From 23e3983a466cd540ffdd2bbc6e0c51e31934f941 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 20 May 2019 17:52:46 -0700 Subject: perf/x86/intel/ds: Fix EVENT vs. UEVENT PEBS constraints This patch fixes an bug revealed by the following commit: 6b89d4c1ae85 ("perf/x86/intel: Fix INTEL_FLAGS_EVENT_CONSTRAINT* masking") That patch modified INTEL_FLAGS_EVENT_CONSTRAINT() to only look at the event code when matching a constraint. If code+umask were needed, then the INTEL_FLAGS_UEVENT_CONSTRAINT() macro was needed instead. This broke with some of the constraints for PEBS events. Several of them, including the one used for cycles:p, cycles:pp, cycles:ppp fell in that category and caused the event to be rejected in PEBS mode. In other words, on some platforms a cmdline such as: $ perf top -e cycles:pp would fail with -EINVAL. This patch fixes this bug by properly using INTEL_FLAGS_UEVENT_CONSTRAINT() when needed in the PEBS constraint tables. Reported-by: Ingo Molnar Signed-off-by: Stephane Eranian Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Cc: kan.liang@intel.com Link: http://lkml.kernel.org/r/20190521005246.423-1-eranian@google.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/ds.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 7a9f5dac5abe..7acc526b4ad2 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -684,7 +684,7 @@ struct event_constraint intel_core2_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01), EVENT_CONSTRAINT_END }; @@ -693,7 +693,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01), /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END @@ -701,7 +701,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { struct event_constraint intel_slm_pebs_event_constraints[] = { /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x1), /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END @@ -726,7 +726,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -743,7 +743,7 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -752,7 +752,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -767,9 +767,9 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -783,9 +783,9 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -806,9 +806,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -829,9 +829,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = { struct event_constraint intel_skl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), /* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f), INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ -- cgit v1.2.3 From 1b038c6e05ff70a1e66e3e571c2e6106bdb75f53 Mon Sep 17 00:00:00 2001 From: Yabin Cui Date: Fri, 17 May 2019 13:52:31 +0200 Subject: perf/ring_buffer: Fix exposing a temporarily decreased data_head In perf_output_put_handle(), an IRQ/NMI can happen in below location and write records to the same ring buffer: ... local_dec_and_test(&rb->nest) ... <-- an IRQ/NMI can happen here rb->user_page->data_head = head; ... In this case, a value A is written to data_head in the IRQ, then a value B is written to data_head after the IRQ. And A > B. As a result, data_head is temporarily decreased from A to B. And a reader may see data_head < data_tail if it read the buffer frequently enough, which creates unexpected behaviors. This can be fixed by moving dec(&rb->nest) to after updating data_head, which prevents the IRQ/NMI above from updating data_head. [ Split up by peterz. ] Signed-off-by: Yabin Cui Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: mark.rutland@arm.com Fixes: ef60777c9abd ("perf: Optimize the perf_output() path by removing IRQ-disables") Link: http://lkml.kernel.org/r/20190517115418.224478157@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 674b35383491..009467a60578 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -51,11 +51,18 @@ again: head = local_read(&rb->head); /* - * IRQ/NMI can happen here, which means we can miss a head update. + * IRQ/NMI can happen here and advance @rb->head, causing our + * load above to be stale. */ - if (!local_dec_and_test(&rb->nest)) + /* + * If this isn't the outermost nesting, we don't have to update + * @rb->user_page->data_head. + */ + if (local_read(&rb->nest) > 1) { + local_dec(&rb->nest); goto out; + } /* * Since the mmap() consumer (userspace) can run on a different CPU: @@ -87,9 +94,18 @@ again: rb->user_page->data_head = head; /* - * Now check if we missed an update -- rely on previous implied - * compiler barriers to force a re-read. + * We must publish the head before decrementing the nest count, + * otherwise an IRQ/NMI can publish a more recent head value and our + * write will (temporarily) publish a stale value. + */ + barrier(); + local_set(&rb->nest, 0); + + /* + * Ensure we decrement @rb->nest before we validate the @rb->head. + * Otherwise we cannot be sure we caught the 'last' nested update. */ + barrier(); if (unlikely(head != local_read(&rb->head))) { local_inc(&rb->nest); goto again; -- cgit v1.2.3 From 3f9fbe9bd86c534eba2faf5d840fd44c6049f50e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 17 May 2019 13:52:32 +0200 Subject: perf/ring_buffer: Add ordering to rb->nest increment Similar to how decrementing rb->next too early can cause data_head to (temporarily) be observed to go backward, so too can this happen when we increment too late. This barrier() ensures the rb->head load happens after the increment, both the one in the 'goto again' path, as the one from perf_output_get_handle() -- albeit very unlikely to matter for the latter. Suggested-by: Yabin Cui Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: acme@kernel.org Cc: mark.rutland@arm.com Cc: namhyung@kernel.org Fixes: ef60777c9abd ("perf: Optimize the perf_output() path by removing IRQ-disables") Link: http://lkml.kernel.org/r/20190517115418.309516009@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 009467a60578..4b5f8d932400 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -48,6 +48,15 @@ static void perf_output_put_handle(struct perf_output_handle *handle) unsigned long head; again: + /* + * In order to avoid publishing a head value that goes backwards, + * we must ensure the load of @rb->head happens after we've + * incremented @rb->nest. + * + * Otherwise we can observe a @rb->head value before one published + * by an IRQ/NMI happening between the load and the increment. + */ + barrier(); head = local_read(&rb->head); /* -- cgit v1.2.3 From 4d839dd9e4356bbacf3eb0ab13a549b83b008c21 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 17 May 2019 13:52:33 +0200 Subject: perf/ring-buffer: Always use {READ,WRITE}_ONCE() for rb->user_page data We must use {READ,WRITE}_ONCE() on rb->user_page data such that concurrent usage will see whole values. A few key sites were missing this. Suggested-by: Yabin Cui Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: acme@kernel.org Cc: mark.rutland@arm.com Cc: namhyung@kernel.org Fixes: 7b732a750477 ("perf_counter: new output ABI - part 1") Link: http://lkml.kernel.org/r/20190517115418.394192145@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 4b5f8d932400..7a0c73e4b3eb 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -100,7 +100,7 @@ again: * See perf_output_begin(). */ smp_wmb(); /* B, matches C */ - rb->user_page->data_head = head; + WRITE_ONCE(rb->user_page->data_head, head); /* * We must publish the head before decrementing the nest count, @@ -496,7 +496,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) perf_event_aux_event(handle->event, aux_head, size, handle->aux_flags); - rb->user_page->aux_head = rb->aux_head; + WRITE_ONCE(rb->user_page->aux_head, rb->aux_head); if (rb_need_aux_wakeup(rb)) wakeup = true; @@ -528,7 +528,7 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; - rb->user_page->aux_head = rb->aux_head; + WRITE_ONCE(rb->user_page->aux_head, rb->aux_head); if (rb_need_aux_wakeup(rb)) { perf_output_wakeup(handle); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; -- cgit v1.2.3 From 5322ea58a06da2e69c5ef36a9b4d4b9255edd423 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 17 May 2019 13:52:34 +0200 Subject: perf/ring-buffer: Use regular variables for nesting While the IRQ/NMI will nest, the nest-count will be invariant over the actual exception, since it will decrement equal to increment. This means we can -- carefully -- use a regular variable since the typical LOAD-STORE race doesn't exist (similar to preempt_count). This optimizes the ring-buffer for all LOAD-STORE architectures, since they need to use atomic ops to implement local_t. Suggested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: acme@kernel.org Cc: mark.rutland@arm.com Cc: namhyung@kernel.org Cc: yabinc@google.com Link: http://lkml.kernel.org/r/20190517115418.481392777@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/internal.h | 4 ++-- kernel/events/ring_buffer.c | 41 ++++++++++++++++++++++++++--------------- 2 files changed, 28 insertions(+), 17 deletions(-) diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 79c47076700a..3aef4191798c 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -24,7 +24,7 @@ struct ring_buffer { atomic_t poll; /* POLL_ for wakeups */ local_t head; /* write position */ - local_t nest; /* nested writers */ + unsigned int nest; /* nested writers */ local_t events; /* event limit */ local_t wakeup; /* wakeup stamp */ local_t lost; /* nr records lost */ @@ -41,7 +41,7 @@ struct ring_buffer { /* AUX area */ long aux_head; - local_t aux_nest; + unsigned int aux_nest; long aux_wakeup; /* last aux_watermark boundary crossed by aux_head */ unsigned long aux_pgoff; int aux_nr_pages; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 7a0c73e4b3eb..ffb59a4ef4ff 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -38,7 +38,12 @@ static void perf_output_get_handle(struct perf_output_handle *handle) struct ring_buffer *rb = handle->rb; preempt_disable(); - local_inc(&rb->nest); + + /* + * Avoid an explicit LOAD/STORE such that architectures with memops + * can use them. + */ + (*(volatile unsigned int *)&rb->nest)++; handle->wakeup = local_read(&rb->wakeup); } @@ -46,6 +51,17 @@ static void perf_output_put_handle(struct perf_output_handle *handle) { struct ring_buffer *rb = handle->rb; unsigned long head; + unsigned int nest; + + /* + * If this isn't the outermost nesting, we don't have to update + * @rb->user_page->data_head. + */ + nest = READ_ONCE(rb->nest); + if (nest > 1) { + WRITE_ONCE(rb->nest, nest - 1); + goto out; + } again: /* @@ -64,15 +80,6 @@ again: * load above to be stale. */ - /* - * If this isn't the outermost nesting, we don't have to update - * @rb->user_page->data_head. - */ - if (local_read(&rb->nest) > 1) { - local_dec(&rb->nest); - goto out; - } - /* * Since the mmap() consumer (userspace) can run on a different CPU: * @@ -108,7 +115,7 @@ again: * write will (temporarily) publish a stale value. */ barrier(); - local_set(&rb->nest, 0); + WRITE_ONCE(rb->nest, 0); /* * Ensure we decrement @rb->nest before we validate the @rb->head. @@ -116,7 +123,7 @@ again: */ barrier(); if (unlikely(head != local_read(&rb->head))) { - local_inc(&rb->nest); + WRITE_ONCE(rb->nest, 1); goto again; } @@ -355,6 +362,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *output_event = event; unsigned long aux_head, aux_tail; struct ring_buffer *rb; + unsigned int nest; if (output_event->parent) output_event = output_event->parent; @@ -385,13 +393,16 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, if (!refcount_inc_not_zero(&rb->aux_refcount)) goto err; + nest = READ_ONCE(rb->aux_nest); /* * Nesting is not supported for AUX area, make sure nested * writers are caught early */ - if (WARN_ON_ONCE(local_xchg(&rb->aux_nest, 1))) + if (WARN_ON_ONCE(nest)) goto err_put; + WRITE_ONCE(rb->aux_nest, nest + 1); + aux_head = rb->aux_head; handle->rb = rb; @@ -419,7 +430,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, if (!handle->size) { /* A, matches D */ event->pending_disable = smp_processor_id(); perf_output_wakeup(handle); - local_set(&rb->aux_nest, 0); + WRITE_ONCE(rb->aux_nest, 0); goto err_put; } } @@ -508,7 +519,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) handle->event = NULL; - local_set(&rb->aux_nest, 0); + WRITE_ONCE(rb->aux_nest, 0); /* can't be last */ rb_free_aux(rb); ring_buffer_put(rb); -- cgit v1.2.3 From 97acec7df172cd1e450f81f5e293c0aa145a2797 Mon Sep 17 00:00:00 2001 From: Shawn Landden Date: Sat, 18 May 2019 15:32:38 -0300 Subject: perf data: Fix 'strncat may truncate' build failure with recent gcc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This strncat() is safe because the buffer was allocated with zalloc(), however gcc doesn't know that. Since the string always has 4 non-null bytes, just use memcpy() here. CC /home/shawn/linux/tools/perf/util/data-convert-bt.o In file included from /usr/include/string.h:494, from /home/shawn/linux/tools/lib/traceevent/event-parse.h:27, from util/data-convert-bt.c:22: In function ‘strncat’, inlined from ‘string_set_value’ at util/data-convert-bt.c:274:4: /usr/include/powerpc64le-linux-gnu/bits/string_fortified.h:136:10: error: ‘__builtin_strncat’ output may be truncated copying 4 bytes from a string of length 4 [-Werror=stringop-truncation] 136 | return __builtin___strncat_chk (__dest, __src, __len, __bos (__dest)); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Shawn Landden Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan LPU-Reference: 20190518183238.10954-1-shawn@git.icu Link: https://lkml.kernel.org/n/tip-289f1jice17ta7tr3tstm9jm@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data-convert-bt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index e0311c9750ad..9097543a818b 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -271,7 +271,7 @@ static int string_set_value(struct bt_ctf_field *field, const char *string) if (i > 0) strncpy(buffer, string, i); } - strncat(buffer + p, numstr, 4); + memcpy(buffer + p, numstr, 4); p += 3; } } -- cgit v1.2.3 From f95d050cdc5d34f9a4417e06c392ccbf146037bb Mon Sep 17 00:00:00 2001 From: Vitaly Chikunov Date: Tue, 21 May 2019 06:02:03 +0300 Subject: perf arm64: Fix mksyscalltbl when system kernel headers are ahead of the kernel When a host system has kernel headers that are newer than a compiling kernel, mksyscalltbl fails with errors such as: : In function 'main': :271:44: error: '__NR_kexec_file_load' undeclared (first use in this function) :271:44: note: each undeclared identifier is reported only once for each function it appears in :272:46: error: '__NR_pidfd_send_signal' undeclared (first use in this function) :273:43: error: '__NR_io_uring_setup' undeclared (first use in this function) :274:43: error: '__NR_io_uring_enter' undeclared (first use in this function) :275:46: error: '__NR_io_uring_register' undeclared (first use in this function) tools/perf/arch/arm64/entry/syscalls//mksyscalltbl: line 48: /tmp/create-table-xvUQdD: Permission denied mksyscalltbl is compiled with default host includes, but run with compiling kernel tree includes, causing some syscall numbers to being undeclared. Committer testing: Before this patch, in my cross build environment, no build problems, but these new syscalls were not in the syscalls.c generated from the unistd.h file, which is a bug, this patch fixes it: perfbuilder@6e20056ed532:/git/perf$ tail /tmp/build/perf/arch/arm64/include/generated/asm/syscalls.c [292] = "io_pgetevents", [293] = "rseq", [294] = "kexec_file_load", [424] = "pidfd_send_signal", [425] = "io_uring_setup", [426] = "io_uring_enter", [427] = "io_uring_register", [428] = "syscalls", }; perfbuilder@6e20056ed532:/git/perf$ strings /tmp/build/perf/perf | egrep '^(io_uring_|pidfd_|kexec_file)' kexec_file_load pidfd_send_signal io_uring_setup io_uring_enter io_uring_register perfbuilder@6e20056ed532:/git/perf$ $ Well, there is that last "syscalls" thing, but that looks like some other bug. Signed-off-by: Vitaly Chikunov Tested-by: Arnaldo Carvalho de Melo Tested-by: Michael Petlan Cc: Alexander Shishkin Cc: Hendrik Brueckner Cc: Jiri Olsa Cc: Kim Phillips Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Link: http://lkml.kernel.org/r/20190521030203.1447-1-vt@altlinux.