diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-04 22:21:28 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-04 22:21:28 +0300 |
| commit | b1b6f83ac938d176742c85757960dec2cf10e468 (patch) | |
| tree | f99e605318232a9327500896b9187b5ec9cad0c1 /arch | |
| parent | 5f82e71a001d14824a7728ad9e49f6aea420f161 (diff) | |
| parent | 9e52fc2b50de3a1c08b44f94c610fbe998c0031a (diff) | |
| download | linux-b1b6f83ac938d176742c85757960dec2cf10e468.tar.xz | |
Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 mm changes from Ingo Molnar:
"PCID support, 5-level paging support, Secure Memory Encryption support
The main changes in this cycle are support for three new, complex
hardware features of x86 CPUs:
- Add 5-level paging support, which is a new hardware feature on
upcoming Intel CPUs allowing up to 128 PB of virtual address space
and 4 PB of physical RAM space - a 512-fold increase over the old
limits. (Supercomputers of the future forecasting hurricanes on an
ever warming planet can certainly make good use of more RAM.)
Many of the necessary changes went upstream in previous cycles,
v4.14 is the first kernel that can enable 5-level paging.
This feature is activated via CONFIG_X86_5LEVEL=y - disabled by
default.
(By Kirill A. Shutemov)
- Add 'encrypted memory' support, which is a new hardware feature on
upcoming AMD CPUs ('Secure Memory Encryption', SME) allowing system
RAM to be encrypted and decrypted (mostly) transparently by the
CPU, with a little help from the kernel to transition to/from
encrypted RAM. Such RAM should be more secure against various
attacks like RAM access via the memory bus and should make the
radio signature of memory bus traffic harder to intercept (and
decrypt) as well.
This feature is activated via CONFIG_AMD_MEM_ENCRYPT=y - disabled
by default.
(By Tom Lendacky)
- Enable PCID optimized TLB flushing on newer Intel CPUs: PCID is a
hardware feature that attaches an address space tag to TLB entries
and thus allows to skip TLB flushing in many cases, even if we
switch mm's.
(By Andy Lutomirski)
All three of these features were in the works for a long time, and
it's coincidence of the three independent development paths that they
are all enabled in v4.14 at once"
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (65 commits)
x86/mm: Enable RCU based page table freeing (CONFIG_HAVE_RCU_TABLE_FREE=y)
x86/mm: Use pr_cont() in dump_pagetable()
x86/mm: Fix SME encryption stack ptr handling
kvm/x86: Avoid clearing the C-bit in rsvd_bits()
x86/CPU: Align CR3 defines
x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages
acpi, x86/mm: Remove encryption mask from ACPI page protection type
x86/mm, kexec: Fix memory corruption with SME on successive kexecs
x86/mm/pkeys: Fix typo in Documentation/x86/protection-keys.txt
x86/mm/dump_pagetables: Speed up page tables dump for CONFIG_KASAN=y
x86/mm: Implement PCID based optimization: try to preserve old TLB entries using PCID
x86: Enable 5-level paging support via CONFIG_X86_5LEVEL=y
x86/mm: Allow userspace have mappings above 47-bit
x86/mm: Prepare to expose larger address space to userspace
x86/mpx: Do not allow MPX if we have mappings above 47-bit
x86/mm: Rename tasksize_32bit/64bit to task_size_32bit/64bit()
x86/xen: Redefine XEN_ELFNOTE_INIT_P2M using PUD_SIZE * PTRS_PER_PUD
x86/mm/dump_pagetables: Fix printout of p4d level
x86/mm/dump_pagetables: Generalize address normalization
x86/boot: Fix memremap() related build failure
...
Diffstat (limited to 'arch')
84 files changed, 2631 insertions, 405 deletions
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h index a3d0211970e9..c86a947f5368 100644 --- a/arch/ia64/include/asm/acpi.h +++ b/arch/ia64/include/asm/acpi.h @@ -112,8 +112,6 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf) buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP; } -#define acpi_unlazy_tlb(x) - #ifdef CONFIG_ACPI_NUMA extern cpumask_t early_cpu_possible_map; #define for_each_possible_early_cpu(cpu) \ diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index 121295637d0d..81416000c5e0 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -757,14 +757,14 @@ efi_memmap_intersects (unsigned long phys_addr, unsigned long size) return 0; } -u32 +int efi_mem_type (unsigned long phys_addr) { efi_memory_desc_t *md = efi_memory_descriptor(phys_addr); if (md) return md->type; - return 0; + return -EINVAL; } u64 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cce15191e9e9..b4b27ab016f6 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -169,6 +169,7 @@ config X86 select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER_UNWINDER && STACK_VALIDATION select HAVE_STACK_VALIDATION if X86_64 @@ -329,6 +330,7 @@ config FIX_EARLYCON_MEM config PGTABLE_LEVELS int + default 5 if X86_5LEVEL default 4 if X86_64 default 3 if X86_PAE default 2 @@ -1399,6 +1401,24 @@ config X86_PAE has the cost of more pagetable lookup overhead, and also consumes more pagetable space per process. +config X86_5LEVEL + bool "Enable 5-level page tables support" + depends on X86_64 + ---help--- + 5-level paging enables access to larger address space: + upto 128 PiB of virtual address space and 4 PiB of + physical address space. + + It will be supported by future Intel CPUs. + + Note: a kernel with this option enabled can only be booted + on machines that support the feature. + + See Documentation/x86/x86_64/5level-paging.txt for more + information. + + Say N if unsure. + config ARCH_PHYS_ADDR_T_64BIT def_bool y depends on X86_64 || X86_PAE @@ -1416,6 +1436,35 @@ config X86_DIRECT_GBPAGES supports them), so don't confuse the user by printing that we have them enabled. +config ARCH_HAS_MEM_ENCRYPT + def_bool y + +config AMD_MEM_ENCRYPT + bool "AMD Secure Memory Encryption (SME) support" + depends on X86_64 && CPU_SUP_AMD + ---help--- + Say yes to enable support for the encryption of system memory. + This requires an AMD processor that supports Secure Memory + Encryption (SME). + +config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT + bool "Activate AMD Secure Memory Encryption (SME) by default" + default y + depends on AMD_MEM_ENCRYPT + ---help--- + Say yes to have system memory encrypted by default if running on + an AMD processor that supports Secure Memory Encryption (SME). + + If set to Y, then the encryption of system memory can be + deactivated with the mem_encrypt=off command line option. + + If set to N, then the encryption of system memory can be + activated with the mem_encrypt=on command line option. + +config ARCH_USE_MEMREMAP_PROT + def_bool y + depends on AMD_MEM_ENCRYPT + # Common NUMA Features config NUMA bool "Numa Memory Allocation and Scheduler Support" diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c index 28029be47fbb..f1aa43854bed 100644 --- a/arch/x86/boot/compressed/pagetable.c +++ b/arch/x86/boot/compressed/pagetable.c @@ -15,6 +15,13 @@ #define __pa(x) ((unsigned long)(x)) #define __va(x) ((void *)((unsigned long)(x))) +/* + * The pgtable.h and mm/ident_map.c includes make use of the SME related + * information which is not used in the compressed image support. Un-define + * the SME support to avoid any compile and link errors. + */ +#undef CONFIG_AMD_MEM_ENCRYPT + #include "misc.h" /* These actually do the work of building the kernel identity maps. */ diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 2efc768e4362..72d867f6b518 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -150,8 +150,6 @@ static inline void disable_acpi(void) { } extern int x86_acpi_numa_init(void); #endif /* CONFIG_ACPI_NUMA */ -#define acpi_unlazy_tlb(x) leave_mm(x) - #ifdef CONFIG_ACPI_APEI static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) { @@ -162,12 +160,13 @@ static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) * you call efi_mem_attributes() during boot and at runtime, * you could theoretically see different attributes. * - * Since we are yet to see any x86 platforms that require - * anything other than PAGE_KERNEL (some arm64 platforms - * require the equivalent of PAGE_KERNEL_NOCACHE), return that - * until we know differently. + * We are yet to see any x86 platforms that require anything + * other than PAGE_KERNEL (some ARM64 platforms require the + * equivalent of PAGE_KERNEL_NOCACHE). Additionally, if SME + * is active, the ACPI information will not be encrypted, + * so return PAGE_KERNEL_NOENC until we know differently. */ - return PAGE_KERNEL; + return PAGE_KERNEL_NOENC; } #endif diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h index e01f7f7ccb0c..84ae170bc3d0 100644 --- a/arch/x86/include/asm/cmdline.h +++ b/arch/x86/include/asm/cmdline.h @@ -2,5 +2,7 @@ #define _ASM_X86_CMDLINE_H int cmdline_find_option_bool(const char *cmdline_ptr, const char *option); +int cmdline_find_option(const char *cmdline_ptr, const char *option, + char *buffer, int bufsize); #endif /* _ASM_X86_CMDLINE_H */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8ea315a11fe0..42bbbf0f173d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -196,6 +196,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 5dff775af7cd..c10c9128f54e 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -21,11 +21,13 @@ # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) # define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) # define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +# define DISABLE_PCID 0 #else # define DISABLE_VME 0 # define DISABLE_K6_MTRR 0 # define DISABLE_CYRIX_ARR 0 # define DISABLE_CENTAUR_MCR 0 +# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31)) #endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -49,7 +51,7 @@ #define DISABLED_MASK1 0 #define DISABLED_MASK2 0 #define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) -#define DISABLED_MASK4 0 +#define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 0 diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 398c79889f5c..1387dafdba2d 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -12,6 +12,7 @@ #include <asm/io.h> #include <asm/swiotlb.h> #include <linux/dma-contiguous.h> +#include <linux/mem_encrypt.h> #ifdef CONFIG_ISA # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24) @@ -57,12 +58,12 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) { - return paddr; + return __sme_set(paddr); } static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) { - return daddr; + return __sme_clr(daddr); } #endif /* CONFIG_X86_DMA_REMAP */ diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index 3c69fed215c5..a8e15b04565b 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -13,9 +13,9 @@ static __always_inline __init void *dmi_alloc(unsigned len) } /* Use early IO mappings for DMI because it's initialized early */ -#define dmi_early_remap early_ioremap -#define dmi_early_unmap early_iounmap -#define dmi_remap ioremap_cache -#define dmi_unmap iounmap +#define dmi_early_remap early_memremap +#define dmi_early_unmap early_memunmap +#define dmi_remap(_x, _l) memremap(_x, _l, MEMREMAP_WB) +#define dmi_unmap(_x) memunmap(_x) #endif /* _ASM_X86_DMI_H */ diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h index a504adc661a4..cd266d830e49 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -39,6 +39,8 @@ extern void e820__setup_pci_gap(void); extern void e820__reallocate_tables(void); extern void e820__register_nosave_regions(unsigned long limit_pfn); +extern int e820__get_entry_type(u64 start, u64 end); + /* * Returns true iff the specified range [start,end) is completely contained inside * the ISA region. diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index bda9f94bcb10..04330c8d9af9 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -305,8 +305,8 @@ static inline int mmap_is_ia32(void) test_thread_flag(TIF_ADDR32)); } -extern unsigned long tasksize_32bit(void); -extern unsigned long tasksize_64bit(void); +extern unsigned long task_size_32bit(void); +extern unsigned long task_size_64bit(int full_addr_space); extern unsigned long get_mmap_base(int is_legacy); #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index b65155cc3760..dcd9fb55e679 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -157,6 +157,26 @@ static inline void __set_fixmap(enum fixed_addresses idx, } #endif +/* + * FIXMAP_PAGE_NOCACHE is used for MMIO. Memory encryption is not + * supported for MMIO addresses, so make sure that the memory encryption + * mask is not part of the page attributes. + */ +#define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_IO_NOCACHE + +/* + * Early memremap routines used for in-place encryption. The mappings created + * by these routines are intended to be used as temporary mappings. + */ +void __init *early_memremap_encrypted(resource_size_t phys_addr, + unsigned long size); +void __init *early_memremap_encrypted_wp(resource_size_t phys_addr, + unsigned long size); +void __init *early_memremap_decrypted(resource_size_t phys_addr, + unsigned long size); +void __init *early_memremap_decrypted_wp(resource_size_t phys_addr, + unsigned long size); + #include <asm-generic/fixmap.h> #define __late_set_fixmap(idx, phys, flags) __set_fixmap(idx, phys, flags) diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 474eb8c66fee..05c4aa00cc86 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -7,6 +7,7 @@ struct x86_mapping_info { unsigned long page_flag; /* page flag for PMD or PUD entry */ unsigned long offset; /* ident mapping offset */ bool direct_gbpages; /* PUD level 1GB page support */ + unsigned long kernpg_flag; /* kernel pagetable flag override */ }; int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 1310e1f1cd65..c40a95c33bb8 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -377,4 +377,12 @@ extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size) #define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc #endif +extern bool arch_memremap_can_ram_remap(resource_size_t offset, + unsigned long size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap + +extern bool phys_mem_access_encrypted(unsigned long phys_addr, + unsigned long size); + #endif /* _ASM_X86_IO_H */ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 70ef205489f0..942c1f444da8 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -147,7 +147,8 @@ unsigned long relocate_kernel(unsigned long indirection_page, unsigned long page_list, unsigned long start_address, - unsigned int preserve_context); + unsigned int preserve_context, + unsigned int sme_active); #endif #define ARCH_HAS_KIMAGE_ARCH @@ -207,6 +208,14 @@ struct kexec_entry64_regs { uint64_t r15; uint64_t rip; }; + +extern int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, + gfp_t gfp); +#define arch_kexec_post_alloc_pages arch_kexec_post_alloc_pages + +extern void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages); +#define arch_kexec_pre_free_pages arch_kexec_pre_free_pages + #endif typedef void crash_vmclear_fn(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 92c9032502d8..369e41c23f07 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1079,7 +1079,7 @@ void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, - u64 acc_track_mask); + u64 acc_track_mask, u64 me_mask); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h new file mode 100644 index 000000000000..8e618fcf1f7c --- /dev/null +++ b/arch/x86/include/asm/mem_encrypt.h @@ -0,0 +1,80 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __X86_MEM_ENCRYPT_H__ +#define __X86_MEM_ENCRYPT_H__ + +#ifndef __ASSEMBLY__ + +#include <linux/init.h> + +#include <asm/bootparam.h> + +#ifdef CONFIG_AMD_MEM_ENCRYPT + +extern unsigned long sme_me_mask; + +void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr, + unsigned long decrypted_kernel_vaddr, + unsigned long kernel_len, + unsigned long encryption_wa, + unsigned long encryption_pgd); + +void __init sme_early_encrypt(resource_size_t paddr, + unsigned long size); +void __init sme_early_decrypt(resource_size_t paddr, + unsigned long size); + +void __init sme_map_bootdata(char *real_mode_data); +void __init sme_unmap_bootdata(char *real_mode_data); + +void __init sme_early_init(void); + +void __init sme_encrypt_kernel(void); +void __init sme_enable(struct boot_params *bp); + +/* Architecture __weak replacement functions */ +void __init mem_encrypt_init(void); + +void swiotlb_set_mem_attributes(void *vaddr, unsigned long size); + +#else /* !CONFIG_AMD_MEM_ENCRYPT */ + +#define sme_me_mask 0UL + +static inline void __init sme_early_encrypt(resource_size_t paddr, + unsigned long size) { } +static inline void __init sme_early_decrypt(resource_size_t paddr, + unsigned long size) { } + +static inline void __init sme_map_bootdata(char *real_mode_data) { } +static inline void __init sme_unmap_bootdata(char *real_mode_data) { } + +static inline void __init sme_early_init(void) { } + +static inline void __init sme_encrypt_kernel(void) { } +static inline void __init sme_enable(struct boot_params *bp) { } + +#endif /* CONFIG_AMD_MEM_ENCRYPT */ + +/* + * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when + * writing to or comparing values from the cr3 register. Having the + * encryption mask set in cr3 enables the PGD entry to be encrypted and + * avoid special case handling of PGD allocations. + */ +#define __sme_pa(x) (__pa(x) | sme_me_mask) +#define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask) + +#endif /* __ASSEMBLY__ */ + +#endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 79b647a7ebd0..bb8c597c2248 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -3,12 +3,28 @@ #include <linux/spinlock.h> #include <linux/mutex.h> +#include <linux/atomic.h> /* - * The x86 doesn't have a mmu context, but - * we put the segment information here. + * x86 has arch-specific MMU state beyond what lives in mm_struct. */ typedef struct { + /* + * ctx_id uniquely identifies this mm_struct. A ctx_id will never + * be reused, and zero is not a valid ctx_id. + */ + u64 ctx_id; + + /* + * Any code that needs to do any sort of TLB flushing for this + * mm will first make its changes to the page tables, then + * increment tlb_gen, then flush. This lets the low-level + * flushing code keep track of what needs flushing. + * + * This is not used on Xen PV. + */ + atomic64_t tlb_gen; + #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; #endif @@ -37,6 +53,11 @@ typedef struct { #endif } mm_context_t; +#define INIT_MM_CONTEXT(mm) \ + .context = { \ + .ctx_id = 1, \ + } + void leave_mm(int cpu); #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 7a234be7e298..7ae318c340d9 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -12,6 +12,9 @@ #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/mpx.h> + +extern atomic64_t last_mm_ctx_id; + #ifndef CONFIG_PARAVIRT static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) @@ -125,13 +128,18 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) - this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY); + int cpu = smp_processor_id(); + + if (cpumask_test_cpu(cpu, mm_cpumask(mm))) + cpumask_clear_cpu(cpu, mm_cpumask(mm)); } static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); + atomic64_set(&mm->context.tlb_gen, 0); + #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and always allocated */ @@ -290,6 +298,9 @@ static inline unsigned long __get_current_cr3_fast(void) { unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); + if (static_cpu_has(X86_FEATURE_PCID)) + cr3 |= this_cpu_read(cpu_tlbstate.loaded_mm_asid); + /* For now, be very restrictive about when this can be called. */ VM_WARN_ON(in_nmi() || preemptible()); diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h