This is identical for each target. So, move the initialization to
common code. Move the variable itself out of tcg_ctx and name it
cpu_env to minimize changes within targets.
This also means we can remove tcg_global_reg_new_{ptr,i32,i64},
since there are no longer global-register temps created by targets.
Backports commit 1c2adb958fc07e5b3e81ed21b801c04a15f41f4f from qemu
We don't really free anything in this function anymore; we just remove
the TB from the binary search tree.
Backports commit be1e01171b556807198c84feac7cf4bca0d904c2 from qemu
This is a prerequisite for supporting multiple TCG contexts, since
we will have threads generating code in separate regions of
code_gen_buffer.
For this we need a new field (.size) in struct tb_tc to keep
track of the size of the translated code. This field uses a size_t
to avoid adding a hole to the struct, although really an unsigned
int would have been enough.
The comparison function we use is optimized for the common case:
insertions. Profiling shows that upon booting debian-arm, 98%
of comparisons are between existing tb's (i.e. a->size and b->size
are both !0), which happens during insertions (and removals, but
those are rare). The remaining cases are lookups. From reading the glib
sources we see that the first key is always the lookup key. However,
the code does not assume this to always be the case because this
behaviour is not guaranteed in the glib docs. However, we embed
this knowledge in the code as a branch hint for the compiler.
Note that tb_free does not free space in the code_gen_buffer anymore,
since we cannot easily know whether the tb is the last one inserted
in code_gen_buffer. The next patch in this series renames tb_free
to tb_remove to reflect this.
Performance-wise, lookups in tb_find_pc are the same as before:
O(log n). However, insertions are O(log n) instead of O(1), which
results in a small slowdown when booting debian-arm:
Performance counter stats for 'build/arm-softmmu/qemu-system-arm \
-machine type=virt -nographic -smp 1 -m 4096 \
-netdev user,id=unet,hostfwd=tcp::2222-:22 \
-device virtio-net-device,netdev=unet \
-drive file=img/arm/jessie-arm32.qcow2,id=myblock,index=0,if=none \
-device virtio-blk-device,drive=myblock \
-kernel img/arm/aarch32-current-linux-kernel-only.img \
-append console=ttyAMA0 root=/dev/vda1 \
-name arm,debug-threads=on -smp 1' (10 runs):
- Before:
8048.598422 task-clock (msec) # 0.931 CPUs utilized ( +- 0.28% )
16,974 context-switches # 0.002 M/sec ( +- 0.12% )
0 cpu-migrations # 0.000 K/sec
10,125 page-faults # 0.001 M/sec ( +- 1.23% )
35,144,901,879 cycles # 4.367 GHz ( +- 0.14% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
65,758,252,643 instructions # 1.87 insns per cycle ( +- 0.33% )
10,871,298,668 branches # 1350.707 M/sec ( +- 0.41% )
192,322,212 branch-misses # 1.77% of all branches ( +- 0.32% )
8.640869419 seconds time elapsed ( +- 0.57% )
- After:
8146.242027 task-clock (msec) # 0.923 CPUs utilized ( +- 1.23% )
17,016 context-switches # 0.002 M/sec ( +- 0.40% )
0 cpu-migrations # 0.000 K/sec
18,769 page-faults # 0.002 M/sec ( +- 0.45% )
35,660,956,120 cycles # 4.378 GHz ( +- 1.22% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
65,095,366,607 instructions # 1.83 insns per cycle ( +- 1.73% )
10,803,480,261 branches # 1326.192 M/sec ( +- 1.95% )
195,601,289 branch-misses # 1.81% of all branches ( +- 0.39% )
8.828660235 seconds time elapsed ( +- 0.38% )
Backports commit 2ac01d6dafabd4a726254eea98824c798d416ee4 from qemu
Now that we have curr_cflags, we can include CF_USE_ICOUNT
early and then remove it as necessary.
