diff options
Diffstat (limited to 'arch/x86')
27 files changed, 364 insertions, 177 deletions
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 8c8d38f0cb1d..003379049924 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -6,6 +6,9 @@ #include <linux/export.h> #include <linux/linkage.h> #include <asm/msr-index.h> +#include <asm/unwind_hints.h> +#include <asm/segment.h> +#include <asm/cache.h> .pushsection .noinstr.text, "ax" @@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb) EXPORT_SYMBOL_GPL(entry_ibpb); .popsection + +/* + * Define the VERW operand that is disguised as entry code so that + * it can be referenced with KPTI enabled. This ensure VERW can be + * used late in exit-to-user path after page tables are switched. + */ +.pushsection .entry.text, "ax" + +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_START_NOALIGN(mds_verw_sel) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + .word __KERNEL_DS +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_END(mds_verw_sel); +/* For KVM */ +EXPORT_SYMBOL_GPL(mds_verw_sel); + +.popsection + diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index c73047bf9f4b..fba427646805 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -885,6 +885,7 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax + CLEAR_CPU_BUFFERS /* * Return back to the vDSO, which will pop ecx and edx. @@ -954,6 +955,7 @@ restore_all_switch_stack: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code + CLEAR_CPU_BUFFERS .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -1146,6 +1148,7 @@ SYM_CODE_START(asm_exc_nmi) /* Not on SYSENTER stack. */ call exc_nmi + CLEAR_CPU_BUFFERS jmp .Lnmi_return .Lnmi_from_sysenter_stack: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index c40f89ab1b4c..9bb485977629 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -161,6 +161,7 @@ syscall_return_via_sysret: SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL) ANNOTATE_NOENDBR swapgs + CLEAR_CPU_BUFFERS sysretq SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR @@ -573,6 +574,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) .Lswapgs_and_iret: swapgs + CLEAR_CPU_BUFFERS /* Assert that the IRET frame indicates user mode. */ testb $3, 8(%rsp) jnz .Lnative_iret @@ -723,6 +725,8 @@ native_irq_return_ldt: */ popq %rax /* Restore user RAX */ + CLEAR_CPU_BUFFERS + /* * RSP now points to an ordinary IRET frame, except that the page * is read-only and RSP[31:16] are preloaded with the userspace @@ -1450,6 +1454,12 @@ nmi_restore: movq $0, 5*8(%rsp) /* clear "NMI executing" */ /* + * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like + * NMI in kernel after user state is restored. For an unprivileged user + * these conditions are hard to meet. + */ + + /* * iretq reads the "iret" frame and exits the NMI stack in a * single instruction. We are returning to kernel mode, so this * cannot result in a fault. Similarly, we don't need to worry @@ -1466,6 +1476,7 @@ SYM_CODE_START(entry_SYSCALL32_ignore) UNWIND_HINT_END_OF_STACK ENDBR mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(entry_SYSCALL32_ignore) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index de94e2e84ecc..eabf48c4d4b4 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -270,6 +270,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL) xorl %r9d, %r9d xorl %r10d, %r10d swapgs + CLEAR_CPU_BUFFERS sysretl SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 96e6c51515f5..cf1b78cb2d04 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -16,6 +16,11 @@ extern struct boot_params boot_params; static struct real_mode_header hv_vtl_real_mode_header; +static bool __init hv_vtl_msi_ext_dest_id(void) +{ + return true; +} + void __init hv_vtl_init_platform(void) { pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); @@ -38,6 +43,8 @@ void __init hv_vtl_init_platform(void) x86_platform.legacy.warm_reset = 0; x86_platform.legacy.reserve_bios_regions = 0; x86_platform.legacy.devices.pnpbios = 0; + + x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id; } static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc) diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 7dcbf153ad72..768d73de0d09 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -15,6 +15,7 @@ #include <asm/io.h> #include <asm/coco.h> #include <asm/mem_encrypt.h> +#include <asm/set_memory.h> #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/mtrr.h> @@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[], } /* + * When transitioning memory between encrypted and decrypted, the caller + * of set_memory_encrypted() or set_memory_decrypted() is responsible for + * ensuring that the memory isn't in use and isn't referenced while the + * transition is in progress. The transition has multiple steps, and the + * memory is in an inconsistent state until all steps are complete. A + * reference while the state is inconsistent could result in an exception + * that can't be cleanly fixed up. + * + * But the Linux kernel load_unaligned_zeropad() mechanism could cause a + * stray reference that can't be prevented by the caller, so Linux has + * specific code