Signed-off-by: Emilio G. Cota <cota@braap.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Prior patch resets can_do_io flag at the TB entry. Therefore there is no
need in resetting this flag at the end of the block.
This patch removes redundant gen_io_end calls.
Signed-off-by: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru>
Message-Id: <156404429499.18669.13404064982854123855.stgit@pasha-Precision-3630-Tower>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@gmail.com>
In my "build everything" tree, changing sysemu/sysemu.h triggers a
recompile of some 5400 out of 6600 objects (not counting tests and
objects that don't depend on qemu/osdep.h).
Almost a third of its inclusions are actually superfluous. Delete
them. Downgrade two more to qapi/qapi-types-run-state.h, and move one
from char/serial.h to char/serial.c.
hw/semihosting/config.c, monitor/monitor.c, qdev-monitor.c, and
stubs/semihost.c define variables declared in sysemu/sysemu.h without
including it. The compiler is cool with that, but include it anyway.
This doesn't reduce actual use much, as it's still included into
widely included headers. The next commit will tackle that.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20190812052359.30071-27-armbru@redhat.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
In preparation for having some more common semihosting code let's
excise the current config magic from vl.c into its own file. We shall
later add more conditionals to the build configurations so we can
avoid building this if we don't need it.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
The Exclusive Instructions provide a general-purpose mechanism for
atomic updates of memory-based synchronization variables that can be
used for exclusion algorithms.
Use cmpxchg-based implementation that is sufficient for the typical use
of exclusive access in atomic operations.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Block prefetch option adds a bunch of non-privileged opcodes that may be
implemented as nops since QEMU doesn't model caches.
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
The Memory Protection Unit Option (MPU) is a combined instruction and
data memory protection unit with more protection flexibility than the
Region Protection Option or the Region Translation Option but without
any translation capability. It does no demand paging and does not
reference a memory-based page table.
Add memory protection unit option, internal state, SRs and opcodes.
Implement MPU entries dumping in dump_mmu.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Add SRs and rsr/wsr/xsr opcodes defined by the parity/ECC xtensa option.
The implementation is trivial since we don't emulate parity/ECC yet.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
SR numbers are not unique: different Xtensa options may reuse SR number
for different purposes. Introduce generic rsr/wsr functions and xsr
template and use them instead of centralized SR access functions. Change
prototypes of specific rsr/wsr functions to match XtensaOpcodeOp and use
them instead of centralized SR access functions. Put xtensa option that
introduces SR into the second opcode description parameter and use it to
test for rsr/wsr/xsr opcode validity. Extract SR and UR names for the
xtensa_cpu_dump_state from libisa. Merge SRs and URs in the dump.
Register names of used SR/UR in init_libisa and use these names for TCG
globals referencing these SR/UR.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
In order to handle TB's that translate to too much code, we
need to place the control of the length of the translation
in the hands of the code gen master loop.
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
CPUClass method dump_statistics() takes an fprintf()-like callback and
a FILE * to pass to it. Most callers pass fprintf() and stderr.
log_cpu_state() passes fprintf() and qemu_log_file.
hmp_info_registers() passes monitor_fprintf() and the current monitor
cast to FILE *. monitor_fprintf() casts it right back, and is
otherwise identical to monitor_printf().
The callback gets passed around a lot, which is tiresome. The
type-punning around monitor_fprintf() is ugly.
Drop the callback, and call qemu_fprintf() instead. Also gets rid of
the type-punning, since qemu_fprintf() takes NULL instead of the
current monitor cast to FILE *.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20190417191805.28198-15-armbru@redhat.com>
break_dependency incorrectly handles the case of dependency on an opcode
that references the same register multiple times. E.g. the following
instruction is translated incorrectly:
{ or a2, a3, a3 ; or a3, a2, a2 }
This happens because resource indices of both dependency graph nodes are
incremented, and a copy for the second instance of the same register in
the ending node is not done.
Only increment resource index of the ending node of the dependency.
Add test.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Load/store opcodes may raise MMU exceptions. Normally exceptions should
be checked in priority order before any actual operations, but since MMU
exceptions are tightly coupled with actual memory access, there's
currently no way to do it.
