diff options
Diffstat (limited to 'arch')
41 files changed, 332 insertions, 191 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 71fc5dd4123f..73e6647bea46 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -136,7 +136,7 @@ config ARM select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RSEQ - select HAVE_RUST if CPU_LITTLE_ENDIAN && CPU_32v7 + select HAVE_RUST if CPU_LITTLE_ENDIAN && CPU_32v7 && !KASAN select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 diff --git a/arch/arm/boot/dts/gemini/gemini-sl93512r.dts b/arch/arm/boot/dts/gemini/gemini-sl93512r.dts index 4992ec276de9..341dec9b636a 100644 --- a/arch/arm/boot/dts/gemini/gemini-sl93512r.dts +++ b/arch/arm/boot/dts/gemini/gemini-sl93512r.dts @@ -146,7 +146,7 @@ partitions { compatible = "redboot-fis"; /* Eraseblock at 0xfe0000 */ - fis-index-block = <0x1fc>; + fis-index-block = <0x7f>; }; }; diff --git a/arch/arm/boot/dts/gemini/gemini-sq201.dts b/arch/arm/boot/dts/gemini/gemini-sq201.dts index f8c6f6e5cdea..bfd1e8581ad6 100644 --- a/arch/arm/boot/dts/gemini/gemini-sq201.dts +++ b/arch/arm/boot/dts/gemini/gemini-sq201.dts @@ -134,7 +134,7 @@ partitions { compatible = "redboot-fis"; /* Eraseblock at 0xfe0000 */ - fis-index-block = <0x1fc>; + fis-index-block = <0x7f>; }; }; diff --git a/arch/arm/boot/dts/microchip/sam9x7.dtsi b/arch/arm/boot/dts/microchip/sam9x7.dtsi index d242d7a934d0..c680a5033b6b 100644 --- a/arch/arm/boot/dts/microchip/sam9x7.dtsi +++ b/arch/arm/boot/dts/microchip/sam9x7.dtsi @@ -990,9 +990,9 @@ <62 IRQ_TYPE_LEVEL_HIGH 3>, /* Queue 3 */ <63 IRQ_TYPE_LEVEL_HIGH 3>, /* Queue 4 */ <64 IRQ_TYPE_LEVEL_HIGH 3>; /* Queue 5 */ - clocks = <&pmc PMC_TYPE_PERIPHERAL 24>, <&pmc PMC_TYPE_PERIPHERAL 24>, <&pmc PMC_TYPE_GCK 24>, <&pmc PMC_TYPE_GCK 67>; - clock-names = "hclk", "pclk", "tx_clk", "tsu_clk"; - assigned-clocks = <&pmc PMC_TYPE_GCK 67>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 24>, <&pmc PMC_TYPE_PERIPHERAL 24>, <&pmc PMC_TYPE_GCK 24>; + clock-names = "hclk", "pclk", "tsu_clk"; + assigned-clocks = <&pmc PMC_TYPE_GCK 24>; assigned-clock-rates = <266666666>; status = "disabled"; }; diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c index 201191cf68f3..349e6c54518e 100644 --- a/arch/arm/mach-socfpga/platsmp.c +++ b/arch/arm/mach-socfpga/platsmp.c @@ -78,6 +78,7 @@ static void __init socfpga_smp_prepare_cpus(unsigned int max_cpus) } socfpga_scu_base_addr = of_iomap(np, 0); + of_node_put(np); if (!socfpga_scu_base_addr) return; scu_enable(socfpga_scu_base_addr); diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 73a10f65ce8b..6b005c8fef70 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -63,6 +63,9 @@ else KBUILD_CFLAGS += -fasynchronous-unwind-tables KBUILD_AFLAGS += -fasynchronous-unwind-tables KBUILD_RUSTFLAGS += -Cforce-unwind-tables=y -Zuse-sync-unwind=n +# Work around rustc bug on compilers without +# https://github.com/rust-lang/rust/pull/156973. +KBUILD_RUSTFLAGS += $(if $(call rustc-min-version,109800),,-Zllvm_module_flag=uwtable:u32:2:max) endif ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) diff --git a/arch/arm64/boot/dts/qcom/eliza.dtsi b/arch/arm64/boot/dts/qcom/eliza.dtsi index 4a7a0ac40ce6..7e97361a5dc5 100644 --- a/arch/arm64/boot/dts/qcom/eliza.dtsi +++ b/arch/arm64/boot/dts/qcom/eliza.dtsi @@ -843,7 +843,11 @@ "qcom,inline-crypto-engine"; reg = <0x0 0x01d88000 0x0 0x18000>; - clocks = <&gcc GCC_UFS_PHY_ICE_CORE_CLK>; + clocks = <&gcc GCC_UFS_PHY_ICE_CORE_CLK>, + <&gcc GCC_UFS_PHY_AHB_CLK>; + clock-names = "core", + "iface"; + power-domains = <&gcc GCC_UFS_PHY_GDSC>; }; tcsr_mutex: hwlock@1f40000 { diff --git a/arch/arm64/boot/dts/qcom/glymur.dtsi b/arch/arm64/boot/dts/qcom/glymur.dtsi index f23cf81ddb77..82436984485d 100644 --- a/arch/arm64/boot/dts/qcom/glymur.dtsi +++ b/arch/arm64/boot/dts/qcom/glymur.dtsi @@ -2314,11 +2314,9 @@ clocks = <&gcc GCC_USB3_MP_PHY_AUX_CLK>, <&tcsr TCSR_USB3_0_CLKREF_EN>, - <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_USB3_MP_PHY_COM_AUX_CLK>, <&gcc GCC_USB3_MP_PHY_PIPE_0_CLK>; clock-names = "aux", - "clkref", "ref", "com_aux", "pipe"; @@ -2343,11 +2341,9 @@ clocks = <&gcc GCC_USB3_MP_PHY_AUX_CLK>, <&tcsr TCSR_USB3_1_CLKREF_EN>, - <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_USB3_MP_PHY_COM_AUX_CLK>, <&gcc GCC_USB3_MP_PHY_PIPE_1_CLK>; clock-names = "aux", - "clkref", "ref", "com_aux", "pipe"; @@ -2482,15 +2478,13 @@ reg = <0x0 0x00fde000 0x0 0x8000>; clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>, - <&rpmhcc RPMH_CXO_CLK>, + <&tcsr TCSR_USB4_1_CLKREF_EN>, <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>, - <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>, - <&tcsr TCSR_USB4_1_CLKREF_EN>; + <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; clock-names = "aux", "ref", "com_aux", - "usb3_pipe", - "clkref"; + "usb3_pipe"; power-domains = <&gcc GCC_USB_1_PHY_GDSC>; @@ -3750,15 +3744,13 @@ reg = <0x0 0x088e1000 0x0 0x8000>; clocks = <&gcc GCC_USB3_TERT_PHY_AUX_CLK>, - <&rpmhcc RPMH_CXO_CLK>, + <&tcsr TCSR_USB4_2_CLKREF_EN>, <&gcc GCC_USB3_TERT_PHY_COM_AUX_CLK>, - <&gcc GCC_USB3_TERT_PHY_PIPE_CLK>, - <&tcsr