* [PATCH 2/8] powerpc/64s/powernv: Allow KVM to handle guest machine check details
From: Nicholas Piggin @ 2020-11-28 7:07 UTC (permalink / raw)
To: linuxppc-dev; +Cc: kvm-ppc, Nicholas Piggin, Mahesh Salgaonkar
In-Reply-To: <20201128070728.825934-1-npiggin@gmail.com>
KVM has strategies to perform machine check recovery. If a MCE hits
in a guest, have the low level handler just decode and save the MCE
but not try to recover anything, so KVM can deal with it.
The host does not own SLBs and does not need to report the SLB state
in case of a multi-hit for example, or know about the virtual memory
map of the guest.
UE and memory poisoning of guest pages in the host is one thing that
is possibly not completely robust at the moment, but this too needs
to go via KVM (possibly via the guest and back out to host via hcall)
rather than being handled at a low level in the host handler.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/mce.c | 2 +-
arch/powerpc/kernel/mce_power.c | 96 ++++++++++++++++++---------------
2 files changed, 55 insertions(+), 43 deletions(-)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 63702c0badb9..8afe8d37b983 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -577,7 +577,7 @@ void machine_check_print_event_info(struct machine_check_event *evt,
#ifdef CONFIG_PPC_BOOK3S_64
/* Display faulty slb contents for SLB errors. */
- if (evt->error_type == MCE_ERROR_TYPE_SLB)
+ if (evt->error_type == MCE_ERROR_TYPE_SLB && !in_guest)
slb_dump_contents(local_paca->mce_faulty_slbs);
#endif
}
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index b7e173754a2e..1372ce3f7bdd 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -62,6 +62,20 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
return pfn;
}
+static bool mce_in_guest(void)
+{
+#ifdef CONFIG_KVM_BOOK3S_HANDLER
+ /*
+ * If machine check is hit when in guest context or low level KVM
+ * code, avoid looking up any translations or making any attempts
+ * to recover, just record the event and pass to KVM.
+ */
+ if (get_paca()->kvm_hstate.in_guest)
+ return true;
+#endif
+ return false;
+}
+
/* flush SLBs and reload */
#ifdef CONFIG_PPC_BOOK3S_64
void flush_and_reload_slb(void)
@@ -69,14 +83,6 @@ void flush_and_reload_slb(void)
/* Invalidate all SLBs */
slb_flush_all_realmode();
-#ifdef CONFIG_KVM_BOOK3S_HANDLER
- /*
- * If machine check is hit when in guest or in transition, we will
- * only flush the SLBs and continue.
- */
- if (get_paca()->kvm_hstate.in_guest)
- return;
-#endif
if (early_radix_enabled())
return;
@@ -490,19 +496,21 @@ static int mce_handle_ierror(struct pt_regs *regs,
if ((srr1 & table[i].srr1_mask) != table[i].srr1_value)
continue;
- /* attempt to correct the error */
- switch (table[i].error_type) {
- case MCE_ERROR_TYPE_SLB:
- if (local_paca->in_mce == 1)
- slb_save_contents(local_paca->mce_faulty_slbs);
- handled = mce_flush(MCE_FLUSH_SLB);
- break;
- case MCE_ERROR_TYPE_ERAT:
- handled = mce_flush(MCE_FLUSH_ERAT);
- break;
- case MCE_ERROR_TYPE_TLB:
- handled = mce_flush(MCE_FLUSH_TLB);
- break;
+ if (!mce_in_guest()) {
+ /* attempt to correct the error */
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_SLB:
+ if (local_paca->in_mce == 1)
+ slb_save_contents(local_paca->mce_faulty_slbs);
+ handled = mce_flush(MCE_FLUSH_SLB);
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ handled = mce_flush(MCE_FLUSH_ERAT);
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ handled = mce_flush(MCE_FLUSH_TLB);
+ break;
+ }
}
/* now fill in mce_error_info */
@@ -534,7 +542,7 @@ static int mce_handle_ierror(struct pt_regs *regs,
mce_err->sync_error = table[i].sync_error;
mce_err->severity = table[i].severity;
mce_err->initiator = table[i].initiator;
- if (table[i].nip_valid) {
+ if (table[i].nip_valid && !mce_in_guest()) {
*addr = regs->nip;
if (mce_err->sync_error &&
table[i].error_type == MCE_ERROR_TYPE_UE) {
@@ -577,22 +585,24 @@ static int mce_handle_derror(struct pt_regs *regs,
if (!(dsisr & table[i].dsisr_value))
continue;
- /* attempt to correct the error */
- switch (table[i].error_type) {
- case MCE_ERROR_TYPE_SLB:
- if (local_paca->in_mce == 1)
- slb_save_contents(local_paca->mce_faulty_slbs);
- if (mce_flush(MCE_FLUSH_SLB))
- handled = 1;
- break;
- case MCE_ERROR_TYPE_ERAT:
- if (mce_flush(MCE_FLUSH_ERAT))
- handled = 1;
- break;
- case MCE_ERROR_TYPE_TLB:
- if (mce_flush(MCE_FLUSH_TLB))
- handled = 1;
- break;
+ if (!mce_in_guest()) {
+ /* attempt to correct the error */
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_SLB:
+ if (local_paca->in_mce == 1)
+ slb_save_contents(local_paca->mce_faulty_slbs);
+ if (mce_flush(MCE_FLUSH_SLB))
+ handled = 1;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ if (mce_flush(MCE_FLUSH_ERAT))
+ handled = 1;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ if (mce_flush(MCE_FLUSH_TLB))
+ handled = 1;
+ break;
+ }
}
/*
@@ -634,7 +644,7 @@ static int mce_handle_derror(struct pt_regs *regs,
mce_err->initiator = table[i].initiator;
if (table[i].dar_valid)
*addr = regs->dar;
- else if (mce_err->sync_error &&
+ else if (mce_err->sync_error && !mce_in_guest() &&
table[i].error_type == MCE_ERROR_TYPE_UE) {
/*
* We do a maximum of 4 nested MCE calls, see
@@ -662,7 +672,8 @@ static int mce_handle_derror(struct pt_regs *regs,
static long mce_handle_ue_error(struct pt_regs *regs,
struct mce_error_info *mce_err)
{
- long handled = 0;
+ if (mce_in_guest())
+ return 0;
mce_common_process_ue(regs, mce_err);
if (mce_err->ignore_event)
@@ -677,9 +688,10 @@ static long mce_handle_ue_error(struct pt_regs *regs,
if (ppc_md.mce_check_early_recovery) {
if (ppc_md.mce_check_early_recovery(regs))
- handled = 1;
+ return 1;
}
- return handled;
+
+ return 0;
}
static long mce_handle_error(struct pt_regs *regs,
--
2.23.0
^ permalink raw reply related
* [PATCH 3/8] KVM: PPC: Book3S HV: Don't attempt to recover machine checks for FWNMI enabled guests
From: Nicholas Piggin @ 2020-11-28 7:07 UTC (permalink / raw)
To: linuxppc-dev; +Cc: kvm-ppc, Nicholas Piggin, Mahesh Salgaonkar
In-Reply-To: <20201128070728.825934-1-npiggin@gmail.com>
Guests that can deal with machine checks would actually prefer the
hypervisor not to try recover for them. For example if SLB multi-hits
are recovered by the hypervisor by clearing the SLB then the guest
will not be able to log the contents and debug its programming error.
If guests don't register for FWNMI, they may not be so capable and so
the hypervisor will continue to recover for those.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_ras.c | 23 ++++++++++++++++-------
1 file changed, 16 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index 6028628ea3ac..d4bca93b79f6 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -65,10 +65,9 @@ static void reload_slb(struct kvm_vcpu *vcpu)
* On POWER7, see if we can handle a machine check that occurred inside
* the guest in real mode, without switching to the host partition.
*/
-static void kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
+static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
{
unsigned long srr1 = vcpu->arch.shregs.msr;
- struct machine_check_event mce_evt;
long handled = 1;
if (srr1 & SRR1_MC_LDSTERR) {
@@ -106,6 +105,21 @@ static void kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
handled = 0;
}
+ return handled;
+}
+
+void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
+{
+ struct machine_check_event mce_evt;
+ long handled;
+
+ if (vcpu->kvm->arch.fwnmi_enabled) {
+ /* FWNMI guests handle their own recovery */
+ handled = 0;
+ } else {
+ handled = kvmppc_realmode_mc_power7(vcpu);
+ }
+
/*
* Now get the event and stash it in the vcpu struct so it can
* be handled by the primary thread in virtual mode. We can't
@@ -122,11 +136,6 @@ static void kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
vcpu->arch.mce_evt = mce_evt;
}
-void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
-{
- kvmppc_realmode_mc_power7(vcpu);
-}
-
/* Check if dynamic split is in force and return subcore size accordingly. */
static inline int kvmppc_cur_subcore_size(void)
{
--
2.23.0
^ permalink raw reply related
* [PATCH 4/8] KVM: PPC: Book3S HV: Ratelimit machine check messages coming from guests
From: Nicholas Piggin @ 2020-11-28 7:07 UTC (permalink / raw)
To: linuxppc-dev; +Cc: kvm-ppc, Nicholas Piggin, Mahesh Salgaonkar
In-Reply-To: <20201128070728.825934-1-npiggin@gmail.com>
A number of machine check exceptions are triggerable by the guest.
Ratelimit these to avoid a guest flooding the host console and logs.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e3b1839fc251..c94f9595133d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1328,8 +1328,12 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
r = RESUME_GUEST;
break;
case BOOK3S_INTERRUPT_MACHINE_CHECK:
- /* Print the MCE event to host console. */
- machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
+ /*
+ * Print the MCE event to host console. Ratelimit so the guest
+ * can't flood the host log.
+ */
+ if (printk_ratelimit())
+ machine_check_print_event_info(&vcpu->arch.mce_evt,false, true);
/*
* If the guest can do FWNMI, exit to userspace so it can
@@ -1519,7 +1523,8 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
/* Pass the machine check to the L1 guest */
r = RESUME_HOST;
/* Print the MCE event to host console. */
- machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
+ if (printk_ratelimit())
+ machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
break;
/*
* We get these next two if the guest accesses a page which it thinks
--
2.23.0
^ permalink raw reply related
* [PATCH 5/8] powerpc/64s/powernv: ratelimit harmless HMI error printing
From: Nicholas Piggin @ 2020-11-28 7:07 UTC (permalink / raw)
To: linuxppc-dev; +Cc: kvm-ppc, Nicholas Piggin, Mahesh Salgaonkar
In-Reply-To: <20201128070728.825934-1-npiggin@gmail.com>
Harmless HMI errors can be triggered by guests in some cases, and don't
contain much useful information anyway. Ratelimit these to avoid
flooding the console/logs.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/platforms/powernv/opal-hmi.c | 27 +++++++++++++----------
1 file changed, 15 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c
index 3e1f064a18db..959da6df0227 100644
--- a/arch/powerpc/platforms/powernv/opal-hmi.c
+++ b/arch/powerpc/platforms/powernv/opal-hmi.c
@@ -240,19 +240,22 @@ static void print_hmi_event_info(struct OpalHMIEvent *hmi_evt)
break;
}
- printk("%s%s Hypervisor Maintenance interrupt [%s]\n",
- level, sevstr,
- hmi_evt->disposition == OpalHMI_DISPOSITION_RECOVERED ?
- "Recovered" : "Not recovered");
- error_info = hmi_evt->type < ARRAY_SIZE(hmi_error_types) ?
- hmi_error_types[hmi_evt->type]
- : "Unknown";
- printk("%s Error detail: %s\n", level, error_info);
- printk("%s HMER: %016llx\n", level, be64_to_cpu(hmi_evt->hmer));
- if ((hmi_evt->type == OpalHMI_ERROR_TFAC) ||
- (hmi_evt->type == OpalHMI_ERROR_TFMR_PARITY))
- printk("%s TFMR: %016llx\n", level,
+ if (hmi_evt->severity != OpalHMI_SEV_NO_ERROR || printk_ratelimit()) {
+ printk("%s%s Hypervisor Maintenance interrupt [%s]\n",
+ level, sevstr,
+ hmi_evt->disposition == OpalHMI_DISPOSITION_RECOVERED ?
+ "Recovered" : "Not recovered");
+ error_info = hmi_evt->type < ARRAY_SIZE(hmi_error_types) ?
+ hmi_error_types[hmi_evt->type]
+ : "Unknown";
+ printk("%s Error detail: %s\n", level, error_info);
+ printk("%s HMER: %016llx\n", level,
+ be64_to_cpu(hmi_evt->hmer));
+ if ((hmi_evt->type == OpalHMI_ERROR_TFAC) ||
+ (hmi_evt->type == OpalHMI_ERROR_TFMR_PARITY))
+ printk("%s TFMR: %016llx\n", level,
be64_to_cpu(hmi_evt->tfmr));
+ }
if (hmi_evt->version < OpalHMIEvt_V2)
return;
--
2.23.0
^ permalink raw reply related
* [PATCH 6/8] powerpc/64s/pseries: Add ERAT specific machine check handler
From: Nicholas Piggin @ 2020-11-28 7:07 UTC (permalink / raw)
To: linuxppc-dev; +Cc: kvm-ppc, Nicholas Piggin, Mahesh Salgaonkar
In-Reply-To: <20201128070728.825934-1-npiggin@gmail.com>
Don't treat ERAT MCEs as SLB, don't save the SLB and use a specific
ERAT flush to recover it.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/mce.h | 1 +
arch/powerpc/kernel/mce_power.c | 2 +-
arch/powerpc/platforms/pseries/ras.c | 5 ++++-
3 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 89aa8248a57d..e6c27ae843dc 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -228,6 +228,7 @@ int mce_register_notifier(struct notifier_block *nb);
int mce_unregister_notifier(struct notifier_block *nb);
#ifdef CONFIG_PPC_BOOK3S_64
void flush_and_reload_slb(void);
+void flush_erat(void);
long __machine_check_early_realmode_p7(struct pt_regs *regs);
long __machine_check_early_realmode_p8(struct pt_regs *regs);
long __machine_check_early_realmode_p9(struct pt_regs *regs);
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 1372ce3f7bdd..667104d4c455 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -97,7 +97,7 @@ void flush_and_reload_slb(void)
}
#endif
-static void flush_erat(void)
+void flush_erat(void)
{
#ifdef CONFIG_PPC_BOOK3S_64
if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) {
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index b2b245b25edb..149cec2212e6 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -526,8 +526,11 @@ static int mce_handle_err_realmode(int disposition, u8 error_type)
#ifdef CONFIG_PPC_BOOK3S_64
if (disposition == RTAS_DISP_NOT_RECOVERED) {
switch (error_type) {
- case MC_ERROR_TYPE_SLB:
case MC_ERROR_TYPE_ERAT:
+ flush_erat();
+ disposition = RTAS_DISP_FULLY_RECOVERED;
+ break;
+ case MC_ERROR_TYPE_SLB:
/*
* Store the old slb content in paca before flushing.
* Print this when we go to virtual mode.
--
2.23.0
^ permalink raw reply related
* [PATCH 7/8] powerpc/64s: Remove "Host" from MCE logging
From: Nicholas Piggin @ 2020-11-28 7:07 UTC (permalink / raw)
To: linuxppc-dev; +Cc: kvm-ppc, Nicholas Piggin, Mahesh Salgaonkar
In-Reply-To: <20201128070728.825934-1-npiggin@gmail.com>
"Host" caused machine check is printed when the kernel sees a MCE
hit in this kernel or userspace, and "Guest" if it hit one of its
guests. This is confusing when a guest kernel handles a hypervisor-
delivered MCE, it also prints "Host".
Just remove "Host". "Guest" is adequate to make the distinction.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/mce.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 8afe8d37b983..9f3e133b57b7 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -555,7 +555,7 @@ void machine_check_print_event_info(struct machine_check_event *evt,
}
printk("%sMCE: CPU%d: machine check (%s) %s %s %s %s[%s]\n",
- level, evt->cpu, sevstr, in_guest ? "Guest" : "Host",
+ level, evt->cpu, sevstr, in_guest ? "Guest" : "",
err_type, subtype, dar_str,
evt->disposition == MCE_DISPOSITION_RECOVERED ?
"Recovered" : "Not recovered");
--
2.23.0
^ permalink raw reply related
* [PATCH 8/8] powerpc/64s: tidy machine check SLB logging
From: Nicholas Piggin @ 2020-11-28 7:07 UTC (permalink / raw)
To: linuxppc-dev; +Cc: kvm-ppc, Nicholas Piggin, Mahesh Salgaonkar
In-Reply-To: <20201128070728.825934-1-npiggin@gmail.com>
Since ISA v3.0, SLB no longer uses the slb_cache, and stab_rr is no
longer correlated with SLB allocation. Move those to pre-3.0.
While here, improve some alignments and reduce whitespace.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/mm/book3s64/slb.c | 39 ++++++++++++++++++----------------
1 file changed, 21 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index c30fcbfa0e32..6d720c1c08a4 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -255,7 +255,6 @@ void slb_dump_contents(struct slb_entry *slb_ptr)
return;
pr_err("SLB contents of cpu 0x%x\n", smp_processor_id());
- pr_err("Last SLB entry inserted at slot %d\n", get_paca()->stab_rr);
for (i = 0; i < mmu_slb_size; i++) {
e = slb_ptr->esid;
@@ -265,34 +264,38 @@ void slb_dump_contents(struct slb_entry *slb_ptr)
if (!e && !v)
continue;
- pr_err("%02d %016lx %016lx\n", i, e, v);
+ pr_err("%02d %016lx %016lx %s\n", i, e, v,
+ (e & SLB_ESID_V) ? "VALID" : "NOT VALID");
- if (!(e & SLB_ESID_V)) {
- pr_err("\n");
+ if (!(e & SLB_ESID_V))
continue;
- }
+
llp = v & SLB_VSID_LLP;
if (v & SLB_VSID_B_1T) {
- pr_err(" 1T ESID=%9lx VSID=%13lx LLP:%3lx\n",
+ pr_err(" 1T ESID=%9lx VSID=%13lx LLP:%3lx\n",
GET_ESID_1T(e),
(v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T, llp);
} else {
- pr_err(" 256M ESID=%9lx VSID=%13lx LLP:%3lx\n",
+ pr_err(" 256M ESID=%9lx VSID=%13lx LLP:%3lx\n",
GET_ESID(e),
(v & ~SLB_VSID_B) >> SLB_VSID_SHIFT, llp);
}
}
- pr_err("----------------------------------\n");
-
- /* Dump slb cache entires as well. */
- pr_err("SLB cache ptr value = %d\n", get_paca()->slb_save_cache_ptr);
- pr_err("Valid SLB cache entries:\n");
- n = min_t(int, get_paca()->slb_save_cache_ptr, SLB_CACHE_ENTRIES);
- for (i = 0; i < n; i++)
- pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]);
- pr_err("Rest of SLB cache entries:\n");
- for (i = n; i < SLB_CACHE_ENTRIES; i++)
- pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]);
+
+ if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) {
+ /* RR is not so useful as it's often not used for allocation */
+ pr_err("SLB RR allocator index %d\n", get_paca()->stab_rr);
+
+ /* Dump slb cache entires as well. */
+ pr_err("SLB cache ptr value = %d\n", get_paca()->slb_save_cache_ptr);
+ pr_err("Valid SLB cache entries:\n");
+ n = min_t(int, get_paca()->slb_save_cache_ptr, SLB_CACHE_ENTRIES);
+ for (i = 0; i < n; i++)
+ pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]);
+ pr_err("Rest of SLB cache entries:\n");
+ for (i = n; i < SLB_CACHE_ENTRIES; i++)
+ pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]);
+ }
}
void slb_vmalloc_update(void)
--
2.23.0
^ permalink raw reply related
* Re: [PATCH 1/2] ALSA: ppc: drop if block with always false condition
From: Takashi Iwai @ 2020-11-28 8:48 UTC (permalink / raw)
To: Uwe Kleine-König
Cc: alsa-devel, linux-fbdev, dri-devel, Jaroslav Kysela,
Paul Mackerras, linux-scsi, Alan Stern, Jakub Kicinski,
Arnd Bergmann, Bartlomiej Zolnierkiewicz, James E.J. Bottomley,
linux-block, Jens Axboe, Martin K. Petersen, Geoff Levand, netdev,
linux-usb, Takashi Iwai, Jim Paris, Greg Kroah-Hartman,
linuxppc-dev, David S. Miller
In-Reply-To: <20201126165950.2554997-1-u.kleine-koenig@pengutronix.de>
On Thu, 26 Nov 2020 17:59:49 +0100,
Uwe Kleine-König wrote:
>
> The remove callback is only called for devices that were probed
> successfully before. As the matching probe function cannot complete
> without error if dev->match_id != PS3_MATCH_ID_SOUND, we don't have to
> check this here.
