mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-07 18:46:39 +07:00
5a0e3ad6af
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
337 lines
9.0 KiB
C
337 lines
9.0 KiB
C
/* ptrace.c */
|
|
/* By Ross Biro 1/23/92 */
|
|
/* edited by Linus Torvalds */
|
|
/* mangled further by Bob Manson (manson@santafe.edu) */
|
|
/* more mutilation by David Mosberger (davidm@azstarnet.com) */
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/user.h>
|
|
#include <linux/security.h>
|
|
#include <linux/signal.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/system.h>
|
|
#include <asm/fpu.h>
|
|
|
|
#include "proto.h"
|
|
|
|
#define DEBUG DBG_MEM
|
|
#undef DEBUG
|
|
|
|
#ifdef DEBUG
|
|
enum {
|
|
DBG_MEM = (1<<0),
|
|
DBG_BPT = (1<<1),
|
|
DBG_MEM_ALL = (1<<2)
|
|
};
|
|
#define DBG(fac,args) {if ((fac) & DEBUG) printk args;}
|
|
#else
|
|
#define DBG(fac,args)
|
|
#endif
|
|
|
|
#define BREAKINST 0x00000080 /* call_pal bpt */
|
|
|
|
/*
|
|
* does not yet catch signals sent when the child dies.
|
|
* in exit.c or in signal.c.
|
|
*/
|
|
|
|
/*
|
|
* Processes always block with the following stack-layout:
|
|
*
|
|
* +================================+ <---- task + 2*PAGE_SIZE
|
|
* | PALcode saved frame (ps, pc, | ^
|
|
* | gp, a0, a1, a2) | |
|
|
* +================================+ | struct pt_regs
|
|
* | | |
|
|
* | frame generated by SAVE_ALL | |
|
|
* | | v
|
|
* +================================+
|
|
* | | ^
|
|
* | frame saved by do_switch_stack | | struct switch_stack
|
|
* | | v
|
|
* +================================+
|
|
*/
|
|
|
|
/*
|
|
* The following table maps a register index into the stack offset at
|
|
* which the register is saved. Register indices are 0-31 for integer
|
|
* regs, 32-63 for fp regs, and 64 for the pc. Notice that sp and
|
|
* zero have no stack-slot and need to be treated specially (see
|
|
* get_reg/put_reg below).
|
|
*/
|
|
enum {
|
|
REG_R0 = 0, REG_F0 = 32, REG_FPCR = 63, REG_PC = 64
|
|
};
|
|
|
|
#define PT_REG(reg) \
|
|
(PAGE_SIZE*2 - sizeof(struct pt_regs) + offsetof(struct pt_regs, reg))
|
|
|
|
#define SW_REG(reg) \
|
|
(PAGE_SIZE*2 - sizeof(struct pt_regs) - sizeof(struct switch_stack) \
|
|
+ offsetof(struct switch_stack, reg))
|
|
|
|
static int regoff[] = {
|
|
PT_REG( r0), PT_REG( r1), PT_REG( r2), PT_REG( r3),
|
|
PT_REG( r4), PT_REG( r5), PT_REG( r6), PT_REG( r7),
|
|
PT_REG( r8), SW_REG( r9), SW_REG( r10), SW_REG( r11),
|
|
SW_REG( r12), SW_REG( r13), SW_REG( r14), SW_REG( r15),
|
|
PT_REG( r16), PT_REG( r17), PT_REG( r18), PT_REG( r19),
|
|
PT_REG( r20), PT_REG( r21), PT_REG( r22), PT_REG( r23),
|
|
PT_REG( r24), PT_REG( r25), PT_REG( r26), PT_REG( r27),
|
|
PT_REG( r28), PT_REG( gp), -1, -1,
|
|
SW_REG(fp[ 0]), SW_REG(fp[ 1]), SW_REG(fp[ 2]), SW_REG(fp[ 3]),
|
|
SW_REG(fp[ 4]), SW_REG(fp[ 5]), SW_REG(fp[ 6]), SW_REG(fp[ 7]),
|
|
SW_REG(fp[ 8]), SW_REG(fp[ 9]), SW_REG(fp[10]), SW_REG(fp[11]),
|
|
SW_REG(fp[12]), SW_REG(fp[13]), SW_REG(fp[14]), SW_REG(fp[15]),
|
|
SW_REG(fp[16]), SW_REG(fp[17]), SW_REG(fp[18]), SW_REG(fp[19]),
|
|
SW_REG(fp[20]), SW_REG(fp[21]), SW_REG(fp[22]), SW_REG(fp[23]),
|
|
SW_REG(fp[24]), SW_REG(fp[25]), SW_REG(fp[26]), SW_REG(fp[27]),
|
|
SW_REG(fp[28]), SW_REG(fp[29]), SW_REG(fp[30]), SW_REG(fp[31]),
|
|
PT_REG( pc)
|
|
};
|
|
|
|
static unsigned long zero;
|
|
|
|
/*
|
|
* Get address of register REGNO in task TASK.
