diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
commit | ace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch) | |
tree | b2d64bc10158fdd5497876388cd68142ca374ed3 /arch/x86/kernel/ptrace.c | |
parent | Initial commit. (diff) | |
download | linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip |
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/x86/kernel/ptrace.c')
-rw-r--r-- | arch/x86/kernel/ptrace.c | 1423 |
1 files changed, 1423 insertions, 0 deletions
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c new file mode 100644 index 0000000000..095f04bdab --- /dev/null +++ b/arch/x86/kernel/ptrace.c @@ -0,0 +1,1423 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* By Ross Biro 1/23/92 */ +/* + * Pentium III FXSR, SSE support + * Gareth Hughes <gareth@valinux.com>, May 2000 + */ + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/sched/task_stack.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/ptrace.h> +#include <linux/user.h> +#include <linux/elf.h> +#include <linux/security.h> +#include <linux/audit.h> +#include <linux/seccomp.h> +#include <linux/signal.h> +#include <linux/perf_event.h> +#include <linux/hw_breakpoint.h> +#include <linux/rcupdate.h> +#include <linux/export.h> +#include <linux/context_tracking.h> +#include <linux/nospec.h> + +#include <linux/uaccess.h> +#include <asm/processor.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> +#include <asm/fpu/xstate.h> +#include <asm/debugreg.h> +#include <asm/ldt.h> +#include <asm/desc.h> +#include <asm/prctl.h> +#include <asm/proto.h> +#include <asm/hw_breakpoint.h> +#include <asm/traps.h> +#include <asm/syscall.h> +#include <asm/fsgsbase.h> +#include <asm/io_bitmap.h> + +#include "tls.h" + +enum x86_regset_32 { + REGSET32_GENERAL, + REGSET32_FP, + REGSET32_XFP, + REGSET32_XSTATE, + REGSET32_TLS, + REGSET32_IOPERM, +}; + +enum x86_regset_64 { + REGSET64_GENERAL, + REGSET64_FP, + REGSET64_IOPERM, + REGSET64_XSTATE, + REGSET64_SSP, +}; + +#define REGSET_GENERAL \ +({ \ + BUILD_BUG_ON((int)REGSET32_GENERAL != (int)REGSET64_GENERAL); \ + REGSET32_GENERAL; \ +}) + +#define REGSET_FP \ +({ \ + BUILD_BUG_ON((int)REGSET32_FP != (int)REGSET64_FP); \ + REGSET32_FP; \ +}) + + +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { +#ifdef CONFIG_X86_64 + REG_OFFSET_NAME(r15), + REG_OFFSET_NAME(r14), + REG_OFFSET_NAME(r13), + REG_OFFSET_NAME(r12), + REG_OFFSET_NAME(r11), + REG_OFFSET_NAME(r10), + REG_OFFSET_NAME(r9), + REG_OFFSET_NAME(r8), +#endif + REG_OFFSET_NAME(bx), + REG_OFFSET_NAME(cx), + REG_OFFSET_NAME(dx), + REG_OFFSET_NAME(si), + REG_OFFSET_NAME(di), + REG_OFFSET_NAME(bp), + REG_OFFSET_NAME(ax), +#ifdef CONFIG_X86_32 + REG_OFFSET_NAME(ds), + REG_OFFSET_NAME(es), + REG_OFFSET_NAME(fs), + REG_OFFSET_NAME(gs), +#endif + REG_OFFSET_NAME(orig_ax), + REG_OFFSET_NAME(ip), + REG_OFFSET_NAME(cs), + REG_OFFSET_NAME(flags), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(ss), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_query_register_name() - query register name from its offset + * @offset: the offset of a register in struct pt_regs. + * + * regs_query_register_name() returns the name of a register from its + * offset in struct pt_regs. If the @offset is invalid, this returns NULL; + */ +const char *regs_query_register_name(unsigned int offset) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (roff->offset == offset) + return roff->name; + return NULL; +} + +/* + * does not yet catch signals sent when the child dies. + * in exit.c or in signal.c. + */ + +/* + * Determines which flags the user has access to [1 = access, 0 = no access]. + */ +#define FLAG_MASK_32 ((unsigned long) \ + (X86_EFLAGS_CF | X86_EFLAGS_PF | \ + X86_EFLAGS_AF | X86_EFLAGS_ZF | \ + X86_EFLAGS_SF | X86_EFLAGS_TF | \ + X86_EFLAGS_DF | X86_EFLAGS_OF | \ + X86_EFLAGS_RF | X86_EFLAGS_AC)) + +/* + * Determines whether a value may be installed in a segment register. + */ +static inline bool invalid_selector(u16 value) +{ + return unlikely(value != 