index a0d662be4c5b..7d7404756bb4 100644 --- a/arch/x86/include/asm/mpx.h +++ b/arch/x86/include/asm/mpx.h @@ -73,6 +73,9 @@ static inline void mpx_mm_init(struct mm_struct *mm) } void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long start, unsigned long end); + +unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, + unsigned long flags); #else static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { @@ -94,6 +97,12 @@ static inline void mpx_notify_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { } + +static inline unsigned long mpx_unmapped_area_check(unsigned long addr, + unsigned long len, unsigned long flags) +{ + return addr; +} #endif /* CONFIG_X86_INTEL_MPX */ #endif /* _ASM_X86_MPX_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 5573c75f8e4c..17f5c12e1afd 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -356,6 +356,8 @@ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d #define MSR_K8_SYSCFG 0xc0010010 +#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_K8_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT) #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index b4a0d43248cf..b50df06ad251 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -51,6 +51,10 @@ static inline void clear_page(void *page) void copy_page(void *to, void *from); +#ifdef CONFIG_X86_MCE +#define arch_unmap_kpfn arch_unmap_kpfn +#endif + #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 7bd0099384ca..b98ed9d14630 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -3,6 +3,7 @@ #include <linux/const.h> #include <linux/types.h> +#include <linux/mem_encrypt.h> /* PAGE_SHIFT determines the page size */ #define PAGE_SHIFT 12 @@ -15,7 +16,7 @@ #define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) -#define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1)) +#define __PHYSICAL_MASK ((phys_addr_t)(__sme_clr((1ULL << __PHYSICAL_MASK_SHIFT) - 1))) #define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) /* Cast *PAGE_MASK to a signed type so that it is sign-extended if diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 77037b6f1caa..bbeae4a2bd01 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H +#include <linux/mem_encrypt.h> #include <asm/page.h> #include <asm/pgtable_types.h> @@ -13,9 +14,18 @@ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ : (prot)) +/* + * Macros to add or remove encryption attribute + */ +#define pgprot_encrypted(prot) __pgprot(__sme_set(pgprot_val(prot))) +#define pgprot_decrypted(prot) __pgprot(__sme_clr(pgprot_val(prot))) + #ifndef __ASSEMBLY__ #include <asm/x86_init.h> +extern pgd_t early_top_pgt[PTRS_PER_PGD]; +int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); + void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); void ptdump_walk_pgd_level_checkwx(void); @@ -38,6 +48,8 @@ extern struct list_head pgd_list; extern struct mm_struct *pgd_page_get_mm(struct page *page); +extern pmdval_t early_pmd_flags; + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT */ @@ -195,6 +207,11 @@ static inline unsigned long p4d_pfn(p4d_t p4d) return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; } +static inline unsigned long pgd_pfn(pgd_t pgd) +{ + return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; +} + static inline int p4d_large(p4d_t p4d) { /* No 512 GiB pages yet */ @@ -704,8 +721,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pmd_page(pmd) \ - pfn_to_page((pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT) +#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD] @@ -773,8 +789,7 @@ static inline unsigned long pud_page_vaddr(pud_t pud) * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pud_page(pud) \ - pfn_to_page((pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT) +#define pud_page(pud) pfn_to_page(pud_pfn(pud)) /* Find an entry in the second-level page table.. */ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) @@ -824,8 +839,7 @@ static inline unsigned long p4d_page_vaddr(p4d_t p4d) * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define p4d_page(p4d) \ - pfn_to_page((p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT) +#define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d)) /* Find an entry in the third-level page table.. */ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) @@ -859,7 +873,7 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd) * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pgd_page(pgd) pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT) +#define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) /* to find an entry in a page-table-directory. */ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index bf9638e1ee42..399261ce904c 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -2,6 +2,8 @@ #define _ASM_X86_PGTABLE_DEFS_H #include <linux/const.h> +#include <linux/mem_encrypt.h> + #include <asm/page_types.h> #define FIRST_USER_ADDRESS 0UL @@ -121,10 +123,10 @@ #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_DIRTY) -#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ - _PAGE_DIRTY) +#define _PAGE_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |\ + _PAGE_ACCESSED | _PAGE_DIRTY) +#define _KERNPG_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | \ + _PAGE_ACCESSED | _PAGE_DIRTY) /* * Set of bits not changed in pte_modify. The pte's @@ -159,6 +161,7 @@ enum page_cache_mode { #define _PAGE_CACHE_MASK (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT) #define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) +#define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) #define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) #define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ @@ -187,22 +190,42 @@ enum page_cache_mode { #define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) #define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) +#define __PAGE_KERNEL_WP (__PAGE_KERNEL | _PAGE_CACHE_WP) #define __PAGE_KERNEL_IO (__PAGE_KERNEL) #define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE) -#define PAGE_KERNEL __pgprot(__PAGE_KERNEL) -#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) -#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) -#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX) -#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE) -#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE) -#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC) -#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL) -#define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR) +#ifndef __ASSEMBLY__ + +#define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) + +#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ + _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_ENC) +#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ + _PAGE_DIRTY | _PAGE_ENC) + +#define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _PAGE_ENC) +#define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _PAGE_ENC) + +#define __PAGE_KERNEL_NOENC (__PAGE_KERNEL) +#define __PAGE_KERNEL_NOENC_WP (__PAGE_KERNEL_WP) + +#define PAGE_KERNEL __pgprot(__PAGE_KERNEL | _PAGE_ENC) +#define PAGE_KERNEL_NOENC __pgprot(__PAGE_KERNEL) +#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO | _PAGE_ENC) +#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC | _PAGE_ENC) +#define PAGE_KERNEL_EXEC_NOENC __pgprot(__PAGE_KERNEL_EXEC) +#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX | _PAGE_ENC) +#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC) +#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC) +#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC) +#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC) +#define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC) + +#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) +#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE) -#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) -#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE) +#endif /* __ASSEMBLY__ */ /* xwr */ #define __P000 PAGE_NONE @@ -287,6 +310,11 @@ static inline p4dval_t native_p4d_val(p4d_t p4d) #else #include <asm-generic/pgtable-nop4d.h> +static inline p4d_t native_make_p4d(pudval_t val) +{ + return (p4d_t) { .pgd = native_make_pgd((pgdval_t)val) }; +} + static inline p4dval_t native_p4d_val(p4d_t p4d) { return native_pgd_val(p4d.pgd); diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 79aa2f98398d..dc723b64acf0 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -2,6 +2,7 @@ #define _ASM_X86_PROCESSOR_FLAGS_H #include <uapi/asm/processor-flags.h> +#include <linux/mem_encrypt.h> #ifdef CONFIG_VM86 #define X86_VM_MASK X86_EFLAGS_VM @@ -32,16 +33,18 @@ * CR3_ADDR_MASK is the mask used by read_cr3_pa(). */ #ifdef CONFIG_X86_64 -/* Mask off the address space ID bits. */ -#define CR3_ADDR_MASK 0x7FFFFFFFFFFFF000ull -#define CR3_PCID_MASK 0xFFFull +/* Mask off the address space ID and SME encryption bits. */ +#define CR3_ADDR_MASK __sme_clr(0x7FFFFFFFFFFFF000ull) +#define CR3_PCID_MASK 0xFFFull +#define CR3_NOFLUSH BIT_ULL(63) #else /* * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save * a tiny bit of code size by setting all the bits. */ -#define CR3_ADDR_MASK 0xFFFFFFFFull -#define CR3_PCID_MASK 0ull +#define CR3_ADDR_MASK 0xFFFFFFFFull +#define CR3_PCID_MASK 0ull +#define CR3_NOFLUSH 0 #endif #endif /* _ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index abc99b9c7ffd..3fa26a61eabc 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -30,6 +30,7 @@ struct vm86; #include <linux/math64.h> #include <linux/err.h> #include <linux/irqflags.h> +#include <linux/mem_encrypt.h> /* * We handle most unaligned accesses in hardware. On the other hand @@ -240,9 +241,14 @@ static inline unsigned long read_cr3_pa(void) return __read_cr3() & CR3_ADDR_MASK; } +static inline unsigned long native_read_cr3_pa(void) +{ + return __native_read_cr3() & CR3_ADDR_MASK; +} + static inline void load_cr3(pgd_t *pgdir) { - write_cr3(__pa(pgdir)); + write_cr3(__sme_pa(pgdir)); } #ifdef CONFIG_X86_32 @@ -805,7 +811,9 @@ static inline void spin_lock_prefetch(const void *x) */ #define IA32_PAGE_OFFSET PAGE_OFFSET #define TASK_SIZE PAGE_OFFSET +#define TASK_SIZE_LOW TASK_SIZE #define TASK_SIZE_MAX TASK_SIZE +#define DEFAULT_MAP_WINDOW TASK_SIZE #define STACK_TOP TASK_SIZE #define STACK_TOP_MAX STACK_TOP @@ -845,7 +853,9 @@ static inline void spin_lock_prefetch(const void *x) * particular problem by preventing anything from being mapped * at the maximum canonical address. */ -#define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE) +#define TASK_SIZE_MAX ((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE) + +#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE) /* This decides where the kernel will search for a free chunk of vm * space during mmap's. @@ -853,12 +863,14 @@ static inline void spin_lock_prefetch(const void *x) #define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \ 0xc0000000 : 0xFFFFe000) +#define TASK_SIZE_LOW (test_thread_flag(TIF_ADDR32) ? \ + IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW) #define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) #define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) -#define STACK_TOP TASK_SIZE +#define STACK_TOP TASK_SIZE_LOW #define STACK_TOP_MAX TASK_SIZE_MAX #define INIT_THREAD { \ @@ -879,7 +891,7 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, * space during mmap's. */ #define __TASK_UNMAPPED_BASE(task_size) (PAGE_ALIGN(task_size / 3)) -#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE) +#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE_LOW) #define KSTK_EIP(task) (task_pt_regs(task)->ip) diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 230e1903acf0..90d91520c13a 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -1,6 +1,15 @@ #ifndef _ARCH_X86_REALMODE_H #define _ARCH_X86_REALMODE_H +/* + * Flag bit definitions for use with the flags field of the trampoline header + * in the CONFIG_X86_64 variant. + */ +#define TH_FLAGS_SME_ACTIVE_BIT 0 +#define TH_FLAGS_SME_ACTIVE BIT(TH_FLAGS_SME_ACTIVE_BIT) + +#ifndef __ASSEMBLY__ + #include <linux/types.h> #include <asm/io.h> @@ -38,6 +47,7 @@ struct trampoline_header { u64 start; u64 efer; u32 cr4; + u32 flags; #endif }; @@ -69,4 +79,6 @@ static inline size_t real_mode_size_needed(void) void set_real_mode_mem(phys_addr_t mem, size_t size); void reserve_real_mode(void); +#endif /* __ASSEMBLY__ */ + #endif /* _ARCH_X86_REALMODE_H */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index eaec6c364e42..cd71273ec49d 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -11,6 +11,7 @@ * Executability : eXeutable, NoteXecutable * Read/Write : ReadOnly, ReadWrite * Presence : NotPresent + * Encryption : Encrypted, Decrypted * * Within a category, the attributes are mutually exclusive. * @@ -42,6 +43,8 @@ int set_memory_wt(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_4k(unsigned long addr, int numpages); +int set_memory_encrypted(unsigned long addr, int numpages); +int set_memory_decrypted(unsigned long addr, int numpages); int set_memory_array_uc(unsigned long *addr, int addrinarray); int set_memory_array_wc(unsigned long *addr, int addrinarray); diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index c7797307fc2b..79a4ca6a9606 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -15,4 +15,18 @@ #include <asm-generic/tlb.h> +/* + * While x86 architecture in general requires an IPI to perform TLB + * shootdown, enablement code for several hypervisors overrides + * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing + * a hypercall. To keep software pagetable walkers safe in this case we + * switch to RCU based table free (HAVE_RCU_TABLE_FREE). See the comment + * below 'ifdef CONFIG_HAVE_RCU_TABLE_FREE' in include/asm-generic/tlb.h + * for more details. + */ +static inline void __tlb_remove_table(void *table) +{ + free_page_and_swap_cache(table); +} + #endif /* _ASM_X86_TLB_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 50ea3482e1d1..d23e61dc0640 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -57,6 +57,23 @@ static inline void invpcid_flush_all_nonglobals(void) __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL); } +static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) +{ + u64 new_tlb_gen; + + /* + * Bump the generation count. This also serves as a full barrier + * that synchronizes with switch_mm(): callers are required to order + * their read of mm_cpumask after their writes to the paging + * structures. + */ + smp_mb__before_atomic(); + new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen); + smp_mb__after_atomic(); + + return new_tlb_gen; +} + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else @@ -65,6 +82,17 @@ static inline void invpcid_flush_all_nonglobals(void) #define __flush_tlb_single(addr) __native_flush_tlb_single(addr) #endif +/* + * 6 because 6 should be plenty and struct tlb_state will fit in + * two cache lines. + */ +#define TLB_NR_DYN_ASIDS 6 + +struct tlb_context { + u64 ctx_id; + u64 tlb_gen; +}; + struct tlb_state { /* * cpu_tlbstate.loaded_mm should match CR3 whenever interrupts @@ -73,13 +101,35 @@ struct tlb_state { * mode even if we've already switched back to swapper_pg_dir. */ struct mm_struct *loaded_mm; - int state; + u16 loaded_mm_asid; + u16 next_asid; /* * Access to this CR4 shadow and to H/W CR4 is protected by * disabling interrupts when modifying either one. */ unsigned long cr4; + + /* + * This is a list of all contexts that might exist in the TLB. + * There is one per ASID that we use, and the ASID (what the + * CPU calls PCID) is the index into ctxts. + * + * For each context, ctx_id indicates which mm the TLB's user + * entries came from. As an invariant, the TLB will never + * contain entries that are out-of-date as when that mm reached + * the tlb_gen in the list. + * + * To be clear, this means that it's legal for the TLB code to + * flush the TLB without updating tlb_gen. This can happen + * (for now, at least) due to paravirt remote flushes. + * + * NB: context 0 is a bit special, since it's also used by + * various bits of init code. This is fine -- code that + * isn't aware of PCID will end up harmlessly flushing + * context 0. + */ + struct tlb_context ctxs[TLB_NR_DYN_ASIDS]; }; DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); @@ -207,6 +257,14 @@ static inline void __flush_tlb_all(void) __flush_tlb_global(); else __flush_tlb(); + + /* + * Note: if we somehow had PCID but not PGE, then this wouldn't work -- + * we'd end up flushing kernel translations for the current ASID but + * we might fail to flush kernel translations for other cached ASIDs. + * + * To avoid this issue, we force PCID off if PGE is off. + */ } static inline void __flush_tlb_one(unsigned long addr) @@ -231,9 +289,26 @@ static inline void __flush_tlb_one(unsigned long addr) * and page-granular flushes are available only on i486 and up. */ struct flush_tlb_info { - struct mm_struct *mm; - unsigned long start; - unsigned long end; + /* + * We support several kinds of flushes. + * + * - Fully flush a single mm. .mm will be set, .end will be + * TLB_FLUSH_ALL, and .new_tlb_gen will be the tlb_gen to + * which the IPI sender is trying to catch us up. + * + * - Partially flush a single mm. .mm will be set, .start and + * .end will indicate the range, and .new_tlb_gen will be set + * such that the changes between generation .new_tlb_gen-1 and + * .new_tlb_gen are entirely contained in the indicated range. + * + * - Fully flush all mms whose tlb_gens have been updated. .mm + * will be NULL, .end will be TLB_FLUSH_ALL, and .new_tlb_gen + * will be zero. + */ + struct mm_struct *mm; + unsigned long start; + unsigned long end; + u64 new_tlb_gen; }; #define local_flush_tlb() __flush_tlb() @@ -256,12 +331,10 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) void native_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info); -#define TLBSTATE_OK 1 -#define TLBSTATE_LAZY 2 - static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, struct mm_struct *mm) { + inc_mm_tlb_gen(mm); cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); } diff --git a/arch/x86/include/asm/vga.h b/arch/x86/include/asm/vga.h index c4b9dc2f67c5..9f42beefc67a 100644 --- a/arch/x86/include/asm/vga.h +++ b/arch/x86/include/asm/vga.h @@ -7,12 +7,24 @@ #ifndef _ASM_X86_VGA_H #define _ASM_X86_VGA_H +#include <asm/set_memory.h> + /* * On the PC, we can just recalculate addresses and then * access the videoram directly without any black magic. + * To support memory encryption however, we need to access + * the videoram as decrypted memory. */ -#define VGA_MAP_MEM(x, s) (unsigned long)phys_to_virt(x) +#define VGA_MAP_MEM(x, s) \ +({ \ + unsigned long start = (unsigned long)phys_to_virt(x); \ + \ + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) \ + set_memory_decrypted(start, (s) >> PAGE_SHIFT); \ + \ + start; \ +}) #define vga_readb(x) (*(x)) #define vga_writeb(x, y) (*(y) = (x)) diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7491e73d9253..97bb2caf3428 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -115,7 +115,7 @@ static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = { #define ACPI_INVALID_GSI INT_MIN /* - * This is just a simple wrapper around early_ioremap(), + * This is just a simple wrapper around early_memremap(), * with sanity checks for phys == 0 and size == 0. */ char *__init __acpi_map_table(unsigned long phys, unsigned long size) @@ -124,7 +124,7 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size) if (!phys || !size) return NULL; - return early_ioremap(phys, size); + return early_memremap(phys, size); } void __init __acpi_unmap_table(char *map, unsigned long size) @@ -132,7 +132,7 @@ void __init __acpi_unmap_table(char *map, unsigned long size) if (!map || !size) return; - early_iounmap(map, size); + early_memunmap(map, size); } #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e44338dd62dd..9862e2cd6d93 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -558,8 +558,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) static void early_init_amd(struct cpuinfo_x86 *c) { + u32 dummy; + early_init_amd_mc(c); + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); + /* * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate * with P/T states and does not stop in deep C-states @@ -622,6 +626,27 @@ static void early_init_amd(struct cpuinfo_x86 *c) */ if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_E400); + + /* + * BIOS support is required for SME. If BIOS has enabled SME then + * adjust x86_phys_bits by the SME physical address space reduction + * value. If BIOS has not enabled SME then don't advertise the + * feature (set in scattered.c). Also, since the SME support requires + * long mode, don't advertise the feature under CONFIG_X86_32. + */ + if (cpu_has(c, X86_FEATURE_SME)) { + u64 msr; + + /* Check if SME is enabled */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (msr & MSR_K8_SYSCFG_MEM_ENCRYPT) { + c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f; + if (IS_ENABLED(CONFIG_X86_32)) + clear_cpu_cap(c, X86_FEATURE_SME); + } else { + clear_cpu_cap(c, X86_FEATURE_SME); + } + } } static void init_amd_k8(struct cpuinfo_x86 *c) @@ -740,8 +765,6 @@ static void init_amd_bd(struct cpuinfo_x86 *c) static void init_amd(struct cpuinfo_x86 *c) { - u32 dummy; - early_init_amd(c); /* @@ -803,8 +826,6 @@ static void init_amd(struct cpuinfo_x86 *c) if (c->x86 > 0x11) set_cpu_cap(c, X86_FEATURE_ARAT); - rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); - /* 3DNow or LM implies PREFETCHW */ if (!cpu_has(c, X86_FEATURE_3DNOWPREFETCH)) if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM)) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0af86d9242da..db684880d74a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -21,6 +21,14 @@ void __init check_bugs(void) { +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif + identify_boot_cpu(); if (!IS_ENABLED(CONFIG_SMP)) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c8b39870f33e..b95cd94ca97b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -168,6 +168,24 @@ static int __init x86_mpx_setup(char *s) } __setup("nompx", x86_mpx_setup); +#ifdef CONFIG_X86_64 +static int __init x86_pcid_setup(char *s) +{ + /* require an exact match without trailing characters */ + if (strlen(s)) + return 0; + + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_PCID)) + return 1; + + setup_clear_cpu_cap(X86_FEATURE_PCID); + pr_info("nopcid: PCID feature disabled\n"); + return 1; +} +__setup("nopcid", x86_pcid_setup); +#endif + static int __init x86_noinvpcid_setup(char *s) { /* noinvpcid doesn't accept parameters */ @@ -311,6 +329,25 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) } } +static void setup_pcid(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_PCID)) { + if (cpu_has(c, X86_FEATURE_PGE)) { + cr4_set_bits(X86_CR4_PCIDE); + } else { + /* + * flush_tlb_all(), as currently implemented, won't + * work if PCID is on but PGE is not. Since that + * combination doesn't exist on real hardware, there's + * no reason to try to fully support it, but it's + * polite to avoid corrupting data if we're on + * an improperly configured VM. + */ + clear_cpu_cap(c, X86_FEATURE_PCID); + } + } +} + /* * Protection Keys are not available in 32-bit mode. */ @@ -1125,6 +1162,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) setup_smep(c); setup_smap(c); + /* Set up PCID */ + setup_pcid(c); + /* * The vendor-specific functions might have changed features. * Now we do "generic changes." diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 6dde0497efc7..3b413065c613 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -51,6 +51,7 @@ #include <asm/mce.h> #include <asm/msr.h> #include <asm/reboot.h> +#include <asm/set_memory.h> #include "mce-internal.h" @@ -1051,6 +1052,48 @@ static int do_memory_failure(struct mce *m) return ret; } +#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE) + +void arch_unmap_kpfn(unsigned long pfn) +{ + unsigned long decoy_addr; + + /* + * Unmap this page from the kernel 1:1 mappings to make sure + * we don't log more errors because of speculative access to + * the page. + * We would like to just call: + * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); + * but doing that would radically increase the odds of a + * speculative access to the posion page because we'd have + * the virtual address of the kernel 1:1 mapping sitting + * around in registers. + * Instead we get tricky. We create a non-canonical address + * that looks just like the one we want, but has bit 63 flipped. + * This relies on set_memory_np() not checking whether we passed + * a legal address. + */ + +/* + * Build time check to see if we have a spare virtual bit. Don't want + * to leave this until run time because most developers don't have a + * system that can exercise this code path. This will only become a + * problem if/when we move beyond 5-level page tables. + * + * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD) + */ +#if PGDIR_SHIFT + 9 < 63 + decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); +#else +#error "no unused virtual bit available" +#endif + + if (set_memory_np(decoy_addr, 1)) + pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); + +} +#endif + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 23c23508c012..05459ad3db46 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,6 +31,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, + { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 532da61d605c..71c11ad5643e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -96,7 +96,8 @@ EXPORT_SYMBOL_GPL(e820__mapped_any); * Note: this function only works correctly once the E820 table is sorted and * not-overlapping (at least for the range specified), which is the case normally. */ -bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) +static struct e820_entry *__e820__mapped_all(u64 start, u64 end, + enum e820_type type) { int i; @@ -122,9 +123,28 @@ bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) * coverage of the desired range exists: */ if (start >= end) - return 1; + return entry; } - return 0; + + return NULL; +} + +/* + * This function checks if the entire range <start,end> is mapped with type. + */ +bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) +{ + return __e820__mapped_all(start, end, type); +} + +/* + * This function returns the type associated with the range <start,end>. + */ +int e820__get_entry_type(u64 start, u64 end) +{ + struct e820_entry *entry = __e820__mapped_all(start, end, 0); + + return entry ? entry->type : -EINVAL; } /* diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 6b91e2eb8d3f..9c4e7ba6870c 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -195,7 +195,7 @@ void init_espfix_ap(int cpu) pte_p = pte_offset_kernel(&pmd, addr); stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); - pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 9ba79543d9ee..6a193b93fd95 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -14,6 +14,7 @@ #include <linux/start_kernel.h> #include <linux/io.h> #include <linux/memblock.h> +#include <linux/mem_encrypt.h> #include <asm/processor.h> #include <asm/proto.h> @@ -33,7 +34,6 @@ /* * Manage page tables very early on. */ -extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); @@ -45,9 +45,11 @@ static void __head *fixup_pointer(void *ptr, unsigned long physaddr) return ptr - (void *)_text + (void *)physaddr; } -void __head __startup_64(unsigned long physaddr) +unsigned long __head __startup_64(unsigned long physaddr, + struct boot_params *bp) { unsigned long load_delta, *p; + unsigned long pgtable_flags; pgdval_t *pgd; p4dval_t *p4d; pudval_t *pud; @@ -69,6 +71,12 @@ void __head __startup_64(unsigned long physaddr) if (load_delta & ~PMD_PAGE_MASK) for (;;); + /* Activate Secure Memory Encryption (SME) if supported and enabled */ + sme_enable(bp); + + /* Include the SME encryption mask in the fixup value */ + load_delta += sme_get_me_mask(); + /* Fixup the physical addresses in the page table */ pgd = fixup_pointer(&early_top_pgt, physaddr); @@ -92,31 +100,35 @@ void __head __startup_64(unsigned long physaddr) * creates a bunch of nonsense entries but that is fine -- * it avoids problems around wraparound. */ + next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr); pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); + pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask(); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE; - pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE; + pgd[i + 0] = (pgdval_t)p4d + pgtable_flags; + pgd[i + 1] = (pgdval_t)p4d + pgtable_flags; i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; - p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; - p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + p4d[i + 0] = (pgdval_t)pud + pgtable_flags; + p4d[i + 1] = (pgdval_t)pud + pgtable_flags; } else { i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; - pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + pgd[i + 0] = (pgdval_t)pud + pgtable_flags; + pgd[i + 1] = (pgdval_t)pud + pgtable_flags; } i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; - pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE; - pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE; + pud[i + 0] = (pudval_t)pmd + pgtable_flags; + pud[i + 1] = (pudval_t)pmd + pgtable_flags; pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; + pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { @@ -137,9 +149,30 @@ void __head __startup_64(unsigned long physaddr) pmd[i] += load_delta; } - /* Fixup phys_base */ + /* + * Fixup phys_base - remove the memory encryption mask to obtain + * the true physical address. + */ p = fixup_pointer(&phys_base, physaddr); - *p += load_delta; + *p += load_delta - sme_get_me_mask(); + + /* Encrypt the kernel (if SME is active) */ + sme_encrypt_kernel(); + + /* + * Return the SME encryption mask (if SME is active) to be used as a + * modifier for the initial pgdir entry programmed into CR3. + */ + return sme_get_me_mask(); +} + +unsigned long __startup_secondary_64(void) +{ + /* + * Return the SME encryption mask (if SME is active) to be used as a + * modifier for the initial pgdir entry programmed into CR3. + */ + return sme_get_me_mask(); } /* Wipe all early page tables except for the kernel symbol map */ @@ -147,17 +180,17 @@ static void __init reset_early_page_tables(void) { memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); next_early_pgt = 0; - write_cr3(__pa_nodebug(early_top_pgt)); + write_cr3(__sme_pa_nodebug(early_top_pgt)); } /* Create a new PMD entry */ -int __init early_make_pgtable(unsigned long address) +int __init __early_make_pgtable(unsigned long address, pmdval_t pmd) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; p4dval_t p4d, *p4d_p; pudval_t pud, *pud_p; - pmdval_t pmd, *pmd_p; + pmdval_t *pmd_p; /* Invalid address or early pgt is done ? */ if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt)) @@ -216,12 +249,21 @@ again: memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } - pmd = (physaddr & PMD_MASK) + early_pmd_flags; pmd_p[pmd_index(address)] = pmd; return 0; } +int __init early_make_pgtable(unsigned long address) +{ + unsigned long physaddr = address - __PAGE_OFFSET; + pmdval_t pmd; + + pmd = (physaddr & PMD_MASK) + early_pmd_flags; + + return __early_make_pgtable(address, pmd); +} + /* Don't add a printk in there. printk relies on the PDA which is not initialized yet. */ static void __init clear_bss(void) @@ -244,6 +286,12 @@ static void __init copy_bootdata(char *real_mode_data) char * command_line; unsigned long cmd_line_ptr; + /* + * If SME is active, this will create decrypted mappings of the + * boot data in advance of the copy operations. + */ + sme_map_bootdata(real_mode_data); + memcpy(&boot_params, real_mode_data, sizeof boot_params); sanitize_boot_params(&boot_params); cmd_line_ptr = get_cmd_line_ptr(); @@ -251,6 +299,14 @@ static void __init copy_bootdata(char *real_mode_data) command_line = __va(cmd_line_ptr); memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); } + + /* + * The old boot data is no longer needed and won't be reserved, + * freeing up that memory for use by the system. If SME is active, + * we need to remove the mappings that were created so that the + * memory doesn't remain mapped as decrypted. + */ + sme_unmap_bootdata(real_mode_data); } asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) @@ -280,6 +336,13 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) clear_page(init_top_pgt); + /* + * SME support may update early_pmd_flags to include the memory + * encryption mask, so it needs to be called before anything + * that may generate a page fault. + */ + sme_early_init(); + kasan_early_init(); for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 6225550883df..513cbb012ecc 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -73,12 +73,19 @@ startup_64: /* Sanitize CPU configuration */ call verify_cpu + /* + * Perform pagetable fixups. Additionally, if SME is active, encrypt + * the kernel and retrieve the modifier (SME encryption mask if SME + * is active) to be added to the initial pgdir entry that will be + * programmed into CR3. + */ leaq _text(%rip), %rdi pushq %rsi call __startup_64 popq %rsi - movq $(early_top_pgt - __START_KERNEL_map), %rax + /* Form the CR3 value being sure to include the CR3 modifier */ + addq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) /* @@ -98,7 +105,16 @@ ENTRY(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu - movq $(init_top_pgt - __START_KERNEL_map), %rax + /* + * Retrieve the modifier (SME encryption mask if SME is active) to be + * added to the initial pgdir entry that will be programmed into CR3. + */ + pushq %rsi + call __startup_secondary_64 + popq %rsi + + /* Form the CR3 value being sure to include the CR3 modifier */ + addq $(init_top_pgt - __START_KERNEL_map), %rax 1: /* Enable PAE mode, PGE and LA57 */ @@ -335,9 +351,9 @@ GLOBAL(name) NEXT_PAGE(early_top_pgt) .fill 511,8,0 #ifdef CONFIG_X86_5LEVEL - .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #else - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #endif NEXT_PAGE(early_dynamic_pgts) @@ -350,15 +366,15 @@ NEXT_PAGE(init_top_pgt) .fill 512,8,0 #else NEXT_PAGE(init_top_pgt) - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC NEXT_PAGE(level3_ident_pgt) - .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .fill 511, 8, 0 NEXT_PAGE(level2_ident_pgt) /* Since I easily can, map the first 1G. @@ -370,14 +386,14 @@ NEXT_PAGE(level2_ident_pgt) #ifdef CONFIG_X86_5LEVEL NEXT_PAGE(level4_kernel_pgt) .fill 511,8,0 - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #endif NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ - .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE - .quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC NEXT_PAGE(level2_kernel_pgt) /* @@ -395,7 +411,7 @@ NEXT_PAGE(level2_kernel_pgt) NEXT_PAGE(level2_fixmap_pgt) .fill 506,8,0 - .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ .fill 5,8,0 diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 38b64587b31b..fd6f8fbbe6f2 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -33,7 +33,6 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf, struct setup_data_node *node = file->private_data; unsigned long remain; loff_t pos = *ppos; - struct page *pg; void *p; u64 pa; @@ -47,18 +46,13 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf, count = node->len - pos; pa = node->paddr + sizeof(struct setup_data) + pos; - pg = pfn_to_page((pa + count - 1) >> PAGE_SHIFT); - if (PageHighMem(pg)) { - p = ioremap_cache(pa, count); - if (!p) - return -ENXIO; - } else - p = __va(pa); + p = memremap(pa, count, MEMREMAP_WB); + if (!p) + return -ENOMEM; remain = copy_to_user(user_buf, p, count); - if (PageHighMem(pg)) - iounmap(p); + memunmap(p); if (remain) return -EFAULT; @@ -109,7 +103,6 @@ static int __init create_setup_data_nodes(struct dentry *parent) struct setup_data *data; int error; struct dentry *d; - struct page *pg; u64 pa_data; int no = 0; @@ -126,16 +119,12 @@ static int __init create_setup_data_nodes(struct dentry *parent) goto err_dir; } - pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT); - if (PageHighMem(pg)) { - data = ioremap_cache(pa_data, sizeof(*data)); - if (!data) { - kfree(node); - error = -ENXIO; - goto err_dir; - } - } else - data = __va(pa_data); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); + if (!data) { + kfree(node); + error = -ENOMEM; + goto err_dir; + } node->paddr = pa_data; node->type = data->type; @@ -143,8 +132,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) error = create_setup_data_node(d, no, node); pa_data = data->next; - if (PageHighMem(pg)) - iounmap(data); + memunmap(data); if (error) goto err_dir; no++; diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 06e1ff5562c0..4b0592ca9e47 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -16,8 +16,8 @@ #include <linux/stat.