xemu/trace-events

128 lines
5.1 KiB
Plaintext
Raw Normal View History

# Trace events for debugging and performance instrumentation
#
# This file is processed by the tracetool script during the build.
#
# To add a new trace event:
#
# 1. Choose a name for the trace event. Declare its arguments and format
# string.
#
# 2. Call the trace event from code using trace_##name, e.g. multiwrite_cb() ->
# trace_multiwrite_cb(). The source file must #include "trace.h".
#
# Format of a trace event:
#
# [disable] <name>(<type1> <arg1>[, <type2> <arg2>] ...) "<format-string>"
#
# Example: g_malloc(size_t size) "size %zu"
#
# The "disable" keyword will build without the trace event.
#
# The <name> must be a valid as a C function name.
#
# Types should be standard C types. Use void * for pointers because the trace
# system may not have the necessary headers included.
#
# The <format-string> should be a sprintf()-compatible format string.
# ioport.c
cpu_in(unsigned int addr, char size, unsigned int val) "addr %#x(%c) value %u"
cpu_out(unsigned int addr, char size, unsigned int val) "addr %#x(%c) value %u"
# balloon.c
# Since requests are raised via monitor, not many tracepoints are needed.
balloon_event(void *opaque, unsigned long addr) "opaque %p addr %lu"
# vl.c
vm_state_notify(int running, int reason) "running %d reason %d"
load_file(const char *name, const char *path) "name %s location %s"
runstate_set(int new_state) "new state %d"
system_wakeup_request(int reason) "reason=%d"
qemu_system_shutdown_request(int reason) "reason=%d"
2014-06-21 18:43:03 +00:00
qemu_system_powerdown_request(void) ""
# monitor.c
monitor_protocol_event_handler(uint32_t event, void *qdict) "event=%d data=%p"
monitor_protocol_event_emit(uint32_t event, void *data) "event=%d data=%p"
monitor_protocol_event_queue(uint32_t event, void *qdict, uint64_t rate) "event=%d data=%p rate=%" PRId64
handle_hmp_command(void *mon, const char *cmdline) "mon %p cmdline: %s"
handle_qmp_command(void *mon, const char *req) "mon %p req: %s"
# dma-helpers.c
dma_blk_io(void *dbs, void *bs, int64_t offset, bool to_dev) "dbs=%p bs=%p offset=%" PRId64 " to_dev=%d"
dma_aio_cancel(void *dbs) "dbs=%p"
dma_complete(void *dbs, int ret, void *cb) "dbs=%p ret=%d cb=%p"
dma_blk_cb(void *dbs, int ret) "dbs=%p ret=%d"
dma_map_wait(void *dbs) "dbs=%p"
# memory.c
memory_region_ops_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
memory_region_ops_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
memory_region_subpage_read(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset %#"PRIx64" value %#"PRIx64" size %u"
memory_region_subpage_write(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset %#"PRIx64" value %#"PRIx64" size %u"
memory_region_tb_read(int cpu_index, uint64_t addr, uint64_t value, unsigned size) "cpu %d addr %#"PRIx64" value %#"PRIx64" size %u"
memory_region_tb_write(int cpu_index, uint64_t addr, uint64_t value, unsigned size) "cpu %d addr %#"PRIx64" value %#"PRIx64" size %u"
memory: Don't use memcpy for ram_device regions With a vfio assigned device we lay down a base MemoryRegion registered as an IO region, giving us read & write accessors. If the region supports mmap, we lay down a higher priority sub-region MemoryRegion on top of the base layer initialized as a RAM device pointer to the mmap. Finally, if we have any quirks for the device (ie. address ranges that need additional virtualization support), we put another IO sub-region on top of the mmap MemoryRegion. When this is flattened, we now