>
> Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Applied this one now. Thanks.
Takashi
^ permalink raw reply
* Re: [PATCH 2/2] powerpc/ps3: make system bus's remove and shutdown callbacks return void
From: Takashi Iwai @ 2020-11-28 8:48 UTC (permalink / raw)
To: Uwe Kleine-König
Cc: alsa-devel, linux-fbdev, dri-devel, Jaroslav Kysela,
Paul Mackerras, linux-scsi, Alan Stern, Jakub Kicinski,
Arnd Bergmann, Bartlomiej Zolnierkiewicz, James E.J. Bottomley,
linux-block, Jens Axboe, Martin K. Petersen, Geoff Levand, netdev,
linux-usb, Takashi Iwai, Jim Paris, Greg Kroah-Hartman,
linuxppc-dev, David S. Miller
In-Reply-To: <20201126165950.2554997-2-u.kleine-koenig@pengutronix.de>
On Thu, 26 Nov 2020 17:59:50 +0100,
Uwe Kleine-König wrote:
>
> The driver core ignores the return value of struct device_driver::remove
> because there is only little that can be done. For the shutdown callback
> it's ps3_system_bus_shutdown() which ignores the return value.
>
> To simplify the quest to make struct device_driver::remove return void,
> let struct ps3_system_bus_driver::remove return void, too. All users
> already unconditionally return 0, this commit makes it obvious that
> returning an error code is a bad idea and ensures future users behave
> accordingly.
>
> Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
For the sound bit:
Acked-by: Takashi Iwai <tiwai@suse.de>
thanks,
Takashi
> ---
> arch/powerpc/include/asm/ps3.h | 4 ++--
> arch/powerpc/platforms/ps3/system-bus.c | 5 ++---
> drivers/block/ps3disk.c | 3 +--
> drivers/block/ps3vram.c | 3 +--
> drivers/char/ps3flash.c | 3 +--
> drivers/net/ethernet/toshiba/ps3_gelic_net.c | 3 +--
> drivers/ps3/ps3-lpm.c | 3 +--
> drivers/ps3/ps3-vuart.c | 10 ++++------
> drivers/scsi/ps3rom.c | 3 +--
> drivers/usb/host/ehci-ps3.c | 4 +---
> drivers/usb/host/ohci-ps3.c | 4 +---
> drivers/video/fbdev/ps3fb.c | 4 +---
> sound/ppc/snd_ps3.c | 3 +--
> 13 files changed, 18 insertions(+), 34 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
> index cb89e4bf55ce..e646c7f218bc 100644
> --- a/arch/powerpc/include/asm/ps3.h
> +++ b/arch/powerpc/include/asm/ps3.h
> @@ -378,8 +378,8 @@ struct ps3_system_bus_driver {
> enum ps3_match_sub_id match_sub_id;
> struct device_driver core;
> int (*probe)(struct ps3_system_bus_device *);
> - int (*remove)(struct ps3_system_bus_device *);
> - int (*shutdown)(struct ps3_system_bus_device *);
> + void (*remove)(struct ps3_system_bus_device *);
> + void (*shutdown)(struct ps3_system_bus_device *);
> /* int (*suspend)(struct ps3_system_bus_device *, pm_message_t); */
> /* int (*resume)(struct ps3_system_bus_device *); */
> };
> diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
> index c62aaa29a9d5..b431f41c6cb5 100644
> --- a/arch/powerpc/platforms/ps3/system-bus.c
> +++ b/arch/powerpc/platforms/ps3/system-bus.c
> @@ -382,7 +382,6 @@ static int ps3_system_bus_probe(struct device *_dev)
>
> static int ps3_system_bus_remove(struct device *_dev)
> {
> - int result = 0;
> struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
> struct ps3_system_bus_driver *drv;
>
> @@ -393,13 +392,13 @@ static int ps3_system_bus_remove(struct device *_dev)
> BUG_ON(!drv);
>
> if (drv->remove)
> - result = drv->remove(dev);
> + drv->remove(dev);
> else
> dev_dbg(&dev->core, "%s:%d %s: no remove method\n",
> __func__, __LINE__, drv->core.name);
>
> pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core));
> - return result;
> + return 0;
> }
>
> static void ps3_system_bus_shutdown(struct device *_dev)
> diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
> index 7b55811c2a81..ba3ece56cbb3 100644
> --- a/drivers/block/ps3disk.c
> +++ b/drivers/block/ps3disk.c
> @@ -507,7 +507,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
> return error;
> }
>
> -static int ps3disk_remove(struct ps3_system_bus_device *_dev)
> +static void ps3disk_remove(struct ps3_system_bus_device *_dev)
> {
> struct ps3_storage_device *dev = to_ps3_storage_device(&_dev->core);
> struct ps3disk_private *priv = ps3_system_bus_get_drvdata(&dev->sbd);
> @@ -526,7 +526,6 @@ static int ps3disk_remove(struct ps3_system_bus_device *_dev)
> kfree(dev->bounce_buf);
> kfree(priv);
> ps3_system_bus_set_drvdata(_dev, NULL);
> - return 0;
> }
>
> static struct ps3_system_bus_driver ps3disk = {
> diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
> index 1088798c8dd0..b71d28372ef3 100644
> --- a/drivers/block/ps3vram.c
> +++ b/drivers/block/ps3vram.c
> @@ -797,7 +797,7 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev)
> return error;
> }
>
> -static int ps3vram_remove(struct ps3_system_bus_device *dev)
> +static void ps3vram_remove(struct ps3_system_bus_device *dev)
> {
> struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
>
> @@ -817,7 +817,6 @@ static int ps3vram_remove(struct ps3_system_bus_device *dev)
> free_pages((unsigned long) priv->xdr_buf, get_order(XDR_BUF_SIZE));
> kfree(priv);
> ps3_system_bus_set_drvdata(dev, NULL);
> - return 0;
> }
>
> static struct ps3_system_bus_driver ps3vram = {
> diff --git a/drivers/char/ps3flash.c b/drivers/char/ps3flash.c
> index 1a07fee33f66..23871cde41fb 100644
> --- a/drivers/char/ps3flash.c
> +++ b/drivers/char/ps3flash.c
> @@ -403,7 +403,7 @@ static int ps3flash_probe(struct ps3_system_bus_device *_dev)
> return error;
> }
>
> -static int ps3flash_remove(struct ps3_system_bus_device *_dev)
> +static void ps3flash_remove(struct ps3_system_bus_device *_dev)
> {
> struct ps3_storage_device *dev = to_ps3_storage_device(&_dev->core);
>
> @@ -413,7 +413,6 @@ static int ps3flash_remove(struct ps3_system_bus_device *_dev)
> kfree(ps3_system_bus_get_drvdata(&dev->sbd));
> ps3_system_bus_set_drvdata(&dev->sbd, NULL);
> ps3flash_dev = NULL;
> - return 0;
> }
>
>
> diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
> index d9a5722f561b..3d1fc8d2ca66 100644
> --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
> +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
> @@ -1791,7 +1791,7 @@ static int ps3_gelic_driver_probe(struct ps3_system_bus_device *dev)
> * ps3_gelic_driver_remove - remove a device from the control of this driver
> */
>
> -static int ps3_gelic_driver_remove(struct ps3_system_bus_device *dev)
> +static void ps3_gelic_driver_remove(struct ps3_system_bus_device *dev)
> {
> struct gelic_card *card = ps3_system_bus_get_drvdata(dev);
> struct net_device *netdev0;
> @@ -1840,7 +1840,6 @@ static int ps3_gelic_driver_remove(struct ps3_system_bus_device *dev)
> ps3_close_hv_device(dev);
>
> pr_debug("%s: done\n", __func__);
> - return 0;
> }
>
> static struct ps3_system_bus_driver ps3_gelic_driver = {
> diff --git a/drivers/ps3/ps3-lpm.c b/drivers/ps3/ps3-lpm.c
> index e54aa2d82f50..65512b6cc6fd 100644
> --- a/drivers/ps3/ps3-lpm.c
> +++ b/drivers/ps3/ps3-lpm.c
> @@ -1196,7 +1196,7 @@ static int ps3_lpm_probe(struct ps3_system_bus_device *dev)
> return 0;
> }
>
> -static int ps3_lpm_remove(struct ps3_system_bus_device *dev)
> +static void ps3_lpm_remove(struct ps3_system_bus_device *dev)
> {
> dev_dbg(&dev->core, " -> %s:%u:\n", __func__, __LINE__);
>
> @@ -1206,7 +1206,6 @@ static int ps3_lpm_remove(struct ps3_system_bus_device *dev)
> lpm_priv = NULL;
>
> dev_info(&dev->core, " <- %s:%u:\n", __func__, __LINE__);
> - return 0;
> }
>
> static struct ps3_system_bus_driver ps3_lpm_driver = {
> diff --git a/drivers/ps3/ps3-vuart.c b/drivers/ps3/ps3-vuart.c
> index 4ed131eaff51..e34ae6a442c7 100644
> --- a/drivers/ps3/ps3-vuart.c
> +++ b/drivers/ps3/ps3-vuart.c
> @@ -1102,7 +1102,7 @@ static int ps3_vuart_cleanup(struct ps3_system_bus_device *dev)
> * device can no longer be used.
> */
>
> -static int ps3_vuart_remove(struct ps3_system_bus_device *dev)
> +static void ps3_vuart_remove(struct ps3_system_bus_device *dev)
> {
> struct ps3_vuart_port_priv *priv = to_port_priv(dev);
> struct ps3_vuart_port_driver *drv;
> @@ -1118,7 +1118,7 @@ static int ps3_vuart_remove(struct ps3_system_bus_device *dev)
> dev_dbg(&dev->core, "%s:%d: no driver bound\n", __func__,
> __LINE__);
> mutex_unlock(&vuart_bus_priv.probe_mutex);
> - return 0;
> + return;
> }
>
> drv = ps3_system_bus_dev_to_vuart_drv(dev);
> @@ -1141,7 +1141,6 @@ static int ps3_vuart_remove(struct ps3_system_bus_device *dev)
>
> dev_dbg(&dev->core, " <- %s:%d\n", __func__, __LINE__);
> mutex_unlock(&vuart_bus_priv.probe_mutex);
> - return 0;
> }
>
> /**
> @@ -1154,7 +1153,7 @@ static int ps3_vuart_remove(struct ps3_system_bus_device *dev)
> * sequence.
> */
>
> -static int ps3_vuart_shutdown(struct ps3_system_bus_device *dev)
> +static void ps3_vuart_shutdown(struct ps3_system_bus_device *dev)
> {
> struct ps3_vuart_port_driver *drv;
>
> @@ -1169,7 +1168,7 @@ static int ps3_vuart_shutdown(struct ps3_system_bus_device *dev)
> dev_dbg(&dev->core, "%s:%d: no driver bound\n", __func__,
> __LINE__);
> mutex_unlock(&vuart_bus_priv.probe_mutex);
> - return 0;
> + return;
> }
>
> drv = ps3_system_bus_dev_to_vuart_drv(dev);
> @@ -1193,7 +1192,6 @@ static int ps3_vuart_shutdown(struct ps3_system_bus_device *dev)
> dev_dbg(&dev->core, " <- %s:%d\n", __func__, __LINE__);
>
> mutex_unlock(&vuart_bus_priv.probe_mutex);
> - return 0;
> }
>
> static int __init ps3_vuart_bus_init(void)
> diff --git a/drivers/scsi/ps3rom.c b/drivers/scsi/ps3rom.c
> index f75c0b5cd587..ccb5771f1cb7 100644
> --- a/drivers/scsi/ps3rom.c
> +++ b/drivers/scsi/ps3rom.c
> @@ -402,7 +402,7 @@ static int ps3rom_probe(struct ps3_system_bus_device *_dev)
> return error;
> }
>
> -static int ps3rom_remove(struct ps3_system_bus_device *_dev)
> +static void ps3rom_remove(struct ps3_system_bus_device *_dev)
> {
> struct ps3_storage_device *dev = to_ps3_storage_device(&_dev->core);
> struct Scsi_Host *host = ps3_system_bus_get_drvdata(&dev->sbd);
> @@ -412,7 +412,6 @@ static int ps3rom_remove(struct ps3_system_bus_device *_dev)
> scsi_host_put(host);
> ps3_system_bus_set_drvdata(&dev->sbd, NULL);
> kfree(dev->bounce_buf);
> - return 0;
> }
>
> static struct ps3_system_bus_driver ps3rom = {
> diff --git a/drivers/usb/host/ehci-ps3.c b/drivers/usb/host/ehci-ps3.c
> index fb52133c3557..98568b046a1a 100644
> --- a/drivers/usb/host/ehci-ps3.c
> +++ b/drivers/usb/host/ehci-ps3.c
> @@ -200,7 +200,7 @@ static int ps3_ehci_probe(struct ps3_system_bus_device *dev)
> return result;
> }
>
> -static int ps3_ehci_remove(struct ps3_system_bus_device *dev)
> +static void ps3_ehci_remove(struct ps3_system_bus_device *dev)
> {
> unsigned int tmp;
> struct usb_hcd *hcd = ps3_system_bus_get_drvdata(dev);
> @@ -227,8 +227,6 @@ static int ps3_ehci_remove(struct ps3_system_bus_device *dev)
>
> ps3_dma_region_free(dev->d_region);
> ps3_close_hv_device(dev);
> -
> - return 0;
> }
>
> static int __init ps3_ehci_driver_register(struct ps3_system_bus_driver *drv)
> diff --git a/drivers/usb/host/ohci-ps3.c b/drivers/usb/host/ohci-ps3.c
> index f77cd6af0ccf..4f5af929c3e4 100644
> --- a/drivers/usb/host/ohci-ps3.c
> +++ b/drivers/usb/host/ohci-ps3.c
> @@ -184,7 +184,7 @@ static int ps3_ohci_probe(struct ps3_system_bus_device *dev)
> return result;
> }
>
> -static int ps3_ohci_remove(struct ps3_system_bus_device *dev)
> +static void ps3_ohci_remove(struct ps3_system_bus_device *dev)
> {
> unsigned int tmp;
> struct usb_hcd *hcd = ps3_system_bus_get_drvdata(dev);
> @@ -212,8 +212,6 @@ static int ps3_ohci_remove(struct ps3_system_bus_device *dev)
>
> ps3_dma_region_free(dev->d_region);
> ps3_close_hv_device(dev);
> -
> - return 0;
> }
>
> static int __init ps3_ohci_driver_register(struct ps3_system_bus_driver *drv)
> diff --git a/drivers/video/fbdev/ps3fb.c b/drivers/video/fbdev/ps3fb.c
> index 203c254f8f6c..2fe08b67eda7 100644
> --- a/drivers/video/fbdev/ps3fb.c
> +++ b/drivers/video/fbdev/ps3fb.c
> @@ -1208,7 +1208,7 @@ static int ps3fb_probe(struct ps3_system_bus_device *dev)
> return retval;
> }
>
> -static int ps3fb_shutdown(struct ps3_system_bus_device *dev)
> +static void ps3fb_shutdown(struct ps3_system_bus_device *dev)
> {
> struct fb_info *info = ps3_system_bus_get_drvdata(dev);
> u64 xdr_lpar = ps3_mm_phys_to_lpar(__pa(ps3fb_videomemory.address));
> @@ -1241,8 +1241,6 @@ static int ps3fb_shutdown(struct ps3_system_bus_device *dev)
> lv1_gpu_memory_free(ps3fb.memory_handle);
> ps3_close_hv_device(dev);
> dev_dbg(&dev->core, " <- %s:%d\n", __func__, __LINE__);
> -
> - return 0;
> }
>
> static struct ps3_system_bus_driver ps3fb_driver = {
> diff --git a/sound/ppc/snd_ps3.c b/sound/ppc/snd_ps3.c
> index 6ab796a5d936..8e44fa5d4dc7 100644
> --- a/sound/ppc/snd_ps3.c
> +++ b/sound/ppc/snd_ps3.c
> @@ -1049,7 +1049,7 @@ static int snd_ps3_driver_probe(struct ps3_system_bus_device *dev)
> }; /* snd_ps3_probe */
>
> /* called when module removal */
> -static int snd_ps3_driver_remove(struct ps3_system_bus_device *dev)
> +static void snd_ps3_driver_remove(struct ps3_system_bus_device *dev)
> {
> int ret;
> pr_info("%s:start id=%d\n", __func__, dev->match_id);
> @@ -1075,7 +1075,6 @@ static int snd_ps3_driver_remove(struct ps3_system_bus_device *dev)
> lv1_gpu_device_unmap(2);
> ps3_close_hv_device(dev);
> pr_info("%s:end id=%d\n", __func__, dev->match_id);
> - return 0;
> } /* snd_ps3_remove */
>
> static struct ps3_system_bus_driver snd_ps3_bus_driver_info = {
> --
> 2.29.2
>
^ permalink raw reply
* Re: [PATCH] ALSA: ppc: remove redundant checks in PS3 driver probe
From: Takashi Iwai @ 2020-11-28 8:49 UTC (permalink / raw)
To: Leonard Goehrs
Cc: alsa-devel, geoff, u.kleine-koenig, tiwai, perex, paulus, kernel,
Geert Uytterhoeven, linuxppc-dev
In-Reply-To: <20201127152259.1470079-1-l.goehrs@pengutronix.de>
On Fri, 27 Nov 2020 16:22:59 +0100,
Leonard Goehrs wrote:
>
> The check for the FW_FEATURE_PS3_LV1 firmware feature is already performed
> in ps3_system_bus_init() before registering the driver. So if the probe
> function is actually used, this feature is already known to be available.
>
> The check for the match id is also superfluous; the condition is always
> true because the bus' match function (ps3_system_bus_match()) only
> considers this driver for devices having:
> dev->match_id == snd_ps3_bus_driver_info.match_id.
>
> Suggested-by: Geert Uytterhoeven <geert@linux-m68k.org>
> Signed-off-by: Leonard Goehrs <l.goehrs@pengutronix.de>
Applied now. Thanks.