TCSR_USB4_2_CLKREF_EN>; + <&gcc GCC_USB3_TERT_PHY_PIPE_CLK>; clock-names = "aux", "ref", "com_aux", - "usb3_pipe", - "clkref"; + "usb3_pipe"; power-domains = <&gcc GCC_USB_2_PHY_GDSC>; diff --git a/arch/arm64/boot/dts/qcom/milos.dtsi b/arch/arm64/boot/dts/qcom/milos.dtsi index 4a64a98a434b..a6e463f3885d 100644 --- a/arch/arm64/boot/dts/qcom/milos.dtsi +++ b/arch/arm64/boot/dts/qcom/milos.dtsi @@ -1275,7 +1275,11 @@ "qcom,inline-crypto-engine"; reg = <0x0 0x01d88000 0x0 0x18000>; - clocks = <&gcc GCC_UFS_PHY_ICE_CORE_CLK>; + clocks = <&gcc GCC_UFS_PHY_ICE_CORE_CLK>, + <&gcc GCC_UFS_PHY_AHB_CLK>; + clock-names = "core", + "iface"; + power-domains = <&gcc UFS_PHY_GDSC>; }; tcsr_mutex: hwlock@1f40000 { diff --git a/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi b/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi index 0d9a324cc6cc..db291730130c 100644 --- a/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi +++ b/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi @@ -982,12 +982,6 @@ status = "okay"; }; -&i2c20 { - clock-frequency = <400000>; - - status = "okay"; -}; - &lpass_tlmm { spkr_01_sd_n_active: spkr-01-sd-n-active-state { pins = "gpio12"; @@ -1308,6 +1302,7 @@ &tlmm { gpio-reserved-ranges = <44 4>, /* SPI11 (TPM) */ <76 4>, /* SPI19 (TZ Protected) */ + <80 2>, /* I2C20 (Battery SMBus) */ <238 1>; /* UFS Reset */ cam_rgb_default: cam-rgb-default-state { diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index d905a0777f93..96ce783f24e7 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -260,6 +260,7 @@ CONFIG_PCI_ENDPOINT=y CONFIG_PCI_ENDPOINT_CONFIGFS=y CONFIG_PCI_EPF_TEST=m CONFIG_PCI_PWRCTRL_GENERIC=m +CONFIG_POWER_SEQUENCING_PCIE_M2=m CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_FW_LOADER_USER_HELPER=y diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index dc2957662ff2..cdf3e8422ea1 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -132,7 +132,7 @@ static inline bool kvm_s2_trans_exec_el0(struct kvm *kvm, struct kvm_s2_trans *t u8 xn = FIELD_GET(KVM_PTE_LEAF_ATTR_HI_S2_XN, trans->desc); if (!kvm_has_xnx(kvm)) - xn &= FIELD_PREP(KVM_PTE_LEAF_ATTR_HI_S2_XN, 0b10); + xn &= 0b10; switch (xn) { case 0b00: @@ -148,7 +148,7 @@ static inline bool kvm_s2_trans_exec_el1(struct kvm *kvm, struct kvm_s2_trans *t u8 xn = FIELD_GET(KVM_PTE_LEAF_ATTR_HI_S2_XN, trans->desc); if (!kvm_has_xnx(kvm)) - xn &= FIELD_PREP(KVM_PTE_LEAF_ATTR_HI_S2_XN, 0b10); + xn &= 0b10; switch (xn) { case 0b00: diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 9f8f0ae8e86e..889c2c15d7bd 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -1569,7 +1569,8 @@ int __kvm_at_s12(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) /* Do the stage-2 translation */ ipa = (par & GENMASK_ULL(47, 12)) | (vaddr & GENMASK_ULL(11, 0)); out.esr = 0; - ret = kvm_walk_nested_s2(vcpu, ipa, &out); + scoped_guard(srcu, &vcpu->kvm->srcu) + ret = kvm_walk_nested_s2(vcpu, ipa, &out); if (ret < 0) return ret; @@ -1665,7 +1666,8 @@ int __kvm_find_s1_desc_level(struct kvm_vcpu *vcpu, u64 va, u64 ipa, int *level) } /* Walk the guest's PT, looking for a match along the way */ - ret = walk_s1(vcpu, &wi, &wr, va); + scoped_guard(srcu, &vcpu->kvm->srcu) + ret = walk_s1(vcpu, &wi, &wr, va); switch (ret) { case -EINTR: /* We interrupted the walk on a match, return the level */ diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 320cd45d49c5..e9b36a3b27bb 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -181,6 +181,8 @@ static inline void __deactivate_cptr_traps_vhe(struct kvm_vcpu *vcpu) val |= CPACR_EL1_ZEN; if (cpus_have_final_cap(ARM64_SME)) val |= CPACR_EL1_SMEN; + if (cpus_have_final_cap(ARM64_HAS_S1POE)) + val |= CPACR_EL1_E0POE; write_sysreg(val, cpacr_el1); } diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 0c1defa5fb0f..91a7dfad6686 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -925,7 +925,9 @@ static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte) static bool stage2_pte_executable(kvm_pte_t pte) { - return kvm_pte_valid(pte) && !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); + enum kvm_pgtable_prot prot = kvm_pgtable_stage2_pte_prot(pte); + + return prot & (KVM_PGTABLE_PROT_UX | KVM_PGTABLE_PROT_PX); } static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 38f672e94087..6f7bc9a9992e 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -89,21 +89,28 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) * again, and there is no reason to affect the whole VM for this. */ num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU; - tmp = kvrealloc(kvm->arch.nested_mmus, - size_mul(sizeof(*kvm->arch.nested_mmus), num_mmus), - GFP_KERNEL_ACCOUNT | __GFP_ZERO); - if (!tmp) - return -ENOMEM; - swap(kvm->arch.nested_mmus, tmp); + if (num_mmus > kvm->arch.nested_mmus_size) { + tmp = kvcalloc(num_mmus, sizeof(*tmp), GFP_KERNEL_ACCOUNT); + if (!tmp) + return -ENOMEM; - /* - * If we went through a realocation, adjust the MMU back-pointers in - * the previously initialised kvm_pgtable structures. - */ - if (kvm->arch.nested_mmus != tmp) - for (int i = 0; i < kvm->arch.nested_mmus_size; i++) - kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i]; + write_lock(&kvm->mmu_lock); + + if (kvm->arch.nested_mmus_size) { + memcpy(tmp, kvm->arch.nested_mmus, + size_mul(sizeof(*tmp), kvm->arch.nested_mmus_size)); + + for (int i = 0; i < kvm->arch.nested_mmus_size; i++) + tmp[i].pgt->mmu = &tmp[i]; + } + + swap(kvm->arch.nested_mmus, tmp); + + write_unlock(&kvm->mmu_lock); + + kvfree(tmp); + } for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++) ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]); diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 1d7e5d560af4..1e3706ac3b8e 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -597,8 +597,10 @@ static void vgic_its_invalidate_cache(struct vgic_its *its) unsigned long idx; xa_for_each(&its->translation_cache, idx, irq) { - xa_erase(&its->translation_cache, idx); - vgic_put_irq(kvm, irq); + /* Only the context that erases the entry drops its cache ref. */ + irq = xa_erase(&its->translation_cache, idx); + if (irq) + vgic_put_irq(kvm, irq); } } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index dd85e093ffdb..8242f93f05e4 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1441,6 +1441,7 @@ static void free_hotplug_page_range(struct page *page, size_t size, static void free_hotplug_pgtable_page(struct page *page) { + pagetable_dtor(page_ptdesc(page)); free_hotplug_page_range(page, PAGE_SIZE, NULL); } diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h index f56966edbf5c..61ee02cee297 100644 --- a/arch/riscv/include/asm/usercfi.h +++ b/arch/riscv/include/asm/usercfi.h @@ -50,6 +50,7 @@ void set_indir_lp_status(struct task_struct *task, bool enable); void set_indir_lp_lock(struct task_struct *task, bool lock); #define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK (PR_SHADOW_STACK_ENABLE) +#define PR_CFI_SUPPORTED_STATUS_MASK (PR_CFI_ENABLE | PR_CFI_DISABLE | PR_CFI_LOCK) #else diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 793bcee46182..f336a183667e 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -413,7 +413,7 @@ static struct user_regset riscv_user_regset[] __ro_after_init = { #endif #ifdef CONFIG_RISCV_USER_CFI [REGSET_CFI] = { - .core_note_type = NT_RISCV_USER_CFI, + USER_REGSET_NOTE_TYPE(RISCV_USER_CFI), .align = sizeof(__u64), .n = sizeof(struct user_cfi_state) / sizeof(__u64), .size = sizeof(__u64), diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index 485ab1d105d3..11c781a4de73 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -235,17 +235,6 @@ static void set_unaligned_access_static_branches(void) modify_unaligned_access_branches(&fast_and_online, num_online_cpus()); } -static int __init lock_and_set_unaligned_access_static_branch(void) -{ - cpus_read_lock(); - set_unaligned_access_static_branches(); - cpus_read_unlock(); - - return 0; -} - -arch_initcall_sync(lock_and_set_unaligned_access_static_branch); - static int riscv_online_cpu(unsigned int cpu) { int ret = cpu_online_unaligned_access_init(cpu); @@ -440,6 +429,10 @@ static int __init check_unaligned_access_all_cpus(void) cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", riscv_online_cpu_vec, NULL); + cpus_read_lock(); + set_unaligned_access_static_branches(); + cpus_read_unlock(); + return 0; } diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index cbfb4e495e9f..5a7113d69bad 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -467,6 +467,9 @@ int arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long if (!is_user_lpad_enabled()) return -EINVAL; + if (state & ~PR_CFI_SUPPORTED_STATUS_MASK) + return -EINVAL; + /* indirect branch tracking is locked and further can't be modified by user */ if (is_indir_lp_locked(t)) return -EINVAL; diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index c28f9a7d0bd8..730c90b4a876 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -56,6 +56,10 @@ CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m +CONFIG_VFIO_DEVICE_CDEV=y +CONFIG_IOMMUFD_DRIVER=y +CONFIG_IOMMUFD_DRIVER_CORE=y +CONFIG_IOMMUFD=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_S390_HYPFS_FS=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index d89c988f33ea..dd5fc1426c88 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -54,6 +54,10 @@ CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m +CONFIG_VFIO_DEVICE_CDEV=y +CONFIG_IOMMUFD_DRIVER=y +CONFIG_IOMMUFD_DRIVER_CORE=y +CONFIG_IOMMUFD=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_S390_HYPFS_FS=y diff --git a/arch/s390/crypto/Kconfig b/arch/s390/crypto/Kconfig index 00051d27db95..228570a1b233 100644 --- a/arch/s390/crypto/Kconfig +++ b/arch/s390/crypto/Kconfig @@ -4,6 +4,7 @@ menu "Accelerated Cryptographic Algorithms for CPU (s390)" config CRYPTO_AES_S390 tristate "Ciphers: AES, modes: ECB, CBC, CTR, XTS, GCM" + select CRYPTO_AEAD select CRYPTO_SKCIPHER help AEAD cipher: AES with GCM diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 59017fd3d935..50a270edb020 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -12,12 +12,11 @@ #if defined(CONFIG_BUG) && defined(CONFIG_CC_HAS_ASM_IMMEDIATE_STRINGS) #ifdef