leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
a103950e0d
linux/arch/powerpc/kernel/mce.c
Linus Torvalds d4173023e6 Merge branch 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace 
Pull siginfo cleanups from Eric Biederman:
 "Long ago when 2.4 was just a testing release copy_siginfo_to_user was
  made to copy individual fields to userspace, possibly for efficiency
  and to ensure initialized values were not copied to userspace.

  Unfortunately the design was complex, it's assumptions unstated, and
  humans are fallible and so while it worked much of the time that
  design failed to ensure unitialized memory is not copied to userspace.

  This set of changes is part of a new design to clean up siginfo and
  simplify things, and hopefully make the siginfo handling robust enough
  that a simple inspection of the code can be made to ensure we don't
  copy any unitializied fields to userspace.

  The design is to unify struct siginfo and struct compat_siginfo into a
  single definition that is shared between all architectures so that
  anyone adding to the set of information shared with struct siginfo can
  see the whole picture. Hopefully ensuring all future si_code
  assignments are arch independent.

  The design is to unify copy_siginfo_to_user32 and
  copy_siginfo_from_user32 so that those function are complete and cope
  with all of the different cases documented in signinfo_layout. I don't
  think there was a single implementation of either of those functions
  that was complete and correct before my changes unified them.

  The design is to introduce a series of helpers including
  force_siginfo_fault that take the values that are needed in struct
  siginfo and build the siginfo structure for their callers. Ensuring
  struct siginfo is built correctly.

  The remaining work for 4.17 (unless someone thinks it is post -rc1
  material) is to push usage of those helpers down into the
  architectures so that architecture specific code will not need to deal
  with the fiddly work of intializing struct siginfo, and then when
  struct siginfo is guaranteed to be fully initialized change copy
  siginfo_to_user into a simple wrapper around copy_to_user.

  Further there is work in progress on the issues that have been
  documented requires arch specific knowledge to sort out.

  The changes below fix or at least document all of the issues that have
  been found with siginfo generation. Then proceed to unify struct
  siginfo the 32 bit helpers that copy siginfo to and from userspace,
  and generally clean up anything that is not arch specific with regards
  to siginfo generation.

  It is a lot but with the unification you can of siginfo you can
  already see the code reduction in the kernel"

* 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (45 commits)
  signal/memory-failure: Use force_sig_mceerr and send_sig_mceerr
  mm/memory_failure: Remove unused trapno from memory_failure
  signal/ptrace: Add force_sig_ptrace_errno_trap and use it where needed
  signal/powerpc: Remove unnecessary signal_code parameter of do_send_trap
  signal: Helpers for faults with specialized siginfo layouts
  signal: Add send_sig_fault and force_sig_fault
  signal: Replace memset(info,...) with clear_siginfo for clarity
  signal: Don't use structure initializers for struct siginfo
  signal/arm64: Better isolate the COMPAT_TASK portion of ptrace_hbptriggered
  ptrace: Use copy_siginfo in setsiginfo and getsiginfo
  signal: Unify and correct copy_siginfo_to_user32
  signal: Remove the code to clear siginfo before calling copy_siginfo_from_user32
  signal: Unify and correct copy_siginfo_from_user32
  signal/blackfin: Remove pointless UID16_SIGINFO_COMPAT_NEEDED
  signal/blackfin: Move the blackfin specific si_codes to asm-generic/siginfo.h
  signal/tile: Move the tile specific si_codes to asm-generic/siginfo.h
  signal/frv: Move the frv specific si_codes to asm-generic/siginfo.h
  signal/ia64: Move the ia64 specific si_codes to asm-generic/siginfo.h
  signal/powerpc: Remove redefinition of NSIGTRAP on powerpc
  signal: Move addr_lsb into the _sigfault union for clarity
  ...
2018-01-30 14:18:52 -08:00

