From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/arch/powerpc/kernel/traps.c | 423 ++++++++++++++++++++++++++++++++++------------------
1 files changed, 273 insertions(+), 150 deletions(-)
diff --git a/kernel/arch/powerpc/kernel/traps.c b/kernel/arch/powerpc/kernel/traps.c
index 2379c4b..5e5a244 100644
--- a/kernel/arch/powerpc/kernel/traps.c
+++ b/kernel/arch/powerpc/kernel/traps.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
* Copyright 2007-2010 Freescale Semiconductor, Inc.
- *
- * 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.
*
* Modified by Cort Dougan (cort@cs.nmt.edu)
* and Paul Mackerras (paulus@samba.org)
@@ -43,7 +39,6 @@
#include <linux/kmsg_dump.h>
#include <asm/emulated_ops.h>
-#include <asm/pgtable.h>
#include <linux/uaccess.h>
#include <asm/debugfs.h>
#include <asm/io.h>
@@ -71,6 +66,7 @@
#include <sysdev/fsl_pci.h>
#include <asm/kprobes.h>
#include <asm/stacktrace.h>
+#include <asm/nmi.h>
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -178,7 +174,7 @@
kmsg_dump(KMSG_DUMP_PANIC);
bust_spinlocks(0);
debug_locks_off();
- console_flush_on_panic();
+ console_flush_on_panic(CONSOLE_FLUSH_PENDING);
}
static unsigned long oops_begin(struct pt_regs *regs)
@@ -247,36 +243,34 @@
mdelay(MSEC_PER_SEC);
}
- if (in_interrupt())
- panic("Fatal exception in interrupt");
if (panic_on_oops)
panic("Fatal exception");
- do_exit(signr);
+ make_task_dead(signr);
}
NOKPROBE_SYMBOL(oops_end);
+
+static char *get_mmu_str(void)
+{
+ if (early_radix_enabled())
+ return " MMU=Radix";
+ if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE))
+ return " MMU=Hash";
+ return "";
+}
static int __die(const char *str, struct pt_regs *regs, long err)
{
printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
- if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN))
- printk("LE ");
- else
- printk("BE ");
-
- if (IS_ENABLED(CONFIG_PREEMPT))
- pr_cont("PREEMPT ");
-
- if (IS_ENABLED(CONFIG_SMP))
- pr_cont("SMP NR_CPUS=%d ", NR_CPUS);
-
- if (debug_pagealloc_enabled())
- pr_cont("DEBUG_PAGEALLOC ");
-
- if (IS_ENABLED(CONFIG_NUMA))
- pr_cont("NUMA ");
-
- pr_cont("%s\n", ppc_md.name ? ppc_md.name : "");
+ printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n",
+ IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
+ PAGE_SIZE / 1024, get_mmu_str(),
+ IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
+ IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
+ IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
+ debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
+ IS_ENABLED(CONFIG_NUMA) ? " NUMA" : "",
+ ppc_md.name ? ppc_md.name : "");
if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP)
return 1;
@@ -307,12 +301,9 @@
}
NOKPROBE_SYMBOL(die);
-void user_single_step_siginfo(struct task_struct *tsk,
- struct pt_regs *regs, siginfo_t *info)
+void user_single_step_report(struct pt_regs *regs)
{
- info->si_signo = SIGTRAP;
- info->si_code = TRAP_TRACE;
- info->si_addr = (void __user *)regs->nip;
+ force_sig_fault(SIGTRAP, TRAP_TRACE, (void __user *)regs->nip);
}
static void show_signal_msg(int signr, struct pt_regs *regs, int code,
@@ -341,14 +332,12 @@
show_user_instructions(regs);
}
-void _exception_pkey(int signr, struct pt_regs *regs, int code,
- unsigned long addr, int key)
+static bool exception_common(int signr, struct pt_regs *regs, int code,
+ unsigned long addr)
{
- siginfo_t info;
-
if (!user_mode(regs)) {
die("Exception in kernel mode", regs, signr);
- return;
+ return false;
}
show_signal_msg(signr, regs, code, addr);
@@ -364,29 +353,116 @@
*/