CONFIG_DEBUG_BUGVERBOSE -#define __BUG_ENTRY_VERBOSE(format, file, line) \ - " .long " format " - . # bug_entry::format\n" \ +#define __BUG_ENTRY_VERBOSE(file, line) \ " .long " file " - . # bug_entry::file\n" \ " .short " line " # bug_entry::line\n" #else -#define __BUG_ENTRY_VERBOSE(format, file, line) +#define __BUG_ENTRY_VERBOSE(file, line) #endif #ifdef CONFIG_DEBUG_BUGVERBOSE_DETAILED @@ -28,9 +27,10 @@ #define __BUG_ENTRY(format, file, line, flags, size) \ " .section __bug_table,\"aw\"\n" \ - "1: .long 0b - . # bug_entry::bug_addr\n" \ - __BUG_ENTRY_VERBOSE(format, file, line) \ - " .short "flags" # bug_entry::flags\n" \ + "1: .long 0b - . # bug_entry::bug_addr\n"\ + " .long " format " - . # bug_entry::format\n" \ + __BUG_ENTRY_VERBOSE(file, line) \ + " .short "flags" # bug_entry::flags\n" \ " .org 1b+"size"\n" \ " .previous" diff --git a/arch/s390/include/asm/gmap_helpers.h b/arch/s390/include/asm/gmap_helpers.h index 2d3ae421077e..d2b616604a46 100644 --- a/arch/s390/include/asm/gmap_helpers.h +++ b/arch/s390/include/asm/gmap_helpers.h @@ -12,5 +12,6 @@ void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr); void gmap_helper_discard(struct mm_struct *mm, unsigned long vmaddr, unsigned long end); int gmap_helper_disable_cow_sharing(void); void gmap_helper_try_set_pte_unused(struct mm_struct *mm, unsigned long vmaddr); +pte_t *try_get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); #endif /* _ASM_S390_GMAP_HELPERS_H */ diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h index df3fb7d8227b..1b3ac553a642 100644 --- a/arch/s390/include/asm/linkage.h +++ b/arch/s390/include/asm/linkage.h @@ -7,4 +7,6 @@ #define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT, 0x07 #define __ALIGN_STR __stringify(__ALIGN) +#define _THIS_IP_ ({ unsigned long __ip; asm volatile("larl %0, ." : "=d" (__ip)); __ip; }) + #endif diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index 4a41c0247ffa..a4fe664f65ee 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -45,7 +45,7 @@ int kvm_s390_mmu_cache_topup(struct kvm_s390_mmu_cache *mc) mc->pts[mc->n_pts] = o; } for ( ; mc->n_rmaps < KVM_S390_MMU_CACHE_N_RMAPS; mc->n_rmaps++) { - o = kzalloc_obj(*mc->rmaps[0], GFP_KERNEL_ACCOUNT); + o = kzalloc_obj(struct vsie_rmap, GFP_KERNEL_ACCOUNT); if (!o) return -ENOMEM; mc->rmaps[mc->n_rmaps] = o; diff --git a/arch/s390/kvm/faultin.c b/arch/s390/kvm/faultin.c index ddf0ca71f374..fee80047bd94 100644 --- a/arch/s390/kvm/faultin.c +++ b/arch/s390/kvm/faultin.c @@ -36,7 +36,8 @@ int kvm_s390_faultin_gfn(struct kvm_vcpu *vcpu, struct kvm *kvm, struct guest_fa struct kvm_s390_mmu_cache *mc = NULL; struct kvm_memory_slot *slot; unsigned long inv_seq; - int foll, rc = 0; + int rc = -EAGAIN; + int foll; foll = f->write_attempt ? FOLL_WRITE : 0; foll |= f->attempt_pfault ? FOLL_NOWAIT : 0; @@ -53,7 +54,14 @@ int kvm_s390_faultin_gfn(struct kvm_vcpu *vcpu, struct kvm *kvm, struct guest_fa return 0; } - while (1) { + if (!mc) { + local_mc = kvm_s390_new_mmu_cache(); + if (!local_mc) + return -ENOMEM; + mc = local_mc; + } + + while (rc == -EAGAIN) { f->valid = false; inv_seq = kvm->mmu_invalidate_seq; /* Pairs with the smp_wmb() in kvm_mmu_invalidate_end(). */ @@ -93,14 +101,7 @@ int kvm_s390_faultin_gfn(struct kvm_vcpu *vcpu, struct kvm *kvm, struct guest_fa if (is_error_pfn(f->pfn)) return -EFAULT; - if (!mc) { - local_mc = kvm_s390_new_mmu_cache(); - if (!local_mc) - return -ENOMEM; - mc = local_mc; - } - - /* Loop, will automatically release the faulted page. */ + /* Loop, release the faulted page. */ if (mmu_invalidate_retry_gfn_unsafe(kvm, inv_seq, f->gfn)) { kvm_release_faultin_page(kvm, f->page, true, false); continue; @@ -110,20 +111,19 @@ int kvm_s390_faultin_gfn(struct kvm_vcpu *vcpu, struct kvm *kvm, struct guest_fa if (!mmu_invalidate_retry_gfn(kvm, inv_seq, f->gfn)) { f->valid = true; rc = gmap_link(mc, kvm->arch.gmap, f, slot); - kvm_release_faultin_page(kvm, f->page, !!rc, f->write_attempt); - f->page = NULL; } + kvm_release_faultin_page(kvm, f->page, !!rc, f->write_attempt); } - kvm_release_faultin_page(kvm, f->page, true, false); if (rc == -ENOMEM) { rc = kvm_s390_mmu_cache_topup(mc); if (rc) return rc; - } else if (rc != -EAGAIN) { - return rc; + rc = -EAGAIN; } } + + return rc; } int kvm_s390_get_guest_page(struct kvm *kvm, struct guest_fault *f, gfn_t gfn, bool w) diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 4f8d5592c9a9..36102b2727fb 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1419,8 +1419,8 @@ edat_applies: return kvm_s390_get_guest_page(kvm, entries + LEVEL_MEM, table.pte.pfra, wr); } -static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union pte *ptep, - struct guest_fault *f, bool p) +static int _do_shadow_pte(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gpa_t raddr, + union pte *ptep_h, union pte *ptep, struct guest_fault *f, bool p) { union pgste pgste; union pte newpte; @@ -1430,7 +1430,7 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union lockdep_assert_held(&sg->parent->children_lock); scoped_guard(spinlock, &sg->host_to_rmap_lock) - rc = gmap_insert_rmap(sg, f->gfn, gpa_to_gfn(raddr), TABLE_TYPE_PAGE_TABLE); + rc = gmap_insert_rmap(mc, sg, f->gfn, gpa_to_gfn(raddr), TABLE_TYPE_PAGE_TABLE); if (rc) return rc; @@ -1462,19 +1462,21 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union return 0; } -static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, union crste *table, - struct guest_fault *f, bool p) +static int _do_shadow_crste(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gpa_t raddr, + union crste *host, union crste *table, struct guest_fault *f, bool p) { union crste newcrste, oldcrste; - gfn_t gfn; + unsigned long mask; + gfn_t r_gfn; int rc; lockdep_assert_held(&sg->kvm->mmu_lock); lockdep_assert_held(&sg->parent->children_lock); - gfn = f->gfn & (is_pmd(*table) ? _SEGMENT_FR_MASK : _REGION3_FR_MASK); + mask = is_pmd(*table) ? _SEGMENT_FR_MASK : _REGION3_FR_MASK; + r_gfn = gpa_to_gfn(raddr) & mask; scoped_guard(spinlock, &sg->host_to_rmap_lock) - rc = gmap_insert_rmap(sg, gfn, gpa_to_gfn(raddr), host->h.tt); + rc = gmap_insert_rmap(mc, sg, f->gfn & mask, r_gfn, host->h.tt); if (rc) return rc; @@ -1497,8 +1499,7 @@ static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, uni return -EAGAIN; newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, 0, !p); - gfn = gpa_to_gfn(raddr); - while (!dat_crstep_xchg_atomic(table, READ_ONCE(*table), newcrste, gfn, sg->asce)) + while (!dat_crstep_xchg_atomic(table, READ_ONCE(*table), newcrste, r_gfn, sg->asce)) ; return 0; } @@ -1577,39 +1578,52 @@ real_address_space: if (KVM_BUG_ON(l > TABLE_TYPE_REGION3, sg->kvm)) return -EFAULT; if (l == TABLE_TYPE_PAGE_TABLE) - return _do_shadow_pte(sg, saddr, ptep_h, ptep, entries + LEVEL_MEM, w->p); - return _do_shadow_crste(sg, saddr, host, table, entries + LEVEL_MEM, w->p); + return _do_shadow_pte(mc, sg, saddr, ptep_h, ptep, entries + LEVEL_MEM, w->p); + return _do_shadow_crste(mc, sg, saddr, host, table, entries + LEVEL_MEM, w->p); } -static inline int _gaccess_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, gpa_t saddr, - unsigned long seq, struct pgtwalk *walk) +static inline int ___gaccess_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, gpa_t saddr, + unsigned long seq, struct pgtwalk *walk) { struct gmap *parent; int rc; - if (kvm_s390_array_needs_retry_unsafe(vcpu->kvm, seq, walk->raw_entries)) + if (kvm_s390_array_needs_retry_safe(vcpu->kvm, seq, walk->raw_entries)) return -EAGAIN; -again: - rc = kvm_s390_mmu_cache_topup(vcpu->arch.mc); - if (rc) - return rc; - scoped_guard(read_lock, &vcpu->kvm->mmu_lock) { - if (kvm_s390_array_needs_retry_safe(vcpu->kvm, seq, walk->raw_entries)) - return -EAGAIN; - parent = READ_ONCE(sg->parent); - if (!parent) + parent = READ_ONCE(sg->parent); + if (!parent) + return -EAGAIN; + scoped_guard(spinlock, &parent->children_lock) { + if (READ_ONCE(sg->parent) != parent) return -EAGAIN; - scoped_guard(spinlock, &parent->children_lock) { - if (READ_ONCE(sg->parent) != parent) - return -EAGAIN; - sg->invalidated = false; - rc = _gaccess_do_shadow(vcpu->arch.mc, sg, saddr, walk); - } - if (rc == -ENOMEM) - goto again; - if (!rc) - kvm_s390_release_faultin_array(vcpu->kvm, walk->raw_entries, false); + sg->invalidated = false; + rc = _gaccess_do_shadow(vcpu->arch.mc, sg, saddr, walk); } + if (!rc) + kvm_s390_release_faultin_array(vcpu->kvm, walk->raw_entries, false); + return rc; +} + +static inline int _gaccess_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, gpa_t saddr, + unsigned long seq, struct pgtwalk *walk) +{ + int rc; + + if (kvm_s390_array_needs_retry_unsafe(vcpu->kvm, seq, walk->raw_entries)) + return -EAGAIN; + + do { + rc = kvm_s390_mmu_cache_topup(vcpu->arch.mc); + if (rc) + return rc; + rc = radix_tree_preload(GFP_KERNEL); + if (rc) + return rc; + scoped_guard(read_lock, &vcpu->kvm->mmu_lock) + rc = ___gaccess_shadow_fault(vcpu, sg, saddr, seq, walk); + radix_tree_preload_end(); + } while (rc == -ENOMEM); + return rc; } diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c index 957126ab991c..1d289f8fa3b2 100644 --- a/arch/s390/kvm/gmap.c +++ b/arch/s390/kvm/gmap.c @@ -395,15 +395,28 @@ static long _gmap_unmap_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct struct gmap_unmap_priv *priv = walk->priv; struct folio *folio = NULL; union crste old = *crstep; + bool ok; if (!old.h.fc) return 0; if (old.s.fc1.pr && test_bit(GMAP_FLAG_EXPORT_ON_UNMAP, &priv->gmap->flags)) folio = phys_to_folio(crste_origin_large(old)); - /* No races should happen because kvm->mmu_lock is held in write mode */ - KVM_BUG_ON(!gmap_crstep_xchg_atomic(priv->gmap, crstep, old, _CRSTE_EMPTY(old.h.tt), gfn), - priv->gmap->kvm); + /* + * No races should happen because kvm->mmu_lock is held in write mode, + * but the unmap operation could have triggered an unshadow, which + * causes gmap_crstep_xchg_atomic() to return false and clear the + * vsie_notif bit. Allow the operation to fail once, if the old crste + * had the vsie_notif bit set. A second failure is not allowed, for + * the reasons above. + */ + ok = gmap_crstep_xchg_atomic(priv->gmap, crstep, old, _CRSTE_EMPTY(old.h.tt), gfn); + if (!ok) { + KVM_BUG_ON(!old.s.fc1.vsie_notif, priv->gmap->kvm); + old.s.fc1.vsie_notif = 0; + ok = gmap_crstep_xchg_atomic(priv->gmap, crstep, old, _CRSTE_EMPTY(old.h.tt), gfn); + KVM_BUG_ON(!ok, priv->gmap->kvm); + } if (folio) uv_convert_from_secure_folio(folio); @@ -987,7 +1000,8 @@ int gmap_pv_destroy_range(struct gmap *gmap, gfn_t start, gfn_t end, bool interr return 0; } -int gmap_insert_rmap(struct gmap *sg, gfn_t p_gfn, gfn_t r_gfn, int level) +int gmap_insert_rmap(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gfn_t p_gfn, + gfn_t r_gfn, int level) { struct vsie_rmap *rmap __free(kvfree) = NULL; struct vsie_rmap *temp; @@ -997,7 +1011,7 @@ int gmap_insert_rmap(struct gmap *sg, gfn_t p_gfn, gfn_t r_gfn, int level) KVM_BUG_ON(!is_shadow(sg), sg->kvm); lockdep_assert_held(&sg->host_to_rmap_lock); - rmap = kzalloc_obj(*rmap, GFP_ATOMIC); + rmap = kvm_s390_mmu_cache_alloc_rmap(mc); if (!rmap) return -ENOMEM; @@ -1044,7 +1058,7 @@ int gmap_protect_rmap(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gfn_t p_gf if (level <= TABLE_TYPE_REGION1) { bitmask = -1UL << (8 + 11 * level); scoped_guard(spinlock, &sg->host_to_rmap_lock) - rc = gmap_insert_rmap(sg, p_gfn, r_gfn & bitmask, level); + rc = gmap_insert_rmap(mc, sg, p_gfn, r_gfn & bitmask, level); } if (rc) return rc; diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h index 742e42a31744..1c040472f56d 100644 --- a/arch/s390/kvm/gmap.h +++ b/arch/s390/kvm/gmap.h @@ -100,7 +100,8 @@ int gmap_ucas_map(struct gmap *gmap, gfn_t p_gfn, gfn_t c_gfn, unsigned long cou void gmap_ucas_unmap(struct gmap *gmap, gfn_t c_gfn, unsigned long count); int gmap_enable_skeys(struct gmap *gmap); int gmap_pv_destroy_range(struct gmap *gmap, gfn_t start, gfn_t end, bool interruptible); -int gmap_insert_rmap(struct gmap *sg, gfn_t p_gfn, gfn_t r_gfn, int level); +int gmap_insert_rmap(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gfn_t p_gfn, + gfn_t r_gfn, int level); int gmap_protect_rmap(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gfn_t p_gfn, gfn_t r_gfn, kvm_pfn_t pfn, int level, bool wr); void gmap_set_cmma_all_dirty(struct gmap *gmap); @@ -273,11 +274,23 @@ static inline bool __must_check _gmap_crstep_xchg_atomic(struct gmap *gmap, unio gmap_unmap_prefix(gmap, gfn, gfn + align); } if (crste_leaf(oldcrste) && crste_needs_unshadow(oldcrste, newcrste)) { + newcrste = oldcrste; newcrste.s.fc1.vsie_notif = 0; if (needs_lock) gmap_handle_vsie_unshadow_event(gmap, gfn); else _gmap_handle_vsie_unshadow_event(gmap, gfn); + if (!dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, gfn, gmap->asce)) + return false; + /* + * Return false even if the swap was successful, as it only + * indicates that the best effort clearing of the vsie_notif + * bit was successful. The caller will have to try again + * regardless, since the desired value has not been set. + * This pointless check is needed to silence a potential + * __must_check warning. + */ + return false; } if (!oldcrste.s.fc1.d && newcrste.s.fc1.d && !newcrste.s.fc1.s) SetPageDirty(phys_to_page(crste_origin_large(newcrste))); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index e09960c2e6ed..ffb20a64d328 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -999,7 +999,10 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att break; } case KVM_S390_VM_MEM_LIMIT_SIZE: { + struct kvm_memslots *slots; + struct kvm_memory_slot *ms; unsigned long new_limit; + int bkt; if (kvm_is_ucontrol(kvm)) return -EINVAL; @@ -1007,6 +1010,9 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att if (get_user(new_limit, (u64 __user *)attr->addr)) return -EFAULT; + guard(mutex)(&kvm->lock); + + new_limit = ALIGN(new_limit, HPAGE_SIZE); if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT && new_limit > kvm->arch.mem_limit) return -E2BIG; @@ -1014,12 +1020,27 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att if (!new_limit) return -EINVAL; - ret = -EBUSY; - if (!kvm->created_vcpus) - ret = gmap_set_limit(kvm->arch.gmap, gpa_to_gfn(new_limit)); + if (kvm->created_vcpus) + return -EBUSY; + + ret = 0; + scoped_guard(mutex, &kvm->slots_lock) { + slots = kvm_memslots(kvm); + if (slots && !kvm_memslots_empty(slots)) { + kvm_for_each_memslot(ms, bkt, slots) { + if (gpa_to_gfn(new_limit) < ms->base_gfn + ms->npages) { + ret = -EBUSY; + break; + } + } + } + if (!ret) + ret = gmap_set_limit(kvm->arch.gmap, gpa_to_gfn(new_limit)); + } + if (ret) + break; VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit); - VM_EVENT(kvm, 3, "New guest asce: 0x%p", - (void *)kvm->arch.gmap->asce.val); + VM_EVENT(kvm, 3, "New guest asce: 0x%p", (void *)kvm->arch.gmap->asce.val); break; } default: @@ -5672,6 +5693,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, return -EINVAL; if ((new->base_gfn + new->npages) * PAGE_SIZE > kvm->arch.mem_limit) return -EINVAL; + if (!asce_contains_gfn(kvm->arch.gmap->asce, new->base_gfn + new->npages - 1)) + return -EINVAL; } if (!kvm->arch.migration_mode) diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index cc0553da14cb..447ec7ed423d 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -1188,6 +1188,7 @@ static void _essa_clear_cbrl(struct kvm_vcpu *vcpu, unsigned long *cbrl, int len union crste *crstep; union pgste pgste; union pte *ptep; + hva_t hva; int i; lockdep_assert_held(&vcpu->kvm->mmu_lock); @@ -1199,8 +1200,11 @@ static void _essa_clear_cbrl(struct kvm_vcpu *vcpu, unsigned long *cbrl, int len if (!ptep || ptep->s.pr) continue; pgste = pgste_get_lock(ptep); - if (pgste.usage == PGSTE_GPS_USAGE_UNUSED || pgste.zero) - gmap_helper_zap_one_page(vcpu->kvm->mm, cbrl[i]); + if (pgste.usage == PGSTE_GPS_USAGE_UNUSED || pgste.zero) { + hva = gpa_to_hva(vcpu->kvm, cbrl[i]); + if (!kvm_is_error_hva(hva)) + gmap_helper_zap_one_page(vcpu->kvm->mm, hva); + } pgste_set_unlock(ptep, pgste); } } diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index c2dafd812a3b..4b865e75351c 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -17,6 +17,7 @@ #include <linux/pagewalk.h> #include <linux/sched/mm.h> #include <linux/mmu_notifier.h> +#include <asm/gmap_helpers.h> #include "kvm-s390.h" #include "dat.h" #include "gaccess.h" @@ -73,6 +74,7 @@ static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_str struct pv_make_secure { void *uvcb; struct folio *folio; + struct kvm *kvm; int rc; bool needs_export; }; @@ -103,9 +105,21 @@ static void _kvm_s390_pv_make_secure(struct guest_fault *f) { struct pv_make_secure *priv = f->priv; struct folio *folio; + spinlock_t *ptl; /* pte lock from try_get_locked_pte() */ + pte_t *ptep; folio = pfn_folio(f->pfn); priv->rc = -EAGAIN; + + if (!mmap_read_trylock(priv->kvm->mm)) + return; + + ptep = try_get_locked_pte(priv->kvm->mm, gfn_to_hva(priv->kvm, f->gfn), &ptl); + if (IS_ERR_VALUE(ptep)) { + priv->rc = PTR_ERR(ptep); + goto out; + } + if (folio_trylock(folio)) { priv->rc = __kvm_s390_pv_make_secure(f, folio); if (priv->rc == -E2BIG || priv->rc == -EBUSY) { @@ -114,6 +128,11 @@ static void _kvm_s390_pv_make_secure(struct guest_fault *f) } folio_unlock(folio); } + + if (ptep) + pte_unmap_unlock(ptep, ptl); +out: + mmap_read_unlock(priv->kvm->mm); } /** @@ -127,7 +146,7 @@ static void _kvm_s390_pv_make_secure(struct guest_fault *f) */ int kvm_s390_pv_make_secure(struct kvm *kvm, unsigned long gaddr, void *uvcb) { - struct pv_make_secure priv = { .uvcb = uvcb }; + struct pv_make_secure priv = { .uvcb = uvcb, .kvm = kvm, }; struct guest_fault f = { .write_attempt = true, .gfn = gpa_to_gfn(gaddr), diff --git a/arch/s390/mm/gmap_helpers.c b/arch/s390/mm/gmap_helpers.c index f8789ffcc05c..ee3f37af8aee 100644 --- a/arch/s390/mm/gmap_helpers.c +++ b/arch/s390/mm/gmap_helpers.c @@ -17,22 +17,68 @@ #include <asm/gmap_helpers.h> /** - * ptep_zap_softleaf_entry() - discard a software leaf entry. + * try_get_locked_pte() - like get_locked_pte(), but atomic and with trylock * @mm: the mm - * @entry: the software leaf entry that needs to be zapped + * @vmaddr: the userspace virtual address whose pte is to be found + * @ptl: will be set to the pointer to the lock used to lock the pte in case + * of success. * - * Discards the given software leaf entry. If the leaf entry was an actual - * swap entry (and not a migration entry, for example), the actual swapped - * page is also discarded from swap. + * This function returns the pointer to the pte corresponding to @addr in @mm, + * similarly to get_locked_pte(). Unlike get_locked_pte(), no attempt is made + * to allocate missing page tables. If a missing or large entry is found, the + * function will return NULL. If the ptl lock is contended, %-EAGAIN is + * returned. + * + * In case of success, *@ptl will point to the locked pte lock for the returned + * pte, like get_locked_pte() does. + * + * Context: mmap_lock or vma lock for read or for write needs to be held. + * Return: + * * %NULL if the pte cannot be reached. + * * %-EAGAIN if the pte can be reached, but cannot be locked. + * * the pointer to the pte corresponding to @addr in @mm, if it can be reached + * and locked. */ -static void ptep_zap_softleaf_entry(struct mm_struct *mm, softleaf_t entry) +pte_t *try_get_locked_pte(struct mm_struct *mm, unsigned long vmaddr, spinlock_t **ptl) { - if (softleaf_is_swap(entry)) - dec_mm_counter(mm, MM_SWAPENTS); - else if (softleaf_is_migration(entry)) - dec_mm_counter(mm, mm_counter(softleaf_to_folio(entry))); - swap_put_entries_direct(entry, 1); + pmd_t *pmdp, pmd, pmdval; + pud_t *pudp, pud; + p4d_t *p4dp, p4d; + pgd_t *pgdp, pgd; + pte_t *ptep; + + pgdp = pgd_offset(mm, vmaddr); + pgd = pgdp_get(pgdp); + if (pgd_none(pgd) || !pgd_present(pgd)) + return NULL; + p4dp = p4d_offset_lockless(pgdp, pgd, vmaddr); + p4d = p4dp_get(p4dp); + if (p4d_none(p4d) || !p4d_present(p4d)) + return NULL; + pudp = pud_offset_lockless(p4dp, p4d, vmaddr); + pud = pudp_get(pudp); + if (pud_none(pud) || pud_leaf(pud) || !pud_present(pud)) + return NULL; + pmdp = pmd_offset_lockless(pudp, pud, vmaddr); + pmd = pmdp_get_lockless(pmdp); + if (pmd_none(pmd) || pmd_leaf(pmd) || !pmd_present(pmd)) + return NULL; + ptep = pte_offset_map_rw_nolock(mm, pmdp, vmaddr, &pmdval, ptl); + if (!ptep) + return NULL; + + if (spin_trylock(*ptl)) { + if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmdp)))) { + pte_unmap_unlock(ptep, *ptl); + return ERR_PTR(-EAGAIN); + } + return ptep; + } + + pte_unmap(ptep); + return ERR_PTR(-EAGAIN); } +EXPORT_SYMBOL_GPL(try_get_locked_pte); /** * gmap_helper_zap_one_page() - discard a page if it was swapped. @@ -46,7 +92,8 @@ static void ptep_zap_softleaf_entry(struct mm_struct *mm, softleaf_t entry) void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr) { struct vm_area_struct *vma; - spinlock_t *ptl; + spinlock_t *ptl; /* Lock for the host (userspace) page table */ + softleaf_t sl; pte_t *ptep; mmap_assert_locked(mm); @@ -57,11 +104,13 @@ void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr) return; /* Get pointer to the page table entry */ - ptep = get_locked_pte(mm, vmaddr, &ptl); - if (unlikely(!ptep)) + ptep = try_get_locked_pte(mm, vmaddr, &ptl); + if (IS_ERR_OR_NULL(ptep)) return; - if (pte_swap(*ptep)) { - ptep_zap_softleaf_entry(mm, softleaf_from_pte(*ptep)); + sl = softleaf_from_pte(*ptep); + if (pte_swap(*ptep) && softleaf_is_swap(sl)) { + dec_mm_counter(mm, MM_SWAPENTS); + swap_put_entries_direct(sl, 1); pte_clear(mm, vmaddr, ptep); } pte_unmap_unlock(ptep, ptl); @@ -113,37 +162,9 @@ EXPORT_SYMBOL_GPL(gmap_helper_discard); */ void gmap_helper_try_set_pte_unused(struct mm_struct *mm, unsigned long vmaddr) { - pmd_t *pmdp, pmd, pmdval; - pud_t *pudp, pud; - p4d_t *p4dp, p4d; - pgd_t *pgdp, pgd; spinlock_t *ptl; /* Lock for the host (userspace) page table */ pte_t *ptep; - pgdp = pgd_offset(mm, vmaddr); - pgd = pgdp_get(pgdp); - if (pgd_none(pgd) || !pgd_present(pgd)) - return; - - p4dp = p4d_offset(pgdp, vmaddr); - p4d = p4dp_get(p4dp); - if (p4d_none(p4d) || !p4d_present(p4d)) - return; - - pudp = pud_offset(p4dp, vmaddr); - pud = pudp_get(pudp); - if (pud_none(pud) || pud_leaf(pud) || !pud_present(pud)) - return; - - pmdp = pmd_offset(pudp, vmaddr); - pmd = pmdp_get_lockless(pmdp); - if (pmd_none(pmd) || pmd_leaf(pmd) || !pmd_present(pmd)) - return; - - ptep = pte_offset_map_rw_nolock(mm, pmdp, vmaddr, &pmdval, &ptl); - if (!ptep) - return; - /* * Several paths exists that takes the ptl lock and then call the * mmu_notifier, which takes the mmu_lock. The unmap path, instead, @@ -156,21 +177,12 @@ void gmap_helper_try_set_pte_unused(struct mm_struct *mm, unsigned long vmaddr) * If the lock is contended the bit is not set and the deadlock is * avoided. */ - if (spin_trylock(ptl)) { - /* - * Make sure the pte we are touching is still the correct - * one. In theory this check should not be needed, but - * better safe than sorry. - * Disabling interrupts or holding the mmap lock is enough to - * guarantee that no concurrent updates to the page tables - * are possible. - */ - if (likely(pmd_same(pmdval, pmdp_get_lockless(pmdp)))) - __atomic64_or(_PAGE_UNUSED, (long *)ptep); - spin_unlock(ptl); - } + ptep = try_get_locked_pte(mm, vmaddr, &ptl); + if (IS_ERR_OR_NULL(ptep)) + return; - pte_unmap(ptep); + __atomic64_or(_PAGE_UNUSED, (long *)ptep); + pte_unmap_unlock(ptep, ptl); } EXPORT_SYMBOL_GPL(gmap_helper_try_set_pte_unused); diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 46fec0b08487..1d526a5d2a83 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -77,6 +77,10 @@ KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx -mno-sse4a KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 +# The target.json file is not available when invoking rustc-option, so use the +# built-in target when checking whether flags are supported instead. +KBUILD_RUSTFLAGS_OPTION_CHKS += --target=x86_64-unknown-none + # # CFLAGS for compiling floating point code inside the kernel. # diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index 19c13afa474e..9adecd65639f 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -14,6 +14,14 @@ endif KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json +# The target.json file is not available when invoking rustc-option, so use the +# built-in target when checking whether flags are supported instead. +ifeq ($(CONFIG_X86_32),y) +KBUILD_RUSTFLAGS_OPTION_CHKS += --target=i686-unknown-linux-gnu +else +KBUILD_RUSTFLAGS_OPTION_CHKS += --target=x86_64-unknown-linux-gnu +endif + ifeq ($(CONFIG_X86_32),y) START := 0x8048000 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2f8e8ff2d000..31f01e9c7114 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -518,7 +518,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) break; case 0x50 ... 0x5f: case 0x80 ... 0xaf: - case 0xc0 ... 0xcf: + case 0xc0 ... 0xef: setup_force_cpu_cap(X86_FEATURE_ZEN6); break; default: diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 9bd87bae4983..59215fef3924 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -377,7 +377,12 @@ static const struct x86_cpu_id snc_cpu_ids[] __initconst = { static __init int snc_get_config(void) { - int ret = topology_num_nodes_per_package(); + int ret; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 1; + + ret = topology_num_nodes_per_package(); if (ret > 1 && !x86_match_cpu(snc_cpu_ids)) { pr_warn("CoD enabled system? Resctrl not supported\n"); |