Backports commit 416986d3f97329655e30da7271a2d11c6d707b06 from qemu
Convert all existing readers of tb->cflags to tb_cflags, so that we
use atomic_read and therefore avoid undefined behaviour in C11.
Note that the remaining setters/getters of the field are protected
by tb_lock, and therefore do not need conversion.
Luckily all readers access the field via 'tb->cflags' (so no foo.cflags,
bar->cflags in the code base), which makes the conversion easily
scriptable:
FILES=$(git grep 'tb->cflags' target include/exec/gen-icount.h \
accel/tcg/translator.c | cut -f1 -d':' | sort | uniq)
perl -pi -e 's/([^.>])tb->cflags/$1tb_cflags(tb)/g' $FILES
perl -pi -e 's/([a-z->.]*)(->|\.)tb->cflags/tb_cflags($1$2tb)/g' $FILES
Then manually fixed the few errors that checkpatch reported.
Compile-tested for all targets.
Backports commit c5a49c63fa26e8825ad101dfe86339ae4c216539 from qemu
This will enable us to decouple code translation from the value
of parallel_cpus at any given time. It will also help us minimize
TB flushes when generating code via EXCP_ATOMIC.
Note that the declaration of parallel_cpus is brought to exec-all.h
to be able to define there the "curr_cflags" inline.
Backports commit 4e2ca83e71b51577b06b1468e836556912bd5b6e from qemu
Having a fixed-size hash table for keeping track of all translation blocks
is suboptimal: some workloads are just too big or too small to get maximum
performance from the hash table. The MRU promotion policy helps improve
performance when the hash table is a little undersized, but it cannot
make up for severely undersized hash tables.
Furthermore, frequent MRU promotions result in writes that are a scalability
bottleneck. For scalability, lookups should only perform reads, not writes.
This is not a big deal for now, but it will become one once MTTCG matures.
The appended fixes these issues by using qht as the implementation of
the TB hash table. This solution is superior to other alternatives considered,
namely:
- master: implementation in QEMU before this patchset
- xxhash: before this patch, i.e. fixed buckets + xxhash hashing + MRU.
- xxhash-rcu: fixed buckets + xxhash + RCU list + MRU.
MRU is implemented here by adding an intermediate struct
that contains the u32 hash and a pointer to the TB; this
allows us, on an MRU promotion, to copy said struct (that is not
at the head), and put this new copy at the head. After a grace
period, the original non-head struct can be eliminated, and
after another grace period, freed.
- qht-fixed-nomru: fixed buckets + xxhash + qht without auto-resize +
no MRU for lookups; MRU for inserts.
The appended solution is the following:
- qht-dyn-nomru: dynamic number of buckets + xxhash + qht w/ auto-resize +
no MRU for lookups; MRU for inserts.
The plots below compare the considered solutions. The Y axis shows the
boot time (in seconds) of a debian jessie image with arm-softmmu; the X axis
sweeps the number of buckets (or initial number of buckets for qht-autoresize).
The plots in PNG format (and with errorbars) can be seen here:
http://imgur.com/a/Awgnq
Each test runs 5 times, and the entire QEMU process is pinned to a
single core for repeatability of results.