Approximate this behavior by executing all load, then all store, and
then all other opcodes in the FLIX bundles. Use opcode dependency
mechanism to express ordering. Mark load/store opcodes with
XTENSA_OP_{LOAD,STORE} flags. Newer libisa has classifier functions that
can tell whether opcode is a load or store, but this information is not
available in the existing overlays.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Currently topologic opcode sorting stops at the first detected
dependency loop. Introduce struct opcode_arg_copy that describes
temporary register copy. Scan remaining opcodes searching for
dependencies that can be broken, break them by introducing temporary
register copies and record them in an array. In case of success
create local temporaries and initialize them with current register
values. Share single temporary copy between all register users. Delete
temporaries after translation.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
libisa represents boolean registers b0..b16 as a BR register file and as
BR4 and BR8 register groups. Add these register files and use
OpcodeArg::{in,out} parameters to access boolean registers in
translators.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
libisa represents MAC16 registers m0..m3 as an MR register file. Add
this register file and reference its registers directly from the
translate_mac16. Drop translator parameter that indicates whether opcode
argument is in ar or in mr.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
To support circular register dependencies in FLIX bundles opcode inputs
and outputs must be separate and adjustable. Circular dependencies can
be broken by making temporary copies of opcode inputs and substituting
them into the arguments array instead of the original registers.
E.g. the circular register dependency in the following bundle:
{ mov a2, a3 ; mov a3, a2 }
can be resolved by making copy a2' = a2 and substituting it as input
argument of the second opcode:
{ mov a2, a3 ; mov a3, a2' }
Change opcode translator prototype to accept OpcodeArg array as
argument. For each register argument initialize OpcodeArg::{in,out} with
TCGv_* of the respective register. Don't explicitly use cpu_R in the
opcode translators, use OpcodeArg::{in,out} instead.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Move return address calculation and WINDOW_START adjustment out of the
retw helper to simplify logic a bit and avoid using registers directly.
Pass a0 as a parameter to the helper.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Opcodes that modify WINDOW_BASE SR don't have dependency on opcodes that
use windowed registers. If such opcodes are combined in a single
instruction they may not be correctly ordered. Instead of adding said
dependency use temporary register to store changed WINDOW_BASE value and
do actual register window rotation as a postprocessing step.
Not all opcodes that change WINDOW_BASE need this: retw, rfwo and rfwu
are also jump opcodes, so they are guaranteed to be translated last and
thus will not affect other opcodes in the same instruction.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Some opcodes may need additional actions at every exit from the
translated instruction or may need to amend TB exit slots available to
jumps generated for the instruction. Add gen_postprocess function and
call it from the gen_jump_slot and from the disas_xtensa_insn.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Opcodes in different slots may read and write same resources (registers,
states). In the absence of resource dependency loops it must be possible
to sort opcodes to avoid interference.
Record resources used by each opcode in the bundle. Build opcode
dependency graph and use topological sort to order its nodes. In case of
success translate opcodes in sort order. In case of failure report and
raise invalid opcode exception.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
FLIX adds branch and loop instruction variants with 15- and 18-bit wide
target offset. Implement them as additional names for the ordinary
branch/loop opcodes.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
There are opcodes that differ only in encoding or possible range of
immediate arguments. Allow multiple names for single opcode translation
table entry to reduce code duplication in that case.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Requirement for alphabetical opcode sorting in opcode tables is awkward
and does not allow sharing implementation between multiple opcodes.
Use hash tables to find opcodes by name. Move implementation from the
translate.c to the helper.c to its only user and remove declaration from
the cpu.h
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Merge gen_callwi and gen_callw into their only users, translate_callw
and translate_callxw. Extract jump slot adjustment logic into a separate
function and use it in gen_jumpi and translate_callw.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Use libisa to extract whether opcode uses windowed registers and
construct mask based on that. This only leaves special case for the
'entry' opcode, as it needs to probe a register dynamically.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
INTERRUPT special register may be changed both by the core (by writing
to INTSET and INTCLEAR registers) and by external events (by triggering
and clearing HW IRQs). In MTTCG this state must be protected from
concurrent access, otherwise interrupts may be lost or spurious
interrupts may be detected.
Use atomic operations to change INTSET SR.
Fix wsr.intset so that it soesn't clear any bits.