539 lines
15 KiB
C
Raw Blame History

/*
* Machine check exception handling.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* Copyright 2013 IBM Corporation
* Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
*/
#undef DEBUG
#define pr_fmt(fmt) "mce: " fmt
#include <linux/hardirq.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/percpu.h>
#include <linux/export.h>
#include <linux/irq_work.h>
#include <asm/machdep.h>
#include <asm/mce.h>
static DEFINE_PER_CPU(int, mce_nest_count);
static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
/* Queue for delayed MCE events. */
static DEFINE_PER_CPU(int, mce_queue_count);
static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue);
/* Queue for delayed MCE UE events. */
static DEFINE_PER_CPU(int, mce_ue_count);
static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT],
mce_ue_event_queue);
static void machine_check_process_queued_event(struct irq_work *work);
void machine_check_ue_event(struct machine_check_event *evt);
static void machine_process_ue_event(struct work_struct *work);
static struct irq_work mce_event_process_work = {
.func = machine_check_process_queued_event,
};
DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
static void mce_set_error_info(struct machine_check_event *mce,
struct mce_error_info *mce_err)
{
mce->error_type = mce_err->error_type;
switch (mce_err->error_type) {
case MCE_ERROR_TYPE_UE:
mce->u.ue_error.ue_error_type = mce_err->u.ue_error_type;
break;
case MCE_ERROR_TYPE_SLB:
mce->u.slb_error.slb_error_type = mce_err->u.slb_error_type;
break;
case MCE_ERROR_TYPE_ERAT:
mce->u.erat_error.erat_error_type = mce_err->u.erat_error_type;
break;
case MCE_ERROR_TYPE_TLB:
mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
break;
case MCE_ERROR_TYPE_USER:
mce->u.user_error.user_error_type = mce_err->u.user_error_type;
break;
case MCE_ERROR_TYPE_RA:
mce->u.ra_error.ra_error_type = mce_err->u.ra_error_type;
break;
case MCE_ERROR_TYPE_LINK:
mce->u.link_error.link_error_type = mce_err->u.link_error_type;
break;
case MCE_ERROR_TYPE_UNKNOWN:
default:
break;
}
}
/*
* Decode and save high level MCE information into per cpu buffer which
* is an array of machine_check_event structure.
*/
void save_mce_event(struct pt_regs *regs, long handled,
struct mce_error_info *mce_err,
uint64_t nip, uint64_t addr, uint64_t phys_addr)
{
int index = __this_cpu_inc_return(mce_nest_count) - 1;
struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
/*
* Return if we don't have enough space to log mce event.
* mce_nest_count may go beyond MAX_MC_EVT but that's ok,
* the check below will stop buffer overrun.
*/
if (index >= MAX_MC_EVT)
return;
/* Populate generic machine check info */
mce->version = MCE_V1;
mce->srr0 = nip;
mce->srr1 = regs->msr;
mce->gpr3 = regs->gpr[3];
mce->in_use = 1;
/* Mark it recovered if we have handled it and MSR(RI=1). */
if (handled && (regs->msr & MSR_RI))
mce->disposition = MCE_DISPOSITION_RECOVERED;
else
mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
mce->initiator = mce_err->initiator;
mce->severity = mce_err->severity;
/*
* Populate the mce error_type and type-specific error_type.
*/
mce_set_error_info(mce, mce_err);
if (!addr)
return;
if (mce->error_type == MCE_ERROR_TYPE_TLB) {
mce->u.tlb_error.effective_address_provided = true;
mce->u.tlb_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_SLB) {
mce->u.slb_error.effective_address_provided = true;