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/io.h> -#include <asm/io.h> #include <asm/setup.h> static ssize_t version_show(struct kobject *kobj, @@ -79,12 +79,12 @@ static int get_setup_data_paddr(int nr, u64 *paddr) *paddr = pa_data; return 0; } - data = ioremap_cache(pa_data, sizeof(*data)); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; pa_data = data->next; - iounmap(data); + memunmap(data); i++; } return -EINVAL; @@ -97,17 +97,17 @@ static int __init get_setup_data_size(int nr, size_t *size) u64 pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = ioremap_cache(pa_data, sizeof(*data)); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; if (nr == i) { *size = data->len; - iounmap(data); + memunmap(data); return 0; } pa_data = data->next; - iounmap(data); + memunmap(data); i++; } return -EINVAL; @@ -127,12 +127,12 @@ static ssize_t type_show(struct kobject *kobj, ret = get_setup_data_paddr(nr, &paddr); if (ret) return ret; - data = ioremap_cache(paddr, sizeof(*data)); + data = memremap(paddr, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; ret = sprintf(buf, "0x%x\n", data->type); - iounmap(data); + memunmap(data); return ret; } @@ -154,7 +154,7 @@ static ssize_t setup_data_data_read(struct file *fp, ret = get_setup_data_paddr(nr, &paddr); if (ret) return ret; - data = ioremap_cache(paddr, sizeof(*data)); + data = memremap(paddr, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; @@ -170,15 +170,15 @@ static ssize_t setup_data_data_read(struct file *fp, goto out; ret = count; - p = ioremap_cache(paddr + sizeof(*data), data->len); + p = memremap(paddr + sizeof(*data), data->len, MEMREMAP_WB); if (!p) { ret = -ENOMEM; goto out; } memcpy(buf, p + off, count); - iounmap(p); + memunmap(p); out: - iounmap(data); + memunmap(data); return ret; } @@ -250,13 +250,13 @@ static int __init get_setup_data_total_num(u64 pa_data, int *nr) *nr = 0; while (pa_data) { *nr += 1; - data = ioremap_cache(pa_data, sizeof(*data)); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) { ret = -ENOMEM; goto out; } pa_data = data->next; - iounmap(data); + memunmap(data); } out: diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index cb0a30473c23..1f790cf9d38f 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -87,7 +87,7 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); } pte = pte_offset_kernel(pmd, vaddr); - set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC)); + set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC)); return 0; err: free_transition_pgtable(image); @@ -115,6 +115,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) .alloc_pgt_page = alloc_pgt_page, .context = image, .page_flag = __PAGE_KERNEL_LARGE_EXEC, + .kernpg_flag = _KERNPG_TABLE_NOENC, }; unsigned long mstart, mend; pgd_t *level4p; @@ -334,7 +335,8 @@ void machine_kexec(struct kimage *image) image->start = relocate_kernel((unsigned long)image->head, (unsigned long)page_list, image->start, - image->preserve_context); + image->preserve_context, + sme_active()); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -602,3 +604,22 @@ void arch_kexec_unprotect_crashkres(void) { kexec_mark_crashkres(false); } + +int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp) +{ + /* + * If SME is active we need to be sure that kexec pages are + * not encrypted because when we boot to the new kernel the + * pages won't be accessed encrypted (initially). + */ + return set_memory_decrypted((unsigned long)vaddr, pages); +} + +void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) +{ + /* + * If SME is active we need to reset the pages back to being + * an encrypted mapping before freeing them. + */ + set_memory_encrypted((unsigned long)vaddr, pages); +} diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 0d904d759ff1..5cbb3177ed17 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -429,16 +429,16 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) } } -static struct mpf_intel *mpf_found; +static unsigned long mpf_base; static unsigned long __init get_mpc_size(unsigned long physptr) { struct mpc_table *mpc; unsigned long size; - mpc = early_ioremap(physptr, PAGE_SIZE); + mpc = early_memremap(physptr, PAGE_SIZE); size = mpc->length; - early_iounmap(mpc, PAGE_SIZE); + early_memunmap(mpc, PAGE_SIZE); apic_printk(APIC_VERBOSE, " mpc: %lx-%lx\n", physptr, physptr + size); return size; @@ -450,7 +450,8 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) unsigned long size; size = get_mpc_size(mpf->physptr); - mpc = early_ioremap(mpf->physptr, size); + mpc = early_memremap(mpf->physptr, size); + /* * Read the physical hardware table. Anything here will * override the defaults. @@ -461,10 +462,10 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) #endif pr_err("BIOS bug, MP table errors detected!...\n"); pr_cont("... disabling SMP support. (tell your hw vendor)\n"); - early_iounmap(mpc, size); + early_memunmap(mpc, size); return -1; } - early_iounmap(mpc, size); + early_memunmap(mpc, size); if (early) return -1; @@ -497,12 +498,12 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) */ void __init default_get_smp_config(unsigned int early) { - struct mpf_intel *mpf = mpf_found; + struct mpf_intel *mpf; if (!smp_found_config) return; - if (!mpf) + if (!mpf_base) return; if (acpi_lapic && early) @@ -515,6 +516,12 @@ void __init default_get_smp_config(unsigned int early) if (acpi_lapic && acpi_ioapic) return; + mpf = early_memremap(mpf_base, sizeof(*mpf)); + if (!mpf) { + pr_err("MPTABLE: error mapping MP table\n"); + return; + } + pr_info("Intel MultiProcessor Specification v1.%d\n", mpf->specification); #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) @@ -529,7 +536,7 @@ void __init default_get_smp_config(unsigned int early) /* * Now see if we need to read further. */ - if (mpf->feature1 != 0) { + if (mpf->feature1) { if (early) { /* * local APIC has default address @@ -542,8 +549,10 @@ void __init default_get_smp_config(unsigned int early) construct_default_ISA_mptable(mpf->feature1); } else if (mpf->physptr) { - if (check_physptr(mpf, early)) + if (check_physptr(mpf, early)) { + early_memunmap(mpf, sizeof(*mpf)); return; + } } else BUG(); @@ -552,6 +561,8 @@ void __init default_get_smp_config(unsigned int early) /* * Only use the first configuration found. */ + + early_memunmap(mpf, sizeof(*mpf)); } static void __init smp_reserve_memory(struct mpf_intel *mpf) @@ -561,15 +572,16 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf) static int __init smp_scan_config(unsigned long base, unsigned long length) { - unsigned int *bp = phys_to_virt(base); + unsigned int *bp; struct mpf_intel *mpf; - unsigned long mem; + int ret = 0; apic_printk(APIC_VERBOSE, "Scan for SMP in [mem %#010lx-%#010lx]\n", base, base + length - 1); BUILD_BUG_ON(sizeof(*mpf) != 16); while (length > 0) { + bp = early_memremap(base, length); mpf = (struct mpf_intel *)bp; if ((*bp == SMP_MAGIC_IDENT) && (mpf->length == 1) && @@ -579,24 +591,26 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) #ifdef CONFIG_X86_LOCAL_APIC smp_found_config = 1; #endif - mpf_found = mpf; + mpf_base = base; - pr_info("found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n", - (unsigned long long) virt_to_phys(mpf), - (unsigned long long) virt_to_phys(mpf) + - sizeof(*mpf) - 1, mpf); + pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n", + base, base + sizeof(*mpf) - 1, mpf); - mem = virt_to_phys(mpf); - memblock_reserve(mem, sizeof(*mpf)); + memblock_reserve(base, sizeof(*mpf)); if (mpf->physptr) smp_reserve_memory(mpf); - return 1; + ret = 1; } - bp += 4; + early_memunmap(bp, length); + + if (ret) + break; + + base += 16; length -= 16; } - return 0; + return ret; } void __init default_find_smp_config(void) @@ -838,29 +852,40 @@ static int __init update_mp_table(void) char oem[10]; struct mpf_intel *mpf; struct mpc_table *mpc, *mpc_new; + unsigned long size; if (!enable_update_mptable) return 0; - mpf = mpf_found; - if (!mpf) + if (!mpf_base) return 0; + mpf = early_memremap(mpf_base, sizeof(*mpf)); + if (!mpf) { + pr_err("MPTABLE: mpf early_memremap() failed\n"); + return 0; + } + /* * Now see if we need to go further. */ - if (mpf->feature1 != 0) - return 0; + if (mpf->feature1) + goto do_unmap_mpf; if (!mpf->physptr) - return 0; + goto do_unmap_mpf; - mpc = phys_to_virt(mpf->physptr); + size = get_mpc_size(mpf->physptr); + mpc = early_memremap(mpf->physptr, size); + if (!mpc) { + pr_err("MPTABLE: mpc early_memremap() failed\n"); + goto do_unmap_mpf; + } if (!smp_check_mpc(mpc, oem, str)) - return 0; + goto do_unmap_mpc; - pr_info("mpf: %llx\n", (u64)virt_to_phys(mpf)); + pr_info("mpf: %llx\n", (u64)mpf_base); pr_info("physptr: %x\n", mpf->physptr); if (mpc_new_phys && mpc->length > mpc_new_length) { @@ -878,21 +903,32 @@ static int __init update_mp_table(void) new = mpf_checksum((unsigned char *)mpc, mpc->length); if (old == new) { pr_info("mpc is readonly, please try alloc_mptable instead\n"); - return 0; + goto do_unmap_mpc; } pr_info("use in-position replacing\n"); } else { + mpc_new = early_memremap(mpc_new_phys, mpc_new_length); + if (!mpc_new) { + pr_err("MPTABLE: new mpc early_memremap() failed\n"); + goto do_unmap_mpc; + } mpf->physptr = mpc_new_phys; - mpc_new = phys_to_virt(mpc_new_phys); memcpy(mpc_new, mpc, mpc->length); + early_memunmap(mpc, size); mpc = mpc_new; + size = mpc_new_length; /* check if we can modify that */ if (mpc_new_phys - mpf->physptr) { struct mpf_intel *mpf_new; /* steal 16 bytes from [0, 1k) */ + mpf_new = early_memremap(0x400 - 16, sizeof(*mpf_new)); + if (!mpf_new) { + pr_err("MPTABLE: new mpf early_memremap() failed\n"); + goto do_unmap_mpc; + } pr_info("mpf new: %x\n", 0x400 - 16); - mpf_new = phys_to_virt(0x400 - 16); memcpy(mpf_new, mpf, 16); + early_memunmap(mpf, sizeof(*mpf)); mpf = mpf_new; mpf->physptr = mpc_new_phys; } @@ -909,6 +945,12 @@ static int __init update_mp_table(void) */ replace_intsrc_all(mpc, mpc_new_phys, mpc_new_length); +do_unmap_mpc: + early_memunmap(mpc, size); + +do_unmap_mpf: + early_memunmap(mpf, sizeof(*mpf)); + return 0; } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 5e16d3f29594..0accc2404b92 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -93,9 +93,12 @@ again: if (gfpflags_allow_blocking(flag)) { page = dma_alloc_from_contiguous(dev, count, get_order(size), flag); - if (page && page_to_phys(page) + size > dma_mask) { - dma_release_from_contiguous(dev, page, count); - page = NULL; + if (page) { + addr = phys_to_dma(dev, page_to_phys(page)); + if (addr + size > dma_mask) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } } } /* fallback */ @@ -104,7 +107,7 @@ again: if (!page) return NULL; - addr = page_to_phys(page); + addr = phys_to_dma(dev, page_to_phys(page)); if (addr + size > dma_mask) { __free_pages(page, get_order(size)); diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index a6d404087fe3..4fc3cb60ea11 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -32,7 +32,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, unsigned long attrs) { - dma_addr_t bus = page_to_phys(page) + offset; + dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset; WARN_ON(size == 0); if (!check_addr("map_single", dev, bus, size)) return NOMMU_MAPPING_ERROR; diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 1e23577e17cf..677077510e30 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -6,12 +6,14 @@ #include <linux/swiotlb.h> #include <linux/bootmem.h> #include <linux/dma-mapping.h> +#include <linux/mem_encrypt.h> #include <asm/iommu.h> #include <asm/swiotlb.h> #include <asm/dma.h> #include <asm/xen/swiotlb-xen.h> #include <asm/iommu_table.h> + int swiotlb __read_mostly; void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, @@ -79,8 +81,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override, pci_swiotlb_late_init); /* - * if 4GB or more detected (and iommu=off not set) return 1 - * and set swiotlb to 1. + * If 4GB or more detected (and iommu=off not set) or if SME is active + * then set swiotlb to 1 and return 1. */ int __init pci_swiotlb_detect_4gb(void) { @@ -89,6 +91,15 @@ int __init pci_swiotlb_detect_4gb(void) if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN) swiotlb = 1; #endif + + /* + * If SME is active then swiotlb will be set to 1 so that bounce + * buffers are allocated and used for devices that do not support + * the addressing range required for the encryption mask. + */ + if (sme_active()) + swiotlb = 1; + return swiotlb; } IOMMU_INIT(pci_swiotlb_detect_4gb, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 3ca198080ea9..bd6b85fac666 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -355,6 +355,7 @@ bool xen_set_default_idle(void) return ret; } #endif + void stop_this_cpu(void *dummy) { local_irq_disable(); @@ -365,8 +366,20 @@ void stop_this_cpu(void *dummy) disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); - for (;;) - halt(); + for (;;) { + /* + * Use wbinvd followed by hlt to stop the processor. This + * provides support for kexec on a processor that supports + * SME. With kexec, going from SME inactive to SME active + * requires clearing cache entries so that addresses without + * the encryption bit set don't corrupt the same physical + * address that has the encryption bit set when caches are + * flushed. To achieve this a wbinvd is performed followed by + * a hlt. Even if the processor is not in the kexec/SME + * scenario this only adds a wbinvd to a halting processor. + */ + asm volatile("wbinvd; hlt" : : : "memory"); + } } /* diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 98111b38ebfd..307d3bac5f04 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -47,6 +47,7 @@ relocate_kernel: * %rsi page_list * %rdx start address * %rcx preserve_context + * %r8 sme_active */ /* Save the CPU context, used for jumping back */ @@ -71,6 +72,9 @@ relocate_kernel: pushq $0 popfq + /* Save SME active flag */ + movq %r8, %r12 + /* * get physical address of control page now * this is impossible after page table switch @@ -132,6 +136,16 @@ identity_mapped: /* Flush the TLB (needed?) */ movq %r9, %cr3 + /* + * If SME is active, there could be old encrypted cache line + * entries that will conflict with the now unencrypted memory + * used by kexec. Flush the caches before copying the kernel. + */ + testq %r12, %r12 + jz 1f + wbinvd +1: + movq %rcx, %r11 call swap_pages diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ecab32282f0f..022ebddb3734 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -69,6 +69,7 @@ #include <linux/crash_dump.h> #include <linux/tboot.h> #include <linux/jiffies.h> +#include <linux/mem_encrypt.h> #include <linux/usb/xhci-dbgp.h> #include <video/edid.h> @@ -375,6 +376,14 @@ static void __init reserve_initrd(void) !ramdisk_image || !ramdisk_size) return; /* No initrd provided by bootloader */ + /* + * If SME is active, this memory will be marked encrypted by the + * kernel when it is accessed (including relocation). However, the + * ramdisk image was loaded decrypted by the bootloader, so make + * sure that it is encrypted before accessing it. + */ + sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image); + initrd_start = 0; mapped_size = memblock_mem_size(max_pfn_mapped); diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 213ddf3e937d..73e4d28112f8 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -21,6 +21,7 @@ #include <asm/compat.h> #include <asm/ia32.h> #include <asm/syscalls.h> +#include <asm/mpx.h> /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. @@ -100,8 +101,8 @@ out: return error; } -static void find_start_end(unsigned long flags, unsigned long *begin, - unsigned long *end) +static void find_start_end(unsigned long addr, unsigned long flags, + unsigned long *begin, unsigned long *end) { if (!in_compat_syscall() && (flags & MAP_32BIT)) { /* This is usually used needed to map code in small @@ -120,7 +121,10 @@ static void find_start_end(unsigned long flags, unsigned long *begin, } *begin = get_mmap_base(1); - *end = in_compat_syscall() ? tasksize_32bit() : tasksize_64bit(); + if (in_compat_syscall()) + *end = task_size_32bit(); + else + *end = task_size_64bit(addr > DEFAULT_MAP_WINDOW); } unsigned long @@ -132,10 +136,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct vm_unmapped_area_info info; unsigned long begin, end; + addr = mpx_unmapped_area_check(addr, len, flags); + if (IS_ERR_VALUE(addr)) + return addr; + if (flags & MAP_FIXED) return addr; - find_start_end(flags, &begin, &end); + find_start_end(addr, flags, &begin, &end); if (len > end) return -ENOMEM; @@ -171,6 +179,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long addr = addr0; struct vm_unmapped_area_info info; + addr = mpx_unmapped_area_check(addr, len, flags); + if (IS_ERR_VALUE(addr)) + return addr; + /* requested length too big for entire address space */ if (len > TASK_SIZE) return -ENOMEM; @@ -195,6 +207,16 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); + + /* + * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area + * in the full address space. + * + * !in_compat_syscall() check to avoid high addresses for x32. + */ + if (addr > DEFAULT_MAP_WINDOW && !in_compat_syscall()) + info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; if (filp) { diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9b1dd114956a..04d750813c9d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -108,7 +108,7 @@ module_param(dbg, bool, 0644); (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1)) -#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) +#define PT64_BASE_ADDR_MASK __sme_clr((((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))) #define PT64_DIR_BASE_ADDR_MASK \ (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1)) #define PT64_LVL_ADDR_MASK(level) \ @@ -126,7 +126,7 @@ module_param(dbg, bool, 0644); * PT32_LEVEL_BITS))) - 1)) #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ - | shadow_x_mask | shadow_nx_mask) + | shadow_x_mask | shadow_nx_mask | shadow_me_mask) #define ACC_EXEC_MASK 1 #define ACC_WRITE_MASK PT_WRITABLE_MASK @@ -186,6 +186,7 @@ static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_mmio_value; static u64 __read_mostly shadow_present_mask; +static u64 __read_mostly shadow_me_mask; /* * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. @@ -349,7 +350,7 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) */ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, - u64 acc_track_mask) + u64 acc_track_mask, u64 me_mask) { BUG_ON(!dirty_mask != !accessed_mask); BUG_ON(!accessed_mask && !acc_track_mask); @@ -362,6 +363,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, shadow_x_mask = x_mask; shadow_present_mask = p_mask; shadow_acc_track_mask = acc_track_mask; + shadow_me_mask = me_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); @@ -2433,7 +2435,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK | - shadow_user_mask | shadow_x_mask; + shadow_user_mask | shadow_x_mask | shadow_me_mask; if (sp_ad_disabled(sp)) spte |= shadow_acc_track_value; @@ -2745,6 +2747,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, pte_access &= ~ACC_WRITE_MASK; spte |= (u64)pfn << PAGE_SHIFT; + spte |= shadow_me_mask; if (pte_access & ACC_WRITE_MASK) { @@ -4106,16 +4109,28 @@ void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + struct rsvd_bits_validate *shadow_zero_check; + int i; /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ - __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + shadow_zero_check = &context->shadow_zero_check; + __reset_rsvds_bits_mask(vcpu, shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); + + if (!shadow_me_mask) + return; + + for (i = context->shadow_root_level; --i >= 0;) { + shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask; + shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask; + } + } EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask); @@ -4133,17 +4148,29 @@ static void reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + struct rsvd_bits_validate *shadow_zero_check; + int i; + + shadow_zero_check = &context->shadow_zero_check; + if (boot_cpu_is_amd()) - __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + __reset_rsvds_bits_mask(vcpu, shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else - __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, + __reset_rsvds_bits_mask_ept(shadow_zero_check, boot_cpu_data.x86_phys_bits, false); + if (!shadow_me_mask) + return; + + for (i = context->shadow_root_level; --i >= 0;) { + shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask; + shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask; + } } /* diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index af256b786a70..8dbd8dbc83eb 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1167,9 +1167,9 @@ static void avic_init_vmcb(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb; struct kvm_arch *vm_data = &svm->vcpu.kvm->arch; - phys_addr_t bpa = page_to_phys(svm->avic_backing_page); - phys_addr_t lpa = page_to_phys(vm_data->avic_logical_id_table_page); - phys_addr_t ppa = page_to_phys(vm_data->avic_physical_id_table_page); + phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page)); + phys_addr_t lpa = __sme_set(page_to_phys(vm_data->avic_logical_id_table_page)); + phys_addr_t ppa = __sme_set(page_to_phys(vm_data->avic_physical_id_table_page)); vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK; vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; @@ -1232,8 +1232,8 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_MWAIT); } - control->iopm_base_pa = iopm_base; - control->msrpm_base_pa = __pa(svm->msrpm); + control->iopm_base_pa = __sme_set(iopm_base); + control->msrpm_base_pa = __sme_set(__pa(svm->msrpm)); control->int_ctl = V_INTR_MASKING_MASK; init_seg(&save->es); @@ -1377,9 +1377,9 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return -EINVAL; new_entry = READ_ONCE(*entry); - new_entry = (page_to_phys(svm->avic_backing_page) & - AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | - AVIC_PHYSICAL_ID_ENTRY_VALID_MASK; + new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & + AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | + AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); WRITE_ONCE(*entry, new_entry); svm->avic_physical_id_cache = entry; @@ -1647,7 +1647,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->vmcb = page_address(page); clear_page(svm->vmcb); - svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; + svm->vmcb_pa = __sme_set(page_to_pfn(page) << PAGE_SHIFT); svm->asid_generation = 0; init_vmcb(svm); @@ -1675,7 +1675,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); + __free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); @@ -2330,7 +2330,7 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; - ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(__sme_clr(cr3)), &pdpte, offset_in_page(cr3) + index * 8, 8); if (ret) return 0; @@ -2342,7 +2342,7 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.nested_cr3 = root; + svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); svm_flush_tlb(vcpu); } @@ -2873,7 +2873,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) svm->nested.msrpm[p] = svm->msrpm[p] | value; } - svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); + svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm)); return true; } @@ -4506,7 +4506,7 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, pr_debug("SVM: %s: use GA mode for irq %u\n", __func__, irq.vector); *svm = to_svm(vcpu); - vcpu_info->pi_desc_addr = page_to_phys((*svm)->avic_backing_page); + vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page)); vcpu_info->vector = irq.vector; return 0; @@ -4557,7 +4557,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, struct amd_iommu_pi_data pi; /* Try to enable guest_mode in IRTE */ - pi.base = page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK; + pi.base = __sme_set(page_to_phys(svm->avic_backing_page) & + AVIC_HPA_MASK); pi.ga_tag = AVIC_GATAG(kvm->arch.avic_vm_id, svm->vcpu.vcpu_id); pi.is_guest_mode = true; @@ -5006,7 +5007,7 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.cr3 = root; + svm->vmcb->save.cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_CR); svm_flush_tlb(vcpu); } @@ -5015,7 +5016,7 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.nested_cr3 = root; + svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); /* Also sync guest cr3 here in case we live migrate */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c6ef2940119b..d40900914a72 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6556,7 +6556,7 @@ void vmx_enable_tdp(void) enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, 0ull, VMX_EPT_EXECUTABLE_MASK, cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, - VMX_EPT_RWX_MASK); + VMX_EPT_RWX_MASK, 0ull); ept_set_mmio_spte_mask(); kvm_enable_tdp(); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 272320eb328c..ef5102f80497 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -54,6 +54,7 @@ #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/sched/stat.h> +#include <linux/mem_encrypt.h> #include <trace/events/kvm.h> @@ -6125,7 +6126,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, - PT_PRESENT_MASK, 0); + PT_PRESENT_MASK, 0, sme_me_mask); kvm_timer_init(); perf_register_guest_info_callbacks(&kvm_guest_cbs); diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c index 5cc78bf57232..3261abb21ef4 100644 --- a/arch/x86/lib/cmdline.c +++ b/arch/x86/lib/cmdline.c @@ -104,7 +104,112 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size, return 0; /* Buffer overrun */ } +/* + * Find a non-boolean option (i.e. option=argument). In accordance with + * standard Linux practice, if this option is repeated, this returns the + * last instance on the command line. + * + * @cmdline: the cmdline string + * @max_cmdline_size: the maximum size of cmdline + * @option: option string to look for + * @buffer: memory buffer to return the option argument + * @bufsize: size of the supplied memory buffer + * + * Returns the length of the argument (regardless of if it was + * truncated to fit in the buffer), or -1 on not found. + */ +static int +__cmdline_find_option(const char *cmdline, int max_cmdline_size, + const char *option, char *buffer, int bufsize) +{ + char c; + int pos = 0, len = -1; + const char *opptr = NULL; + char *bufptr = buffer; + enum { + st_wordstart = 0, /* Start of word/after whitespace */ + st_wordcmp, /* Comparing this word */ + st_wordskip, /* Miscompare, skip */ + st_bufcpy, /* Copying this to buffer */ + } state = st_wordstart; + + if (!cmdline) + return -1; /* No command line */ + + /* + * This 'pos' check ensures we do not overrun + * a non-NULL-terminated 'cmdline' + */ + while (pos++ < max_cmdline_size) { + c = *(char *)cmdline++; + if (!c) + break; + + switch (state) { + case st_wordstart: + if (myisspace(c)) + break; + + state = st_wordcmp; + opptr = option; + /* fall through */ + + case st_wordcmp: + if ((c == '=') && !*opptr) { + /* + * We matched all the way to the end of the + * option we were looking for, prepare to + * copy the argument. + */ + len = 0; + bufptr = buffer; + state = st_bufcpy; + break; + } else if (c == *opptr++) { + /* + * We are currently matching, so continue + * to the next character on the cmdline. + */ + break; + } + state = st_wordskip; + /* fall through */ + + case st_wordskip: + if (myisspace(c)) + state = st_wordstart; + break; + + case st_bufcpy: + if (myisspace(c)) { + state = st_wordstart; + } else { + /* + * Increment len, but don't overrun the + * supplied buffer and leave room for the + * NULL terminator. + */ + if (++len < bufsize) + *bufptr++ = c; + } + break; + } + } + + if (bufsize) + *bufptr = '\0'; + + return len; +} + int cmdline_find_option_bool(const char *cmdline, const char *option) { return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option); } + +int cmdline_find_option(const char *cmdline, const char *option, char *buffer, + int bufsize) +{ + return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option, + buffer, bufsize); +} diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 0fbdcb64f9f8..72bf8c01c6e3 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -39,3 +39,5 @@ obj-$(CONFIG_X86_INTEL_MPX) += mpx.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0470826d2bdc..5e3ac6fe6c9e 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -13,12 +13,12 @@ */ #include <linux/debugfs.h> +#include <linux/kasan.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/seq_file.h> -#include <asm/kasan.h> #include <asm/pgtable.h> /* @@ -138,7 +138,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) { pgprotval_t pr = pgprot_val(prot); static const char * const level_name[] = - { "cr3", "pgd", "pud", "pmd", "pte" }; + { "cr3", "pgd", "p4d", "pud", "pmd", "pte" }; if (!pgprot_val(prot)) { /* Not present */ @@ -162,12 +162,12 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) pt_dump_cont_printf(m, dmsg, " "); /* Bit 7 has a different meaning on level 3 vs 4 */ - if (level <= 3 && pr & _PAGE_PSE) + if (level <= 4 && pr & _PAGE_PSE) pt_dump_cont_printf(m, dmsg, "PSE "); else pt_dump_cont_printf(m, dmsg, " "); - if ((level == 4 && pr & _PAGE_PAT) || - ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE)) + if ((level == 5 && pr & _PAGE_PAT) || + ((level == 4 || level == 3) && pr & _PAGE_PAT_LARGE)) pt_dump_cont_printf(m, dmsg, "PAT "); else pt_dump_cont_printf(m, dmsg, " "); @@ -188,11 +188,12 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) */ static unsigned long normalize_addr(unsigned long u) { -#ifdef CONFIG_X86_64 - return (signed long)(u << 16) >> 16; -#else - return u; -#endif + int shift; + if (!IS_ENABLED(CONFIG_X86_64)) + return u; + + shift = 64 - (__VIRTUAL_MASK_SHIFT + 1); + return (signed long)(u << shift) >> shift; } /* @@ -297,32 +298,62 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, for (i = 0; i < PTRS_PER_PTE; i++) { prot = pte_flags(*start); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); - note_page(m, st, __pgprot(prot), 4); + note_page(m, st, __pgprot(prot), 5); start++; } } +#ifdef CONFIG_KASAN + +/* + * This is an optimization for KASAN=y case. Since all kasan page tables + * eventually point to the kasan_zero_page we could call note_page() + * right away without walking through lower level page tables. This saves + * us dozens of seconds (minutes for 5-level config) while checking for + * W+X mapping or reading kernel_page_tables debugfs file. + */ +static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, + void *pt) +{ + if (__pa(pt) == __pa(kasan_zero_pmd) || +#ifdef CONFIG_X86_5LEVEL + __pa(pt) == __pa(kasan_zero_p4d) || +#endif + __pa(pt) == __pa(kasan_zero_pud)) { + pgprotval_t prot = pte_flags(kasan_zero_pte[0]); + note_page(m, st, __pgprot(prot), 5); + return true; + } + return false; +} +#else +static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, + void *pt) +{ + return false; +} +#endif #if PTRS_PER_PMD > 1 static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, unsigned long P) { int i; - pmd_t *start; + pmd_t *start, *pmd_start; pgprotval_t prot; - start = (pmd_t *)pud_page_vaddr(addr); + pmd_start = start = (pmd_t *)pud_page_vaddr(addr); for (i = 0; i < PTRS_PER_PMD; i++) { st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); if (!pmd_none(*start)) { if (pmd_large(*start) || !pmd_present(*start)) { prot = pmd_flags(*start); - note_page(m, st, __pgprot(prot), 3); - } else { + note_page(m, st, __pgprot(prot), 4); + } else if (!kasan_page_table(m, st, pmd_start)) { walk_pte_level(m, st, *start, P + i * PMD_LEVEL_MULT); } } else - note_page(m, st, __pgprot(0), 3); + note_page(m, st, __pgprot(0), 4); start++; } } @@ -335,39 +366,27 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, #if PTRS_PER_PUD > 1 -/* - * This is an optimization for CONFIG_DEBUG_WX=y + CONFIG_KASAN=y - * KASAN fills page tables with the same values. Since there is no - * point in checking page table more than once we just skip repeated - * entries. This saves us dozens of seconds during boot. - */ -static bool pud_already_checked(pud_t *prev_pud, pud_t *pud, bool checkwx) -{ - return checkwx && prev_pud && (pud_val(*prev_pud) == pud_val(*pud)); -} - static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, unsigned long P) { int i; - pud_t *start; + pud_t *start, *pud_start; pgprotval_t prot; pud_t *prev_pud = NULL; - start = (pud_t *)p4d_page_vaddr(addr); + pud_start = start = (pud_t *)p4d_page_vaddr(addr); for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); - if (!pud_none(*start) && - !pud_already_checked(prev_pud, start, st->check_wx)) { + if (!pud_none(*start)) { if (pud_large(*start) || !pud_present(*start)) { prot = pud_flags(*start); - note_page(m, st, __pgprot(prot), 2); - } else { + note_page(m, st, __pgprot(prot), 3); + } else if (!kasan_page_table(m, st, pud_start)) { walk_pmd_level(m, st, *start, P + i * PUD_LEVEL_MULT); } } else - note_page(m, st, __pgprot(0), 2); + note_page(m, st, __pgprot(0), 3); prev_pud = start; start++; @@ -385,10 +404,10 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, unsigned long P) { int i; - p4d_t *start; + p4d_t *start, *p4d_start; pgprotval_t prot; - start = (p4d_t *)pgd_page_vaddr(addr); + p4d_start = start = (p4d_t *)pgd_page_vaddr(addr); for (i = 0; i < PTRS_PER_P4D; i++) { st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT); @@ -396,7 +415,7 @@ static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, if (p4d_large(*start) || !p4d_present(*start)) { prot = p4d_flags(*start); note_page(m, st, __pgprot(prot), 2); - } else { + } else if (!kasan_page_table(m, st, p4d_start)) { walk_pud_level(m, st, *start, P + i * P4D_LEVEL_MULT); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2a1fa10c6a98..0cdf14cf3270 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -396,14 +396,18 @@ static void dump_pagetable(unsigned long address) pte_t *pte; #ifdef CONFIG_X86_PAE - printk("*pdpt = %016Lx ", pgd_val(*pgd)); + pr_info("*pdpt = %016Lx ", pgd_val(*pgd)); if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd)) goto out; +#define pr_pde pr_cont +#else +#define pr_pde pr_info #endif p4d = p4d_offset(pgd, address); pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); - printk(KERN_CONT "*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); + pr_pde("*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); +#undef pr_pde /* * We must not directly access the pte in the highpte @@ -415,9 +419,9 @@ static void dump_pagetable(unsigned long address) goto out; pte = pte_offset_kernel(pmd, address); - printk("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte)); + pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte)); out: - printk("\n"); + pr_cont("\n"); } #else /* CONFIG_X86_64: */ @@ -565,7 +569,7 @@ static void dump_pagetable(unsigned long address) if (bad_address(pgd)) goto bad; - printk("PGD %lx ", pgd_val(*pgd)); + pr_info("PGD %lx ", pgd_val(*pgd)); if (!pgd_present(*pgd)) goto out; @@ -574,7 +578,7 @@ static void dump_pagetable(unsigned long address) if (bad_address(p4d)) goto bad; - printk("P4D %lx ", p4d_val(*p4d)); + pr_cont("P4D %lx ", p4d_val(*p4d)); if (!p4d_present(*p4d) || p4d_large(*p4d)) goto out; @@ -582,7 +586,7 @@ static void dump_pagetable(unsigned long address) if (bad_address(pud)) goto bad; - printk("PUD %lx ", pud_val(*pud)); + pr_cont("PUD %lx ", pud_val(*pud)); if (!pud_present(*pud) || pud_large(*pud)) goto out; @@ -590,7 +594,7 @@ static void dump_pagetable(unsigned long address) if (bad_address(pmd)) goto bad; - printk("PMD %lx ", pmd_val(*pmd)); + pr_cont("PMD %lx ", pmd_val(*pmd)); if (!pmd_present(*pmd) || pmd_large(*pmd)) goto out; @@ -598,12 +602,12 @@ static void dump_pagetable(unsigned long address) if (bad_address(pte)) goto bad; - printk("PTE %lx", pte_val(*pte)); + pr_cont("PTE %lx", pte_val(*pte)); out: - printk("\n"); + pr_cont("\n"); return; bad: - printk("BAD\n"); + pr_info("BAD\n"); } #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 2824607df108..6d06cf33e3de 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -18,6 +18,7 @@ #include <asm/tlbflush.h> #include <asm/pgalloc.h> #include <asm/elf.h> +#include <asm/mpx.h> #if 0 /* This is just for testing */ struct page * @@ -85,25 +86,38 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, info.flags = 0; info.length = len; info.low_limit = get_mmap_base(1); + + /* + * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area + * in the full address space. + */ info.high_limit = in_compat_syscall() ? - tasksize_32bit() : tasksize_64bit(); + task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW); + info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); } static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, - unsigned long addr0, unsigned long len, + unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); struct vm_unmapped_area_info info; - unsigned long addr; info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); + + /* + * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area + * in the full address space. + */ + if (addr > DEFAULT_MAP_WINDOW && !in_compat_syscall()) + info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; + info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); @@ -118,7 +132,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = TASK_UNMAPPED_BASE; - info.high_limit = TASK_SIZE; + info.high_limit = TASK_SIZE_LOW; addr = vm_unmapped_area(&info); } @@ -135,6 +149,11 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (len & ~huge_page_mask(h)) return -EINVAL; + + addr = mpx_unmapped_area_check(addr, len, flags); + if (IS_ERR_VALUE(addr)) + return addr; + if (len > TASK_SIZE) return -ENOMEM; diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index adab1595f4bd..31cea988fa36 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -51,7 +51,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, if (!pmd) return -ENOMEM; ident_pmd_init(info, pmd, addr, next); - set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + set_pud(pud, __pud(__pa(pmd) | info->kernpg_flag)); } return 0; @@ -79,7 +79,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page, if (!pud) return -ENOMEM; ident_pud_init(info, pud, addr, next); - set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); + set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag)); } return 0; @@ -93,6 +93,10 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, unsigned long next; int result; + /* Set the default pagetable flags if not supplied */ + if (!info->kernpg_flag) + info->kernpg_flag = _KERNPG_TABLE; + for (; addr < end; addr = next) { pgd_t *pgd = pgd_page + pgd_index(addr); p4d_t *p4d; @@ -116,14 +120,14 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, if (result) return result; if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE)); + set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag)); } else { /* * With p4d folded, pgd is equal to p4d. * The pgd entry has to point to the pud page table in this case. */ pud_t *pud = pud_offset(p4d, 0); - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag)); } } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index bf3f1065d6ad..7777ccc0e9f9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -815,7 +815,7 @@ void __init zone_sizes_init(void) DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, - .state = 0, + .