- Linux-stable-mirror - lists.linaro.org

[PATCH v2 1/2] gpiolib-acpi: Only defer request_irq for GpioInt ACPI event handlers

by Hans de Goede

Commit 78d3a92edbfb ("gpiolib-acpi: Register GpioInt ACPI event handlers from a late_initcall") deferred the entire acpi_gpiochip_request_interrupt call for each event resource. This means it also delays the gpiochip_request_own_desc(..., "ACPI:Event") call. This is a problem if some AML code reads the GPIO pin before we run the deferred acpi_gpiochip_request_interrupt, because in that case acpi_gpio_adr_space_handler() will already have called gpiochip_request_own_desc(..., "ACPI:OpRegion") causing the call from acpi_gpiochip_request_interrupt to fail with -EBUSY and we will fail to register an event handler. acpi_gpio_adr_space_handler is prepared for acpi_gpiochip_request_interrupt already having claimed the pin, but the other way around does not work. One example of a problem this causes, is the event handler for the OTG ID pin on a Prowise PT301 tablet not registering, keeping the port stuck in whatever mode it was in during boot and e.g. only allowing charging after a reboot. This commit fixes this by only deferring the request_irq call and the initial run of edge-triggered IRQs instead of deferring all of acpi_gpiochip_request_interrupt. Cc: stable(a)vger.kernel.org Fixes: 78d3a92edbfb ("gpiolib-acpi: Register GpioInt ACPI event ...") Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> --- Changes in v2: -add kernel-doc describing struct acpi_gpio_event members (requested by Mika) -s/acpi_gpiochip_request_interrupt_desc/acpi_gpiochip_alloc_event/ (req Mika) -minor style fixups (requested by Andy) --- drivers/gpio/gpiolib-acpi.c | 144 +++++++++++++++++++++--------------- 1 file changed, 84 insertions(+), 60 deletions(-) diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 55b72fbe1631..7f93954c58ea 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -19,11 +19,28 @@ #include "gpiolib.h" +/** + * struct acpi_gpio_event - ACPI GPIO event handler data + * + * @node: list-entry of the events list of the struct acpi_gpio_chip + * @handle: handle of ACPI method to execute when the IRQ triggers + * @handler: irq_handler to pass to request_irq when requesting the IRQ + * @pin: GPIO pin number on the gpio_chip + * @irq: Linux IRQ number for the event, for request_ / free_irq + * @irqflags: flags to pass to request_irq when requesting the IRQ + * @irq_is_wake: If the ACPI flags indicate the IRQ is a wakeup source + * @is_requested: True if request_irq has been done + * @desc: gpio_desc for the GPIO pin for this event + */ struct acpi_gpio_event { struct list_head node; acpi_handle handle; + irq_handler_t handler; unsigned int pin; unsigned int irq; + unsigned long irqflags; + bool irq_is_wake; + bool irq_requested; struct gpio_desc *desc; }; @@ -49,10 +66,10 @@ struct acpi_gpio_chip { /* * For gpiochips which call acpi_gpiochip_request_interrupts() before late_init - * (so builtin drivers) we register the ACPI GpioInt event handlers from a + * (so builtin drivers) we register the ACPI GpioInt IRQ handlers from a * late_initcall_sync handler, so that other builtin drivers can register their * OpRegions before the event handlers can run. This list contains gpiochips - * for which the acpi_gpiochip_request_interrupts() has been deferred. + * for which the acpi_gpiochip_request_irqs() call has been deferred. */ static DEFINE_MUTEX(acpi_gpio_deferred_req_irqs_lock); static LIST_HEAD(acpi_gpio_deferred_req_irqs_list); @@ -133,8 +150,42 @@ bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, } EXPORT_SYMBOL_GPL(acpi_gpio_get_irq_resource); -static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, - void *context) +static void acpi_gpiochip_request_irq(struct acpi_gpio_chip *acpi_gpio, + struct acpi_gpio_event *event) +{ + int ret, value; + + ret = request_threaded_irq(event->irq, NULL, event->handler, + event->irqflags, "ACPI:Event", event); + if (ret) { + dev_err(acpi_gpio->chip->parent, + "Failed to setup interrupt handler for %d\n", + event->irq); + return; + } + + if (event->irq_is_wake) + enable_irq_wake(event->irq); + + event->irq_requested = true; + + /* Make sure we trigger the initial state of edge-triggered IRQs */ + value = gpiod_get_raw_value_cansleep(event->desc); + if (((event->irqflags & IRQF_TRIGGER_RISING) && value == 1) || + ((event->irqflags & IRQF_TRIGGER_FALLING) && value == 0)) + event->handler(event->irq, event); +} + +static void acpi_gpiochip_request_irqs(struct acpi_gpio_chip *acpi_gpio) +{ + struct acpi_gpio_event *event; + + list_for_each_entry(event, &acpi_gpio->events, node) + acpi_gpiochip_request_irq(acpi_gpio, event); +} + +static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, + void *context) { struct acpi_gpio_chip *acpi_gpio = context; struct gpio_chip *chip = acpi_gpio->chip; @@ -143,8 +194,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, struct acpi_gpio_event *event; irq_handler_t handler = NULL; struct gpio_desc *desc; - unsigned long irqflags; - int ret, pin, irq, value; + int ret, pin, irq; if (!acpi_gpio_get_irq_resource(ares, &agpio)) return AE_OK; @@ -175,8 +225,6 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, gpiod_direction_input(desc); - value = gpiod_get_value_cansleep(desc); - ret = gpiochip_lock_as_irq(chip, pin); if (ret) { dev_err(chip->parent, "Failed to lock GPIO as interrupt\n"); @@ -189,64 +237,42 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, goto fail_unlock_irq; } - irqflags = IRQF_ONESHOT; + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + goto fail_unlock_irq; + + event->irqflags = IRQF_ONESHOT; if (agpio->triggering == ACPI_LEVEL_SENSITIVE) { if (agpio->polarity == ACPI_ACTIVE_HIGH) - irqflags |= IRQF_TRIGGER_HIGH; + event->irqflags |= IRQF_TRIGGER_HIGH; else - irqflags |= IRQF_TRIGGER_LOW; + event->irqflags |= IRQF_TRIGGER_LOW; } else { switch (agpio->polarity) { case ACPI_ACTIVE_HIGH: - irqflags |= IRQF_TRIGGER_RISING; + event->irqflags |= IRQF_TRIGGER_RISING; break; case ACPI_ACTIVE_LOW: - irqflags |= IRQF_TRIGGER_FALLING; + event->irqflags |= IRQF_TRIGGER_FALLING; break; default: - irqflags |= IRQF_TRIGGER_RISING | - IRQF_TRIGGER_FALLING; + event->irqflags |= IRQF_TRIGGER_RISING | + IRQF_TRIGGER_FALLING; break; } } - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (!event) - goto fail_unlock_irq; - event->handle = evt_handle; + event->handler = handler; event->irq = irq; + event->irq_is_wake = agpio->wake_capable == ACPI_WAKE_CAPABLE; event->pin = pin; event->desc = desc; - ret = request_threaded_irq(event->irq, NULL, handler, irqflags, - "ACPI:Event", event); - if (ret) { - dev_err(chip->parent, - "Failed to setup interrupt handler for %d\n", - event->irq); - goto fail_free_event; - } - - if (agpio->wake_capable == ACPI_WAKE_CAPABLE) - enable_irq_wake(irq); - list_add_tail(&event->node, &acpi_gpio->events); - /* - * Make sure we trigger the initial state of the IRQ when using RISING - * or FALLING. Note we run the handlers on late_init, the AML code - * may refer to OperationRegions from other (builtin) drivers which - * may be probed after us. - */ - if (((irqflags & IRQF_TRIGGER_RISING) && value == 1) || - ((irqflags & IRQF_TRIGGER_FALLING) && value == 0)) - handler(event->irq, event); - return AE_OK; -fail_free_event: - kfree(event); fail_unlock_irq: gpiochip_unlock_as_irq(chip, pin); fail_free_desc: @@ -283,6 +309,9 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) if (ACPI_FAILURE(status)) return; + acpi_walk_resources(handle, "_AEI", + acpi_gpiochip_alloc_event, acpi_gpio); + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); defer = !acpi_gpio_deferred_req_irqs_done; if (defer) @@ -293,8 +322,7 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) if (defer) return; - acpi_walk_resources(handle, "_AEI", - acpi_gpiochip_request_interrupt, acpi_gpio); + acpi_gpiochip_request_irqs(acpi_gpio); } EXPORT_SYMBOL_GPL(acpi_gpiochip_request_interrupts); @@ -331,10 +359,13 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) { struct gpio_desc *desc; - if (irqd_is_wakeup_set(irq_get_irq_data(event->irq))) - disable_irq_wake(event->irq); + if (event->irq_requested) { + if (event->irq_is_wake) + disable_irq_wake(event->irq); + + free_irq(event->irq, event); + } - free_irq(event->irq, event); desc = event->desc; if (WARN_ON(IS_ERR(desc))) continue; @@ -1200,23 +1231,16 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) return con_id == NULL; } -/* Run deferred acpi_gpiochip_request_interrupts() */ -static int acpi_gpio_handle_deferred_request_interrupts(void) +/* Run deferred acpi_gpiochip_request_irqs() */ +static int acpi_gpio_handle_deferred_request_irqs(void) { struct acpi_gpio_chip *acpi_gpio, *tmp; mutex_lock(&acpi_gpio_deferred_req_irqs_lock); list_for_each_entry_safe(acpi_gpio, tmp, &acpi_gpio_deferred_req_irqs_list, - deferred_req_irqs_list_entry) { - acpi_handle handle; - - handle = ACPI_HANDLE(acpi_gpio->chip->parent); - acpi_walk_resources(handle, "_AEI", - acpi_gpiochip_request_interrupt, acpi_gpio); - - list_del_init(&acpi_gpio->deferred_req_irqs_list_entry); - } + deferred_req_irqs_list_entry) + acpi_gpiochip_request_irqs(acpi_gpio); acpi_gpio_deferred_req_irqs_done = true; mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); @@ -1224,4 +1248,4 @@ static int acpi_gpio_handle_deferred_request_interrupts(void) return 0; } /* We must use _sync so that this runs after the first deferred_probe run */ -late_initcall_sync(acpi_gpio_handle_deferred_request_interrupts); +late_initcall_sync(acpi_gpio_handle_deferred_request_irqs); -- 2.19.1