potentially have sub-page mmap MemoryRegions exposed which cannot be directly mapped through KVM. This is as expected, but a subtle detail of this is that we end up with two different access mechanisms through QEMU. If we disable the mmap MemoryRegion, we make use of the IO MemoryRegion and service accesses using pread and pwrite to the vfio device file descriptor. If the mmap MemoryRegion is enabled and results in one of these sub-page gaps, QEMU handles the access as RAM, using memcpy to the mmap. Using either pread/pwrite or the mmap directly should be correct, but using memcpy causes us problems. I expect that not only does memcpy not necessarily honor the original width and alignment in performing a copy, but it potentially also uses processor instructions not intended for MMIO spaces. It turns out that this has been a problem for Realtek NIC assignment, which has such a quirk that creates a sub-page mmap MemoryRegion access. To resolve this, we disable memory_access_is_direct() for ram_device regions since QEMU assumes that it can use memcpy for those regions. Instead we access through MemoryRegionOps, which replaces the memcpy with simple de-references of standard sizes to the host memory. With this patch we attempt to provide unrestricted access to the RAM device, allowing byte through qword access as well as unaligned access. The assumption here is that accesses initiated by the VM are driven by a device specific driver, which knows the device capabilities. If unaligned accesses are not supported by the device, we don't want them to work in a VM by performing multiple aligned accesses to compose the unaligned access. A down-side of this philosophy is that the xp command from the monitor attempts to use the largest available access weidth, unaware of the underlying device. Using memcpy had this same restriction, but at least now an operator can dump individual registers, even if blocks of device memory may result in access widths beyond the capabilities of a given device (RTL NICs only support up to dword). Reported-by: Thorsten Kohfeldt <thorsten.kohfeldt@gmx.de> Signed-off-by: Alex Williamson <alex.williamson@redhat.com> Acked-by: Paolo Bonzini <pbonzini@redhat.com>
2016-10-31 15:53:03 +00:00
memory_region_ram_device_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
memory_region_ram_device_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
### Guest events, keep at bottom
## vCPU
# Hot-plug a new virtual (guest) CPU
#
# Mode: user, softmmu
# Targets: all
vcpu guest_cpu_enter(void)
# Hot-unplug a virtual (guest) CPU
#
# Mode: user, softmmu
# Targets: all
vcpu guest_cpu_exit(void)
# Reset the state of a virtual (guest) CPU
#
# Mode: user, softmmu
# Targets: all
vcpu guest_cpu_reset(void)
# @vaddr: Access' virtual address.
# @info : Access' information (see below).
#
# Start virtual memory access (before any potential access violation).
#
# Does not include memory accesses performed by devices.
#
# Access information can be parsed as:
#
# struct mem_info {
# uint8_t size_shift : 2; /* interpreted as "1 << size_shift" bytes */
# bool sign_extend: 1; /* sign-extended */
# uint8_t endianness : 1; /* 0: little, 1: big */
# bool store : 1; /* wheter it's a store operation */
# };
#
# Mode: user, softmmu
# Targets: TCG(all)
trace: [trivial] Statically enable all guest events The existing optimizations makes it feasible to have them available on all builds. Some quick'n'dirty numbers with 400.perlbench (SPECcpu2006) on the train input (medium