Takashi
^ permalink raw reply
* [RFC PATCH] KVM: PPC: Book3S HV: Remove support for running HPT guest on RPT host without mixed mode support
From: Nicholas Piggin @ 2020-11-28 9:52 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
This reverts much of commit c01015091a770 ("KVM: PPC: Book3S HV: Run HPT
guests on POWER9 radix hosts"), which was required to run HPT guests on
RPT hosts on early POWER9 CPUs without support for "mixed mode", which
meant the host could not run with MMU on while guests were running.
This code has some corner case bugs, e.g., when the guest hits a machine
check or HMI the primary locks up waiting for secondaries to switch LPCR
to host, which they never do. This could all be fixed in software, but
most CPUs in production have mixed mode support, and those that don't
are believed to be all in installations that don't use this capability.
So simplify things and remove support.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/kvm_book3s_asm.h | 11 ---
arch/powerpc/kernel/asm-offsets.c | 3 -
arch/powerpc/kvm/book3s_hv.c | 56 +++----------
arch/powerpc/kvm/book3s_hv_builtin.c | 99 +----------------------
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 80 +++++-------------
5 files changed, 32 insertions(+), 217 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 078f4648ea27..b6d31bff5209 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -74,16 +74,6 @@ struct kvm_split_mode {
u8 do_nap;
u8 napped[MAX_SMT_THREADS];
struct kvmppc_vcore *vc[MAX_SUBCORES];
- /* Bits for changing lpcr on P9 */
- unsigned long lpcr_req;
- unsigned long lpidr_req;
- unsigned long host_lpcr;
- u32 do_set;
- u32 do_restore;
- union {
- u32 allphases;
- u8 phase[4];
- } lpcr_sync;
};
/*
@@ -110,7 +100,6 @@ struct kvmppc_host_state {
u8 hwthread_state;
u8 host_ipi;
u8 ptid; /* thread number within subcore when split */
- u8 tid; /* thread number within whole core */
u8 fake_suspend;
struct kvm_vcpu *kvm_vcpu;
struct kvmppc_vcore *kvm_vcore;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c2722ff36e98..21496ea09bf1 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -690,7 +690,6 @@ int main(void)
HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
HSTATE_FIELD(HSTATE_PTID, ptid);
- HSTATE_FIELD(HSTATE_TID, tid);
HSTATE_FIELD(HSTATE_FAKE_SUSPEND, fake_suspend);
HSTATE_FIELD(HSTATE_MMCR0, host_mmcr[0]);
HSTATE_FIELD(HSTATE_MMCR1, host_mmcr[1]);
@@ -720,8 +719,6 @@ int main(void)
OFFSET(KVM_SPLIT_LDBAR, kvm_split_mode, ldbar);
OFFSET(KVM_SPLIT_DO_NAP, kvm_split_mode, do_nap);
OFFSET(KVM_SPLIT_NAPPED, kvm_split_mode, napped);
- OFFSET(KVM_SPLIT_DO_SET, kvm_split_mode, do_set);
- OFFSET(KVM_SPLIT_DO_RESTORE, kvm_split_mode, do_restore);
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c94f9595133d..86b78f8e3dde 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -134,7 +134,7 @@ static inline bool nesting_enabled(struct kvm *kvm)
}
/* If set, the threads on each CPU core have to be in the same MMU mode */
-static bool no_mixing_hpt_and_radix;
+static bool no_mixing_hpt_and_radix __read_mostly;
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
@@ -2855,11 +2855,6 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
if (one_vm_per_core && vc->kvm != cip->vc[0]->kvm)
return false;
- /* Some POWER9 chips require all threads to be in the same MMU mode */
- if (no_mixing_hpt_and_radix &&
- kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm))
- return false;
-
if (n_threads < cip->max_subcore_threads)
n_threads = cip->max_subcore_threads;
if (!subcore_config_ok(cip->n_subcores + 1, n_threads))
@@ -2898,6 +2893,9 @@ static void prepare_threads(struct kvmppc_vcore *vc)
for_each_runnable_thread(i, vcpu, vc) {
if (signal_pending(vcpu->arch.run_task))
vcpu->arch.ret = -EINTR;
+ else if (no_mixing_hpt_and_radix &&
+ kvm_is_radix(vc->kvm) != radix_enabled())
+ vcpu->arch.ret = -EINVAL;
else if (vcpu->arch.vpa.update_pending ||
vcpu->arch.slb_shadow.update_pending ||
vcpu->arch.dtl.update_pending)
@@ -3103,7 +3101,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
int controlled_threads;
int trap;
bool is_power8;
- bool hpt_on_radix;
/*
* Remove from the list any threads that have a signal pending
@@ -3136,11 +3133,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
* this is a HPT guest on a radix host machine where the
* CPU threads may not be in different MMU modes.
*/
- hpt_on_radix = no_mixing_hpt_and_radix && radix_enabled() &&
- !kvm_is_radix(vc->kvm);
- if (((controlled_threads > 1) &&
- ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) ||
- (hpt_on_radix && vc->kvm->arch.threads_indep)) {
+ if ((controlled_threads > 1) &&
+ ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
for_each_runnable_thread(i, vcpu, vc) {
vcpu->arch.ret = -EBUSY;
kvmppc_remove_runnable(vc, vcpu);
@@ -3208,7 +3202,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S)
&& !cpu_has_feature(CPU_FTR_ARCH_300);
- if (split > 1 || hpt_on_radix) {
+ if (split > 1) {
sip = &split_info;
memset(&split_info, 0, sizeof(split_info));
for (sub = 0; sub < core_info.n_subcores; ++sub)
@@ -3230,13 +3224,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
split_info.subcore_size = subcore_size;
} else {
split_info.subcore_size = 1;
- if (hpt_on_radix) {
- /* Use the split_info for LPCR/LPIDR changes */
- split_info.lpcr_req = vc->lpcr;
- split_info.lpidr_req = vc->kvm->arch.lpid;
- split_info.host_lpcr = vc->kvm->arch.host_lpcr;
- split_info.do_set = 1;
- }
}
/* order writes to split_info before kvm_split_mode pointer */
@@ -3246,7 +3233,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
for (thr = 0; thr < controlled_threads; ++thr) {
struct paca_struct *paca = paca_ptrs[pcpu + thr];
- paca->kvm_hstate.tid = thr;
paca->kvm_hstate.napping = 0;
paca->kvm_hstate.kvm_split_mode = sip;
}
@@ -3320,10 +3306,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
* When doing micro-threading, poke the inactive threads as well.
* This gets them to the nap instruction after kvm_do_nap,
* which reduces the time taken to unsplit later.
- * For POWER9 HPT guest on radix host, we need all the secondary
- * threads woken up so they can do the LPCR/LPIDR change.
*/
- if (cmd_bit || hpt_on_radix) {
+ if (cmd_bit) {
split_info.do_nap = 1; /* ask secondaries to nap when done */
for (thr = 1; thr < threads_per_subcore; ++thr)
if (!(active & (1 << thr)))
@@ -3384,19 +3368,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
cpu_relax();
++loops;
}
- } else if (hpt_on_radix) {
- /* Wait for all threads to have seen final sync */
- for (thr = 1; thr < controlled_threads; ++thr) {
- struct paca_struct *paca = paca_ptrs[pcpu + thr];
-
- while (paca->kvm_hstate.kvm_split_mode) {
- HMT_low();
- barrier();
- }
- HMT_medium();
- }
+ split_info.do_nap = 0;
}
- split_info.do_nap = 0;
kvmppc_set_host_core(pcpu);
@@ -4166,7 +4139,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
kvmppc_clear_host_core(pcpu);
- local_paca->kvm_hstate.tid = 0;
local_paca->kvm_hstate.napping = 0;
local_paca->kvm_hstate.kvm_split_mode = NULL;
kvmppc_start_thread(vcpu, vc);
@@ -4351,15 +4323,11 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
do {
/*
- * The early POWER9 chips that can't mix radix and HPT threads
- * on the same core also need the workaround for the problem
- * where the TLB would prefetch entries in the guest exit path
- * for radix guests using the guest PIDR value and LPID 0.
- * The workaround is in the old path (kvmppc_run_vcpu())
- * but not the new path (kvmhv_run_single_vcpu()).
+ * The TLB prefetch bug fixup is only in the kvmppc_run_vcpu
+ * path, which also handles hash and dependent threads mode.
*/
if (kvm->arch.threads_indep && kvm_is_radix(kvm) &&
- !no_mixing_hpt_and_radix)
+ !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
vcpu->arch.vcore->lpcr);
else
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8f58dd20b362..f3d3183249fe 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -277,8 +277,7 @@ void kvmhv_commence_exit(int trap)
struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
int ptid = local_paca->kvm_hstate.ptid;
struct kvm_split_mode *sip = local_paca->kvm_hstate.kvm_split_mode;
- int me, ee, i, t;
- int cpu0;
+ int me, ee, i;
/* Set our bit in the threads-exiting-guest map in the 0xff00
bits of vcore->entry_exit_map */
@@ -320,22 +319,6 @@ void kvmhv_commence_exit(int trap)
if ((ee >> 8) == 0)
kvmhv_interrupt_vcore(vc, ee);
}
-
- /*
- * On POWER9 when running a HPT guest on a radix host (sip != NULL),
- * we have to interrupt inactive CPU threads to get them to
- * restore the host LPCR value.
- */
- if (sip->lpcr_req) {
- if (cmpxchg(&sip->do_restore, 0, 1) == 0) {
- vc = local_paca->kvm_hstate.kvm_vcore;
- cpu0 = vc->pcpu + ptid - local_paca->kvm_hstate.tid;
- for (t = 1; t < threads_per_core; ++t) {
- if (sip->napped[t])
- kvmhv_rm_send_ipi(cpu0 + t);
- }
- }
- }
}
struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv;
@@ -667,86 +650,6 @@ void kvmppc_bad_interrupt(struct pt_regs *regs)
panic("Bad KVM trap");
}
-/*
- * Functions used to switch LPCR HR and UPRT bits on all threads
- * when entering and exiting HPT guests on a radix host.
- */
-
-#define PHASE_REALMODE 1 /* in real mode */
-#define PHASE_SET_LPCR 2 /* have set LPCR */
-#define PHASE_OUT_OF_GUEST 4 /* have finished executing in guest */
-#define PHASE_RESET_LPCR 8 /* have reset LPCR to host value */
-
-#define ALL(p) (((p) << 24) | ((p) << 16) | ((p) << 8) | (p))
-
-static void wait_for_sync(struct kvm_split_mode *sip, int phase)
-{
- int thr = local_paca->kvm_hstate.tid;
-
- sip->lpcr_sync.phase[thr] |= phase;
- phase = ALL(phase);
- while ((sip->lpcr_sync.allphases & phase) != phase) {
- HMT_low();
- barrier();
- }
- HMT_medium();
-}
-
-void kvmhv_p9_set_lpcr(struct kvm_split_mode *sip)
-{
- unsigned long rb, set;
-
- /* wait for every other thread to get to real mode */
- wait_for_sync(sip, PHASE_REALMODE);
-
- /* Set LPCR and LPIDR */
- mtspr(SPRN_LPCR, sip->lpcr_req);
- mtspr(SPRN_LPID, sip->lpidr_req);
- isync();
-
- /* Invalidate the TLB on thread 0 */
- if (local_paca->kvm_hstate.tid == 0) {
- sip->do_set = 0;
- asm volatile("ptesync" : : : "memory");
- for (set = 0; set < POWER9_TLB_SETS_RADIX; ++set) {
- rb = TLBIEL_INVAL_SET_LPID +
- (set << TLBIEL_INVAL_SET_SHIFT);
- asm volatile(PPC_TLBIEL(%0, %1, 0, 0, 0) : :
- "r" (rb), "r" (0));
- }
- asm volatile("ptesync" : : : "memory");
- }
-
- /* indicate that we have done so and wait for others */
- wait_for_sync(sip, PHASE_SET_LPCR);
- /* order read of sip->lpcr_sync.allphases vs. sip->do_set */
- smp_rmb();
-}
-
-/*
- * Called when a thread that has been in the guest needs
- * to reload the host LPCR value - but only on POWER9 when
- * running a HPT guest on a radix host.
- */
-void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip)
-{
- /* we're out of the guest... */
- wait_for_sync(sip, PHASE_OUT_OF_GUEST);
-
- mtspr(SPRN_LPID, 0);
- mtspr(SPRN_LPCR, sip->host_lpcr);
- isync();
-
- if (local_paca->kvm_hstate.tid == 0) {
- sip->do_restore = 0;
- smp_wmb(); /* order store of do_restore vs. phase */
- }
-
- wait_for_sync(sip, PHASE_RESET_LPCR);
- smp_mb();
- local_paca->kvm_hstate.kvm_split_mode = NULL;
-}
-
static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
{
vcpu->arch.ceded = 0;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index cd9995ee8441..d5a9b57ec129 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -85,19 +85,6 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline)
RFI_TO_KERNEL
kvmppc_call_hv_entry:
-BEGIN_FTR_SECTION
- /* On P9, do LPCR setting, if necessary */
- ld r3, HSTATE_SPLIT_MODE(r13)
- cmpdi r3, 0
- beq 46f
- lwz r4, KVM_SPLIT_DO_SET(r3)
- cmpwi r4, 0
- beq 46f
- bl kvmhv_p9_set_lpcr
- nop
-46:
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
ld r4, HSTATE_KVM_VCPU(r13)
bl kvmppc_hv_entry
@@ -361,11 +348,11 @@ kvm_secondary_got_guest:
LOAD_REG_ADDR(r6, decrementer_max)
ld r6, 0(r6)
mtspr SPRN_HDEC, r6
+BEGIN_FTR_SECTION
/* and set per-LPAR registers, if doing dynamic micro-threading */
ld r6, HSTATE_SPLIT_MODE(r13)
cmpdi r6, 0
beq 63f
-BEGIN_FTR_SECTION
ld r0, KVM_SPLIT_RPR(r6)
mtspr SPRN_RPR, r0
ld r0, KVM_SPLIT_PMMAR(r6)
@@ -373,16 +360,7 @@ BEGIN_FTR_SECTION
ld r0, KVM_SPLIT_LDBAR(r6)
mtspr SPRN_LDBAR, r0
isync
-FTR_SECTION_ELSE
- /* On P9 we use the split_info for coordinating LPCR changes */
- lwz r4, KVM_SPLIT_DO_SET(r6)
- cmpwi r4, 0
- beq 1f
- mr r3, r6
- bl kvmhv_p9_set_lpcr
- nop
-1:
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
63:
/* Order load of vcpu after load of vcore */
lwsync
@@ -452,19 +430,15 @@ kvm_no_guest:
mtcr r5
blr
-53: HMT_LOW
+53:
+BEGIN_FTR_SECTION
+ HMT_LOW
ld r5, HSTATE_KVM_VCORE(r13)
cmpdi r5, 0
bne 60f
ld r3, HSTATE_SPLIT_MODE(r13)
cmpdi r3, 0
beq kvm_no_guest
- lwz r0, KVM_SPLIT_DO_SET(r3)
- cmpwi r0, 0
- bne kvmhv_do_set
- lwz r0, KVM_SPLIT_DO_RESTORE(r3)
- cmpwi r0, 0
- bne kvmhv_do_restore
lbz r0, KVM_SPLIT_DO_NAP(r3)
cmpwi r0, 0
beq kvm_no_guest
@@ -472,24 +446,19 @@ kvm_no_guest:
b kvm_unsplit_nap
60: HMT_MEDIUM
b kvm_secondary_got_guest
+FTR_SECTION_ELSE
+ HMT_LOW
+ ld r5, HSTATE_KVM_VCORE(r13)
+ cmpdi r5, 0
+ beq kvm_no_guest
+ HMT_MEDIUM
+ b kvm_secondary_got_guest
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
54: li r0, KVM_HWTHREAD_IN_KVM
stb r0, HSTATE_HWTHREAD_STATE(r13)
b kvm_no_guest
-kvmhv_do_set:
- /* Set LPCR, LPIDR etc. on P9 */
- HMT_MEDIUM
- bl kvmhv_p9_set_lpcr
- nop
- b kvm_no_guest
-
-kvmhv_do_restore:
- HMT_MEDIUM
- bl kvmhv_p9_restore_lpcr
- nop
- b kvm_no_guest
-
/*
* Here the primary thread is trying to return the core to
* whole-core mode, so we need to nap.
@@ -527,7 +496,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
/* Set kvm_split_mode.napped[tid] = 1 */
ld r3, HSTATE_SPLIT_MODE(r13)
li r0, 1
- lbz r4, HSTATE_TID(r13)
+ lhz r4, PACAPACAINDEX(r13)
+ clrldi r4, r4, 61 /* micro-threading => P8 => 8 threads/core */
addi r4, r4, KVM_SPLIT_NAPPED
stbx r0, r3, r4
/* Check the do_nap flag again after setting napped[] */
@@ -1938,24 +1908,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
19: lis r8,0x7fff /* MAX_INT@h */
mtspr SPRN_HDEC,r8
-16:
-BEGIN_FTR_SECTION
- /* On POWER9 with HPT-on-radix we need to wait for all other threads */
- ld r3, HSTATE_SPLIT_MODE(r13)
- cmpdi r3, 0
- beq 47f
- lwz r8, KVM_SPLIT_DO_RESTORE(r3)
- cmpwi r8, 0
- beq 47f
- bl kvmhv_p9_restore_lpcr
- nop
- b 48f
-47:
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
- ld r8,KVM_HOST_LPCR(r4)
+16: ld r8,KVM_HOST_LPCR(r4)
mtspr SPRN_LPCR,r8
isync
-48:
+
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
/* Finish timing, if we have a vcpu */
ld r4, HSTATE_KVM_VCPU(r13)
@@ -2779,8 +2735,10 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
beq kvm_end_cede
cmpwi r0, NAPPING_NOVCPU
beq kvm_novcpu_wakeup
+BEGIN_FTR_SECTION
cmpwi r0, NAPPING_UNSPLIT
beq kvm_unsplit_wakeup
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
twi 31,0,0 /* Nap state must not be zero */
33: mr r4, r3
--
2.23.0
^ permalink raw reply related
* [PATCH 2/3] powerpc/pseries/hotplug-cpu: fix memleak in dlpar_cpu_add_by_count
From: Qinglang Miao @ 2020-11-28 10:20 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras
Cc: linuxppc-dev, linux-kernel, Qinglang Miao
kfree(cpu_drcs) should be called when it fails to perform
of_find_node_by_path("/cpus") in dlpar_cpu_add_by_count,
otherwise there would be a memleak.
In fact, the patch a0ff72f9f5a7 ought to remove kfree in
find_dlpar_cpus_to_add rather than dlpar_cpu_add_by_count.
I guess there might be a mistake when apply that one.
Fixes: a0ff72f9f5a7 ("powerpc/pseries/hotplug-cpu: Remove double free in error path")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Qinglang Miao <miaoqinglang@huawei.com>
---
arch/powerpc/platforms/pseries/hotplug-cpu.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index f2837e33b..4bb1c9f2b 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -743,6 +743,7 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add)
parent = of_find_node_by_path("/cpus");
if (!parent) {
pr_warn("Could not find CPU root node in device tree\n");
+ kfree(cpu_drcs);
return -1;
}
--
2.23.0
^ permalink raw reply related
* [PATCH v3 00/19] powerpc: interrupt wrappers
From: Nicholas Piggin @ 2020-11-28 14:40 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
This adds interrupt handler wrapper functions, similar to the
generic / x86 code, and moves several common operations into them
from either asm or open coded in the individual handlers.
