Preparation for collapsing the two byte swaps, adjust_endianness and
handle_bswap, along the I/O path.
Target dependant attributes are conditionalized upon NEED_CPU_H.
Signed-off-by: Tony Nguyen <tony.nguyen@bt.com>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Message-Id: <81d9cd7d7f5aaadfa772d6c48ecee834e9cf7882.1566466906.git.tony.nguyen@bt.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This patch moves the define of target access alignment earlier from
target/foo/cpu.h to configure.
Suggested in Richard Henderson's reply to "[PATCH 1/4] tcg: TCGMemOp is now
accelerator independent MemOp"
Signed-off-by: Tony Nguyen <tony.nguyen@bt.com>
Message-Id: <11e818d38ebc40e986cfa62dd7d0afdc@tpw09926dag18e.domain1.systemhost.net>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: tony.nguyen@bt.com <tony.nguyen@bt.com>
No header includes qemu-common.h after this commit, as prescribed by
qemu-common.h's file comment.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20190523143508.25387-5-armbru@redhat.com>
[Rebased with conflicts resolved automatically, except for
include/hw/arm/xlnx-zynqmp.h hw/arm/nrf51_soc.c hw/arm/msf2-soc.c
block/qcow2-refcount.c block/qcow2-cluster.c block/qcow2-cache.c
target/arm/cpu.h target/lm32/cpu.h target/m68k/cpu.h target/mips/cpu.h
target/moxie/cpu.h target/nios2/cpu.h target/openrisc/cpu.h
target/riscv/cpu.h target/tilegx/cpu.h target/tricore/cpu.h
target/unicore32/cpu.h target/xtensa/cpu.h; bsd-user/main.c and
net/tap-bsd.c fixed up]
Perform a per-element conditional move. This combination operation is
easier to implement on some host vector units than plain cmp+bitsel.
Omit the usual gvec interface, as this is intended to be used by
target-specific gvec expansion call-backs.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This operation performs d = (b & a) | (c & ~a), and is present
on a majority of host vector units. Include gvec expanders.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Replace the single opcode in .opc with a null-terminated
array in .opt_opc. We still require that all opcodes be
used with the same .vece.
Validate the contents of this list with CONFIG_DEBUG_TCG.
All tcg_gen_*_vec functions will check any list active
during .fniv expansion. Swap the active list in and out
as we expand other opcodes, or take control away from the
front-end function.
Convert all existing vector aware front ends.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
If the TB generates too much code, such that backend relocations
overflow, try again with a smaller TB. In support of this, move
relocation processing from a random place within tcg_out_op, in
the handling of branch opcodes, to a new function at the end of
tcg_gen_code.
This is not a complete solution, as there are additional relocs
generated for out-of-line ldst handling and constant pools.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This will let backends implement the double-word shift operation.
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
dump_exec_info() takes an fprintf()-like callback and a FILE * to pass
to it.
Its only caller hmp_info_jit() passes monitor_fprintf() and the
current monitor cast to FILE *. monitor_fprintf() casts it right
back, and is otherwise identical to monitor_printf(). The
type-punning is ugly.
Drop the callback, and call qemu_printf() instead.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20190417191805.28198-5-armbru@redhat.com>
dump_opcount_info() takes an fprintf()-like callback and a FILE * to
pass to it.
Its only caller hmp_info_opcount() passes monitor_fprintf() and the
current monitor cast to FILE *. monitor_fprintf() casts it right
back, and is otherwise identical to monitor_printf(). The
type-punning is ugly.
Drop the callback, and call qemu_printf() instead.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20190417191805.28198-4-armbru@redhat.com>
Currently, a jump to a label that is not defined anywhere will
be emitted not be relocated. This results in a jump to a random
jump target. With tcg debugging, print a diagnostic to the -d op
file and abort.
This could help debug or detect errors like
c2d9644e6d ("target/arm: Fix crash on conditional instruction in an IT block")
Reported-by: Roman Kapl <code@rkapl.cz>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Most list head structs need not be given a name. In most cases the
name is given just in case one is going to use QTAILQ_LAST, QTAILQ_PREV
or reverse iteration, but this does not apply to lists of other kinds,
and even for QTAILQ in practice this is only rarely needed. In addition,
we will soon reimplement those macros completely so that they do not
need a name for the head struct. So clean up everything, not giving a
name except in the rare case where it is necessary.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Use this to notice the opcodes that exit the TB, which implies
that local temps are really dead and need not be synced.
