace cluster is symmetric and each cluster + * has a different package id. + */ + if (!slit_cluster_symmetric(n)) + return false; + pkg_id = slit_cluster_package(n); + if (pkg_id == ~0) + return false; + if (pkg && pkg_id == prev_pkg_id) + return false; + + prev_pkg_id = pkg_id; + } + + return true; +} + +/* + * Compute a sanitized SLIT table for SNC; notably SNC-3 can end up with + * asymmetric off-trace clusters, reflecting physical assymmetries. However + * this leads to 'unfortunate' sched_domain configurations. + * + * For example dual socket GNR with SNC-3: + * + * node distances: + * node 0 1 2 3 4 5 + * 0: 10 15 17 21 28 26 + * 1: 15 10 15 23 26 23 + * 2: 17 15 10 26 23 21 + * 3: 21 28 26 10 15 17 + * 4: 23 26 23 15 10 15 + * 5: 26 23 21 17 15 10 + * + * Fix things up by averaging out the off-trace clusters; resulting in: + * + * node 0 1 2 3 4 5 + * 0: 10 15 17 24 24 24 + * 1: 15 10 15 24 24 24 + * 2: 17 15 10 24 24 24 + * 3: 24 24 24 10 15 17 + * 4: 24 24 24 15 10 15 + * 5: 24 24 24 17 15 10 + */ +static int slit_cluster_distance(int i, int j) +{ + static int slit_valid = -1; + int u = topology_num_nodes_per_package(); + long d = 0; + int x, y; + + if (slit_valid < 0) { + slit_valid = slit_validate(); + if (!slit_valid) + pr_err(FW_BUG "SLIT table doesn't have the expected form for SNC -- fixup disabled!\n"); + else + pr_info("Fixing up SNC SLIT table.\n"); + } + + /* + * Is this a unit cluster on the trace? + */ + if ((i / u) == (j / u) || !slit_valid) + return node_distance(i, j); + + /* + * Off-trace cluster. + * + * Notably average out the symmetric pair of off-trace clusters to + * ensure the resulting SLIT table is symmetric. + */ + x = i - (i % u); + y = j - (j % u); + + for (i = x; i < x + u; i++) { + for (j = y; j < y + u; j++) { + d += node_distance(i, j); + d += node_distance(j, i); + } + } + + return d / (2*u*u); } int arch_sched_node_distance(int from, int to) @@ -549,34 +658,14 @@ int arch_sched_node_distance(int from, int to) switch (boot_cpu_data.x86_vfm) { case INTEL_GRANITERAPIDS_X: case INTEL_ATOM_DARKMONT_X: - - if (!x86_has_numa_in_package || topology_max_packages() == 1 || - d < REMOTE_DISTANCE) + if (topology_max_packages() == 1 || + topology_num_nodes_per_package() < 3) return d; /* - * With SNC enabled, there could be too many levels of remote - * NUMA node distances, creating NUMA domain levels - * including local nodes and partial remote nodes. - * - * Trim finer distance tuning for NUMA nodes in remote package - * for the purpose of building sched domains. Group NUMA nodes - * in the remote package in the same sched group. - * Simplify NUMA domains and avoid extra NUMA levels including - * different remote NUMA nodes and local nodes. - * - * GNR and CWF don't expect systems with more than 2 packages - * and more than 2 hops between packages. Single average remote - * distance won't be appropriate if there are more than 2 - * packages as average distance to different remote packages - * could be different. + * Handle SNC-3 asymmetries. */ - WARN_ONCE(topology_max_packages() > 2, - "sched: Expect only up to 2 packages for GNR or CWF, " - "but saw %d packages when building sched domains.", - topology_max_packages()); - - d = avg_remote_numa_distance(); + return slit_cluster_distance(from, to); } return d; } @@ -606,7 +695,7 @@ void set_cpu_sibling_map(int cpu) o = &cpu_data(i); if (match_pkg(c, o) && !topology_same_node(c, o)) - x86_has_numa_in_package = true; + WARN_ON_ONCE(topology_num_nodes_per_package() == 1); if ((i == cpu) || (has_smt && match_smt(c, o))) link_mask(topology_sibling_cpumask, cpu, i); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 5a6a772e0a6c..4dbff8ef9b1c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -397,7 +397,7 @@ static inline void handle_invalid_op(struct pt_regs *regs) ILL_ILLOPN, error_get_trap_addr(regs)); } -static noinstr bool handle_bug(struct pt_regs *regs) +noinstr bool handle_bug(struct pt_regs *regs) { unsigned long addr = regs->ip; bool handled = false; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3a24a3fc55f5..4711a35e706c 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -427,6 +427,7 @@ SECTIONS .llvm_bb_addr_map : { *(.llvm_bb_addr_map) } #endif + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index d916bd766c94..801bf9e520db 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -20,7 +20,6 @@ if VIRTUALIZATION config KVM_X86 def_tristate KVM if (KVM_INTEL != n || KVM_AMD != n) select KVM_COMMON - select KVM_GENERIC_MMU_NOTIFIER select KVM_ELIDE_TLB_FLUSH_IF_YOUNG select KVM_MMU_LOCKLESS_AGING select HAVE_KVM_IRQCHIP diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index