thread_pkey_regs_save(¤t->thread);
- clear_siginfo(&info);
- info.si_signo = signr;
- info.si_code = code;
- info.si_addr = (void __user *) addr;
- info.si_pkey = key;
+ return true;
+}
- force_sig_info(signr, &info, current);
+void _exception_pkey(struct pt_regs *regs, unsigned long addr, int key)
+{
+ if (!exception_common(SIGSEGV, regs, SEGV_PKUERR, addr))
+ return;
+
+ force_sig_pkuerr((void __user *) addr, key);
}
void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
{
- _exception_pkey(signr, regs, code, addr, 0);
+ if (!exception_common(signr, regs, code, addr))
+ return;
+
+ force_sig_fault(signr, code, (void __user *)addr);
+}
+
+/*
+ * The interrupt architecture has a quirk in that the HV interrupts excluding
+ * the NMIs (0x100 and 0x200) do not clear MSR[RI] at entry. The first thing
+ * that an interrupt handler must do is save off a GPR into a scratch register,
+ * and all interrupts on POWERNV (HV=1) use the HSPRG1 register as scratch.
+ * Therefore an NMI can clobber an HV interrupt's live HSPRG1 without noticing
+ * that it is non-reentrant, which leads to random data corruption.
+ *
+ * The solution is for NMI interrupts in HV mode to check if they originated
+ * from these critical HV interrupt regions. If so, then mark them not
+ * recoverable.
+ *
+ * An alternative would be for HV NMIs to use SPRG for scratch to avoid the
+ * HSPRG1 clobber, however this would cause guest SPRG to be clobbered. Linux
+ * guests should always have MSR[RI]=0 when its scratch SPRG is in use, so
+ * that would work. However any other guest OS that may have the SPRG live
+ * and MSR[RI]=1 could encounter silent corruption.
+ *
+ * Builds that do not support KVM could take this second option to increase
+ * the recoverability of NMIs.
+ */
+void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_POWERNV
+ unsigned long kbase = (unsigned long)_stext;
+ unsigned long nip = regs->nip;
+
+ if (!(regs->msr & MSR_RI))
+ return;
+ if (!(regs->msr & MSR_HV))
+ return;
+ if (regs->msr & MSR_PR)
+ return;
+
+ /*
+ * Now test if the interrupt has hit a range that may be using
+ * HSPRG1 without having RI=0 (i.e., an HSRR interrupt). The
+ * problem ranges all run un-relocated. Test real and virt modes
+ * at the same time by droping the high bit of the nip (virt mode
+ * entry points still have the +0x4000 offset).
+ */
+ nip &= ~0xc000000000000000ULL;
+ if ((nip >= 0x500 && nip < 0x600) || (nip >= 0x4500 && nip < 0x4600))
+ goto nonrecoverable;
+ if ((nip >= 0x980 && nip < 0xa00) || (nip >= 0x4980 && nip < 0x4a00))
+ goto nonrecoverable;
+ if ((nip >= 0xe00 && nip < 0xec0) || (nip >= 0x4e00 && nip < 0x4ec0))
+ goto nonrecoverable;
+ if ((nip >= 0xf80 && nip < 0xfa0) || (nip >= 0x4f80 && nip < 0x4fa0))
+ goto nonrecoverable;
+
+ /* Trampoline code runs un-relocated so subtract kbase. */
+ if (nip >= (unsigned long)(start_real_trampolines - kbase) &&
+ nip < (unsigned long)(end_real_trampolines - kbase))
+ goto nonrecoverable;
+ if (nip >= (unsigned long)(start_virt_trampolines - kbase) &&
+ nip < (unsigned long)(end_virt_trampolines - kbase))
+ goto nonrecoverable;
+ return;
+
+nonrecoverable:
+ regs->msr &= ~MSR_RI;
+#endif
}
void system_reset_exception(struct pt_regs *regs)
{
+ unsigned long hsrr0, hsrr1;
+ bool saved_hsrrs = false;
+ u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
+
+ this_cpu_set_ftrace_enabled(0);
+
+ nmi_enter();
+
/*
- * Avoid crashes in case of nested NMI exceptions. Recoverability
- * is determined by RI and in_nmi
+ * System reset can interrupt code where HSRRs are live and MSR[RI]=1.
