diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-10 20:01:51 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-10 20:01:51 +0200 |
commit | 93c26d7dc02380fe11e57ff0d152368743762169 (patch) | |
tree | 5234bc86561c6b8c7fd698a2d456add3c960db1f /arch/x86 | |
parent | Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/ker... (diff) | |
parent | x86/pkeys: Update documentation (diff) | |
download | linux-93c26d7dc02380fe11e57ff0d152368743762169.tar.xz linux-93c26d7dc02380fe11e57ff0d152368743762169.zip |
Merge branch 'mm-pkeys-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull protection keys syscall interface from Thomas Gleixner:
"This is the final step of Protection Keys support which adds the
syscalls so user space can actually allocate keys and protect memory
areas with them. Details and usage examples can be found in the
documentation.
The mm side of this has been acked by Mel"
* 'mm-pkeys-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/pkeys: Update documentation
x86/mm/pkeys: Do not skip PKRU register if debug registers are not used
x86/pkeys: Fix pkeys build breakage for some non-x86 arches
x86/pkeys: Add self-tests
x86/pkeys: Allow configuration of init_pkru
x86/pkeys: Default to a restrictive init PKRU
pkeys: Add details of system call use to Documentation/
generic syscalls: Wire up memory protection keys syscalls
x86: Wire up protection keys system calls
x86/pkeys: Allocation/free syscalls
x86/pkeys: Make mprotect_key() mask off additional vm_flags
mm: Implement new pkey_mprotect() system call
x86/pkeys: Add fault handling for PF_PK page fault bit
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/entry/syscalls/syscall_32.tbl | 5 | ||||
-rw-r--r-- | arch/x86/entry/syscalls/syscall_64.tbl | 5 | ||||
-rw-r--r-- | arch/x86/include/asm/mmu.h | 8 | ||||
-rw-r--r-- | arch/x86/include/asm/mmu_context.h | 25 | ||||
-rw-r--r-- | arch/x86/include/asm/pkeys.h | 73 | ||||
-rw-r--r-- | arch/x86/kernel/fpu/core.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/fpu/xstate.c | 5 | ||||
-rw-r--r-- | arch/x86/kernel/process_64.c | 13 | ||||
-rw-r--r-- | arch/x86/mm/fault.c | 9 | ||||
-rw-r--r-- | arch/x86/mm/pkeys.c | 142 |
10 files changed, 267 insertions, 22 deletions
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index f848572169ea..ff6ef7b30822 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -386,3 +386,8 @@ 377 i386 copy_file_range sys_copy_file_range 378 i386 preadv2 sys_preadv2 compat_sys_preadv2 379 i386 pwritev2 sys_pwritev2 compat_sys_pwritev2 +380 i386 pkey_mprotect sys_pkey_mprotect +381 i386 pkey_alloc sys_pkey_alloc +382 i386 pkey_free sys_pkey_free +#383 i386 pkey_get sys_pkey_get +#384 i386 pkey_set sys_pkey_set diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index e9ce9c7c39b4..2f024d02511d 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -335,6 +335,11 @@ 326 common copy_file_range sys_copy_file_range 327 64 preadv2 sys_preadv2 328 64 pwritev2 sys_pwritev2 +329 common pkey_mprotect sys_pkey_mprotect +330 common pkey_alloc sys_pkey_alloc +331 common pkey_free sys_pkey_free +#332 common pkey_get sys_pkey_get +#333 common pkey_set sys_pkey_set # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 1ea0baef1175..72198c64e646 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -23,6 +23,14 @@ typedef struct { const struct vdso_image *vdso_image; /* vdso image in use */ atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */ +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + /* + * One bit per protection key says whether userspace can + * use it or not. protected by mmap_sem. + */ + u16 pkey_allocation_map; + s16 execute_only_pkey; +#endif } mm_context_t; #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index d8abfcf524d1..8e0a9fe86de4 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -4,6 +4,7 @@ #include <asm/desc.h> #include <linux/atomic.h> #include <linux/mm_types.h> +#include <linux/pkeys.h> #include <trace/events/tlb.h> @@ -107,7 +108,16 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { + /* pkey 0 is the default and always allocated */ + mm->context.pkey_allocation_map = 0x1; + /* -1 means unallocated or invalid */ + mm->context.execute_only_pkey = -1; + } + #endif init_new_context_ldt(tsk, mm); + return 0; } static inline void destroy_context(struct mm_struct *mm) @@ -195,16 +205,20 @@ static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma, mpx_notify_unmap(mm, vma, start, end); } +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS static inline int vma_pkey(struct vm_area_struct *vma) { - u16 pkey = 0; -#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3; - pkey = (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT; -#endif - return pkey; + + return (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT; +} +#else +static inline int vma_pkey(struct vm_area_struct *vma) +{ + return 0; } +#endif static inline bool __pkru_allows_pkey(u16 pkey, bool write) { @@ -258,5 +272,4 @@ static inline bool arch_pte_access_permitted(pte_t pte, bool write) { return __pkru_allows_pkey(pte_flags_pkey(pte_flags(pte)), write); } - #endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 7b84565c916c..34684adb6899 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -10,7 +10,6 @@ extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, * Try to dedicate one of the protection keys to be used as an * execute-only protection key. */ -#define PKEY_DEDICATED_EXECUTE_ONLY 15 extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { @@ -31,4 +30,76 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, return __arch_override_mprotect_pkey(vma, prot, pkey); } +extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val); + +#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) + +#define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) +#define mm_set_pkey_allocated(mm, pkey) do { \ + mm_pkey_allocation_map(mm) |= (1U << pkey); \ +} while (0) +#define mm_set_pkey_free(mm, pkey) do { \ + mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ +} while (0) + +static inline +bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) +{ + return mm_pkey_allocation_map(mm) & (1U << pkey); +} + +/* + * Returns a positive, 4-bit key on success, or -1 on failure. + */ +static inline +int mm_pkey_alloc(struct mm_struct *mm) +{ + /* + * Note: this is the one and only place we make sure + * that the pkey is valid as far as the hardware is + * concerned. The rest of the kernel trusts that + * only good, valid pkeys come out of here. + */ + u16 all_pkeys_mask = ((1U << arch_max_pkey()) - 1); + int ret; + + /* + * Are we out of pkeys? We must handle this specially + * because ffz() behavior is undefined if there are no + * zeros. + */ + if (mm_pkey_allocation_map(mm) == all_pkeys_mask) + return -1; + + ret = ffz(mm_pkey_allocation_map(mm)); + + mm_set_pkey_allocated(mm, ret); + + return ret; +} + +static inline +int mm_pkey_free(struct mm_struct *mm, int pkey) +{ + /* + * pkey 0 is special, always allocated and can never + * be freed. + */ + if (!pkey) + return -EINVAL; + if (!mm_pkey_is_allocated(mm, pkey)) + return -EINVAL; + + mm_set_pkey_free(mm, pkey); + + return 0; +} + +extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val); +extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val); +extern void copy_init_pkru_to_fpregs(void); + #endif /*_ASM_X86_PKEYS_H */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 3fc03a09a93b..47004010ad5d 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -12,6 +12,7 @@ #include <asm/traps.h> #include <linux/hardirq.h> +#include <linux/pkeys.h> #define CREATE_TRACE_POINTS #include <asm/trace/fpu.h> @@ -505,6 +506,9 @@ static inline void copy_init_fpstate_to_fpregs(void) copy_kernel_to_fxregs(&init_fpstate.fxsave); else copy_kernel_to_fregs(&init_fpstate.fsave); + + if (boot_cpu_has(X86_FEATURE_OSPKE)) + copy_init_pkru_to_fpregs(); } /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 01567aa87503..124aa5c593f8 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -5,6 +5,7 @@ */ #include <linux/compat.h> #include <linux/cpu.h> +#include <linux/mman.h> #include <linux/pkeys.h> #include <asm/fpu/api.h> @@ -866,9 +867,10 @@ const void *get_xsave_field_ptr(int xsave_state) return get_xsave_addr(&fpu->state.xsave, xsave_state); } +#ifdef CONFIG_ARCH_HAS_PKEYS + #define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) #define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) - /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. @@ -914,6 +916,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, return 0; } +#endif /* ! CONFIG_ARCH_HAS_PKEYS */ /* * This is similar to user_regset_copyout(), but will not add offset to diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ee944bd2310d..b3760b3c1ca0 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -109,12 +109,13 @@ void __show_regs(struct pt_regs *regs, int all) get_debugreg(d7, 7); /* Only print out debug registers if they are in their non-default state. */ - if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && - (d6 == DR6_RESERVED) && (d7 == 0x400)) - return; - - printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); - printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); + if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && + (d6 == DR6_RESERVED) && (d7 == 0x400))) { + printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", + d0, d1, d2); + printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", + d3, d6, d7); + } if (boot_cpu_has(X86_FEATURE_OSPKE)) printk(KERN_DEFAULT "PKRU: %08x\n", read_pkru()); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 1e525122cbe4..4dc13340653e 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1144,6 +1144,15 @@ access_error(unsigned long error_code, struct vm_area_struct *vma) { /* This is only called for the current mm, so: */ bool foreign = false; + + /* + * Read or write was blocked by protection keys. This is + * always an unconditional error and can never result in + * a follow-up action to resolve the fault, like a COW. + */ + if (error_code & PF_PK) + return 1; + /* * Make sure to check the VMA so that we do not perform * faults just to hit a PF_PK as soon as we fill in a diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index e8c474451928..f88ce0e5efd9 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -11,6 +11,7 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. */ +#include <linux/debugfs.h> /* debugfs_create_u32() */ #include <linux/mm_types.h> /* mm_struct, vma, etc... */ #include <linux/pkeys.h> /* PKEY_* */ #include <uapi/asm-generic/mman-common.h> @@ -21,8 +22,19 @@ int __execute_only_pkey(struct mm_struct *mm) { + bool need_to_set_mm_pkey = false; + int execute_only_pkey = mm->context.execute_only_pkey; int ret; + /* Do we need to assign a pkey for mm's execute-only maps? */ + if (execute_only_pkey == -1) { + /* Go allocate one to use, which might fail */ + execute_only_pkey = mm_pkey_alloc(mm); + if (execute_only_pkey < 0) + return -1; + need_to_set_mm_pkey = true; + } + /* * We do not want to go through the relatively costly * dance to set PKRU if we do not need to. Check it @@ -32,22 +44,33 @@ int __execute_only_pkey(struct mm_struct *mm) * can make fpregs inactive. */ preempt_disable(); - if (fpregs_active() && - !__pkru_allows_read(read_pkru(), PKEY_DEDICATED_EXECUTE_ONLY)) { + if (!need_to_set_mm_pkey && + fpregs_active() && + !