linux/arch/powerpc/kernel/hw_breakpoint.c

392 lines
9.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
* using the CPU's debug registers. Derived from
* "arch/x86/kernel/hw_breakpoint.c"
*
* Copyright 2010 IBM Corporation
* Author: K.Prasad <prasad@linux.vnet.ibm.com>
*/
#include <linux/hw_breakpoint.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/percpu.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/smp.h>
powerpc: Add force enable of DAWR on P9 option This adds a flag so that the DAWR can be enabled on P9 via: echo Y > /sys/kernel/debug/powerpc/dawr_enable_dangerous The DAWR was previously force disabled on POWER9 in: 9654153158 powerpc: Disable DAWR in the base POWER9 CPU features Also see Documentation/powerpc/DAWR-POWER9.txt This is a dangerous setting, USE AT YOUR OWN RISK. Some users may not care about a bad user crashing their box (ie. single user/desktop systems) and really want the DAWR. This allows them to force enable DAWR. This flag can also be used to disable DAWR access. Once this is cleared, all DAWR access should be cleared immediately and your machine once again safe from crashing. Userspace may get confused by toggling this. If DAWR is force enabled/disabled between getting the number of breakpoints (via PTRACE_GETHWDBGINFO) and setting the breakpoint, userspace will get an inconsistent view of what's available. Similarly for guests. For the DAWR to be enabled in a KVM guest, the DAWR needs to be force enabled in the host AND the guest. For this reason, this won't work on POWERVM as it doesn't allow the HCALL to work. Writes of 'Y' to the dawr_enable_dangerous file will fail if the hypervisor doesn't support writing the DAWR. To double check the DAWR is working, run this kernel selftest: tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c Any errors/failures/skips mean something is wrong. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-01 14:03:12 +08:00
#include <linux/debugfs.h>
#include <linux/init.h>
#include <asm/hw_breakpoint.h>
#include <asm/processor.h>
#include <asm/sstep.h>
#include <asm/debug.h>
powerpc: Add force enable of DAWR on P9 option This adds a flag so that the DAWR can be enabled on P9 via: echo Y > /sys/kernel/debug/powerpc/dawr_enable_dangerous The DAWR was previously force disabled on POWER9 in: 9654153158 powerpc: Disable DAWR in the base POWER9 CPU features Also see Documentation/powerpc/DAWR-POWER9.txt This is a dangerous setting, USE AT YOUR OWN RISK. Some users may not care about a bad user crashing their box (ie. single user/desktop systems) and really want the DAWR. This allows them to force enable DAWR. This flag can also be used to disable DAWR access. Once this is cleared, all DAWR access should be cleared immediately and your machine once again safe from crashing. Userspace may get confused by toggling this. If DAWR is force enabled/disabled between getting the number of breakpoints (via PTRACE_GETHWDBGINFO) and setting the breakpoint, userspace will get an inconsistent view of what's available. Similarly for guests. For the DAWR to be enabled in a KVM guest, the DAWR needs to be force enabled in the host AND the guest. For this reason, this won't work on POWERVM as it doesn't allow the HCALL to work. Writes of 'Y' to the dawr_enable_dangerous file will fail if the hypervisor doesn't support writing the DAWR. To double check the DAWR is working, run this kernel selftest: tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c Any errors/failures/skips mean something is wrong. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-01 14:03:12 +08:00
#include <asm/debugfs.h>
#include <asm/hvcall.h>
#include <linux/uaccess.h>
/*
* Stores the breakpoints currently in use on each breakpoint address
* register for every cpu
*/
static DEFINE_PER_CPU(struct perf_event *, bp_per_reg);
/*
* Returns total number of data or instruction breakpoints available.
*/
int hw_breakpoint_slots(int type)
{
if (type == TYPE_DATA)
return HBP_NUM;
return 0; /* no instruction breakpoints available */
}
/*
* Install a perf counter breakpoint.
*
* We seek a free debug address register and use it for this
* breakpoint.
*
* Atomic: we hold the counter->ctx->lock and we only handle variables
* and registers local to this cpu.
