From 6bd330083e0e97b7ddc053459190bf3d5768ca83 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 6 Feb 2012 13:03:09 -0800 Subject: x86: Factor out TIF_IA32 from 32-bit address space Factor out IA32 (compatibility instruction set) from 32-bit address space in the thread_info flags; this is a precondition patch for x32 support. Originally-by: H. J. Lu Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/n/tip-4pr1xnnksprt7t0h3w5fw4rv@git.kernel.org --- arch/x86/kernel/process_64.c | 2 ++ arch/x86/kernel/sys_x86_64.c | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9b9fe4a85c87..0e900d09e232 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -508,6 +508,7 @@ void set_personality_64bit(void) /* Make sure to be in 64bit mode */ clear_thread_flag(TIF_IA32); + clear_thread_flag(TIF_ADDR32); /* Ensure the corresponding mm is not marked. */ if (current->mm) @@ -526,6 +527,7 @@ void set_personality_ia32(void) /* Make sure to be in 32bit mode */ set_thread_flag(TIF_IA32); + set_thread_flag(TIF_ADDR32); current->personality |= force_personality32; /* Mark the associated mm as containing 32-bit tasks. */ diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 051489082d59..f921df8c2099 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -98,7 +98,7 @@ out: static void find_start_end(unsigned long flags, unsigned long *begin, unsigned long *end) { - if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) { + if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) { unsigned long new_begin; /* This is usually used needed to map code in small model, so it needs to be in the first 31bit. Limit @@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, (!vma || addr + len <= vma->vm_start)) return addr; } - if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32)) + if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32)) && len <= mm->cached_hole_size) { mm->cached_hole_size = 0; mm->free_area_cache = begin; @@ -205,7 +205,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; /* for MAP_32BIT mappings we force the legact mmap base */ - if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) + if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) goto bottomup; /* requesting a specific address */ -- cgit v1.2.3 From bb2127240c5595ae4ef7115494f51e973692f64e Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 14 Feb 2012 13:56:49 -0800 Subject: x32: Add a thread flag for x32 processes An x32 process is *almost* the same thing as a 64-bit process with a 32-bit address limit, but there are a few minor differences -- in particular core dumps are 32 bits and signal handling is different. Signed-off-by: H. Peter Anvin --- arch/x86/kernel/process_64.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0e900d09e232..5fe2fbaa56ba 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -509,6 +509,7 @@ void set_personality_64bit(void) /* Make sure to be in 64bit mode */ clear_thread_flag(TIF_IA32); clear_thread_flag(TIF_ADDR32); + clear_thread_flag(TIF_X32); /* Ensure the corresponding mm is not marked. */ if (current->mm) @@ -528,6 +529,7 @@ void set_personality_ia32(void) /* Make sure to be in 32bit mode */ set_thread_flag(TIF_IA32); set_thread_flag(TIF_ADDR32); + clear_thread_flag(TIF_X32); current->personality |= force_personality32; /* Mark the associated mm as containing 32-bit tasks. */ -- cgit v1.2.3 From 6630f11ba54414b9870d87dfef2bee467bfa842a Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 14 Feb 2012 14:18:50 -0800 Subject: x32: Add x32 system calls to syscall/syscall_64.tbl Split the 64-bit system calls into "64" (64-bit only) and "common" (64-bit or x32) and add the x32 system call numbers. Signed-off-by: H. Peter Anvin --- arch/x86/kernel/asm-offsets_64.c | 2 ++ arch/x86/kernel/syscall_64.c | 3 +++ 2 files changed, 5 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 834e897b1e25..c3354f7b0a06 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -1,6 +1,8 @@ #include #define __SYSCALL_64(nr, sym, compat) [nr] = 1, +#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1, +#define __SYSCALL_X32(nr, sym, compat) /* Not yet */ static char syscalls_64[] = { #include }; diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c index 7ac7943be02c..26c4ca1f20e8 100644 --- a/arch/x86/kernel/syscall_64.c +++ b/arch/x86/kernel/syscall_64.c @@ -5,6 +5,9 @@ #include #include +#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) +#define __SYSCALL_X32(nr, sym, compat) /* Not yet */ + #define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; #include #undef __SYSCALL_64 -- cgit v1.2.3 From f28f0c23576662fb293defe9b1884d5a6e1bd85c Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 19 Feb 2012 07:38:43 -0800 Subject: x86: Move some signal-handling definitions to a common header There are some definitions which are duplicated between kernel/signal.c and ia32/ia32_signal.c; move them to a common header file. Rather than adding stuff to existing header files which contain data structures, create a new header file; hence the slightly odd name ("all the good ones were taken.") Note: nothing relied on signal_fault() being defined in . Signed-off-by: H. Peter Anvin --- arch/x86/kernel/signal.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 46a01bdc27e2..c432dc0e65f0 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -10,10 +10,8 @@ #include #include #include -#include #include #include -#include #include #include #include @@ -26,6 +24,7 @@ #include #include #include +#include #ifdef CONFIG_X86_64 #include @@ -37,13 +36,6 @@ #include -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - -#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ - X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ - X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ - X86_EFLAGS_CF) - #ifdef CONFIG_X86_32 # define FIX_EFLAGS (__FIX_EFLAGS | X86_EFLAGS_RF) #else -- cgit v1.2.3 From 851394229e79c11b0b5b74c509817848e9a80564 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 19 Feb 2012 07:43:09 -0800 Subject: x32: Export setup/restore_sigcontext from signal.c Export setup_sigcontext() and restore_sigcontext() from signal.c, so we can use the 64-bit versions verbatim for x32. Signed-off-by: H. Peter Anvin --- arch/x86/kernel/signal.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index c432dc0e65f0..450fb255f877 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -60,9 +60,8 @@ regs->seg = GET_SEG(seg) | 3; \ } while (0) -static int -restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, - unsigned long *pax) +int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, + unsigned long *pax) { void __user *buf; unsigned int tmpflags; @@ -117,9 +116,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, return err; } -static int -setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, - struct pt_regs *regs, unsigned long mask) +int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, + struct pt_regs *regs, unsigned long mask) { int err = 0; -- cgit v1.2.3 From fca460f95e928bae373daa8295877b6905bc62b8 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 19 Feb 2012 07:56:26 -0800 Subject: x32: Handle the x32 system call flag x32 shares most system calls with x86-64, but unfortunately some subsystem (the input subsystem is the chief offender) which require is_compat() when operating with a 32-bit userspace. The input system actually has text files in sysfs whose meaning is dependent on sizeof(long) in userspace! We could solve this by having two completely disjoint system call tables; requiring that each system call be duplicated. This patch takes a different approach: we add a flag to the system call number; this flag doesn't affect the system call dispatch but requests compat treatment from affected subsystems for the duration of the system call. The change of cmpq to cmpl is safe since it immediately follows the and. Signed-off-by: H. Peter Anvin --- arch/x86/kernel/entry_64.S | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 3fe8239fd8fb..a17b34216971 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -482,7 +482,12 @@ GLOBAL(system_call_after_swapgs) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) jnz tracesys system_call_fastpath: +#if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif ja badsys movq %r10,%rcx call *sys_call_table(,%rax,8) # XXX: rip relative @@ -596,7 +601,12 @@ tracesys: */ LOAD_ARGS ARGOFFSET, 1 RESTORE_REST +#if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) -- cgit v1.2.3 From c5a373942bbc41698724fc948c74f959f73407e5 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 19 Feb 2012 09:41:09 -0800 Subject: x32: Signal-related system calls x32 uses the 64-bit signal frame format, obviously, but there are some structures which mixes that with pointers or sizeof(long) types, as such we have to create a handful of system calls specific to x32. By and large these are a mixture of the 64-bit and the compat system calls. Originally-by: H. J. Lu Signed-off-by: H. Peter Anvin --- arch/x86/kernel/entry_64.S | 19 ++++++++ arch/x86/kernel/signal.c | 118 ++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 136 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index a17b34216971..53dc821f0a62 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -746,6 +746,25 @@ ENTRY(stub_rt_sigreturn) CFI_ENDPROC END(stub_rt_sigreturn) +#ifdef CONFIG_X86_X32_ABI + PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx + +ENTRY(stub_x32_rt_sigreturn) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + movq %rsp,%rdi + FIXUP_TOP_OF_STACK %r11 + call sys32_x32_rt_sigreturn + movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_x32_rt_sigreturn) + +#endif + /* * Build the entry stubs and pointer table with some assembler magic. * We pack 7 stubs into a single 32-byte chunk, which will fit in a diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 450fb255f877..c3846b6fb726 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -29,6 +29,7 @@ #ifdef CONFIG_X86_64 #include #include +#include #endif /* CONFIG_X86_64 */ #include @@ -632,6 +633,16 @@ static int signr_convert(int sig) #define is_ia32 0 #endif /* CONFIG_IA32_EMULATION */ +#ifdef CONFIG_X86_X32_ABI +#define is_x32 test_thread_flag(TIF_X32) + +static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, + siginfo_t *info, compat_sigset_t *set, + struct pt_regs *regs); +#else /* !CONFIG_X86_X32_ABI */ +#define is_x32 0 +#endif /* CONFIG_X86_X32_ABI */ + int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs); int ia32_setup_frame(int sig, struct k_sigaction *ka, @@ -656,8 +667,14 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, ret = ia32_setup_rt_frame(usig, ka, info, set, regs); else ret = ia32_setup_frame(usig, ka, set, regs); - } else +#ifdef CONFIG_X86_X32_ABI + } else if (is_x32) { + ret = x32_setup_rt_frame(usig, ka, info, + (compat_sigset_t *)set, regs); +#endif + } else { ret = __setup_rt_frame(sig, ka, info, set, regs); + } if (ret) { force_sigsegv(sig, current); @@ -840,3 +857,102 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) force_sig(SIGSEGV, me); } + +#ifdef CONFIG_X86_X32_ABI +static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, + siginfo_t *info, compat_sigset_t *set, + struct pt_regs *regs) +{ + struct rt_sigframe_x32 __user *frame; + void __user *restorer; + int err = 0; + void __user *fpstate = NULL; + + frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + return -EFAULT; + + if (ka->sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user32(&frame->info, info)) + return -EFAULT; + } + + put_user_try { + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + put_user_ex(sas_ss_flags(regs->sp), + &frame->uc.uc_stack.ss_flags); + put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + put_user_ex(0, &frame->uc.uc__pad0); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + if (ka->sa.sa_flags & SA_RESTORER) { + restorer = ka->sa.sa_restorer; + } else { + /* could use a vstub here */ + restorer = NULL; + err |= -EFAULT; + } + put_user_ex(restorer, &frame->pretcode); + } put_user_catch(err); + + if (err) + return -EFAULT; + + /* Set up registers for signal handler */ + regs->sp = (unsigned long) frame; + regs->ip = (unsigned long) ka->sa.sa_handler; + + /* We use the x32 calling convention here... */ + regs->di = sig; + regs->si = (unsigned long) &frame->info; + regs->dx = (unsigned long) &frame->uc; + + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); + + regs->cs = __USER_CS; + regs->ss = __USER_DS; + + return 0; +} + +asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) +{ + struct rt_sigframe_x32 __user *frame; + sigset_t set; + unsigned long ax; + struct pt_regs tregs; + + frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + sigdelsetmask(&set, ~_BLOCKABLE); + set_current_blocked(&set); + + if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) + goto badframe; + + tregs = *regs; + if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT) + goto badframe; + + return ax; + +badframe: + signal_fault(regs, frame, "x32 rt_sigreturn"); + return 0; +} +#endif -- cgit v1.2.3 From d1a797f388d6d30fa502915d1b9937ed758b7137 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 19 Feb 2012 10:06:34 -0800 Subject: x32: Handle process creation Allow an x32 process to be started. Originally-by: H. J. Lu Signed-off-by: H. Peter Anvin Cc: Peter Zijlstra --- arch/x86/kernel/cpu/perf_event.c | 4 +++- arch/x86/kernel/entry_64.S | 15 +++++++++++++++ arch/x86/kernel/process_64.c | 23 ++++++++++++++++------- 3 files changed, 34 insertions(+), 8 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5adce1040b11..63c0e058a405 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include @@ -1595,6 +1594,9 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) } #ifdef CONFIG_COMPAT + +#include + static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) { diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 53dc821f0a62..9e036f0ce5e0 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -763,6 +763,21 @@ ENTRY(stub_x32_rt_sigreturn) CFI_ENDPROC END(stub_x32_rt_sigreturn) +ENTRY(stub_x32_execve) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + FIXUP_TOP_OF_STACK %r11 + movq %rsp, %rcx + call sys32_execve + RESTORE_TOP_OF_STACK %r11 + movq %rax,RAX(%rsp) + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_x32_execve) + #endif /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 5fe2fbaa56ba..a0701da2bd18 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -364,7 +364,9 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) { start_thread_common(regs, new_ip, new_sp, - __USER32_CS, __USER32_DS, __USER32_DS); + test_thread_flag(TIF_X32) + ? __USER_CS : __USER32_CS, + __USER_DS, __USER_DS); } #endif @@ -508,6 +510,7 @@ void set_personality_64bit(void) /* Make sure to be in 64bit mode */ clear_thread_flag(TIF_IA32); + clear_thread_flag(TIF_X32); clear_thread_flag(TIF_ADDR32); clear_thread_flag(TIF_X32); @@ -522,22 +525,28 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -void set_personality_ia32(void) +void set_personality_ia32(bool x32) { /* inherit personality from parent */ /* Make sure to be in 32bit mode */ - set_thread_flag(TIF_IA32); set_thread_flag(TIF_ADDR32); - clear_thread_flag(TIF_X32); - current->personality |= force_personality32; /* Mark the associated mm as containing 32-bit tasks. */ if (current->mm) current->mm->context.ia32_compat = 1; - /* Prepare the first "return" to user space */ - current_thread_info()->status |= TS_COMPAT; + if (x32) { + clear_thread_flag(TIF_IA32); + set_thread_flag(TIF_X32); + current->personality &= ~READ_IMPLIES_EXEC; + } else { + set_thread_flag(TIF_IA32); + clear_thread_flag(TIF_X32); + current->personality |= force_personality32; + /* Prepare the first "return" to user space */ + current_thread_info()->status |= TS_COMPAT; + } } unsigned long get_wchan(struct task_struct *p) -- cgit v1.2.3 From a06c9bc0647f66df0534fb887ddf6cddd35f426c Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 19 Feb 2012 11:08:37 -0800 Subject: x32: If configured, add x32 system calls to system call tables If CONFIG_X86_X32_ABI is defined, add the x32 system calls to the system call tables. Signed-off-by: H. Peter Anvin --- arch/x86/kernel/asm-offsets_64.c | 6 +++++- arch/x86/kernel/syscall_64.c | 7 ++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index c3354f7b0a06..1b4754f82ba7 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -2,7 +2,11 @@ #define __SYSCALL_64(nr, sym, compat) [nr] = 1, #define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1, -#define __SYSCALL_X32(nr, sym, compat) /* Not yet */ +#ifdef CONFIG_X86_X32_ABI +# define __SYSCALL_X32(nr, sym, compat) [nr] = 1, +#else +# define __SYSCALL_X32(nr, sym, compat) /* nothing */ +#endif static char syscalls_64[] = { #include }; diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c index 26c4ca1f20e8..5c7f8c20da74 100644 --- a/arch/x86/kernel/syscall_64.c +++ b/arch/x86/kernel/syscall_64.c @@ -6,7 +6,12 @@ #include #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) -#define __SYSCALL_X32(nr, sym, compat) /* Not yet */ + +#ifdef CONFIG_X86_X32_ABI +# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat) +#else +# define __SYSCALL_X32(nr, sym, compat) /* nothing */ +#endif #define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; #include -- cgit v1.2.3 From ce5f7a99df87918b5be4618a9386213a8e9a7146 Mon Sep 17 00:00:00 2001 From: Bobby Powers Date: Sat, 25 Feb 2012 23:25:38 -0500 Subject: x32: Make sure TS_COMPAT is cleared for x32 tasks If a process has a non-x32 ia32 personality and changes to x32, the process would keep its TS_COMPAT flag. x32 uses the presence of the x32 flag on a syscall to determine compat status, so make sure TS_COMPAT is cleared. Signed-off-by: Bobby Powers Link: http://lkml.kernel.org/r/1330230338-25077-1-git-send-email-bobbypowers@gmail.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/process_64.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a0701da2bd18..32e04120b2cd 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -540,6 +540,9 @@ void set_personality_ia32(bool x32) clear_thread_flag(TIF_IA32); set_thread_flag(TIF_X32); current->personality &= ~READ_IMPLIES_EXEC; + /* is_compat_task() uses the presence of the x32 + syscall bit flag to determine compat status */ + current_thread_info()->status &= ~TS_COMPAT; } else { set_thread_flag(TIF_IA32); clear_thread_flag(TIF_X32); -- cgit v1.2.3 From 00194b2e845da29395ad00c13a884d9acb9306b5 Mon Sep 17 00:00:00 2001 From: Bobby Powers Date: Sat, 25 Feb 2012 22:59:34 -0500 Subject: x32: Only clear TIF_X32 flag once Commits bb212724 and d1a797f3 both added a call to clear_thread_flag(TIF_X32) under set_personality_64bit() - only one is needed. Signed-off-by: Bobby Powers Link: http://lkml.kernel.org/r/1330228774-24223-1-git-send-email-bobbypowers@gmail.com Signed-off-by: H. Peter Anvin --- arch/x86/kernel/process_64.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 32e04120b2cd..a4659739e202 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -510,7 +510,6 @@ void set_personality_64bit(void) /* Make sure to be in 64bit mode */ clear_thread_flag(TIF_IA32); - clear_thread_flag(TIF_X32); clear_thread_flag(TIF_ADDR32); clear_thread_flag(TIF_X32); -- cgit v1.2.3 From b263b31e8ad65cdbfa5a7f739460f350554a2dc1 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 27 Feb 2012 15:15:25 -0800 Subject: x86, mtrr: Use explicit sizing and padding for the 64-bit ioctls Specify the data structures for the 64-bit ioctls with explicit sizing and padding so that the x32 kernel will correctly use the 64-bit forms of these ioctls. Note that these ioctls are bogus in both forms on both 32 and 64 bits; even on 64 bits the maximum MTRR size is only 44 bits long. Note that nothing really is supposed to use these ioctls and that the preferred interface is text strings on /proc/mtrr, or better yet, nothing at all (use /sys/bus/pci/devices/*/resource*_wc for write combining; that uses PAT not MTRRs.) Signed-off-by: H. Peter Anvin Cc: H. J. Lu Tested-by: Nitin A. Kamble Link: http://lkml.kernel.org/n/tip-vwvnlu3hjmtkwvij4qxtm90l@git.kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/mtrr/if.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 79289632cb27..a041e094b8b9 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -167,6 +167,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) { int err = 0; mtrr_type type; + unsigned long base; unsigned long size; struct mtrr_sentry sentry; struct mtrr_gentry gentry; @@ -267,14 +268,14 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #endif if (gentry.regnum >= num_var_ranges) return -EINVAL; - mtrr_if->get(gentry.regnum, &gentry.base, &size, &type); + mtrr_if->get(gentry.regnum, &base, &size, &type); /* Hide entries that go above 4GB */ - if (gentry.base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)) + if (base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)) || size >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))) gentry.base = gentry.size = gentry.type = 0; else { - gentry.base <<= PAGE_SHIFT; + gentry.base = base << PAGE_SHIFT; gentry.size = size << PAGE_SHIFT; gentry.type = type; } @@ -321,11 +322,12 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #endif if (gentry.regnum >= num_var_ranges) return -EINVAL; - mtrr_if->get(gentry.regnum, &gentry.base, &size, &type); + mtrr_if->get(gentry.regnum, &base, &size, &type); /* Hide entries that would overflow */ if (size != (__typeof__(gentry.size))size) gentry.base = gentry.size = gentry.type = 0; else { + gentry.base = base; gentry.size = size; gentry.type = type; } -- cgit v1.2.3 From 55283e2537714f9370c4ab847d170acf223daf90 Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Mon, 5 Mar 2012 15:32:11 -0800 Subject: x32: Add ptrace for x32 X32 ptrace is a hybrid of 64bit ptrace and compat ptrace with 32bit address and longs. It use 64bit ptrace to access the full 64bit registers. PTRACE_PEEKUSR and PTRACE_POKEUSR are only allowed to access segment and debug registers. PTRACE_PEEKUSR returns the lower 32bits and PTRACE_POKEUSR zero-extends 32bit value to 64bit. It works since the upper 32bits of segment and debug registers of x32 process are always zero. GDB only uses PTRACE_PEEKUSR and PTRACE_POKEUSR to access segment and debug registers. [ hpa: changed TIF_X32 test to use !is_ia32_task() instead, and moved the system call number to the now-unused 521 slot. ] Signed-off-by: "H.J. Lu" Signed-off-by: H. Peter Anvin Cc: Roland McGrath Cc: Oleg Nesterov Link: http://lkml.kernel.org/r/1329696488-16970-1-git-send-email-hpa@zytor.com --- arch/x86/kernel/ptrace.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 50267386b766..93e7877a19c4 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1130,6 +1130,100 @@ static int genregs32_set(struct task_struct *target, return ret; } +#ifdef CONFIG_X86_X32_ABI +static long x32_arch_ptrace(struct task_struct *child, + compat_long_t request, compat_ulong_t caddr, + compat_ulong_t cdata) +{ + unsigned long addr = caddr; + unsigned long data = cdata; + void __user *datap = compat_ptr(data); + int ret; + + switch (request) { + /* Read 32bits at location addr in the USER area. Only allow + to return the lower 32bits of segment and debug registers. */ + case PTRACE_PEEKUSR: { + u32 tmp; + + ret = -EIO; + if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) || + addr < offsetof(struct user_regs_struct, cs)) + break; + + tmp = 0; /* Default return condition */ + if (addr < sizeof(struct user_regs_struct)) + tmp = getreg(child, addr); + else if (addr >= offsetof(struct user, u_debugreg[0]) && + addr <= offsetof(struct user, u_debugreg[7])) { + addr -= offsetof(struct user, u_debugreg[0]); + tmp = ptrace_get_debugreg(child, addr / sizeof(data)); + } + ret = put_user(tmp, (__u32 __user *)datap); + break; + } + + /* Write the word at location addr in the USER area. Only allow + to update segment and debug registers with the upper 32bits + zero-extended. */ + case PTRACE_POKEUSR: + ret = -EIO; + if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) || + addr < offsetof(struct user_regs_struct, cs)) + break; + + if (addr < sizeof(struct user_regs_struct)) + ret = putreg(child, addr, data); + else if (addr >= offsetof(struct user, u_debugreg[0]) && + addr <= offsetof(struct user, u_debugreg[7])) { + addr -= offsetof(struct user, u_debugreg[0]); + ret = ptrace_set_debugreg(child, + addr / sizeof(data), data); + } + break; + + case PTRACE_GETREGS: /* Get all gp regs from the child. */ + return copy_regset_to_user(child, + task_user_regset_view(current), + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct), + datap); + + case PTRACE_SETREGS: /* Set all gp regs in the child. */ + return copy_regset_from_user(child, + task_user_regset_view(current), + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct), + datap); + + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + return copy_regset_to_user(child, + task_user_regset_view(current), + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + return copy_regset_from_user(child, + task_user_regset_view(current), + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + + /* normal 64bit interface to access TLS data. + Works just like arch_prctl, except that the arguments + are reversed. */ + case PTRACE_ARCH_PRCTL: + return do_arch_prctl(child, data, addr); + + default: + return compat_ptrace_request(child, request, addr, data); + } + + return ret; +} +#endif + long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { @@ -1139,6 +1233,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, int ret; __u32 val; +#ifdef CONFIG_X86_X32_ABI + if (!is_ia32_task()) + return x32_arch_ptrace(child, request, caddr, cdata); +#endif + switch (request) { case PTRACE_PEEKUSR: ret = getreg32(child, addr, &val); -- cgit v1.2.3