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/entry/syscalls/mksyscalltbl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl index c88fd32563eb..459469b7222c 100755 --- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -56,7 +56,7 @@ create_table() echo "};" } -$gcc -E -dM -x c $input \ +$gcc -E -dM -x c -I $incpath/include/uapi $input \ |sed -ne 's/^#define __NR_//p' \ |sort -t' ' -k2 -nu \ |create_table -- cgit v1.2.3 From fba29f1820ddd42e63c38049028422dac2d86596 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 20 May 2019 12:03:30 -0300 Subject: tools include UAPI: Update copy of files related to new fspick, fsmount, fsconfig, fsopen, move_mount and open_tree syscalls MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Copy the headers changed by these csets: d8076bdb56af ("uapi: Wire up the mount API syscalls on non-x86 arches [ver #2]") 9c8ad7a2ff0b ("uapi, x86: Fix the syscall numbering of the mount API syscalls [ver #2]") cf3cba4a429b ("vfs: syscall: Add fspick() to select a superblock for reconfiguration") 93766fbd2696 ("vfs: syscall: Add fsmount() to create a mount for a superblock") ecdab150fddb ("vfs: syscall: Add fsconfig() for configuring and managing a context") 24dcb3d90a1f ("vfs: syscall: Add fsopen() to prepare for superblock creation") 2db154b3ea8e ("vfs: syscall: Add move_mount(2) to move mounts around") a07b20004793 ("vfs: syscall: Add open_tree(2) to reference or clone a mount") We need to create tables for all the flags argument in the new syscalls, in followup patches. This silences these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/linux/mount.h' differs from latest version at 'include/uapi/linux/mount.h' diff -u tools/include/uapi/linux/mount.h include/uapi/linux/mount.h Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Cc: Adrian Hunter Cc: Al Viro Cc: David Howells Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-knpqr1u2ffvz6641056z2mwu@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/asm-generic/unistd.h | 14 ++++- tools/include/uapi/linux/fcntl.h | 2 + tools/include/uapi/linux/mount.h | 62 +++++++++++++++++++++++ tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 6 +++ 4 files changed, 83 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index dee7292e1df6..a87904daf103 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -832,9 +832,21 @@ __SYSCALL(__NR_io_uring_setup, sys_io_uring_setup) __SYSCALL(__NR_io_uring_enter, sys_io_uring_enter) #define __NR_io_uring_register 427 __SYSCALL(__NR_io_uring_register, sys_io_uring_register) +#define __NR_open_tree 428 +__SYSCALL(__NR_open_tree, sys_open_tree) +#define __NR_move_mount 429 +__SYSCALL(__NR_move_mount, sys_move_mount) +#define __NR_fsopen 430 +__SYSCALL(__NR_fsopen, sys_fsopen) +#define __NR_fsconfig 431 +__SYSCALL(__NR_fsconfig, sys_fsconfig) +#define __NR_fsmount 432 +__SYSCALL(__NR_fsmount, sys_fsmount) +#define __NR_fspick 433 +__SYSCALL(__NR_fspick, sys_fspick) #undef __NR_syscalls -#define __NR_syscalls 428 +#define __NR_syscalls 434 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index a2f8658f1c55..1d338357df8a 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -91,5 +91,7 @@ #define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */ #define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */ +#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */ + #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h index 3f9ec42510b0..96a0240f23fe 100644 --- a/tools/include/uapi/linux/mount.h +++ b/tools/include/uapi/linux/mount.h @@ -55,4 +55,66 @@ #define MS_MGC_VAL 0xC0ED0000 #define MS_MGC_MSK 0xffff0000 +/* + * open_tree() flags. + */ +#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */ +#define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */ + +/* + * move_mount() flags. + */ +#define MOVE_MOUNT_F_SYMLINKS 0x00000001 /* Follow symlinks on from path */ +#define MOVE_MOUNT_F_AUTOMOUNTS 0x00000002 /* Follow automounts on from path */ +#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */ +#define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */ +#define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ +#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ +#define MOVE_MOUNT__MASK 0x00000077 + +/* + * fsopen() flags. + */ +#define FSOPEN_CLOEXEC 0x00000001 + +/* + * fspick() flags. + */ +#define FSPICK_CLOEXEC 0x00000001 +#define FSPICK_SYMLINK_NOFOLLOW 0x00000002 +#define FSPICK_NO_AUTOMOUNT 0x00000004 +#define FSPICK_EMPTY_PATH 0x00000008 + +/* + * The type of fsconfig() call made. + */ +enum fsconfig_command { + FSCONFIG_SET_FLAG = 0, /* Set parameter, supplying no value */ + FSCONFIG_SET_STRING = 1, /* Set parameter, supplying a string value */ + FSCONFIG_SET_BINARY = 2, /* Set parameter, supplying a binary blob value */ + FSCONFIG_SET_PATH = 3, /* Set parameter, supplying an object by path */ + FSCONFIG_SET_PATH_EMPTY = 4, /* Set parameter, supplying an object by (empty) path */ + FSCONFIG_SET_FD = 5, /* Set parameter, supplying an object by fd */ + FSCONFIG_CMD_CREATE = 6, /* Invoke superblock creation */ + FSCONFIG_CMD_RECONFIGURE = 7, /* Invoke superblock reconfiguration */ +}; + +/* + * fsmount() flags. + */ +#define FSMOUNT_CLOEXEC 0x00000001 + +/* + * Mount attributes. + */ +#define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */ +#define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */ +#define MOUNT_ATTR_NODEV 0x00000004 /* Disallow access to device special files */ +#define MOUNT_ATTR_NOEXEC 0x00000008 /* Disallow program execution */ +#define MOUNT_ATTR__ATIME 0x00000070 /* Setting on how atime should be updated */ +#define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */ +#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */ +#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ +#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ + #endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 92ee0b4378d4..b4e6f9e6204a 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -349,6 +349,12 @@ 425 common io_uring_setup __x64_sys_io_uring_setup 426 common io_uring_enter __x64_sys_io_uring_enter 427 common io_uring_register __x64_sys_io_uring_register +428 common open_tree __x64_sys_open_tree +429 common move_mount __x64_sys_move_mount +430 common fsopen __x64_sys_fsopen +431 common fsconfig __x64_sys_fsconfig +432 common fsmount __x64_sys_fsmount +433 common fspick __x64_sys_fspick # # x32-specific system call numbers start at 512 to avoid cache impact -- cgit v1.2.3 From b979540a7522617e190636621e7c5ffae469f8f0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 21 May 2019 16:39:42 -0300 Subject: tools arch x86: Sync asm/cpufeatures.h with the with the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To pick up the changes in: ed5194c2732c ("x86/speculation/mds: Add basic bug infrastructure for MDS") e261f209c366 ("x86/speculation/mds: Add BUG_MSBDS_ONLY") That don't affect anything in tools/. This silences this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Cc: Adrian Hunter Cc: Andi Kleen Cc: Brendan Gregg Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Thomas Gleixner Link: https://lkml.kernel.org/n/tip-jp1afecx3ql1jkuirpgkqfad@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 981ff9479648..75f27ee2c263 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -344,6 +344,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ @@ -382,5 +383,7 @@ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ #define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ +#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ +#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #endif /* _ASM_X86_CPUFEATURES_H */ -- cgit v1.2.3 From c27de2b8911db7624be9bde1b5d58067dd58371d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 21 May 2019 16:43:32 -0300 Subject: tools headers UAPI: Sync linux/sched.h with the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To pick up the change in: b3e583825266 ("clone: add CLONE_PIDFD") This requires changes in the 'perf trace' beautification routines for the 'clone' syscall args, which is done in a followup patch. This silences the following perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/sched.h' differs from latest version at 'include/uapi/linux/sched.h' diff -u tools/include/uapi/linux/sched.h include/uapi/linux/sched.h Cc: Adrian Hunter Cc: Brendan Gregg Cc: Christian Brauner Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-lenja6gmy26dkt0ybk747qgq@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/sched.