d2486506a808..8137927e7387 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -776,7 +776,10 @@ do { \ #define SYNTHESIZED_F(name) \ ({ \ kvm_cpu_cap_synthesized |= feature_bit(name); \ - F(name); \ + \ + BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ + if (boot_cpu_has(X86_FEATURE_##name)) \ + F(name); \ }) /* diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 30202942289a..9b140bbdc1d8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1981,16 +1981,17 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY) goto out_flush_all; - if (is_noncanonical_invlpg_address(entries[i], vcpu)) - continue; - /* * Lower 12 bits of 'address' encode the number of additional * pages to flush. */ gva = entries[i] & PAGE_MASK; - for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) + for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) { + if (is_noncanonical_invlpg_address(gva + j * PAGE_SIZE, vcpu)) + continue; + kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE); + } ++vcpu->stat.tlb_flush; } diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index bb257793b6cb..eed96ff6e722 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -321,7 +321,8 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, idx = srcu_read_lock(&kvm->irq_srcu); gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); if (gsi != -1) - hlist_for_each_entry_rcu(kimn, &ioapic->mask_notifier_list, link) + hlist_for_each_entry_srcu(kimn, &ioapic->mask_notifier_list, link, + srcu_read_lock_held(&kvm->irq_srcu)) if (kimn->irq == gsi) kimn->func(kimn, mask); srcu_read_unlock(&kvm->irq_srcu, idx); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index f92214b1a938..f7ec7914e3c4 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -189,12 +189,12 @@ static void avic_activate_vmcb(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); - vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; vmcb->control.avic_physical_id |= avic_get_max_physical_id(vcpu); - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + svm_clr_intercept(svm, INTERCEPT_CR8_WRITE); + /* * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR * accesses, while interrupt injection to a running vCPU can be @@ -226,6 +226,9 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm) vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; + if (!sev_es_guest(svm->vcpu.kvm)) + svm_set_intercept(svm, INTERCEPT_CR8_WRITE); + /* * If running nested and the guest uses its own MSR bitmap, there * is no need to update L0's msr bitmap @@ -368,7 +371,7 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb) vmcb->control.avic_physical_id = __sme_set(__pa(kvm_svm->avic_physical_id_table)); vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE; - if (kvm_apicv_activated(svm->vcpu.kvm)) + if (kvm_vcpu_apicv_active(&svm->vcpu)) avic_activate_vmcb(svm); else avic_deactivate_vmcb(svm); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 53ab6ce3cc26..b36c33255bed 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -418,6 +418,15 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu) return __nested_vmcb_check_controls(vcpu, ctl); } +int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu) +{ + if (!nested_vmcb_check_save(vcpu) || + !nested_vmcb_check_controls(vcpu)) + return -EINVAL; + + return 0; +} + /* * If a feature is not advertised to L1, clear the corresponding vmcb12 * intercept. @@ -1028,8 +1037,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - if (!nested_vmcb_check_save(vcpu) || - !nested_vmcb_check_controls(vcpu)) { + if (nested_svm_check_cached_vmcb12(vcpu) < 0) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_info_1 = 0; vmcb12->control.exit_info_2 = 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8f8bc863e214..e6477affac9a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1077,8 +1077,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event) svm_set_intercept(svm, INTERCEPT_CR0_WRITE); svm_set_intercept(svm, INTERCEPT_CR3_WRITE); svm_set_intercept(svm, INTERCEPT_CR4_WRITE); - if (!kvm_vcpu_apicv_active(vcpu)) - svm_set_intercept(svm, INTERCEPT_CR8_WRITE); + svm_set_intercept(svm, INTERCEPT_CR8_WRITE); set_dr_intercepts(svm); @@ -1189,7 +1188,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event) if (guest_cpu_cap_has(vcpu, X86_FEATURE_ERAPS)) svm->vmcb->control.erap_ctl |= ERAP_CONTROL_ALLOW_LARGER_RAP; - if (kvm_vcpu_apicv_active(vcpu)) + if (enable_apicv && irqchip_in_kernel(vcpu->kvm)) avic_init_vmcb(svm, vmcb); if (vnmi) @@ -2674,9 +2673,11 @@ static int dr_interception(struct kvm_vcpu *vcpu) static int cr8_write_interception(struct kvm_vcpu *vcpu) { + u8 