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).
Backports commit 1b16ded6a512809f99c133a97f19026fe612b2de from qemu
Setting skip_dump on a MemoryRegion allows us to modify one specific
code path, but the restriction we're trying to address encompasses
more than that. If we have a RAM MemoryRegion backed by a physical
device, it not only restricts our ability to dump that region, but
also affects how we should manipulate it. Here we recognize that
MemoryRegions do not change to sometimes allow dumps and other times
not, so we replace setting the skip_dump flag with a new initializer
so that we know exactly the type of region to which we're applying
this behavior.
Backports commit ca83f87a66d19fdaabf23d4f5ebb49396fe232c1 from qemu
Rather than rely on recursion during the middle of register allocation,
lower indirect registers to loads and stores off the indirect base into
plain temps.
For an x86_64 host, with sufficient registers, this results in identical
code, modulo the actual register assignments.
For an i686 host, with insufficient registers, this means that temps can
be (temporarily) spilled to the stack in order to satisfy an allocation.
This as opposed to the possibility of not being able to spill, to allocate
a register for the indirect base, in order to perform a spill.
Backports commit 5a18407f55ade924aa6397c9a043a9ffd59645fe from qemu
Instead of using -1 as end of chain, use 0, and link through the 0
entry as a fully circular double-linked list.
Backports commit dcb8e75870e2de199db853697f8839cb603beefe from qemu
Make it obvious which macros are safe in which situations.
Useful since QEMU_ALIGN_UP and ROUND_UP both purport to do
the same thing, but differ on whether the alignment must be
a power of 2.
Assertions help both Coverity and the clang static analyzer avoid
false positives, but on the other hand both are confused when
the condition is compiled as (void)(x != FOO). Always expand
assertion macros when using Coverity or clang, through a new
QEMU_STATIC_ANALYSIS preprocessor symbol.
This fixes a couple false positives in TCG.
Backports commit 8bff06a0bbf257a2083223534c1607bf87d913e6 from qemu
Header guard symbols should match their file name to make guard
collisions less likely. Offenders found with
scripts/clean-header-guards.pl -vn.
Cleaned up with scripts/clean-header-guards.pl, followed by some
renaming of new guard symbols picked by the script to better ones.
Backports commit 121d07125bb6d7079c7ebafdd3efe8c3a01cc440 from qemu
Tracked down with an ugly, brittle and probably buggy Perl script.
Also move includes converted to <...> up so they get included before
ours where that's obviously okay.
Backports commit a9c94277f07d19d3eb14f199c3e93491aa3eae0e from qemu
Add a documentation comment describing the functions for
converting between the cpu and little or bigendian formats.
Backports commit 7d820b766a2049f33ca7e078aa51018f2335f8c5 from qemu
Now that all uses of cpu_to_*w() and *_to_cpup() have been replaced
with either ld*_p()/st*_p() or by doing direct dereferences and
using the cpu_to_*()/*_to_cpu() byteswap functions, we can remove
the unused implementations.
Backports commit f76bde702916d0230bf359d478bcac8d7f3b30ae from qemu
There are functions tlb_fill(), cpu_unaligned_access() and
do_unaligned_access() that are called with access type and mmu index
arguments. But these arguments are named 'is_write' and 'is_user' in their
declarations. The patches fix the arguments to avoid a confusion.
Backports commit b35399bb4e9968296a12303b00f9f2066470e987 from qemu
Some architectures (e.g. ARMv8) need the address which is aligned
to a size more than the size of the memory access.
To support such check it's enough the current costless alignment
check implementation in QEMU, but we need to support
an alignment size specifying.
Backports commit 1f00b27f17518a1bcb4cedca49eaec96a4d560bd from qemu
We have a couple places in the code base that want to deep-clone
one QAPI object into another, and they were resorting to serializing
the struct out to QObject then reparsing it. A much more efficient
version can be done by adding a new clone visitor.
Since cloning is still relatively uncommon, expose the use of the
new visitor via a QAPI_CLONE() macro that takes care of type-punning
the underlying function pointer, rather than generating lots of
unused functions for types that won't be cloned. And yes, we're
relying on the compiler treating all pointers equally, even though
a strict C program cannot portably do so - but we're not the first
one in the qemu code base to expect it to work (hello, glib!).
The choice of adding a fourth visitor type deserves some explanation.
On the surface, the clone visitor is mostly an input visitor (it
takes arbitrary input - in this case, another QAPI object - and
creates a new QAPI object during the course of the visit). But
ever since commit da72ab0 consolidated enum visits based on the
visitor type, using VISITOR_INPUT would cause us to run
visit_type_str(), even though for cloning there is nothing to do
(we just copy the enum value across, without regards to its mapping
to strings). Also, since our input happens to be a QAPI object,
we can also satisfy the internal checks for VISITOR_OUTPUT. So in
the end, I settled with a new VISITOR_CLONE, and chose its value
such that many internal checks can use 'v->type & mask', sticking
to 'v->type == value' where the difference matters.
Note that we can only clone objects (including alternates) and lists,
not built-ins or enums. The visitor core hides integer width from
the actual visitor (since commit 04e070d), and as long as that's the
case, we can't clone top-level integers. Then again, those can
always be cloned by direct copy, since they are not objects with
deep pointers, so it's no real loss. And restricting cloning to
just objects and lists is cleaner than restricting it to non-integers.
As such, I documented that the clone visitor is for direct use only
by code internal to QAPI, and should not be used on incomplete objects
(other than a hack to work around the fact that we allow NULL in place
of "" in visit_type_str() in other output visitors). Note that as
written, the clone visitor will never fail on a complete object.
Scalars (including enums) not at the root of the clone copy just fine
with no additional effort while visiting the scalar, by virtue of a
g_memdup() each time we push another struct onto the stack. Cloning
a string requires deduplication of a pointer, which means it can also
provide the guarantee of an input visitor of never producing NULL
even when still accepting NULL in place of "" the way the QMP output
visitor does.
Cloning an 'any' type could be possible by incrementing the QObject
refcnt, but it's not obvious whether that is better than implementing
a QObject deep clone. So for now, we document it as unsupported,
and intentionally omit the .type_any() callback to let a developer
know their usage needs implementation.
Add testsuite coverage for several different clone situations, to
ensure that the code is working. I also tested that valgrind was
happy with the test.
Backports commit a15fcc3cf69ee3d408f60d6cc316488d2b0249b4 from qemu
Making each output visitor provide its own output collection
function was the only remaining reason for exposing visitor
sub-types to the rest of the code base. Add a polymorphic
visit_complete() function which is a no-op for input visitors,
and which populates an opaque pointer for output visitors. For
maximum type-safety, also add a parameter to the output visitor
constructors with a type-correct version of the output pointer,
and assert that the two uses match.