Fix wsr.intclear so that it doesn't clear bit that corresponds to NMI.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Don't invalidate TB with the end of zero overhead loop when LBEG or LEND
change. Instead encode the distance from the start of the page where the
TB starts to the LEND in the TB cs_base and generate loopback code when
the next PC matches encoded LEND. Distance to a destination within the
same page and up to a maximum instruction length into the next page is
encoded literally, otherwise it's zero. The distance from LEND to LBEG
is also encoded in the cs_base: it's encoded literally when less than
256 or as 0 otherwise. This allows for TB chaining for the loopback
branch at the end of a loop for the most common loop sizes.
With this change the resulting emulation speed is about 10% higher in
softmmu mode on uClibc-ng and LTP tests. Emulation speed in linux
user mode is a few percent lower because there's no direct TB chaining
between different memory pages. Testing with lower limit on direct TB
chaining range shows gradual slowdown to ~15% for the block size of 64
bytes and ~50% for the block size of 32 bytes.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
- mark instructions that affect active IRQ level;
- put call for gen_check_interrupts right after the instruction
translation; when FLIX is enabled it will need to appear before
other exits from the TB as well;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Now that all logic for TB termination is extracted from rsr/wsr their
return value is not used and may be dropped.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
- mark instructions that require TB termination via slot 0;
- put TB termination right after the instruction translation loop, if
termination w/o TB linking wasn't requested;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Currently we only end TB in icount mode, because access to CCOUNT or
write to CCOMPARE are IO operations. Simplify the behaviour a bit and
end TB unconditionally.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Opcode decoding with libisa takes care about range of valid group SRs,
like CCOMPARE, IBREAKA, DBREAKA or DBREAKC. Turn range checks in wsr
implementations into assertions.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
- mark all instructions that exit TB and require dynamic search for the
next TB;
- put TB termination right after the instruction translation loop;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
- mark quos/quou/rems/remu instructions;
- drop parameter 0 from the translate_quou and split translate_remu from
it;
- put test for division by zero exception right after the coprocessor
exception test;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
- add XtensaOpcodeOps::coprocessor with bitmask of coprocessors used by
the instruction;
- replace coprocessor id parameter of gen_check_cpenable with the
bitmask of used coprocessors;
- collect coprocessor IDs used by an instruction in the disassembly
loop;
- put test for coprocessor disabled exception after the alloca test;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
- mark retw and retw.n instructions;
- extract window inderflow test from retw helper;
- put underflow exception check generation right after the overflow
check;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
- add ps.callinc to the TB flags, that allows testing all instructions
for window overflow statically;
- drop gen_window_check* functions; replace them with get_window_check
that accepts bitmask of used registers;
- add XtensaOpcodeOps::test_overflow that returns bitmask of implicitly
used registers; use it for entry and call{,x}{4,8,12};
- drop window overflow test from the entry helper;
- drop parameter 0 from translate_[di]cache and use translate_nop for
d/i cache opcodes that don't need memory accessibility check;
- add bitmask XtensaOpcodeOps::windowed_register_op that marks opcode
arguments that refer to windowed registers;
- translate windowed_register_op mask to a mask of actually used
registers in the disassembly loop;
- add check for window overflow right after the check for debug
exception;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
- mark break and break.n instructions;
- collect debug cause bits from parameter 0 of instructions marked for
debug exception;
- put debug exception check right after syscall check;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
- mark privileged instructions;
- put single privileged instruction check after disassembly loop;
- translate_[di]cache: drop parameter 0, shift parameters one down;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
- TB flags: add XTENSA_TBFLAG_CWOE that corresponds to the architectural
CWOE state;
- entry: move CWOE check from the helper to the test_ill_entry;
- retw: move CWOE check from the helper to the test_ill_retw;
- separate instruction disassembly loop and translation loop; save
disassembly results in local array;
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
s32c1i must load and store value with target endianness, not host.
This results in an infinite loop in atomic cmpxchg sequences when target
endianness doesn't match host endianness.
Fixes: 9fb40342d4 ("target/xtensa: support MTTCG")
Cc: qemu-stable@nongnu.org
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
- FPU2000 defines rfr and wfr opcodes, not rfr.s and wfr.s;
- movcond.s uses incorrect operand in tcg_gen_movcond: in case the
condition is not satisfied it must not change its argument 0.
Fixes: c04e1692e3 ("target/xtensa: extract FPU2000 opcode
translators")
Cc: qemu-stable@nongnu.org
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Emilio G. Cota