cr8_prev = kvm_get_cr8(vcpu); int r; - u8 cr8_prev = kvm_get_cr8(vcpu); + WARN_ON_ONCE(kvm_vcpu_apicv_active(vcpu)); + /* instruction emulation calls kvm_set_cr8() */ r = cr_interception(vcpu); if (lapic_in_kernel(vcpu)) @@ -4879,11 +4880,15 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) vmcb12 = map.hva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false); - if (ret) + if (nested_svm_check_cached_vmcb12(vcpu) < 0) + goto unmap_save; + + if (enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, + vmcb12, false) != 0) goto unmap_save; + ret = 0; svm->nested.nested_run_pending = 1; unmap_save: diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index ebd7b36b1ceb..6942e6b0eda6 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -797,6 +797,7 @@ static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code) int nested_svm_exit_handled(struct vcpu_svm *svm); int nested_svm_check_permissions(struct kvm_vcpu *vcpu); +int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu); int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 248635da6766..937aeb474af7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3300,10 +3300,24 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, if (CC(vmcs12->guest_cr4 & X86_CR4_CET && !(vmcs12->guest_cr0 & X86_CR0_WP))) return -EINVAL; - if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && - (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || - CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false)))) - return -EINVAL; + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { + u64 debugctl = vmcs12->guest_ia32_debugctl; + + /* + * FREEZE_IN_SMM is not virtualized, but allow L1 to set it in + * vmcs12's DEBUGCTL under a quirk for backwards compatibility. + * Note that the quirk only relaxes the consistency check. The + * vmcc02 bit is still under the control of the host. In + * particular, if a host administrator decides to clear the bit, + * then L1 has no say in the matter. + */ + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM)) + debugctl &= ~DEBUGCTLMSR_FREEZE_IN_SMM; + + if (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || + CC(!vmx_is_valid_debugctl(vcpu, debugctl, false))) + return -EINVAL; + } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && CC(!kvm_pat_valid(vmcs12->guest_ia32_pat))) @@ -6842,13 +6856,34 @@ void vmx_leave_nested(struct kvm_vcpu *vcpu) free_nested(vcpu); } +int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu) +{ + enum vm_entry_failure_code ignored; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + if (nested_cpu_has_shadow_vmcs(vmcs12) && + vmcs12->vmcs_link_pointer != INVALID_GPA) { + struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); + + if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION || + !shadow_vmcs12->hdr.shadow_vmcs) + return -EINVAL; + } + + if (nested_vmx_check_controls(vcpu, vmcs12) || + nested_vmx_check_host_state(vcpu, vmcs12) || + nested_vmx_check_guest_state(vcpu, vmcs12, &ignored)) + return -EINVAL; + + return 0; +} + static int vmx_set_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, struct kvm_nested_state *kvm_state) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12; - enum vm_entry_failure_code ignored; struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = &user_kvm_nested_state->data.vmx[0]; int ret; @@ -6979,25 +7014,20 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmx->nested.mtf_pending = !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING); - ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != INVALID_GPA) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); + ret = -EINVAL; if (kvm_state->size < sizeof(*kvm_state) + sizeof(user_vmx_nested_state->vmcs12) + sizeof(*shadow_vmcs12)) goto error_guest_mode; + ret = -EFAULT; if (copy_from_user(shadow_vmcs12, user_vmx_nested_state->shadow_vmcs12, - sizeof(*shadow_vmcs12))) { - ret = -EFAULT; - goto error_guest_mode; - } - - if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION || - !shadow_vmcs12->hdr.shadow_vmcs) + sizeof(*shadow_vmcs12))) goto error_guest_mode; } @@ -7008,9 +7038,8 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, kvm_state->hdr.vmx.preemption_timer_deadline; } - if (nested_vmx_check_controls(vcpu, vmcs12) || - nested_vmx_check_host_state(vcpu, vmcs12) || - nested_vmx_check_guest_state(vcpu, vmcs12, &ignored)) + ret = nested_vmx_check_restored_vmcs12(vcpu); + if (ret < 0) goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index b844c5d59025..213a448104af 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -22,6 +22,7 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); +int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 