6 years, 10 months

4
3
0 0

[crypto chcr 1/2] small packet Tx stalls the queue

by Atul Gupta

Immediate packets sent to hardware should include the work request length in calculating the flits. WR occupy one flit and if not accounted result in invalid request which stalls the HW queue. Cc: stable(a)vger.kernel.org Signed-off-by: Atul Gupta <atul.gupta(a)chelsio.com> --- drivers/crypto/chelsio/chcr_ipsec.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/chelsio/chcr_ipsec.c b/drivers/crypto/chelsio/chcr_ipsec.c index 461b97e..1ff8738 100644 --- a/drivers/crypto/chelsio/chcr_ipsec.c +++ b/drivers/crypto/chelsio/chcr_ipsec.c @@ -303,7 +303,10 @@ static bool chcr_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x) static inline int is_eth_imm(const struct sk_buff *skb, unsigned int kctx_len) { - int hdrlen = sizeof(struct chcr_ipsec_req) + kctx_len; + int hdrlen; + + hdrlen = sizeof(struct fw_ulptx_wr) + + sizeof(struct chcr_ipsec_req) + kctx_len; hdrlen += sizeof(struct cpl_tx_pkt); if (skb->len <= MAX_IMM_TX_PKT_LEN - hdrlen) -- 1.8.3.1