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index 22627f80063e..ed4ee170bee2 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -10,6 +10,7 @@ #define CLONE_FS 0x00000200 /* set if fs info shared between processes */ #define CLONE_FILES 0x00000400 /* set if open files shared between processes */ #define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */ +#define CLONE_PIDFD 0x00001000 /* set if a pidfd should be placed in parent */ #define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */ #define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */ #define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */ -- cgit v1.2.3 From b5b999dca673bd7b2d4c267faf3478dca7baff7f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 21 May 2019 17:07:20 -0300 Subject: tools headers UAPI: Sync linux/fs.h with the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To pick up the changes in: c553ea4fdf27 ("fs/sync.c: sync_file_range(2) may use WB_SYNC_ALL writeback") That should be used to beautify the 'sync_file_range' syscall 'flags' arg. This silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/fs.h' differs from latest version at 'include/uapi/linux/fs.h' diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h Cc: Adrian Hunter Cc: Amir Goldstein Cc: Brendan Gregg Cc: Jiri Olsa Cc: Linus Torvalds Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-at3uoqcvmqdkwaysmvbj1wpv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index 121e82ce296b..59c71fa8c553 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -320,6 +320,9 @@ struct fscrypt_key { #define SYNC_FILE_RANGE_WAIT_BEFORE 1 #define SYNC_FILE_RANGE_WRITE 2 #define SYNC_FILE_RANGE_WAIT_AFTER 4 +#define SYNC_FILE_RANGE_WRITE_AND_WAIT (SYNC_FILE_RANGE_WRITE | \ + SYNC_FILE_RANGE_WAIT_BEFORE | \ + SYNC_FILE_RANGE_WAIT_AFTER) /* * Flags for preadv2/pwritev2: -- cgit v1.2.3 From e6aff9f8bfbecd4610ce0e2f4811cea42494dc62 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 22 May 2019 07:58:44 -0300 Subject: tools headers UAPI: Sync drm/i915_drm.h with the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To pick up the changes from: d1172ab3d443 ("drm/i915: Introduce struct class_instance for engines across the uAPI") 96fd2c6633b0 ("drm/i915: Drop new chunks of context creation ABI (for now)") ea593dbba4c8 ("drm/i915: Allow contexts to share a single timeline across all engines") b91715417244 ("drm/i915: Extend CONTEXT_CREATE to set parameters upon construction") e0695db7298e ("drm/i915: Create/destroy VM (ppGTT) for use with contexts") 9d1305ef80b9 ("drm/i915: Introduce the i915_user_extension_method") c8b502422bfe ("drm/i915: Remove last traces of exec-id (GEM_BUSY)") d90c06d57027 ("drm/i915: Fix I915_EXEC_RING_MASK") e88619646971 ("drm/i915: Use HW semaphores for inter-engine synchronisation on gen8+") be03564bd7b6 ("drm/i915: Include reminders about leaving no holes in uAPI enums") ba4fda620a5f ("drm/i915: Optionally disable automatic recovery after a GPU reset") We still don't take into account the _IOC_SIZE() to differentiate ioctl cmds, so more work is needed to support the extension mechanism that is being used here so that we can differentiate DRM_IOCTL_I915_GEM_CONTEXT_CREATE from the newly introduced DRM_IOCTL_I915_GEM_CONTEXT_CREATE_EXT cmd. This silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h' diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h Cc: Adrian Hunter Cc: Brendan Gregg Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Chris Wilson Link: https://lkml.kernel.org/n/tip-csn0vanmc7pevyka5qcg0xyw@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/i915_drm.h | 254 +++++++++++++++++++++++++++----------- 1 file changed, 181 insertions(+), 73 deletions(-) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 397810fa2d33..3a73f5316766 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -62,6 +62,28 @@ extern "C" { #define I915_ERROR_UEVENT "ERROR" #define I915_RESET_UEVENT "RESET" +/* + * i915_user_extension: Base class for defining a chain of extensions + * + * Many interfaces need to grow over time. In most cases we can simply + * extend the struct and have userspace pass in more data. Another option, + * as demonstrated by Vulkan's approach to providing extensions for forward + * and backward compatibility, is to use a list of optional structs to + * provide those extra details. + * + * The key advantage to using an extension chain is that it allows us to + * redefine the interface more easily than an ever growing struct of + * increasing complexity, and for large parts of that interface to be + * entirely optional. The downside is more pointer chasing; chasing across + * the __user boundary with pointers encapsulated inside u64. + */ +struct i915_user_extension { + __u64 next_extension; + __u32 name; + __u32 flags; /* All undefined bits must be zero. */ + __u32 rsvd[4]; /* Reserved for future use; must be zero. */ +}; + /* * MOCS indexes used for GPU surfaces, defining the cacheability of the * surface data and the coherency for this data wrt. CPU vs. GPU accesses. @@ -99,9 +121,23 @@ enum drm_i915_gem_engine_class { I915_ENGINE_CLASS_VIDEO = 2, I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, + /* should be kept compact */ + I915_ENGINE_CLASS_INVALID = -1 }; +/* + * There may be more than one engine fulfilling any role within the system. + * Each engine of a class is given a unique instance number and therefore + * any engine can be specified by its class:instance tuplet. APIs that allow + * access to any engine in the system will use struct i915_engine_class_instance + * for this identification. + */ +struct i915_engine_class_instance { + __u16 engine_class; /* see enum drm_i915_gem_engine_class */ + __u16 engine_instance; +}; + /** * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915 * @@ -319,6 +355,7 @@ typedef struct _drm_i915_sarea { #define DRM_I915_PERF_ADD_CONFIG 0x37 #define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_I915_QUERY 0x39 +/* Must be kept compact -- no holes */ #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -367,6 +404,7 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey) #define DRM_IOCTL_I915_GEM_WAIT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait) #define DRM_IOCTL_I915_GEM_CONTEXT_CREATE DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create) +#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE_EXT DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create_ext) #define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy) #define DRM_IOCTL_I915_REG_READ DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read) #define DRM_IOCTL_I915_GET_RESET_STATS DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats) @@ -476,6 +514,7 @@ typedef struct drm_i915_irq_wait { #define I915_SCHEDULER_CAP_ENABLED (1ul << 0) #define I915_SCHEDULER_CAP_PRIORITY (1ul << 1) #define I915_SCHEDULER_CAP_PREEMPTION (1ul << 2) +#define I915_SCHEDULER_CAP_SEMAPHORES (1ul << 3) #define I915_PARAM_HUC_STATUS 42 @@ -559,6 +598,8 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_MMAP_GTT_COHERENT 52 +/* Must be kept compact -- no holes and well documented */ + typedef struct drm_i915_getparam { __s32 param; /* @@ -574,6 +615,7 @@ typedef struct drm_i915_getparam { #define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY 2 #define I915_SETPARAM_ALLOW_BATCHBUFFER 3 #define I915_SETPARAM_NUM_USED_FENCES 4 +/* Must be kept compact -- no holes */ typedef struct drm_i915_setparam { int param; @@ -972,7 +1014,7 @@ struct drm_i915_gem_execbuffer2 { * struct drm_i915_gem_exec_fence *fences. */ __u64 cliprects_ptr; -#define I915_EXEC_RING_MASK (7<<0) +#define I915_EXEC_RING_MASK (0x3f) #define I915_EXEC_DEFAULT (0<<0) #define I915_EXEC_RENDER (1<<0) #define I915_EXEC_BSD (2<<0) @@ -1120,32 +1162,34 @@ struct drm_i915_gem_busy { * as busy may become idle before the ioctl is completed. * * Furthermore, if the object is busy, which engine is busy is only - * provided as a guide. There are race conditions which prevent the - * report of which engines are busy from being always accurate. - * However, the converse is not true. If the object is idle, the - * result of the ioctl, that all engines are idle, is accurate. + * provided as a guide and only indirectly by reporting its class + * (there may be more than one engine in each class). There are race + * conditions which prevent the report of which engines are busy from + * being always accurate. However, the converse is not true. If the + * object is idle, the result of the ioctl, that all engines are idle, + * is accurate. * * The returned dword is split into two fields to indicate both - * the engines on which the object is being read, and the - * engine on which it is currently being written (if any). + * the engine classess on which the object is being read, and the + * engine class on which it is currently being written (if any). * * The low word (bits 0:15) indicate if the object is being written * to by any engine (there can only be one, as the GEM implicit * synchronisation rules force writes to be serialised). Only the - * engine for the last write is reported. + * engine class (offset by 1, I915_ENGINE_CLASS_RENDER is reported as + * 1 not 0 etc) for the last write is reported. * - * The high word (bits 16:31) are a bitmask of which engines are - * currently reading from the object. Multiple engines may be + * The high word (bits 16:31) are a bitmask of which engines classes + * are currently reading from the object. Multiple engines may be * reading from the object simultaneously. * - * The value of each engine is the same as specified in the - * EXECBUFFER2 ioctl, i.e. I915_EXEC_RENDER, I915_EXEC_BSD etc. - * Note I915_EXEC_DEFAULT is a symbolic value and is mapped to - * the I915_EXEC_RENDER engine for execution, and so it is never + * The value of each engine class is the same as specified in the + * I915_CONTEXT_SET_ENGINES parameter and via perf, i.e. + * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc. * reported as active itself. Some hardware may have parallel * execution engines, e.g. multiple media engines, which are - * mapped to the same identifier in the EXECBUFFER2 ioctl and - * so are not separately reported for busyness. + * mapped to the same class identifier and so are not separately + * reported for busyness. * * Caveat emptor: * Only the boolean result of this query is reliable; that is whether @@ -1412,65 +1456,17 @@ struct drm_i915_gem_wait { }; struct drm_i915_gem_context_create { - /* output: id of new context*/ - __u32 ctx_id; - __u32 pad; -}; - -struct drm_i915_gem_context_destroy { - __u32 ctx_id; + __u32 ctx_id; /* output: id of new context*/ __u32 pad; }; -struct drm_i915_reg_read { - /* - * Register offset. - * For 64bit wide registers where the upper 32bits don't immediately - * follow the lower 32bits, the offset of the lower 32bits must - * be specified - */ - __u64 offset; -#define I915_REG_READ_8B_WA (1ul << 0) - - __u64 val; /* Return value */ -}; -/* Known registers: - * - * Render engine timestamp - 0x2358 + 64bit - gen7+ - * - Note this register returns an invalid value if using the default - * single instruction 8byte read, in order to workaround that pass - * flag I915_REG_READ_8B_WA in offset field. - * - */ - -struct drm_i915_reset_stats { - __u32 ctx_id; - __u32 flags; - - /* All resets since boot/module reload, for all contexts */ - __u32 reset_count; - - /* Number of batches lost when active in GPU, for this context */ - __u32 batch_active; - - /* Number of batches lost pending for execution, for this context */ - __u32 batch_pending; - - __u32 pad; -}; - -struct drm_i915_gem_userptr { - __u64 user_ptr; - __u64 user_size; +struct drm_i915_gem_context_create_ext { + __u32 ctx_id; /* output: id of new context*/ __u32 flags; -#define I915_USERPTR_READ_ONLY 0x1 -#define I915_USERPTR_UNSYNCHRONIZED 0x80000000 - /** - * Returned handle for the object. - * - * Object handles are nonzero. - */ - __u32 handle; +#define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0) +#define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \ + (-(I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS << 1)) + __u64 extensions; }; struct drm_i915_gem_context_param { @@ -1491,6 +1487,28 @@ struct drm_i915_gem_context_param { * drm_i915_gem_context_param_sseu. */ #define I915_CONTEXT_PARAM_SSEU 0x7 + +/* + * Not all clients may want to attempt automatic recover of a context after + * a hang (for example, some clients may only submit very small incremental + * batches relying on known logical state of previous batches which will never + * recover correctly and each attempt will hang), and so would prefer that + * the context is forever banned instead. + * + * If set to false (0), after a reset, subsequent (and in flight) rendering + * from this context is discarded, and the client will need to create a new + * context to use instead. + * + * If set to true (1), the kernel will automatically attempt to recover the + * context by skipping the hanging batch and executing the next batch starting + * from the default context state (discarding the incomplete logical context + * state lost due to the reset). + * + * On creation, all new contexts are marked as recoverable. + */ +#define I915_CONTEXT_PARAM_RECOVERABLE 0x8 +/* Must be kept compact -- no holes and well documented */ + __u64 value; }; @@ -1519,8 +1537,7 @@ struct drm_i915_gem_context_param_sseu { /* * Engine class & instance to be configured or queried. */ - __u16 engine_class; - __u16 engine_instance; + struct i915_engine_class_instance engine; /* * Unused for now. Must be cleared to zero. @@ -1553,6 +1570,96 @@ struct drm_i915_gem_context_param_sseu { __u32 rsvd; }; +struct drm_i915_gem_context_create_ext_setparam { +#define I915_CONTEXT_CREATE_EXT_SETPARAM 0 + struct i915_user_extension base; + struct drm_i915_gem_context_param param; +}; + +struct drm_i915_gem_context_destroy { + __u32 ctx_id; + __u32 pad; +}; + +/* + * DRM_I915_GEM_VM_CREATE - + * + * Create a new virtual memory address space (ppGTT) for use within a context + * on the same file. Extensions can be provided to configure exactly how the + * address space is setup upon creation. + * + * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is + * returned in the outparam @id. + * + * No flags are defined, with all bits reserved and must be zero. + * + * An extension chain maybe provided, starting with @extensions, and terminated + * by the @next_extension being 0. Currently, no extensions are defined. + * + * DRM_I915_GEM_VM_DESTROY - + * + * Destroys a previously created VM id, specified in @id. + * + * No extensions or flags are allowed currently, and so must be zero. + */ +struct drm_i915_gem_vm_control { + __u64 extensions; + __u32 flags; + __u32 vm_id; +}; + +struct drm_i915_reg_read { + /* + * Register offset. + * For 64bit wide registers where the upper 32bits don't immediately + * follow the lower 32bits, the offset of the lower 32bits must + * be specified + */ + __u64 offset; +#define I915_REG_READ_8B_WA (1ul << 0) + + __u64 val; /* Return value */ +}; + +/* Known registers: + * + * Render engine timestamp - 0x2358 + 64bit - gen7+ + * - Note this register returns an invalid value if using the default + * single instruction 8byte read, in order to workaround that pass + * flag I915_REG_READ_8B_WA in offset field. + * + */ + +struct drm_i915_reset_stats { + __u32 ctx_id; + __u32 flags; + + /* All resets since boot/module reload, for all contexts */ + __u32 reset_count; + + /* Number of batches lost when active in GPU, for this context */ + __u32 batch_active; + + /* Number of batches lost pending for execution, for this context */ + __u32 batch_pending; + + __u32 pad; +}; + +struct drm_i915_gem_userptr { + __u64 user_ptr; + __u64 user_size; + __u32 flags; +#define I915_USERPTR_READ_ONLY 0x1 +#define I915_USERPTR_UNSYNCHRONIZED 0x80000000 + /** + * Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; +}; + enum drm_i915_oa_format { I915_OA_FORMAT_A13 = 1, /* HSW only */ I915_OA_FORMAT_A29, /* HSW only */ @@ -1714,6 +1821,7 @@ struct drm_i915_perf_oa_config { struct drm_i915_query_item { __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 +/* Must be kept compact -- no holes and well documented */ /* * When set to zero by userspace, this is filled with the size of the -- cgit v1.2.3 From 9903c64f0fe7fa4829c948fa0e742f578e084548 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 22 May 2019 10:26:12 -0300 Subject: tools headers UAPI: Sync drm/drm.h with the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To pick up the changes in these csets: 060cebb20cdb ("drm: introduce a capability flag for syncobj timeline support") 50d1ebef79ef ("drm/syncobj: add timeline signal ioctl for syncobj v5") ea569910cbab ("drm/syncobj: add transition iotcls between binary and timeline v2") 27b575a9aa2f ("drm/syncobj: add timeline payload query ioctl v6") 01d6c3578379 ("drm/syncobj: add support for timeline point wait v8") 783195ec1cad ("drm/syncobj: disable the timeline UAPI for now v2") 48197bc564c7 ("drm: add syncobj timeline support v9") Which automagically results in the following new ioctls being recognized by the 'perf trace' ioctl cmd arg beautifier: $ tools/perf/trace/beauty/drm_ioctl.sh > /tmp/before $ cp include/uapi/drm/drm.h tools/include/uapi/drm/drm.h $ tools/perf/trace/beauty/drm_ioctl.sh > /tmp/after $ diff -u /tmp/before /tmp/after --- /tmp/before 2019-05-22 10:25:31.443151182 -0300 +++ /tmp/after 2019-05-22 10:25:46.449354819 -0300 @@ -103,6 +103,10 @@ [0xC7] = "MODE_LIST_LESSEES", [0xC8] = "MODE_GET_LEASE", [0xC9] = "MODE_REVOKE_LEASE", + [0xCA] = "SYNCOBJ_TIMELINE_WAIT", + [0xCB] = "SYNCOBJ_QUERY", + [0xCC] = "SYNCOBJ_TRANSFER", + [0xCD] = "SYNCOBJ_TIMELINE_SIGNAL", [DRM_COMMAND_BASE + 0x00] = "I915_INIT", [DRM_COMMAND_BASE + 0x01] = "I915_FLUSH", [DRM_COMMAND_BASE + 0x02] = "I915_FLIP", $ I.e. the strace like raw_tracepoint:sys_enter handler in 'perf trace' will get the cmd integer value and map it to the string. At some point it should be possible to translate from string to integer and use to filter using expressions such as: # perf trace -e ioctl/cmd==DRM_IOCTL_SYNCOBJ*/ Or some more suitable syntax to express that only these ioctls when acting on DRM fds should be shown. Acked-by: Lionel Landwerlin Cc: Adrian Hunter Cc: Brendan Gregg Cc: Christian König Cc: Chunming Zhou Cc: Dave Airlie Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-jrc9ogw33w4zgqc3pu7o1l3g@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/drm.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 300f336633f2..661d73f9a919 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -649,6 +649,7 @@ struct drm_gem_open { #define DRM_CAP_PAGE_FLIP_TARGET 0x11 #define DRM_CAP_CRTC_IN_VBLANK_EVENT 0x12 #define DRM_CAP_SYNCOBJ 0x13 +#define DRM_CAP_SYNCOBJ_TIMELINE 0x14 /** DRM_IOCTL_GET_CAP ioctl argument type */ struct drm_get_cap { @@ -735,8 +736,18 @@ struct drm_syncobj_handle { __u32 pad; }; +struct drm_syncobj_transfer { + __u32 src_handle; + __u32 dst_handle; + __u64 src_point; + __u64 dst_point; + __u32 flags; + __u32 pad; +}; + #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */ struct drm_syncobj_wait { __u64 handles; /* absolute timeout */ @@ -747,12 +758,33 @@ struct drm_syncobj_wait { __u32 pad; }; +struct drm_syncobj_timeline_wait { + __u64 handles; + /* wait on specific timeline point for every handles*/ + __u64 points; + /* absolute timeout */ + __s64 timeout_nsec; + __u32 count_handles; + __u32 flags; + __u32 first_signaled; /* only valid when not waiting all */ + __u32 pad; +}; + + struct drm_syncobj_array { __u64 handles; __u32 count_handles; __u32 pad; }; +struct drm_syncobj_timeline_array { + __u64 handles; + __u64 points; + __u32 count_handles; + __u32 pad; +}; + + /* Query current scanout sequence number */ struct drm_crtc_get_sequence { __u32 crtc_id; /* requested crtc_id */ @@ -909,6 +941,11 @@ extern "C" { #define DRM_IOCTL_MODE_GET_LEASE DRM_IOWR(0xC8, struct drm_mode_get_lease) #define DRM_IOCTL_MODE_REVOKE_LEASE DRM_IOWR(0xC9, struct drm_mode_revoke_lease) +#define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait) +#define DRM_IOCTL_SYNCOBJ_QUERY DRM_IOWR(0xCB, struct drm_syncobj_timeline_array) +#define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) +#define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) + /** * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. -- cgit v1.2.3 From 6584140ba9e6762dd7ec73795243289b914f31f9 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 22 May 2019 14:32:48 +0900 Subject: perf namespace: Protect reading thread's namespace It seems that the current code lacks holding the namespace lock in thread__namespaces(). Otherwise it can see inconsistent results. Signed-off-by: Namhyung Kim Cc: Hari Bathini Cc: Jiri Olsa Cc: Krister Johansen Link: http://lkml.kernel.org/r/20190522053250.207156-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/thread.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 403045a2bbea..b413ba5b9835 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -133,7 +133,7 @@ void thread__put(struct thread *thread) } } -struct namespaces *thread__namespaces(const struct thread *thread) +static struct namespaces *__thread__namespaces(const struct thread *thread) { if (list_empty(&thread->namespaces_list)) return NULL; @@ -141,10 +141,21 @@ struct namespaces *thread__namespaces(const struct thread *thread) return list_first_entry(&thread->namespaces_list, struct namespaces, list); } +struct namespaces *thread__namespaces(const struct thread *thread) +{ + struct namespaces *ns; + + down_read((struct rw_semaphore *)&thread->namespaces_lock); + ns = __thread__namespaces(thread); + up_read((struct rw_semaphore *)&thread->namespaces_lock); + + return ns; +} + static int __thread__set_namespaces(struct thread *thread, u64 timestamp, struct namespaces_event *event) { - struct namespaces *new, *curr = thread__namespaces(thread); + struct namespaces *new, *curr = __thread__namespaces(thread); new = namespaces__new(event); if (!new) -- cgit v1.2.3 From acd244b84b80d53fa2cee98659b55d3f09b4f5a7 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 22 May 2019 14:32:49 +0900 Subject: perf session: Add missing swap ops for namespace events In case it's recorded in a different arch. Signed-off-by: Namhyung Kim Cc: Hari Bathini Cc: Jiri Olsa Cc: Krister Johansen Fixes: f3b3614a284d ("perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info") Link: http://lkml.kernel.org/r/20190522053250.207156-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 2310a1752983..54cf163347f7 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -647,6 +647,26 @@ static void perf_event__throttle_swap(union perf_event *event, swap_sample_id_all(event, &event->throttle + 1); } +static void perf_event__namespaces_swap(union perf_event *event, + bool sample_id_all) +{ + u64 i; + + event->namespaces.pid = bswap_32(event->namespaces.pid); + event->namespaces.tid = bswap_32(event->namespaces.tid); + event->namespaces.nr_namespaces = bswap_64(event->namespaces.nr_namespaces); + + for (i = 0; i < event->namespaces.nr_namespaces; i++) { + struct perf_ns_link_info *ns = &event->namespaces.link_info[i]; + + ns->dev = bswap_64(ns->dev); + ns->ino = bswap_64(ns->ino); + } + + if (sample_id_all) + swap_sample_id_all(event, &event->namespaces.link_info[i]); +} + static u8 revbyte(u8 b) { int rev = (b >> 4) | ((b & 0xf) << 4); @@ -887,6 +907,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_LOST_SAMPLES] = perf_event__all64_swap, [PERF_RECORD_SWITCH] = perf_event__switch_swap, [PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap, + [PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, -- cgit v1.2.3 From 93f678b9ae8feb7f7cec29c2dcbb5756ad22d9a1 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 24 May 2019 15:39:00 -0300 Subject: perf test vmlinux-kallsyms: Ignore aliases to _etext when searching on kallsyms No need to search for aliases for the symbol that marks the end of the kernel text segment, the following patch will make such symbols not to be found when searching in the kallsyms maps causing this test to fail. So as a prep patch to avoid breaking bisection, ignore such symbols. Tested-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stanislav Fomichev Cc: Thomas Richter Link: https://lkml.kernel.org/n/tip-qfwuih8cvmk9doh7k5k244eq@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/vmlinux-kallsyms.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 7691980b7df1..f101576d1c72 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -161,9 +161,16 @@ next_pair: continue; } - } else + } else if (mem_start == kallsyms.vmlinux_map->end) { + /* + * Ignore aliases to _etext, i.e. to the end of the kernel text area, + * such as __indirect_thunk_end. + */ + continue; + } else { pr_debug("ERR : %#" PRIx64 ": %s not on kallsyms\n", mem_start, sym->name); + } err = -1; } -- cgit v1.2.3 From ed9adb2035b5be5896d465b19040262be5f4a824 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 8 May 2019 15:20:03 +0200 Subject: perf machine: Read also the end of the kernel We mark the end of kernel based on the first module, but that could cover some bpf program maps. Reading _etext symbol if it's present to get precise kernel map end. Signed-off-by: Jiri Olsa Acked-by: Song Liu Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: Thomas Richter Link: http://lkml.kernel.org/r/20190508132010.14512-6-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 28a9541c4835..dc7aafe45a2b 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -924,7 +924,8 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; * symbol_name if it's not that important. */ static int machine__get_running_kernel_start(struct machine *machine, - const char **symbol_name, u64 *start) + const char **symbol_name, + u64 *start, u64 *end) { char filename[PATH_MAX]; int i, err = -1; @@ -949,6 +950,11 @@ static int machine__get_running_kernel_start(struct machine *machine, *symbol_name = name; *start = addr; + + err = kallsyms__get_function_start(filename, "_etext", &addr); + if (!err) + *end = addr; + return 0; } @@ -1441,7 +1447,7 @@ int machine__create_kernel_maps(struct machine *machine) struct dso *kernel = machine__get_kernel(machine); const char *name = NULL; struct map *map; - u64 addr = 0; + u64 start = 0, end = ~0ULL; int ret; if (kernel == NULL) @@ -1460,9 +1466,9 @@ int machine__create_kernel_maps(struct machine *machine) "continuing anyway...\n", machine->pid); } - if (!machine__get_running_kernel_start(machine, &name, &addr)) { + if (!machine__get_running_kernel_start(machine, &name, &start, &end)) { if (name && - map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, addr)) { + map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, start)) { machine__destroy_kernel_maps(machine); ret = -1; goto out_put; @@ -1472,16 +1478,19 @@ int machine__create_kernel_maps(struct machine *machine) * we have a real start address now, so re-order the kmaps * assume it's the last in the kmaps */ - machine__update_kernel_mmap(machine, addr, ~0ULL); + machine__update_kernel_mmap(machine, start, end); } if (machine__create_extra_kernel_maps(machine, kernel)) pr_debug("Problems creating extra kernel maps, continuing anyway...\n"); - /* update end address of the kernel map using adjacent module address */ - map = map__next(machine__kernel_map(machine)); - if (map) - machine__set_kernel_mmap(machine, addr, map->start); + if (end == ~0ULL) { + /* update end address of the kernel map using adjacent module address */ + map = map__next(machine__kernel_map(machine)); + if (map) + machine__set_kernel_mmap(machine, start, map->start); + } + out_put: dso__put(kernel); return ret; -- cgit v1.2.3 From 6738028dd57df064b969d8392c943ef3b3ae705d Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 22 May 2019 16:46:01 +0200 Subject: perf record: Fix s390 missing module symbol and warning for non-root users Command 'perf record' and 'perf report' on a system without kernel debuginfo packages uses /proc/kallsyms and /proc/modules to find addresses for kernel and module symbols. On x86 this works for root and non-root users. On s390, when invoked as non-root user, many of the following warnings are shown and module symbols are missing: proc/{kallsyms,modules} inconsistency while looking for "[sha1_s390]" module! Command 'perf record' creates a list of module start addresses by parsing the output of /proc/modules and creates a PERF_RECORD_MMAP record for the kernel and each module. The following function call sequence is executed: machine__create_kernel_maps machine__create_module modules__parse machine__create_module --> for each line in /proc/modules arch__fix_module_text_start Function arch__fix_module_text_start() is s390 specific. It opens file /sys/module//sections/.text to extract the module's .text section start address. On s390 the module loader prepends a header before the first section, whereas on x86 the module's text section address is identical the the module's load address. However module section files are root readable only. For non-root the read operation fails and machine__create_module() returns an error. Command perf record does not generate any PERF_RECORD_MMAP record for loaded modules. Later command perf report complains about missing module maps. To fix this function arch__fix_module_text_start() always returns success. For root users there is no change, for non-root users the module's load address is used as module's text start address (the prepended header then counts as part of the text section). This enable non-root users to use module symbols and avoid the warning when perf report is executed. Output before: [tmricht@m83lp54 perf]$ ./perf report -D | fgrep MMAP 0 0x168 [0x50]: PERF_RECORD_MMAP ... x [kernel.kallsyms]_text Output after: [tmricht@m83lp54 perf]$ ./perf report -D | fgrep MMAP 0 0x168 [0x50]: PERF_RECORD_MMAP ... x [kernel.kallsyms]_text 0 0x1b8 [0x98]: PERF_RECORD_MMAP ... x /lib/modules/.../autofs4.ko.xz 0 0x250 [0xa8]: PERF_RECORD_MMAP ... x /lib/modules/.../sha_common.ko.xz 0 0x2f8 [0x98]: PERF_RECORD_MMAP ... x /lib/modules/.../des_generic.ko.xz Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Cc: Heiko Carstens Link: http://lkml.kernel.org/r/20190522144601.50763-4-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/machine.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index 0b2054007314..a19690a17291 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -5,16 +5,19 @@ #include "util.h" #include "machine.h" #include "api/fs/fs.h" +#include "debug.h" int arch__fix_module_text_start(u64 *start, const char *name) { + u64 m_start = *start; char path[PATH_MAX]; snprintf(path, PATH_MAX, "module/%.*s/sections/.text", (int)strlen(name) - 2, name + 1); - - if (sysfs__read_ull(path, (unsigned long long *)start) < 0) - return -1; + if (sysfs__read_ull(path, (unsigned long long *)start) < 0) { + pr_debug2("Using module %s start:%#lx\n", path, m_start); + *start = m_start; + } return 0; } -- cgit v1.2.3 From a7350998a25ac10cdca5b33dee1d343a74debbfe Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 24 May 2019 14:04:15 -0300 Subject: tools headers UAPI: Sync kvm.h headers with the kernel sources MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dd53f6102c30 ("Merge tag 'kvmarm-for-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD") 59c5c58c5b93 ("Merge tag 'kvm-ppc-next-5.2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD") d7547c55cbe7 ("KVM: Introduce KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2") 6520ca64cde7 ("KVM: PPC: Book3S HV: XIVE: Add a mapping for the source ESB pages") 39e9af3de5ca ("KVM: PPC: Book3S HV: XIVE: Add a TIMA mapping") e4945b9da52b ("KVM: PPC: Book3S HV: XIVE: Add get/set accessors for the VP XIVE state") e6714bd1671d ("KVM: PPC: Book3S HV: XIVE: Add a control to dirty the XIVE EQ pages") 7b46b6169ab8 ("KVM: PPC: Book3S HV: XIVE: Add a control to sync the sources") 5ca806474859 ("KVM: PPC: Book3S HV: XIVE: Add a global reset control") 13ce3297c576 ("KVM: PPC: Book3S HV: XIVE: Add controls for the EQ configuration") e8676ce50e22 ("KVM: PPC: Book3S HV: XIVE: Add a control to configure a source") 4131f83c3d64 ("KVM: PPC: Book3S HV: XIVE: add a control to initialize a source") eacc56bb9de3 ("KVM: PPC: Book3S HV: XIVE: Introduce a new capability KVM_CAP_PPC_IRQ_XIVE") 90c73795afa2 ("KVM: PPC: Book3S HV: Add a new KVM device for the XIVE native exploitation mode") 4f45b90e1c03 ("KVM: s390: add deflate conversion facilty to cpu model") a243c16d18be ("KVM: arm64: Add capability to advertise ptrauth for guest") a22fa321d13b ("KVM: arm64: Add userspace flag to enable pointer authentication") 4bd774e57b29 ("KVM: arm64/sve: Simplify KVM_REG_ARM64_SVE_VLS array sizing") 8ae6efdde451 ("KVM: arm64/sve: Clean up UAPI register ID definitions") 173aec2d5a9f ("KVM: s390: add enhanced sort facilty to cpu model") 555f3d03e7fb ("KVM: arm64: Add a capability to advertise SVE support") 9033bba4b535 ("KVM: arm64/sve: Add pseudo-register for the guest's vector lengths") 7dd32a0d0103 ("KVM: arm/arm64: Add KVM_ARM_VCPU_FINALIZE ioctl") e1c9c98345b3 ("KVM: arm64/sve: Add SVE support to register access ioctl interface") 2b953ea34812 ("KVM: Allow 2048-bit register access via ioctl interface") None entails changes in tooling, the closest to that were some new arch specific ioctls, that are still not handled by the tools/perf/trace/beauty/ library, that needs to create per-arch tables to convert ioctl cmd->string (and back). From a quick look the arch specific kvm-stat.c files at: $ ls -1 tools/perf/arch/*/util/kvm-stat.c tools/perf/arch/powerpc/util/kvm-stat.c tools/perf/arch/s390/util/kvm-stat.c tools/perf/arch/x86/util/kvm-stat.c $ Are not affected. This silences these perf building warnings: Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h' diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h Warning: Kernel ABI header at 'tools/arch/powerpc/include/uapi/asm/kvm.h' differs from latest version at 'arch/powerpc/include/uapi/asm/kvm.h' diff -u tools/arch/powerpc/include/uapi/asm/kvm.h arch/powerpc/include/uapi/asm/kvm.h Warning: Kernel ABI header at 'tools/arch/s390/include/uapi/asm/kvm.h' differs from latest version at 'arch/s390/include/uapi/asm/kvm.h' diff -u tools/arch/s390/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm.h Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Cc: Adrian Hunter Cc: Amit Daniel Kachhap Cc: Brendan Gregg Cc: Cédric Le Goater Cc: Christian Borntraeger Cc: Dave Martin Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Marc Zyngier Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Paul Mackerras Cc: Peter Xu Link: https://lkml.kernel.org/n/tip-3msmqjenlmb7eygcdnmlqaq1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/kvm.h | 43 +++++++++++++++++++++++++++++ tools/arch/powerpc/include/uapi/asm/kvm.h | 46 +++++++++++++++++++++++++++++++ tools/arch/s390/include/uapi/asm/kvm.h | 4 ++- tools/include/uapi/linux/kvm.h | 15 ++++++++-- 4 files changed, 105 insertions(+), 3 deletions(-) diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 97c3478ee6e7..7b7ac0f6cec9 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -35,6 +35,7 @@ #include #include #include +#include #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE @@ -102,6 +103,9 @@ struct kvm_regs { #define KVM_ARM_VCPU_EL1_32BIT 1 /* CPU running a 32bit VM */ #define KVM_ARM_VCPU_PSCI_0_2 2 /* CPU uses PSCI v0.2 */ #define KVM_ARM_VCPU_PMU_V3 3 /* Support guest PMUv3 */ +#define KVM_ARM_VCPU_SVE 4 /* enable SVE for this CPU */ +#define KVM_ARM_VCPU_PTRAUTH_ADDRESS 5 /* VCPU uses address authentication */ +#define KVM_ARM_VCPU_PTRAUTH_GENERIC 6 /* VCPU uses generic authentication */ struct kvm_vcpu_init { __u32 target; @@ -226,6 +230,45 @@ struct kvm_vcpu_events { KVM_REG_ARM_FW | ((r) & 0xffff)) #define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) +/* SVE registers */ +#define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) + +/* Z- and P-regs occupy blocks at the following offsets within this range: */ +#define KVM_REG_ARM64_SVE_ZREG_BASE 0 +#define KVM_REG_ARM64_SVE_PREG_BASE 0x400 +#define KVM_REG_ARM64_SVE_FFR_BASE 0x600 + +#define KVM_ARM64_SVE_NUM_ZREGS __SVE_NUM_ZREGS +#define KVM_ARM64_SVE_NUM_PREGS __SVE_NUM_PREGS + +#define KVM_ARM64_SVE_MAX_SLICES 32 + +#define KVM_REG_ARM64_SVE_ZREG(n, i) \ + (KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_ZREG_BASE | \ + KVM_REG_SIZE_U2048 | \ + (((n) & (KVM_ARM64_SVE_NUM_ZREGS - 1)) << 5) | \ + ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1))) + +#define KVM_REG_ARM64_SVE_PREG(n, i) \ + (KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_PREG_BASE | \ + KVM_REG_SIZE_U256 | \ + (((n) & (KVM_ARM64_SVE_NUM_PREGS - 1)) << 5) | \ + ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1))) + +#define KVM_REG_ARM64_SVE_FFR(i) \ + (KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_FFR_BASE | \ + KVM_REG_SIZE_U256 | \ + ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1))) + +#define KVM_ARM64_SVE_VQ_MIN __SVE_VQ_MIN +#define KVM_ARM64_SVE_VQ_MAX __SVE_VQ_MAX + +/* Vector lengths pseudo-register: */ +#define KVM_REG_ARM64_SVE_VLS (KVM_REG_ARM64 | KVM_REG_ARM64_SVE | \ + KVM_REG_SIZE_U512 | 0xffff) +#define KVM_ARM64_SVE_VLS_WORDS \ + ((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1) + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 26ca425f4c2c..b0f72dea8b11 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -482,6 +482,8 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_ICP_PPRI_SHIFT 16 /* pending irq priority */ #define KVM_REG_PPC_ICP_PPRI_MASK 0xff +#define KVM_REG_PPC_VP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x8d) + /* Device control API: PPC-specific devices */ #define KVM_DEV_MPIC_GRP_MISC 1 #define KVM_DEV_MPIC_BASE_ADDR 0 /* 64-bit */ @@ -677,4 +679,48 @@ struct kvm_ppc_cpu_char { #define KVM_XICS_PRESENTED (1ULL << 43) #define KVM_XICS_QUEUED (1ULL << 44) +/* POWER9 XIVE Native Interrupt Controller */ +#define KVM_DEV_XIVE_GRP_CTRL 1 +#define KVM_DEV_XIVE_RESET 1 +#define KVM_DEV_XIVE_EQ_SYNC 2 +#define KVM_DEV_XIVE_GRP_SOURCE 2 /* 64-bit source identifier */ +#define KVM_DEV_XIVE_GRP_SOURCE_CONFIG 3 /* 64-bit source identifier */ +#define KVM_DEV_XIVE_GRP_EQ_CONFIG 4 /* 64-bit EQ identifier */ +#define KVM_DEV_XIVE_GRP_SOURCE_SYNC 5 /* 64-bit source identifier */ + +/* Layout of 64-bit XIVE source attribute values */ +#define KVM_XIVE_LEVEL_SENSITIVE (1ULL << 0) +#define KVM_XIVE_LEVEL_ASSERTED (1ULL << 1) + +/* Layout of 64-bit XIVE source configuration attribute values */ +#define KVM_XIVE_SOURCE_PRIORITY_SHIFT 0 +#define KVM_XIVE_SOURCE_PRIORITY_MASK 0x7 +#define KVM_XIVE_SOURCE_SERVER_SHIFT 3 +#define KVM_XIVE_SOURCE_SERVER_MASK 0xfffffff8ULL +#define KVM_XIVE_SOURCE_MASKED_SHIFT 32 +#define KVM_XIVE_SOURCE_MASKED_MASK 0x100000000ULL +#define KVM_XIVE_SOURCE_EISN_SHIFT 33 +#define KVM_XIVE_SOURCE_EISN_MASK 0xfffffffe00000000ULL + +/* Layout of 64-bit EQ identifier */ +#define KVM_XIVE_EQ_PRIORITY_SHIFT 0 +#define KVM_XIVE_EQ_PRIORITY_MASK 0x7 +#define KVM_XIVE_EQ_SERVER_SHIFT 3 +#define KVM_XIVE_EQ_SERVER_MASK 0xfffffff8ULL + +/* Layout of EQ configuration values (64 bytes) */ +struct kvm_ppc_xive_eq { + __u32 flags; + __u32 qshift; + __u64 qaddr; + __u32 qtoggle; + __u32 qindex; + __u8 pad[40]; +}; + +#define KVM_XIVE_EQ_ALWAYS_NOTIFY 0x00000001 + +#define KVM_XIVE_TIMA_PAGE_OFFSET 0 +#define KVM_XIVE_ESB_PAGE_OFFSET 4 + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 09652eabe769..47104e5b47fd 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -153,7 +153,9 @@ struct kvm_s390_vm_cpu_subfunc { __u8 ppno[16]; /* with MSA5 */ __u8 kma[16]; /* with MSA8 */ __u8 kdsa[16]; /* with MSA9 */ - __u8 reserved[1792]; + __u8 sortl[32]; /* with STFLE.150 */ + __u8 dfltcc[32]; /* with STFLE.151 */ + __u8 reserved[1728]; }; /* kvm attributes for crypto */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 6d4ea4b6c922..2fe12b40d503 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -986,8 +986,13 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163 #define KVM_CAP_EXCEPTION_PAYLOAD 164 #define KVM_CAP_ARM_VM_IPA_SIZE 165 -#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 +#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 /* Obsolete */ #define KVM_CAP_HYPERV_CPUID 167 +#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 168 +#define KVM_CAP_PPC_IRQ_XIVE 169 +#define KVM_CAP_ARM_SVE 170 +#define KVM_CAP_ARM_PTRAUTH_ADDRESS 171 +#define KVM_CAP_ARM_PTRAUTH_GENERIC 172 #ifdef KVM_CAP_IRQ_ROUTING @@ -1145,6 +1150,7 @@ struct kvm_dirty_tlb { #define KVM_REG_SIZE_U256 0x0050000000000000ULL #define KVM_REG_SIZE_U512 0x0060000000000000ULL #define KVM_REG_SIZE_U1024 0x0070000000000000ULL +#define KVM_REG_SIZE_U2048 0x0080000000000000ULL struct kvm_reg_list { __u64 n; /* number of regs */ @@ -1211,6 +1217,8 @@ enum kvm_device_type { #define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_ITS, #define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS + KVM_DEV_TYPE_XIVE, +#define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_MAX, }; @@ -1434,12 +1442,15 @@ struct kvm_enc_region { #define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state) #define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state) -/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT */ +/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */ #define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log) /* Available with KVM_CAP_HYPERV_CPUID */ #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2) +/* Available with KVM_CAP_ARM_SVE */ +#define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3