0 && (value & SEGMENT_RPL_MASK) != USER_RPL); +} + +#ifdef CONFIG_X86_32 + +#define FLAG_MASK FLAG_MASK_32 + +static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno) +{ + BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0); + return ®s->bx + (regno >> 2); +} + +static u16 get_segment_reg(struct task_struct *task, unsigned long offset) +{ + /* + * Returning the value truncates it to 16 bits. + */ + unsigned int retval; + if (offset != offsetof(struct user_regs_struct, gs)) + retval = *pt_regs_access(task_pt_regs(task), offset); + else { + if (task == current) + savesegment(gs, retval); + else + retval = task->thread.gs; + } + return retval; +} + +static int set_segment_reg(struct task_struct *task, + unsigned long offset, u16 value) +{ + if (WARN_ON_ONCE(task == current)) + return -EIO; + + /* + * The value argument was already truncated to 16 bits. + */ + if (invalid_selector(value)) + return -EIO; + + /* + * For %cs and %ss we cannot permit a null selector. + * We can permit a bogus selector as long as it has USER_RPL. + * Null selectors are fine for other segment registers, but + * we will never get back to user mode with invalid %cs or %ss + * and will take the trap in iret instead. Much code relies + * on user_mode() to distinguish a user trap frame (which can + * safely use invalid selectors) from a kernel trap frame. + */ + switch (offset) { + case offsetof(struct user_regs_struct, cs): + case offsetof(struct user_regs_struct, ss): + if (unlikely(value == 0)) + return -EIO; + fallthrough; + + default: + *pt_regs_access(task_pt_regs(task), offset) = value; + break; + + case offsetof(struct user_regs_struct, gs): + task->thread.gs = value; + } + + return 0; +} + +#else /* CONFIG_X86_64 */ + +#define FLAG_MASK (FLAG_MASK_32 | X86_EFLAGS_NT) + +static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long offset) +{ + BUILD_BUG_ON(offsetof(struct pt_regs, r15) != 0); + return ®s->r15 + (offset / sizeof(regs->r15)); +} + +static u16 get_segment_reg(struct task_struct *task, unsigned long offset) +{ + /* + * Returning the value truncates it to 16 bits. + */ + unsigned int seg; + + switch (offset) { + case offsetof(struct user_regs_struct, fs): + if (task == current) { + /* Older gas can't assemble movq %?s,%r?? */ + asm("movl %%fs,%0" : "=r" (seg)); + return seg; + } + return task->thread.fsindex; + case offsetof(struct user_regs_struct, gs): + if (task == current) { + asm("movl %%gs,%0" : "=r" (seg)); + return seg; + } + return task->thread.gsindex; + case offsetof(struct user_regs_struct, ds): + if (task == current) { + asm("movl %%ds,%0" : "=r" (seg)); + return seg; + } + return task->thread.ds; + case offsetof(struct user_regs_struct, es): + if (task == current) { + asm("movl %%es,%0" : "=r" (seg)); + return seg; + } + return task->thread.es; + + case offsetof(struct user_regs_struct, cs): + case offsetof(struct user_regs_struct, ss): + break; + } + return *pt_regs_access(task_pt_regs(task), offset); +} + +static int set_segment_reg(struct task_struct *task, + unsigned long offset, u16 value) +{ + if (WARN_ON_ONCE(task == current)) + return -EIO; + + /* + * The value argument was already truncated to 16 bits. + */ + if (invalid_selector(value)) + return -EIO; + + /* + * Writes to FS and GS will change the stored selector. Whether + * this changes the segment base as well depends on whether + * FSGSBASE is enabled. + */ + + switch (offset) { + case offsetof(struct user_regs_struct,fs): + task->thread.fsindex = value; + break; + case offsetof(struct user_regs_struct,gs): + task->thread.gsindex = value; + break; + case offsetof(struct user_regs_struct,ds): + task->thread.ds = value; + break; + case offsetof(struct user_regs_struct,es): + task->thread.es = value; + break; + + /* + * Can't actually change these in 64-bit mode. + */ + case offsetof(struct user_regs_struct,cs): + if (unlikely(value == 0)) + return -EIO; + task_pt_regs(task)->cs = value; + break; + case offsetof(struct user_regs_struct,ss): + if (unlikely(value == 0)) + return -EIO; + task_pt_regs(task)->ss = value; + break; + } + + return 0; +} + +#endif /* CONFIG_X86_32 */ + +static unsigned long get_flags(struct task_struct *task) +{ + unsigned long retval = task_pt_regs(task)->flags; + + /* + * If the debugger set TF, hide it from the readout. + */ + if (test_tsk_thread_flag(task, TIF_FORCED_TF)) + retval &= ~X86_EFLAGS_TF; + + return retval; +} + +static int set_flags(struct task_struct *task, unsigned long value) +{ + struct pt_regs *regs = task_pt_regs(task); + + /* + * If the user value contains TF, mark that + * it was not "us" (the debugger) that set it. + * If not, make sure it stays set if we had. + */ + if (value & X86_EFLAGS_TF) + clear_tsk_thread_flag(task, TIF_FORCED_TF); + else if (test_tsk_thread_flag(task, TIF_FORCED_TF)) + value |= X86_EFLAGS_TF; + + regs->flags = (regs->flags & ~FLAG_MASK) | (value & FLAG_MASK); + + return 0; +} + +static int putreg(struct task_struct *child, + unsigned long offset, unsigned long value) +{ + switch (offset) { + case offsetof(struct user_regs_struct, cs): + case offsetof(struct user_regs_struct, ds): + case offsetof(struct user_regs_struct, es): + case offsetof(struct user_regs_struct, fs): + case offsetof(struct user_regs_struct, gs): + case offsetof(struct user_regs_struct, ss): + return set_segment_reg(child, offset, value); + + case offsetof(struct user_regs_struct, flags): + return set_flags(child, value); + +#ifdef CONFIG_X86_64 + case offsetof(struct user_regs_struct,fs_base): + if (value >= TASK_SIZE_MAX) + return -EIO; + x86_fsbase_write_task(child, value); + return 0; + case offsetof(struct user_regs_struct,gs_base): + if (value >= TASK_SIZE_MAX) + return -EIO; + x86_gsbase_write_task(child, value); + return 0; +#endif + } + + *pt_regs_access(task_pt_regs(child), offset) = value; + return 0; +} + +static unsigned long getreg(struct task_struct *task, unsigned long offset) +{ + switch (offset) { + case offsetof(struct user_regs_struct, cs): + case offsetof(struct user_regs_struct, ds): + case offsetof(struct user_regs_struct, es): + case offsetof(struct user_regs_struct, fs): + case offsetof(struct user_regs_struct, gs): + case offsetof(struct user_regs_struct, ss): + return get_segment_reg(task, offset); + + case offsetof(struct user_regs_struct, flags): + return get_flags(task); + +#ifdef CONFIG_X86_64 + case offsetof(struct user_regs_struct, fs_base): + return x86_fsbase_read_task(task); + case offsetof(struct user_regs_struct, gs_base): + return x86_gsbase_read_task(task); +#endif + } + + return *pt_regs_access(task_pt_regs(task), offset); +} + +static int genregs_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + int reg; + + for (reg = 0; to.left; reg++) + membuf_store(&to, getreg(target, reg * sizeof(unsigned long))); + return 0; +} + +static int genregs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret = 0; + if (kbuf) { + const unsigned long *k = kbuf; + while (count >= sizeof(*k) && !ret) { + ret = putreg(target, pos, *k++); + count -= sizeof(*k); + pos += sizeof(*k); + } + } else { + const unsigned long __user *u = ubuf; + while (count >= sizeof(*u) && !ret) { + unsigned long word; + ret = __get_user(word, u++); + if (ret) + break; + ret = putreg(target, pos, word); + count -= sizeof(*u); + pos += sizeof(*u); + } + } + return ret; +} + +static void ptrace_triggered(struct perf_event *bp, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + int i; + struct thread_struct *thread = &(current->thread); + + /* + * Store in the virtual DR6 register the fact that the breakpoint + * was hit so the thread's debugger will see it. + */ + for (i = 0; i < HBP_NUM; i++) { + if (thread->ptrace_bps[i] == bp) + break; + } + + thread->virtual_dr6 |= (DR_TRAP0 << i); +} + +/* + * Walk through every ptrace breakpoints for this thread and + * build the dr7 value on top of their attributes. + * + */ +static unsigned long ptrace_get_dr7(struct perf_event *bp[]) +{ + int i; + int dr7 = 0; + struct