Previously we so marked the true end of the TB, but that was
immediately overwritten by the la_bb_end invoked by any
TCG_OPF_BB_END opcode, like exit_tb.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Allocate storage for, but do not yet fill in, per-opcode
preferences for the output operands. Pass it in to the
register allocation routines for output operands.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Increment when adding branches, and decrement when removing them.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Remember which helpers have been marked noreturn.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Previously, the low 4 bits were used for TCG_CALL_TYPE_MASK,
which was removed in 6a18ae2d29.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
It's unused since 75e8b9b7aa.
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <20181209193749.12277-9-cota@braap.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Both GCC v4.8 and Clang v3.4 (our minimum versions) support
__builtin_unreachable(), so we can remove the version check here now.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Thomas Huth <thuth@redhat.com>
GCC7+ will no longer advertise support for 16-byte __atomic operations
if only cmpxchg is supported, as for x86_64. Fortunately, x86_64 still
has support for __sync_compare_and_swap_16 and we can make use of that.
AArch64 does not have, nor ever has had such support, so open-code it.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
When we implemented per-vCPU TCG contexts, we forgot to also
distribute the tcg_time counter, which has remained as a global
accessed without any serialization, leading to potentially missed
counts.
Fix it by distributing the field over the TCG contexts, embedding
it into TCGProfile with a field called "cpu_exec_time", which is more
descriptive than "tcg_time". Add a function to query this value
directly, and for completeness, fill in the field in
tcg_profile_snapshot, even though its callers do not use it.
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <20181010144853.13005-5-cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This plugs two 4-byte holes in 64-bit.
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <20181010144853.13005-4-cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Also, assert that we don't overflow any of two different offsets into
the TB. Both unwind and goto_tb both record a uint16_t for later use.
This fixes an arm-softmmu test case utilizing NEON in which there is
a TB generated that runs to 7800 opcodes, and compiles to 96k on an
x86_64 host. This overflows the 16-bit offset in which we record the
goto_tb reset offset. Because of that overflow, we install a jump
destination that goes to neverland. Boom.
With this reduced op count, the same TB compiles to about 48k for
aarch64, ppc64le, and x86_64 hosts, and neither assertion fires.
Cc: qemu-stable@nongnu.org
Reported-by: "Jason A. Donenfeld" <Jason@zx2c4.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Use mmap_lock in user-mode to protect TCG state and the page descriptors.
In !user-mode, each vCPU has its own TCG state, so no locks needed.
Per-page locks are used to protect the page descriptors.
Per-TB locks are used in both modes to protect TB jumps.
Some notes:
- tb_lock is removed from notdirty_mem_write by passing a
locked page_collection to tb_invalidate_phys_page_fast.
- tcg_tb_lookup/remove/insert/etc have their own internal lock(s),
so there is no need to further serialize access to them.
- do_tb_flush is run in a safe async context, meaning no other
vCPU threads are running. Therefore acquiring mmap_lock there
is just to please tools such as thread sanitizer.
- Not visible in the diff, but tb_invalidate_phys_page already
has an assert_memory_lock.
- cpu_io_recompile is !user-only, so no mmap_lock there.
- Added mmap_unlock()'s before all siglongjmp's that could
be called in user-mode while mmap_lock is held.
+ Added an assert for !have_mmap_lock() after returning from
the longjmp in cpu_exec, just like we do in cpu_exec_step_atomic.
Performance numbers before/after:
Host: AMD Opteron(tm) Processor 6376
ubuntu 17.04 ppc64 bootup+shutdown time
700 +-+--+----+------+------------+-----------+------------*--+-+
| + + + + + *B |
| before ***B*** ** * |
|tb lock removal ###D### *** |
600 +-+ *** +-+
| ** # |
| *B* #D |
| *** * ## |
500 +-+ *** ### +-+
| * *** ### |
| *B* # ## |
| ** * #D# |
400 +-+ ** ## +-+
| ** ### |
| ** ## |
| ** # ## |
300 +-+ * B* #D# +-+
| B *** ### |
| * ** #### |
| * *** ### |
200 +-+ B *B #D# +-+
| #B* * ## # |
| #* ## |
| + D##D# + + + + |
100 +-+--+----+------+------------+-----------+------------+--+-+
1 8 16 Guest CPUs 48 64
png: https://imgur.com/HwmBHXe
debian jessie aarch64 bootup+shutdown time
90 +-+--+-----+-----+------------+------------+------------+--+-+
| + + + + + + |
| before ***B*** B |
80 +tb lock removal ###D### **D +-+
| **### |
| **## |
70 +-+ ** # +-+
| ** ## |
| ** # |
60 +-+ *B ## +-+
| ** ## |
| *** #D |
50 +-+ *** ## +-+
| * ** ### |
| **B* ### |
40 +-+ **** # ## +-+
| **** #D# |
| ***B** ### |
30 +-+ B***B** #### +-+
| B * * # ### |
| B ###D# |
20 +-+ D ##D## +-+
| D# |
| + + + + + + |
10 +-+--+-----+-----+------------+------------+------------+--+-+
1 8 16 Guest CPUs 48 64
png: https://imgur.com/iGpGFtv
The gains are high for 4-8 CPUs. Beyond that point, however, unrelated
lock contention significantly hurts scalability.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Thereby making it per-TCGContext. Once we remove tb_lock, this will
avoid an atomic increment every time a TB is invalidated.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This paves the way for enabling scalable parallel generation of TCG code.