This approach was considered superior to either passing the
output parameter only during construction (action at a distance
during visit_free() feels awkward) or only during visit_complete()
(defeating type safety makes it easier to use incorrectly).
Most callers were function-local, and therefore a mechanical
conversion; the testsuite was a bit trickier, but the previous
cleanup patch minimized the churn here.
The visit_complete() function may be called at most once; doing
so lets us use transfer semantics rather than duplication or
ref-count semantics to get the just-built output back to the
caller, even though it means our behavior is not idempotent.
Generated code is simplified as follows for events:
|@@ -26,7 +26,7 @@ void qapi_event_send_acpi_device_ost(ACP
| QDict *qmp;
| Error *err = NULL;
| QMPEventFuncEmit emit;
|- QmpOutputVisitor *qov;
|+ QObject *obj;
| Visitor *v;
| q_obj_ACPI_DEVICE_OST_arg param = {
| info
|@@ -39,8 +39,7 @@ void qapi_event_send_acpi_device_ost(ACP
|
| qmp = qmp_event_build_dict("ACPI_DEVICE_OST");
|
|- qov = qmp_output_visitor_new();
|- v = qmp_output_get_visitor(qov);
|+ v = qmp_output_visitor_new(&obj);
|
| visit_start_struct(v, "ACPI_DEVICE_OST", NULL, 0, &err);
| if (err) {
|@@ -55,7 +54,8 @@ void qapi_event_send_acpi_device_ost(ACP
| goto out;
| }
|
|- qdict_put_obj(qmp, "data", qmp_output_get_qobject(qov));
|+ visit_complete(v, &obj);
|+ qdict_put_obj(qmp, "data", obj);
| emit(QAPI_EVENT_ACPI_DEVICE_OST, qmp, &err);
and for commands:
| {
| Error *err = NULL;
|- QmpOutputVisitor *qov = qmp_output_visitor_new();
| Visitor *v;
|
|- v = qmp_output_get_visitor(qov);
|+ v = qmp_output_visitor_new(ret_out);
| visit_type_AddfdInfo(v, "unused", &ret_in, &err);
|- if (err) {
|- goto out;
|+ if (!err) {
|+ visit_complete(v, ret_out);
| }
|- *ret_out = qmp_output_get_qobject(qov);
|-
|-out:
| error_propagate(errp, err);
Backports commit 3b098d56979d2f7fd707c5be85555d114353a28d from qemu
Now that we have a polymorphic visit_free(), we no longer need
qmp_output_visitor_cleanup(); however, we still need to
expose the subtype for qmp_output_get_qobject().
Backports commit 1830f22a6777cedaccd67a08f675d30f7a85ebfd from qemu
Now that we have a polymorphic visit_free(), we no longer need
qmp_input_visitor_cleanup(); which in turn means we no longer
need to return a subtype from qmp_input_visitor_new() nor a
public upcast function.
Generated code changes to qmp-marshal.c look like:
|@@ -52,11 +52,10 @@ void qmp_marshal_add_fd(QDict *args, QOb
| {
| Error *err = NULL;
| AddfdInfo *retval;
|- QmpInputVisitor *qiv = qmp_input_visitor_new(QOBJECT(args), true);
| Visitor *v;
| q_obj_add_fd_arg arg = {0};
|
|- v = qmp_input_get_visitor(qiv);
|+ v = qmp_input_visitor_new(QOBJECT(args), true);
| visit_start_struct(v, NULL, NULL, 0, &err);
| if (err) {
| goto out;
Backports commit b70ce1018a251c0c33498d9c927a07cade655a5e from qemu
Now that we have a polymorphic visit_free(), we no longer need
string_input_visitor_cleanup(); which in turn means we no longer
need to return a subtype from string_input_visitor_new() nor a
public upcast function.
Backports commit 7a0525c7be6b38d32d586e3fd12e7377ded21faa from qemu
Making each visitor provide its own (awkwardly-named) FOO_cleanup()
is unusual, when we can instead have a polymorphic visit_free()
interface. Over the next few patches, we can use the polymorphic
functions to eliminate the need for a FOO_get_visitor() function
for accessing specific visitor functionality, once everything can
be accessed directly through the Visitor* interfaces.
The dealloc visitor is the first one converted to completely use
the new entry point, since qapi_dealloc_visitor_cleanup() was the
only reason that qapi_dealloc_get_visitor() existed, and only
generated and testsuite code was even using it. With the new
visit_free() entry point in place, we no longer need to expose
the QapiDeallocVisitor subtype through qapi_dealloc_visitor_new(),
and can get by with less generated code, with diffs that look like:
| void qapi_free_ACPIOSTInfo(ACPIOSTInfo *obj)
| {
|- QapiDeallocVisitor *qdv;
| Visitor *v;
|
| if (!obj) {
| return;
| }
|
|- qdv = qapi_dealloc_visitor_new();
|- v = qapi_dealloc_get_visitor(qdv);
|+ v = qapi_dealloc_visitor_new();
| visit_type_ACPIOSTInfo(v, NULL, &obj, NULL);
|- qapi_dealloc_visitor_cleanup(qdv);
|+ visit_free(v);
|}
Backports commit 2c0ef9f411ae6081efa9eca5b3eab2dbeee45a6c from qemu
Rather than making the dealloc visitor track of stack of pointers
remembered during visit_start_* in order to free them during
visit_end_*, it's a lot easier to just make all callers pass the
same pointer to visit_end_*. The generated code has access to the
same pointer, while all other users are doing virtual walks and
can pass NULL. The dealloc visitor is then greatly simplified.
All three visit_end_*() functions intentionally take a void**,
even though the visit_start_*() functions differ between void**,
GenericList**, and GenericAlternate**. This is done for several
reasons: when doing a virtual walk, passing NULL doesn't care
what the type is, but when doing a generated walk, we already
have to cast the caller's specific FOO* to call visit_start,
while using void** lets us use visit_end without a cast. Also,
an upcoming patch will add a clone visitor that wants to use
the same implementation for all three visit_end callbacks,
which is made easier if all three share the same signature.
For visitors with already track per-object state (the QMP visitors
via a stack, and the string visitors which do not allow nesting),
add an assertion that the caller is indeed passing the same
pointer to paired calls.
Backports commit 1158bb2a058fcdd0c8fc3e60dc77f7a57ddbb271 from qemu
Range represents a range as follows. Member @start is the inclusive
lower bound, member @end is the exclusive upper bound. Zero @end is
special: if @start is also zero, the range is empty, else @end is to
be interpreted as 2^64. No other empty ranges may occur.