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; EXPORT_SYMBOL_GPL(cpu_tlbstate); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 4c1b5fd0c7ad..34f0e1847dd6 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -13,6 +13,8 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mmiotrace.h> +#include <linux/mem_encrypt.h> +#include <linux/efi.h> #include <asm/set_memory.h> #include <asm/e820/api.h> @@ -21,6 +23,7 @@ #include <asm/tlbflush.h> #include <asm/pgalloc.h> #include <asm/pat.h> +#include <asm/setup.h> #include "physaddr.h" @@ -106,12 +109,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, } /* - * Don't remap the low PCI/ISA area, it's always mapped.. - */ - if (is_ISA_range(phys_addr, last_addr)) - return (__force void __iomem *)phys_to_virt(phys_addr); - - /* * Don't allow anybody to remap normal RAM that we're using.. */ pfn = phys_addr >> PAGE_SHIFT; @@ -340,13 +337,17 @@ void iounmap(volatile void __iomem *addr) return; /* - * __ioremap special-cases the PCI/ISA range by not instantiating a - * vm_area and by simply returning an address into the kernel mapping - * of ISA space. So handle that here. + * The PCI/ISA range special-casing was removed from __ioremap() + * so this check, in theory, can be removed. However, there are + * cases where iounmap() is called for addresses not obtained via + * ioremap() (vga16fb for example). Add a warning so that these + * cases can be caught and fixed. */ if ((void __force *)addr >= phys_to_virt(ISA_START_ADDRESS) && - (void __force *)addr < phys_to_virt(ISA_END_ADDRESS)) + (void __force *)addr < phys_to_virt(ISA_END_ADDRESS)) { + WARN(1, "iounmap() called for ISA range not obtained using ioremap()\n"); return; + } addr = (volatile void __iomem *) (PAGE_MASK & (unsigned long __force)addr); @@ -399,12 +400,10 @@ void *xlate_dev_mem_ptr(phys_addr_t phys) unsigned long offset = phys & ~PAGE_MASK; void *vaddr; - /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ - if (page_is_ram(start >> PAGE_SHIFT)) - return __va(phys); + /* memremap() maps if RAM, otherwise falls back to ioremap() */ + vaddr = memremap(start, PAGE_SIZE, MEMREMAP_WB); - vaddr = ioremap_cache(start, PAGE_SIZE); - /* Only add the offset on success and return NULL if the ioremap() failed: */ + /* Only add the offset on success and return NULL if memremap() failed */ if (vaddr) vaddr += offset; @@ -413,11 +412,263 @@ void *xlate_dev_mem_ptr(phys_addr_t phys) void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) { - if (page_is_ram(phys >> PAGE_SHIFT)) - return; + memunmap((void *)((unsigned long)addr & PAGE_MASK)); +} + +/* + * Examine the physical address to determine if it is an area of memory + * that should be mapped decrypted. If the memory is not part of the + * kernel usable area it was accessed and created decrypted, so these + * areas should be mapped decrypted. And since the encryption key can + * change across reboots, persistent memory should also be mapped + * decrypted. + */ +static bool memremap_should_map_decrypted(resource_size_t phys_addr, + unsigned long size) +{ + int is_pmem; + + /* + * Check if the address is part of a persistent memory region. + * This check covers areas added by E820, EFI and ACPI. + */ + is_pmem = region_intersects(phys_addr, size, IORESOURCE_MEM, + IORES_DESC_PERSISTENT_MEMORY); + if (is_pmem != REGION_DISJOINT) + return true; + + /* + * Check if the non-volatile attribute is set for an EFI + * reserved area. + */ + if (efi_enabled(EFI_BOOT)) { + switch (efi_mem_type(phys_addr)) { + case EFI_RESERVED_TYPE: + if (efi_mem_attributes(phys_addr) & EFI_MEMORY_NV) + return true; + break; + default: + break; + } + } + + /* Check if the address is outside kernel usable area */ + switch (e820__get_entry_type(phys_addr, phys_addr + size - 1)) { + case E820_TYPE_RESERVED: + case E820_TYPE_ACPI: + case E820_TYPE_NVS: + case E820_TYPE_UNUSABLE: + case E820_TYPE_PRAM: + return true; + default: + break; + } + + return false; +} + +/* + * Examine the physical address to determine if it is EFI data. Check + * it against the boot params structure and EFI tables and memory types. + */ +static bool memremap_is_efi_data(resource_size_t phys_addr, + unsigned long size) +{ + u64 paddr; + + /* Check if the address is part of EFI boot/runtime data */ + if (!efi_enabled(EFI_BOOT)) + return false; + + paddr = boot_params.efi_info.efi_memmap_hi; + paddr <<= 32; + paddr |= boot_params.efi_info.efi_memmap; + if (phys_addr == paddr) + return true; + + paddr = boot_params.efi_info.efi_systab_hi; + paddr <<= 32; + paddr |= boot_params.efi_info.efi_systab; + if (phys_addr == paddr) + return true; + + if (efi_is_table_address(phys_addr)) + return true; + + switch (efi_mem_type(phys_addr)) { + case EFI_BOOT_SERVICES_DATA: + case EFI_RUNTIME_SERVICES_DATA: + return true; + default: + break; + } + + return false; +} + +/* + * Examine the physical address to determine if it is boot data by checking + * it against the boot params setup_data chain. + */ +static bool memremap_is_setup_data(resource_size_t phys_addr, + unsigned long size) +{ + struct setup_data *data; + u64 paddr, paddr_next; + + paddr = boot_params.hdr.setup_data; + while (paddr) { + unsigned int len; + + if (phys_addr == paddr) + return true; + + data = memremap(paddr, sizeof(*data), + MEMREMAP_WB | MEMREMAP_DEC); + + paddr_next = data->next; + len = data->len; + + memunmap(data); + + if ((phys_addr > paddr) && (phys_addr < (paddr + len))) + return true; + + paddr = paddr_next; + } + + return false; +} + +/* + * Examine the physical address to determine if it is boot data by checking + * it against the boot params setup_data chain (early boot version). + */ +static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, + unsigned long size) +{ + struct setup_data *data; + u64 paddr, paddr_next; + + paddr = boot_params.hdr.setup_data; + while (paddr) { + unsigned int len; + + if (phys_addr == paddr) + return true; + + data = early_memremap_decrypted(paddr, sizeof(*data)); + + paddr_next = data->next; + len = data->len; + + early_memunmap(data, sizeof(*data)); + + if ((phys_addr > paddr) && (phys_addr < (paddr + len))) + return true; + + paddr = paddr_next; + } + + return false; +} + +/* + * Architecture function to determine if RAM remap is allowed. By default, a + * RAM remap will map the data as encrypted. Determine if a RAM remap should + * not be done so that the data will be mapped decrypted. + */ +bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, + unsigned long flags) +{ + if (!sme_active()) + return true; + + if (flags & MEMREMAP_ENC) + return true; + + if (flags & MEMREMAP_DEC) + return false; + + if (memremap_is_setup_data(phys_addr, size) || + memremap_is_efi_data(phys_addr, size) || + memremap_should_map_decrypted(phys_addr, size)) + return false; + + return true; +} + +/* + * Architecture override of __weak function to adjust the protection attributes + * used when remapping memory. By default, early_memremap() will map the data + * as encrypted. Determine if an encrypted mapping should not be done and set + * the appropriate protection attributes. + */ +pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, + unsigned long size, + pgprot_t prot) +{ + if (!sme_active()) + return prot; + + if (early_memremap_is_setup_data(phys_addr, size) || + memremap_is_efi_data(phys_addr, size) || + memremap_should_map_decrypted(phys_addr, size)) + prot = pgprot_decrypted(prot); + else + prot = pgprot_encrypted(prot); + + return prot; +} + +bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size) +{ + return arch_memremap_can_ram_remap(phys_addr, size, 0); +} + +#ifdef CONFIG_ARCH_USE_MEMREMAP_PROT +/* Remap memory with encryption */ +void __init *early_memremap_encrypted(resource_size_t phys_addr, + unsigned long size) +{ + return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC); +} + +/* + * Remap memory with encryption and write-protected - cannot be called + * before pat_init() is called + */ +void __init *early_memremap_encrypted_wp(resource_size_t phys_addr, + unsigned long size) +{ + /* Be sure the write-protect PAT entry is set for write-protect */ + if (__pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] != _PAGE_CACHE_MODE_WP) + return NULL; + + return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC_WP); +} + +/* Remap memory without encryption */ +void __init *early_memremap_decrypted(resource_size_t phys_addr, + unsigned long size) +{ + return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC); +} + +/* + * Remap memory without encryption and write-protected - cannot be called + * before pat_init() is called + */ +void __init *early_memremap_decrypted_wp(resource_size_t phys_addr, + unsigned long size) +{ + /* Be sure the write-protect PAT entry is set for write-protect */ + if (__pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] != _PAGE_CACHE_MODE_WP) + return NULL; - iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK)); + return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC_WP); } +#endif /* CONFIG_ARCH_USE_MEMREMAP_PROT */ static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 02c9d7553409..bc84b73684b7 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -11,8 +11,8 @@ #include <asm/e820/types.h> #include <asm/tlbflush.h> #include <asm/sections.h> +#include <asm/pgtable.h> -extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern struct range pfn_mapped[E820_MAX_ENTRIES]; static int __init map_range(struct range *range) @@ -87,7 +87,7 @@ static struct notifier_block kasan_die_notifier = { void __init kasan_early_init(void) { int i; - pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL; + pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL | _PAGE_ENC; pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE; pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE; p4dval_t p4d_val = __pa_nodebug(kasan_zero_pud) | _KERNPG_TABLE; @@ -153,7 +153,7 @@ void __init kasan_init(void) */ memset(kasan_zero_page, 0, PAGE_SIZE); for (i = 0; i < PTRS_PER_PTE; i++) { - pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO); + pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO | _PAGE_ENC); set_pte(&kasan_zero_pte[i], pte); } /* Flush TLBs again to be sure that write protection applied. */ diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c new file mode 100644 index 000000000000..0fbd09269757 --- /dev/null +++ b/arch/x86/mm/mem_encrypt.c @@ -0,0 +1,593 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/dma-mapping.h> +#include <linux/swiotlb.h> +#include <linux/mem_encrypt.h> + +#include <asm/tlbflush.h> +#include <asm/fixmap.h> +#include <asm/setup.h> +#include <asm/bootparam.h> +#include <asm/set_memory.h> +#include <asm/cacheflush.h> +#include <asm/sections.h> +#include <asm/processor-flags.h> +#include <asm/msr.h> +#include <asm/cmdline.h> + +static char sme_cmdline_arg[] __initdata = "mem_encrypt"; +static char sme_cmdline_on[] __initdata = "on"; +static char sme_cmdline_off[] __initdata = "off"; + +/* + * Since SME related variables are set early in the boot process they must + * reside in the .data section so as not to be zeroed out when the .bss + * section is later cleared. + */ +unsigned long sme_me_mask __section(.data) = 0; +EXPORT_SYMBOL_GPL(sme_me_mask); + +/* Buffer used for early in-place encryption by BSP, no locking needed */ +static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE); + +/* + * This routine does not change the underlying encryption setting of the + * page(s) that map this memory. It assumes that eventually the memory is + * meant to be accessed as either encrypted or decrypted but the contents + * are currently not in the desired state. + * + * This routine follows the steps outlined in the AMD64 Architecture + * Programmer's Manual Volume 2, Section 7.10.8 Encrypt-in-Place. + */ +static void __init __sme_early_enc_dec(resource_size_t paddr, + unsigned long size, bool enc) +{ + void *src, *dst; + size_t len; + + if (!sme_me_mask) + return; + + local_flush_tlb(); + wbinvd(); + + /* + * There are limited number of early mapping slots, so map (at most) + * one page at time. + */ + while (size) { + len = min_t(size_t, sizeof(sme_early_buffer), size); + + /* + * Create mappings for the current and desired format of + * the memory. Use a write-protected mapping for the source. + */ + src = enc ? early_memremap_decrypted_wp(paddr, len) : + early_memremap_encrypted_wp(paddr, len); + + dst = enc ? early_memremap_encrypted(paddr, len) : + early_memremap_decrypted(paddr, len); + + /* + * If a mapping can't be obtained to perform the operation, + * then eventual access of that area in the desired mode + * will cause a crash. + */ + BUG_ON(!src || !dst); + + /* + * Use a temporary buffer, of cache-line multiple size, to + * avoid data corruption as documented in the APM. + */ + memcpy(sme_early_buffer, src, len); + memcpy(dst, sme_early_buffer, len); + + early_memunmap(dst, len); + early_memunmap(src, len); + + paddr += len; + size -= len; + } +} + +void __init sme_early_encrypt(resource_size_t paddr, unsigned long size) +{ + __sme_early_enc_dec(paddr, size, true); +} + +void __init sme_early_decrypt(resource_size_t paddr, unsigned long size) +{ + __sme_early_enc_dec(paddr, size, false); +} + +static void __init __sme_early_map_unmap_mem(void *vaddr, unsigned long size, + bool map) +{ + unsigned long paddr = (unsigned long)vaddr - __PAGE_OFFSET; + pmdval_t pmd_flags, pmd; + + /* Use early_pmd_flags but remove the encryption mask */ + pmd_flags = __sme_clr(early_pmd_flags); + + do { + pmd = map ? (paddr & PMD_MASK) + pmd_flags : 0; + __early_make_pgtable((unsigned long)vaddr, pmd); + + vaddr += PMD_SIZE; + paddr += PMD_SIZE; + size = (size <= PMD_SIZE) ? 0 : size - PMD_SIZE; + } while (size); + + __native_flush_tlb(); +} + +void __init sme_unmap_bootdata(char *real_mode_data) +{ + struct boot_params *boot_data; + unsigned long cmdline_paddr; + + if (!sme_active()) + return; + + /* Get the command line address before unmapping the real_mode_data */ + boot_data = (struct boot_params *)real_mode_data; + cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32); + + __sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), false); + + if (!cmdline_paddr) + return; + + __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, false); +} + +void __init sme_map_bootdata(char *real_mode_data) +{ + struct boot_params *boot_data; + unsigned long cmdline_paddr; + + if (!sme_active()) + return; + + __sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), true); + + /* Get the command line address after mapping the real_mode_data */ + boot_data = (struct boot_params *)real_mode_data; + cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32); + + if (!cmdline_paddr) + return; + + __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true); +} + +void __init sme_early_init(void) +{ + unsigned int i; + + if (!sme_me_mask) + return; + + early_pmd_flags = __sme_set(early_pmd_flags); + + __supported_pte_mask = __sme_set(__supported_pte_mask); + + /* Update the protection map with memory encryption mask */ + for (i = 0; i < ARRAY_SIZE(protection_map); i++) + protection_map[i] = pgprot_encrypted(protection_map[i]); +} + +/* Architecture __weak replacement functions */ +void __init mem_encrypt_init(void) +{ + if (!sme_me_mask) + return; + + /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ + swiotlb_update_mem_attributes(); + + pr_info("AMD Secure Memory Encryption (SME) active\n"); +} + +void swiotlb_set_mem_attributes(void *vaddr, unsigned long size) +{ + WARN(PAGE_ALIGN(size) != size, + "size is not page-aligned (%#lx)\n", size); + + /* Make the SWIOTLB buffer area decrypted */ + set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT); +} + +static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start, + unsigned long end) +{ + unsigned long pgd_start, pgd_end, pgd_size; + pgd_t *pgd_p; + + pgd_start = start & PGDIR_MASK; + pgd_end = end & PGDIR_MASK; + + pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1); + pgd_size *= sizeof(pgd_t); + + pgd_p = pgd_base + pgd_index(start); + + memset(pgd_p, 0, pgd_size); +} + +#define PGD_FLAGS _KERNPG_TABLE_NOENC +#define P4D_FLAGS _KERNPG_TABLE_NOENC +#define PUD_FLAGS _KERNPG_TABLE_NOENC +#define PMD_FLAGS (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) + +static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, + unsigned long vaddr, pmdval_t pmd_val) +{ + pgd_t *pgd_p; + p4d_t *p4d_p; + pud_t *pud_p; + pmd_t *pmd_p; + + pgd_p = pgd_base + pgd_index(vaddr); + if (native_pgd_val(*pgd_p)) { + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); + else + pud_p = (pud_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); + } else { + pgd_t pgd; + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d_p = pgtable_area; + memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); + pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; + + pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS); + } else { + pud_p = pgtable_area; + memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); + pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + + pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS); + } + native_set_pgd(pgd_p, pgd); + } + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d_p += p4d_index(vaddr); + if (native_p4d_val(*p4d_p)) { + pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK); + } else { + p4d_t p4d; + + pud_p = pgtable_area; + memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); + pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + + p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS); + native_set_p4d(p4d_p, p4d); + } + } + + pud_p += pud_index(vaddr); + if (native_pud_val(*pud_p)) { + if (native_pud_val(*pud_p) & _PAGE_PSE) + goto out; + + pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK); + } else { + pud_t pud; + + pmd_p = pgtable_area; + memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); + pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; + + pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS); + native_set_pud(pud_p, pud); + } + + pmd_p += pmd_index(vaddr); + if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE)) + native_set_pmd(pmd_p, native_make_pmd(pmd_val)); + +out: + return pgtable_area; +} + +static unsigned long __init sme_pgtable_calc(unsigned long len) +{ + unsigned long p4d_size, pud_size, pmd_size; + unsigned long total; + + /* + * Perform a relatively simplistic calculation of the pagetable + * entries that are needed. That mappings will be covered by 2MB + * PMD entries so we can conservatively calculate the required + * number of P4D, PUD and PMD structures needed to perform the + * mappings. Incrementing the count for each covers the case where + * the addresses cross entries. + */ + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; + p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D; + pud_size = (ALIGN(len, P4D_SIZE) / P4D_SIZE) + 1; + pud_size *= sizeof(pud_t) * PTRS_PER_PUD; + } else { + p4d_size = 0; + pud_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; + pud_size *= sizeof(pud_t) * PTRS_PER_PUD; + } + pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1; + pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; + + total = p4d_size + pud_size + pmd_size; + + /* + * Now calculate the added pagetable structures needed to populate + * the new pagetables. + */ + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE; + p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D; + pud_size = ALIGN(total, P4D_SIZE) / P4D_SIZE; + pud_size *= sizeof(pud_t) * PTRS_PER_PUD; + } else { + p4d_size = 0; + pud_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE; + pud_size *= sizeof(pud_t) * PTRS_PER_PUD; + } + pmd_size = ALIGN(total, PUD_SIZE) / PUD_SIZE; + pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; + + total += p4d_size + pud_size + pmd_size; + + return total; +} + +void __init sme_encrypt_kernel(void) +{ + unsigned long workarea_start, workarea_end, workarea_len; + unsigned long execute_start, execute_end, execute_len; + unsigned long kernel_start, kernel_end, kernel_len; + unsigned long pgtable_area_len; + unsigned long paddr, pmd_flags; + unsigned long decrypted_base; + void *pgtable_area; + pgd_t *pgd; + + if (!sme_active()) + return; + + /* + * Prepare for encrypting the kernel by building new pagetables with + * the necessary attributes needed to encrypt the kernel in place. + * + * One range of virtual addresses will map the memory occupied + * by the kernel as encrypted. + * + * Another range of virtual addresses will map the memory occupied + * by the kernel as decrypted and write-protected. + * + * The use of write-protect attribute will prevent any of the + * memory from being cached. + */ + + /* Physical addresses gives us the identity mapped virtual addresses */ + kernel_start = __pa_symbol(_text); + kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); + kernel_len = kernel_end - kernel_start; + + /* Set the encryption workarea to be immediately after the kernel */ + workarea_start = kernel_end; + + /* + * Calculate required number of workarea bytes needed: + * executable encryption area size: + * stack page (PAGE_SIZE) + * encryption routine page (PAGE_SIZE) + * intermediate copy buffer (PMD_PAGE_SIZE) + * pagetable structures for the encryption of the kernel + * pagetable structures for