Instead of tracking TBs with a single binary search tree (BST), use a
BST for each TCG region, protecting it with a lock. This is as scalable
as it gets, since each TCG thread operates on a separate region.
The core of this change is the introduction of struct tcg_region_tree,
which contains a pointer to a GTree and an associated lock to serialize
accesses to it. We then allocate an array of tcg_region_tree's, adding
the appropriate padding to avoid false sharing based on
qemu_dcache_linesize.
Given a tc_ptr, we first find the corresponding region_tree. This
is done by special-casing the first and last regions first, since they
might be of size != region.size; otherwise we just divide the offset
by region.stride. I was worried about this division (several dozen
cycles of latency), but profiling shows that this is not a fast path.
Note that region.stride is not required to be a power of two; it
is only required to be a multiple of the host's page size.
Note that with this design we can also provide consistent snapshots
about all region trees at once; for instance, tcg_tb_foreach
acquires/releases all region_tree locks before/after iterating over them.
For this reason we now drop tb_lock in dump_exec_info().
As an alternative I considered implementing a concurrent BST, but this
can be tricky to get right, offers no consistent snapshots of the BST,
and performance and scalability-wise I don't think it could ever beat
having separate GTrees, given that our workload is insert-mostly (all
concurrent BST designs I've seen focus, understandably, on making
lookups fast, which comes at the expense of convoluted, non-wait-free
insertions/removals).
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Do the cast to uintptr_t within the helper, so that the compiler
can type check the pointer argument. We can also do some more
sanity checking of the index argument.
Reviewed-by: Laurent Vivier <laurent@vivier.eu>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
* hw/arm/iotkit.c: fix minor memory leak
* softfloat: fix wrong-exception-flags bug for multiply-add corner case
* arm: isolate and clean up DTB generation
* implement Arm v8.1-Atomics extension
* Fix some bugs and missing instructions in the v8.2-FP16 extension
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=uXY+
-----END PGP SIGNATURE-----
Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20180510' into staging
target-arm queue:
* hw/arm/iotkit.c: fix minor memory leak
* softfloat: fix wrong-exception-flags bug for multiply-add corner case
* arm: isolate and clean up DTB generation
* implement Arm v8.1-Atomics extension
* Fix some bugs and missing instructions in the v8.2-FP16 extension
# gpg: Signature made Thu 10 May 2018 18:44:34 BST
# gpg: using RSA key 3C2525ED14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg: aka "Peter Maydell <pmaydell@gmail.com>"
# gpg: aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83 15CF 3C25 25ED 1436 0CDE
* remotes/pmaydell/tags/pull-target-arm-20180510: (21 commits)
target/arm: Clear SVE high bits for FMOV
target/arm: Fix float16 to/from int16
target/arm: Implement vector shifted FCVT for fp16
target/arm: Implement vector shifted SCVF/UCVF for fp16
target/arm: Enable ARM_FEATURE_V8_ATOMICS for user-only
target/arm: Implement CAS and CASP
target/arm: Fill in disas_ldst_atomic
target/arm: Introduce ARM_FEATURE_V8_ATOMICS and initial decode
target/riscv: Use new atomic min/max expanders
tcg: Use GEN_ATOMIC_HELPER_FN for opposite endian atomic add
tcg: Introduce atomic helpers for integer min/max
target/xtensa: Use new min/max expanders
target/arm: Use new min/max expanders
tcg: Introduce helpers for integer min/max
atomic.h: Work around gcc spurious "unused value" warning
make sure that we aren't overwriting mc->get_hotplug_handler by accident
arm/boot: split load_dtb() from arm_load_kernel()
platform-bus-device: use device plug callback instead of machine_done notifier
pc: simplify MachineClass::get_hotplug_handler handling
softfloat: Handle default NaN mode after pickNaNMulAdd, not before
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
# Conflicts:
# target/riscv/translate.c
Given that this atomic operation will be used by both risc-v
and aarch64, let's not duplicate code across the two targets.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20180508151437.4232-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
In 6001f7729e we partially attempt to address the branch
displacement overflow caused by 15fa08f845.
However, gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vqtbX.c
is a testcase that contains a TB so large as to overflow anyway.
The limit here of 8000 ops produces a maximum output TB size of
24112 bytes on a ppc64le host with that test case. This is still
much less than the maximum forward branch distance of 32764 bytes.
Cc: qemu-stable@nongnu.org
Fixes: 15fa08f845 ("tcg: Dynamically allocate TCGOps")
Reviewed-by: Laurent Vivier <laurent@vivier.eu>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
ppc64 uses a BC instruction to call the tcg_out_qemu_ld/st
slow path. BC instruction uses a relative address encoded
on 14 bits.
The slow path functions are added at the end of the generated
instructions buffer, in the reverse order of the callers.
So more we have slow path functions more the distance between
the caller (BC) and the function increases.
This patch changes the behavior to generate the functions in
the same order of the callers.
Cc: qemu-stable@nongnu.org
Fixes: 15fa08f845 ("tcg: Dynamically allocate TCGOps")
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Message-Id: <20180429235840.16659-1-lvivier@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Drop TCGV_PTR_TO_NAT and TCGV_NAT_TO_PTR internal macros.
Add tcg_temp_local_new_ptr, tcg_gen_brcondi_ptr, tcg_gen_ext_i32_ptr,
tcg_gen_trunc_i64_ptr, tcg_gen_extu_ptr_i64, tcg_gen_trunc_ptr_i32.
Use inlines instead of macros where possible.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
The parameters for tcg_gen_insn_start are target_ulong, which may be split
into two TCGArg parameters for storage in the opcode on 32-bit hosts.
Fixes the ARM target and its direct use of tcg_set_insn_param, which would
set the wrong argument in the 64-on-32 case.
Cc: qemu-stable@nongnu.org
Reported-by: alarson@ddci.com
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20180410003558.2470-1-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Opcodes are added for scalar and vector shifts, but considering the
varied semantics of these do not expose them to the front ends. Do
go ahead and provide them in case they are needed for backend expansion.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
We already handle this in the backends, and the lifetime datum
for the TCGOp is already large enough.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
We had two fields specific to INDEX_op_call. Rename these and
add some macros so that the fields may be reused for other opcodes.
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
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.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
These are now trivial sets and tests against NULL. Unwrap.
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
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.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This enables parallel TCG code generation. However, we do not take
advantage of it yet since tb_lock is still held during tb_gen_code.
In user-mode we use a single TCG context; see the documentation
added to tcg_region_init for the rationale.
Note that targets do not need any conversion: targets initialize a
TCGContext (e.g. defining TCG globals), and after this initialization
has finished, the context is cloned by the vCPU threads, each of
them keeping a separate copy.
TCG threads claim one entry in tcg_ctxs[] by atomically increasing
n_tcg_ctxs. Do not be too annoyed by the subsequent atomic_read's
of that variable and tcg_ctxs; they are there just to play nice with
analysis tools such as thread sanitizer.
Note that we do not allocate an array of contexts (we allocate
an array of pointers instead) because when tcg_context_init
is called, we do not know yet how many contexts we'll use since
the bool behind qemu_tcg_mttcg_enabled() isn't set yet.
Previous patches folded some TCG globals into TCGContext. The non-const
globals remaining are only set at init time, i.e. before the TCG
threads are spawned. Here is a list of these set-at-init-time globals
under tcg/:
Only written by tcg_context_init:
- indirect_reg_alloc_order
- tcg_op_defs
Only written by tcg_target_init (called from tcg_context_init):
- tcg_target_available_regs
- tcg_target_call_clobber_regs
- arm: arm_arch, use_idiv_instructions
- i386: have_cmov, have_bmi1, have_bmi2, have_lzcnt,
have_movbe, have_popcnt
- mips: use_movnz_instructions, use_mips32_instructions,
use_mips32r2_instructions, got_sigill (tcg_target_detect_isa)
- ppc: have_isa_2_06, have_isa_3_00, tb_ret_addr
- s390: tb_ret_addr, s390_facilities
- sparc: qemu_ld_trampoline, qemu_st_trampoline (build_trampolines),
use_vis3_instructions
Only written by tcg_prologue_init:
- 'struct jit_code_entry one_entry'
- aarch64: tb_ret_addr
- arm: tb_ret_addr
- i386: tb_ret_addr, guest_base_flags
- ia64: tb_ret_addr
- mips: tb_ret_addr, bswap32_addr, bswap32u_addr, bswap64_addr
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This is groundwork for supporting multiple TCG contexts.