mce->u.slb_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
mce->u.erat_error.effective_address_provided = true;
mce->u.erat_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_USER) {
mce->u.user_error.effective_address_provided = true;
mce->u.user_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_RA) {
mce->u.ra_error.effective_address_provided = true;
mce->u.ra_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_LINK) {
mce->u.link_error.effective_address_provided = true;
mce->u.link_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
mce->u.ue_error.effective_address_provided = true;
mce->u.ue_error.effective_address = addr;
if (phys_addr != ULONG_MAX) {
mce->u.ue_error.physical_address_provided = true;
mce->u.ue_error.physical_address = phys_addr;
machine_check_ue_event(mce);
}
}
return;
}
/*
* get_mce_event:
* mce Pointer to machine_check_event structure to be filled.
* release Flag to indicate whether to free the event slot or not.
* 0 <= do not release the mce event. Caller will invoke
* release_mce_event() once event has been consumed.
* 1 <= release the slot.
*
* return 1 = success
* 0 = failure
*
* get_mce_event() will be called by platform specific machine check
* handle routine and in KVM.
* When we call get_mce_event(), we are still in interrupt context and
* preemption will not be scheduled until ret_from_expect() routine
* is called.
*/
int get_mce_event(struct machine_check_event *mce, bool release)
{
int index = __this_cpu_read(mce_nest_count) - 1;
struct machine_check_event *mc_evt;
int ret = 0;
/* Sanity check */
if (index < 0)
return ret;
/* Check if we have MCE info to process. */
if (index < MAX_MC_EVT) {
mc_evt = this_cpu_ptr(&mce_event[index]);
/* Copy the event structure and release the original */
if (mce)
*mce = *mc_evt;
if (release)
mc_evt->in_use = 0;
ret = 1;
}
/* Decrement the count to free the slot. */
if (release)
__this_cpu_dec(mce_nest_count);
return ret;
}
void release_mce_event(void)
{
get_mce_event(NULL, true);
}
/*
* Queue up the MCE event which then can be handled later.
*/
void machine_check_ue_event(struct machine_check_event *evt)
{
int index;
index = __this_cpu_inc_return(mce_ue_count) - 1;
/* If queue is full, just return for now. */
if (index >= MAX_MC_EVT) {
__this_cpu_dec(mce_ue_count);
return;
}
memcpy(this_cpu_ptr(&mce_ue_event_queue[index]), evt, sizeof(*evt));
/* Queue work to process this event later. */
schedule_work(&mce_ue_event_work);
}
/*
* Queue up the MCE event which then can be handled later.
*/
void machine_check_queue_event(void)
{
int index;
struct machine_check_event evt;
if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
return;
index = __this_cpu_inc_return(mce_queue_count) - 1;
/* If queue is full, just return for now. */
if (index >= MAX_MC_EVT) {
__this_cpu_dec(mce_queue_count);
return;
}
memcpy(this_cpu_ptr(&mce_event_queue[index]), &evt, sizeof(evt));
/* Queue irq work to process this event later. */
irq_work_queue(&mce_event_process_work);
}
/*
* process pending MCE event from the mce event queue. This function will be
* called during syscall exit.
*/
static void machine_process_ue_event(struct work_struct *work)
{
int index;
struct machine_check_event *evt;
while (__this_cpu_read(mce_ue_count) > 0) {
index = __this_cpu_read(mce_ue_count) - 1;
evt = this_cpu_ptr(&mce_ue_event_queue[index]);
#ifdef CONFIG_MEMORY_FAILURE
/*
* This should probably queued elsewhere, but
* oh! well
*/
if (evt->error_type == MCE_ERROR_TYPE_UE) {
if (evt->u.ue_error.physical_address_provided) {
unsigned long pfn;
pfn = evt->u.ue_error.physical_address >>
PAGE_SHIFT;
memory_failure(pfn, 0);
} else
pr_warn("Failed to identify bad address from "
"where the uncorrectable error (UE) "
"was generated\n");
}
#endif
__this_cpu_dec(mce_ue_count);
}
}
/*
* process pending MCE event from the mce event queue. This function will be
* called during syscall exit.
*/
static void machine_check_process_queued_event(struct irq_work *work)
{
int index;
struct machine_check_event *evt;
add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
/*
* For now just print it to console.
* TODO: log this error event to FSP or nvram.
*/
while (__this_cpu_read(mce_queue_count) > 0) {
index = __this_cpu_read(mce_queue_count) - 1;
evt = this_cpu_ptr(&mce_event_queue[index]);
machine_check_print_event_info(evt, false);
__this_cpu_dec(mce_queue_count);
}
}
void machine_check_print_event_info(struct machine_check_event *evt,
bool user_mode)
{
const char *level, *sevstr, *subtype;
static const char *mc_ue_types[] = {
"Indeterminate",
"Instruction fetch",
"Page table walk ifetch",
"Load/Store",
"Page table walk Load/Store",
};
static const char *mc_slb_types[] = {
"Indeterminate",
"Parity",
"Multihit",
};
static const char *mc_erat_types[] = {
"Indeterminate",
"Parity",
"Multihit",
};
static const char *mc_tlb_types[] = {
"Indeterminate",
"Parity",
"Multihit",
};
static const char *mc_user_types[] = {
"Indeterminate",
"tlbie(l) invalid",
};
static const char *mc_ra_types[] = {
"Indeterminate",
"Instruction fetch (bad)",
"Instruction fetch (foreign)",
"Page table walk ifetch (bad)",
"Page table walk ifetch (foreign)",
"Load (bad)",
"Store (bad)",
"Page table walk Load/Store (bad)",
"Page table walk Load/Store (foreign)",
"Load/Store (foreign)",
};
static const char *mc_link_types[] = {
"Indeterminate",
"Instruction fetch (timeout)",
"Page table walk ifetch (timeout)",
"Load (timeout)",
"Store (timeout)",
"Page table walk Load/Store (timeout)",
};
/* Print things out */
if (evt->version != MCE_V1) {
pr_err("Machine Check Exception, Unknown event version %d !\n",
evt->version);
return;
}
switch (evt->severity) {
case MCE_SEV_NO_ERROR:
level = KERN_INFO;
sevstr = "Harmless";
break;
case MCE_SEV_WARNING:
level = KERN_WARNING;
sevstr = "";
break;
case MCE_SEV_ERROR_SYNC:
level = KERN_ERR;
sevstr = "Severe";
break;
case MCE_SEV_FATAL:
default:
level = KERN_ERR;
sevstr = "Fatal";
break;
}
printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
evt->disposition == MCE_DISPOSITION_RECOVERED ?
"Recovered" : "Not recovered");
if (user_mode) {
printk("%s NIP: [%016llx] PID: %d Comm: %s\n", level,
evt->srr0, current->pid, current->comm);
} else {
printk("%s NIP [%016llx]: %pS\n", level, evt->srr0,
(void *)evt->srr0);
}
printk("%s Initiator: %s\n", level,
evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
switch (evt->error_type) {
case MCE_ERROR_TYPE_UE:
subtype = evt->u.ue_error.ue_error_type <
ARRAY_SIZE(mc_ue_types) ?
mc_ue_types[evt->u.ue_error.ue_error_type]
: "Unknown";
printk("%s Error type: UE [%s]\n", level, subtype);
if (evt->u.ue_error.effective_address_provided)
printk("%s Effective address: %016llx\n",
level, evt->u.ue_error.effective_address);
if (evt->u.ue_error.physical_address_provided)
printk("%s Physical address: %016llx\n",
level, evt->u.ue_error.physical_address);
break;
case MCE_ERROR_TYPE_SLB:
subtype = evt->u.slb_error.slb_error_type <