The range [0,2^64-1] cannot be represented. If you try to create it
with range_set_bounds1(), you get the empty range instead. If you try
to create it with range_set_bounds() or range_extend(), assertions
fail. Before range_set_bounds() existed, the open-coded creation
usually got you the empty range instead. Open deathtrap.
Moreover, the code dealing with the janus-faced @end is too clever by
half.
Dumb this down to a more pedestrian representation: members @lob and
@upb are inclusive lower and upper bounds. The empty range is encoded
as @lob = 1, @upb = 0.
Backports commit 6dd726a2bf1b800289d90a84d5fcb5ce7b78a8e1 from qemu
Users of struct Range mess liberally with its members, which makes
refactoring hard. Create a set of methods, and convert all users to
call them instead of accessing members. The methods have carefully
worded contracts, and use assertions to check them.
Backports commit a0efbf16604770b9d805bcf210ec29942321134f from qemu
Add a macro that creates a 64bit value which has length number of ones
shifted across by the value of shift.
Backports commit ae2923b5c20a21c6457680330506a9c13873485c from qemu
It doesn't make sense to pass a NULL ops argument to
memory_region_init_rom_device(), because the effect will
be that if the guest tries to write to the memory region
then QEMU will segfault. Catch the bug earlier by sanity
checking the arguments to this function, and remove the
misleading documentation that suggests that passing NULL
might be sensible.
Backports commit 39e0b03dec518254fabd2acff29548d3f1d2b754 from qemu
Provide a new helper function memory_region_init_rom() for memory
regions which are read-only (and unlike those created by
memory_region_init_rom_device() don't have special behaviour
for writes). This has the same behaviour as calling
memory_region_init_ram() and then memory_region_set_readonly()
(which is what we do today in boards with pure ROMs) but is a
more easily discoverable API for the purpose.
Backports commit a1777f7f6462c66e1ee6e98f0d5c431bfe988aa5 from qemu
The IOMMU driver may change behavior depending on whether a notifier
client is present. In the case of POWER, this represents a change in
the visibility of the IOTLB, for other drivers such as intel-iommu and
future AMD-Vi emulation, notifier support is not yet enabled and this
provides the opportunity to flag that incompatibility.
Backports commit d22d8956b185c002b50a4d0883aff61f857347ef from qemu
Commit 7f8f9ef1 introduced the ability to store a list of
integers as a sorted list of ranges, but when merging ranges,
it leaks one or more ranges. It was also using range_get_last()
incorrectly within range_compare() (a range is a start/end pair,
but range_get_last() is for start/len pairs), and will also
mishandle a range ending in UINT64_MAX (remember, we document
that no range covers 2**64 bytes, but that ranges that end on
UINT64_MAX have end < begin).
The whole merge algorithm was rather complex, and included
unnecessary passes over data within glib functions, and enough
indirection to make it hard to easily plug the data leaks.
Since we are already hard-coding things to a list of ranges,
just rewrite the thing to open-code the traversal and
comparisons, by making the range_compare() helper function give
us an answer that is easier to use, at which point we avoid the
need to pass any callbacks to g_list_*(). Then by reusing
range_extend() instead of duplicating effort with range_merge(),
we cover the corner cases correctly.
Drop the now-unused range_merge() and ranges_can_merge().
Doing this lets test-string-{input,output}-visitor pass under
valgrind without leaks.
Backports commit db486cc334aafd3dbdaf107388e37fc3d6d3e171 from qemu
Calling our function g_list_insert_sorted_merged is a misnomer,
since we are NOT writing a glib function. Furthermore, we are
making every caller pass the same comparator function of
range_merge(): any caller that would try otherwise would break
in weird ways since our internal call to ranges_can_merge() is
hard-coded to operate only on ranges, rather than paying
attention to the caller's comparator.
Better is to fix things so that callers don't have to care about
our internal comparator, by picking a function name and updating
the parameter type away from a gratuitous use of void*, to make
it obvious that we are operating specifically on a list of ranges
and not a generic list. Plus, refactoring the code here will
make it easier to plug a memory leak in the next patch.
range_compare() is now internal only, and moves to the .c file.
Backports commit 7c47959d0cb05db43014141a156ada0b6d53a750 from qemu
g_list_insert_sorted_merged() is rather large to be an inline
function; move it to its own file. range_merge() and
ranges_can_merge() can likewise move, as they are only used
internally. Also, it becomes obvious that the condition within
range_merge() is already satisfied by its caller, and that the
return value is not used.
The diffstat is misleading, because of the copyright boilerplate.
Backports commit fec0fc0a13ac7f1a1130433a6740cd850c3db34a from qemu
This patch modifies SoftFloat library so that it can be configured in
run-time in relation to the meaning of signaling NaN bit, while, at the
same time, strictly preserving its behavior on all existing platforms.
Background:
In floating-point calculations, there is a need for denoting undefined or
unrepresentable values. This is achieved by defining certain floating-point
numerical values to be NaNs (which stands for "not a number"). For additional
reasons, virtually all modern floating-point unit implementations use two
kinds of NaNs: quiet and signaling. The binary representations of these two
kinds of NaNs, as a rule, differ only in one bit (that bit is, traditionally,
the first bit of mantissa).
Up to 2008, standards for floating-point did not specify all details about
binary representation of NaNs. More specifically, the meaning of the bit
that is used for distinguishing between signaling and quiet NaNs was not
strictly prescribed. (IEEE 754-2008 was the first floating-point standard
that defined that meaning clearly, see [1], p. 35) As a result, different
platforms took different approaches, and that presented considerable
challenge for multi-platform emulators like QEMU.
Mips platform represents the most complex case among QEMU-supported
platforms regarding signaling NaN bit. Up to the Release 6 of Mips
architecture, "1" in signaling NaN bit denoted signaling NaN, which is
opposite to IEEE 754-2008 standard. From Release 6 on, Mips architecture
adopted IEEE standard prescription, and "0" denotes signaling NaN. On top of
that, Mips architecture for SIMD (also known as MSA, or vector instructions)
also specifies signaling bit in accordance to IEEE standard. MSA unit can be
implemented with both pre-Release 6 and Release 6 main processor units.
QEMU uses SoftFloat library to implement various floating-point-related
instructions on all platforms. The current QEMU implementation allows for
defining meaning of signaling NaN bit during build time, and is implemented
via preprocessor macro called SNAN_BIT_IS_ONE.
On the other hand, the change in this patch enables SoftFloat library to be
configured in run-time. This configuration is meant to occur during CPU
initialization, at the moment when it is definitely known what desired
behavior for particular CPU (or any additional FPUs) is.