size - suns.pl) and the guest_mem_before event: * vanilla, statically disabled real 0m2,259s user 0m2,252s sys 0m0,004s * vanilla, statically enabled (overhead: 2.18x) real 0m4,921s user 0m4,912s sys 0m0,008s * multi-tb, statically disabled (overhead: 0.99x) [within noise range] real 0m2,228s user 0m2,216s sys 0m0,008s * multi-tb, statically enabled (overhead: 0.99x) [within noise range] real 0m2,229s user 0m2,224s sys 0m0,004s Now enabling all events when booting an ARM system that immediately shuts down (https://lists.gnu.org/archive/html/qemu-devel/2017-06/msg04085.html): * vanilla, statically disabled real 0m32,153s user 0m31,276s sys 0m0,108s * vanilla, statically enabled (overhead: 1.35x) real 0m43,507s user 0m42,680s sys 0m0,168s * multi-tb, statically disabled (overhead: 1.03x) real 0m32,993s user 0m32,516s sys 0m0,104s * multi-tb, statically enabled (overhead: 1.00x) [within noise range] real 0m32,110s user 0m31,176s sys 0m0,156s And finally enabling all events using Emilio's dbt-bench (where orig == vanilla, new == multi-tb): NBench score; higher is better 180 +-+--------+----------+----------+---------+----------+----------+----------+----------+----------+---------+----------+--------+-+ | | | *** $$$$%% orig | 160 +-+....................................*.*.$..$.%............................................................orig-enabled +-+ | * * $ $ % new | 140 +-+....................................*.*.$..$.%............................................................new-disabled.......+-+ | * * $ $ % | | * * $ $ % | 120 +-+....................................*.*.$..$.%...............................................................................+-+ | * * $ $ % | | * * $ $ % | 100 +-+....................................*.*.$..$.%.....$$$%%%....................................................................+-+ | * * $ $ % *** $ $ % *** $$$%% | 80 +-+....................................*.*.$..$.%.*.*.$.$..%.*.*.$.$.%..........................................................+-+ | * * $ $ % * * $ $ % * * $ $ % | | * * $ $ % * * $ $ % * * $ $ % | 60 +-+.........................***..$$$%%.*.*##..$.%.*.*.$.$..%.*.*.$.$.%..***.$$$%%...............................................+-+ | **** $$$%% * * $ $ % * * # $ % * *## $ % * * $ $ % * * $ $ % | | * * $ $ % * * $ $ % * * # $ % * * # $ % * *## $ % * * $ $ % | 40 +-+..............*..*.$.$.%.*.*..$.$.%.*.*.#..$.%.*.*.#.$..%.*.*.#.$.%..*.*.$.$.%...............................................+-+ | * * $ $ % * * $ $ % * * # $ % * * # $ % * * # $ % * *## $ % *** $$$%%% | 20 +-+....***.$$$%%.*..*##.$.%.*.*###.$.%.*.*.#..$.%.*.*.#.$..%.*.*.#.$.%..*.*.#.$.%..................................*.*.$.$..%...+-+ | * *## $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * *## $ % | | * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % ***###$$%% ***##$$$%% * * # $ % | 0 +-+----***##$$%%-****##$$%%-***###$$%%-***##$$$%%-***##$$%%%-***##$$%%--***##$$%%-****##$$%%-***###$$%%-***##$$$%%-***##$$%%%---+-+ NUMERIC SORTSTRING SORT BITFIEFP EMULATION ASSIGNMENT IDEA HUFFMAN FOURIER NEURLU DECOMPOSITION gmean png: http://imgur.com/a/8XG5S Signed-off-by: Lluís Vilanova <vilanova@ac.upc.edu> Reviewed-by: Emilio G. Cota <cota@braap.org> Signed-off-by: Emilio G. Cota <cota@braap.org> Message-id: 149915849243.6295.4484103824675839071.stgit@frigg.lan Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2017-07-04 08:54:52 +00:00
vcpu tcg guest_mem_before(TCGv vaddr, uint8_t info) "info=%d", "vaddr=0x%016"PRIx64" info=%d"