*/
int arch_install_hw_breakpoint(struct perf_event *bp)
{
struct arch_hw_breakpoint *info = counter_arch_bp(bp);
powerpc: Replace __get_cpu_var uses This still has not been merged and now powerpc is the only arch that does not have this change. Sorry about missing linuxppc-dev before. V2->V2 - Fix up to work against 3.18-rc1 __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to __this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to __this_cpu_inc(y) Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> CC: Paul Mackerras <paulus@samba.org> Signed-off-by: Christoph Lameter <cl@linux.com> [mpe: Fix build errors caused by set/or_softirq_pending(), and rework assignment in __set_breakpoint() to use memcpy().] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-22 04:23:25 +08:00
struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
*slot = bp;
/*
* Do not install DABR values if the instruction must be single-stepped.
* If so, DABR will be populated in single_step_dabr_instruction().
*/
if (current->thread.last_hit_ubp != bp)
__set_breakpoint(info);
return 0;
}
/*
* Uninstall the breakpoint contained in the given counter.
*
* First we search the debug address register it uses and then we disable
* it.
*
* Atomic: we hold the counter->ctx->lock and we only handle variables
* and registers local to this cpu.
*/
void arch_uninstall_hw_breakpoint(struct perf_event *bp)
{
powerpc: Replace __get_cpu_var uses This still has not been merged and now powerpc is the only arch that does not have this change. Sorry about missing linuxppc-dev before. V2->V2 - Fix up to work against 3.18-rc1 __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to __this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to __this_cpu_inc(y) Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> CC: Paul Mackerras <paulus@samba.org> Signed-off-by: Christoph Lameter <cl@linux.com> [mpe: Fix build errors caused by set/or_softirq_pending(), and rework assignment in __set_breakpoint() to use memcpy().] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-22 04:23:25 +08:00
struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
if (*slot != bp) {
WARN_ONCE(1, "Can't find the breakpoint");
return;
}
*slot = NULL;
hw_breakpoint_disable();
}
/*
* Perform cleanup of arch-specific counters during unregistration
* of the perf-event
*/
void arch_unregister_hw_breakpoint(struct perf_event *bp)
{
/*
* If the breakpoint is unregistered between a hw_breakpoint_handler()
* and the single_step_dabr_instruction(), then cleanup the breakpoint
* restoration variables to prevent dangling pointers.
* FIXME, this should not be using bp->ctx at all! Sayeth peterz.
*/
if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L))
bp->ctx->task->thread.last_hit_ubp = NULL;
}
/*
* Check for virtual address in kernel space.
*/
int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
{
return is_kernel_addr(hw->address);
}
int arch_bp_generic_fields(int type, int *gen_bp_type)
{
*gen_bp_type = 0;
if (type & HW_BRK_TYPE_READ)
*gen_bp_type |= HW_BREAKPOINT_R;
if (type & HW_BRK_TYPE_WRITE)
*gen_bp_type |= HW_BREAKPOINT_W;
if (*gen_bp_type == 0)
return -EINVAL;
return 0;
}
/*
* Validate the arch-specific HW Breakpoint register settings
*/
int hw_breakpoint_arch_parse(struct perf_event *bp,
const struct perf_event_attr *attr,
struct arch_hw_breakpoint *hw)
{
int ret = -EINVAL, length_max;
if (!bp)
return ret;
hw->type = HW_BRK_TYPE_TRANSLATE;
if (attr->bp_type & HW_BREAKPOINT_R)
hw->type |= HW_BRK_TYPE_READ;
if (attr->bp_type & HW_BREAKPOINT_W)
hw->type |= HW_BRK_TYPE_WRITE;
if (hw->type == HW_BRK_TYPE_TRANSLATE)
/* must set alteast read or write */
return ret;
if (!attr->exclude_user)
hw->type |= HW_BRK_TYPE_USER;
if (!attr->exclude_kernel)
hw->type |= HW_BRK_TYPE_KERNEL;
if (!attr->exclude_hv)
hw->type |= HW_BRK_TYPE_HYP;
hw->address = attr->bp_addr;
hw->len = attr->bp_len;
/*
* Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8)
* and breakpoint addresses are aligned to nearest double-word
* HW_BREAKPOINT_ALIGN by rounding off to the lower address, the
* 'symbolsize' should satisfy the check below.