Since v1:
- Fixed a couple of compile issues
- Fixed perf weirdness (sometimes NMI, sometimes not)
- Also move irq_enter/exit into wrappers
Since v2:
- Rebased upstream
- Took code in patch 3 from Christophe
- Fixed some compile errors from 0day
Thanks,
Nick
Nicholas Piggin (19):
powerpc/64s: move the last of the page fault handling logic to C
powerpc: remove arguments from fault handler functions
powerpc: bad_page_fault, do_break get registers from regs
powerpc/perf: move perf irq/nmi handling details into traps.c
powerpc: interrupt handler wrapper functions
powerpc: add interrupt wrapper entry / exit stub functions
powerpc: add interrupt_cond_local_irq_enable helper
powerpc/64: context tracking remove _TIF_NOHZ
powerpc/64: context tracking move to interrupt wrappers
powerpc/64: add context tracking to asynchronous interrupts
powerpc: handle irq_enter/irq_exit in interrupt handler wrappers
powerpc/64s: move context tracking exit to interrupt exit path
powerpc/64s: reconcile interrupts in C
powerpc/64: move account_stolen_time into its own function
powerpc/64: entry cpu time accounting in C
powerpc: move NMI entry/exit code into wrapper
powerpc/64s: move NMI soft-mask handling to C
powerpc/64s: runlatch interrupt handling in C
powerpc/64s: power4 nap fixup in C
arch/Kconfig | 6 -
arch/powerpc/Kconfig | 1 -
arch/powerpc/include/asm/asm-prototypes.h | 29 --
arch/powerpc/include/asm/bug.h | 5 +-
arch/powerpc/include/asm/cputime.h | 15 +
arch/powerpc/include/asm/debug.h | 3 +-
arch/powerpc/include/asm/hw_irq.h | 9 -
arch/powerpc/include/asm/interrupt.h | 405 +++++++++++++++++++++
arch/powerpc/include/asm/ppc_asm.h | 24 --
arch/powerpc/include/asm/processor.h | 1 +
arch/powerpc/include/asm/thread_info.h | 10 +-
arch/powerpc/include/asm/time.h | 2 +
arch/powerpc/kernel/dbell.c | 15 +-
arch/powerpc/kernel/entry_32.S | 18 +-
arch/powerpc/kernel/exceptions-64e.S | 6 +-
arch/powerpc/kernel/exceptions-64s.S | 307 ++--------------
arch/powerpc/kernel/head_40x.S | 10 +-
arch/powerpc/kernel/head_8xx.S | 11 +-
arch/powerpc/kernel/head_book3s_32.S | 15 +-
arch/powerpc/kernel/head_booke.h | 4 +-
arch/powerpc/kernel/idle_book3s.S | 4 +
arch/powerpc/kernel/irq.c | 7 +-
arch/powerpc/kernel/mce.c | 16 +-
arch/powerpc/kernel/process.c | 7 +-
arch/powerpc/kernel/ptrace/ptrace.c | 4 -
arch/powerpc/kernel/signal.c | 4 -
arch/powerpc/kernel/syscall_64.c | 30 +-
arch/powerpc/kernel/tau_6xx.c | 5 +-
arch/powerpc/kernel/time.c | 7 +-
arch/powerpc/kernel/traps.c | 231 ++++++------
arch/powerpc/kernel/watchdog.c | 15 +-
arch/powerpc/kvm/book3s_hv.c | 1 +
arch/powerpc/kvm/book3s_hv_builtin.c | 1 +
arch/powerpc/kvm/booke.c | 1 +
arch/powerpc/mm/book3s64/hash_utils.c | 82 +++--
arch/powerpc/mm/book3s64/slb.c | 12 +-
arch/powerpc/mm/fault.c | 78 +++-
arch/powerpc/perf/core-book3s.c | 35 +-
arch/powerpc/perf/core-fsl-emb.c | 25 --
arch/powerpc/platforms/8xx/machine_check.c | 2 +-
arch/powerpc/platforms/powernv/idle.c | 1 +
41 files changed, 772 insertions(+), 692 deletions(-)
create mode 100644 arch/powerpc/include/asm/interrupt.h
--
2.23.0
^ permalink raw reply
* [PATCH v3 02/19] powerpc: remove arguments from fault handler functions
From: Nicholas Piggin @ 2020-11-28 14:40 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
Make mm fault handlers all just take the pt_regs * argument and load
DAR/DSISR from that. Make those that return a value return long.
This is done to make the function signatures match other handlers, which
will help with a future patch to add wrappers. Explicit arguments could
be added for performance but that would require more wrapper macro
variants.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 4 ++--
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 2 +-
arch/powerpc/include/asm/bug.h | 4 ++--
arch/powerpc/kernel/exceptions-64e.S | 2 --
arch/powerpc/kernel/exceptions-64s.S | 14 ++------------
arch/powerpc/kernel/head_40x.S | 10 +++++-----
arch/powerpc/kernel/head_8xx.S | 6 +++---
arch/powerpc/kernel/head_book3s_32.S | 6 ++----
arch/powerpc/kernel/head_booke.h | 4 +---
arch/powerpc/mm/book3s64/hash_utils.c | 8 +++++---
arch/powerpc/mm/book3s64/slb.c | 11 +++++++----
arch/powerpc/mm/fault.c | 16 +++++++++-------
12 files changed, 39 insertions(+), 48 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index d0b832cbbec8..22c9d08fa3a4 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -82,8 +82,8 @@ void kernel_bad_stack(struct pt_regs *regs);
void system_reset_exception(struct pt_regs *regs);
void machine_check_exception(struct pt_regs *regs);
void emulation_assist_interrupt(struct pt_regs *regs);
-long do_slb_fault(struct pt_regs *regs, unsigned long ea);
-void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err);
+long do_slb_fault(struct pt_regs *regs);
+void do_bad_slb_fault(struct pt_regs *regs);
/* signals, syscalls and interrupts */
long sys_swapcontext(struct ucontext __user *old_ctx,
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index bc8c91f2d26f..e843d0b193d3 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -453,7 +453,7 @@ static inline unsigned long hpt_hash(unsigned long vpn,
#define HPTE_LOCAL_UPDATE 0x1
#define HPTE_NOHPTE_UPDATE 0x2
-int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr);
+long do_hash_fault(struct pt_regs *regs);
extern int __hash_page_4K(unsigned long ea, unsigned long access,
unsigned long vsid, pte_t *ptep, unsigned long trap,
unsigned long flags, int ssize, int subpage_prot);
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index c0e9b7a967a8..897bad6b6bbb 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -111,8 +111,8 @@
#ifndef __ASSEMBLY__
struct pt_regs;
-extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
-int hash__do_page_fault(struct pt_regs *, unsigned long, unsigned long);
+long do_page_fault(struct pt_regs *);
+long hash__do_page_fault(struct pt_regs *);
extern void bad_page_fault(struct pt_regs *, unsigned long, int);
extern void _exception(int, struct pt_regs *, int, unsigned long);
extern void _exception_pkey(struct pt_regs *, unsigned long, int);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index f579ce46eef2..25fa7d5a643c 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1011,8 +1011,6 @@ storage_fault_common:
std r14,_DAR(r1)
std r15,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
- mr r4,r14
- mr r5,r15
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
bl do_page_fault
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 336fa1fa39d1..690058043b17 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1438,8 +1438,6 @@ EXC_VIRT_BEGIN(data_access, 0x4300, 0x80)
EXC_VIRT_END(data_access, 0x4300, 0x80)
EXC_COMMON_BEGIN(data_access_common)
GEN_COMMON data_access
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
bl do_hash_fault
@@ -1492,10 +1490,9 @@ EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80)
EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
EXC_COMMON_BEGIN(data_access_slb_common)
GEN_COMMON data_access_slb
- ld r4,_DAR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
/* HPT case, do SLB fault */
+ addi r3,r1,STACK_FRAME_OVERHEAD
bl do_slb_fault
cmpdi r3,0
bne- 1f
@@ -1507,8 +1504,6 @@ MMU_FTR_SECTION_ELSE
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
RECONCILE_IRQ_STATE(r10, r11)
- ld r4,_DAR(r1)
- ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
@@ -1543,8 +1538,6 @@ EXC_VIRT_BEGIN(instruction_access, 0x4400, 0x80)
EXC_VIRT_END(instruction_access, 0x4400, 0x80)
EXC_COMMON_BEGIN(instruction_access_common)
GEN_COMMON instruction_access
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
bl do_hash_fault
@@ -1588,10 +1581,9 @@ EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80)
EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80)
EXC_COMMON_BEGIN(instruction_access_slb_common)
GEN_COMMON instruction_access_slb
- ld r4,_DAR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
/* HPT case, do SLB fault */
+ addi r3,r1,STACK_FRAME_OVERHEAD
bl do_slb_fault
cmpdi r3,0
bne- 1f
@@ -1603,8 +1595,6 @@ MMU_FTR_SECTION_ELSE
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
RECONCILE_IRQ_STATE(r10, r11)
- ld r4,_DAR(r1)
- ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index a1ae00689e0f..3c5577ac4dc8 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -179,9 +179,9 @@ _ENTRY(saved_ksp_limit)
*/
START_EXCEPTION(0x0300, DataStorage)
EXCEPTION_PROLOG
- mfspr r5, SPRN_ESR /* Grab the ESR, save it, pass arg3 */
+ mfspr r5, SPRN_ESR /* Grab the ESR, save it */
stw r5, _ESR(r11)
- mfspr r4, SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
+ mfspr r4, SPRN_DEAR /* Grab the DEAR, save it */
stw r4, _DEAR(r11)
EXC_XFER_LITE(0x300, handle_page_fault)
@@ -191,9 +191,9 @@ _ENTRY(saved_ksp_limit)
*/
START_EXCEPTION(0x0400, InstructionAccess)
EXCEPTION_PROLOG
- mr r4,r12 /* Pass SRR0 as arg2 */
- stw r4, _DEAR(r11)
- li r5,0 /* Pass zero as arg3 */
+ li r5,0
+ stw r5, _ESR(r11) /* Zero ESR */
+ stw r12, _DEAR(r11) /* SRR0 as DEAR */
EXC_XFER_LITE(0x400, handle_page_fault)
/* 0x0500 - External Interrupt Exception */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index ee0bfebc375f..8acd365a2be6 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -324,14 +324,14 @@ DataStoreTLBMiss:
. = 0x1300
InstructionTLBError:
EXCEPTION_PROLOG
- mr r4,r12
andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
andis. r10,r9,SRR1_ISI_NOPT@h
beq+ .Litlbie
- tlbie r4
+ tlbie r12
/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
.Litlbie:
- stw r4, _DAR(r11)
+ stw r12, _DAR(r11)
+ stw r5, _DSISR(r11)
EXC_XFER_LITE(0x400, handle_page_fault)
/* This is the data TLB error on the MPC8xx. This could be due to
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index a0dda2a1f2df..7addf67832f9 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -370,9 +370,9 @@ BEGIN_MMU_FTR_SECTION
bl hash_page
END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
#endif /* CONFIG_VMAP_STACK */
-1: mr r4,r12
andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
- stw r4, _DAR(r11)
+ stw r5, _DSISR(r11)
+ stw r12, _DAR(r11)
EXC_XFER_LITE(0x400, handle_page_fault)
/* External interrupt */
@@ -687,8 +687,6 @@ handle_page_fault_tramp_1:
#ifdef CONFIG_VMAP_STACK
EXCEPTION_PROLOG_2 handle_dar_dsisr=1
#endif
- lwz r4, _DAR(r11)
- lwz r5, _DSISR(r11)
/* fall through */
handle_page_fault_tramp_2:
EXC_XFER_LITE(0x300, handle_page_fault)
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 71c359d438b5..1da0c1d1b0a1 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -477,9 +477,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
NORMAL_EXCEPTION_PROLOG(INST_STORAGE); \
mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
stw r5,_ESR(r11); \
- mr r4,r12; /* Pass SRR0 as arg2 */ \
- stw r4, _DEAR(r11); \
- li r5,0; /* Pass zero as arg3 */ \
+ stw r12, _DEAR(r11); /* Pass SRR0 as arg2 */ \
EXC_XFER_LITE(0x0400, handle_page_fault)
#define ALIGNMENT_EXCEPTION \
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index bfa1b1966218..0f0bd4af4b2d 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1510,13 +1510,15 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
}
EXPORT_SYMBOL_GPL(hash_page);
-int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr)
+long do_hash_fault(struct pt_regs *regs)
{
+ unsigned long ea = regs->dar;
+ unsigned long dsisr = regs->dsisr;
unsigned long access = _PAGE_PRESENT | _PAGE_READ;
unsigned long flags = 0;
struct mm_struct *mm;
unsigned int region_id;
- int err;
+ long err;
if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_DABRMATCH | DSISR_KEYFAULT)))
goto _do_page_fault;
@@ -1580,7 +1582,7 @@ int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr)
} else if (err) {
_do_page_fault:
- err = hash__do_page_fault(regs, ea, dsisr);
+ err = hash__do_page_fault(regs);
}
return err;
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index c30fcbfa0e32..cc34d50874c1 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -837,8 +837,9 @@ static long slb_allocate_user(struct mm_struct *mm, unsigned long ea)
return slb_insert_entry(ea, context, flags, ssize, false);
}
-long do_slb_fault(struct pt_regs *regs, unsigned long ea)
+long do_slb_fault(struct pt_regs *regs)
{
+ unsigned long ea = regs->dar;
unsigned long id = get_region_id(ea);
/* IRQs are not reconciled here, so can't check irqs_disabled */
@@ -889,13 +890,15 @@ long do_slb_fault(struct pt_regs *regs, unsigned long ea)
}
}
-void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err)
+void do_bad_slb_fault(struct pt_regs *regs)
{
+ int err = regs->result;
+
if (err == -EFAULT) {
if (user_mode(regs))
- _exception(SIGSEGV, regs, SEGV_BNDERR, ea);
+ _exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar);
else
- bad_page_fault(regs, ea, SIGSEGV);
+ bad_page_fault(regs, regs->dar, SIGSEGV);
} else if (err == -EINVAL) {
unrecoverable_exception(regs);
} else {
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index e65a49f246ef..390a296b16a3 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -549,11 +549,12 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
}
NOKPROBE_SYMBOL(__do_page_fault);
-int do_page_fault(struct pt_regs *regs, unsigned long address,
- unsigned long error_code)
+long do_page_fault(struct pt_regs *regs)
{
enum ctx_state prev_state = exception_enter();
- int err;
+ unsigned long address = regs->dar;
+ unsigned long error_code = regs->dsisr;
+ long err;
err = __do_page_fault(regs, address, error_code);
@@ -580,11 +581,12 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
NOKPROBE_SYMBOL(do_page_fault);
#ifdef CONFIG_PPC_BOOK3S_64
-/* Same as do_page_fault but interrupt entry has already run in do_hash_fault */
-int hash__do_page_fault(struct pt_regs *regs, unsigned long address,
- unsigned long error_code)
+/* Same as do_page_fault but no interrupt entry */
+long hash__do_page_fault(struct pt_regs *regs)
{
- int err;
+ unsigned long address = regs->dar;
+ unsigned long error_code = regs->dsisr;
+ long err;
err = __do_page_fault(regs, address, error_code);
if (unlikely(err)) {
--
2.23.0
^ permalink raw reply related
* [PATCH v3 01/19] powerpc/64s: move the last of the page fault handling logic to C
From: Nicholas Piggin @ 2020-11-28 14:40 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
The page fault handling still has some complex logic particularly around
hash table handling, in asm. Implement this in C instead.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 +
arch/powerpc/include/asm/bug.h | 1 +
arch/powerpc/kernel/exceptions-64s.S | 131 +++---------------
arch/powerpc/mm/book3s64/hash_utils.c | 77 ++++++----
arch/powerpc/mm/fault.c | 57 +++++++-
5 files changed, 127 insertions(+), 140 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 683a9c7d1b03..bc8c91f2d26f 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -453,6 +453,7 @@ static inline unsigned long hpt_hash(unsigned long vpn,
#define HPTE_LOCAL_UPDATE 0x1
#define HPTE_NOHPTE_UPDATE 0x2
+int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr);
extern int __hash_page_4K(unsigned long ea, unsigned long access,
unsigned long vsid, pte_t *ptep, unsigned long trap,
unsigned long flags, int ssize, int subpage_prot);
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 338f36cd9934..c0e9b7a967a8 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -112,6 +112,7 @@
struct pt_regs;
extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
+int hash__do_page_fault(struct pt_regs *, unsigned long, unsigned long);
extern void bad_page_fault(struct pt_regs *, unsigned long, int);
extern void _exception(int, struct pt_regs *, int, unsigned long);
extern void _exception_pkey(struct pt_regs *, unsigned long, int);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4d01f09ecf80..336fa1fa39d1 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1401,14 +1401,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
*
* Handling:
* - Hash MMU
- * Go to do_hash_page first to see if the HPT can be filled from an entry in
- * the Linux page table. Hash faults can hit in kernel mode in a fairly
+ * Go to do_hash_fault, which attempts to fill the HPT from an entry in the
+ * Linux page table. Hash faults can hit in kernel mode in a fairly
* arbitrary state (e.g., interrupts disabled, locks held) when accessing
* "non-bolted" regions, e.g., vmalloc space. However these should always be
- * backed by Linux page tables.
+ * backed by Linux page table entries.
*
- * If none is found, do a Linux page fault. Linux page faults can happen in
- * kernel mode due to user copy operations of course.
+ * If no entry is found the Linux page fault handler is invoked (by
+ * do_hash_fault). Linux page faults can happen in kernel mode due to user
+ * copy operations of course.
*
* KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest
* MMU context, which may cause a DSI in the host, which must go to the
@@ -1439,13 +1440,17 @@ EXC_COMMON_BEGIN(data_access_common)
GEN_COMMON data_access
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
- ld r6,_MSR(r1)
- li r3,0x300
- b do_hash_page /* Try to handle as hpte fault */
+ bl do_hash_fault
MMU_FTR_SECTION_ELSE
- b handle_page_fault
+ bl do_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ cmpdi r3,0
+ beq+ interrupt_return
+ /* We need to restore NVGPRS */
+ REST_NVGPRS(r1)
+ b interrupt_return
GEN_KVM data_access
@@ -1540,13 +1545,17 @@ EXC_COMMON_BEGIN(instruction_access_common)
GEN_COMMON instruction_access
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
- ld r6,_MSR(r1)
- li r3,0x400
- b do_hash_page /* Try to handle as hpte fault */
+ bl do_hash_fault
MMU_FTR_SECTION_ELSE
- b handle_page_fault
+ bl do_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ cmpdi r3,0
+ beq+ interrupt_return
+ /* We need to restore NVGPRS */
+ REST_NVGPRS(r1)
+ b interrupt_return
GEN_KVM instruction_access
@@ -3202,99 +3211,3 @@ disable_machine_check:
RFI_TO_KERNEL
1: mtlr r0
blr
-
-/*
- * Hash table stuff
- */
- .balign IFETCH_ALIGN_BYTES
-do_hash_page:
-#ifdef CONFIG_PPC_BOOK3S_64
- lis r0,(DSISR_BAD_FAULT_64S | DSISR_DABRMATCH | DSISR_KEYFAULT)@h
- ori r0,r0,DSISR_BAD_FAULT_64S@l
- and. r0,r5,r0 /* weird error? */
- bne- handle_page_fault /* if not, try to insert a HPTE */
-
- /*
- * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
- * don't call hash_page, just fail the fault. This is required to
- * prevent re-entrancy problems in the hash code, namely perf
- * interrupts hitting while something holds H_PAGE_BUSY, and taking a
- * hash fault. See the comment in hash_preload().