Host: Intel Xeon E5-2690
28 ++------------+-------------+-------------+-------------+------------++
A***** + + + master **A*** +
27 ++ * xxhash ##B###++
| A******A****** xxhash-rcu $$C$$$ |
26 C$$ A******A****** qht-fixed-nomru*%%D%%%++
D%%$$ A******A******A*qht-dyn-mru A*E****A
25 ++ %%$$ qht-dyn-nomru &&F&&&++
B#####% |
24 ++ #C$$$$$ ++
| B### $ |
| ## C$$$$$$ |
23 ++ # C$$$$$$ ++
| B###### C$$$$$$ %%%D
22 ++ %B###### C$$$$$$C$$$$$$C$$$$$$C$$$$$$C$$$$$$C
| D%%%%%%B###### @E@@@@@@ %%%D%%%@@@E@@@@@@E
21 E@@@@@@E@@@@@@F&&&@@@E@@@&&&D%%%%%%B######B######B######B######B######B
+ E@@@ F&&& + E@ + F&&& + +
20 ++------------+-------------+-------------+-------------+------------++
14 16 18 20 22 24
log2 number of buckets
Host: Intel i7-4790K
14.5 ++------------+------------+-------------+------------+------------++
A** + + + master **A*** +
14 ++ ** xxhash ##B###++
13.5 ++ ** xxhash-rcu $$C$$$++
| qht-fixed-nomru %%D%%% |
13 ++ A****** qht-dyn-mru @@E@@@++
| A*****A******A****** qht-dyn-nomru &&F&&& |
12.5 C$$ A******A******A*****A****** ***A
12 ++ $$ A*** ++
D%%% $$ |
11.5 ++ %% ++
B### %C$$$$$$ |
11 ++ ## D%%%%% C$$$$$ ++
| # % C$$$$$$ |
10.5 F&&&&&&B######D%%%%% C$$$$$$C$$$$$$C$$$$$$C$$$$$C$$$$$$ $$$C
10 E@@@@@@E@@@@@@B#####B######B######E@@@@@@E@@@%%%D%%%%%D%%%###B######B
+ F&& D%%%%%%B######B######B#####B###@@@D%%% +
9.5 ++------------+------------+-------------+------------+------------++
14 16 18 20 22 24
log2 number of buckets
Note that the original point before this patch series is X=15 for "master";
the little sensitivity to the increased number of buckets is due to the
poor hashing function in master.
xxhash-rcu has significant overhead due to the constant churn of allocating
and deallocating intermediate structs for implementing MRU. An alternative
would be do consider failed lookups as "maybe not there", and then
acquire the external lock (tb_lock in this case) to really confirm that
there was indeed a failed lookup. This, however, would not be enough
to implement dynamic resizing--this is more complex: see
"Resizable, Scalable, Concurrent Hash Tables via Relativistic
Programming" by Triplett, McKenney and Walpole. This solution was
discarded due to the very coarse RCU read critical sections that we have
in MTTCG; resizing requires waiting for readers after every pointer update,
and resizes require many pointer updates, so this would quickly become
prohibitive.
qht-fixed-nomru shows that MRU promotion is advisable for undersized
hash tables.
However, qht-dyn-mru shows that MRU promotion is not important if the
hash table is properly sized: there is virtually no difference in
performance between qht-dyn-nomru and qht-dyn-mru.
Before this patch, we're at X=15 on "xxhash"; after this patch, we're at
X=15 @ qht-dyn-nomru. This patch thus matches the best performance that we
can achieve with optimum sizing of the hash table, while keeping the hash
table scalable for readers.
The improvement we get before and after this patch for booting debian jessie
with arm-softmmu is:
- Intel Xeon E5-2690: 10.5% less time
- Intel i7-4790K: 5.2% less time
We could get this same improvement _for this particular workload_ by
statically increasing the size of the hash table. But this would hurt
workloads that do not need a large hash table. The dynamic (upward)
resizing allows us to start small and enlarge the hash table as needed.
A quick note on downsizing: the table is resized back to 2**15 buckets
on every tb_flush; this makes sense because it is not guaranteed that the
table will reach the same number of TBs later on (e.g. most bootup code is
thrown away after boot); it makes sense to grow the hash table as
more code blocks are translated. This also avoids the complication of
having to build downsizing hysteresis logic into qht.
Backports commit 909eaac9bbc2ed4f3a82ce38e905b87d478a3e00 from qemu
This shares an cached empty FlatView among address spaces. The empty
FV is used every time when a root MR renders into a FV without memory
sections which happens when MR or its children are not enabled or
zero-sized. The empty_view is not NULL to keep the rest of memory
API intact; it also has a dispatch tree for the same reason.
On POWER8 with 255 CPUs, 255 virtio-net, 40 PCI bridges guest this halves
the amount of FlatView's in use (557 -> 260) and dispatch tables
(~800000 -> ~370000). In an unrelated experiment with 112 non-virtio
devices on x86 ("-M pc"), only 4 FlatViews are alive, and about ~2000
are created at startup.
Backports commit 092aa2fc65b7a35121616aad8f39d47b8f921618 from qemu
Since FlatViews are shared now and ASes not, this gets rid of
address_space_init_shareable().
This should cause no behavioural change.
Backports commit b516572f31c0ea0937cd9d11d9bd72dd83809886 from qemu
This renames some helpers to reflect better what they do.
This should cause no behavioural change.
Backports commit 8629d3fcb77e9775e44d9051bad0fb5187925eae from qemu
FlatView's will be shared between AddressSpace's and subpage_t
and MemoryRegionSection cannot store AS anymore, hence this change.
In particular, for:
typedef struct subpage_t {
MemoryRegion iomem;
- AddressSpace *as;
+ FlatView *fv;
hwaddr base;
uint16_t sub_section[];
} subpage_t;
struct MemoryRegionSection {
MemoryRegion *mr;
- AddressSpace *address_space;
+ FlatView *fv;
hwaddr offset_within_region;
Int128 size;
hwaddr offset_within_address_space;
bool readonly;
};
This should cause no behavioural change.
Backports commit 166206845f7fd75e720e6feea0bb01957c8da07f from qemu
As we are going to share FlatView's between AddressSpace's,
and AddressSpaceDispatch is a structure to perform quick lookup
in FlatView, this moves ASD to FlatView.
After previosly open coded ASD rendering, we can also remove
as->next_dispatch as the new FlatView pointer is stored
on a stack and set to an AS atomically.
flatview_destroy() is executed under RCU instead of
address_space_dispatch_free() now.
This makes mem_begin/mem_commit to work with ASD and mem_add with FV
as later on mem_add will be taking FV as an argument anyway.
This should cause no behavioural change.
Backports commit 66a6df1dc6d5b28cc3e65db0d71683fbdddc6b62 from qemu
This allows us to explicitly pass float16 to helpers rather than
assuming uint32_t and dealing with the result. Of course they will be
passed in i32 sized registers by default.
Backports commit 35737497008aeabce5dc381a41d3827bec486192 from qemu
The MC68040 MMU provides the size of the access that
triggers the page fault.
This size is set in the Special Status Word which
is written in the stack frame of the access fault
exception.
So we need the size in m68k_cpu_unassigned_access() and
m68k_cpu_handle_mmu_fault().
To be able to do that, this patch modifies the prototype of
handle_mmu_fault handler, tlb_fill() and probe_write().
do_unassigned_access() already includes a size parameter.
This patch also updates handle_mmu_fault handlers and
tlb_fill() of all targets (only parameter, no code change).
Backports commit 98670d47cd8d63a529ff230fd39ddaa186156f8c from qemu
With no fixed array allocation, we can't overflow a buffer.
This will be important as optimizations related to host vectors
may expand the number of ops used.
Use QTAILQ to link the ops together.
Backports commit 15fa08f8451babc88d733bd411d4c94976f9d0f8 from qemu
Normally we create an address space for that CPU and pass that address
space into the function. Let's just do it inside to unify address space
creations. It'll simplify my next patch to rename those address spaces.
Backports commit 80ceb07a83375e3a0091591f96bd47bce2f640ce from qemu
This was never used since its introduction in commit
196ea13104f8 ("memory: Add global-locking property to memory
regions").
Backports commit e2fbe20851ceec5ccd7b539a89db0420393fb85d from qemu
The GET and MAKE functions weren't really specific enough.
We now have a full complement of functions that convert exactly
between temporaries, arguments, tcgv pointers, and indices.
The target/sparc change is also a bug fix, which would have affected
a host that defines TCG_TARGET_HAS_extr[lh]_i64_i32, i.e. MIPS64.
Backports commit dc41aa7d34989b552efe712ffe184236216f960b from qemu
Transform TCGv_* to an "argument" or a temporary.
For now, an argument is simply the temporary index.
Backports commit ae8b75dc6ec808378487064922f25f1e7ea7a9be from qemu
In preparation for adding tc.size to be able to keep track of
TB's using the binary search tree implementation from glib.
Backports commit e7e168f41364c6e83d0f75fc1b3ce7f9c41ccf76 from qemu
And fix the following warning when DEBUG_TB_INVALIDATE is enabled
in translate-all.c:
CC mipsn32-linux-user/accel/tcg/translate-all.o
/data/src/qemu/accel/tcg/translate-all.c: In function ‘tb_alloc_page’:
/data/src/qemu/accel/tcg/translate-all.c:1201:16: error: format ‘%lx’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘tb_page_addr_t {aka unsigned int}’ [-Werror=format=]
printf("protecting code page: 0x" TARGET_FMT_lx "\n",
^
cc1: all warnings being treated as errors
/data/src/qemu/rules.mak:66: recipe for target 'accel/tcg/translate-all.o' failed
make[1]: *** [accel/tcg/translate-all.o] Error 1
Makefile:328: recipe for target 'subdir-mipsn32-linux-user' failed
make: *** [subdir-mipsn32-linux-user] Error 2
cota@flamenco:/data/src/qemu/build ((18f3fe1...) *$)$
Backports commit 67a5b5d2f6eb6d3b980570223ba5c478487ddb6f from qemu
Replace the USE_DIRECT_JUMP ifdef with a TCG_TARGET_HAS_direct_jump
boolean test. Replace the tb_set_jmp_target1 ifdef with an unconditional
function tb_target_set_jmp_target.
While we're touching all backends, add a parameter for tb->tc_ptr;
we're going to need it shortly for some backends.
Move tb_set_jmp_target and tb_add_jump from exec-all.h to cpu-exec.c.
Backports commit a85833933628384d74ec412024d55cf012640287 from qemu
Used later. An enum makes expected values explicit and
bounds the value space of switches.
Backports commit 77fc6f5e28667634916f114ae04c6029cd7b9c45 from qemu
This will allow some amount of cleanup to happen before
switching the backends over to enum DisasJumpType.
Backports commit 5dc66895b0113034cd37fd5e65911d7959fc26a9 from qemu
Move the MemTxResult type to memattrs.h. We're going to want to
use it in cpu/qom.h, which doesn't want to include all of
memory.h. In practice MemTxResult and MemTxAttrs are pretty
closely linked since both are used for the new-style
read_with_attrs and write_with_attrs callbacks, so memattrs.h
is a reasonable home for this rather than creating a whole
new header file for it.
Backports commit 3114d092b1740f9db9aa559aeb48ee387011e1da from qemu
We are going to share FlatView's between AddressSpace's and per-AS
memory listeners won't suit the purpose anymore so open code
the dispatch tree rendering.
Since there is a good chance that dispatch_listener was the only
listener, this avoids address_space_update_topology_pass() if there is
no registered listeners; this should improve starting time.
This should cause no behavioural change.
Backports commit 1b04a1580917d9e41fd37ca62cbff9b4bf061e96 from qemu
As a precursor to later patches attempt to come up with a more
concrete wording for what each of the common exit cases would be.
Backports commit df0311e634828fdc99ca59352aef68503d631aad from qemu
Rename memory_region_init_rom() to memory_region_init_rom_nomigrate()
and memory_region_init_rom_device() to
memory_region_init_rom_device_nomigrate().
Backports commit b59821a95bd1d7cb4697fd7748725c910582e0e7 from qemu
Rename memory_region_init_ram() to memory_region_init_ram_nomigrate().
This leaves the way clear for us to provide a memory_region_init_ram()
which does handle migration.
Backports commit 1cfe48c1ce219b60a9096312f7a61806fae64ab3 from qemu
The various functions for initializing RAM MemoryRegions do not do
anything to cause the data in the MemoryRegion to be migrated.
Note in their documentation comments that this is the responsibility
of the caller.
(We will shortly add a new function that *does* do this for you.)
Backports commit a5c0234bb2754f5248e67929a34c843dbe039da5 from qemu
Now that we have proper locking after MTTCG patches have landed, we
can revert the commit. This reverts commit
a9353fe897ca2687e5b3385ed39e3db3927a90e0.
Backports commit 406bc339b0505fcfc2ffcbca1f05a3756e338a65 from qemu
Add CONFIG_TCG around TLB-related functions and structure declarations.
Some of these functions are defined in ./accel/tcg/cputlb.c, which will
not be linked in if TCG is disabled, and have no stubs; therefore, their
callers will also be compiled out for --disable-tcg.
Backports commit b11ec7f2e44b285a3967d629b55d1a6970b06787 from qemu
translate-all.c will be disabled if tcg is disabled in the build,
so page_size_init() function and related variables will be moved
to exec.c file.
Backports commit a0be0c585f5dcc4d50a37f6a20d3d625c5ef3a2c from qemu
Commit 1f5c00cfdb8114c ("qom/cpu: move tlb_flush to cpu_common_reset")
moved the call to tlb_flush() from the target-specific reset handlers
into the common code qom/cpu.c file, and protected the call with
"#ifdef CONFIG_SOFTMMU" to avoid that it is called for linux-user
only targets. But since qom/cpu.c is common code, CONFIG_SOFTMMU is
*never* defined here, so the tlb_flush() was simply never executed
anymore. Fix it by introducing a wrapper for tlb_flush() in a file
that is re-compiled for each target, i.e. in translate-all.c.
Backports commit 2cd53943115be5118b5b2d4b80ee0a39c94c4f73 from qemu
We are relying on cpu_env being defined as a global, yet most
targets (i.e. all but arm/a64) have it defined as a local variable.
Luckily all of them use the same "cpu_env" name, but really
compilation shouldn't break if the name of that local variable
changed.
Fix it by using tcg_ctx.tcg_env, which all targets set in their
translate_init function. This change also helps paving the way
for the upcoming "translation loop common to all targets" work.
Backports commit 53f6672bcf57d82b794a2cc3a3469be7d35c8653 from qemu
Allocating an arbitrarily-sized array of tbs results in either
(a) a lot of memory wasted or (b) unnecessary flushes of the code
cache when we run out of TB structs in the array.
An obvious solution would be to just malloc a TB struct when needed,
and keep the TB array as an array of pointers (recall that tb_find_pc()
needs the TB array to run in O(log n)).
Perhaps a better solution, which is implemented in this patch, is to
allocate TB's right before the translated code they describe. This
results in some memory waste due to padding to have code and TBs in
separate cache lines--for instance, I measured 4.7% of padding in the
used portion of code_gen_buffer when booting aarch64 Linux on a
host with 64-byte cache lines. However, it can allow for optimizations
in some host architectures, since TCG backends could safely assume that
the TB and the corresponding translated code are very close to each
other in memory. See this message by rth for a detailed explanation:
https://lists.gnu.org/archive/html/qemu-devel/2017-03/msg05172.html
Subject: Re: GSoC 2017 Proposal: TCG performance enhancements
Backports commit 6e3b2bfd6af488a896f7936e99ef160f8f37e6f2 from qemu
Instead of exporting goto_ptr directly to TCG frontends, export
tcg_gen_lookup_and_goto_ptr(), which calls goto_ptr with the pointer
returned by the lookup_tb_ptr() helper. This is the only use case
we have for goto_ptr and lookup_tb_ptr, so having this function is
very convenient. Furthermore, it trivially allows us to avoid calling
the lookup helper if goto_ptr is not implemented by the backend.
Backports commit cedbcb01529cb6cf9a2289cdbebbc63f6149fc18 from qemu