The change is implemented so that it is consistent with existing
implementation of similar cases. This means that structure float_status is
used for passing the information about desired signaling NaN bit on each
invocation of SoftFloat functions. The additional field in float_status is
called snan_bit_is_one, which supersedes macro SNAN_BIT_IS_ONE.
IMPORTANT:
This change is not meant to create any change in emulator behavior or
functionality on any platform. It just provides the means for SoftFloat
library to be used in a more flexible way - in other words, it will just
prepare SoftFloat library for usage related to Mips platform and its
specifics regarding signaling bit meaning, which is done in some of
subsequent patches from this series.
Further break down of changes:
1) Added field snan_bit_is_one to the structure float_status, and
correspondent setter function set_snan_bit_is_one().
2) Constants <float16|float32|float64|floatx80|float128>_default_nan
(used both internally and externally) converted to functions
<float16|float32|float64|floatx80|float128>_default_nan(float_status*).
This is necessary since they are dependent on signaling bit meaning.
At the same time, for the sake of code cleanup and simplicity, constants
<floatx80|float128>_default_nan_<low|high> (used only internally within
SoftFloat library) are removed, as not needed.
3) Added a float_status* argument to SoftFloat library functions
XXX_is_quiet_nan(XXX a_), XXX_is_signaling_nan(XXX a_),
XXX_maybe_silence_nan(XXX a_). This argument must be present in
order to enable correct invocation of new version of functions
XXX_default_nan(). (XXX is <float16|float32|float64|floatx80|float128>
here)
4) Updated code for all platforms to reflect changes in SoftFloat library.
This change is twofolds: it includes modifications of SoftFloat library
functions invocations, and an addition of invocation of function
set_snan_bit_is_one() during CPU initialization, with arguments that
are appropriate for each particular platform. It was established that
all platforms zero their main CPU data structures, so snan_bit_is_one(0)
in appropriate places is not added, as it is not needed.
[1] "IEEE Standard for Floating-Point Arithmetic",
IEEE Computer Society, August 29, 2008.
Backports commit af39bc8c49224771ec0d38f1b693ea78e221d7bc from qemu
Every IOMMU has some granularity which MemoryRegionIOMMUOps::translate
uses when translating, however this information is not available outside
the translate context for various checks.
This adds a get_min_page_size callback to MemoryRegionIOMMUOps and
a wrapper for it so IOMMU users (such as VFIO) can know the minimum
actual page size supported by an IOMMU.
As IOMMU MR represents a guest IOMMU, this uses TARGET_PAGE_SIZE
as fallback.
This removes vfio_container_granularity() and uses new helper in
memory_region_iommu_replay() when replaying IOMMU mappings on added
IOMMU memory region.
Backports the relevant parts of commit f682e9c244af7166225f4a50cc18ff296bb9d43e from qemu
A half-shuffle operation takes a word with zeros in the high half:
0000 0000 0000 0000 ABCD EFGH IJKL MNOP
and spreads the bits out so they are in every other bit of the word:
0A0B 0C0D 0E0F 0G0H 0I0J 0K0L 0M0N 0O0P
A half-unshuffle performs the reverse operation.
Provide functions in bitops.h which implement these operations
for 32-bit and 64-bit inputs, and add tests for them.
Backports commit b355438de52d0782983bf4bdc47936189a0c988b from qemu
Add an API object_type_get_size(const char *typename) that returns the
instance_size of the give typename.
Backports commit 3f97b53a682d2595747c926c00d78b9d406f1be0 from qemu
For some workloads such as arm bootup, tb_phys_hash is performance-critical.
The is due to the high frequency of accesses to the hash table, originated
by (frequent) TLB flushes that wipe out the cpu-private tb_jmp_cache's.
More info:
https://lists.nongnu.org/archive/html/qemu-devel/2016-03/msg05098.html
To dig further into this I modified an arm image booting debian jessie to
immediately shut down after boot. Analysis revealed that quite a bit of time
is unnecessarily spent in tb_phys_hash: the cause is poor hashing that
results in very uneven loading of chains in the hash table's buckets;
the longest observed chain had ~550 elements.
The appended addresses this with two changes:
1) Use xxhash as the hash table's hash function. xxhash is a fast,
high-quality hashing function.
2) Feed the hashing function with not just tb_phys, but also pc and flags.
This improves performance over using just tb_phys for hashing, since that
resulted in some hash buckets having many TB's, while others getting very few;
with these changes, the longest observed chain on a single hash bucket is
brought down from ~550 to ~40.
Tests show that the other element checked for in tb_find_physical,
cs_base, is always a match when tb_phys+pc+flags are a match,
so hashing cs_base is wasteful. It could be that this is an ARM-only
thing, though. UPDATE:
On Tue, Apr 05, 2016 at 08:41:43 -0700, Richard Henderson wrote:
> The cs_base field is only used by i386 (in 16-bit modes), and sparc (for a TB
> consisting of only a delay slot).
> It may well still turn out to be reasonable to ignore cs_base for hashing.
BTW, after this change the hash table should not be called "tb_hash_phys"
anymore; this is addressed later in this series.
This change gives consistent bootup time improvements. I tested two
host machines:
- Intel Xeon E5-2690: 11.6% less time
- Intel i7-4790K: 19.2% less time
Increasing the number of hash buckets yields further improvements. However,
using a larger, fixed number of buckets can degrade performance for other
workloads that do not translate as many blocks (600K+ for debian-jessie arm
bootup). This is dealt with later in this series.
Backports commit 42bd32287f3a18d823f2258b813824a39ed7c6d9 from qemu
This will be used by upcoming changes for hashing the tb hash.
Add this into a separate file to include the copyright notice from
xxhash.
Backports commit dc8b295d05ec35a8c032f9abca421772347ba5d4 from qemu
The function cpu_resume_from_signal() is now always called with a
NULL puc argument, and is rather misnamed since it is never called
from a signal handler. It is essentially forcing an exit to the
top level cpu loop but without raising any exception, so rename
it to cpu_loop_exit_noexc() and drop the useless unused argument.
Backports commit 6886b98036a8f8f5bce8b10756ce080084cef11b from qemu
The WORDS_ALIGNED #define is not used anywhere, and hasn't been since
2013 when commit 612d590ebc6cef rewrote the various ld<type>_<endian>_p
functions to not use it. Remove the #define and the comment describing it.
Also remove the line in the comment about TARGET_WORDS_ALIGNED, since
it has never actually existed.
Backports commit 0d5c21f2b3bf1e0b562a2c74e353d2e03f2f50ef from qemu
Let users of qemu_get_ram_ptr and qemu_ram_ptr_length pass in an
address that is relative to the MemoryRegion. This basically means
what address_space_translate returns.
Because the semantics of the second parameter change, rename the
function to qemu_map_ram_ptr.