ARRAY_SIZE(mc_slb_types) ?
mc_slb_types[evt->u.slb_error.slb_error_type]
: "Unknown";
printk("%s Error type: SLB [%s]\n", level, subtype);
if (evt->u.slb_error.effective_address_provided)
printk("%s Effective address: %016llx\n",
level, evt->u.slb_error.effective_address);
break;
case MCE_ERROR_TYPE_ERAT:
subtype = evt->u.erat_error.erat_error_type <
ARRAY_SIZE(mc_erat_types) ?
mc_erat_types[evt->u.erat_error.erat_error_type]
: "Unknown";
printk("%s Error type: ERAT [%s]\n", level, subtype);
if (evt->u.erat_error.effective_address_provided)
printk("%s Effective address: %016llx\n",
level, evt->u.erat_error.effective_address);
break;
case MCE_ERROR_TYPE_TLB:
subtype = evt->u.tlb_error.tlb_error_type <
ARRAY_SIZE(mc_tlb_types) ?
mc_tlb_types[evt->u.tlb_error.tlb_error_type]
: "Unknown";
printk("%s Error type: TLB [%s]\n", level, subtype);
if (evt->u.tlb_error.effective_address_provided)
printk("%s Effective address: %016llx\n",
level, evt->u.tlb_error.effective_address);
break;
case MCE_ERROR_TYPE_USER:
subtype = evt->u.user_error.user_error_type <
ARRAY_SIZE(mc_user_types) ?
mc_user_types[evt->u.user_error.user_error_type]
: "Unknown";
printk("%s Error type: User [%s]\n", level, subtype);
if (evt->u.user_error.effective_address_provided)
printk("%s Effective address: %016llx\n",
level, evt->u.user_error.effective_address);
break;
case MCE_ERROR_TYPE_RA:
subtype = evt->u.ra_error.ra_error_type <
ARRAY_SIZE(mc_ra_types) ?
mc_ra_types[evt->u.ra_error.ra_error_type]
: "Unknown";
printk("%s Error type: Real address [%s]\n", level, subtype);
if (evt->u.ra_error.effective_address_provided)
printk("%s Effective address: %016llx\n",
level, evt->u.ra_error.effective_address);
break;
case MCE_ERROR_TYPE_LINK:
subtype = evt->u.link_error.link_error_type <
ARRAY_SIZE(mc_link_types) ?
mc_link_types[evt->u.link_error.link_error_type]
: "Unknown";
printk("%s Error type: Link [%s]\n", level, subtype);
if (evt->u.link_error.effective_address_provided)
printk("%s Effective address: %016llx\n",
level, evt->u.link_error.effective_address);
break;
default:
case MCE_ERROR_TYPE_UNKNOWN:
printk("%s Error type: Unknown\n", level);
break;
}
}
EXPORT_SYMBOL_GPL(machine_check_print_event_info);
/*
* This function is called in real mode. Strictly no printk's please.
*
* regs->nip and regs->msr contains srr0 and ssr1.
*/
long machine_check_early(struct pt_regs *regs)
{
long handled = 0;
__this_cpu_inc(irq_stat.mce_exceptions);
if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
handled = cur_cpu_spec->machine_check_early(regs);
return handled;
}
long hmi_exception_realmode(struct pt_regs *regs)
{
__this_cpu_inc(irq_stat.hmi_exceptions);
#ifdef CONFIG_PPC_BOOK3S_64
/* Workaround for P9 vector CI loads (see p9_hmi_special_emu) */
if (pvr_version_is(PVR_POWER9)) {
unsigned long hmer = mfspr(SPRN_HMER);
/* Do we have the debug bit set */
if (hmer & PPC_BIT(17)) {
hmer &= ~PPC_BIT(17);
mtspr(SPRN_HMER, hmer);
/*
* Now to avoid problems with soft-disable we
* only do the emulation if we are coming from
* user space
*/
if (user_mode(regs))
local_paca->hmi_p9_special_emu = 1;
/*
* Don't bother going to OPAL if that's the
* only relevant bit.
*/
if (!(hmer & mfspr(SPRN_HMEER)))
return local_paca->hmi_p9_special_emu;
}
}
#endif /* CONFIG_PPC_BOOK3S_64 */
wait_for_subcore_guest_exit();
if (ppc_md.hmi_exception_early)
ppc_md.hmi_exception_early(regs);
wait_for_tb_resync();
return 1;
}
Reference in New Issue View Git Blame Copy Permalink