+ * The system reset interrupt itself may clobber HSRRs (e.g., to call
+ * OPAL), so save them here and restore them before returning.
+ *
+ * Machine checks don't need to save HSRRs, as the real mode handler
+ * is careful to avoid them, and the regular handler is not delivered
+ * as an NMI.
*/
- bool nested = in_nmi();
- if (!nested)
- nmi_enter();
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ hsrr0 = mfspr(SPRN_HSRR0);
+ hsrr1 = mfspr(SPRN_HSRR1);
+ saved_hsrrs = true;
+ }
+
+ hv_nmi_check_nonrecoverable(regs);
__this_cpu_inc(irq_stat.sreset_irqs);
@@ -439,8 +515,14 @@
die("Unrecoverable System Reset", regs, SIGABRT);
}
- if (!nested)
- nmi_exit();
+ if (saved_hsrrs) {
+ mtspr(SPRN_HSRR0, hsrr0);
+ mtspr(SPRN_HSRR1, hsrr1);
+ }
+
+ nmi_exit();
+
+ this_cpu_set_ftrace_enabled(ftrace_enabled);
/* What should we do here? We could issue a shutdown or hard reset. */
}
@@ -450,9 +532,6 @@
* Check if the NIP corresponds to the address of a sync
* instruction for which there is an entry in the exception
* table.
- * Note that the 601 only takes a machine check on TEA
- * (transfer error ack) signal assertion, and does not
- * set any of the top 16 bits of SRR1.
* -- paulus.
*/
static inline int check_io_access(struct pt_regs *regs)
@@ -501,6 +580,8 @@
#define REASON_ILLEGAL (ESR_PIL | ESR_PUO)
#define REASON_PRIVILEGED ESR_PPR
#define REASON_TRAP ESR_PTR
+#define REASON_PREFIXED 0
+#define REASON_BOUNDARY 0
/* single-step stuff */
#define single_stepping(regs) (current->thread.debug.dbcr0 & DBCR0_IC)
@@ -515,11 +596,15 @@
#define REASON_ILLEGAL SRR1_PROGILL
#define REASON_PRIVILEGED SRR1_PROGPRIV
#define REASON_TRAP SRR1_PROGTRAP
+#define REASON_PREFIXED SRR1_PREFIXED
+#define REASON_BOUNDARY SRR1_BOUNDARY
#define single_stepping(regs) ((regs)->msr & MSR_SE)
#define clear_single_step(regs) ((regs)->msr &= ~MSR_SE)
#define clear_br_trace(regs) ((regs)->msr &= ~MSR_BE)
#endif
+
+#define inst_length(reason) (((reason) & REASON_PREFIXED) ? 8 : 4)
#if defined(CONFIG_E500)
int machine_check_e500mc(struct pt_regs *regs)
@@ -539,10 +624,10 @@
printk("Caused by (from MCSR=%lx): ", reason);
if (reason & MCSR_MCP)
- printk("Machine Check Signal\n");
+ pr_cont("Machine Check Signal\n");
if (reason & MCSR_ICPERR) {
- printk("Instruction Cache Parity Error\n");
+ pr_cont("Instruction Cache Parity Error\n");
/*
* This is recoverable by invalidating the i-cache.