*/
if (!ppc_breakpoint_available())
return -ENODEV;
length_max = DABR_MAX_LEN; /* DABR */
powerpc: Add force enable of DAWR on P9 option This adds a flag so that the DAWR can be enabled on P9 via: echo Y > /sys/kernel/debug/powerpc/dawr_enable_dangerous The DAWR was previously force disabled on POWER9 in: 9654153158 powerpc: Disable DAWR in the base POWER9 CPU features Also see Documentation/powerpc/DAWR-POWER9.txt This is a dangerous setting, USE AT YOUR OWN RISK. Some users may not care about a bad user crashing their box (ie. single user/desktop systems) and really want the DAWR. This allows them to force enable DAWR. This flag can also be used to disable DAWR access. Once this is cleared, all DAWR access should be cleared immediately and your machine once again safe from crashing. Userspace may get confused by toggling this. If DAWR is force enabled/disabled between getting the number of breakpoints (via PTRACE_GETHWDBGINFO) and setting the breakpoint, userspace will get an inconsistent view of what's available. Similarly for guests. For the DAWR to be enabled in a KVM guest, the DAWR needs to be force enabled in the host AND the guest. For this reason, this won't work on POWERVM as it doesn't allow the HCALL to work. Writes of 'Y' to the dawr_enable_dangerous file will fail if the hypervisor doesn't support writing the DAWR. To double check the DAWR is working, run this kernel selftest: tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c Any errors/failures/skips mean something is wrong. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-01 14:03:12 +08:00
if (dawr_enabled()) {
length_max = DAWR_MAX_LEN; /* 64 doublewords */
/* DAWR region can't cross 512 boundary */
if ((attr->bp_addr >> 9) !=
((attr->bp_addr + attr->bp_len - 1) >> 9))
return -EINVAL;
}
if (hw->len >
(length_max - (hw->address & HW_BREAKPOINT_ALIGN)))
return -EINVAL;
return 0;
}
/*
* Restores the breakpoint on the debug registers.
* Invoke this function if it is known that the execution context is
* about to change to cause loss of MSR_SE settings.
*/
void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
{
struct arch_hw_breakpoint *info;
if (likely(!tsk->thread.last_hit_ubp))
return;
info = counter_arch_bp(tsk->thread.last_hit_ubp);
regs->msr &= ~MSR_SE;
__set_breakpoint(info);
tsk->thread.last_hit_ubp = NULL;
}
static bool is_larx_stcx_instr(struct pt_regs *regs, unsigned int instr)
{
int ret, type;
struct instruction_op op;
ret = analyse_instr(&op, regs, instr);
type = GETTYPE(op.type);
return (!ret && (type == LARX || type == STCX));
}
/*
* Handle debug exception notifications.
*/
static bool stepping_handler(struct pt_regs *regs, struct perf_event *bp,
unsigned long addr)
{
unsigned int instr = 0;
if (__get_user_inatomic(instr, (unsigned int *)regs->nip))
goto fail;
if (is_larx_stcx_instr(regs, instr)) {
printk_ratelimited("Breakpoint hit on instruction that can't be emulated."
" Breakpoint at 0x%lx will be disabled.\n", addr);
goto disable;
}
/* Do not emulate user-space instructions, instead single-step them */
if (user_mode(regs)) {
current->thread.last_hit_ubp = bp;
regs->msr |= MSR_SE;
return false;
}
if (!emulate_step(regs, instr))
goto fail;
return true;
fail:
/*
* We've failed in reliably handling the hw-breakpoint. Unregister
* it and throw a warning message to let the user know about it.