Backports commit 0878d0e11ba8013dd759c6921cbf05ba6a41bd71 from qemu
Move the old qemu_ram_addr_from_host to memory_region_from_host and
make it return an offset within the region. For qemu_ram_addr_from_host
return the ram_addr_t directly, similar to what it was before
commit 1b5ec23 ("memory: return MemoryRegion from qemu_ram_addr_from_host",
2013-07-04).
Backports commit 07bdaa4196b51bc7ffa7c3f74e9e4a9dc8a7966a from qemu
Of the two callers, one does not use it, and the other can compute
it itself based on the other output argument (offset) and the RAMBlock.
Backports commit f615f39616c4fd1a3a3b078af8d75bb4be6390de from qemu
Remove direct uses of ram_addr_t and optimize memory_region_{get,set}_fd
now that a MemoryRegion knows its RAMBlock directly.
Backports commit 4ff87573df3606856a92c14eef3393a63d736d11 from qemu
Currently we emit a consume-load in atomic_rcu_read. Because of
limitations in current compilers, this is overkill for non-Alpha hosts
and it is only useful to make Thread Sanitizer work.
This patch leaves the consume-load in atomic_rcu_read when
compiling with Thread Sanitizer enabled, and resorts to a
relaxed load + smp_read_barrier_depends otherwise.
On an RMO host architecture, such as aarch64, the performance
improvement of this change is easily measurable. For instance,
qht-bench performs an atomic_rcu_read on every lookup. Performance
before and after applying this patch:
$ tests/qht-bench -d 5 -n 1
Before: 9.78 MT/s
After: 10.96 MT/s
Backports commit 15487aa132109891482f79d78a30d6cfd465a391 from qemu
For correctness, smp_read_barrier_depends() is only required to
emit a barrier on Alpha hosts. However, we are currently emitting
a consume fence unconditionally, and most compilers currently treat
consume and acquire fences as equivalent.
Fix it by keeping the consume fence if we're compiling with Thread
Sanitizer, since this might help prevent false warnings. Otherwise,
only emit the barrier for Alpha hosts. Note that we still guarantee
that smp_read_barrier_depends() is a compiler barrier.
Backports commit c983895258a771f8a5e4a53950bfb7fd2216651c from qemu
The macro will be used by code that will stop calling
qemu_hw_version() at runtime and just need a constant value.
Backports commit d494352c2f7818aeba184a8ef757569083740bb2 from qemu
The collision check does nothing and hasn't been used. Remove the
variable together with related code.
Backports commit b61359781958759317ee6fd1a45b59be0b7dbbe1 from qemu
On the one hand, we have already qemu_get_ram_block() whose function
is similar. On the other hand, we can directly use mr->ram_block but
searching RAMblock by ram_addr which is a kind of waste.
Backports commit fa53a0e53efdc7002497ea4a76aacf6cceb170ef from qemu
Include qom/object.h and exec/memory.h instead of exec/ioport.h;
exec/ioport.h was almost everywhere required only for those two
includes, not for the content of the header itself.
Remove block/aio.h, everybody is already including it through
another path.
With this change, include/hw/hw.h is freed from qemu-common.h.
Backports commit df43d49cb8708b9c88a20afe0d1a3089b550a5b8 from qemu
pio_addr_t is almost unused, because these days I/O ports are simply
accessed through the address space. cpu_{in,out}[bwl] themselves are
almost unused; monitor.c and xen-hvm.c could use address_space_read/write
directly, since they have an integer size at hand. This leaves qtest as
the only user of those functions.
On the other hand even portio_* functions use this type; the only
interesting use of pio_addr_t thus is include/hw/sysbus.h. I guess I
could move it there, but I don't see much benefit in that either. Using
uint32_t is enough and avoids the need to include ioport.h everywhere.
Backports commit 89a80e7400f7225d9401b35ef32454b4ab29dc67 from qemu
exec-all.h contains TCG-specific definitions. It is not needed outside
TCG-specific files such as translate.c, exec.c or *helper.c.
One generic function had snuck into include/exec/exec-all.h; move it to
include/qom/cpu.h.
Backports commit 63c915526d6a54a95919ebece83fa9ca631b2508 from qemu
TCG backends do not need most of exec-all.h; extract what they actually
need to a separate file or move it directly to tcg.h. The next patch
will stop including exec-all.h from everywhere.
Backports commit 00f6da6a1a5d1ce085334eccbb50ec899ceed513 from qemu
Move it to the actual users. There are still a few includes of
qemu/bswap.h in headers; removing them is left for future work.
Backports commit 58369e22cf971448411bfbc8c894b2addebe2111 from qemu
Disentangle cpu-common.h and memory.h from NEED_CPU_H. Prototypes are
not defined for !NEED_CPU_H, so remove them from poison.h too. Only
macros need poisoning.
Backports commit a7d6039cb35592683ecc56d2b37817da2d2f8b00 from qemu
Return the negated value of accel_initialised is meaningless,
and the caller vl doesn't check it.
Backports commit bdc3f61dec2f9c227235bb5f677a0272e1184c82 from qemu
This field was used for telling cpu_interrupt() to unlink a chain of TBs
being executed when it worked that way. Now, cpu_interrupt() don't do
this anymore. So we don't need this field anymore.
Backports commit 3213525f8ab48742db09dab18cb9ae6f36a6c921 from qemu
'tb_invalidated_flag' was meant to catch two events:
* some TB has been invalidated by tb_phys_invalidate();
* the whole translation buffer has been flushed by tb_flush().
Then it was checked:
* in cpu_exec() to ensure that the last executed TB can be safely
linked to directly call the next one;
* in cpu_exec_nocache() to decide if the original TB should be provided
for further possible invalidation along with the temporarily
generated TB.
It is always safe to patch an invalidated TB since it is not going to be
used anyway. It is also safe to call tb_phys_invalidate() for an already
invalidated TB. Thus, setting this flag in tb_phys_invalidate() is
simply unnecessary. Moreover, it can prevent from pretty proper linking
of TBs, if any arbitrary TB has been invalidated. So just don't touch it
in tb_phys_invalidate().
If this flag is only used to catch whether tb_flush() has been called
then rename it to 'tb_flushed'. Declare it as 'bool' and stick to using
only 'true' and 'false' to set its value. Also, instead of setting it in
tb_gen_code(), just after tb_flush() has been called, do it right inside
of tb_flush().
In cpu_exec(), this flag is used to track if tb_flush() has been called
and have made 'next_tb' (a reference to the last executed TB) invalid
for linking it to directly call the next TB. tb_flush() can be called
during the CPU execution loop from tb_gen_code(), during TB execution or
by another thread while 'tb_lock' is released. Catch for translation
buffer flush reliably by resetting this flag once before first TB lookup
and each time we find it set before trying to add a direct jump. Don't
touch in in tb_find_physical().