workarea (in case not currently mapped) + */ + execute_start = workarea_start; + execute_end = execute_start + (PAGE_SIZE * 2) + PMD_PAGE_SIZE; + execute_len = execute_end - execute_start; + + /* + * One PGD for both encrypted and decrypted mappings and a set of + * PUDs and PMDs for each of the encrypted and decrypted mappings. + */ + pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD; + pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2; + + /* PUDs and PMDs needed in the current pagetables for the workarea */ + pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len); + + /* + * The total workarea includes the executable encryption area and + * the pagetable area. + */ + workarea_len = execute_len + pgtable_area_len; + workarea_end = workarea_start + workarea_len; + + /* + * Set the address to the start of where newly created pagetable + * structures (PGDs, PUDs and PMDs) will be allocated. New pagetable + * structures are created when the workarea is added to the current + * pagetables and when the new encrypted and decrypted kernel + * mappings are populated. + */ + pgtable_area = (void *)execute_end; + + /* + * Make sure the current pagetable structure has entries for + * addressing the workarea. + */ + pgd = (pgd_t *)native_read_cr3_pa(); + paddr = workarea_start; + while (paddr < workarea_end) { + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr, + paddr + PMD_FLAGS); + + paddr += PMD_PAGE_SIZE; + } + + /* Flush the TLB - no globals so cr3 is enough */ + native_write_cr3(__native_read_cr3()); + + /* + * A new pagetable structure is being built to allow for the kernel + * to be encrypted. It starts with an empty PGD that will then be + * populated with new PUDs and PMDs as the encrypted and decrypted + * kernel mappings are created. + */ + pgd = pgtable_area; + memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD); + pgtable_area += sizeof(*pgd) * PTRS_PER_PGD; + + /* Add encrypted kernel (identity) mappings */ + pmd_flags = PMD_FLAGS | _PAGE_ENC; + paddr = kernel_start; + while (paddr < kernel_end) { + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr, + paddr + pmd_flags); + + paddr += PMD_PAGE_SIZE; + } + + /* + * A different PGD index/entry must be used to get different + * pagetable entries for the decrypted mapping. Choose the next + * PGD index and convert it to a virtual address to be used as + * the base of the mapping. + */ + decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1); + decrypted_base <<= PGDIR_SHIFT; + + /* Add decrypted, write-protected kernel (non-identity) mappings */ + pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT); + paddr = kernel_start; + while (paddr < kernel_end) { + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr + decrypted_base, + paddr + pmd_flags); + + paddr += PMD_PAGE_SIZE; + } + + /* Add decrypted workarea mappings to both kernel mappings */ + paddr = workarea_start; + while (paddr < workarea_end) { + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr, + paddr + PMD_FLAGS); + + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr + decrypted_base, + paddr + PMD_FLAGS); + + paddr += PMD_PAGE_SIZE; + } + + /* Perform the encryption */ + sme_encrypt_execute(kernel_start, kernel_start + decrypted_base, + kernel_len, workarea_start, (unsigned long)pgd); + + /* + * At this point we are running encrypted. Remove the mappings for + * the decrypted areas - all that is needed for this is to remove + * the PGD entry/entries. + */ + sme_clear_pgd(pgd, kernel_start + decrypted_base, + kernel_end + decrypted_base); + + sme_clear_pgd(pgd, workarea_start + decrypted_base, + workarea_end + decrypted_base); + + /* Flush the TLB - no globals so cr3 is enough */ + native_write_cr3(__native_read_cr3()); +} + +void __init __nostackprotector sme_enable(struct boot_params *bp) +{ + const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; + unsigned int eax, ebx, ecx, edx; + bool active_by_default; + unsigned long me_mask; + char buffer[16]; + u64 msr; + + /* Check for the SME support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return; + + /* + * Check for the SME feature: + * CPUID Fn8000_001F[EAX] - Bit 0 + * Secure Memory Encryption support + * CPUID Fn8000_001F[EBX] - Bits 5:0 + * Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (!(eax & 1)) + return; + + me_mask = 1UL << (ebx & 0x3f); + + /* Check if SME is enabled */ + msr = __rdmsr(MSR_K8_SYSCFG); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + + /* + * Fixups have not been applied to phys_base yet and we're running + * identity mapped, so we must obtain the address to the SME command + * line argument data using rip-relative addressing. + */ + asm ("lea sme_cmdline_arg(%%rip), %0" + : "=r" (cmdline_arg) + : "p" (sme_cmdline_arg)); + asm ("lea sme_cmdline_on(%%rip), %0" + : "=r" (cmdline_on) + : "p" (sme_cmdline_on)); + asm ("lea sme_cmdline_off(%%rip), %0" + : "=r" (cmdline_off) + : "p" (sme_cmdline_off)); + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT)) + active_by_default = true; + else + active_by_default = false; + + cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | + ((u64)bp->ext_cmd_line_ptr << 32)); + + cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)); + + if (!strncmp(buffer, cmdline_on, sizeof(buffer))) + sme_me_mask = me_mask; + else if (!strncmp(buffer, cmdline_off, sizeof(buffer))) + sme_me_mask = 0; + else + sme_me_mask = active_by_default ? me_mask : 0; +} diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S new file mode 100644 index 000000000000..730e6d541df1 --- /dev/null +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -0,0 +1,149 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/pgtable.h> +#include <asm/page.h> +#include <asm/processor-flags.h> +#include <asm/msr-index.h> + + .text + .code64 +ENTRY(sme_encrypt_execute) + + /* + * Entry parameters: + * RDI - virtual address for the encrypted kernel mapping + * RSI - virtual address for the decrypted kernel mapping + * RDX - length of kernel + * RCX - virtual address of the encryption workarea, including: + * - stack page (PAGE_SIZE) + * - encryption routine page (PAGE_SIZE) + * - intermediate copy buffer (PMD_PAGE_SIZE) + * R8 - physcial address of the pagetables to use for encryption + */ + + push %rbp + movq %rsp, %rbp /* RBP now has original stack pointer */ + + /* Set up a one page stack in the non-encrypted memory area */ + movq %rcx, %rax /* Workarea stack page */ + leaq PAGE_SIZE(%rax), %rsp /* Set new stack pointer */ + addq $PAGE_SIZE, %rax /* Workarea encryption routine */ + + push %r12 + movq %rdi, %r10 /* Encrypted kernel */ + movq %rsi, %r11 /* Decrypted kernel */ + movq %rdx, %r12 /* Kernel length */ + + /* Copy encryption routine into the workarea */ + movq %rax, %rdi /* Workarea encryption routine */ + leaq __enc_copy(%rip), %rsi /* Encryption routine */ + movq $(.L__enc_copy_end - __enc_copy), %rcx /* Encryption routine length */ + rep movsb + + /* Setup registers for call */ + movq %r10, %rdi /* Encrypted kernel */ + movq %r11, %rsi /* Decrypted kernel */ + movq %r8, %rdx /* Pagetables used for encryption */ + movq %r12, %rcx /* Kernel length */ + movq %rax, %r8 /* Workarea encryption routine */ + addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ + + call *%rax /* Call the encryption routine */ + + pop %r12 + + movq %rbp, %rsp /* Restore original stack pointer */ + pop %rbp + + ret +ENDPROC(sme_encrypt_execute) + +ENTRY(__enc_copy) +/* + * Routine used to encrypt kernel. + * This routine must be run outside of the kernel proper since + * the kernel will be encrypted during the process. So this + * routine is defined here and then copied to an area outside + * of the kernel where it will remain and run decrypted + * during execution. + * + * On entry the registers must be: + * RDI - virtual address for the encrypted kernel mapping + * RSI - virtual address for the decrypted kernel mapping + * RDX - address of the pagetables to use for encryption + * RCX - length of kernel + * R8 - intermediate copy buffer + * + * RAX - points to this routine + * + * The kernel will be encrypted by copying from the non-encrypted + * kernel space to an intermediate buffer and then copying from the + * intermediate buffer back to the encrypted kernel space. The physical + * addresses of the two kernel space mappings are the same which + * results in the kernel being encrypted "in place". + */ + /* Enable the new page tables */ + mov %rdx, %cr3 + + /* Flush any global TLBs */ + mov %cr4, %rdx + andq $~X86_CR4_PGE, %rdx + mov %rdx, %cr4 + orq $X86_CR4_PGE, %rdx + mov %rdx, %cr4 + + /* Set the PAT register PA5 entry to write-protect */ + push %rcx + movl $MSR_IA32_CR_PAT, %ecx + rdmsr + push %rdx /* Save original PAT value */ + andl $0xffff00ff, %edx /* Clear PA5 */ + orl $0x00000500, %edx /* Set PA5 to WP */ + wrmsr + pop %rdx /* RDX contains original PAT value */ + pop %rcx + + movq %rcx, %r9 /* Save kernel length */ + movq %rdi, %r10 /* Save encrypted kernel address */ + movq %rsi, %r11 /* Save decrypted kernel address */ + + wbinvd /* Invalidate any cache entries */ + + /* Copy/encrypt 2MB at a time */ +1: + movq %r11, %rsi /* Source - decrypted kernel */ + movq %r8, %rdi /* Dest - intermediate copy buffer */ + movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + rep movsb + + movq %r8, %rsi /* Source - intermediate copy buffer */ + movq %r10, %rdi /* Dest - encrypted kernel */ + movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + rep movsb + + addq $PMD_PAGE_SIZE, %r11 + addq $PMD_PAGE_SIZE, %r10 + subq $PMD_PAGE_SIZE, %r9 /* Kernel length decrement */ + jnz 1b /* Kernel length not zero? */ + + /* Restore PAT register */ + push %rdx /* Save original PAT value */ + movl $MSR_IA32_CR_PAT, %ecx + rdmsr + pop %rdx /* Restore original PAT value */ + wrmsr + + ret +.L__enc_copy_end: +ENDPROC(__enc_copy) diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index a88cfbfbd078..a99679826846 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -37,21 +37,21 @@ struct va_alignment __read_mostly va_align = { .flags = -1, }; -unsigned long tasksize_32bit(void) +unsigned long task_size_32bit(void) { return IA32_PAGE_OFFSET; } -unsigned long tasksize_64bit(void) +unsigned long task_size_64bit(int full_addr_space) { - return TASK_SIZE_MAX; + return full_addr_space ? TASK_SIZE_MAX : DEFAULT_MAP_WINDOW; } static unsigned long stack_maxrandom_size(unsigned long task_size) { unsigned long max = 0; if (current->flags & PF_RANDOMIZE) { - max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit()); + max = (-1UL) & __STACK_RND_MASK(task_size == task_size_32bit()); max <<= PAGE_SHIFT; } @@ -141,7 +141,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) mm->get_unmapped_area = arch_get_unmapped_area_topdown; arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base, - arch_rnd(mmap64_rnd_bits), tasksize_64bit()); + arch_rnd(mmap64_rnd_bits), task_size_64bit(0)); #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES /* @@ -151,7 +151,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) * mmap_base, the compat syscall uses mmap_compat_base. */ arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base, - arch_rnd(mmap32_rnd_bits), tasksize_32bit()); + arch_rnd(mmap32_rnd_bits), task_size_32bit()); #endif } diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 1c34b767c84c..9ceaa955d2ba 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -355,10 +355,19 @@ int mpx_enable_management(void) */ bd_base = mpx_get_bounds_dir(); down_write(&mm->mmap_sem); + + /* MPX doesn't support addresses above 47 bits yet. */ + if (find_vma(mm, DEFAULT_MAP_WINDOW)) { + pr_warn_once("%s (%d): MPX cannot handle addresses " + "above 47-bits. Disabling.", + current->comm, current->pid); + ret = -ENXIO; + goto out; + } mm->context.bd_addr = bd_base; if (mm->context.bd_addr == MPX_INVALID_BOUNDS_DIR) ret = -ENXIO; - +out: up_write(&mm->mmap_sem); return ret; } @@ -1030,3 +1039,25 @@ void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma, if (ret) force_sig(SIGSEGV, current); } + +/* MPX cannot handle addresses above 47 bits yet. */ +unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, + unsigned long flags) +{ + if (!kernel_managing_mpx_tables(current->mm)) + return addr; + if (addr + len <= DEFAULT_MAP_WINDOW) + return addr; + if (flags & MAP_FIXED) + return -ENOMEM; + + /* + * Requested len is larger than the whole area we're allowed to map in. + * Resetting hinting address wouldn't do much good -- fail early. + */ + if (len > DEFAULT_MAP_WINDOW) + return -ENOMEM; + + /* Look for unmap area within DEFAULT_MAP_WINDOW */ + return 0; +} diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 757b0bcdf712..dfb7d657cf43 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1775,6 +1775,70 @@ int set_memory_4k(unsigned long addr, int numpages) __pgprot(0), 1, 0, NULL); } +static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) +{ + struct cpa_data cpa; + unsigned long start; + int ret; + + /* Nothing to do if the SME is not active */ + if (!sme_active()) + return 0; + + /* Should not be working on unaligned addresses */ + if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr)) + addr &= PAGE_MASK; + + start = addr; + + memset(&cpa, 0, sizeof(cpa)); + cpa.vaddr = &addr; + cpa.numpages = numpages; + cpa.mask_set = enc ? __pgprot(_PAGE_ENC) : __pgprot(0); + cpa.mask_clr = enc ? __pgprot(0) : __pgprot(_PAGE_ENC); + cpa.pgd = init_mm.pgd; + + /* Must avoid aliasing mappings in the highmem code */ + kmap_flush_unused(); + vm_unmap_aliases(); + + /* + * Before changing the encryption attribute, we need to flush caches. + */ + if (static_cpu_has(X86_FEATURE_CLFLUSH)) + cpa_flush_range(start, numpages, 1); + else + cpa_flush_all(1); + + ret = __change_page_attr_set_clr(&cpa, 1); + + /* + * After changing the encryption attribute, we need to flush TLBs + * again in case any speculative TLB caching occurred (but no need + * to flush caches again). We could just use cpa_flush_all(), but + * in case TLB flushing gets optimized in the cpa_flush_range() + * path use the same logic as above. + */ + if (static_cpu_has(X86_FEATURE_CLFLUSH)) + cpa_flush_range(start, numpages, 0); + else + cpa_flush_all(0); + + return ret; +} + +int set_memory_encrypted(unsigned long addr, int numpages) +{ + return __set_memory_enc_dec(addr, numpages, true); +} +EXPORT_SYMBOL_GPL(set_memory_encrypted); + +int set_memory_decrypted(unsigned long addr, int numpages) +{ + return __set_memory_enc_dec(addr, numpages, false); +} +EXPORT_SYMBOL_GPL(set_memory_decrypted); + int set_pages_uc(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); @@ -2020,6 +2084,9 @@ int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, if (!(page_flags & _PAGE_RW)) cpa.mask_clr = __pgprot(_PAGE_RW); + if (!(page_flags & _PAGE_ENC)) + cpa.mask_clr = pgprot_encrypted(cpa.mask_clr); + cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags); retval = __change_page_attr_set_clr(&cpa, 0); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 45979502f64b..fe7d57a8fb60 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -293,7 +293,7 @@ void init_cache_modes(void) * pat_init - Initialize PAT MSR and PAT table * * This function initializes PAT MSR and PAT table with an OS-defined value - * to enable additional cache attributes, WC and WT. + * to enable additional cache attributes, WC, WT and WP. * * This function must be called on all CPUs using the specific sequence of * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this @@ -352,7 +352,7 @@ void pat_init(void) * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS * 011 3 UC : _PAGE_CACHE_MODE_UC * 100 4 WB : Reserved - * 101 5 WC : Reserved + * 101 5 WP : _PAGE_CACHE_MODE_WP * 110 6 UC-: Reserved * 111 7 WT : _PAGE_CACHE_MODE_WT * @@ -360,7 +360,7 @@ void pat_init(void) * corresponding types in the presence of PAT errata. */ pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, WT); + PAT(4, WB) | PAT(5, WP) | PAT(6, UC_MINUS) | PAT(7, WT); } if (!boot_cpu_done) { @@ -744,6 +744,9 @@ EXPORT_SYMBOL(arch_io_free_memtype_wc); pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { + if (!phys_mem_access_encrypted(pfn << PAGE_SHIFT, size)) + vma_prot = pgprot_decrypted(vma_prot); + return vma_prot; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 508a708eb9a6..218834a3e9ad 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -56,7 +56,7 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { pgtable_page_dtor(pte); paravirt_release_pte(page_to_pfn(pte)); - tlb_remove_page(tlb, pte); + tlb_remove_table(tlb, pte); } #if CONFIG_PGTABLE_LEVELS > 2 @@ -72,21 +72,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) tlb->need_flush_all = 1; #endif pgtable_pmd_page_dtor(page); - tlb_remove_page(tlb, page); + tlb_remove_table(tlb, page); } #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); - tlb_remove_page(tlb, virt_to_page(pud)); + tlb_remove_table(tlb, virt_to_page(pud)); } #if CONFIG_PGTABLE_LEVELS > 4 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) { paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT); - tlb_remove_page(tlb, virt_to_page(p4d)); + tlb_remove_table(tlb, virt_to_page(p4d)); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 014d07a80053..ce104b962a17 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -28,6 +28,42 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ +atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); + +static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, + u16 *new_asid, bool *need_flush) +{ + u16 asid; + + if (!static_cpu_has(X86_FEATURE_PCID)) { + *new_asid = 0; + *need_flush = true; + return; + } + + for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) { + if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) != + next->context.ctx_id) + continue; + + *new_asid = asid; + *need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) < + next_tlb_gen); + return; + } + + /* + * We don't currently own an ASID slot on this CPU. + * Allocate a slot. + */ + *new_asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1; + if (*new_asid >= TLB_NR_DYN_ASIDS) { + *new_asid = 0; + this_cpu_write(cpu_tlbstate.next_asid, 1); + } + *need_flush = true; +} + void leave_mm(int cpu) { struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); @@ -43,12 +79,11 @@ void leave_mm(int cpu) if (loaded_mm == &init_mm) return; - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) - BUG(); + /* Warn if we're not lazy. */ + WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))); switch_mm(NULL, &init_mm, NULL); } -EXPORT_SYMBOL_GPL(leave_mm); void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) @@ -63,115 +98,219 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { - unsigned cpu = smp_processor_id(); struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); + u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + unsigned cpu = smp_processor_id(); + u64 next_tlb_gen; /* - * NB: The scheduler will call us with prev == next when - * switching from lazy TLB mode to normal mode if active_mm - * isn't changing. When this happens, there is no guarantee - * that CR3 (and hence cpu_tlbstate.loaded_mm) matches next. + * NB: The scheduler will call us with prev == next when switching + * from lazy TLB mode to normal mode if active_mm isn't changing. + * When this happens, we don't assume that CR3 (and hence + * cpu_tlbstate.loaded_mm) matches next. * * NB: leave_mm() calls us with prev == NULL and tsk == NULL. */ - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); + /* We don't want flush_tlb_func_* to run concurrently with us. */ + if (IS_ENABLED(CONFIG_PROVE_LOCKING)) + WARN_ON_ONCE(!irqs_disabled()); + + /* + * Verify that CR3 is what we think it is. This will catch + * hypothetical buggy code that directly switches to swapper_pg_dir + * without going through leave_mm() / switch_mm_irqs_off() or that + * does something like write_cr3(read_cr3_pa()). + */ + VM_BUG_ON(__read_cr3() != (__sme_pa(real_prev->pgd) | prev_asid)); if (real_prev == next) { - /* - * There's nothing to do: we always keep the per-mm control - * regs in sync with cpu_tlbstate.loaded_mm. Just - * sanity-check mm_cpumask. - */ - if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(next)))) - cpumask_set_cpu(cpu, mm_cpumask(next)); - return; - } + VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != + next->context.ctx_id); + + if (cpumask_test_cpu(cpu, mm_cpumask(next))) { + /* + * There's nothing to do: we weren't lazy, and we + * aren't changing our mm. We don't need to flush + * anything, nor do we need to update CR3, CR4, or + * LDTR. + */ + return; + } + + /* Resume remote flushes and then read tlb_gen. */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + next_tlb_gen = atomic64_read(&next->context.tlb_gen); + + if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) < + next_tlb_gen) { + /* + * Ideally, we'd have a flush_tlb() variant that + * takes the known CR3 value as input. This would + * be faster on Xen PV and on hypothetical CPUs + * on which INVPCID is fast. + */ + this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen, + next_tlb_gen); + write_cr3(__sme_pa(next->pgd) | prev_asid); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, + TLB_FLUSH_ALL); + } - if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* - * If our current stack is in vmalloc space and isn't - * mapped in the new pgd, we'll double-fault. Forcibly - * map it. + * We just exited lazy mode, which means that CR4 and/or LDTR + * may be stale. (Changes to the required CR4 and LDTR states + * are not reflected in tlb_gen.) */ - unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); - - pgd_t *pgd = next->pgd + stack_pgd_index; - - if (unlikely(pgd_none(*pgd))) - set_pgd(pgd, init_mm.pgd[stack_pgd_index]); - } + } else { + u16 new_asid; + bool need_flush; + + if (IS_ENABLED(CONFIG_VMAP_STACK)) { + /* + * If our current stack is in vmalloc space and isn't + * mapped in the new pgd, we'll double-fault. Forcibly + * map it. + */ + unsigned int index = pgd_index(current_stack_pointer()); + pgd_t *pgd = next->pgd + index; + + if (unlikely(pgd_none(*pgd))) + set_pgd(pgd, init_mm.pgd[index]); + } - this_cpu_write(cpu_tlbstate.loaded_mm, next); + /* Stop remote flushes for the previous mm */ + if (cpumask_test_cpu(cpu, mm_cpumask(real_prev))) + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); - WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); - cpumask_set_cpu(cpu, mm_cpumask(next)); + VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); - /* - * Re-load page tables. - * - * This logic has an ordering constraint: - * - * CPU 0: Write to a PTE for 'next' - * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. - * CPU 1: set bit 1 in next's mm_cpumask - * CPU 1: load from the PTE that CPU 0 writes (implicit) - * - * We need to prevent an outcome in which CPU 1 observes - * the new PTE value and CPU 0 observes bit 1 clear in - * mm_cpumask. (If that occurs, then the IPI will never - * be sent, and CPU 0's TLB will contain a stale entry.) - * - * The bad outcome can occur if either CPU's load is - * reordered before that CPU's store, so both CPUs must - * execute full barriers to prevent this from happening. - * - * Thus, switch_mm needs a full barrier between the - * store to mm_cpumask and any operation that could load - * from next->pgd. TLB fills are special and can happen - * due to instruction fetches or for no reason at all, - * and neither LOCK nor MFENCE orders them. - * Fortunately, load_cr3() is serializing and gives the - * ordering guarantee we need. - */ - load_cr3(next->pgd); - - /* - * This gets called via leave_mm() in the idle path where RCU - * functions differently. Tracing normally uses RCU, so we have to - * call the tracepoint specially here. - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + /* + * Start remote flushes and then read tlb_gen. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + next_tlb_gen = atomic64_read(&next->context.tlb_gen); + + choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); + + if (need_flush) { + this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); + write_cr3(__sme_pa(next->pgd) | new_asid); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, + TLB_FLUSH_ALL); + } else { + /* The new ASID is already up to date. */ + write_cr3(__sme_pa(next->pgd) | new_asid | CR3_NOFLUSH); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); + } - /* Stop flush ipis for the previous mm */ - WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && - real_prev != &init_mm); - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + this_cpu_write(cpu_tlbstate.loaded_mm, next); + this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); + } - /* Load per-mm CR4 and LDTR state */ load_mm_cr4(next); switch_ldt(real_prev, next); } +/* + * flush_tlb_func_common()'s memory ordering requirement is that any + * TLB fills that happen after we flush the TLB are ordered after we + * read active_mm's tlb_gen. We don't need any explicit barriers + * because all x86 flush operations are serializing and the + * atomic64_read operation won't be reordered by the compiler. + */ static void flush_tlb_func_common(const struct flush_tlb_info *f, bool local, enum tlb_flush_reason reason) { + /* + * We have three different tlb_gen values in here. They are: + * + * - mm_tlb_gen: the latest generation. + * - local_tlb_gen: the generation that this CPU has already caught + * up to. + * - f->new_tlb_gen: the generation that the requester of the flush + * wants us to catch up to. + */ + struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); + u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + u64 mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen); + u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen); + /* This code cannot presently handle being reentered. */ VM_WARN_ON(!irqs_disabled()); - if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) { - leave_mm(smp_processor_id()); + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != + loaded_mm->context.ctx_id); + + if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) { + /* + * We're in lazy mode -- don't flush. We can get here on + * remote flushes due to races and on local flushes if a + * kernel thread coincidentally flushes the mm it's lazily + * still using. + */ return; } - if (f->end == TLB_FLUSH_ALL) { - local_flush_tlb(); - if (local) - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - trace_tlb_flush(reason, TLB_FLUSH_ALL); - } else { + if (unlikely(local_tlb_gen == mm_tlb_gen)) { + /* + * There's nothing to do: we're already up to date. This can + * happen if two concurrent flushes happen -- the first flush to + * be handled can catch us all the way up, leaving no work for + * the second flush. + */ + trace_tlb_flush(reason, 0); + return; + } + + WARN_ON_ONCE(local_tlb_gen > mm_tlb_gen); + WARN_ON_ONCE(f->new_tlb_gen > mm_tlb_gen); + + /* + * If we get to this point, we know that our TLB is out of date. + * This does not strictly imply that we need to flush (it's + * possible that f->new_tlb_gen <= local_tlb_gen), but we're + * going to need to flush in the very near future, so we might + * as well get it over with. + * + * The only question is whether to do a full or partial flush. + * + * We do a partial flush if requested and two extra conditions + * are met: + * + * 1. f->new_tlb_gen == local_tlb_gen + 1. We have an invariant that + * we've always done all needed flushes to catch up to + * local_tlb_gen. If, for example, local_tlb_gen == 2 and + * f->new_tlb_gen == 3, then we know that the flush needed to bring + * us up to date for tlb_gen 3 is the partial flush we're + * processing. + * + * As an example of why this check is needed, suppose that there + * are two concurrent flushes. The first is a full flush that + * changes context.tlb_gen from 1 to 2. The second is a partial + * flush that changes context.tlb_gen from 2 to 3. If they get + * processed on this CPU in reverse order, we'll see + * local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL. + * If we were to use __flush_tlb_single() and set local_tlb_gen to + * 3, we'd be break the invariant: we'd update local_tlb_gen above + * 1 without the full flush that's needed for tlb_gen 2. + * + * 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimiation. + * Partial TLB flushes are not all that much cheaper than full TLB + * flushes, so it seems unlikely that it would be a performance win + * to do a partial flush if that won't bring our TLB fully up to + * date. By doing a full flush instead, we can increase + * local_tlb_gen all the way to mm_tlb_gen and we can probably + * avoid another flush in the very near future. + */ + if (f->end != TLB_FLUSH_ALL && + f->new_tlb_gen == local_tlb_gen + 1 && + f->new_tlb_gen == mm_tlb_gen) { + /* Partial flush */ unsigned long addr; unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT; + addr = f->start; while (addr < f->end) { __flush_tlb_single(addr); @@ -180,7 +319,16 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, if (local) count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages); trace_tlb_flush(reason, nr_pages); + } else { + /* Full flush. */ + local_flush_tlb(); + if (local) + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + trace_tlb_flush(reason, TLB_FLUSH_ALL); } + + /* Both paths above update our state to mm_tlb_gen. */ + this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen); } static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason) @@ -214,6 +362,21 @@ void native_flush_tlb_others(const struct cpumask *cpumask, (info->end - info->start) >> PAGE_SHIFT); if (is_uv_system()) { + /* + * This whole special case is confused. UV has a "Broadcast + * Assist Unit", which seems to be a fancy way to send IPIs. + * Back when x86 used an explicit TLB flush IPI, UV was + * optimized to use its own mechanism. These days, x86 uses + * smp_call_function_many(), but UV still uses a manual IPI, + * and that IPI's action is out of date -- it does a manual + * flush instead of calling flush_tlb_func_remote(). This + * means that the percpu tlb_gen variables won't be updated + * and we'll do pointless flushes on future context switches. + * + * Rather than hooking native_flush_tlb_others() here, I think + * that UV should be updated so that smp_call_function_many(), + * etc, are optimal on UV. + */ unsigned int cpu; cpu = smp_processor_id(); @@ -250,8 +413,8 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, cpu = get_cpu(); - /* Synchronize with switch_mm. */ - smp_mb(); + /* This is also a barrier that synchronizes with switch_mm(). */ + info.new_tlb_gen = inc_mm_tlb_gen(mm); /* Should we flush just the requested range? */ if ((end != TLB_FLUSH_ALL) && @@ -273,6 +436,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), &info); + put_cpu(); } @@ -281,8 +445,6 @@ static void do_flush_tlb_all(void *info) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); __flush_tlb_all(); - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) - leave_mm(smp_processor_id()); } void flush_tlb_all(void) @@ -335,6 +497,7 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) flush_tlb_others(&batch->cpumask, &info); + cpumask_clear(&batch->cpumask); put_cpu(); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index dbe2132b0ed4..7a5350d08cef 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -674,7 +674,7 @@ int pcibios_add_device(struct pci_dev *dev) pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = ioremap(pa_data, sizeof(*rom)); + data = memremap(pa_data, sizeof(*rom), MEMREMAP_WB); if (!data) return -ENOMEM; @@ -693,7 +693,7 @@ int pcibios_add_device(struct pci_dev *dev) } } pa_data = data->next; - iounmap(data); + memunmap(data); } set_dma_domain_ops(dev); set_dev_domain_options(dev); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index f084d8718ac4..6217b23e85f6 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -1035,12 +1035,12 @@ void __init efi_enter_virtual_mode(void) /* * Convenience functions to obtain memory types and attributes */ -u32 efi_mem_type(unsigned long phys_addr) +int efi_mem_type(unsigned long phys_addr) { efi_memory_desc_t *md; if (!efi_enabled(EFI_MEMMAP)) - return 0; + return -ENOTSUPP; for_each_efi_memory_desc(md) { if ((md->phys_addr <= phys_addr) && @@ -1048,7 +1048,7 @@ u32 efi_mem_type(unsigned long phys_addr) (md->num_pages << EFI_PAGE_SHIFT)))) return md->type; } - return 0; + return -EINVAL; } static int __init arch_parse_efi_cmdline(char *str) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 9bf72f5bfedb..12e83888e5b9 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -327,7 +327,7 @@ virt_to_phys_or_null_size(void *va, unsigned long size) int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { - unsigned long pfn, text; + unsigned long pfn, text, pf; struct page *page; unsigned npages; pgd_t *pgd; @@ -335,7 +335,12 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) if (efi_enabled(EFI_OLD_MEMMAP)) return 0; - efi_scratch.efi_pgt = (pgd_t *)__pa(efi_pgd); + /* + * Since the PGD is encrypted, set the encryption mask so that when + * this value is loaded into cr3 the PGD will be decrypted during + * the pagetable walk. + */ + efi_scratch.efi_pgt = (pgd_t *)__sme_pa(efi_pgd); pgd = efi_pgd; /* @@ -345,7 +350,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * phys_efi_set_virtual_address_map(). */ pfn = pa_memmap >> PAGE_SHIFT; - if (kernel_map_pages_in_pgd(pgd, pfn, pa_memmap, num_pages, _PAGE_NX | _PAGE_RW)) { + pf = _PAGE_NX | _PAGE_RW | _PAGE_ENC; + if (kernel_map_pages_in_pgd(pgd, pfn, pa_memmap, num_pages, pf)) { pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap); return 1; } @@ -388,7 +394,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) text = __pa(_text); pfn = text >> PAGE_SHIFT; - if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, _PAGE_RW)) { + pf = _PAGE_RW | _PAGE_ENC; + if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, pf)) { pr_err("Failed to map kernel text 1:1\n"); return 1; } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index cd4be19c36dc..1f71980fc5e0 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -1,6 +1,7 @@ #include <linux/io.h> #include <linux/slab.h> #include <linux/memblock.h> +#include <linux/mem_encrypt.h> #include <asm/set_memory.h> #include <asm/pgtable.h> @@ -59,6 +60,13 @@ static void __init setup_real_mode(void) base = (unsigned char *)real_mode_header; + /* + * If SME is active, the trampoline area will need to be in + * decrypted memory in order to bring up other processors + * successfully. + */ + set_memory_decrypted((unsigned long)base, size >> PAGE_SHIFT); + memcpy(base, real_mode_blob, size); phys_base = __pa(base); @@ -100,6 +108,10 @@ static void __init setup_real_mode(void) trampoline_cr4_features = &trampoline_header->cr4; *trampoline_cr4_features = mmu_cr4_features; + trampoline_header->flags = 0; + if (sme_active()) + trampoline_header->flags |= TH_FLAGS_SME_ACTIVE; + trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; trampoline_pgd[511] = init_top_pgt[511].pgd; diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index dac7b20d2f9d..614fd7064d0a 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -30,6 +30,7 @@ #include <asm/msr.h> #include <asm/segment.h> #include <asm/processor-flags.h> +#include <asm/realmode.h> #include "realmode.h" .text @@ -92,6 +93,28 @@ ENTRY(startup_32) movl %edx, %fs movl %edx, %gs + /* + * Check for memory encryption support. This is a safety net in + * case BIOS hasn't done the necessary step of setting the bit in + * the MSR for this AP. If SME is active and we've gotten this far + * then it is safe for us to set the MSR bit and continue. If we + * don't we'll eventually crash trying to execute encrypted + * instructions. + */ + bt $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags + jnc .Ldone + movl $MSR_K8_SYSCFG, %ecx + rdmsr + bts $MSR_K8_SYSCFG_MEM_ENCRYPT_BIT, %eax + jc .Ldone + + /* + * Memory encryption is enabled but the SME enable bit for this + * CPU has has not been set. It is safe to set it, so do so. + */ + wrmsr +.Ldone: + movl pa_tr_cr4, %eax movl %eax, %cr4 # Enable PAE mode @@ -147,6 +170,7 @@ GLOBAL(trampoline_header) tr_start: .space 8 GLOBAL(tr_efer) .space 8 GLOBAL(tr_cr4) .space 4 + GLOBAL(tr_flags) .space 4 END(trampoline_header) #include "trampoline_common.S" diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 027987638e98..1ecd419811a2 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -17,6 +17,9 @@ config XEN_PV bool "Xen PV guest support" default y depends on XEN + # XEN_PV is not ready to work with 5-level paging. + # Changes to hypervisor are also required. + depends on !X86_5LEVEL select XEN_HAVE_PVMMU select XEN_HAVE_VPMU help @@ -75,4 +78,6 @@ config XEN_DEBUG_FS config XEN_PVH bool "Support for running as a PVH guest" depends on XEN && XEN_PVHVM && ACPI + # Pre-built page tables are not ready to handle 5-level paging. + depends on !X86_5LEVEL def_bool n diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 98491521bb43..6c279c8f0a0e 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -263,6 +263,13 @@ static void __init xen_init_capabilities(void) setup_clear_cpu_cap(X86_FEATURE_MTRR); setup_clear_cpu_cap(X86_FEATURE_ACC); setup_clear_cpu_cap(X86_FEATURE_X2APIC); + setup_clear_cpu_cap(X86_FEATURE_SME); + + /* + * Xen PV would need some work to support PCID: CR3 handling as well + * as xen_flush_tlb_others() would need updating. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); if (!xen_initial_domain()) setup_clear_cpu_cap(X86_FEATURE_ACPI); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index cab28cf2cffb..e437714750f8 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1005,14 +1005,12 @@ static void xen_drop_mm_ref(struct mm_struct *mm) /* Get the "official" set of cpus referring to our pagetable. */ if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) { for_each_online_cpu(cpu) { - if (!cpumask_test_cpu(cpu, mm_cpumask(mm)) - && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) + if (per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) continue; smp_call_function_single(cpu, drop_mm_ref_this_cpu, mm, 1); } return; } - cpumask_copy(mask, mm_cpumask(mm)); /* * It's possible that a vcpu may have a stale reference to our @@ -1021,6 +1019,7 @@ static void xen_drop_mm_ref(struct mm_struct *mm) * look at its actual current cr3 value, and force it to flush * if needed. */ + cpumask_clear(mask); for_each_online_cpu(cpu) { if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd)) cpumask_set_cpu(cpu, mask); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 72a8e6adebe6..a7525e95d53f 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -58,7 +58,7 @@ ENTRY(hypercall_page) #else ELFNOTE(Xen, XEN_ELFNOTE_VIRT_BASE, _ASM_PTR __START_KERNEL_map) /* Map the p2m table to a 512GB-aligned user address. */ - ELFNOTE(Xen, XEN_ELFNOTE_INIT_P2M, .quad PGDIR_SIZE) + ELFNOTE(Xen, XEN_ELFNOTE_INIT_P2M, .quad (PUD_SIZE * PTRS_PER_PUD)) #endif #ifdef CONFIG_XEN_PV ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, _ASM_PTR startup_xen) |