*/
WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
"0x%lx will be disabled.", addr);
disable:
perf_event_disable_inatomic(bp);
return false;
}
int hw_breakpoint_handler(struct die_args *args)
{
int rc = NOTIFY_STOP;
struct perf_event *bp;
struct pt_regs *regs = args->regs;
struct arch_hw_breakpoint *info;
unsigned long dar = regs->dar;
/* Disable breakpoints during exception handling */
hw_breakpoint_disable();
/*
* The counter may be concurrently released but that can only
* occur from a call_rcu() path. We can then safely fetch
* the breakpoint, use its callback, touch its counter
* while we are in an rcu_read_lock() path.
*/
rcu_read_lock();
powerpc: Replace __get_cpu_var uses This still has not been merged and now powerpc is the only arch that does not have this change. Sorry about missing linuxppc-dev before. V2->V2 - Fix up to work against 3.18-rc1 __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to __this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to __this_cpu_inc(y) Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> CC: Paul Mackerras <paulus@samba.org> Signed-off-by: Christoph Lameter <cl@linux.com> [mpe: Fix build errors caused by set/or_softirq_pending(), and rework assignment in __set_breakpoint() to use memcpy().] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-22 04:23:25 +08:00
bp = __this_cpu_read(bp_per_reg);
if (!bp) {
rc = NOTIFY_DONE;
goto out;
}
info = counter_arch_bp(bp);
/*
* Return early after invoking user-callback function without restoring
* DABR if the breakpoint is from ptrace which always operates in
* one-shot mode. The ptrace-ed process will receive the SIGTRAP signal
* generated in do_dabr().
*/
if (bp->overflow_handler == ptrace_triggered) {
perf_bp_event(bp, regs);
rc = NOTIFY_DONE;
goto out;
}
/*
* Verify if dar lies within the address range occupied by the symbol
* being watched to filter extraneous exceptions. If it doesn't,
* we still need to single-step the instruction, but we don't
* generate an event.
*/
info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
if (!((bp->attr.bp_addr <= dar) &&
(dar - bp->attr.bp_addr < bp->attr.bp_len)))
info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info->address))
goto out;
/*
* As a policy, the callback is invoked in a 'trigger-after-execute'
* fashion
*/
if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
perf_bp_event(bp, regs);
__set_breakpoint(info);
out:
rcu_read_unlock();
return rc;
}
NOKPROBE_SYMBOL(hw_breakpoint_handler);
/*
* Handle single-step exceptions following a DABR hit.
*/
static int single_step_dabr_instruction(struct die_args *args)
{
struct pt_regs *regs = args->regs;
struct perf_event *bp = NULL;
struct arch_hw_breakpoint *info;
bp = current->thread.last_hit_ubp;
/*
* Check if we are single-stepping as a result of a
* previous HW Breakpoint exception
*/
if (!bp)
return NOTIFY_DONE;
info = counter_arch_bp(bp);
/*
* We shall invoke the user-defined callback function in the single
* stepping handler to confirm to 'trigger-after-execute' semantics
*/
if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
perf_bp_event(bp, regs);
__set_breakpoint(info);
current->thread.last_hit_ubp = NULL;
/*
* If the process was being single-stepped by ptrace, let the
* other single-step actions occur (e.g. generate SIGTRAP).
*/
if (test_thread_flag(TIF_SINGLESTEP))
return NOTIFY_DONE;
return NOTIFY_STOP;
}
NOKPROBE_SYMBOL(single_step_dabr_instruction);
/*
* Handle debug exception notifications.
*/
int hw_breakpoint_exceptions_notify(
struct notifier_block *unused, unsigned long val, void *data)
{
int ret = NOTIFY_DONE;
switch (val) {
case DIE_DABR_MATCH:
ret = hw_breakpoint_handler(data);
break;
case DIE_SSTEP:
ret = single_step_dabr_instruction(data);
break;
}
return ret;
}
NOKPROBE_SYMBOL(hw_breakpoint_exceptions_notify);
/*
* Release the user breakpoints used by ptrace
*/
void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
{
struct thread_struct *t = &tsk->thread;
unregister_hw_breakpoint(t->ptrace_bps[0]);
t->ptrace_bps[0] = NULL;
}
void hw_breakpoint_pmu_read(struct perf_event *bp)
{
/* TODO */
}