- */
- ld r11, PACA_THREAD_INFO(r13)
- lwz r0,TI_PREEMPT(r11)
- andis. r0,r0,NMI_MASK@h
- bne 77f
-
- /*
- * r3 contains the trap number
- * r4 contains the faulting address
- * r5 contains dsisr
- * r6 msr
- *
- * at return r3 = 0 for success, 1 for page fault, negative for error
- */
- bl __hash_page /* build HPTE if possible */
- cmpdi r3,0 /* see if __hash_page succeeded */
-
- /* Success */
- beq interrupt_return /* Return from exception on success */
-
- /* Error */
- blt- 13f
-
- /* Reload DAR/DSISR into r4/r5 for the DABR check below */
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-/* Here we have a page fault that hash_page can't handle. */
-handle_page_fault:
-11: andis. r0,r5,DSISR_DABRMATCH@h
- bne- handle_dabr_fault
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_page_fault
- cmpdi r3,0
- beq+ interrupt_return
- mr r5,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
- bl bad_page_fault
- b interrupt_return
-
-/* We have a data breakpoint exception - handle it */
-handle_dabr_fault:
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_break
- /*
- * do_break() may have changed the NV GPRS while handling a breakpoint.
- * If so, we need to restore them with their updated values.
- */
- REST_NVGPRS(r1)
- b interrupt_return
-
-
-#ifdef CONFIG_PPC_BOOK3S_64
-/* We have a page fault that hash_page could handle but HV refused
- * the PTE insertion
- */
-13: mr r5,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
- bl low_hash_fault
- b interrupt_return
-#endif
-
-/*
- * We come here as a result of a DSI at a point where we don't want
- * to call hash_page, such as when we are accessing memory (possibly
- * user memory) inside a PMU interrupt that occurred while interrupts
- * were soft-disabled. We want to invoke the exception handler for
- * the access, or panic if there isn't a handler.
- */
-77: addi r3,r1,STACK_FRAME_OVERHEAD
- li r5,SIGSEGV
- bl bad_page_fault
- b interrupt_return
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 24702c0a92e0..bfa1b1966218 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1510,16 +1510,40 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
}
EXPORT_SYMBOL_GPL(hash_page);
-int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr,
- unsigned long msr)
+int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr)
{
unsigned long access = _PAGE_PRESENT | _PAGE_READ;
unsigned long flags = 0;
- struct mm_struct *mm = current->mm;
- unsigned int region_id = get_region_id(ea);
+ struct mm_struct *mm;
+ unsigned int region_id;
+ int err;
+
+ if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_DABRMATCH | DSISR_KEYFAULT)))
+ goto _do_page_fault;
+
+ /*
+ * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
+ * don't call hash_page, just fail the fault. This is required to
+ * prevent re-entrancy problems in the hash code, namely perf
+ * interrupts hitting while something holds H_PAGE_BUSY, and taking a
+ * hash fault. See the comment in hash_preload().
+ *
+ * We come here as a result of a DSI at a point where we don't want
+ * to call hash_page, such as when we are accessing memory (possibly
+ * user memory) inside a PMU interrupt that occurred while interrupts
+ * were soft-disabled. We want to invoke the exception handler for
+ * the access, or panic if there isn't a handler.
+ */
+ if (unlikely(in_nmi())) {
+ bad_page_fault(regs, ea, SIGSEGV);
+ return 0;
+ }
+ region_id = get_region_id(ea);
if ((region_id == VMALLOC_REGION_ID) || (region_id == IO_REGION_ID))
mm = &init_mm;
+ else
+ mm = current->mm;
if (dsisr & DSISR_NOHPTE)
flags |= HPTE_NOHPTE_UPDATE;
@@ -1535,13 +1559,31 @@ int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr,
* 2) user space access kernel space.
*/
access |= _PAGE_PRIVILEGED;
- if ((msr & MSR_PR) || (region_id == USER_REGION_ID))
+ if (user_mode(regs) || (region_id == USER_REGION_ID))
access &= ~_PAGE_PRIVILEGED;
- if (trap == 0x400)
+ if (regs->trap == 0x400)
access |= _PAGE_EXEC;
- return hash_page_mm(mm, ea, access, trap, flags);
+ err = hash_page_mm(mm, ea, access, regs->trap, flags);
+ if (unlikely(err < 0)) {
+ // failed to instert a hash PTE due to an hypervisor error
+ if (user_mode(regs)) {
+ if (IS_ENABLED(CONFIG_PPC_SUBPAGE_PROT) && err == -2)
+ _exception(SIGSEGV, regs, SEGV_ACCERR, ea);
+ else
+ _exception(SIGBUS, regs, BUS_ADRERR, ea);
+ } else {
+ bad_page_fault(regs, ea, SIGBUS);
+ }
+ err = 0;
+
+ } else if (err) {
+_do_page_fault:
+ err = hash__do_page_fault(regs, ea, dsisr);
+ }
+
+ return err;
}
#ifdef CONFIG_PPC_MM_SLICES
@@ -1841,27 +1883,6 @@ void flush_hash_range(unsigned long number, int local)
}
}
-/*
- * low_hash_fault is called when we the low level hash code failed
- * to instert a PTE due to an hypervisor error
- */
-void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
-{
- enum ctx_state prev_state = exception_enter();
-
- if (user_mode(regs)) {
-#ifdef CONFIG_PPC_SUBPAGE_PROT
- if (rc == -2)
- _exception(SIGSEGV, regs, SEGV_ACCERR, address);
- else
-#endif
- _exception(SIGBUS, regs, BUS_ADRERR, address);
- } else
- bad_page_fault(regs, address, SIGBUS);
-
- exception_exit(prev_state);
-}
-
long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
unsigned long pa, unsigned long rflags,
unsigned long vflags, int psize, int ssize)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 0add963a849b..e65a49f246ef 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -370,7 +370,9 @@ static void sanity_check_fault(bool is_write, bool is_user,
#define page_fault_is_write(__err) ((__err) & DSISR_ISSTORE)
#if defined(CONFIG_PPC_8xx)
#define page_fault_is_bad(__err) ((__err) & DSISR_NOEXEC_OR_G)
-#elif defined(CONFIG_PPC64)
+#elif defined(CONFIG_PPC_BOOK3S_64)
+#define page_fault_is_bad(__err) ((__err) & (DSISR_BAD_FAULT_64S | DSISR_DABRMATCH))
+#elif defined(CONFIG_PPC_BOOK3E_64)
#define page_fault_is_bad(__err) ((__err) & DSISR_BAD_FAULT_64S)
#else
#define page_fault_is_bad(__err) ((__err) & DSISR_BAD_FAULT_32S)
@@ -406,6 +408,9 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
return 0;
if (unlikely(page_fault_is_bad(error_code))) {
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && (error_code & DSISR_DABRMATCH))
+ return -1;
+
if (is_user) {
_exception(SIGBUS, regs, BUS_OBJERR, address);
return 0;
@@ -548,12 +553,58 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
enum ctx_state prev_state = exception_enter();
- int rc = __do_page_fault(regs, address, error_code);
+ int err;
+
+ err = __do_page_fault(regs, address, error_code);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* 32 and 64e handle errors in their asm code */
+ if (unlikely(err)) {
+ if (err > 0) {
+ bad_page_fault(regs, address, err);
+ err = 0;
+ } else {
+ /*
+ * do_break() may change NV GPRS while handling the
+ * breakpoint. Return -ve to caller to do that.
+ */
+ do_break(regs, address, error_code);
+ }
+ }
+#endif
+
exception_exit(prev_state);
- return rc;
+
+ return err;
}
NOKPROBE_SYMBOL(do_page_fault);
+#ifdef CONFIG_PPC_BOOK3S_64
+/* Same as do_page_fault but interrupt entry has already run in do_hash_fault */
+int hash__do_page_fault(struct pt_regs *regs, unsigned long address,
+ unsigned long error_code)
+{
+ int err;
+
+ err = __do_page_fault(regs, address, error_code);
+ if (unlikely(err)) {
+ if (err > 0) {
+ bad_page_fault(regs, address, err);
+ err = 0;
+ } else {
+ /*
+ * do_break() may change NV GPRS while handling the
+ * breakpoint. Return -ve to caller to do that.
+ */
+ do_break(regs, address, error_code);
+ }
+ }
+
+ return err;
+}
+NOKPROBE_SYMBOL(hash__do_page_fault);
+#endif
+
/*
* bad_page_fault is called when we have a bad access from the kernel.
* It is called from the DSI and ISI handlers in head.S and from some
--
2.23.0
^ permalink raw reply related
* [PATCH v3 03/19] powerpc: bad_page_fault, do_break get registers from regs
From: Nicholas Piggin @ 2020-11-28 14:40 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
Similar to the previous patch this makes interrupt handler function
types more regular so they can be wrapped with the next patch.
bad_page_fault and do_break are not performance critical.
[32s DABR code from Christophe Leroy <christophe.leroy@csgroup.eu>]
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/bug.h | 2 +-
arch/powerpc/include/asm/debug.h | 3 +--
arch/powerpc/kernel/entry_32.S | 18 +-----------------
arch/powerpc/kernel/exceptions-64e.S | 3 +--
arch/powerpc/kernel/exceptions-64s.S | 3 +--
arch/powerpc/kernel/head_8xx.S | 5 ++---
arch/powerpc/kernel/head_book3s_32.S | 3 +++
arch/powerpc/kernel/process.c | 7 +++----
arch/powerpc/kernel/traps.c | 2 +-
arch/powerpc/mm/book3s64/hash_utils.c | 4 ++--
arch/powerpc/mm/book3s64/slb.c | 2 +-
arch/powerpc/mm/fault.c | 10 +++++-----
arch/powerpc/platforms/8xx/machine_check.c | 2 +-
13 files changed, 23 insertions(+), 41 deletions(-)
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 897bad6b6bbb..49162faba33f 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -113,7 +113,7 @@
struct pt_regs;
long do_page_fault(struct pt_regs *);
long hash__do_page_fault(struct pt_regs *);
-extern void bad_page_fault(struct pt_regs *, unsigned long, int);
+void bad_page_fault(struct pt_regs *, int);
extern void _exception(int, struct pt_regs *, int, unsigned long);
extern void _exception_pkey(struct pt_regs *, unsigned long, int);
extern void die(const char *, struct pt_regs *, long);
diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
index ec57daf87f40..0550eceab3ca 100644
--- a/arch/powerpc/include/asm/debug.h
+++ b/arch/powerpc/include/asm/debug.h
@@ -52,8 +52,7 @@ extern void do_send_trap(struct pt_regs *regs, unsigned long address,
unsigned long error_code, int brkpt);
#else
-extern void do_break(struct pt_regs *regs, unsigned long address,
- unsigned long error_code);
+void do_break(struct pt_regs *regs);
#endif
#endif /* _ASM_POWERPC_DEBUG_H */
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 8cdc8bcde703..57b8e95ea2a0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -657,10 +657,6 @@ ppc_swapcontext:
.globl handle_page_fault
handle_page_fault:
addi r3,r1,STACK_FRAME_OVERHEAD
-#ifdef CONFIG_PPC_BOOK3S_32
- andis. r0,r5,DSISR_DABRMATCH@h
- bne- handle_dabr_fault
-#endif
bl do_page_fault
cmpwi r3,0
beq+ ret_from_except
@@ -668,23 +664,11 @@ handle_page_fault:
lwz r0,_TRAP(r1)
clrrwi r0,r0,1
stw r0,_TRAP(r1)
- mr r5,r3
+ mr r4,r3 /* err arg for bad_page_fault */
addi r3,r1,STACK_FRAME_OVERHEAD
- lwz r4,_DAR(r1)
bl bad_page_fault
b ret_from_except_full
-#ifdef CONFIG_PPC_BOOK3S_32
- /* We have a data breakpoint exception - handle it */
-handle_dabr_fault:
- SAVE_NVGPRS(r1)
- lwz r0,_TRAP(r1)
- clrrwi r0,r0,1
- stw r0,_TRAP(r1)
- bl do_break
- b ret_from_except_full
-#endif
-
/*
* This routine switches between two different tasks. The process
* state of one is saved on its kernel stack. Then the state
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 25fa7d5a643c..dc728bb1c89a 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1018,9 +1018,8 @@ storage_fault_common:
bne- 1f
b ret_from_except_lite
1: bl save_nvgprs
- mr r5,r3
+ mr r4,r3
addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
bl bad_page_fault
b ret_from_except
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 690058043b17..77b730f515c4 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2136,8 +2136,7 @@ EXC_COMMON_BEGIN(h_data_storage_common)
GEN_COMMON h_data_storage
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
- ld r4,_DAR(r1)
- li r5,SIGSEGV
+ li r4,SIGSEGV
bl bad_page_fault
MMU_FTR_SECTION_ELSE
bl unknown_exception
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 8acd365a2be6..71ad7ce28469 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -376,10 +376,9 @@ do_databreakpoint:
addi r3,r1,STACK_FRAME_OVERHEAD
mfspr r4,SPRN_BAR
stw r4,_DAR(r11)
-#ifdef CONFIG_VMAP_STACK
- lwz r5,_DSISR(r11)
-#else
+#ifndef CONFIG_VMAP_STACK
mfspr r5,SPRN_DSISR
+ stw r5,_DSISR(r11)
#endif
EXC_XFER_STD(0x1c00, do_break)
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 7addf67832f9..5875f8795d5b 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -689,7 +689,10 @@ handle_page_fault_tramp_1:
#endif
/* fall through */
handle_page_fault_tramp_2:
+ andis. r0, r5, DSISR_DABRMATCH@h
+ bne- 1f
EXC_XFER_LITE(0x300, handle_page_fault)
+1: EXC_XFER_STD(0x300, do_break)
#ifdef CONFIG_VMAP_STACK
.macro save_regs_thread thread
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index d421a2c7f822..0bdd3ed653df 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -660,11 +660,10 @@ static void do_break_handler(struct pt_regs *regs)
}
}
-void do_break (struct pt_regs *regs, unsigned long address,
- unsigned long error_code)
+void do_break(struct pt_regs *regs)
{
current->thread.trap_nr = TRAP_HWBKPT;
- if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
+ if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, regs->dsisr,
11, SIGSEGV) == NOTIFY_STOP)
return;
@@ -682,7 +681,7 @@ void do_break (struct pt_regs *regs, unsigned long address,
do_break_handler(regs);
/* Deliver the signal to userspace */
- force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)address);
+ force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)regs->dar);
}
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 5006dcbe1d9f..902fcbd1a778 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1641,7 +1641,7 @@ void alignment_exception(struct pt_regs *regs)
if (user_mode(regs))
_exception(sig, regs, code, regs->dar);
else
- bad_page_fault(regs, regs->dar, sig);
+ bad_page_fault(regs, sig);
bail:
exception_exit(prev_state);
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 0f0bd4af4b2d..731518e7d56f 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1537,7 +1537,7 @@ long do_hash_fault(struct pt_regs *regs)
* the access, or panic if there isn't a handler.
*/
if (unlikely(in_nmi())) {
- bad_page_fault(regs, ea, SIGSEGV);
+ bad_page_fault(regs, SIGSEGV);
return 0;
}
@@ -1576,7 +1576,7 @@ long do_hash_fault(struct pt_regs *regs)
else
_exception(SIGBUS, regs, BUS_ADRERR, ea);
} else {
- bad_page_fault(regs, ea, SIGBUS);
+ bad_page_fault(regs, SIGBUS);
}
err = 0;
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index cc34d50874c1..ae89ad516247 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -898,7 +898,7 @@ void do_bad_slb_fault(struct pt_regs *regs)
if (user_mode(regs))
_exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar);
else
- bad_page_fault(regs, regs->dar, SIGSEGV);
+ bad_page_fault(regs, SIGSEGV);
} else if (err == -EINVAL) {
unrecoverable_exception(regs);
} else {
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 390a296b16a3..e11989be8f1c 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -562,14 +562,14 @@ long do_page_fault(struct pt_regs *regs)
/* 32 and 64e handle errors in their asm code */
if (unlikely(err)) {
if (err > 0) {
- bad_page_fault(regs, address, err);
+ bad_page_fault(regs, err);
err = 0;
} else {
/*
* do_break() may change NV GPRS while handling the
* breakpoint. Return -ve to caller to do that.
*/
- do_break(regs, address, error_code);
+ do_break(regs);
}
}
#endif
@@ -591,14 +591,14 @@ long hash__do_page_fault(struct pt_regs *regs)
err = __do_page_fault(regs, address, error_code);
if (unlikely(err)) {
if (err > 0) {
- bad_page_fault(regs, address, err);
+ bad_page_fault(regs, err);
err = 0;
} else {
/*
* do_break() may change NV GPRS while handling the
* breakpoint. Return -ve to caller to do that.
*/
- do_break(regs, address, error_code);
+ do_break(regs);
}
}
@@ -612,7 +612,7 @@ NOKPROBE_SYMBOL(hash__do_page_fault);
* It is called from the DSI and ISI handlers in head.S and from some
* of the procedures in traps.c.
*/
-void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
+void bad_page_fault(struct pt_regs *regs, int sig)
{
const struct exception_table_entry *entry;
int is_write = page_fault_is_write(regs->dsisr);
diff --git a/arch/powerpc/platforms/8xx/machine_check.c b/arch/powerpc/platforms/8xx/machine_check.c
index 88dedf38eccd..656365975895 100644
--- a/arch/powerpc/platforms/8xx/machine_check.c
+++ b/arch/powerpc/platforms/8xx/machine_check.c
@@ -26,7 +26,7 @@ int machine_check_8xx(struct pt_regs *regs)
* to deal with that than having a wart in the mcheck handler.
* -- BenH
*/
- bad_page_fault(regs, regs->dar, SIGBUS);
+ bad_page_fault(regs, SIGBUS);
return 1;
#else
return 0;
--
2.23.0
^ permalink raw reply related
* [PATCH v3 04/19] powerpc/perf: move perf irq/nmi handling details into traps.c
From: Nicholas Piggin @ 2020-11-28 14:40 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
This is required in order to allow more significant differences between
NMI type interrupt handlers and regular asynchronous handlers.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/traps.c | 31 +++++++++++++++++++++++++++-
arch/powerpc/perf/core-book3s.c | 35 ++------------------------------
arch/powerpc/perf/core-fsl-emb.c | 25 -----------------------
3 files changed, 32 insertions(+), 59 deletions(-)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 902fcbd1a778..7dda72eb97cc 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1919,11 +1919,40 @@ void vsx_unavailable_tm(struct pt_regs *regs)
}
#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
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 08643cba1494..9fd8cae09218 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -109,10 +109,6 @@ static inline void perf_read_regs(struct pt_regs *regs)
{
regs->result = 0;
}
-static inline int perf_intr_is_nmi(struct pt_regs *regs)
-{
- return 0;
-}
static inline int siar_valid(struct pt_regs *regs)
{
@@ -328,15 +324,6 @@ static inline void perf_read_regs(struct pt_regs *regs)
regs->result = use_siar;
}
-/*
- * If interrupts were soft-disabled when a PMU interrupt occurs, treat
- * it as an NMI.
- */
-static inline int perf_intr_is_nmi(struct pt_regs *regs)
-{
- return (regs->softe & IRQS_DISABLED);
-}
-
/*
* On processors like P7+ that have the SIAR-Valid bit, marked instructions
* must be sampled only if the SIAR-valid bit is set.
@@ -2224,7 +2211,6 @@ static void __perf_event_interrupt(struct pt_regs *regs)
struct perf_event *event;
unsigned long val[8];
int found, active;
- int nmi;
if (cpuhw->n_limited)
freeze_limited_counters(cpuhw, mfspr(SPRN_PMC5),
@@ -2232,18 +2218,6 @@ static void __perf_event_interrupt(struct pt_regs *regs)
perf_read_regs(regs);
- /*
- * 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. See the NMI test in
- * do_hash_page.
- */
- nmi = perf_intr_is_nmi(regs);
- if (nmi)
- nmi_enter();
- else
- irq_enter();
-
/* Read all the PMCs since we'll need them a bunch of times */
for (i = 0; i < ppmu->n_counter; ++i)
val[i] = read_pmc(i + 1);
@@ -2289,8 +2263,8 @@ static void __perf_event_interrupt(struct pt_regs *regs)
}
}
}
- if (!found && !nmi && printk_ratelimit())
- printk(KERN_WARNING "Can't find PMC that caused IRQ\n");
+ if (unlikely(!found) && !arch_irq_disabled_regs(regs))
+ printk_ratelimited(KERN_WARNING "Can't find PMC that caused IRQ\n");
/*
* Reset MMCR0 to its normal value. This will set PMXE and
@@ -2300,11 +2274,6 @@ static void __perf_event_interrupt(struct pt_regs *regs)
* we get back out of this interrupt.
*/
write_mmcr0(cpuhw, cpuhw->mmcr.mmcr0);
-
- if (nmi)
- nmi_exit();
- else
- irq_exit();
}
static void perf_event_interrupt(struct pt_regs *regs)
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index e0e7e276bfd2..ee721f420a7b 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -31,19 +31,6 @@ static atomic_t num_events;
/* Used to avoid races in calling reserve/release_pmc_hardware */
static DEFINE_MUTEX(pmc_reserve_mutex);
-/*
- * If interrupts were soft-disabled when a PMU interrupt occurs, treat
- * it as an NMI.
- */
-static inline int perf_intr_is_nmi(struct pt_regs *regs)
-{
-#ifdef __powerpc64__
- return (regs->softe & IRQS_DISABLED);
-#else
- return 0;
-#endif
-}
-
static void perf_event_interrupt(struct pt_regs *regs);
/*
@@ -659,13 +646,6 @@ static void perf_event_interrupt(struct pt_regs *regs)
struct perf_event *event;
unsigned long val;
int found = 0;
- int nmi;
-
- nmi = perf_intr_is_nmi(regs);
- if (nmi)
- nmi_enter();
- else
- irq_enter();
for (i = 0; i < ppmu->n_counter; ++i) {
event = cpuhw->event[i];
@@ -690,11 +670,6 @@ static void perf_event_interrupt(struct pt_regs *regs)
mtmsr(mfmsr() | MSR_PMM);
mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE);
isync();
-
- if (nmi)
- nmi_exit();
- else
- irq_exit();
}
void hw_perf_event_setup(int cpu)
--
2.23.0
^ permalink raw reply related
* [PATCH v3 05/19] powerpc: interrupt handler wrapper functions
From: Nicholas Piggin @ 2020-11-28 14:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
Add wrapper functions (derived from x86 macros) for interrupt handler
functions. This allows interrupt entry code to be written in C.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 29 ---
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 -
arch/powerpc/include/asm/hw_irq.h | 9 -
arch/powerpc/include/asm/interrupt.h | 205 ++++++++++++++++++
arch/powerpc/include/asm/time.h | 2 +
arch/powerpc/kernel/dbell.c | 12 +-
arch/powerpc/kernel/exceptions-64s.S | 7 +-
arch/powerpc/kernel/head_book3s_32.S | 6 +-
arch/powerpc/kernel/irq.c | 3 +-
arch/powerpc/kernel/mce.c | 5 +-
arch/powerpc/kernel/syscall_64.c | 1 +
arch/powerpc/kernel/tau_6xx.c | 2 +-
arch/powerpc/kernel/time.c | 3 +-
arch/powerpc/kernel/traps.c | 90 +++++---
arch/powerpc/kernel/watchdog.c | 7 +-
arch/powerpc/kvm/book3s_hv.c | 1 +
arch/powerpc/kvm/book3s_hv_builtin.c | 1 +
arch/powerpc/kvm/booke.c | 1 +
arch/powerpc/mm/book3s64/hash_utils.c | 3 +-
arch/powerpc/mm/book3s64/slb.c | 5 +-
arch/powerpc/mm/fault.c | 10 +-
arch/powerpc/platforms/powernv/idle.c | 1 +
22 files changed, 311 insertions(+), 93 deletions(-)
create mode 100644 arch/powerpc/include/asm/interrupt.h
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 22c9d08fa3a4..939f3c94c8f3 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -56,35 +56,6 @@ int exit_vmx_usercopy(void);
int enter_vmx_ops(void);
void *exit_vmx_ops(void *dest);
-/* Traps */
-long machine_check_early(struct pt_regs *regs);
-long hmi_exception_realmode(struct pt_regs *regs);
-void SMIException(struct pt_regs *regs);
-void handle_hmi_exception(struct pt_regs *regs);
-void instruction_breakpoint_exception(struct pt_regs *regs);
-void RunModeException(struct pt_regs *regs);
-void single_step_exception(struct pt_regs *regs);
-void program_check_exception(struct pt_regs *regs);
-void alignment_exception(struct pt_regs *regs);
-void StackOverflow(struct pt_regs *regs);
-void stack_overflow_exception(struct pt_regs *regs);
-void kernel_fp_unavailable_exception(struct pt_regs *regs);
-void altivec_unavailable_exception(struct pt_regs *regs);
-void vsx_unavailable_exception(struct pt_regs *regs);
-void fp_unavailable_tm(struct pt_regs *regs);
-void altivec_unavailable_tm(struct pt_regs *regs);
-void vsx_unavailable_tm(struct pt_regs *regs);
-void facility_unavailable_exception(struct pt_regs *regs);
-void TAUException(struct pt_regs *regs);
-void altivec_assist_exception(struct pt_regs *regs);
-void unrecoverable_exception(struct pt_regs *regs);
-void kernel_bad_stack(struct pt_regs *regs);
-void system_reset_exception(struct pt_regs *regs);
-void machine_check_exception(struct pt_regs *regs);
-void emulation_assist_interrupt(struct pt_regs *regs);
-long do_slb_fault(struct pt_regs *regs);
-void do_bad_slb_fault(struct pt_regs *regs);
-
/* signals, syscalls and interrupts */
long sys_swapcontext(struct ucontext __user *old_ctx,
struct ucontext __user *new_ctx,
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index e843d0b193d3..683a9c7d1b03 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -453,7 +453,6 @@ static inline unsigned long hpt_hash(unsigned long vpn,
#define HPTE_LOCAL_UPDATE 0x1
#define HPTE_NOHPTE_UPDATE 0x2
-long do_hash_fault(struct pt_regs *regs);
extern int __hash_page_4K(unsigned long ea, unsigned long access,
unsigned long vsid, pte_t *ptep, unsigned long trap,
unsigned long flags, int ssize, int subpage_prot);
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 0363734ff56e..614957f74cee 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -50,15 +50,6 @@
#ifndef __ASSEMBLY__
-extern void replay_system_reset(void);
-extern void replay_soft_interrupts(void);
-
-extern void timer_interrupt(struct pt_regs *);
-extern void timer_broadcast_interrupt(void);
-extern void performance_monitor_exception(struct pt_regs *regs);
-extern void WatchdogException(struct pt_regs *regs);
-extern void unknown_exception(struct pt_regs *regs);
-
#ifdef CONFIG_PPC64
#include <asm/paca.h>
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
new file mode 100644
index 000000000000..5f6eeb6d43f2
--- /dev/null
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_INTERRUPT_H
+#define _ASM_POWERPC_INTERRUPT_H
+
+#include <linux/context_tracking.h>
+#include <asm/ftrace.h>
+
+/**
+ * DECLARE_INTERRUPT_HANDLER_RAW - Declare raw interrupt handler function
+ * @func: Function name of the entry point
+ * @returns: Returns a value back to asm caller
+ */
+#define DECLARE_INTERRUPT_HANDLER_RAW(func) \
+ __visible long func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER_RAW - Define raw interrupt handler function
+ * @func: Function name of the entry point
+ * @returns: Returns a value back to asm caller
+ *
+ * @func is called from ASM entry code.
+ *
+ * This is a plain function which does no tracing, reconciling, etc.
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ */
+#define DEFINE_INTERRUPT_HANDLER_RAW(func) \
+static __always_inline long ___##func(struct pt_regs *regs); \
+ \
+__visible noinstr long func(struct pt_regs *regs) \
+{ \
+ long ret; \
+ \
+ ret = ___##func (regs); \
+ \
+ return ret; \
+} \
+ \
+static __always_inline long ___##func(struct pt_regs *regs)
+
+/**
+ * DECLARE_INTERRUPT_HANDLER - Declare synchronous interrupt handler function
+ * @func: Function name of the entry point
+ */
+#define DECLARE_INTERRUPT_HANDLER(func) \
+ __visible void func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER - Define synchronous interrupt handler function
+ * @func: Function name of the entry point
+ *
+ * @func is called from ASM entry code.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ */
+#define DEFINE_INTERRUPT_HANDLER(func) \
+static __always_inline void ___##func(struct pt_regs *regs); \
+ \
+__visible noinstr void func(struct pt_regs *regs) \
+{ \
+ ___##func (regs); \
+} \
+ \
+static __always_inline void ___##func(struct pt_regs *regs)
+
+/**
+ * DECLARE_INTERRUPT_HANDLER_RET - Declare synchronous interrupt handler function
+ * @func: Function name of the entry point
+ * @returns: Returns a value back to asm caller
+ */
+#define DECLARE_INTERRUPT_HANDLER_RET(func) \
+ __visible long func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER_RET - Define synchronous interrupt handler function
+ * @func: Function name of the entry point
+ * @returns: Returns a value back to asm caller
+ *
+ * @func is called from ASM entry code.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ */
+#define DEFINE_INTERRUPT_HANDLER_RET(func) \
+static __always_inline long ___##func(struct pt_regs *regs); \
+ \
+__visible noinstr long func(struct pt_regs *regs) \
+{ \
+ long ret; \
+ \
+ ret = ___##func (regs); \
+ \
+ return ret; \
+} \
+ \
+static __always_inline long ___##func(struct pt_regs *regs)
+
+/**
+ * DECLARE_INTERRUPT_HANDLER_ASYNC - Declare asynchronous interrupt handler function
+ * @func: Function name of the entry point
+ */
+#define DECLARE_INTERRUPT_HANDLER_ASYNC(func) \
+ __visible void func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER_ASYNC - Define asynchronous interrupt handler function
+ * @func: Function name of the entry point
+ *
+ * @func is called from ASM entry code.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ */
+#define DEFINE_INTERRUPT_HANDLER_ASYNC(func) \
+static __always_inline void ___##func(struct pt_regs *regs); \
+ \
+__visible noinstr void func(struct pt_regs *regs) \
+{ \
+ ___##func (regs); \
+} \
+ \
+static __always_inline void ___##func(struct pt_regs *regs)
+
+/**
+ * DECLARE_INTERRUPT_HANDLER_NMI - Declare NMI interrupt handler function
+ * @func: Function name of the entry point
+ * @returns: Returns a value back to asm caller
+ */
+#define DECLARE_INTERRUPT_HANDLER_NMI(func) \
+ __visible long func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER_NMI - Define NMI interrupt handler function
+ * @func: Function name of the entry point
+ * @returns: Returns a value back to asm caller
+ *
+ * @func is called from ASM entry code.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ */
+#define DEFINE_INTERRUPT_HANDLER_NMI(func) \
+static __always_inline long ___##func(struct pt_regs *regs); \
+ \
+__visible noinstr long func(struct pt_regs *regs) \
+{ \
+ long ret; \
+ \
+ ret = ___##func (regs); \
+ \
+ return ret; \
+} \
+ \
+static __always_inline long ___##func(struct pt_regs *regs)
+
+
+/* Interrupt handlers */
+DECLARE_INTERRUPT_HANDLER_NMI(machine_check_early);
+DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode);
+DECLARE_INTERRUPT_HANDLER(SMIException);
+DECLARE_INTERRUPT_HANDLER(handle_hmi_exception);
+DECLARE_INTERRUPT_HANDLER(instruction_breakpoint_exception);
+DECLARE_INTERRUPT_HANDLER(RunModeException);
+DECLARE_INTERRUPT_HANDLER(single_step_exception);
+DECLARE_INTERRUPT_HANDLER(program_check_exception);
+DECLARE_INTERRUPT_HANDLER(alignment_exception);
+DECLARE_INTERRUPT_HANDLER(StackOverflow);
+DECLARE_INTERRUPT_HANDLER(stack_overflow_exception);
+DECLARE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(altivec_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(vsx_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(fp_unavailable_tm);
+DECLARE_INTERRUPT_HANDLER(altivec_unavailable_tm);
+DECLARE_INTERRUPT_HANDLER(vsx_unavailable_tm);
+DECLARE_INTERRUPT_HANDLER(facility_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
+DECLARE_INTERRUPT_HANDLER(altivec_assist_exception);
+DECLARE_INTERRUPT_HANDLER(unrecoverable_exception);
+DECLARE_INTERRUPT_HANDLER(kernel_bad_stack);
+DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception);
+#ifdef CONFIG_PPC_BOOK3S_64
+DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception);
+#else
+DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception);
+#endif
+DECLARE_INTERRUPT_HANDLER(emulation_assist_interrupt);
+DECLARE_INTERRUPT_HANDLER_RAW(do_slb_fault);
+DECLARE_INTERRUPT_HANDLER(do_bad_slb_fault);
+DECLARE_INTERRUPT_HANDLER_RET(do_hash_fault);
+DECLARE_INTERRUPT_HANDLER_RET(do_page_fault);
+DECLARE_INTERRUPT_HANDLER(do_bad_page_fault);
+
+DECLARE_INTERRUPT_HANDLER_ASYNC(timer_interrupt);
+DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi);
+DECLARE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async);
+DECLARE_INTERRUPT_HANDLER_RAW(performance_monitor_exception);
+DECLARE_INTERRUPT_HANDLER(WatchdogException);
+DECLARE_INTERRUPT_HANDLER(unknown_exception);
+DECLARE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception);
+
+void replay_system_reset(void);
+void replay_soft_interrupts(void);
+
+#endif /* _ASM_POWERPC_INTERRUPT_H */
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 2f566c1a754c..335d6fd589a7 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -131,6 +131,8 @@ DECLARE_PER_CPU(u64, decrementers_next_tb);
/* Convert timebase ticks to nanoseconds */
unsigned long long tb_to_ns(unsigned long long tb_ticks);
+void timer_broadcast_interrupt(void);
+
/* SPLPAR */
void accumulate_stolen_time(void);
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 52680cf07c9d..c0f99f8ffa7d 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -12,14 +12,14 @@
#include <linux/hardirq.h>
#include <asm/dbell.h>
+#include <asm/interrupt.h>
#include <asm/irq_regs.h>
#include <asm/kvm_ppc.h>
#include <asm/trace.h>
-#ifdef CONFIG_SMP
-
-void doorbell_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
{
+#ifdef CONFIG_SMP
struct pt_regs *old_regs = set_irq_regs(regs);
irq_enter();
@@ -37,11 +37,7 @@ void doorbell_exception(struct pt_regs *regs)
trace_doorbell_exit(regs);
irq_exit();
set_irq_regs(old_regs);
-}
#else /* CONFIG_SMP */
-void doorbell_exception(struct pt_regs *regs)
-{
printk(KERN_WARNING "Received doorbell on non-smp system\n");
-}
#endif /* CONFIG_SMP */
-
+}
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 77b730f515c4..f6ec455db13c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1923,7 +1923,7 @@ EXC_COMMON_BEGIN(doorbell_super_common)
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
#else
- bl unknown_exception
+ bl unknown_async_exception
#endif
b interrupt_return
@@ -2136,8 +2136,7 @@ EXC_COMMON_BEGIN(h_data_storage_common)
GEN_COMMON h_data_storage
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
- li r4,SIGSEGV
- bl bad_page_fault
+ bl do_bad_page_fault
MMU_FTR_SECTION_ELSE
bl unknown_exception
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
@@ -2310,7 +2309,7 @@ EXC_COMMON_BEGIN(h_doorbell_common)
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
#else
- bl unknown_exception
+ bl unknown_async_exception
#endif
b interrupt_return
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 5875f8795d5b..2185c6c89f33 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -240,8 +240,8 @@ __secondary_hold_acknowledge:
/* System reset */
/* core99 pmac starts the seconary here by changing the vector, and
- putting it back to what it was (unknown_exception) when done. */
- EXCEPTION(0x100, Reset, unknown_exception, EXC_XFER_STD)
+ putting it back to what it was (unknown_async_exception) when done. */
+ EXCEPTION(0x100, Reset, unknown_async_exception, EXC_XFER_STD)
/* Machine check */
/*
@@ -642,7 +642,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
#endif
#ifndef CONFIG_TAU_INT
-#define TAUException unknown_exception
+#define TAUException unknown_async_exception
#endif
EXCEPTION(0x1300, Trap_13, instruction_breakpoint_exception, EXC_XFER_STD)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 6b1eca53e36c..2055d204d08e 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -54,6 +54,7 @@
#include <linux/pgtable.h>
#include <linux/uaccess.h>
+#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/cache.h>
@@ -665,7 +666,7 @@ void __do_irq(struct pt_regs *regs)
irq_exit();
}
-void do_IRQ(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
{
struct pt_regs *old_regs = set_irq_regs(regs);
void *cursp, *irqsp, *sirqsp;
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 63702c0badb9..b84459f45b1a 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -18,6 +18,7 @@
#include <linux/extable.h>
#include <linux/ftrace.h>
+#include <asm/interrupt.h>
#include <asm/machdep.h>
#include <asm/mce.h>
#include <asm/nmi.h>
@@ -588,7 +589,7 @@ EXPORT_SYMBOL_GPL(machine_check_print_event_info);
*
* regs->nip and regs->msr contains srr0 and ssr1.
*/
-long notrace machine_check_early(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
{
long handled = 0;
u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
@@ -722,7 +723,7 @@ long hmi_handle_debugtrig(struct pt_regs *regs)
/*
* Return values:
*/
-long hmi_exception_realmode(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode)
{
int ret;
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 310bcd768cd5..16eb2b5dafde 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -5,6 +5,7 @@
#include <asm/kup.h>
#include <asm/cputime.h>
#include <asm/hw_irq.h>
+#include <asm/interrupt.h>
#include <asm/kprobes.h>
#include <asm/paca.h>
#include <asm/ptrace.h>
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 0b4694b8d248..46b2e5de4ef5 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -100,7 +100,7 @@ static void TAUupdate(int cpu)
* with interrupts disabled
*/
-void TAUException(struct pt_regs * regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(TAUException)
{
int cpu = smp_processor_id();
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 7d372ff3504b..0089df57bb49 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -56,6 +56,7 @@
#include <linux/processor.h>
#include <asm/trace.h>
+#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/nvram.h>
#include <asm/cache.h>
@@ -545,7 +546,7 @@ void arch_irq_work_raise(void)
* timer_interrupt - gets called when the decrementer overflows,
* with interrupts disabled.
