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