# @num: System call number.
# @arg*: System call argument value.
#
# Start executing a guest system call in syscall emulation mode.
#
# Mode: user
# Targets: TCG(all)
trace: [trivial] Statically enable all guest events The existing optimizations makes it feasible to have them available on all builds. Some quick'n'dirty numbers with 400.perlbench (SPECcpu2006) on the train input (medium size - suns.pl) and the guest_mem_before event: * vanilla, statically disabled real 0m2,259s user 0m2,252s sys 0m0,004s * vanilla, statically enabled (overhead: 2.18x) real 0m4,921s user 0m4,912s sys 0m0,008s * multi-tb, statically disabled (overhead: 0.99x) [within noise range] real 0m2,228s user 0m2,216s sys 0m0,008s * multi-tb, statically enabled (overhead: 0.99x) [within noise range] real 0m2,229s user 0m2,224s sys 0m0,004s Now enabling all events when booting an ARM system that immediately shuts down (https://lists.gnu.org/archive/html/qemu-devel/2017-06/msg04085.html): * vanilla, statically disabled real 0m32,153s user 0m31,276s sys 0m0,108s * vanilla, statically enabled (overhead: 1.35x) real 0m43,507s user 0m42,680s sys 0m0,168s * multi-tb, statically disabled (overhead: 1.03x) real 0m32,993s user 0m32,516s sys 0m0,104s * multi-tb, statically enabled (overhead: 1.00x) [within noise range] real 0m32,110s user 0m31,176s sys 0m0,156s And finally enabling all events using Emilio's dbt-bench (where orig == vanilla, new == multi-tb): NBench score; higher is better 180 +-+--------+----------+----------+---------+----------+----------+----------+----------+----------+---------+----------+--------+-+ | | | *** $$$$%% orig | 160 +-+....................................*.*.$..$.%............................................................orig-enabled +-+ | * * $ $ % new | 140 +-+....................................*.*.$..$.%............................................................new-disabled.......+-+ | * * $ $ % | | * * $ $ % | 120 +-+....................................*.*.$..$.%...............................................................................+-+ | * * $ $ % | | * * $ $ % | 100 +-+....................................*.*.$..$.%.....$$$%%%....................................................................+-+ | * * $ $ % *** $ $ % *** $$$%% | 80 +-+....................................*.*.$..$.%.*.*.$.$..%.*.*.$.$.%..........................................................+-+ | * * $ $ % * * $ $ % * * $ $ % | | * * $ $ % * * $ $ % * * $ $ % | 60 +-+.........................***..$$$%%.*.*##..$.%.*.*.$.$..%.*.*.$.$.%..***.$$$%%...............................................+-+ | **** $$$%% * * $ $ % * * # $ % * *## $ % * * $ $ % * * $ $ % | | * * $ $ % * * $ $ % * * # $ % * * # $ % * *## $ % * * $ $ % | 40 +-+..............*..*.$.$.%.*.*..$.$.%.*.*.#..$.%.*.*.#.$..%.*.*.#.$.%..*.*.$.$.%...............................................+-+ | * * $ $ % * * $ $ % * * # $ % * * # $ % * * # $ % * *## $ % *** $$$%%% | 20 +-+....***.$$$%%.*..*##.$.%.*.*###.$.%.*.*.#..$.%.*.*.#.$..%.*.*.#.$.%..*.*.#.$.%..................................*.*.$.$..%...+-+ | * *## $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * *## $ % | | * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % ***###$$%% ***##$$$%% * * # $ % | 0 +-+----***##$$%%-****##$$%%-***###$$%%-***##$$$%%-***##$$%%%-***##$$%%--***##$$%%-****##$$%%-***###$$%%-***##$$$%%-***##$$%%%---+-+ NUMERIC SORTSTRING SORT BITFIEFP EMULATION ASSIGNMENT IDEA HUFFMAN FOURIER NEURLU DECOMPOSITION gmean png: http://imgur.com/a/8XG5S Signed-off-by: Lluís Vilanova <vilanova@ac.upc.edu> Reviewed-by: Emilio G. Cota <cota@braap.org> Signed-off-by: Emilio G. Cota <cota@braap.org> Message-id: 149915849243.6295.4484103824675839071.stgit@frigg.lan Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2017-07-04 08:54:52 +00:00
vcpu guest_user_syscall(uint64_t num, uint64_t arg1, uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, uint64_t arg6, uint64_t arg7, uint64_t arg8) "num=0x%016"PRIx64" arg1=0x%016"PRIx64" arg2=0x%016"PRIx64" arg3=0x%016"PRIx64" arg4=0x%016"PRIx64" arg5=0x%016"PRIx64" arg6=0x%016"PRIx64" arg7=0x%016"PRIx64" arg8=0x%016"PRIx64
# @num: System call number.
# @ret: System call result value.
#
# Finish executing a guest system call in syscall emulation mode.
#
# Mode: user
# Targets: TCG(all)
trace: [trivial] Statically enable all guest events The existing optimizations makes it feasible to have them available on all builds. Some quick'n'dirty numbers with 400.perlbench (SPECcpu2006) on the train input (medium size - suns.pl) and the guest_mem_before event: * vanilla, statically disabled real 0m2,259s user 0m2,252s sys 0m0,004s * vanilla, statically enabled (overhead: 2.18x) real 0m4,921s user 0m4,912s sys 0m0,008s * multi-tb, statically disabled (overhead: 0.99x) [within noise range] real 0m2,228s user 0m2,216s sys 0m0,008s * multi-tb, statically enabled (overhead: 0.99x) [within noise range] real 0m2,229s user 0m2,224s sys 0m0,004s Now enabling all events when booting an ARM system that immediately shuts down (https://lists.gnu.org/archive/html/qemu-devel/2017-06/msg04085.html): * vanilla, statically disabled real 0m32,153s user 0m31,276s sys 0m0,108s * vanilla, statically enabled (overhead: 1.35x) real 0m43,507s user 0m42,680s sys 0m0,168s * multi-tb, statically disabled (overhead: 1.03x) real 0m32,993s user 0m32,516s sys 0m0,104s * multi-tb, statically enabled (overhead: 1.00x) [within noise range] real 0m32,110s user 0m31,176s sys 0m0,156s And finally enabling all events using Emilio's dbt-bench (where orig == vanilla, new == multi-tb): NBench score; higher is better 180 +-+--------+----------+----------+---------+----------+----------+----------+----------+----------+---------+----------+--------+-+ | | | *** $$$$%% orig | 160 +-+....................................*.*.$..$.%............................................................orig-enabled +-+ | * * $ $ % new | 140 +-+....................................*.*.$..$.%............................................................new-disabled.......+-+ | * * $ $ % | | * * $ $ % | 120 +-+....................................*.*.$..$.%...............................................................................+-+ | * * $ $ % | | * * $ $ % | 100 +-+....................................*.*.$..$.%.....$$$%%%....................................................................+-+ | * * $ $ % *** $ $ % *** $$$%% | 80 +-+....................................*.*.$..$.%.*.*.$.$..%.*.*.$.$.%..........................................................+-+ | * * $ $ % * * $ $ % * * $ $ % | | * * $ $ % * * $ $ % * * $ $ % | 60 +-+.........................***..$$$%%.*.*##..$.%.*.*.$.$..%.*.*.$.$.%..***.$$$%%...............................................+-+ | **** $$$%% * * $ $ % * * # $ % * *## $ % * * $ $ % * * $ $ % | | * * $ $ % * * $ $ % * * # $ % * * # $ % * *## $ % * * $ $ % | 40 +-+..............*..*.$.$.%.*.*..$.$.%.*.*.#..$.%.*.*.#.$..%.*.*.#.$.%..*.*.$.$.%...............................................+-+ | * * $ $ % * * $ $ % * * # $ % * * # $ % * * # $ % * *## $ % *** $$$%%% | 20 +-+....***.$$$%%.*..*##.$.%.*.*###.$.%.*.*.#..$.%.*.*.#.$..%.*.*.#.$.%..*.*.#.$.%..................................*.*.$.$..%...+-+ | * *## $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * *## $ % | | * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % * * # $ % ***###$$%% ***##$$$%% * * # $ % | 0 +-+----***##$$%%-****##$$%%-***###$$%%-***##$$$%%-***##$$%%%-***##$$%%--***##$$%%-****##$$%%-***###$$%%-***##$$$%%-***##$$%%%---+-+ NUMERIC SORTSTRING SORT BITFIEFP EMULATION ASSIGNMENT IDEA HUFFMAN FOURIER NEURLU DECOMPOSITION gmean png: http://imgur.com/a/8XG5S Signed-off-by: Lluís Vilanova <vilanova@ac.upc.edu> Reviewed-by: Emilio G. Cota <cota@braap.org> Signed-off-by: Emilio G. Cota <cota@braap.org> Message-id: 149915849243.6295.4484103824675839071.stgit@frigg.lan Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2017-07-04 08:54:52 +00:00
vcpu guest_user_syscall_ret(uint64_t num, uint64_t ret) "num=0x%016"PRIx64" ret=0x%016"PRIx64