967b58a8ab9d..8b24e682535b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1149,7 +1149,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, } vmx_add_auto_msr(&m->guest, msr, guest_val, VM_ENTRY_MSR_LOAD_COUNT, kvm); - vmx_add_auto_msr(&m->guest, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm); + vmx_add_auto_msr(&m->host, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm); } static bool update_transition_efer(struct vcpu_vmx *vmx) @@ -8528,9 +8528,13 @@ int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) } if (vmx->nested.smm.guest_mode) { + /* Triple fault if the state is invalid. */ + if (nested_vmx_check_restored_vmcs12(vcpu) < 0) + return 1; + ret = nested_vmx_enter_non_root_mode(vcpu, false); - if (ret) - return ret; + if (ret != NVMX_VMENTRY_SUCCESS) + return 1; vmx->nested.nested_run_pending = 1; vmx->nested.smm.guest_mode = false; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3fb64905d190..fd1c4a36b593 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -243,7 +243,7 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_ipiv); bool __read_mostly enable_device_posted_irqs = true; EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_device_posted_irqs); -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, mmu_shadow_zapped), STATS_DESC_COUNTER(VM, mmu_pte_write), @@ -269,7 +269,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, pf_taken), STATS_DESC_COUNTER(VCPU, pf_fixed), @@ -4805,7 +4805,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #endif case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: - case KVM_CAP_SYNC_MMU: case KVM_CAP_USER_NMI: case KVM_CAP_IRQ_INJECT_STATUS: case KVM_CAP_IOEVENTFD: diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 2fdc1f1f5adb..6b9ff1c6cafa 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -411,14 +411,11 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) return; if (trapnr == X86_TRAP_UD) { - if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { - /* Skip the ud2. */ - regs->ip += LEN_UD2; + if (handle_bug(regs)) return; - } /* - * If this was a BUG and report_bug returns or if this + * If this was a BUG and handle_bug returns or if this * was just a normal #UD, we want to continue onward and * crash. */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 7a97327140df..99d0a9332c14 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -48,6 +48,8 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] = { [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE }; +nodemask_t numa_phys_nodes_parsed __initdata; + int numa_cpu_node(int cpu) { u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu); @@ -57,6 +59,11 @@ int numa_cpu_node(int cpu) return NUMA_NO_NODE; } +int __init num_phys_nodes(void) +{ + return bitmap_weight(numa_phys_nodes_parsed.bits, MAX_NUMNODES); +} + cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; EXPORT_SYMBOL(node_to_cpumask_map); @@ -210,6 +217,7 @@ static int __init dummy_numa_init(void) 0LLU, PFN_PHYS(max_pfn) - 1); node_set(0, numa_nodes_parsed); + node_set(0, numa_phys_nodes_parsed); numa_add_memblk(0, 0, PFN_PHYS(max_pfn)); return 0; diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 6f8e0f21c710..44ca66651756 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -57,6 +57,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) } set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); + node_set(node, numa_phys_nodes_parsed); pr_debug("SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node); } @@ -97,6 +98,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); + node_set(node, numa_phys_nodes_parsed); pr_debug("SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node); } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8f10080e6fe3..e9b78040d703 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -438,17 +438,8 @@ static void emit_kcfi(u8 **pprog, u32 hash) EMIT1_off32(0xb8, hash); /* movl $hash, %eax */ #ifdef CONFIG_CALL_PADDING - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); + for (int i = 0; i < CONFIG_FUNCTION_PADDING_CFI; i++) + EMIT1(0x90); #endif EMIT_ENDBR(); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index d00c6de7f3b7..d84c6020dda1 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -836,7 +836,7 @@ static void __init __efi_enter_virtual_mode(void) } efi_check_for_embedded_firmwares(); - efi_free_boot_services(); + efi_unmap_boot_services(); if (!efi_is_mixed()) efi_native_runtime_setup(); diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 553f330198f2..35caa5746115 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -341,7 +341,7 @@ void __init efi_reserve_boot_services(void) /* * Because the following memblock_reserve() is paired - * with memblock_free_late() for this region in + * with free_reserved_area() for this region in * efi_free_boot_services(), we must be extremely * careful not to reserve, and subsequently free, * critical regions of memory (like the kernel image) or @@ -404,17 +404,33 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md) pr_err("Failed to unmap VA mapping for 0x%llx\n", va); } -void __init efi_free_boot_services(void) +struct efi_freeable_range { + u64 start; + u64 end; +}; + +static struct efi_freeable_range *ranges_to_free; + +void __init efi_unmap_boot_services(void) { struct efi_memory_map_data data = { 0 }; efi_memory_desc_t *md; int num_entries = 0; + int idx = 0; + size_t sz; void *new, *new_md; /* Keep all regions for /sys/kernel/debug/efi */ if (efi_enabled(EFI_DBG)) return; + sz = sizeof(*ranges_to_free) * efi.memmap.nr_map + 1; + ranges_to_free = kzalloc(sz, GFP_KERNEL); + if (!ranges_to_free) { + pr_err("Failed to allocate storage for freeable EFI regions\n"); + return; + } + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; @@ -471,7 +487,15 @@ void __init efi_free_boot_services(void) start = SZ_1M; } - memblock_free_late(start, size); + /* + * With CONFIG_DEFERRED_STRUCT_PAGE_INIT parts of the memory + * map are still not initialized and we can't reliably free + * memory here. + * Queue the ranges to free at a later point. + */ + ranges_to_free[idx].start = start; + ranges_to_free[idx].end = start + size; + idx++; } if (!num_entries) @@ -512,6 +536,31 @@ void __init efi_free_boot_services(void) } } +static int __init efi_free_boot_services(void) +{ + struct efi_freeable_range *range = ranges_to_free; + unsigned long freed = 0; + + if (!ranges_to_free) + return 0; + + while (range->start) { + void *start = phys_to_virt(range->start); + void *end = phys_to_virt(range->end); + + free_reserved_area(start, end, -1, NULL); + freed += (end - start); + range++; + } + kfree(ranges_to_free); + + if (freed) + pr_info("Freeing EFI boot services memory: %ldK\n", freed / SZ_1K); + + return 0; +} +arch_initcall(efi_free_boot_services); + /* * A number of config table entries get remapped to virtual addresses * after entering EFI virtual mode. However, the kexec kernel requires diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 2263885d16ba..f2053cbe9b0c 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -25,11 +25,6 @@ struct hvm_start_info __initdata pvh_start_info; const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info); -static u64 __init pvh_get_root_pointer(void) -{ - return pvh_start_info.rsdp_paddr; -} - /* * Xen guests are able to obtain the memory map from the hypervisor via the * HYPERVISOR_memory_op hypercall. @@ -95,7 +90,7 @@ static void __init init_pvh_bootparams(bool xen_guest) pvh_bootparams.hdr.version = (2 << 8) | 12; pvh_bootparams.hdr.type_of_loader = ((xen_guest ? 0x9 : 0xb) << 4) | 0; - x86_init.acpi.get_root_pointer = pvh_get_root_pointer; + pvh_bootparams.acpi_rsdp_addr = pvh_start_info.rsdp_paddr; } /* diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 6e459e47cafd..eaad22b47206 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -392,7 +392,7 @@ static void __init xen_init_capabilities(void) /* * Xen PV would need some work to support PCID: CR3 handling as well - * as xen_flush_tlb_others() would need updating. + * as xen_flush_tlb_multi() would need updating. */ setup_clear_cpu_cap(X86_FEATURE_PCID); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 3254eaa88471..c80d0058efd1 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -105,6 +105,9 @@ pte_t xen_make_pte_init(pteval_t pte); static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; #endif +static pud_t level3_ident_pgt[PTRS_PER_PUD] __page_aligned_bss; +static pmd_t level2_ident_pgt[PTRS_PER_PMD] __page_aligned_bss; + /* * Protects atomic reservation decrease/increase against concurrent increases. * Also protects non-atomic updates of current_pages and balloon lists. @@ -1777,6 +1780,12 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Zap identity mapping */ init_top_pgt[0] = __pgd(0); + init_top_pgt[pgd_index(__PAGE_OFFSET_BASE_L4)].pgd = + __pa_symbol(level3_ident_pgt) + _KERNPG_TABLE_NOENC; + init_top_pgt[pgd_index(__START_KERNEL_map)].pgd = + __pa_symbol(level3_kernel_pgt) + _PAGE_TABLE_NOENC; + level3_ident_pgt[0].pud = __pa_symbol(level2_ident_pgt) + _KERNPG_TABLE_NOENC; + /* Pre-constructed entries are in pfn, so convert to mfn */ /* L4[273] -> level3_ident_pgt */ /* L4[511] -> level3_kernel_pgt */ |