__pkru_allows_read(read_pkru(), execute_only_pkey)) { preempt_enable(); - return PKEY_DEDICATED_EXECUTE_ONLY; + return execute_only_pkey; } preempt_enable(); - ret = arch_set_user_pkey_access(current, PKEY_DEDICATED_EXECUTE_ONLY, + + /* + * Set up PKRU so that it denies access for everything + * other than execution. + */ + ret = arch_set_user_pkey_access(current, execute_only_pkey, PKEY_DISABLE_ACCESS); /* * If the PKRU-set operation failed somehow, just return * 0 and effectively disable execute-only support. */ - if (ret) - return 0; + if (ret) { + mm_set_pkey_free(mm, execute_only_pkey); + return -1; + } - return PKEY_DEDICATED_EXECUTE_ONLY; + /* We got one, store it and use it from here on out */ + if (need_to_set_mm_pkey) + mm->context.execute_only_pkey = execute_only_pkey; + return execute_only_pkey; } static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma) @@ -55,7 +78,7 @@ static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma) /* Do this check first since the vm_flags should be hot */ if ((vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) != VM_EXEC) return false; - if (vma_pkey(vma) != PKEY_DEDICATED_EXECUTE_ONLY) + if (vma_pkey(vma) != vma->vm_mm->context.execute_only_pkey) return false; return true; @@ -99,3 +122,106 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey */ return vma_pkey(vma); } + +#define PKRU_AD_KEY(pkey) (PKRU_AD_BIT << ((pkey) * PKRU_BITS_PER_PKEY)) + +/* + * Make the default PKRU value (at execve() time) as restrictive + * as possible. This ensures that any threads clone()'d early + * in the process's lifetime will not accidentally get access + * to data which is pkey-protected later on. + */ +u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) | + PKRU_AD_KEY( 4) | PKRU_AD_KEY( 5) | PKRU_AD_KEY( 6) | + PKRU_AD_KEY( 7) | PKRU_AD_KEY( 8) | PKRU_AD_KEY( 9) | + PKRU_AD_KEY(10) | PKRU_AD_KEY(11) | PKRU_AD_KEY(12) | + PKRU_AD_KEY(13) | PKRU_AD_KEY(14) | PKRU_AD_KEY(15); + +/* + * Called from the FPU code when creating a fresh set of FPU + * registers. This is called from a very specific context where + * we know the FPU regstiers are safe for use and we can use PKRU + * directly. The fact that PKRU is only available when we are + * using eagerfpu mode makes this possible. + */ +void copy_init_pkru_to_fpregs(void) +{ + u32 init_pkru_value_snapshot = READ_ONCE(init_pkru_value); + /* + * Any write to PKRU takes it out of the XSAVE 'init + * state' which increases context switch cost. Avoid + * writing 0 when PKRU was already 0. + */ + if (!init_pkru_value_snapshot && !read_pkru()) + return; + /* + * Override the PKRU state that came from 'init_fpstate' + * with the baseline from the process. + */ + write_pkru(init_pkru_value_snapshot); +} + +static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + char buf[32]; + unsigned int len; + + len = sprintf(buf, "0x%x\n", init_pkru_value); + return simple_read_from_buffer(user_buf, count, ppos, buf, len); +} + +static ssize_t init_pkru_write_file(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + char buf[32]; + ssize_t len; + u32 new_init_pkru; + + len = min(count, sizeof(buf) - 1); + if (copy_from_user(buf, user_buf, len)) + return -EFAULT; + + /* Make the buffer a valid string that we can not overrun */ + buf[len] = '\0'; + if (kstrtouint(buf, 0, &new_init_pkru)) + return -EINVAL; + + /* + * Don't allow insane settings that will blow the system + * up immediately if someone attempts to disable access + * or writes to pkey 0. + */ + if (new_init_pkru & (PKRU_AD_BIT|PKRU_WD_BIT)) + return -EINVAL; + + WRITE_ONCE(init_pkru_value, new_init_pkru); + return count; +} + +static const struct file_operations fops_init_pkru = { + .read = init_pkru_read_file, + .write = init_pkru_write_file, + .llseek = default_llseek, +}; + +static int __init create_init_pkru_value(void) +{ + debugfs_create_file("init_pkru", S_IRUSR | S_IWUSR, + arch_debugfs_dir, NULL, &fops_init_pkru); + return 0; +} +late_initcall(create_init_pkru_value); + +static __init int setup_init_pkru(char *opt) +{ + u32 new_init_pkru; + + if (kstrtouint(opt, 0, &new_init_pkru)) + return 1; + + WRITE_ONCE(init_pkru_value, new_init_pkru); + + return 1; +} +__setup("init_pkru=", setup_init_pkru); |