|
|
*/
|
|
static unsigned long *
|
|
get_reg_addr(struct task_struct * task, unsigned long regno)
|
|
{
|
|
unsigned long *addr;
|
|
|
|
if (regno == 30) {
|
|
addr = &task_thread_info(task)->pcb.usp;
|
|
} else if (regno == 65) {
|
|
addr = &task_thread_info(task)->pcb.unique;
|
|
} else if (regno == 31 || regno > 65) {
|
|
zero = 0;
|
|
addr = &zero;
|
|
} else {
|
|
addr = task_stack_page(task) + regoff[regno];
|
|
}
|
|
return addr;
|
|
}
|
|
|
|
/*
|
|
* Get contents of register REGNO in task TASK.
|
|
*/
|
|
static unsigned long
|
|
get_reg(struct task_struct * task, unsigned long regno)
|
|
{
|
|
/* Special hack for fpcr -- combine hardware and software bits. */
|
|
if (regno == 63) {
|
|
unsigned long fpcr = *get_reg_addr(task, regno);
|
|
unsigned long swcr
|
|
= task_thread_info(task)->ieee_state & IEEE_SW_MASK;
|
|
swcr = swcr_update_status(swcr, fpcr);
|
|
return fpcr | swcr;
|
|
}
|
|
return *get_reg_addr(task, regno);
|
|
}
|
|
|
|
/*
|
|
* Write contents of register REGNO in task TASK.
|
|
*/
|
|
static int
|
|
put_reg(struct task_struct *task, unsigned long regno, unsigned long data)
|
|
{
|
|
if (regno == 63) {
|
|
task_thread_info(task)->ieee_state
|
|
= ((task_thread_info(task)->ieee_state & ~IEEE_SW_MASK)
|
|
| (data & IEEE_SW_MASK));
|
|
data = (data & FPCR_DYN_MASK) | ieee_swcr_to_fpcr(data);
|
|
}
|
|
*get_reg_addr(task, regno) = data;
|
|
return 0;
|
|
}
|
|
|
|
static inline int
|
|
read_int(struct task_struct *task, unsigned long addr, int * data)
|
|
{
|
|
int copied = access_process_vm(task, addr, data, sizeof(int), 0);
|
|
return (copied == sizeof(int)) ? 0 : -EIO;
|
|
}
|
|
|
|
static inline int
|
|
write_int(struct task_struct *task, unsigned long addr, int data)
|
|
{
|
|
int copied = access_process_vm(task, addr, &data, sizeof(int), 1);
|
|
return (copied == sizeof(int)) ? 0 : -EIO;
|
|
}
|
|
|
|
/*
|
|
* Set breakpoint.
|
|
*/
|
|
int
|
|
ptrace_set_bpt(struct task_struct * child)
|
|
{
|
|
int displ, i, res, reg_b, nsaved = 0;
|
|
unsigned int insn, op_code;
|
|
unsigned long pc;
|
|
|
|
pc = get_reg(child, REG_PC);
|
|
res = read_int(child, pc, (int *) &insn);
|
|
if (res < 0)
|
|
return res;
|
|
|
|
op_code = insn >> 26;
|
|
if (op_code >= 0x30) {
|
|
/*
|
|
* It's a branch: instead of trying to figure out
|
|
* whether the branch will be taken or not, we'll put
|
|
* a breakpoint at either location. This is simpler,
|
|
* more reliable, and probably not a whole lot slower
|
|
* than the alternative approach of emulating the
|
|
* branch (emulation can be tricky for fp branches).
|
|
*/
|
|
displ = ((s32)(insn << 11)) >> 9;
|
|
task_thread_info(child)->bpt_addr[nsaved++] = pc + 4;
|
|
if (displ) /* guard against unoptimized code */
|
|
task_thread_info(child)->bpt_addr[nsaved++]
|
|
= pc + 4 + displ;
|
|
DBG(DBG_BPT, ("execing branch\n"));
|
|
} else if (op_code == 0x1a) {
|
|
reg_b = (insn >> 16) & 0x1f;
|
|
task_thread_info(child)->bpt_addr[nsaved++] = get_reg(child, reg_b);
|
|
DBG(DBG_BPT, ("execing jump\n"));
|
|
} else {
|
|
task_thread_info(child)->bpt_addr[nsaved++] = pc + 4;
|
|
DBG(DBG_BPT, ("execing normal insn\n"));
|
|
}
|
|
|
|
/* install breakpoints: */
|
|
for (i = 0; i < nsaved; ++i) {
|
|
res = read_int(child, task_thread_info(child)->bpt_addr[i],
|
|
(int *) &insn);
|
|
if (res < 0)
|
|
return res;
|
|
task_thread_info(child)->bpt_insn[i] = insn;
|
|
DBG(DBG_BPT, (" -> next_pc=%lx\n",
|
|
task_thread_info(child)->bpt_addr[i]));
|
|
res = write_int(child, task_thread_info(child)->bpt_addr[i],
|
|
BREAKINST);
|
|
if (res < 0)
|
|
return res;
|
|
}
|
|
task_thread_info(child)->bpt_nsaved = nsaved;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Ensure no single-step breakpoint is pending. Returns non-zero
|
|
* value if child was being single-stepped.
|
|
*/
|
|
int
|
|
ptrace_cancel_bpt(struct task_struct * child)
|
|
{
|
|
int i, nsaved = task_thread_info(child)->bpt_nsaved;
|
|
|
|
task_thread_info(child)->bpt_nsaved = 0;
|
|
|
|
if (nsaved > 2) {
|
|
printk("ptrace_cancel_bpt: bogus nsaved: %d!\n", nsaved);
|
|
nsaved = 2;
|
|
}
|
|
|
|
for (i = 0; i < nsaved; ++i) {
|
|
write_int(child, task_thread_info(child)->bpt_addr[i],
|
|
task_thread_info(child)->bpt_insn[i]);
|
|
}
|
|
return (nsaved != 0);
|
|
}
|
|
|
|
void user_enable_single_step(struct task_struct *child)
|
|
{
|
|
/* Mark single stepping. */
|
|
task_thread_info(child)->bpt_nsaved = -1;
|
|
}
|
|
|
|
void user_disable_single_step(struct task_struct *child)
|
|
{
|
|
ptrace_cancel_bpt(child);
|
|
}
|
|
|
|
/*
|
|
* 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);
|
|
}
|
|
|
|
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
|
|
{
|
|
unsigned long tmp;
|
|
size_t copied;
|
|
long ret;
|
|
|
|
switch (request) {
|
|
/* When I and D space are separate, these will need to be fixed. */
|
|
case PTRACE_PEEKTEXT: /* read word at location addr. */
|
|
case PTRACE_PEEKDATA:
|
|
copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
|
|
ret = -EIO;
|
|
if (copied != sizeof(tmp))
|
|
break;
|
|
|
|
force_successful_syscall_return();
|
|
ret = tmp;
|
|
break;
|
|
|
|
/* Read register number ADDR. */
|
|
case PTRACE_PEEKUSR:
|
|
force_successful_syscall_return();
|
|
ret = get_reg(child, addr);
|
|
DBG(DBG_MEM, ("peek $%ld->%#lx\n", addr, ret));
|
|
break;
|
|
|
|
/* When I and D space are separate, this will have to be fixed. */
|
|
case PTRACE_POKETEXT: /* write the word at location addr. */
|
|
case PTRACE_POKEDATA:
|
|
ret = generic_ptrace_pokedata(child, addr, data);
|
|
break;
|
|
|
|
case PTRACE_POKEUSR: /* write the specified register */
|
|
DBG(DBG_MEM, ("poke $%ld<-%#lx\n", addr, data));
|
|
ret = put_reg(child, addr, data);
|
|
break;
|
|
default:
|
|
ret = ptrace_request(child, request, addr, data);
|
|
break;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
asmlinkage void
|
|
syscall_trace(void)
|
|
{
|
|
if (!test_thread_flag(TIF_SYSCALL_TRACE))
|
|
return;
|
|
if (!(current->ptrace & PT_PTRACED))
|
|
return;
|
|
/* The 0x80 provides a way for the tracing parent to distinguish
|
|
between a syscall stop and SIGTRAP delivery */
|
|
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
|
|
? 0x80 : 0));
|
|
|
|
/*
|
|
* This isn't the same as continuing with a signal, but it will do
|
|
* for normal use. strace only continues with a signal if the
|
|
* stopping signal is not SIGTRAP. -brl
|
|
*/
|
|
if (current->exit_code) {
|
|
send_sig(current->exit_code, current, 1);
|
|
current->exit_code = 0;
|
|
}
|
|
}
|