*/
-void timer_interrupt(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
{
struct clock_event_device *evt = this_cpu_ptr(&decrementers);
u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 7dda72eb97cc..e726fe5c384d 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -41,6 +41,7 @@
#include <asm/emulated_ops.h>
#include <linux/uaccess.h>
#include <asm/debugfs.h>
+#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/machdep.h>
#include <asm/rtas.h>
@@ -436,8 +437,7 @@ void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
regs->msr &= ~MSR_RI;
#endif
}
-
-void system_reset_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
{
unsigned long hsrr0, hsrr1;
bool saved_hsrrs = false;
@@ -522,7 +522,10 @@ void system_reset_exception(struct pt_regs *regs)
this_cpu_set_ftrace_enabled(ftrace_enabled);
/* What should we do here? We could issue a shutdown or hard reset. */
+
+ return 0;
}
+NOKPROBE_SYMBOL(system_reset_exception);
/*
* I/O accesses can cause machine checks on powermacs.
@@ -819,7 +822,12 @@ int machine_check_generic(struct pt_regs *regs)
}
#endif /* everything else */
-void machine_check_exception(struct pt_regs *regs)
+
+#ifdef CONFIG_PPC_BOOK3S_64
+DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception)
+#else
+DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
+#endif
{
int recover = 0;
@@ -869,13 +877,21 @@ void machine_check_exception(struct pt_regs *regs)
if (!(regs->msr & MSR_RI))
die("Unrecoverable Machine check", regs, SIGBUS);
+#ifdef CONFIG_PPC_BOOK3S_64
+bail:
return;
+#else
+ return 0;
bail:
if (nmi) nmi_exit();
+
+ return 0;
+#endif
}
+NOKPROBE_SYMBOL(machine_check_exception);
-void SMIException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */
{
die("System Management Interrupt", regs, SIGABRT);
}
@@ -1061,7 +1077,7 @@ static void p9_hmi_special_emu(struct pt_regs *regs)
}
#endif /* CONFIG_VSX */
-void handle_hmi_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
{
struct pt_regs *old_regs;
@@ -1090,7 +1106,7 @@ void handle_hmi_exception(struct pt_regs *regs)
set_irq_regs(old_regs);
}
-void unknown_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(unknown_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1102,7 +1118,19 @@ void unknown_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void instruction_breakpoint_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
+{
+ enum ctx_state prev_state = exception_enter();
+
+ printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
+ regs->nip, regs->msr, regs->trap);
+
+ _exception(SIGTRAP, regs, TRAP_UNK, 0);
+
+ exception_exit(prev_state);
+}
+
+DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1117,12 +1145,12 @@ void instruction_breakpoint_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void RunModeException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(RunModeException)
{
_exception(SIGTRAP, regs, TRAP_UNK, 0);
}
-void single_step_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(single_step_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1465,7 +1493,7 @@ static int emulate_math(struct pt_regs *regs)
static inline int emulate_math(struct pt_regs *regs) { return -1; }
#endif
-void program_check_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(program_check_exception)
{
enum ctx_state prev_state = exception_enter();
unsigned int reason = get_reason(regs);
@@ -1590,14 +1618,14 @@ NOKPROBE_SYMBOL(program_check_exception);
* This occurs when running in hypervisor mode on POWER6 or later
* and an illegal instruction is encountered.
*/
-void emulation_assist_interrupt(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(emulation_assist_interrupt)
{
regs->msr |= REASON_ILLEGAL;
program_check_exception(regs);
}
NOKPROBE_SYMBOL(emulation_assist_interrupt);
-void alignment_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(alignment_exception)
{
enum ctx_state prev_state = exception_enter();
int sig, code, fixed = 0;
@@ -1647,7 +1675,7 @@ void alignment_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void StackOverflow(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(StackOverflow)
{
pr_crit("Kernel stack overflow in process %s[%d], r1=%lx\n",
current->comm, task_pid_nr(current), regs->gpr[1]);
@@ -1656,7 +1684,7 @@ void StackOverflow(struct pt_regs *regs)
panic("kernel stack overflow");
}
-void stack_overflow_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(stack_overflow_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1665,7 +1693,7 @@ void stack_overflow_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void kernel_fp_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1676,7 +1704,7 @@ void kernel_fp_unavailable_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void altivec_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(altivec_unavailable_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1695,7 +1723,7 @@ void altivec_unavailable_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void vsx_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
{
if (user_mode(regs)) {
/* A user program has executed an vsx instruction,
@@ -1726,7 +1754,7 @@ static void tm_unavailable(struct pt_regs *regs)
die("Unrecoverable TM Unavailable Exception", regs, SIGABRT);
}
-void facility_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(facility_unavailable_exception)
{
static char *facility_strings[] = {
[FSCR_FP_LG] = "FPU",
@@ -1846,7 +1874,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-void fp_unavailable_tm(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(fp_unavailable_tm)
{
/* Note: This does not handle any kind of FP laziness. */
@@ -1879,7 +1907,7 @@ void fp_unavailable_tm(struct pt_regs *regs)
tm_recheckpoint(¤t->thread);
}
-void altivec_unavailable_tm(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(altivec_unavailable_tm)
{
/* See the comments in fp_unavailable_tm(). This function operates
* the same way.
@@ -1894,7 +1922,7 @@ void altivec_unavailable_tm(struct pt_regs *regs)
current->thread.used_vr = 1;
}
-void vsx_unavailable_tm(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm)
{
/* See the comments in fp_unavailable_tm(). This works similarly,
* though we're loading both FP and VEC registers in here.
@@ -1919,7 +1947,8 @@ void vsx_unavailable_tm(struct pt_regs *regs)
}
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-static void performance_monitor_exception_nmi(struct pt_regs *regs)
+#ifdef CONFIG_PPC64
+DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
{
nmi_enter();
@@ -1928,9 +1957,12 @@ static void performance_monitor_exception_nmi(struct pt_regs *regs)
perf_irq(regs);
nmi_exit();
+
+ return 0;
}
+#endif
-static void performance_monitor_exception_async(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async)
{
irq_enter();
@@ -1941,7 +1973,7 @@ static void performance_monitor_exception_async(struct pt_regs *regs)
irq_exit();
}
-void performance_monitor_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RAW(performance_monitor_exception)
{
/*
* On 64-bit, if perf interrupts hit in a local_irq_disable
@@ -1953,6 +1985,8 @@ void performance_monitor_exception(struct pt_regs *regs)
performance_monitor_exception_nmi(regs);
else
performance_monitor_exception_async(regs);
+
+ return 0;
}
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -2086,7 +2120,7 @@ NOKPROBE_SYMBOL(DebugException);
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
#ifdef CONFIG_ALTIVEC
-void altivec_assist_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(altivec_assist_exception)
{
int err;
@@ -2228,7 +2262,7 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
* in the MSR is 0. This indicates that SRR0/1 are live, and that
* we therefore lost state by taking this exception.
*/
-void unrecoverable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(unrecoverable_exception)
{
pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
regs->trap, regs->nip, regs->msr);
@@ -2248,7 +2282,7 @@ void __attribute__ ((weak)) WatchdogHandler(struct pt_regs *regs)
return;
}
-void WatchdogException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(WatchdogException) /* XXX NMI? async? */
{
printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n");
WatchdogHandler(regs);
@@ -2259,7 +2293,7 @@ void WatchdogException(struct pt_regs *regs)
* We enter here if we discover during exception entry that we are
* running in supervisor mode with a userspace value in the stack pointer.
*/
-void kernel_bad_stack(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(kernel_bad_stack)
{
printk(KERN_EMERG "Bad kernel stack pointer %lx at %lx\n",
regs->gpr[1], regs->nip);
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index af3c15a1d41e..824b9376ac35 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -26,6 +26,7 @@
#include <linux/delay.h>
#include <linux/smp.h>
+#include <asm/interrupt.h>
#include <asm/paca.h>
/*
@@ -247,14 +248,14 @@ static void watchdog_timer_interrupt(int cpu)
watchdog_smp_panic(cpu, tb);
}
-void soft_nmi_interrupt(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
{
unsigned long flags;
int cpu = raw_smp_processor_id();
u64 tb;
if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
- return;
+ return 0;
nmi_enter();
@@ -291,6 +292,8 @@ void soft_nmi_interrupt(struct pt_regs *regs)
out:
nmi_exit();
+
+ return 0;
}
static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e3b1839fc251..01816de0e0ec 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -53,6 +53,7 @@
#include <asm/cputable.h>
#include <asm/cacheflush.h>
#include <linux/uaccess.h>
+#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8f58dd20b362..a2f3e6e70361 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -17,6 +17,7 @@
#include <asm/asm-prototypes.h>
#include <asm/cputable.h>
+#include <asm/interrupt.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/archrandom.h>
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index b1abcb816439..2a9817311ac1 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -20,6 +20,7 @@
#include <asm/cputable.h>
#include <linux/uaccess.h>
+#include <asm/interrupt.h>
#include <asm/kvm_ppc.h>
#include <asm/cacheflush.h>
#include <asm/dbell.h>
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 731518e7d56f..a48c484b9e9b 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -38,6 +38,7 @@
#include <linux/pgtable.h>
#include <asm/debugfs.h>
+#include <asm/interrupt.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
@@ -1510,7 +1511,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
}
EXPORT_SYMBOL_GPL(hash_page);
-long do_hash_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RET(do_hash_fault)
{
unsigned long ea = regs->dar;
unsigned long dsisr = regs->dsisr;
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index ae89ad516247..efac69e73ca8 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -10,6 +10,7 @@
*/
#include <asm/asm-prototypes.h>
+#include <asm/interrupt.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/paca.h>
@@ -837,7 +838,7 @@ static long slb_allocate_user(struct mm_struct *mm, unsigned long ea)
return slb_insert_entry(ea, context, flags, ssize, false);
}
-long do_slb_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RAW(do_slb_fault)
{
unsigned long ea = regs->dar;
unsigned long id = get_region_id(ea);
@@ -890,7 +891,7 @@ long do_slb_fault(struct pt_regs *regs)
}
}
-void do_bad_slb_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(do_bad_slb_fault)
{
int err = regs->result;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index e11989be8f1c..93663f7fbe9e 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -34,6 +34,7 @@
#include <linux/uaccess.h>
#include <asm/firmware.h>
+#include <asm/interrupt.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
@@ -549,7 +550,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
}
NOKPROBE_SYMBOL(__do_page_fault);
-long do_page_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
{
enum ctx_state prev_state = exception_enter();
unsigned long address = regs->dar;
@@ -656,3 +657,10 @@ void bad_page_fault(struct pt_regs *regs, int sig)
die("Kernel access of bad area", regs, sig);
}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+DEFINE_INTERRUPT_HANDLER(do_bad_page_fault)
+{
+ bad_page_fault(regs, SIGSEGV);
+}
+#endif
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 1ed7c5286487..2fc7049fef53 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -14,6 +14,7 @@
#include <asm/asm-prototypes.h>
#include <asm/firmware.h>
+#include <asm/interrupt.h>
#include <asm/machdep.h>
#include <asm/opal.h>
#include <asm/cputhreads.h>
--
2.23.0
^ permalink raw reply related
* [PATCH v3 06/19] powerpc: add interrupt wrapper entry / exit stub functions
From: Nicholas Piggin @ 2020-11-28 14:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
These will be used by subsequent patches.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 66 ++++++++++++++++++++++++++++
1 file changed, 66 insertions(+)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 5f6eeb6d43f2..516b32f5b3cc 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -5,6 +5,50 @@
#include <linux/context_tracking.h>
#include <asm/ftrace.h>
+struct interrupt_state {
+};
+
+static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+/*
+ * Care should be taken to note that interrupt_exit_prepare and
+ * interrupt_async_exit_prepare do not necessarily return immediately to
+ * regs context (e.g., if regs is usermode, we don't necessarily return to
+ * user mode). Other interrupts might be taken between here and return,
+ * context switch / preemption may occur in the exit path after this, or a
+ * signal may be delivered, etc.
+ *
+ * The real interrupt exit code is platform specific, e.g.,
+ * interrupt_exit_user_prepare / interrupt_exit_kernel_prepare for 64s.
+ *
+ * However interrupt_nmi_exit_prepare does return directly to regs, because
+ * NMIs do not do "exit work" or replay soft-masked interrupts.
+ */
+static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+struct interrupt_nmi_state {
+};
+
+static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
+{
+}
+
+static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
+{
+}
+
/**
* DECLARE_INTERRUPT_HANDLER_RAW - Declare raw interrupt handler function
* @func: Function name of the entry point
@@ -59,7 +103,13 @@ static __always_inline void ___##func(struct pt_regs *regs); \
\
__visible noinstr void func(struct pt_regs *regs) \
{ \
+ struct interrupt_state state; \
+ \
+ interrupt_enter_prepare(regs, &state); \
+ \
___##func (regs); \
+ \
+ interrupt_exit_prepare(regs, &state); \
} \
\
static __always_inline void ___##func(struct pt_regs *regs)
@@ -87,10 +137,15 @@ static __always_inline long ___##func(struct pt_regs *regs); \
\
__visible noinstr long func(struct pt_regs *regs) \
{ \
+ struct interrupt_state state; \
long ret; \
\
+ interrupt_enter_prepare(regs, &state); \
+ \
ret = ___##func (regs); \
\
+ interrupt_exit_prepare(regs, &state); \
+ \
return ret; \
} \
\
@@ -117,7 +172,13 @@ static __always_inline void ___##func(struct pt_regs *regs); \
\
__visible noinstr void func(struct pt_regs *regs) \
{ \
+ struct interrupt_state state; \
+ \
+ interrupt_async_enter_prepare(regs, &state); \
+ \
___##func (regs); \
+ \
+ interrupt_async_exit_prepare(regs, &state); \
} \
\
static __always_inline void ___##func(struct pt_regs *regs)
@@ -145,10 +206,15 @@ static __always_inline long ___##func(struct pt_regs *regs); \
\
__visible noinstr long func(struct pt_regs *regs) \
{ \
+ struct interrupt_nmi_state state; \
long ret; \
\
+ interrupt_nmi_enter_prepare(regs, &state); \
+ \
ret = ___##func (regs); \
\
+ interrupt_nmi_exit_prepare(regs, &state); \
+ \
return ret; \
} \
\
--
2.23.0
^ permalink raw reply related
* [PATCH v3 07/19] powerpc: add interrupt_cond_local_irq_enable helper
From: Nicholas Piggin @ 2020-11-28 14:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
Simple helper for synchronous interrupt handlers to use to enable
interrupts if they were taken in interrupt-enabled context.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 7 +++++++
arch/powerpc/kernel/traps.c | 24 +++++++-----------------
arch/powerpc/mm/fault.c | 4 +---
3 files changed, 15 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 516b32f5b3cc..2ab0675c27aa 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -3,6 +3,7 @@
#define _ASM_POWERPC_INTERRUPT_H
#include <linux/context_tracking.h>
+#include <linux/hardirq.h>
#include <asm/ftrace.h>
struct interrupt_state {
@@ -268,4 +269,10 @@ DECLARE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception);
void replay_system_reset(void);
void replay_soft_interrupts(void);
+static inline void interrupt_cond_local_irq_enable(struct pt_regs *regs)
+{
+ if (!arch_irq_disabled_regs(regs))
+ local_irq_enable();
+}
+
#endif /* _ASM_POWERPC_INTERRUPT_H */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index e726fe5c384d..8a6cb2838ce6 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -343,8 +343,8 @@ static bool exception_common(int signr, struct pt_regs *regs, int code,
show_signal_msg(signr, regs, code, addr);
- if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs))
- local_irq_enable();
+ if (arch_irqs_disabled())
+ interrupt_cond_local_irq_enable(regs);
current->thread.trap_nr = code;
@@ -1575,9 +1575,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
if (!user_mode(regs))
goto sigill;
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
/* (reason & REASON_ILLEGAL) would be the obvious thing here,
* but there seems to be a hardware bug on the 405GP (RevD)
@@ -1631,9 +1629,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
int sig, code, fixed = 0;
unsigned long reason;
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
reason = get_reason(regs);
@@ -1794,9 +1790,7 @@ DEFINE_INTERRUPT_HANDLER(facility_unavailable_exception)
die("Unexpected facility unavailable exception", regs, SIGABRT);
}
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
if (status == FSCR_DSCR_LG) {
/*
@@ -2176,9 +2170,7 @@ void SPEFloatingPointException(struct pt_regs *regs)
int code = FPE_FLTUNK;
int err;
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
flush_spe_to_thread(current);
@@ -2225,9 +2217,7 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
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();
+ interrupt_cond_local_irq_enable(regs);
preempt_disable();
if (regs->msr & MSR_SPE)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 93663f7fbe9e..4896f44c8374 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -443,9 +443,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
return bad_area_nosemaphore(regs, address);
}
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
--
2.23.0
^ permalink raw reply related
* [PATCH v3 08/19] powerpc/64: context tracking remove _TIF_NOHZ
From: Nicholas Piggin @ 2020-11-28 14:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
Add context tracking to the system call handler explicitly, and remove
_TIF_NOHZ.
This saves 35 cycles on gettid system call cost on POWER9 with a
CONFIG_NOHZ_FULL kernel.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/Kconfig | 6 ------
arch/powerpc/Kconfig | 1 -
arch/powerpc/include/asm/thread_info.h | 4 +---
arch/powerpc/kernel/ptrace/ptrace.c | 4 ----
arch/powerpc/kernel/signal.c | 4 ----
arch/powerpc/kernel/syscall_64.c | 10 ++++++++++
6 files changed, 11 insertions(+), 18 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 56b6ccc0e32d..a0b6213f7820 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -618,12 +618,6 @@ config HAVE_CONTEXT_TRACKING
protected inside rcu_irq_enter/rcu_irq_exit() but preemption or signal
handling on irq exit still need to be protected.
-config HAVE_TIF_NOHZ
- bool
- help
- Arch relies on TIF_NOHZ and syscall slow path to implement context
- tracking calls to user_enter()/user_exit().
-
config HAVE_VIRT_CPU_ACCOUNTING
bool
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index e9f13fe08492..6eaf12a504f8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -193,7 +193,6 @@ config PPC
select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
select HAVE_CONTEXT_TRACKING if PPC64
- select HAVE_TIF_NOHZ if PPC64
select HAVE_DEBUG_KMEMLEAK
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_DYNAMIC_FTRACE
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 46a210b03d2b..c9443c16e5fb 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -95,7 +95,6 @@ void arch_setup_new_exec(void);
#define TIF_PATCH_PENDING 6 /* pending live patching update */
#define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
#define TIF_SINGLESTEP 8 /* singlestepping active */
-#define TIF_NOHZ 9 /* in adaptive nohz mode */
#define TIF_SECCOMP 10 /* secure computing */
#define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */
#define TIF_NOERROR 12 /* Force successful syscall return */
@@ -128,11 +127,10 @@ void arch_setup_new_exec(void);
#define _TIF_UPROBE (1<<TIF_UPROBE)
#define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT)
#define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE)
-#define _TIF_NOHZ (1<<TIF_NOHZ)
#define _TIF_SYSCALL_EMU (1<<TIF_SYSCALL_EMU)
#define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
- _TIF_NOHZ | _TIF_SYSCALL_EMU)
+ _TIF_SYSCALL_EMU)
#define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
_TIF_NOTIFY_RESUME | _TIF_UPROBE | \
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index f6e51be47c6e..8970400e521c 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -290,8 +290,6 @@ long do_syscall_trace_enter(struct pt_regs *regs)
{
u32 flags;
- user_exit();
-
flags = READ_ONCE(current_thread_info()->flags) &
(_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
@@ -368,8 +366,6 @@ void do_syscall_trace_leave(struct pt_regs *regs)
step = test_thread_flag(TIF_SINGLESTEP);
if (step || test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, step);
-
- user_enter();
}
void __init pt_regs_check(void);
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index d2c356f37077..44ec7b34b27e 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -310,8 +310,6 @@ static void do_signal(struct task_struct *tsk)
void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
{
- user_exit();
-
if (thread_info_flags & _TIF_UPROBE)
uprobe_notify_resume(regs);
@@ -327,8 +325,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
tracehook_notify_resume(regs);
rseq_handle_notify_resume(NULL, regs);
}
-
- user_enter();
}
unsigned long get_tm_stackpointer(struct task_struct *tsk)
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 16eb2b5dafde..9e855b25bd15 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -1,9 +1,11 @@
// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/context_tracking.h>
#include <linux/err.h>
#include <asm/asm-prototypes.h>
#include <asm/kup.h>
#include <asm/cputime.h>
+#include <asm/interrupt.h>
#include <asm/hw_irq.h>
#include <asm/interrupt.h>
#include <asm/kprobes.h>
@@ -28,6 +30,9 @@ notrace long system_call_exception(long r3, long r4, long r5,
if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+ CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
+ user_exit_irqoff();
+
trace_hardirqs_off(); /* finish reconciling */
if (IS_ENABLED(CONFIG_PPC_BOOK3S))
@@ -158,6 +163,8 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
unsigned long ti_flags;
unsigned long ret = 0;
+ CT_WARN_ON(ct_state() == CONTEXT_USER);
+
kuap_check_amr();
regs->result = r3;
@@ -234,8 +241,11 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
}
}
+ user_enter_irqoff();
+
/* scv need not set RI=0 because SRRs are not used */
if (unlikely(!prep_irq_for_enabled_exit(!scv))) {
+ user_exit_irqoff();
local_irq_enable();
goto again;
}
--
2.23.0
^ permalink raw reply related
* [PATCH v3 09/19] powerpc/64: context tracking move to interrupt wrappers
From: Nicholas Piggin @ 2020-11-28 14:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
This moves exception_enter/exit calls to wrapper functions for
synchronous interrupts. More interrupt handlers are covered by
this than previously.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 9 ++++
arch/powerpc/kernel/traps.c | 74 ++++++---------------------
arch/powerpc/mm/book3s64/hash_utils.c | 2 -
arch/powerpc/mm/fault.c | 3 --
4 files changed, 26 insertions(+), 62 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 2ab0675c27aa..e2410f54c6e9 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -7,10 +7,16 @@
#include <asm/ftrace.h>
struct interrupt_state {
+#ifdef CONFIG_PPC64
+ enum ctx_state ctx_state;
+#endif
};
static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+#ifdef CONFIG_PPC64
+ state->ctx_state = exception_enter();
+#endif
}
/*
@@ -29,6 +35,9 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
*/
static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+#ifdef CONFIG_PPC64
+ exception_exit(state->ctx_state);
+#endif
}
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 8a6cb2838ce6..f40b45086b93 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1108,41 +1108,28 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
DEFINE_INTERRUPT_HANDLER(unknown_exception)
{
- enum ctx_state prev_state = exception_enter();
-
printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
regs->nip, regs->msr, regs->trap);
_exception(SIGTRAP, regs, TRAP_UNK, 0);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
{
- enum ctx_state prev_state = exception_enter();
-
printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
regs->nip, regs->msr, regs->trap);
_exception(SIGTRAP, regs, TRAP_UNK, 0);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
{
- enum ctx_state prev_state = exception_enter();
-
if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
5, SIGTRAP) == NOTIFY_STOP)
- goto bail;
+ return;
if (debugger_iabr_match(regs))
- goto bail;
+ return;
_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-
-bail:
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(RunModeException)
@@ -1152,8 +1139,6 @@ DEFINE_INTERRUPT_HANDLER(RunModeException)
DEFINE_INTERRUPT_HANDLER(single_step_exception)
{
- enum ctx_state prev_state = exception_enter();
-
clear_single_step(regs);
clear_br_trace(regs);
@@ -1162,14 +1147,11 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
if (notify_die(DIE_SSTEP, "single_step", regs, 5,
5, SIGTRAP) == NOTIFY_STOP)
- goto bail;
+ return;
if (debugger_sstep(regs))
- goto bail;
+ return;
_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
-
-bail:
- exception_exit(prev_state);
}
NOKPROBE_SYMBOL(single_step_exception);
@@ -1495,7 +1477,6 @@ static inline int emulate_math(struct pt_regs *regs) { return -1; }
DEFINE_INTERRUPT_HANDLER(program_check_exception)
{
- enum ctx_state prev_state = exception_enter();
unsigned int reason = get_reason(regs);
/* We can now get here via a FP Unavailable exception if the core
@@ -1504,22 +1485,22 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
if (reason & REASON_FP) {
/* IEEE FP exception */
parse_fpe(regs);
- goto bail;
+ return;
}
if (reason & REASON_TRAP) {
unsigned long bugaddr;
/* Debugger is first in line to stop recursive faults in
* rcu_lock, notify_die, or atomic_notifier_call_chain */
if (debugger_bpt(regs))
- goto bail;
+ return;
if (kprobe_handler(regs))
- goto bail;
+ return;
/* trap exception */
if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP)
== NOTIFY_STOP)
- goto bail;
+ return;
bugaddr = regs->nip;
/*
@@ -1531,10 +1512,10 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
if (!(regs->msr & MSR_PR) && /* not user-mode */
report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
regs->nip += 4;
- goto bail;
+ return;
}
_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
- goto bail;
+ return;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (reason & REASON_TM) {
@@ -1555,7 +1536,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
*/
if (user_mode(regs)) {
_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
- goto bail;
+ return;
} else {
printk(KERN_EMERG "Unexpected TM Bad Thing exception "
"at %lx (msr 0x%lx) tm_scratch=%llx\n",
@@ -1586,7 +1567,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
* pattern to occurrences etc. -dgibson 31/Mar/2003
*/
if (!emulate_math(regs))
- goto bail;
+ return;
/* Try to emulate it if we should. */
if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
@@ -1594,10 +1575,10 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
case 0:
regs->nip += 4;
emulate_single_step(regs);
- goto bail;
+ return;
case -EFAULT:
_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
- goto bail;
+ return;
}
}
@@ -1606,9 +1587,6 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
else
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-
-bail:
- exception_exit(prev_state);
}
NOKPROBE_SYMBOL(program_check_exception);
@@ -1625,14 +1603,12 @@ NOKPROBE_SYMBOL(emulation_assist_interrupt);
DEFINE_INTERRUPT_HANDLER(alignment_exception)
{
- enum ctx_state prev_state = exception_enter();
int sig, code, fixed = 0;
unsigned long reason;
interrupt_cond_local_irq_enable(regs);
reason = get_reason(regs);
-
if (reason & REASON_BOUNDARY) {
sig = SIGBUS;
code = BUS_ADRALN;
@@ -1640,7 +1616,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
}
if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
- goto bail;
+ return;
/* we don't implement logging of alignment exceptions */
if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
@@ -1650,7 +1626,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
/* skip over emulated instruction */
regs->nip += inst_length(reason);
emulate_single_step(regs);
- goto bail;
+ return;
}
/* Operand address was bad */
@@ -1666,9 +1642,6 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
_exception(sig, regs, code, regs->dar);
else
bad_page_fault(regs, sig);
-
-bail:
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(StackOverflow)
@@ -1682,41 +1655,28 @@ DEFINE_INTERRUPT_HANDLER(StackOverflow)
DEFINE_INTERRUPT_HANDLER(stack_overflow_exception)
{
- enum ctx_state prev_state = exception_enter();
-
die("Kernel stack overflow", regs, SIGSEGV);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception)
{
- enum ctx_state prev_state = exception_enter();
-
printk(KERN_EMERG "Unrecoverable FP Unavailable Exception "
"%lx at %lx\n", regs->trap, regs->nip);
die("Unrecoverable FP Unavailable Exception", regs, SIGABRT);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(altivec_unavailable_exception)
{
- enum ctx_state prev_state = exception_enter();
-
if (user_mode(regs)) {
/* A user program has executed an altivec instruction,
but this kernel doesn't support altivec. */
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
- goto bail;
+ return;
}
printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
"%lx at %lx\n", regs->trap, regs->nip);
die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
-
-bail:
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index a48c484b9e9b..39dcfaf7ba36 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1289,7 +1289,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
unsigned long flags)
{
bool is_thp;
- enum ctx_state prev_state = exception_enter();
pgd_t *pgdir;
unsigned long vsid;
pte_t *ptep;
@@ -1489,7 +1488,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
DBG_LOW(" -> rc=%d\n", rc);
bail:
- exception_exit(prev_state);
return rc;
}
EXPORT_SYMBOL_GPL(hash_page_mm);
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 4896f44c8374..2778fe0a41d5 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -550,7 +550,6 @@ NOKPROBE_SYMBOL(__do_page_fault);
DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
{
- enum ctx_state prev_state = exception_enter();
unsigned long address = regs->dar;
unsigned long error_code = regs->dsisr;
long err;
@@ -573,8 +572,6 @@ DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
}
#endif
- exception_exit(prev_state);
-
return err;
}
NOKPROBE_SYMBOL(do_page_fault);
--
2.23.0
^ permalink raw reply related
* [PATCH v3 10/19] powerpc/64: add context tracking to asynchronous interrupts
From: Nicholas Piggin @ 2020-11-28 14:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
Previously context tracking was not done for asynchronous interrupts,
(those that run in interrupt context), and if those would cause a
reschedule when they exit, then scheduling functions (schedule_user,
preempt_schedule_irq) call exception_enter/exit to fix this up and
exit user context.
This is a hack we would like to get away from, so do context tracking
for asynchronous interrupts too.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index e2410f54c6e9..8f7db1c8cbe0 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -42,10 +42,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+ interrupt_enter_prepare(regs, state);
}
static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+ interrupt_exit_prepare(regs, state);
}
struct interrupt_nmi_state {
--
2.23.0
^ permalink raw reply related
* [PATCH v3 13/19] powerpc/64s: reconcile interrupts in C
From: Nicholas Piggin @ 2020-11-28 14:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
There is no need for this to be in asm, use the new intrrupt entry wrapper.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 15 +++++++++++----
arch/powerpc/kernel/exceptions-64s.S | 26 --------------------------
2 files changed, 11 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 542ad8e9c313..c31fa26b3f60 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -14,11 +14,14 @@ struct interrupt_state {
static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
-#ifdef CONFIG_PPC_BOOK3E_64
- state->ctx_state = exception_enter();
-#endif
-
+ /*
+ * Book3E reconciles irq soft mask in asm
+ */
#ifdef CONFIG_PPC_BOOK3S_64
+ if (irq_soft_mask_set_return(IRQS_ALL_DISABLED) == IRQS_ENABLED)
+ trace_hardirqs_off();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
if (user_mode(regs)) {
CT_WARN_ON(ct_state() != CONTEXT_USER);
user_exit_irqoff();
@@ -31,6 +34,10 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
}
#endif
+
+#ifdef CONFIG_PPC_BOOK3E_64
+ state->ctx_state = exception_enter();
+#endif
}
/*
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f6ec455db13c..647b7743bc9c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -139,7 +139,6 @@ name:
#define IKVM_VIRT .L_IKVM_VIRT_\name\() /* Virt entry tests KVM */
#define ISTACK .L_ISTACK_\name\() /* Set regular kernel stack */
#define __ISTACK(name) .L_ISTACK_ ## name
-#define IRECONCILE .L_IRECONCILE_\name\() /* Do RECONCILE_IRQ_STATE */
#define IKUAP .L_IKUAP_\name\() /* Do KUAP lock */
#define INT_DEFINE_BEGIN(n) \
@@ -203,9 +202,6 @@ do_define_int n
.ifndef ISTACK
ISTACK=1
.endif
- .ifndef IRECONCILE
- IRECONCILE=1
- .endif
.ifndef IKUAP
IKUAP=1
.endif
@@ -653,10 +649,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.if ISTACK
ACCOUNT_STOLEN_TIME
.endif
-
- .if IRECONCILE
- RECONCILE_IRQ_STATE(r10, r11)
- .endif
.endm
/*
@@ -935,7 +927,6 @@ INT_DEFINE_BEGIN(system_reset)
*/
ISET_RI=0
ISTACK=0
- IRECONCILE=0
IKVM_REAL=1
INT_DEFINE_END(system_reset)
@@ -1123,7 +1114,6 @@ INT_DEFINE_BEGIN(machine_check_early)
ISTACK=0
IDAR=1
IDSISR=1
- IRECONCILE=0
IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
INT_DEFINE_END(machine_check_early)
@@ -1476,7 +1466,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
INT_DEFINE_BEGIN(data_access_slb)
IVEC=0x380
IAREA=PACA_EXSLB
- IRECONCILE=0
IDAR=1
IKVM_SKIP=1
IKVM_REAL=1
@@ -1503,7 +1492,6 @@ MMU_FTR_SECTION_ELSE
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
@@ -1565,7 +1553,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
INT_DEFINE_BEGIN(instruction_access_slb)
IVEC=0x480
IAREA=PACA_EXSLB
- IRECONCILE=0
IISIDE=1
IDAR=1
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@@ -1594,7 +1581,6 @@ MMU_FTR_SECTION_ELSE
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
@@ -1754,7 +1740,6 @@ EXC_COMMON_BEGIN(program_check_common)
*/
INT_DEFINE_BEGIN(fp_unavailable)
IVEC=0x800
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
@@ -1769,7 +1754,6 @@ EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
EXC_COMMON_BEGIN(fp_unavailable_common)
GEN_COMMON fp_unavailable
bne 1f /* if from user, just load it up */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_fp_unavailable_exception
0: trap
@@ -1788,7 +1772,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl fp_unavailable_tm
b interrupt_return
@@ -1853,7 +1836,6 @@ INT_DEFINE_BEGIN(hdecrementer)
IVEC=0x980
IHSRR=1
ISTACK=0
- IRECONCILE=0
IKVM_REAL=1
IKVM_VIRT=1
INT_DEFINE_END(hdecrementer)
@@ -2227,7 +2209,6 @@ INT_DEFINE_BEGIN(hmi_exception_early)
IHSRR=1
IREALMODE_COMMON=1
ISTACK=0
- IRECONCILE=0
IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
IKVM_REAL=1
INT_DEFINE_END(hmi_exception_early)
@@ -2401,7 +2382,6 @@ EXC_COMMON_BEGIN(performance_monitor_common)
*/
INT_DEFINE_BEGIN(altivec_unavailable)
IVEC=0xf20
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
@@ -2431,7 +2411,6 @@ BEGIN_FTR_SECTION
b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_tm
b interrupt_return
@@ -2439,7 +2418,6 @@ BEGIN_FTR_SECTION
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_exception
b interrupt_return
@@ -2455,7 +2433,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
*/
INT_DEFINE_BEGIN(vsx_unavailable)
IVEC=0xf40
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
@@ -2484,7 +2461,6 @@ BEGIN_FTR_SECTION
b load_up_vsx
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_tm
b interrupt_return
@@ -2492,7 +2468,6 @@ BEGIN_FTR_SECTION
1:
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_exception
b interrupt_return
@@ -2827,7 +2802,6 @@ EXC_VIRT_NONE(0x5800, 0x100)
INT_DEFINE_BEGIN(soft_nmi)
IVEC=0x900
ISTACK=0
- IRECONCILE=0 /* Soft-NMI may fire under local_irq_disable */
INT_DEFINE_END(soft_nmi)
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v3 11/19] powerpc: handle irq_enter/irq_exit in interrupt handler wrappers
From: Nicholas Piggin @ 2020-11-28 14:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20201128144114.944000-1-npiggin@gmail.com>
Move irq_enter/irq_exit into asynchronous interrupt handler wrappers.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 2 ++
arch/powerpc/kernel/dbell.c | 3 +--
arch/powerpc/kernel/irq.c | 4 ----
arch/powerpc/kernel/tau_6xx.c | 3 ---
arch/powerpc/kernel/time.c | 4 ++--
arch/powerpc/kernel/traps.c | 6 ------
6 files changed, 5 insertions(+), 17 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 8f7db1c8cbe0..21acf0d0154f 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -43,10 +43,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
interrupt_enter_prepare(regs, state);
+ irq_enter();
}
static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+ irq_exit();
interrupt_exit_prepare(regs, state);
}
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index c0f99f8ffa7d..84ee9c511459 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -22,7 +22,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
#ifdef CONFIG_SMP
struct pt_regs *old_regs = set_irq_regs(regs);
- irq_enter();
trace_doorbell_entry(regs);
ppc_msgsync();
@@ -35,7 +34,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
smp_ipi_demux_relaxed(); /* already performed the barrier */
trace_doorbell_exit(regs);
- irq_exit();
+
set_irq_regs(old_regs);
#else /* CONFIG_SMP */
printk(KERN_WARNING "Received doorbell on non-smp system\n");
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 2055d204d08e..681abb7c0507 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -641,8 +641,6 @@ void __do_irq(struct pt_regs *regs)
{
unsigned int irq;
- irq_enter();
-
trace_irq_entry(regs);
/*
@@ -662,8 +660,6 @@ void __do_irq(struct pt_regs *regs)
generic_handle_irq(irq);
trace_irq_exit(regs);
-
- irq_exit();
}
DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 46b2e5de4ef5..d864f07bab74 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -104,12 +104,9 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(TAUException)
{
int cpu = smp_processor_id();
- irq_enter();
tau[cpu].interrupts++;
TAUupdate(cpu);
-
- irq_exit();
}
#endif /* CONFIG_TAU_INT */
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0089df57bb49..7dd0ab55e700 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -585,7 +585,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
#endif
old_regs = set_irq_regs(regs);
- irq_enter();
+
trace_timer_interrupt_entry(regs);
if (test_irq_work_pending()) {
@@ -610,7 +610,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
}
trace_timer_interrupt_exit(regs);
- irq_exit();
+
set_irq_regs(old_regs);
}
EXPORT_SYMBOL(timer_interrupt);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f40b45086b93..06b638a7f0b0 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1082,7 +1082,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
struct pt_regs *old_regs;
old_regs = set_irq_regs(regs);
- irq_enter();
#ifdef CONFIG_VSX
/* Real mode flagged P9 special emu is needed */
@@ -1102,7 +1101,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
if (ppc_md.handle_hmi_exception)
ppc_md.handle_hmi_exception(regs);
- irq_exit();
set_irq_regs(old_regs);
}
@@ -1918,13 +1916,9 @@ DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async)
{
- irq_enter();
-
__this_cpu_inc(irq_stat.pmu_irqs);
perf_irq(regs);
-
- irq_exit();
}
DEFINE_INTERRUPT_HANDLER_RAW(performance_monitor_exception)
--
2.23.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox