mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-16 00:46:47 +07:00
192f0f8e9d
Notable changes: - Removal of the NPU DMA code, used by the out-of-tree Nvidia driver, as well as some other functions only used by drivers that haven't (yet?) made it upstream. - A fix for a bug in our handling of hardware watchpoints (eg. perf record -e mem: ...) which could lead to register corruption and kernel crashes. - Enable HAVE_ARCH_HUGE_VMAP, which allows us to use large pages for vmalloc when using the Radix MMU. - A large but incremental rewrite of our exception handling code to use gas macros rather than multiple levels of nested CPP macros. And the usual small fixes, cleanups and improvements. Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Andreas Schwab, Aneesh Kumar K.V, Anju T Sudhakar, Anton Blanchard, Arnd Bergmann, Athira Rajeev, Cédric Le Goater, Christian Lamparter, Christophe Leroy, Christophe Lombard, Christoph Hellwig, Daniel Axtens, Denis Efremov, Enrico Weigelt, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Geliang Tang, Gen Zhang, Greg Kroah-Hartman, Greg Kurz, Gustavo Romero, Krzysztof Kozlowski, Madhavan Srinivasan, Masahiro Yamada, Mathieu Malaterre, Michael Neuling, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Nishad Kamdar, Oliver O'Halloran, Qian Cai, Ravi Bangoria, Sachin Sant, Sam Bobroff, Satheesh Rajendran, Segher Boessenkool, Shaokun Zhang, Shawn Anastasio, Stewart Smith, Suraj Jitindar Singh, Thiago Jung Bauermann, YueHaibing. -----BEGIN PGP SIGNATURE----- iQIcBAABAgAGBQJdKVoLAAoJEFHr6jzI4aWA0kIP/A6shIbbE7H5W2hFrqt/PPPK 3+VrvPKbOFF+W6hcE/RgSZmEnUo0svdNjHUd/eMfFS1vb/uRt2QDdrsHUNNwURQL M2mcLXFwYpnjSjb/XMgDbHpAQxjeGfTdYLonUIejN7Rk8KQUeLyKQ3SBn6kfMc46 DnUUcPcjuRGaETUmVuZZ4e40ZWbJp8PKDrSJOuUrTPXMaK5ciNbZk5mCWXGbYl6G BMQAyv4ld/417rNTjBEP/T2foMJtioAt4W6mtlgdkOTdIEZnFU67nNxDBthNSu2c 95+I+/sML4KOp1R4yhqLSLIDDbc3bg3c99hLGij0d948z3bkSZ8bwnPaUuy70C4v U8rvl/+N6C6H3DgSsPE/Gnkd8DnudqWY8nULc+8p3fXljGwww6/Qgt+6yCUn8BdW WgixkSjKgjDmzTw8trIUNEqORrTVle7cM2hIyIK2Q5T4kWzNQxrLZ/x/3wgoYjUa 1KwIzaRo5JKZ9D3pJnJ5U+knE2/90rJIyfcp0W6ygyJsWKi2GNmq1eN3sKOw0IxH Tg86RENIA/rEMErNOfP45sLteMuTR7of7peCG3yumIOZqsDVYAzerpvtSgip2cvK aG+9HcYlBFOOOF9Dabi8GXsTBLXLfwiyjjLSpA9eXPwW8KObgiNfTZa7ujjTPvis 4mk9oukFTFUpfhsMmI3T =3dBZ -----END PGP SIGNATURE----- Merge tag 'powerpc-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux Pull powerpc updates from Michael Ellerman: "Notable changes: - Removal of the NPU DMA code, used by the out-of-tree Nvidia driver, as well as some other functions only used by drivers that haven't (yet?) made it upstream. - A fix for a bug in our handling of hardware watchpoints (eg. perf record -e mem: ...) which could lead to register corruption and kernel crashes. - Enable HAVE_ARCH_HUGE_VMAP, which allows us to use large pages for vmalloc when using the Radix MMU. - A large but incremental rewrite of our exception handling code to use gas macros rather than multiple levels of nested CPP macros. And the usual small fixes, cleanups and improvements. Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Andreas Schwab, Aneesh Kumar K.V, Anju T Sudhakar, Anton Blanchard, Arnd Bergmann, Athira Rajeev, Cédric Le Goater, Christian Lamparter, Christophe Leroy, Christophe Lombard, Christoph Hellwig, Daniel Axtens, Denis Efremov, Enrico Weigelt, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Geliang Tang, Gen Zhang, Greg Kroah-Hartman, Greg Kurz, Gustavo Romero, Krzysztof Kozlowski, Madhavan Srinivasan, Masahiro Yamada, Mathieu Malaterre, Michael Neuling, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Nishad Kamdar, Oliver O'Halloran, Qian Cai, Ravi Bangoria, Sachin Sant, Sam Bobroff, Satheesh Rajendran, Segher Boessenkool, Shaokun Zhang, Shawn Anastasio, Stewart Smith, Suraj Jitindar Singh, Thiago Jung Bauermann, YueHaibing" * tag 'powerpc-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (163 commits) powerpc/powernv/idle: Fix restore of SPRN_LDBAR for POWER9 stop state. powerpc/eeh: Handle hugepages in ioremap space ocxl: Update for AFU descriptor template version 1.1 powerpc/boot: pass CONFIG options in a simpler and more robust way powerpc/boot: add {get, put}_unaligned_be32 to xz_config.h powerpc/irq: Don't WARN continuously in arch_local_irq_restore() powerpc/module64: Use symbolic instructions names. powerpc/module32: Use symbolic instructions names. powerpc: Move PPC_HA() PPC_HI() and PPC_LO() to ppc-opcode.h powerpc/module64: Fix comment in R_PPC64_ENTRY handling powerpc/boot: Add lzo support for uImage powerpc/boot: Add lzma support for uImage powerpc/boot: don't force gzipped uImage powerpc/8xx: Add microcode patch to move SMC parameter RAM. powerpc/8xx: Use IO accessors in microcode programming. powerpc/8xx: replace #ifdefs by IS_ENABLED() in microcode.c powerpc/8xx: refactor programming of microcode CPM params. powerpc/8xx: refactor printing of microcode patch name. powerpc/8xx: Refactor microcode write powerpc/8xx: refactor writing of CPM microcode arrays ...
369 lines
9.1 KiB
C
369 lines
9.1 KiB
C
// 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>
|
|
#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>
|
|
#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);
|
|
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)
|
|
{
|
|
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 = 8; /* DABR */
|
|
if (dawr_enabled()) {
|
|
length_max = 512 ; /* 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;
|
|
}
|
|
|
|
/*
|
|
* Handle debug exception notifications.
|
|
*/
|
|
int hw_breakpoint_handler(struct die_args *args)
|
|
{
|
|
int rc = NOTIFY_STOP;
|
|
struct perf_event *bp;
|
|
struct pt_regs *regs = args->regs;
|
|
#ifndef CONFIG_PPC_8xx
|
|
int stepped = 1;
|
|
unsigned int instr;
|
|
#endif
|
|
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();
|
|
|
|
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;
|
|
|
|
#ifndef CONFIG_PPC_8xx
|
|
/* Do not emulate user-space instructions, instead single-step them */
|
|
if (user_mode(regs)) {
|
|
current->thread.last_hit_ubp = bp;
|
|
regs->msr |= MSR_SE;
|
|
goto out;
|
|
}
|
|
|
|
stepped = 0;
|
|
instr = 0;
|
|
if (!__get_user_inatomic(instr, (unsigned int *) regs->nip))
|
|
stepped = emulate_step(regs, instr);
|
|
|
|
/*
|
|
* emulate_step() could not execute it. We've failed in reliably
|
|
* handling the hw-breakpoint. Unregister it and throw a warning
|
|
* message to let the user know about it.
|
|
*/
|
|
if (!stepped) {
|
|
WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
|
|
"0x%lx will be disabled.", info->address);
|
|
perf_event_disable_inatomic(bp);
|
|
goto out;
|
|
}
|
|
#endif
|
|
/*
|
|
* 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 */
|
|
}
|