@@ -560,7 +645,7 @@
}
if (reason & MCSR_DCPERR_MC) {
- printk("Data Cache Parity Error\n");
+ pr_cont("Data Cache Parity Error\n");
/*
* In write shadow mode we auto-recover from the error, but it
@@ -579,38 +664,38 @@
}
if (reason & MCSR_L2MMU_MHIT) {
- printk("Hit on multiple TLB entries\n");
+ pr_cont("Hit on multiple TLB entries\n");
recoverable = 0;
}
if (reason & MCSR_NMI)
- printk("Non-maskable interrupt\n");
+ pr_cont("Non-maskable interrupt\n");
if (reason & MCSR_IF) {
- printk("Instruction Fetch Error Report\n");
+ pr_cont("Instruction Fetch Error Report\n");
recoverable = 0;
}
if (reason & MCSR_LD) {
- printk("Load Error Report\n");
+ pr_cont("Load Error Report\n");
recoverable = 0;
}
if (reason & MCSR_ST) {
- printk("Store Error Report\n");
+ pr_cont("Store Error Report\n");
recoverable = 0;
}
if (reason & MCSR_LDG) {
- printk("Guarded Load Error Report\n");
+ pr_cont("Guarded Load Error Report\n");
recoverable = 0;
}
if (reason & MCSR_TLBSYNC)
- printk("Simultaneous tlbsync operations\n");
+ pr_cont("Simultaneous tlbsync operations\n");
if (reason & MCSR_BSL2_ERR) {
- printk("Level 2 Cache Error\n");
+ pr_cont("Level 2 Cache Error\n");
recoverable = 0;
}
@@ -620,7 +705,7 @@
addr = mfspr(SPRN_MCAR);
addr |= (u64)mfspr(SPRN_MCARU) << 32;
- printk("Machine Check %s Address: %#llx\n",
+ pr_cont("Machine Check %s Address: %#llx\n",
reason & MCSR_MEA ? "Effective" : "Physical", addr);
}
@@ -644,29 +729,29 @@
printk("Caused by (from MCSR=%lx): ", reason);
if (reason & MCSR_MCP)
- printk("Machine Check Signal\n");
+ pr_cont("Machine Check Signal\n");
if (reason & MCSR_ICPERR)
- printk("Instruction Cache Parity Error\n");
+ pr_cont("Instruction Cache Parity Error\n");
if (reason & MCSR_DCP_PERR)
- printk("Data Cache Push Parity Error\n");
+ pr_cont("Data Cache Push Parity Error\n");
if (reason & MCSR_DCPERR)
- printk("Data Cache Parity Error\n");
+ pr_cont("Data Cache Parity Error\n");
if (reason & MCSR_BUS_IAERR)
- printk("Bus - Instruction Address Error\n");
+ pr_cont("Bus - Instruction Address Error\n");
if (reason & MCSR_BUS_RAERR)
- printk("Bus - Read Address Error\n");
+ pr_cont("Bus - Read Address Error\n");
if (reason & MCSR_BUS_WAERR)
- printk("Bus - Write Address Error\n");
+ pr_cont("Bus - Write Address Error\n");
if (reason & MCSR_BUS_IBERR)
- printk("Bus - Instruction Data Error\n");
+ pr_cont("Bus - Instruction Data Error\n");
if (reason & MCSR_BUS_RBERR)
- printk("Bus - Read Data Bus Error\n");
+ pr_cont("Bus - Read Data Bus Error\n");
if (reason & MCSR_BUS_WBERR)
- printk("Bus - Write Data Bus Error\n");
+ pr_cont("Bus - Write Data Bus Error\n");
if (reason & MCSR_BUS_IPERR)
- printk("Bus - Instruction Parity Error\n");
+ pr_cont("Bus - Instruction Parity Error\n");
if (reason & MCSR_BUS_RPERR)
- printk("Bus - Read Parity Error\n");
+ pr_cont("Bus - Read Parity Error\n");
return 0;
}
@@ -684,19 +769,19 @@
printk("Caused by (from MCSR=%lx): ", reason);
if (reason & MCSR_MCP)
- printk("Machine Check Signal\n");
+ pr_cont("Machine Check Signal\n");
if (reason & MCSR_CP_PERR)
- printk("Cache Push Parity Error\n");
+ pr_cont("Cache Push Parity Error\n");
if (reason & MCSR_CPERR)
- printk("Cache Parity Error\n");
+ pr_cont("Cache Parity Error\n");
if (reason & MCSR_EXCP_ERR)
- printk("ISI, ITLB, or Bus Error on first instruction fetch for an exception handler\n");
+ pr_cont("ISI, ITLB, or Bus Error on first instruction fetch for an exception handler\n");
if (reason & MCSR_BUS_IRERR)
- printk("Bus - Read Bus Error on instruction fetch\n");
+ pr_cont("Bus - Read Bus Error on instruction fetch\n");
if (reason & MCSR_BUS_DRERR)
- printk("Bus - Read Bus Error on data load\n");
+ pr_cont("Bus - Read Bus Error on data load\n");
if (reason & MCSR_BUS_WRERR)
- printk("Bus - Write Bus Error on buffered store or cache line push\n");
+ pr_cont("Bus - Write Bus Error on buffered store or cache line push\n");
return 0;
}
@@ -709,30 +794,29 @@
printk("Caused by (from SRR1=%lx): ", reason);
switch (reason & 0x601F0000) {
case 0x80000:
- printk("Machine check signal\n");
+ pr_cont("Machine check signal\n");
break;
- case 0: /* for 601 */
case 0x40000:
case 0x140000: /* 7450 MSS error and TEA */
- printk("Transfer error ack signal\n");
+ pr_cont("Transfer error ack signal\n");
break;
case 0x20000:
- printk("Data parity error signal\n");
+ pr_cont("Data parity error signal\n");
break;
case 0x10000:
- printk("Address parity error signal\n");
+ pr_cont("Address parity error signal\n");
break;
case 0x20000000:
- printk("L1 Data Cache error\n");
+ pr_cont("L1 Data Cache error\n");
break;
case 0x40000000:
- printk("L1 Instruction Cache error\n");
+ pr_cont("L1 Instruction Cache error\n");
break;
case 0x00100000:
- printk("L2 data cache parity error\n");
+ pr_cont("L2 data cache parity error\n");
break;
default:
- printk("Unknown values in msr\n");
+ pr_cont("Unknown values in msr\n");
}
return 0;
}
@@ -741,13 +825,22 @@
void machine_check_exception(struct pt_regs *regs)
{
int recover = 0;
- bool nested = in_nmi();
- if (!nested)
- nmi_enter();
- /* 64s accounts the mce in machine_check_early when in HVMODE */
- if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !cpu_has_feature(CPU_FTR_HVMODE))
- __this_cpu_inc(irq_stat.mce_exceptions);
+ /*
+ * BOOK3S_64 does not call this handler as a non-maskable interrupt
+ * (it uses its own early real-mode handler to handle the MCE proper
+ * and then raises irq_work to call this handler when interrupts are
+ * enabled).
+ *
+ * This is silly. The BOOK3S_64 should just call a different function
+ * rather than expecting semantics to magically change. Something
+ * like 'non_nmi_machine_check_exception()', perhaps?
+ */
+ const bool nmi = !IS_ENABLED(CONFIG_PPC_BOOK3S_64);
+
+ if (nmi) nmi_enter();
+
+ __this_cpu_inc(irq_stat.mce_exceptions);
add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
@@ -771,8 +864,7 @@
if (check_io_access(regs))
goto bail;
- if (!nested)
- nmi_exit();
+ if (nmi) nmi_exit();
die("Machine check", regs, SIGBUS);
@@ -783,8 +875,7 @@
return;
bail:
- if (!nested)
- nmi_exit();
+ if (nmi) nmi_exit();
}
void SMIException(struct pt_regs *regs)
@@ -845,7 +936,7 @@
addr = (__force const void __user *)ea;
/* Check it */
- if (!access_ok(VERIFY_READ, addr, 16)) {
+ if (!access_ok(addr, 16)) {
pr_devel("HMI vec emu: bad access %i:%s[%d] nip=%016lx"
" instr=%08x addr=%016lx\n",
smp_processor_id(), current->comm, current->pid,
@@ -1442,7 +1533,8 @@
goto bail;
} else {
printk(KERN_EMERG "Unexpected TM Bad Thing exception "
- "at %lx (msr 0x%x)\n", regs->nip, reason);
+ "at %lx (msr 0x%lx) tm_scratch=%llx\n",
+ regs->nip, regs->msr, get_paca()->tm_scratch);
die("Unrecoverable exception", regs, SIGABRT);
}
}
@@ -1512,10 +1604,19 @@
{
enum ctx_state prev_state = exception_enter();
int sig, code, fixed = 0;
+ unsigned long reason;
/* We restore the interrupt state now */
if (!arch_irq_disabled_regs(regs))
local_irq_enable();
+
+ reason = get_reason(regs);
+
+ if (reason & REASON_BOUNDARY) {
+ sig = SIGBUS;
+ code = BUS_ADRALN;
+ goto bad;
+ }
if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
goto bail;
@@ -1525,7 +1626,8 @@
fixed = fix_alignment(regs);
if (fixed == 1) {
- regs->nip += 4; /* skip over emulated instruction */
+ /* skip over emulated instruction */
+ regs->nip += inst_length(reason);
emulate_single_step(regs);
goto bail;
}
@@ -1538,6 +1640,7 @@
sig = SIGBUS;
code = BUS_ADRALN;
}
+bad:
if (user_mode(regs))
_exception(sig, regs, code, regs->dar);
else
@@ -1556,12 +1659,13 @@
panic("kernel stack overflow");
}
-void nonrecoverable_exception(struct pt_regs *regs)
+void stack_overflow_exception(struct pt_regs *regs)
{
- printk(KERN_ERR "Non-recoverable exception at PC=%lx MSR=%lx\n",
- regs->nip, regs->msr);
- debugger(regs);
- die("nonrecoverable exception", regs, SIGKILL);
+ enum ctx_state prev_state = exception_enter();
+
+ die("Kernel stack overflow", regs, SIGSEGV);
+
+ exception_exit(prev_state);
}
void kernel_fp_unavailable_exception(struct pt_regs *regs)
@@ -1638,6 +1742,7 @@
[FSCR_TAR_LG] = "TAR",
[FSCR_MSGP_LG] = "MSGP",
[FSCR_SCV_LG] = "SCV",
+ [FSCR_PREFIX_LG] = "PREFIX",
};
char *facility = "unknown";
u64 value;
@@ -1759,16 +1864,20 @@
* checkpointed FP registers need to be loaded.
*/
tm_reclaim_current(TM_CAUSE_FAC_UNAV);
- /* Reclaim didn't save out any FPRs to transact_fprs. */
+
+ /*
+ * Reclaim initially saved out bogus (lazy) FPRs to ckfp_state, and
+ * then it was overwrite by the thr->fp_state by tm_reclaim_thread().
+ *
+ * At this point, ck{fp,vr}_state contains the exact values we want to
+ * recheckpoint.
+ */
/* Enable FP for the task: */
current->thread.load_fp = 1;
- /* This loads and recheckpoints the FP registers from
- * thread.fpr[]. They will remain in registers after the
- * checkpoint so we don't need to reload them after.
- * If VMX is in use, the VRs now hold checkpointed values,
- * so we don't want to load the VRs from the thread_struct.
+ /*
+ * Recheckpoint all the checkpointed ckpt, ck{fp, vr}_state registers.