Each vCPU has its own execution loop in multithreaded mode and thus
should have its own copy of the flag to be able to reset it with its own
'next_tb' and don't affect any other vCPU execution thread. So make this
flag per-vCPU and move it to CPUState.
In cpu_exec_nocache(), we only need to check if tb_flush() has been
called from tb_gen_code() called by cpu_exec_nocache() itself. To do
this reliably, preserve the old value of the flag, reset it before
calling tb_gen_code(), check afterwards, and combine the saved value
back to the flag.
This patch is based on the patch "tcg: move tb_invalidated_flag to
CPUState" from Paolo Bonzini <pbonzini@redhat.com>.
Backports commit 6f789be56d3f38e9214dafcfab3bf9be7191f370 from qemu
The check is to make sure that another thread hasn't already done the
same while we were outside of tb_lock. Mention this in a comment.
Backports commit 9962c478b153a18fe88a6509fe58cd178aff8abc from qemu
These fields do not contain pure pointers to a TranslationBlock
structure. So uintptr_t is the most appropriate type for them.
Also put some asserts to assure that the two least significant bits of
the pointer are always zero before assigning it to jmp_list_first.
Backports commit c37e6d7e3589ecb96914faa21025ad7ba6654aea from qemu
Briefly describe in a comment how direct block chaining is done. It
should help in understanding of the following data fields.
Rename some fields in TranslationBlock and TCGContext structures to
better reflect their purpose (dropping excessive 'tb_' prefix in
TranslationBlock but keeping it in TCGContext):
tb_next_offset => jmp_reset_offset
tb_jmp_offset => jmp_insn_offset
tb_next => jmp_target_addr
jmp_next => jmp_list_next
jmp_first => jmp_list_first
Avoid using a magic constant as an invalid offset which is used to
indicate that there's no n-th jump generated.
Backports commit f309101c26b59641fc1aa8fb2a98a5441cdaea03 from qemu
Ensure direct jump patching in ARM is atomic by using
atomic_read()/atomic_set() for code patching.
Backports commit 7d14e0e2d661479985197203589c38840e1066df from qemu
Ensure direct jump patching in s390 is atomic by:
* naturally aligning a location of direct jump address;
* using atomic_read()/atomic_set() for code patching.
Backports commit ed3d51ecd7fe248d3959e469d53890ac9ffe0cd2 from qemu
Ensure direct jump patching in i386 is atomic by:
* naturally aligning a location of direct jump address;
* using atomic_read()/atomic_set() for code patching.
Backports commit 0d07abf05e98903c7faf204a9a90f7d45b7554dc from qemu
These macros provide a convenient way to n-byte align pointers up and
down and check if a pointer is n-byte aligned.
Backports commit 6b587d3cda48e7ba26de8d30bf0d8a7063970715 from qemu
We are inconsistent with the type of tb->flags: usage varies loosely
between int and uint64_t. Settle to uint32_t everywhere, which is
superior to both: at least one target (aarch64) uses the most significant
bit in the u32, and uint64_t is wasteful.
Compile-tested for all targets.
Backports commit 89fee74a0f066dfd73830a7b5fa137e87888c870 from qemu
Use tcg_set_insn_param() instead of directly accessing internal
tcg data structures to update an insn param.
Backports commit 25caa94c4a26daaab1e65c6d887e2972aeb5749e from qemu
Returning a partial object on error is an invitation for a careless
caller to leak memory. We already fixed things in an earlier
patch to guarantee NULL if visit_start fails ("qapi: Guarantee
NULL obj on input visitor callback error"), but that does not
help the case where visit_start succeeds but some other failure
happens before visit_end, such that we leak a partially constructed
object outside visit_type_FOO(). As no one outside the testsuite
was actually relying on these semantics, it is cleaner to just
document and guarantee that ALL pointer-based visit_type_FOO()
functions always leave a safe value in *obj during an input visitor
(either the new object on success, or NULL if an error is
encountered), so callers can now unconditionally use
qapi_free_FOO() to clean up regardless of whether an error occurred.
The decision is done by adding visit_is_input(), then updating the
generated code to check if additional cleanup is needed based on
the type of visitor in use.
Note that we still leave *obj unchanged after a scalar-based
visit_type_FOO(); I did not feel like auditing all uses of
visit_type_Enum() to see if the callers would tolerate a specific
sentinel value (not to mention having to decide whether it would
be better to use 0 or ENUM__MAX as that sentinel).
Backports commit 68ab47e4b4ecc1c4649362b8cc1e49794d1a6537 from qemu
The semantics of the list visit are somewhat baroque, with the
following pseudocode when FooList is used:
start()
for (prev = head; cur = next(prev); prev = &cur) {
visit(&cur->value)
}
Note that these semantics (advance before visit) requires that
the first call to next() return the list head, while all other
calls return the next element of the list; that is, every visitor
implementation is required to track extra state to decide whether
to return the input as-is, or to advance. It also requires an
argument of 'GenericList **' to next(), solely because the first
iteration might need to modify the caller's GenericList head, so
that all other calls have to do a layer of dereferencing.
Thankfully, we only have two uses of list visits in the entire
code base: one in spapr_drc (which completely avoids
visit_next_list(), feeding in integers from a different source
than uint8List), and one in qapi-visit.py. That is, all other
list visitors are generated in qapi-visit.c, and share the same
paradigm based on a qapi FooList type, so we can refactor how
lists are laid out with minimal churn among clients.
We can greatly simplify things by hoisting the special case
into the start() routine, and flipping the order in the loop
to visit before advance:
start(head)
for (tail = *head; tail; tail = next(tail)) {
visit(&tail->value)
}
With the simpler semantics, visitors have less state to track,
the argument to next() is reduced to 'GenericList *', and it
also becomes obvious whether an input visitor is allocating a
FooList during visit_start_list() (rather than the old way of
not knowing if an allocation happened until the first
visit_next_list()). As a minor drawback, we now allocate in
two functions instead of one, and have to pass the size to
both functions (unless we were to tweak the input visitors to
cache the size to start_list for reuse during next_list, but
that defeats the goal of less visitor state).
The signature of visit_start_list() is chosen to match
visit_start_struct(), with the new parameters after 'name'.
The spapr_drc case is a virtual visit, done by passing NULL for
list, similarly to how NULL is passed to visit_start_struct()
when a qapi type is not used in those visits. It was easy to
provide these semantics for qmp-output and dealloc visitors,
and a bit harder for qmp-input (several prerequisite patches
refactored things to make this patch straightforward). But it
turned out that the string and opts visitors munge enough other
state during visit_next_list() to make it easier to just
document and require a GenericList visit for now; an assertion
will remind us to adjust things if we need the semantics in the
future.