6 years, 10 months

2
1
0 0

[PATCH 09/75] perf script: Use fallbacks for branch stacks

by Arnaldo Carvalho de Melo

From: Adrian Hunter <adrian.hunter(a)intel.com> Branch stacks do not necessarily have the same cpumode as the 'ip'. Use the fallback functions in those cases. This patch depends on patch "perf tools: Add fallback functions for cases where cpumode is insufficient". Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: stable(a)vger.kernel.org Link: http://lkml.kernel.org/r/20181106210712.12098-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- tools/perf/builtin-script.c | 12 ++++++------ .../util/scripting-engines/trace-event-python.c | 16 ++++++++-------- 2 files changed, 14 insertions(+), 14 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 04913136bac9..3ea98fe72f7f 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -724,8 +724,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, if (PRINT_FIELD(DSO)) { memset(&alf, 0, sizeof(alf)); memset(&alt, 0, sizeof(alt)); - thread__find_map(thread, sample->cpumode, from, &alf); - thread__find_map(thread, sample->cpumode, to, &alt); + thread__find_map_fb(thread, sample->cpumode, from, &alf); + thread__find_map_fb(thread, sample->cpumode, to, &alt); } printed += fprintf(fp, " 0x%"PRIx64, from); @@ -771,8 +771,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_symbol(thread, sample->cpumode, from, &alf); - thread__find_symbol(thread, sample->cpumode, to, &alt); + thread__find_symbol_fb(thread, sample->cpumode, from, &alf); + thread__find_symbol_fb(thread, sample->cpumode, to, &alt); printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp); if (PRINT_FIELD(DSO)) { @@ -816,11 +816,11 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - if (thread__find_map(thread, sample->cpumode, from, &alf) && + if (thread__find_map_fb(thread, sample->cpumode, from, &alf) && !alf.map->dso->adjust_symbols) from = map__map_ip(alf.map, from); - if (thread__find_map(thread, sample->cpumode, to, &alt) && + if (thread__find_map_fb(thread, sample->cpumode, to, &alt) && !alt.map->dso->adjust_symbols) to = map__map_ip(alt.map, to); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 69aa93d4ee99..0c4b050f6fc2 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -494,14 +494,14 @@ static PyObject *python_process_brstack(struct perf_sample *sample, pydict_set_item_string_decref(pyelem, "cycles", PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles)); - thread__find_map(thread, sample->cpumode, - br->entries[i].from, &al); + thread__find_map_fb(thread, sample->cpumode, + br->entries[i].from, &al); dsoname = get_dsoname(al.map); pydict_set_item_string_decref(pyelem, "from_dsoname", _PyUnicode_FromString(dsoname)); - thread__find_map(thread, sample->cpumode, - br->entries[i].to, &al); + thread__find_map_fb(thread, sample->cpumode, + br->entries[i].to, &al); dsoname = get_dsoname(al.map); pydict_set_item_string_decref(pyelem, "to_dsoname", _PyUnicode_FromString(dsoname)); @@ -576,14 +576,14 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample, if (!pyelem) Py_FatalError("couldn't create Python dictionary"); - thread__find_symbol(thread, sample->cpumode, - br->entries[i].from, &al); + thread__find_symbol_fb(thread, sample->cpumode, + br->entries[i].from, &al); get_symoff(al.sym, &al, true, bf, sizeof(bf)); pydict_set_item_string_decref(pyelem, "from", _PyUnicode_FromString(bf)); - thread__find_symbol(thread, sample->cpumode, - br->entries[i].to, &al); + thread__find_symbol_fb(thread, sample->cpumode, + br->entries[i].to, &al); get_symoff(al.sym, &al, true, bf, sizeof(bf)); pydict_set_item_string_decref(pyelem, "to", _PyUnicode_FromString(bf)); -- 2.19.2