to handle this case. But when the #VC and #VE exceptions + * routed to a paravisor, the specific code doesn't work. To avoid this + * problem, mark the pages as "not present" while the transition is in + * progress. If load_unaligned_zeropad() causes a stray reference, a normal + * page fault is generated instead of #VC or #VE, and the page-fault-based + * handlers for load_unaligned_zeropad() resolve the reference. When the + * transition is complete, hv_vtom_set_host_visibility() marks the pages + * as "present" again. + */ +static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc) +{ + return !set_memory_np(kbuffer, pagecount); +} + +/* * hv_vtom_set_host_visibility - Set specified memory visible to host. * * In Isolation VM, all guest memory is encrypted from host and guest @@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo enum hv_mem_host_visibility visibility = enc ? VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE; u64 *pfn_array; + phys_addr_t paddr; + void *vaddr; int ret = 0; bool result = true; int i, pfn; pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); - if (!pfn_array) - return false; + if (!pfn_array) { + result = false; + goto err_set_memory_p; + } for (i = 0, pfn = 0; i < pagecount; i++) { - pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE); + /* + * Use slow_virt_to_phys() because the PRESENT bit has been + * temporarily cleared in the PTEs. slow_virt_to_phys() works + * without the PRESENT bit while virt_to_hvpfn() or similar + * does not. + */ + vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE); + paddr = slow_virt_to_phys(vaddr); + pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT; pfn++; if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) { @@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo } } - err_free_pfn_array: +err_free_pfn_array: kfree(pfn_array); + +err_set_memory_p: + /* + * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present() + * did. Do this even if there is an error earlier in this function in + * order to avoid leaving the memory range in a "broken" state. Setting + * the PRESENT bits shouldn't fail, but return an error if it does. + */ + if (set_memory_p(kbuffer, pagecount)) + result = false; + return result; } static bool hv_vtom_tlb_flush_required(bool private) { - return true; + /* + * Since hv_vtom_clear_present() marks the PTEs as "not present" + * and flushes the TLB, they can't be in the TLB. That makes the + * flush controlled by this function redundant, so return "false". + */ + return false; } static bool hv_vtom_cache_flush_required(void) @@ -608,6 +662,7 @@ void __init hv_vtom_init(void) x86_platform.hyper.is_private_mmio = hv_is_private_mmio; x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required; x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required; + x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present; x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility; /* Set WB as the default cache mode. */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index fdf723b6f6d0..2b62cdd8dd12 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -95,7 +95,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index ce8f50192ae3..7e523bb3d2d3 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static __always_inline void arch_exit_to_user_mode(void) { - mds_user_clear_cpu_buffers(); amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 262e65539f83..2aa52cab1e46 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,6 +315,17 @@ #endif .endm +/* + * Macro to execute VERW instruction that mitigate transient data sampling + * attacks such as MDS. On affected systems a microcode update overloaded VERW + * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. + * + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +.macro CLEAR_CPU_BUFFERS + ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF +.endm + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -529,13 +540,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); +extern u16 mds_verw_sel; + #include <asm/segment.h> /** @@ -562,17 +574,6 @@ static __always_inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability - * - * Clear CPU buffers if the corresponding static key is enabled - */ -static __always_inline void mds_user_clear_cpu_buffers(void) -{ - if (static_branch_likely(&mds_user_clear)) - mds_clear_cpu_buffers(); -} - -/** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index a5e89641bd2d..9aee31862b4a 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -47,6 +47,7 @@ int set_memory_uc(unsigned long addr, int numpages); int set_memory_wc(unsigned long addr, int numpages); int set_memory_wb(unsigned long addr, int numpages); int set_memory_np(unsigned long addr, int numpages); +int set_memory_p(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index ab60a71a8dcb..472f0263dbc6 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,6 +4,7 @@ #include <linux/seqlock.h> #include <uapi/asm/vsyscall.h> +#include <asm/page_types.h> #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); @@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code, } #endif +/* + * The (legacy) vsyscall page is the long page in the kernel portion + * of the address space that has user-accessible permissions. + */ +static inline bool is_vsyscall_vaddr(unsigned long vaddr) +{ + return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); +} + #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bb0ab8466b91..48d049cd74e7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -111,9 +111,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -/* Control MDS CPU buffer clear before returning to user space */ -DEFINE_STATIC_KEY_FALSE(mds_user_clear); -EXPORT_SYMBOL_GPL(mds_user_clear); /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); @@ -252,7 +249,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -356,7 +353,7 @@ static void __init taa_select_mitigation(void) * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -424,7 +421,7 @@ static void __init mmio_select_mitigation(void) */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else static_branch_enable(&mmio_stale_data_clear); @@ -484,12 +481,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return; - if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out; /* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0b97bcde70c6..fbc4e60d027c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1589,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) get_cpu_vendor(c); get_cpu_cap(c); setup_force_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); cpu_parse_early_param(); if (this_cpu->c_early_init) @@ -1601,10 +1602,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); } else { setup_clear_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); } - get_cpu_address_sizes(c); - setup_force_cpu_cap(X86_FEATURE_ALWAYS); cpu_set_bug_bits(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index a927a8fc9624..40dec9b56f87 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -322,6 +406,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (detect_extended_topology_early(c) < 0) detect_ht_early(c); + + /* + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. + */ + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); } static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -482,90 +573,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -702,9 +709,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_ia32_feat_ctl(c); - if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c); split_lock_init(); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fb8cf953380d..b66f540de054 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* - * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need - * to be reserved. + * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by + * kexec and do not need to be reserved. */ - if (data->type != SETUP_EFI && data->type != SETUP_IMA) + if (data->type != SETUP_EFI && + data->type != SETUP_IMA && + data->type != SETUP_RNG_SEED) e820__range_update_kexec(pa_data, sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 17e955ab69fe..3082cf24b69e 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -563,9 +563,6 @@ nmi_restart: } if (this_cpu_dec_return(nmi_state)) goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); } #if IS_ENABLED(CONFIG_KVM_INTEL) diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 87e3da7b0439..65ed14b6540b 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -80,9 +80,10 @@ config KVM_SW_PROTECTED_VM depends on KVM && X86_64 select KVM_GENERIC_PRIVATE_MEM help - Enable support for KVM software-protected VMs. Currently "protected" - means the VM can be backed with memory provided by - KVM_CREATE_GUEST_MEMFD. + Enable support for KVM software-protected VMs. Currently, software- + protected VMs are purely a development and testing vehicle for + KVM_CREATE_GUEST_MEMFD. Attempting to run a "real" VM workload as a + software-protected VM will fail miserably. If unsure, say "N". diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2d6cdeab1f8a..0544700ca50b 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4405,6 +4405,31 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); + /* + * Check for a relevant mmu_notifier invalidation event before getting + * the pfn from the primary MMU, and before acquiring mmu_lock. + * + * For mmu_lock, if there is an in-progress invalidation and the kernel + * allows preemption, the invalidation task may drop mmu_lock and yield + * in response to mmu_lock being contended, which is *very* counter- + * productive as this vCPU can't actually make forward progress until + * the invalidation completes. + * + * Retrying now can also avoid unnessary lock contention in the primary + * MMU, as the primary MMU doesn't necessarily hold a single lock for + * the duration of the invalidation, i.e. faulting in a conflicting pfn + * can cause the invalidation to take longer by holding locks that are + * needed to complete the invalidation. + * + * Do the pre-check even for non-preemtible kernels, i.e. even if KVM + * will never yield mmu_lock in response to contention, as this vCPU is + * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held + * to detect retry guarantees the worst case latency for the vCPU. + */ + if (fault->slot && + mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) + return RET_PF_RETRY; + ret = __kvm_faultin_pfn(vcpu, fault); if (ret != RET_PF_CONTINUE) return ret; @@ -4415,6 +4440,18 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (unlikely(!fault->slot)) return kvm_handle_noslot_fault(vcpu, fault, access); + /* + * Check again for a relevant mmu_notifier invalidation event purely to + * avoid contending mmu_lock. Most invalidations will be detected by + * the previous check, but checking is extremely cheap relative to the + * overall cost of failing to detect the invalidation until after + * mmu_lock is acquired. + */ + if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) { + kvm_release_pfn_clean(fault->pfn); + return RET_PF_RETRY; + } + return RET_PF_CONTINUE; } @@ -4442,6 +4479,11 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) return true; + /* + * Check for a relevant mmu_notifier invalidation event one last time + * now that mmu_lock is held, as the "unsafe" checks performed without + * holding mmu_lock can get false negatives. + */ return fault->slot && mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn); } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index f760106c31f8..a8ce5226b3b5 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -57,7 +57,7 @@ static bool sev_es_enabled = true; module_param_named(sev_es, sev_es_enabled, bool, 0444); /* enable/disable SEV-ES DebugSwap support */ -static bool sev_es_debug_swap_enabled = true; +static bool sev_es_debug_swap_enabled = false; module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444); #else #define sev_enabled false @@ -612,8 +612,11 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; - if (sev_es_debug_swap_enabled) + if (sev_es_debug_swap_enabled) { save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP; + pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. " + "This will not work starting with Linux 6.10\n"); + } pr_debug("Virtual Machine Save Area (VMSA):\n"); print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); @@ -1975,20 +1978,22 @@ int sev_mem_enc_register_region(struct kvm *kvm, goto e_free; } - region->uaddr = range->addr; - region->size = range->size; - - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are * flushed to ensure that guest data gets written into memory with - * correct C-bit. + * correct C-bit. Note, this must be done before dropping kvm->lock, + * as region and its array of pages can be freed by a different task + * once kvm->lock is released. */ sev_clflush_pages(region->pages, region->npages); + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + return ret; e_free: diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index edc3f16cc189..6a9bfdfbb6e5 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,7 +2,10 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H -#define VMX_RUN_VMRESUME (1 << 0) -#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 + +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) #endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 906ecd001511..2bfbf758d061 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -139,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - test $VMX_RUN_VMRESUME, %ebx + bt $VMX_RUN_VMRESUME_SHIFT, %ebx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -161,8 +161,11 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */ - jz .Lvmlaunch + /* Clobbers EFLAGS.ZF */ + CLEAR_CPU_BUFFERS + + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ + jnc .Lvmlaunch /* * After a successful VMRESUME/VMLAUNCH, control flow "magically" diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 1111d9d08903..88a4ff200d04 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -388,7 +388,16 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && + /* + * Disable VERW's behavior of clearing CPU buffers for the guest if the + * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled + * the mitigation. Disabling the clearing behavior provides a + * performance boost for guests that aren't aware that manually clearing + * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry + * and VM-Exit. + */ + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && !boot_cpu_has_bug(X86_BUG_MDS) && !boot_cpu_has_bug(X86_BUG_TAA); @@ -7224,11 +7233,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, guest_state_enter_irqoff(); - /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 48a61d283406..e02cc710f56d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4580,7 +4580,7 @@ static bool kvm_is_vm_type_supported(unsigned long type) { return type == KVM_X86_DEFAULT_VM || (type == KVM_X86_SW_PROTECTED_VM && - IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled); + IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -8007,6 +8007,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (r < 0) return X86EMUL_UNHANDLEABLE; + + /* + * Mark the page dirty _before_ checking whether or not the CMPXCHG was + * successful, as the old value is written back on failure. Note, for + * live migration, this is unnecessarily conservative as CMPXCHG writes + * back the original value and the access is atomic, but KVM's ABI is + * that all writes are dirty logged, regardless of the value written. + */ + kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); + if (r) return X86EMUL_CMPXCHG_FAILED; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 679b09cfe241..d6375b3c633b 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -798,15 +798,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, show_opcodes(regs, loglvl); } -/* - * The (legacy) vsyscall page is the long page in the kernel portion - * of the address space that has user-accessible permissions. - */ -static bool is_vsyscall_vaddr(unsigned long vaddr) -{ - return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); -} - static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index 6993f026adec..42115ac079cf 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -3,6 +3,8 @@ #include <linux/uaccess.h> #include <linux/kernel.h> +#include <asm/vsyscall.h> + #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { @@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) return false; /* + * Reading from the vsyscall page may cause an unhandled fault in + * certain cases. Though it is at an address above TASK_SIZE_MAX, it is + * usually considered as a user space address. + */ + if (is_vsyscall_vaddr(vaddr)) + return false; + + /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early * exception handlers. diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index adc497b93f03..65e9a6e391c0 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -934,7 +934,7 @@ static int __init cmp_memblk(const void *a, const void *b) const struct numa_memblk *ma = *(const struct numa_memblk **)a; const struct numa_memblk *mb = *(const struct numa_memblk **)b; - return ma->start - mb->start; + return (ma->start > mb->start) - (ma->start < mb->start); } static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; @@ -944,14 +944,12 @@ static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; * @start: address to begin fill * @end: address to end fill * - * Find and extend numa_meminfo memblks to cover the @start-@end - * physical address range, such that the first memblk includes - * @start, the last memblk includes @end, and any gaps in between - * are filled. + * Find and extend numa_meminfo memblks to cover the physical + * address range @start-@end * * RETURNS: * 0 : Success - * NUMA_NO_MEMBLK : No memblk exists in @start-@end range + * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end */ int __init numa_fill_memblks(u64 start, u64 end) @@ -963,17 +961,14 @@ int __init numa_fill_memblks(u64 start, u64 end) /* * Create a list of pointers to numa_meminfo memblks that - * overlap start, end. Exclude (start == bi->end) since - * end addresses in both a CFMWS range and a memblk range - * are exclusive. - * - * This list of pointers is used to make in-place changes - * that fill out the numa_meminfo memblks. + * overlap start, end. The list is used to make in-place + * changes that fill out the numa_meminfo memblks. */ for (int i = 0; i < mi->nr_blks; i++) { struct numa_memblk *bi = &mi->blk[i]; - if (start < bi->end && end >= bi->start) { + if (memblock_addrs_overlap(start, end - start, bi->start, + bi->end - bi->start)) { blk[count] = &mi->blk[i]; count++; } diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index e9b448d1b1b7..102880404046 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address) * areas on 32-bit NUMA systems. The percpu areas can * end up in this kind of memory, for instance. * - * This could be optimized, but it is only intended to be - * used at initialization time, and keeping it - * unoptimized should increase the testing coverage for - * the more obscure platforms. + * Note that as long as the PTEs are well-formed with correct PFNs, this + * works without checking the PRESENT bit in the leaf PTE. This is unlike + * the similar vmalloc_to_page() and derivatives. Callers may depend on + * this behavior. + * + * This could be optimized, but it is only used in paths that are not perf + * sensitive, and keeping it unoptimized should increase the testing coverage + * for the more obscure platforms. */ phys_addr_t slow_virt_to_phys(void *__virt_addr) { @@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn) return rc; } -static int set_memory_p(unsigned long *addr, int numpages) -{ - return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0); -} - /* Restore full speculative operation to the pfn. */ int clear_mce_nospec(unsigned long pfn) { unsigned long addr = (unsigned long) pfn_to_kaddr(pfn); - return set_memory_p(&addr, 1); + return set_memory_p(addr, 1); } EXPORT_SYMBOL_GPL(clear_mce_nospec); #endif /* CONFIG_X86_64 */ @@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages) CPA_NO_CHECK_ALIAS, NULL); } +int set_memory_p(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); +} + int set_memory_4k(unsigned long addr, int numpages) { return change_page_attr_set_clr(&addr, numpages, __pgprot(0), |