Several pre-requisite cleanup patches made the reshuffling of
the various visitors easier; particularly the qmp input visitor.
Backports commit d9f62dde1303286b24ac8ce88be27e2b9b9c5f46 from qemu
As mentioned in previous patches, we want to call visit_end_struct()
functions unconditionally, so that visitors can release resources
tied up since the matching visit_start_struct() without also having
to worry about error priority if more than one error occurs.
Even though error_propagate() can be safely used to ignore a second
error during cleanup caused by a first error, it is simpler if the
cleanup cannot set an error. So, split out the error checking
portion (basically, input visitors checking for unvisited keys) into
a new function visit_check_struct(), which can be safely skipped if
any earlier errors are encountered, and leave the cleanup portion
(which never fails, but must be called unconditionally if
visit_start_struct() succeeded) in visit_end_struct().
Generated code in qapi-visit.c has diffs resembling:
|@@ -59,10 +59,12 @@ void visit_type_ACPIOSTInfo(Visitor *v,
| goto out_obj;
| }
| visit_type_ACPIOSTInfo_members(v, obj, &err);
|- error_propagate(errp, err);
|- err = NULL;
|+ if (err) {
|+ goto out_obj;
|+ }
|+ visit_check_struct(v, &err);
| out_obj:
|- visit_end_struct(v, &err);
|+ visit_end_struct(v);
| out:
and in qapi-event.c:
@@ -47,7 +47,10 @@ void qapi_event_send_acpi_device_ost(ACP
| goto out;
| }
| visit_type_q_obj_ACPI_DEVICE_OST_arg_members(v, ¶m, &err);
|- visit_end_struct(v, err ? NULL : &err);
|+ if (!err) {
|+ visit_check_struct(v, &err);
|+ }
|+ visit_end_struct(v);
| if (err) {
| goto out;
Backports commit 15c2f669e3fb2bc97f7b42d1871f595c0ac24af8 from qemu
Right now, qmp-output-visitor happens to produce a QNull result
if nothing is actually visited between the creation of the visitor
and the request for the resulting QObject. A stronger protocol
would require that a QMP output visit MUST visit something. But
to still be able to produce a JSON 'null' output, we need a new
visitor function that states our intentions. Yes, we could say
that such a visit must go through visit_type_any(), but that
feels clunky.
So this patch introduces the new visit_type_null() interface and
its no-op interface in the dealloc visitor, and stubs in the
qmp visitors (the next patch will finish the implementation).
For the visitors that will not implement the callback, document
the situation. The code in qapi-visit-core unconditionally
dereferences the callback pointer, so that a segfault will inform
a developer if they need to implement the callback for their
choice of visitor.
Note that JSON has a primitive null type, with the single value
null; likewise with the QNull type for QObject; but for QAPI,
we just have the 'null' value without a null type. We may
eventually want to add more support in QAPI for null (most likely,
we'd use it via an alternate type that permits 'null' or an
object); but we'll create that usage when we need it.
Backports commit 3bc97fd5924561d92f32758c67eaffd2e4e25038 from qemu
The visitor interface for mapping between QObject/QemuOpts/string
and QAPI is scandalously under-documented, making changes to visitor
core, individual visitors, and users of visitors difficult to
coordinate. Among other questions: when is it safe to pass NULL,
vs. when a string must be provided; which visitors implement which
callbacks; the difference between concrete and virtual visits.
Correct this by retrofitting proper contracts, and document where some
of the interface warts remain (for example, we may want to modify
visit_end_* to require the same 'obj' as the visit_start counterpart,
so the dealloc visitor can be simplified). Later patches in this
series will tackle some, but not all, of these warts.
Add assertions to (partially) enforce the contract. Some of these
were only made possible by recent cleanup commits.
Backports commit adfb264c9ed04bfc694921b72173be8e29e90024 from qemu
After recent changes, the only remaining use of
visit_start_implicit_struct() is for allocating the space needed
when visiting an alternate. Since the term 'implicit struct' is
hard to explain, rename the function to its current usage. While
at it, we can merge the functionality of visit_get_next_type()
into the same function, making it more like visit_start_struct().
Generated code is now slightly smaller:
| {
| Error *err = NULL;
|
|- visit_start_implicit_struct(v, (void**) obj, sizeof(BlockdevRef), &err);
|+ visit_start_alternate(v, name, (GenericAlternate **)obj, sizeof(**obj),
|+ true, &err);
| if (err) {
| goto out;
| }
|- visit_get_next_type(v, name, &(*obj)->type, true, &err);
|- if (err) {
|- goto out_obj;
|- }
| switch ((*obj)->type) {
| case QTYPE_QDICT:
| visit_start_struct(v, name, NULL, 0, &err);
...
| }
|-out_obj:
|- visit_end_implicit_struct(v);
|+ visit_end_alternate(v);
| out:
| error_propagate(errp, err);
| }
Backports commit dbf11922622685934bfb41e7cf2be9bd4a0405c0 from qemu
Rather than having two separate ways to create a QMP input
visitor, where the safer approach has the more verbose name,
it is better to consolidate things into a single function
where the caller must explicitly choose whether to be strict
or to ignore excess input. This patch is the strictly
mechanical conversion; the next patch will then audit which
uses can be made stricter.
Backports commit fc471c18d5d2ec713d5a019f9530398675494bc8 from qemu
By sticking the next pointer first, we don't need a union with
64-bit padding for smaller types. On 32-bit platforms, this
can reduce the size of uint8List from 16 bytes (or 12, depending
on whether 64-bit ints can tolerate 4-byte alignment) down to 8.
It has no effect on 64-bit platforms (where alignment still
dictates a 16-byte struct); but fewer anonymous unions is still
a win in my book.
It requires visit_next_list() to gain a size parameter, to know
what size element to allocate; comparable to the size parameter
of visit_start_struct().
I debated about going one step further, to allow for fewer casts,
by doing:
typedef GenericList GenericList;
struct GenericList {
GenericList *next;
};
struct FooList {
GenericList base;
Foo *value;
};
so that you convert to 'GenericList *' by '&foolist->base', and
back by 'container_of(generic, GenericList, base)' (as opposed to
the existing '(GenericList *)foolist' and '(FooList *)generic').
But doing that would require hoisting the declaration of
GenericList prior to inclusion of qapi-types.h, rather than its
current spot in visitor.h; it also makes iteration a bit more
verbose through 'foolist->base.next' instead of 'foolist->next'.