6 years, 10 months

1
0
0 0

[PATCH 08/75] perf tools: Use fallback for sample_addr_correlates_sym() cases

by Arnaldo Carvalho de Melo

From: Adrian Hunter <adrian.hunter(a)intel.com> thread__resolve() is used in the sample_addr_correlates_sym() cases where 'addr' is a destination of a branch which does not necessarily have the same cpumode as the 'ip'. Use the fallback function in that case. This patch depends on patch "perf tools: Add fallback functions for cases where cpumode is insufficient". Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: stable(a)vger.kernel.org Link: http://lkml.kernel.org/r/20181106210712.12098-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- tools/perf/util/event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 9431b20c1337..24493200cf80 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1706,7 +1706,7 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr) void thread__resolve(struct thread *thread, struct addr_location *al, struct perf_sample *sample) { - thread__find_map(thread, sample->cpumode, sample->addr, al); + thread__find_map_fb(thread, sample->cpumode, sample->addr, al); al->cpu = sample->cpu; al->sym = NULL; -- 2.19.2

6 years, 10 months

1
0
0 0

[PATCH 07/75] perf thread: Add fallback functions for cases where cpumode is insufficient

by Arnaldo Carvalho de Melo

From: Adrian Hunter <adrian.hunter(a)intel.com> For branch stacks or branch samples, the sample cpumode might not be correct because it applies only to the sample 'ip' and not necessary to 'addr' or branch stack addresses. Add fallback functions that can be used to deal with those cases Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: stable(a)vger.kernel.org Link: http://lkml.kernel.org/r/20181106210712.12098-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- tools/perf/util/event.c | 27 +++++++++++++++++++++++++++ tools/perf/util/machine.c | 27 +++++++++++++++++++++++++++ tools/perf/util/machine.h | 2 ++ tools/perf/util/thread.h | 4 ++++ 4 files changed, 60 insertions(+) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index e9c108a6b1c3..9431b20c1337 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1577,6 +1577,24 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, return al->map; } +/* + * For branch stacks or branch samples, the sample cpumode might not be correct + * because it applies only to the sample 'ip' and not necessary to 'addr' or + * branch stack addresses. If possible, use a fallback to deal with those cases. + */ +struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al) +{ + struct map *map = thread__find_map(thread, cpumode, addr, al); + struct machine *machine = thread->mg->machine; + u8 addr_cpumode = machine__addr_cpumode(machine, cpumode, addr); + + if (map || addr_cpumode == cpumode) + return map; + + return thread__find_map(thread, addr_cpumode, addr, al); +} + struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { @@ -1586,6 +1604,15 @@ struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, return al->sym; } +struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode, + u64 addr, struct addr_location *al) +{ + al->sym = NULL; + if (thread__find_map_fb(thread, cpumode, addr, al)) + al->sym = map__find_symbol(al->map, al->addr); + return al->sym; +} + /* * Callers need to drop the reference to al->thread, obtained in * machine__findnew_thread() diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 8f36ce813bc5..9397e3f2444d 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2592,6 +2592,33 @@ int machine__get_kernel_start(struct machine *machine) return err; } +u8 machine__addr_cpumode(struct machine *machine, u8 cpumode, u64 addr) +{ + u8 addr_cpumode = cpumode; + bool kernel_ip; + + if (!machine->single_address_space) + goto out; + + kernel_ip = machine__kernel_ip(machine, addr); + switch (cpumode) { + case PERF_RECORD_MISC_KERNEL: + case PERF_RECORD_MISC_USER: + addr_cpumode = kernel_ip ? PERF_RECORD_MISC_KERNEL : + PERF_RECORD_MISC_USER; + break; + case PERF_RECORD_MISC_GUEST_KERNEL: + case PERF_RECORD_MISC_GUEST_USER: + addr_cpumode = kernel_ip ? PERF_RECORD_MISC_GUEST_KERNEL : + PERF_RECORD_MISC_GUEST_USER; + break; + default: + break; + } +out: + return addr_cpumode; +} + struct dso *machine__findnew_dso(struct machine *machine, const char *filename) { return dsos__findnew(&machine->dsos, filename); diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index ca897a73014c..ebde3ea70225 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -100,6 +100,8 @@ static inline bool machine__kernel_ip(struct machine *machine, u64 ip) return ip >= kernel_start; } +u8 machine__addr_cpumode(struct machine *machine, u8 cpumode, u64 addr); + struct thread *machine__find_thread(struct machine *machine, pid_t pid, pid_t tid); struct comm *machine__thread_exec_comm(struct machine *machine, diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 30e2b4c165fe..5920c3bb8ffe 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -96,9 +96,13 @@ struct thread *thread__main_thread(struct machine *machine, struct thread *threa struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al); +struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al); struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al); +struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode, + u64 addr, struct addr_location *al); void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, struct addr_location *al); -- 2.19.2