*/
tm_recheckpoint(¤t->thread);
}
@@ -1813,11 +1922,40 @@
}
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-void performance_monitor_exception(struct pt_regs *regs)
+static void performance_monitor_exception_nmi(struct pt_regs *regs)
{
+ nmi_enter();
+
__this_cpu_inc(irq_stat.pmu_irqs);
perf_irq(regs);
+
+ nmi_exit();
+}
+
+static void performance_monitor_exception_async(struct pt_regs *regs)
+{
+ irq_enter();
+
+ __this_cpu_inc(irq_stat.pmu_irqs);
+
+ perf_irq(regs);
+
+ irq_exit();
+}
+
+void performance_monitor_exception(struct pt_regs *regs)
+{
+ /*
+ * On 64-bit, if perf interrupts hit in a local_irq_disable
+ * (soft-masked) region, we consider them as NMIs. This is required to
+ * prevent hash faults on user addresses when reading callchains (and
+ * looks better from an irq tracing perspective).
+ */
+ if (IS_ENABLED(CONFIG_PPC64) && unlikely(arch_irq_disabled_regs(regs)))
+ performance_monitor_exception_nmi(regs);
+ else
+ performance_monitor_exception_async(regs);
}
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -1950,14 +2088,6 @@
NOKPROBE_SYMBOL(DebugException);
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
-#if !defined(CONFIG_TAU_INT)
-void TAUException(struct pt_regs *regs)
-{
- printk("TAU trap at PC: %lx, MSR: %lx, vector=%lx %s\n",
- regs->nip, regs->msr, regs->trap, print_tainted());
-}
-#endif /* CONFIG_INT_TAU */
-
#ifdef CONFIG_ALTIVEC
void altivec_assist_exception(struct pt_regs *regs)
{
@@ -2015,6 +2145,10 @@
int code = FPE_FLTUNK;
int err;
+ /* We restore the interrupt state now */
+ if (!arch_irq_disabled_regs(regs))
+ local_irq_enable();
+
flush_spe_to_thread(current);
spefscr = current->thread.spefscr;
@@ -2060,6 +2194,10 @@
extern int speround_handler(struct pt_regs *regs);
int err;
+ /* We restore the interrupt state now */
+ if (!arch_irq_disabled_regs(regs))
+ local_irq_enable();
+
preempt_disable();
if (regs->msr & MSR_SPE)
giveup_spe(current);
@@ -2095,8 +2233,8 @@
*/
void unrecoverable_exception(struct pt_regs *regs)
{
- printk(KERN_EMERG "Unrecoverable exception %lx at %lx\n",
- regs->trap, regs->nip);
+ pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
+ regs->trap, regs->nip, regs->msr);
die("Unrecoverable exception", regs, SIGABRT);
}
NOKPROBE_SYMBOL(unrecoverable_exception);
@@ -2184,35 +2322,20 @@
static int __init ppc_warn_emulated_init(void)
{
- struct dentry *dir, *d;
+ struct dentry *dir;
unsigned int i;
struct ppc_emulated_entry *entries = (void *)&ppc_emulated;
- if (!powerpc_debugfs_root)
- return -ENODEV;
-
dir = debugfs_create_dir("emulated_instructions",
powerpc_debugfs_root);
- if (!dir)
- return -ENOMEM;
- d = debugfs_create_u32("do_warn", 0644, dir,
- &ppc_warn_emulated);
- if (!d)
- goto fail;
+ debugfs_create_u32("do_warn", 0644, dir, &ppc_warn_emulated);
- for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++) {
- d = debugfs_create_u32(entries[i].name, 0644, dir,
- (u32 *)&entries[i].val.counter);
- if (!d)
- goto fail;
- }
+ for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++)
+ debugfs_create_u32(entries[i].name, 0644, dir,
+ (u32 *)&entries[i].val.counter);
return 0;
-
-fail:
- debugfs_remove_recursive(dir);
- return -ENOMEM;
}
device_initcall(ppc_warn_emulated_init);
--
Gitblit v1.6.2