Note that for lists of objects, the 'value' payload is still
hidden behind a boxed pointer. Someday, it would be nice to do:
struct FooList {
FooList *next;
Foo value;
};
for one less level of malloc for each list element. This patch
is a step in that direction (now that 'next' is no longer at a
fixed non-zero offset within the struct, we can store more than
just a pointer's-worth of data as the value payload), but the
actual conversion would be a task for another series, as it will
touch a lot of code.
Backports commit e65d89bf1a4484e0db0f3dc820a8b209f2fb1e8b from qemu
We have three classes of QAPI visitors: input, output, and dealloc.
Currently, all implementations of these visitors have one thing in
common based on their visitor type: the implementation used for the
visit_type_enum() callback. But since we plan to add more such
common behavior, in relation to documenting and further refining
the semantics, it makes more sense to have the visitor
implementations advertise which class they belong to, so the common
qapi-visit-core code can use that information in multiple places.
A later patch will better document the types of visitors directly
in visitor.h.
For this patch, knowing the class of a visitor implementation lets
us make input_type_enum() and output_type_enum() become static
functions, by replacing the callback function Visitor.type_enum()
with the simpler enum member Visitor.type. Share a common
assertion in qapi-visit-core as part of the refactoring.
Move comments in opts-visitor.c to match the refactored layout.
Backports commit 983f52d4b3f86fb9dc9f8b142132feb5a8723016 from qemu
Move the architecture agnostic function prototypes for exec.c out of
cputlb.h to exec-all.h. This allows hiding of the arch specific
cputlb.h from exec.c which should be getting close to having no
architecture specifics. Prepares support for multi-arch, which will have
a minimal cpu.h that services exec.c but not cputlb.h.
Backports commit dfccc7602374c9fd3b083208b552d62daa244811 from qemu
To prepare for multi-arch, cputlb.c should only have awareness of one
single architecture. This means it should not have access to the full
CPU lists which may be heterogeneous. Instead, push the CPU_LOOP() up
to the one and only caller in exec.c.
Backports commit 9a13565d52bfd321934fb44ee004bbaf5f5913a8 from qemu
The last two arguments to these functions are the last and first bit to
check relative to the base. The code was using incorrectly the first
bit and the number of bits. Fix this in cpu_physical_memory_get_dirty
and cpu_physical_memory_all_dirty. This requires a few changes in the
iteration; change the code in cpu_physical_memory_set_dirty_range to
match.
Backports commit 88c73d16ad1b6c22a2ab082064d0d521f756296a from qemu
The __atomic primitives have been available since GCC 4.7 and provide
a richer interface for describing memory ordering requirements. As a
bonus by using the primitives instead of hand-rolled functions we can
use tools such as the ThreadSanitizer which need the use of well
defined APIs for its analysis.
If we have __ATOMIC defines we exclusively use the __atomic primitives
for all our atomic access. Otherwise we fall back to the mixture of
__sync and hand-rolled barrier cases.
Backports commit a0aa44b488b3601415d55041e4619aef5f3a4ba8 from qemu
__atomic_thread_fence does not include a compiler barrier; in the
C++11 memory model, fences take effect in combination with other
atomic operations. GCC implements this by making __atomic_load and
__atomic_store access memory as if the pointer was volatile, and
leaves no trace whatsoever of acquire and release fences in the
compiler's intermediate representation.
In QEMU, we want memory barriers to act on all memory, but at the same
time we would like to use __atomic_thread_fence for portability reasons.
Add compiler barriers manually around the __atomic_thread_fence.
Backports commit 3bbf572345c65813f86a8fc434ea1b23beb08e16 from qemu
Although accesses to ram_list.dirty_memory[] use atomics so multiple
threads can safely dirty the bitmap, the data structure is not fully
thread-safe yet.
This patch handles the RAM hotplug case where ram_list.dirty_memory[] is
grown. ram_list.dirty_memory[] is change from a regular bitmap to an
RCU array of pointers to fixed-size bitmap blocks. Threads can continue
accessing bitmap blocks while the array is being extended. See the
comments in the code for an in-depth explanation of struct
DirtyMemoryBlocks.
I have tested that live migration with virtio-blk dataplane works.
Backports commit 5b82b703b69acc67b78b98a5efc897a3912719eb from qemu
There is no particular reason to keep these functions in the header.
Suggested by Paolo.
Backports commit 99affd1d5bd4e396ecda50e53dfbc5147fa1313d from qemu
qemu-log: dfilter-ise exec, out_asm, op and opt_op
This ensures the code generation debug code will honour -dfilter if set.
For the "exec" tracing I've added a new inline macro for efficiency's
sake.
Backports commit d977e1c2dbc9e63454b2000f91954d02543bf43b from qemu
When debugging big programs or system emulation sometimes you want both
the verbosity of cpu,exec et all but don't want to generate lots of logs
for unneeded stuff. This patch adds a new option -dfilter which allows
you to specify interesting address ranges in the form:
-dfilter 0x8000..0x8fff,0xffffffc000080000+0x200,...
Then logging code can use the new qemu_log_in_addr_range() function to
decide if it will output logging information for the given range.
Backports commit 3514552e04388d8e7686bcf89efd022e892acb5b from qemu
Improve the TB execution logging so that it is easier to identify
what is happening from trace logs:
* move the "Trace" logging of executed TBs into cpu_tb_exec()
so that it is emitted if and only if we actually execute a TB,
and for consistency for the CPU state logging
* log when we link two TBs together via tb_add_jump()
* log when cpu_tb_exec() returns early from a chain of TBs
The new style logging looks like this:
Trace 0x7fb7cc822ca0 [ffffffc0000dce00]
Linking TBs 0x7fb7cc822ca0 [ffffffc0000dce00] index 0 -> 0x7fb7cc823110 [ffffffc0000dce10]
Trace 0x7fb7cc823110 [ffffffc0000dce10]
Trace 0x7fb7cc823420 [ffffffc000302688]
Trace 0x7fb7cc8234a0 [ffffffc000302698]
Trace 0x7fb7cc823520 [ffffffc0003026a4]
Trace 0x7fb7cc823560 [ffffffc0000dce44]
Linking TBs 0x7fb7cc823560 [ffffffc0000dce44] index 1 -> 0x7fb7cc8235d0 [ffffffc0000dce70]
Trace 0x7fb7cc8235d0 [ffffffc0000dce70]
Stopped execution of TB chain before 0x7fb7cc8235d0 [ffffffc0000dce70]
Trace 0x7fb7cc8235d0 [ffffffc0000dce70]
Trace 0x7fb7cc822fd0 [ffffffc0000dd52c]
Backports commit 1a830635229e14c403600167823ea6b3b79d3097 from qemu