6 years, 10 months

1
0
0 0

[PATCH 06/75] perf machine: Record if a arch has a single user/kernel address space

by Arnaldo Carvalho de Melo

From: Adrian Hunter <adrian.hunter(a)intel.com> Some architectures have a single address space for kernel and user addresses, which makes it possible to determine if an address is in kernel space or user space. Some don't, e.g.: sparc. Cache that info in perf_env so that, for instance, code needing to fallback failed symbol lookups at the kernel space in single address space arches can lookup at userspace. Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: stable(a)vger.kernel.org Link: http://lkml.kernel.org/r/20181106210712.12098-2-adrian.hunter@intel.com [ split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- tools/perf/arch/common.c | 10 ++++++++++ tools/perf/arch/common.h | 1 + tools/perf/util/machine.h | 1 + tools/perf/util/session.c | 4 ++++ 4 files changed, 16 insertions(+) diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 82657c01a3b8..5f69fd0b745a 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -200,3 +200,13 @@ int perf_env__lookup_objdump(struct perf_env *env, const char **path) return perf_env__lookup_binutils_path(env, "objdump", path); } + +/* + * Some architectures have a single address space for kernel and user addresses, + * which makes it possible to determine if an address is in kernel space or user + * space. + */ +bool perf_env__single_address_space(struct perf_env *env) +{ + return strcmp(perf_env__arch(env), "sparc"); +} diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h index 2167001b18c5..c298a446d1f6 100644 --- a/tools/perf/arch/common.h +++ b/tools/perf/arch/common.h @@ -5,5 +5,6 @@ #include "../util/env.h" int perf_env__lookup_objdump(struct perf_env *env, const char **path); +bool perf_env__single_address_space(struct perf_env *env); #endif /* ARCH_PERF_COMMON_H */ diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index d856b85862e2..ca897a73014c 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -42,6 +42,7 @@ struct machine { u16 id_hdr_size; bool comm_exec; bool kptr_restrict_warned; + bool single_address_space; char *root_dir; char *mmap_name; struct threads threads[THREADS__TABLE_SIZE]; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 7d2c8ce6cfad..f8eab197f35c 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -24,6 +24,7 @@ #include "thread.h" #include "thread-stack.h" #include "stat.h" +#include "arch/common.h" static int perf_session__deliver_event(struct perf_session *session, union perf_event *event, @@ -150,6 +151,9 @@ struct perf_session *perf_session__new(struct perf_data *data, session->machines.host.env = &perf_env; } + session->machines.host.single_address_space = + perf_env__single_address_space(session->machines.host.env); + if (!data || perf_data__is_write(data)) { /* * In O_RDONLY mode this will be performed when reading the -- 2.19.2

6 years, 10 months

1
0
0 0

[PATCH 05/75] perf env: Also consider env->arch == NULL as local operation

by Arnaldo Carvalho de Melo

From: Arnaldo Carvalho de Melo <acme(a)redhat.com> We'll set a new machine field based on env->arch, which for live mode, like with 'perf top' means we need to use uname() to figure the name of the arch, fix perf_env__arch() to consider both (env == NULL) and (env->arch == NULL) as local operation. Cc: Adrian Hunter <adrian.hunter(a)intel.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: David Ahern <dsahern(a)gmail.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Wang Nan <wangnan0(a)huawei.com> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/n/tip-vcz4ufzdon7cwy8dm2ua53xk@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- tools/perf/util/env.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 59f38c7693f8..4c23779e271a 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -166,7 +166,7 @@ const char *perf_env__arch(struct perf_env *env) struct utsname uts; char *arch_name; - if (!env) { /* Assume local operation */ + if (!env || !env->arch) { /* Assume local operation */ if (uname(&uts) < 0) return NULL; arch_name = uts.machine; -- 2.19.2