arch_hw_breakpoint *info; + + for (i = 0; i < HBP_NUM; i++) { + if (bp[i] && !bp[i]->attr.disabled) { + info = counter_arch_bp(bp[i]); + dr7 |= encode_dr7(i, info->len, info->type); + } + } + + return dr7; +} + +static int ptrace_fill_bp_fields(struct perf_event_attr *attr, + int len, int type, bool disabled) +{ + int err, bp_len, bp_type; + + err = arch_bp_generic_fields(len, type, &bp_len, &bp_type); + if (!err) { + attr->bp_len = bp_len; + attr->bp_type = bp_type; + attr->disabled = disabled; + } + + return err; +} + +static struct perf_event * +ptrace_register_breakpoint(struct task_struct *tsk, int len, int type, + unsigned long addr, bool disabled) +{ + struct perf_event_attr attr; + int err; + + ptrace_breakpoint_init(&attr); + attr.bp_addr = addr; + + err = ptrace_fill_bp_fields(&attr, len, type, disabled); + if (err) + return ERR_PTR(err); + + return register_user_hw_breakpoint(&attr, ptrace_triggered, + NULL, tsk); +} + +static int ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, + int disabled) +{ + struct perf_event_attr attr = bp->attr; + int err; + + err = ptrace_fill_bp_fields(&attr, len, type, disabled); + if (err) + return err; + + return modify_user_hw_breakpoint(bp, &attr); +} + +/* + * Handle ptrace writes to debug register 7. + */ +static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data) +{ + struct thread_struct *thread = &tsk->thread; + unsigned long old_dr7; + bool second_pass = false; + int i, rc, ret = 0; + + data &= ~DR_CONTROL_RESERVED; + old_dr7 = ptrace_get_dr7(thread->ptrace_bps); + +restore: + rc = 0; + for (i = 0; i < HBP_NUM; i++) { + unsigned len, type; + bool disabled = !decode_dr7(data, i, &len, &type); + struct perf_event *bp = thread->ptrace_bps[i]; + + if (!bp) { + if (disabled) + continue; + + bp = ptrace_register_breakpoint(tsk, + len, type, 0, disabled); + if (IS_ERR(bp)) { + rc = PTR_ERR(bp); + break; + } + + thread->ptrace_bps[i] = bp; + continue; + } + + rc = ptrace_modify_breakpoint(bp, len, type, disabled); + if (rc) + break; + } + + /* Restore if the first pass failed, second_pass shouldn't fail. */ + if (rc && !WARN_ON(second_pass)) { + ret = rc; + data = old_dr7; + second_pass = true; + goto restore; + } + + return ret; +} + +/* + * Handle PTRACE_PEEKUSR calls for the debug register area. + */ +static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) +{ + struct thread_struct *thread = &tsk->thread; + unsigned long val = 0; + + if (n < HBP_NUM) { + int index = array_index_nospec(n, HBP_NUM); + struct perf_event *bp = thread->ptrace_bps[index]; + + if (bp) + val = bp->hw.info.address; + } else if (n == 6) { + val = thread->virtual_dr6 ^ DR6_RESERVED; /* Flip back to arch polarity */ + } else if (n == 7) { + val = thread->ptrace_dr7; + } + return val; +} + +static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, + unsigned long addr) +{ + struct thread_struct *t = &tsk->thread; + struct perf_event *bp = t->ptrace_bps[nr]; + int err = 0; + + if (!bp) { + /* + * Put stub len and type to create an inactive but correct bp. + * + * CHECKME: the previous code returned -EIO if the addr wasn't + * a valid task virtual addr. The new one will return -EINVAL in + * this case. + * -EINVAL may be what we want for in-kernel breakpoints users, + * but -EIO looks better for ptrace, since we refuse a register + * writing for the user. And anyway this is the previous + * behaviour. + */ + bp = ptrace_register_breakpoint(tsk, + X86_BREAKPOINT_LEN_1, X86_BREAKPOINT_WRITE, + addr, true); + if (IS_ERR(bp)) + err = PTR_ERR(bp); + else + t->ptrace_bps[nr] = bp; + } else { + struct perf_event_attr attr = bp->attr; + + attr.bp_addr = addr; + err = modify_user_hw_breakpoint(bp, &attr); + } + + return err; +} + +/* + * Handle PTRACE_POKEUSR calls for the debug register area. + */ +static int ptrace_set_debugreg(struct task_struct *tsk, int n, + unsigned long val) +{ + struct thread_struct *thread = &tsk->thread; + /* There are no DR4 or DR5 registers */ + int rc = -EIO; + + if (n < HBP_NUM) { + rc = ptrace_set_breakpoint_addr(tsk, n, val); + } else if (n == 6) { + thread->virtual_dr6 = val ^ DR6_RESERVED; /* Flip to positive polarity */ + rc = 0; + } else if (n == 7) { + rc = ptrace_write_dr7(tsk, val); + if (!rc) + thread->ptrace_dr7 = val; + } + return rc; +} + +/* + * These access the current or another (stopped) task's io permission + * bitmap for debugging or core dump. + */ +static int ioperm_active(struct task_struct *target, + const struct user_regset *regset) +{ + struct io_bitmap *iobm = target->thread.io_bitmap; + + return iobm ? DIV_ROUND_UP(iobm->max, regset->size) : 0; +} + +static int ioperm_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct io_bitmap *iobm = target->thread.io_bitmap; + + if (!iobm) + return -ENXIO; + + return membuf_write(&to, iobm->bitmap, IO_BITMAP_BYTES); +} + +/* + * Called by kernel/ptrace.c when detaching.. + * + * Make sure the single step bit is not set. + */ +void ptrace_disable(struct task_struct *child) +{ + user_disable_single_step(child); +} + +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION +static const struct user_regset_view user_x86_32_view; /* Initialized below. */ +#endif +#ifdef CONFIG_X86_64 +static const struct user_regset_view user_x86_64_view; /* Initialized below. */ +#endif + +long arch_ptrace(struct task_struct *child, long request, + unsigned long addr, unsigned long data) +{ + int ret; + unsigned long __user *datap = (unsigned long __user *)data; + +#ifdef CONFIG_X86_64 + /* This is native 64-bit ptrace() */ + const struct user_regset_view *regset_view = &user_x86_64_view; +#else + /* This is native 32-bit ptrace() */ + const struct user_regset_view *regset_view = &user_x86_32_view; +#endif + + switch (request) { + /* read the word at location addr in the USER area. */ + case PTRACE_PEEKUSR: { + unsigned long tmp; + + ret = -EIO; + if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user)) + 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, datap); + break; + } + + case PTRACE_POKEUSR: /* write the word at location addr in the USER area */ + ret = -EIO; + if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user)) + 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, + regset_view, + 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, + regset_view, + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct), + datap); + + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + return copy_regset_to_user(child, + regset_view, + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + return copy_regset_from_user(child, + regset_view, + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + +#ifdef CONFIG_X86_32 + case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET32_XFP, + 0, sizeof(struct user_fxsr_struct), + datap) ? -EIO : 0; + + case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ + return copy_regset_from_user(child, &user_x86_32_view, + REGSET32_XFP, + 0, sizeof(struct user_fxsr_struct), + datap) ? -EIO : 0; +#endif + +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION + case PTRACE_GET_THREAD_AREA: + if ((int) addr < 0) + return -EIO; + ret = do_get_thread_area(child, addr, + (struct user_desc __user *)data); + break; + + case PTRACE_SET_THREAD_AREA: + if ((int) addr < 0) + return -EIO; + ret = do_set_thread_area(child, addr, + (struct user_desc __user *)data, 0); + break; +#endif + +#ifdef CONFIG_X86_64 + /* normal 64bit interface to access TLS data. + Works just like arch_prctl, except that the arguments + are reversed. */ + case PTRACE_ARCH_PRCTL: + ret = do_arch_prctl_64(child, data, addr); + break; +#endif + + default: + ret = ptrace_request(child, request, addr, data); + break; + } + + return ret; +} + +#ifdef CONFIG_IA32_EMULATION + +#include <linux/compat.h> +#include <linux/syscalls.h> +#include <asm/ia32.h> +#include <asm/user32.h> + +#define R32(l,q) \ + case offsetof(struct user32, regs.l): \ + regs->q = value; break + +#define SEG32(rs) \ + case offsetof(struct user32, regs.rs): \ + return set_segment_reg(child, \ + offsetof(struct user_regs_struct, rs), \ + value); \ + break + +static int putreg32(struct task_struct *child, unsigned regno, u32 value) +{ + struct pt_regs *regs = task_pt_regs(child); + int ret; + + switch (regno) { + + SEG32(cs); + SEG32(ds); + SEG32(es); + + /* + * A 32-bit ptracer on a 64-bit kernel expects that writing + * FS or GS will also update the base. This is needed for + * operations like PTRACE_SETREGS to fully restore a saved + * CPU state. + */ + + case offsetof(struct user32, regs.fs): + ret = set_segment_reg(child, + offsetof(struct user_regs_struct, fs), + value); + if (ret == 0) + child->thread.fsbase = + x86_fsgsbase_read_task(child, value); + return ret; + + case offsetof(struct user32, regs.gs): + ret = set_segment_reg(child, + offsetof(struct user_regs_struct, gs), + value); + if (ret == 0) + child->thread.gsbase = + x86_fsgsbase_read_task(child, value); + return ret; + + SEG32(ss); + + R32(ebx, bx); + R32(ecx, cx); + R32(edx, dx); + R32(edi, di); + R32(esi, si); + R32(ebp, bp); + R32(eax, ax); + R32(eip, ip); + R32(esp, sp); + + case offsetof(struct user32, regs.orig_eax): + /* + * Warning: bizarre corner case fixup here. A 32-bit + * debugger setting orig_eax to -1 wants to disable + * syscall restart. Make sure that the syscall + * restart code sign-extends orig_ax. Also make sure + * we interpret the -ERESTART* codes correctly if + * loaded into regs->ax in case the task is not + * actually still sitting at the exit from a 32-bit + * syscall with TS_COMPAT still set. + */ + regs->orig_ax = value; + if (syscall_get_nr(child, regs) != -1) + child->thread_info.status |= TS_I386_REGS_POKED; + break; + + case offsetof(struct user32, regs.eflags): + return set_flags(child, value); + + case offsetof(struct user32, u_debugreg[0]) ... + offsetof(struct user32, u_debugreg[7]): + regno -= offsetof(struct user32, u_debugreg[0]); + return ptrace_set_debugreg(child, regno / 4, value); + + default: + if (regno > sizeof(struct user32) || (regno & 3)) + return -EIO; + + /* + * Other dummy fields in the virtual user structure + * are ignored + */ + break; + } + return 0; +} + +#undef R32 +#undef SEG32 + +#define R32(l,q) \ + case offsetof(struct user32, regs.l): \ + *val = regs->q; break + +#define SEG32(rs) \ + case offsetof(struct user32, regs.rs): \ + *val = get_segment_reg(child, \ + offsetof(struct user_regs_struct, rs)); \ + break + +static int getreg32(struct task_struct *child, unsigned regno, u32 *val) +{ + struct pt_regs *regs = task_pt_regs(child); + + switch (regno) { + + SEG32(ds); + SEG32(es); + SEG32(fs); + SEG32(gs); + + R32(cs, cs); + R32(ss, ss); + R32(ebx, bx); + R32(ecx, cx); + R32(edx, dx); + R32(edi, di); + R32(esi, si); + R32(ebp, bp); + R32(eax, ax); + R32(orig_eax, orig_ax); + R32(eip, ip); + R32(esp, sp); + + case offsetof(struct user32, regs.eflags): + *val = get_flags(child); + break; + + case offsetof(struct user32, u_debugreg[0]) ... + offsetof(struct user32, u_debugreg[7]): + regno -= offsetof(struct user32, u_debugreg[0]); + *val = ptrace_get_debugreg(child, regno / 4); + break; + + default: + if (regno > sizeof(struct user32) || (regno & 3)) + return -EIO; + + /* + * Other dummy fields in the virtual user structure + * are ignored + */ + *val = 0; + break; + } + return 0; +} + +#undef R32 +#undef SEG32 + +static int genregs32_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + int reg; + + for (reg = 0; to.left; reg++) { + u32 val; + getreg32(target, reg * 4, &val); + membuf_store(&to, val); + } + return 0; +} + +static int genregs32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret = 0; + if (kbuf) { + const compat_ulong_t *k = kbuf; + while (count >= sizeof(*k) && !ret) { + ret = putreg32(target, pos, *k++); + count -= sizeof(*k); + pos += sizeof(*k); + } + } else { + const compat_ulong_t __user *u = ubuf; + while (count >= sizeof(*u) && !ret) { + compat_ulong_t word; + ret = __get_user(word, u++); + if (ret) + break; + ret = putreg32(target, pos, word); + count -= sizeof(*u); + pos += sizeof(*u); + } + } + return ret; +} + +static long ia32_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; + __u32 val; + + switch (request) { + case PTRACE_PEEKUSR: + ret = getreg32(child, addr, &val); + if (ret == 0) + ret = put_user(val, (__u32 __user *)datap); + break; + + case PTRACE_POKEUSR: + ret = putreg32(child, addr, data); + break; + + case PTRACE_GETREGS: /* Get all gp regs from the child. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct32), + datap); + + case PTRACE_SETREGS: /* Set all gp regs in the child. */ + return copy_regset_from_user(child, &user_x86_32_view, + REGSET_GENERAL, 0, + sizeof(struct user_regs_struct32), + datap); + + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_FP, 0, + sizeof(struct user_i387_ia32_struct), + datap); + + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + return copy_regset_from_user( + child, &user_x86_32_view, REGSET_FP, + 0, sizeof(struct user_i387_ia32_struct), datap); + + case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET32_XFP, 0, + sizeof(struct user32_fxsr_struct), + datap); + + case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ + return copy_regset_from_user(child, &user_x86_32_view, + REGSET32_XFP, 0, + sizeof(struct user32_fxsr_struct), + datap); + + case PTRACE_GET_THREAD_AREA: + case PTRACE_SET_THREAD_AREA: + return arch_ptrace(child, request, addr, data); + + default: + return compat_ptrace_request(child, request, addr, data); + } + + return ret; +} +#endif /* CONFIG_IA32_EMULATION */ + +#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, + &user_x86_64_view, + 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, + &user_x86_64_view, + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct), + datap); + + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + return copy_regset_to_user(child, + &user_x86_64_view, + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + return copy_regset_from_user(child, + &user_x86_64_view, + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + + default: + return compat_ptrace_request(child, request, addr, data); + } + + return ret; +} +#endif + +#ifdef CONFIG_COMPAT +long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) +{ +#ifdef CONFIG_X86_X32_ABI + if (!in_ia32_syscall()) + return x32_arch_ptrace(child, request, caddr, cdata); +#endif +#ifdef CONFIG_IA32_EMULATION + return ia32_arch_ptrace(child, request, caddr, cdata); +#else + return 0; +#endif +} +#endif /* CONFIG_COMPAT */ + +#ifdef CONFIG_X86_64 + +static struct user_regset x86_64_regsets[] __ro_after_init = { + [REGSET64_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = sizeof(struct user_regs_struct) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .regset_get = genregs_get, + .set = genregs_set + }, + [REGSET64_FP] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(struct fxregs_state) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .active = regset_xregset_fpregs_active, + .regset_get = xfpregs_get, + .set = xfpregs_set + }, + [REGSET64_XSTATE] = { + .core_note_type = NT_X86_XSTATE, + .size = sizeof(u64), + .align = sizeof(u64), + .active = xstateregs_active, + .regset_get = xstateregs_get, + .set = xstateregs_set + }, + [REGSET64_IOPERM] = { + .core_note_type = NT_386_IOPERM, + .n = IO_BITMAP_LONGS, + .size = sizeof(long), + .align = sizeof(long), + .active = ioperm_active, + .regset_get = ioperm_get + }, +#ifdef CONFIG_X86_USER_SHADOW_STACK + [REGSET64_SSP] = { + .core_note_type = NT_X86_SHSTK, + .n = 1, + .size = sizeof(u64), + .align = sizeof(u64), + .active = ssp_active, + .regset_get = ssp_get, + .set = ssp_set + }, +#endif +}; + +static const struct user_regset_view user_x86_64_view = { + .name = "x86_64", .e_machine = EM_X86_64, + .regsets = x86_64_regsets, .n = ARRAY_SIZE(x86_64_regsets) +}; + +#else /* CONFIG_X86_32 */ + +#define user_regs_struct32 user_regs_struct +#define genregs32_get genregs_get +#define genregs32_set genregs_set + +#endif /* CONFIG_X86_64 */ + +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION +static struct user_regset x86_32_regsets[] __ro_after_init = { + [REGSET32_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = sizeof(struct user_regs_struct32) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = genregs32_get, + .set = genregs32_set + }, + [REGSET32_FP] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .active = regset_fpregs_active, + .regset_get = fpregs_get, + .set = fpregs_set + }, + [REGSET32_XFP] = { + .core_note_type = NT_PRXFPREG, + .n = sizeof(struct fxregs_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .active = regset_xregset_fpregs_active, + .regset_get = xfpregs_get, + .set = xfpregs_set + }, + [REGSET32_XSTATE] = { + .core_note_type = NT_X86_XSTATE, + .size = sizeof(u64), + .align = sizeof(u64), + .active = xstateregs_active, + .regset_get = xstateregs_get, + .set = xstateregs_set + }, + [REGSET32_TLS] = { + .core_note_type = NT_386_TLS, + .n = GDT_ENTRY_TLS_ENTRIES, + .bias = GDT_ENTRY_TLS_MIN, + .size = sizeof(struct user_desc), + .align = sizeof(struct user_desc), + .active = regset_tls_active, + .regset_get = regset_tls_get, + .set = regset_tls_set + }, + [REGSET32_IOPERM] = { + .core_note_type = NT_386_IOPERM, + .n = IO_BITMAP_BYTES / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .active = ioperm_active, + .regset_get = ioperm_get + }, +}; + +static const struct user_regset_view user_x86_32_view = { + .name = "i386", .e_machine = EM_386, + .regsets = x86_32_regsets, .n = ARRAY_SIZE(x86_32_regsets) +}; +#endif + +/* + * This represents bytes 464..511 in the memory layout exported through + * the REGSET_XSTATE interface. + */ +u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; + +void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask) +{ +#ifdef CONFIG_X86_64 + x86_64_regsets[REGSET64_XSTATE].n = size / sizeof(u64); +#endif +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION + x86_32_regsets[REGSET32_XSTATE].n = size / sizeof(u64); +#endif + xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask; +} + +/* + * This is used by the core dump code to decide which regset to dump. The + * core dump code writes out the resulting .e_machine and the corresponding + * regsets. This is suboptimal if the task is messing around with its CS.L + * field, but at worst the core dump will end up missing some information. + * + * Unfortunately, it is also used by the broken PTRACE_GETREGSET and + * PTRACE_SETREGSET APIs. These APIs look at the .regsets field but have + * no way to make sure that the e_machine they use matches the caller's + * expectations. The result is that the data format returned by + * PTRACE_GETREGSET depends on the returned CS field (and even the offset + * of the returned CS field depends on its value!) and the data format + * accepted by PTRACE_SETREGSET is determined by the old CS value. The + * upshot is that it is basically impossible to use these APIs correctly. + * + * The best way to fix it in the long run would probably be to add new + * improved ptrace() APIs to read and write registers reliably, possibly by + * allowing userspace to select the ELF e_machine variant that they expect. + */ +const struct user_regset_view *task_user_regset_view(struct task_struct *task) +{ +#ifdef CONFIG_IA32_EMULATION + if (!user_64bit_mode(task_pt_regs(task))) +#endif +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION + return &user_x86_32_view; +#endif +#ifdef CONFIG_X86_64 + return &user_x86_64_view; +#endif +} + +void send_sigtrap(struct pt_regs *regs, int error_code, int si_code) +{ + struct task_struct *tsk = current; + + tsk->thread.trap_nr = X86_TRAP_DB; + tsk->thread.error_code = error_code; + + /* Send us the fake SIGTRAP */ + force_sig_fault(SIGTRAP, si_code, + user_mode(regs) ? (void __user *)regs->ip : NULL); +} + +void user_single_step_report(struct pt_regs *regs) +{ + send_sigtrap(regs, 0, TRAP_BRKPT); +} |