The naive solution here is to split code_gen_buffer statically
among the TCG threads; this however results in poor utilization
if translation needs are different across TCG threads.
What we do here is to add an extra layer of indirection, assigning
regions that act just like pages do in virtual memory allocation.
(BTW if you are wondering about the chosen naming, I did not want
to use blocks or pages because those are already heavily used in QEMU).
We use a global lock to serialize allocations as well as statistics
reporting (we now export the size of the used code_gen_buffer with
tcg_code_size()). Note that for the allocator we could just use
a counter and atomic_inc; however, that would complicate the gathering
of tcg_code_size()-like stats. So given that the region operations are
not a fast path, a lock seems the most reasonable choice.
The effectiveness of this approach is clear after seeing some numbers.
I used the bootup+shutdown of debian-arm with '-tb-size 80' as a benchmark.
Note that I'm evaluating this after enabling per-thread TCG (which
is done by a subsequent commit).
* -smp 1, 1 region (entire buffer):
qemu: flush code_size=83885014 nb_tbs=154739 avg_tb_size=357
qemu: flush code_size=83884902 nb_tbs=153136 avg_tb_size=363
qemu: flush code_size=83885014 nb_tbs=152777 avg_tb_size=364
qemu: flush code_size=83884950 nb_tbs=150057 avg_tb_size=373
qemu: flush code_size=83884998 nb_tbs=150234 avg_tb_size=373
qemu: flush code_size=83885014 nb_tbs=154009 avg_tb_size=360
qemu: flush code_size=83885014 nb_tbs=151007 avg_tb_size=370
qemu: flush code_size=83885014 nb_tbs=151816 avg_tb_size=367
That is, 8 flushes.
* -smp 8, 32 regions (80/32 MB per region) [i.e. this patch]:
qemu: flush code_size=76328008 nb_tbs=141040 avg_tb_size=356
qemu: flush code_size=75366534 nb_tbs=138000 avg_tb_size=361
qemu: flush code_size=76864546 nb_tbs=140653 avg_tb_size=361
qemu: flush code_size=76309084 nb_tbs=135945 avg_tb_size=375
qemu: flush code_size=74581856 nb_tbs=132909 avg_tb_size=375
qemu: flush code_size=73927256 nb_tbs=135616 avg_tb_size=360
qemu: flush code_size=78629426 nb_tbs=142896 avg_tb_size=365
qemu: flush code_size=76667052 nb_tbs=138508 avg_tb_size=368
Again, 8 flushes. Note how buffer utilization is not 100%, but it
is close. Smaller region sizes would yield higher utilization,
but we want region allocation to be rare (it acquires a lock), so
we do not want to go too small.
* -smp 8, static partitioning of 8 regions (10 MB per region):
qemu: flush code_size=21936504 nb_tbs=40570 avg_tb_size=354
qemu: flush code_size=11472174 nb_tbs=20633 avg_tb_size=370
qemu: flush code_size=11603976 nb_tbs=21059 avg_tb_size=365
qemu: flush code_size=23254872 nb_tbs=41243 avg_tb_size=377
qemu: flush code_size=28289496 nb_tbs=52057 avg_tb_size=358
qemu: flush code_size=43605160 nb_tbs=78896 avg_tb_size=367
qemu: flush code_size=45166552 nb_tbs=82158 avg_tb_size=364
qemu: flush code_size=63289640 nb_tbs=116494 avg_tb_size=358
qemu: flush code_size=51389960 nb_tbs=93937 avg_tb_size=362
qemu: flush code_size=59665928 nb_tbs=107063 avg_tb_size=372
qemu: flush code_size=38380824 nb_tbs=68597 avg_tb_size=374
qemu: flush code_size=44884568 nb_tbs=79901 avg_tb_size=376
qemu: flush code_size=50782632 nb_tbs=90681 avg_tb_size=374
qemu: flush code_size=39848888 nb_tbs=71433 avg_tb_size=372
qemu: flush code_size=64708840 nb_tbs=119052 avg_tb_size=359
qemu: flush code_size=49830008 nb_tbs=90992 avg_tb_size=362
qemu: flush code_size=68372408 nb_tbs=123442 avg_tb_size=368
qemu: flush code_size=33555560 nb_tbs=59514 avg_tb_size=378
qemu: flush code_size=44748344 nb_tbs=80974 avg_tb_size=367
qemu: flush code_size=37104248 nb_tbs=67609 avg_tb_size=364
That is, 20 flushes. Note how a static partitioning approach uses
the code buffer poorly, leading to many unnecessary flushes.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