6 years, 10 months

1
0
0 0

[PATCH 3/3] drm/i915/execlists: Apply a full mb before execution for Braswell

by Chris Wilson

Braswell is really picky about having our writes posted to memory before we execute or else the GPU may see stale values. A wmb() is insufficient as it only ensures the writes are visible to other cores, we need a full mb() to ensure the writes are in memory and visible to the GPU. The most frequent failure in flushing before execution is that we see stale PTE values and execute the wrong pages. References: 987abd5c62f9 ("drm/i915/execlists: Force write serialisation into context image vs execution") Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala(a)linux.intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Cc: stable(a)vger.kernel.org --- drivers/gpu/drm/i915/intel_lrc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index de1e9dc6aec0..e6a86fa4502d 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -379,8 +379,13 @@ static u64 execlists_update_context(struct i915_request *rq) * may not be visible to the HW prior to the completion of the UC * register write and that we may begin execution from the context * before its image is complete leading to invalid PD chasing. + * + * Furthermore, Braswell, at least, wants a full mb to be sure that + * the writes are coherent in memory (visible to the GPU) prior to + * execution, and not just visible to other CPUs (as is the result of + * wmb). */ - wmb(); + mb(); return ce->lrc_desc; } -- 2.20.0.rc2

6 years, 10 months

2
2
0 0

stable-rc/linux-4.4.y boot: 102 boots: 1 failed, 100 passed with 1 offline (v4.4.166-57-g4e21c8c946b3)

by kernelci.org bot

stable-rc/linux-4.4.y boot: 102 boots: 1 failed, 100 passed with 1 offline (v4.4.166-57-g4e21c8c946b3) Full Boot Summary: https://kernelci.org/boot/all/job/stable-rc/branch/linux-4.4.y/kernel/v4.4.… Full Build Summary: https://kernelci.org/build/stable-rc/branch/linux-4.4.y/kernel/v4.4.166-57-… Tree: stable-rc Branch: linux-4.4.y Git Describe: v4.4.166-57-g4e21c8c946b3 Git Commit: 4e21c8c946b3ad212abb91845378dbe0f3042ccd Git URL: http://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git Tested: 45 unique boards, 21 SoC families, 15 builds out of 187 Boot Failure Detected: arm64: defconfig qcom-qdf2400: 1 failed lab Offline Platforms: arm: multi_v7_defconfig: stih410-b2120: 1 offline lab --- For more info write to <info(a)kernelci.org>

6 years, 10 months

1
0
0 0

stable-rc/linux-4.19.y boot: 120 boots: 0 failed, 119 passed with 1 offline (v4.19.7-42-g62b84b3cf313)

by kernelci.org bot

stable-rc/linux-4.19.y boot: 120 boots: 0 failed, 119 passed with 1 offline (v4.19.7-42-g62b84b3cf313) Full Boot Summary: https://kernelci.org/boot/all/job/stable-rc/branch/linux-4.19.y/kernel/v4.1… Full Build Summary: https://kernelci.org/build/stable-rc/branch/linux-4.19.y/kernel/v4.19.7-42-… Tree: stable-rc Branch: linux-4.19.y Git Describe: v4.19.7-42-g62b84b3cf313 Git Commit: 62b84b3cf313e064c6ad249e95a5fb8feb22c77e Git URL: http://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git Tested: 60 unique boards, 23 SoC families, 14 builds out of 202 Offline Platforms: arm: multi_v7_defconfig: stih410-b2120: 1 offline lab --- For more info write to <info(a)kernelci.org>

6 years, 10 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror