Elisha Hollander <just4now666666@gmail.com> writes:
> weird...
Richard has posted some patches:
Message-ID: <20240910212351.977753-1-richard.henderson@linaro.org" target="_blank" rel="noreferrer">20240910212351.977753-1-richard.henderson@linaro.org>
Date: Tue, 10 Sep 2024 14:23:49 -0700
Subject: [PATCH 0/2] tcg: Fix branch/label link during plugin expansion
From: Richard Henderson <richard.henderson@linaro.org>
which work for me. Can you try them out?
>
> On Tue, Sep 3, 2024, 14:13 Alex Bennée <alex.bennee@linaro.org> wrote:
>
> Alex Bennée <alex.bennee@linaro.org> writes:
>
> > Elisha Hollander <just4now666666@gmail.com> writes:
> >
> >> Sure!
> >>
> >> `build/qemu-system-i386 -plugin build/contrib/plugins/libips.so,ips=1 -display curses -bios bios.raw`
> >>
> >> Also, I just tested with 9.1.0-rc4 and it resulted with
> >> `tcg.c:3167:remove_label_use: code should not be reached`
> >
> > I can replicate but it seems to be an edge case with ips=1, try a higher
> > number, even ips=10 doesn't trigger the crash (but 10 instructions a
> > second is very slow to do anything).
> >
> > ./qemu-system-i386 -plugin contrib/plugins/libips.so,ips=1 -display none -serial mon:stdio
> > **
> > ERROR:../../tcg/tcg.c:3167:remove_label_use: code should not be reached
> > Bail out! ERROR:../../tcg/tcg.c:3167:remove_label_use: code should not be reached
> > fish: Job 1, './qemu-system-i386 -plugin con…' terminated by signal
> > SIGABRT (Abort)
>
> Well this is fascinating and I suspect Richard needs to comment but:
>
> ./qemu-system-i386 -plugin contrib/plugins/libips.so,ips=9 -display none -serial mon:stdio -d in_asm,op,op_opt,out_asm
> -plugin contrib/plugins/libstoptrigger.so,icount=20 -D broken.log
> **
> ERROR:../../tcg/tcg.c:3167:remove_label_use: code should not be reached
> Bail out! ERROR:../../tcg/tcg.c:3167:remove_label_use: code should not be reached
> fish: Job 1, './qemu-system-i386 -plugin con…' terminated by signal SIGABRT (Abort)
>
> and:
>
> ./qemu-system-i386 -plugin contrib/plugins/libips.so,ips=10 -display none -serial mon:stdio -d in_asm,op,op_opt,out_asm
> -plugin contrib/plugins/libstoptrigger.so,icount=20 -D working.log
>
> But for the life of me I can't see the difference between the two sets
> of input, the first crashes before the optimisation step:
>
> PROLOGUE: [size=45]
> 0x7f2198000000: 55 pushq %rbp
> 0x7f2198000001: 53 pushq %rbx
> 0x7f2198000002: 41 54 pushq %r12
> 0x7f2198000004: 41 55 pushq %r13
> 0x7f2198000006: 41 56 pushq %r14
> 0x7f2198000008: 41 57 pushq %r15
> 0x7f219800000a: 48 8b ef movq %rdi, %rbp
> 0x7f219800000d: 48 81 c4 78 fb ff ff addq $-0x488, %rsp
> 0x7f2198000014: ff e6 jmpq *%rsi
> 0x7f2198000016: 33 c0 xorl %eax, %eax
> 0x7f2198000018: 48 81 c4 88 04 00 00 addq $0x488, %rsp
> 0x7f219800001f: c5 f8 77 vzeroupper
> 0x7f2198000022: 41 5f popq %r15
> 0x7f2198000024: 41 5e popq %r14
> 0x7f2198000026: 41 5d popq %r13
> 0x7f2198000028: 41 5c popq %r12
> 0x7f219800002a: 5b popq %rbx
> 0x7f219800002b: 5d popq %rbp
> 0x7f219800002c: c3 retq
>
> ----------------
> IN:
> 0xfffffff0: ea 5b e0 00 f0 ljmpw $0xf000:$0xe05b
>
> OP:
> ld_i32 loc9,env,$0xfffffffffffffff8
> brcond_i32 loc9,$0x0,lt,$L0
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> mul_i32 tmp18,tmp18,$0x18
> ext_i32_i64 tmp17,tmp18
> add_i64 tmp17,tmp17,$0x55912c381e38
> ld_i64 tmp21,tmp17,$0x0
> add_i64 tmp21,tmp21,$0x1
> st_i64 tmp21,tmp17,$0x0
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> mul_i32 tmp18,tmp18,$0x18
> ext_i32_i64 tmp17,tmp18
> add_i64 tmp17,tmp17,$0x55912c381e38
> ld_i64 tmp21,tmp17,$0x0
> brcond_i64 tmp21,$0x0,ltu,$L1
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> call plugin(0x7f21efe82550),$0x1,$0,tmp18,$0x0
> set_label $L1
> st8_i32 $0x1,env,$0xfffffffffffffffc
>
> ---- 0000000000000ff0 0000000000000000
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> shl_i32 tmp18,tmp18,$0x3
> ext_i32_i64 tmp17,tmp18
> add_i64 tmp17,tmp17,$0x55912c3803b0
> ld_i64 tmp21,tmp17,$0x0
> add_i64 tmp21,tmp21,$0x1
> st_i64 tmp21,tmp17,$0x0
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> shl_i32 tmp18,tmp18,$0x3
> ext_i32_i64 tmp17,tmp18
> add_i64 tmp17,tmp17,$0x55912c3803b0
> ld_i64 tmp21,tmp17,$0x0
> brcond_i64 tmp21,$0x15,ne,$L2
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> call plugin(0x7f21efe7d420),$0x1,$0,tmp18,$0xfffffff0
> set_label $L2
> mov_i32 loc0,$0xe05b
> mov_i32 loc1,$0xf000
> ext16u_i32 loc13,loc1
> st_i32 loc13,env,$0x54
> shl_i32 cs_base,loc13,$0x4
> mov_i32 eip,loc0
> call lookup_tb_ptr,$0x6,$1,tmp15,env
> goto_ptr tmp15
> set_label $L0
> exit_tb $0x7f2198000043
>
> BOOM!!!
>
> and the working case:
>
> PROLOGUE: [size=45]
> 0x7f110c000000: 55 pushq %rbp
> 0x7f110c000001: 53 pushq %rbx
> 0x7f110c000002: 41 54 pushq %r12
> 0x7f110c000004: 41 55 pushq %r13
> 0x7f110c000006: 41 56 pushq %r14
> 0x7f110c000008: 41 57 pushq %r15
> 0x7f110c00000a: 48 8b ef movq %rdi, %rbp
> 0x7f110c00000d: 48 81 c4 78 fb ff ff addq $-0x488, %rsp
> 0x7f110c000014: ff e6 jmpq *%rsi
> 0x7f110c000016: 33 c0 xorl %eax, %eax
> 0x7f110c000018: 48 81 c4 88 04 00 00 addq $0x488, %rsp
> 0x7f110c00001f: c5 f8 77 vzeroupper
> 0x7f110c000022: 41 5f popq %r15
> 0x7f110c000024: 41 5e popq %r14
> 0x7f110c000026: 41 5d popq %r13
> 0x7f110c000028: 41 5c popq %r12
> 0x7f110c00002a: 5b popq %rbx
> 0x7f110c00002b: 5d popq %rbp
> 0x7f110c00002c: c3 retq
>
> ----------------
> IN:
> 0xfffffff0: ea 5b e0 00 f0 ljmpw $0xf000:$0xe05b
>
> OP:
> ld_i32 loc9,env,$0xfffffffffffffff8
> brcond_i32 loc9,$0x0,lt,$L0
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> mul_i32 tmp18,tmp18,$0x18
> ext_i32_i64 tmp17,tmp18
> add_i64 tmp17,tmp17,$0x55c2cb346e38
> ld_i64 tmp21,tmp17,$0x0
> add_i64 tmp21,tmp21,$0x1
> st_i64 tmp21,tmp17,$0x0
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> mul_i32 tmp18,tmp18,$0x18
> ext_i32_i64 tmp17,tmp18
> add_i64 tmp17,tmp17,$0x55c2cb346e38
> ld_i64 tmp21,tmp17,$0x0
> brcond_i64 tmp21,$0x1,ltu,$L1
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> call plugin(0x7f11633ab550),$0x1,$0,tmp18,$0x0
> set_label $L1
> st8_i32 $0x1,env,$0xfffffffffffffffc
>
> ---- 0000000000000ff0 0000000000000000
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> shl_i32 tmp18,tmp18,$0x3
> ext_i32_i64 tmp17,tmp18
> add_i64 tmp17,tmp17,$0x55c2cb3453b0
> ld_i64 tmp21,tmp17,$0x0
> add_i64 tmp21,tmp21,$0x1
> st_i64 tmp21,tmp17,$0x0
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> shl_i32 tmp18,tmp18,$0x3
> ext_i32_i64 tmp17,tmp18
> add_i64 tmp17,tmp17,$0x55c2cb3453b0
> ld_i64 tmp21,tmp17,$0x0
> brcond_i64 tmp21,$0x15,ne,$L2
> ld_i32 tmp18,env,$0xffffffffffffdaf8
> call plugin(0x7f11633a6420),$0x1,$0,tmp18,$0xfffffff0
> set_label $L2
> mov_i32 loc0,$0xe05b
> mov_i32 loc1,$0xf000
> ext16u_i32 loc13,loc1
> st_i32 loc13,env,$0x54
> shl_i32 cs_base,loc13,$0x4
> mov_i32 eip,loc0
> call lookup_tb_ptr,$0x6,$1,tmp15,env
> goto_ptr tmp15
> set_label $L0
> exit_tb $0x7f110c000043
>
> OP after optimization and liveness analysis:
> ld_i32 tmp9,env,$0xfffffffffffffff8 pref=0xffff
> brcond_i32 tmp9,$0x0,lt,$L0 dead: 0 1
> ld_i32 tmp18,env,$0xffffffffffffdaf8 pref=0xffff
> mul_i32 tmp18,tmp18,$0x18 dead: 1 pref=0xffff
> ext_i32_i64 tmp17,tmp18 dead: 1 pref=0xffff
> add_i64 tmp17,tmp17,$0x55c2cb346e38 dead: 1 pref=0xffff
> ld_i64 tmp21,tmp17,$0x0 pref=0xffff
> add_i64 tmp21,tmp21,$0x1 dead: 1 pref=0xffff
> st_i64 tmp21,tmp17,$0x0 dead: 0 1
> ld_i32 tmp18,env,$0xffffffffffffdaf8 pref=0xffff
> mul_i32 tmp18,tmp18,$0x18 dead: 1 2 pref=0xffff
> ext_i32_i64 tmp17,tmp18 dead: 1 pref=0xffff
> add_i64 tmp17,tmp17,$0x55c2cb346e38 dead: 1 2 pref=0xffff
> ld_i64 tmp21,tmp17,$0x0 dead: 1 pref=0xffff
> brcond_i64 tmp21,$0x1,ltu,$L1 dead: 0 1
> ld_i32 tmp18,env,$0xffffffffffffdaf8 dead: 1 pref=0x80
> call plugin(0x7f11633ab550),$0x1,$0,tmp18,$0x0 dead: 0 1
> set_label $L1
> st8_i32 $0x1,env,$0xfffffffffffffffc dead: 0
>
> ---- 0000000000000ff0 0000000000000000
> ld_i32 tmp18,env,$0xffffffffffffdaf8 pref=0xffff
> shl_i32 tmp18,tmp18,$0x3 dead: 1 pref=0xffff
> ext_i32_i64 tmp17,tmp18 dead: 1 pref=0xffff
> add_i64 tmp17,tmp17,$0x55c2cb3453b0 dead: 1 pref=0xffff
> ld_i64 tmp21,tmp17,$0x0 pref=0xffff
> add_i64 tmp21,tmp21,$0x1 dead: 1 2 pref=0xffff
> st_i64 tmp21,tmp17,$0x0 dead: 0 1
> ld_i32 tmp18,env,$0xffffffffffffdaf8 pref=0xffff
> shl_i32 tmp18,tmp18,$0x3 dead: 1 2 pref=0xffff
> ext_i32_i64 tmp17,tmp18 dead: 1 pref=0xffff
> add_i64 tmp17,tmp17,$0x55c2cb3453b0 dead: 1 2 pref=0xffff
> ld_i64 tmp21,tmp17,$0x0 dead: 1 pref=0xffff
> brcond_i64 tmp21,$0x15,ne,$L2 dead: 0 1
> ld_i32 tmp18,env,$0xffffffffffffdaf8 dead: 1 pref=0x80
> call plugin(0x7f11633a6420),$0x1,$0,tmp18,$0xfffffff0 dead: 0 1
> set_label $L2
> st_i32 $0xf000,env,$0x54 dead: 0
> mov_i32 cs_base,$0xf0000 sync: 0 dead: 0 1 pref=0xffff
> mov_i32 eip,$0xe05b sync: 0 dead: 0 1 pref=0xffff
> call lookup_tb_ptr,$0x6,$1,tmp15,env dead: 1 pref=none
> goto_ptr tmp15 dead: 0
> set_label $L0
> exit_tb $0x7f110c000043
>
> OUT: [size=224]
> -- guest addr 0x0000000000000ff0 + tb prologue
> 0x7f110c000100: 8b 5d f8 movl -8(%rbp), %ebx
> 0x7f110c000103: 85 db testl %ebx, %ebx
> 0x7f110c000105: 0f 8c bd 00 00 00 jl 0x7f110c0001c8
> 0x7f110c00010b: 8b 9d f8 da ff ff movl -0x2508(%rbp), %ebx
> 0x7f110c000111: 6b db 18 imull $0x18, %ebx, %ebx
> 0x7f110c000114: 48 63 db movslq %ebx, %rbx
> 0x7f110c000117: 49 bc 38 6e 34 cb c2 55 movabsq $0x55c2cb346e38, %r12
> 0x7f110c00011f: 00 00
> 0x7f110c000121: 49 03 dc addq %r12, %rbx
> 0x7f110c000124: 4c 8b 2b movq (%rbx), %r13
> 0x7f110c000127: 49 ff c5 incq %r13
> 0x7f110c00012a: 4c 89 2b movq %r13, (%rbx)
> 0x7f110c00012d: 8b 9d f8 da ff ff movl -0x2508(%rbp), %ebx
> 0x7f110c000133: 6b db 18 imull $0x18, %ebx, %ebx
> 0x7f110c000136: 48 63 db movslq %ebx, %rbx
> 0x7f110c000139: 49 03 dc addq %r12, %rbx
> 0x7f110c00013c: 48 8b 1b movq (%rbx), %rbx
> 0x7f110c00013f: 48 83 fb 01 cmpq $1, %rbx
> 0x7f110c000143: 0f 82 0d 00 00 00 jb 0x7f110c000156
> 0x7f110c000149: 8b bd f8 da ff ff movl -0x2508(%rbp), %edi
> 0x7f110c00014f: 33 f6 xorl %esi, %esi
> 0x7f110c000151: e8 fa b3 3a 57 callq 0x7f11633ab550
> 0x7f110c000156: c6 45 fc 01 movb $1, -4(%rbp)
> 0x7f110c00015a: 8b 9d f8 da ff ff movl -0x2508(%rbp), %ebx
> 0x7f110c000160: c1 e3 03 shll $3, %ebx
> 0x7f110c000163: 48 63 db movslq %ebx, %rbx
> 0x7f110c000166: 49 bc b0 53 34 cb c2 55 movabsq $0x55c2cb3453b0, %r12
> 0x7f110c00016e: 00 00
> 0x7f110c000170: 49 03 dc addq %r12, %rbx
> 0x7f110c000173: 4c 8b 2b movq (%rbx), %r13
> 0x7f110c000176: 49 ff c5 incq %r13
> 0x7f110c000179: 4c 89 2b movq %r13, (%rbx)
> 0x7f110c00017c: 8b 9d f8 da ff ff movl -0x2508(%rbp), %ebx
> 0x7f110c000182: c1 e3 03 shll $3, %ebx
> 0x7f110c000185: 48 63 db movslq %ebx, %rbx
> 0x7f110c000188: 49 03 dc addq %r12, %rbx
> 0x7f110c00018b: 48 8b 1b movq (%rbx), %rbx
> 0x7f110c00018e: 48 83 fb 15 cmpq $0x15, %rbx
> 0x7f110c000192: 0f 85 10 00 00 00 jne 0x7f110c0001a8
> 0x7f110c000198: 8b bd f8 da ff ff movl -0x2508(%rbp), %edi
> 0x7f110c00019e: be f0 ff ff ff movl $0xfffffff0, %esi
> 0x7f110c0001a3: e8 78 62 3a 57 callq 0x7f11633a6420
> 0x7f110c0001a8: c7 45 54 00 f0 00 00 movl $0xf000, 0x54(%rbp)
> 0x7f110c0001af: c7 45 58 00 00 0f 00 movl $0xf0000, 0x58(%rbp)
> 0x7f110c0001b6: c7 45 20 5b e0 00 00 movl $0xe05b, 0x20(%rbp)
> 0x7f110c0001bd: 48 8b fd movq %rbp, %rdi
> 0x7f110c0001c0: ff 15 12 00 00 00 callq *0x12(%rip)
> 0x7f110c0001c6: ff e0 jmpq *%rax
> 0x7f110c0001c8: 48 8d 05 74 fe ff ff leaq -0x18c(%rip), %rax
> 0x7f110c0001cf: e9 44 fe ff ff jmp 0x7f110c000018
> -- tb slow paths + alignment
> 0x7f110c0001d4: 90 nop
> 0x7f110c0001d5: 90 nop
> 0x7f110c0001d6: 90 nop
> 0x7f110c0001d7: 90 nop
> data: [size=8]
> 0x7f110c0001d8: .quad 0x000055c2ba75abc0
>
> before continuing to execute.
>
> >
> >
> >>
> >> On Mon, Sep 2, 2024, 16:08 Alex Bennée <alex.bennee@linaro.org> wrote:
> >>
> >> Elisha Hollander <just4now666666@gmail.com> writes:
> >>
> >> > But for qemu_plugin_update_ns
> >> >
> >> > On Mon, Sep 2, 2024, 15:38 Elisha Hollander <just4now666666@gmail.com> wrote:
> >> >
> >> > Just checked with 9.0.2 it it still gives the error...
> >> >
> >> > On Wed, Aug 28, 2024, 14:05 Alex Bennée <alex.bennee@linaro.org> wrote:
> >> >
> >> > Elisha Hollander <just4now666666@gmail.com> writes:
> >> >
> >> > > Although it gives `undefined symbol: qemu_plugin_scoreboard_free`. But
> >> > > probably I messed something up...
> >> >
> >> > Are you using an older QEMU? We should trigger an API warning if they
> >> > are mismatched but maybe thats not working.
> >> >
> >> > >
> >> > > On Tue, Aug 27, 2024, 14:59 Elisha Hollander <just4now666666@gmail.com> wrote:
> >> > >
> >> > > Oh nice, I didn't know that
> >> > >
> >> > > On Tue, Aug 27, 2024, 12:39 Alex Bennée <alex.bennee@linaro.org> wrote:
> >> > >
> >> > > Elisha Hollander <just4now666666@gmail.com> writes:
> >> > >
> >> > > > Signed-off-by: Elisha Hollander <just4now666666@gmail.com>
> >> > >
> >> > > What is the use-case for this patch?
> >> > >
> >> > > If you are simply looking to slow the emulated system down please have a
> >> > > look at:
> >> > >
> >> > > https://qemu.readthedocs.io/en/master/about/emulation.html#limit-instructions-per-second
> >> > >
> >> > > which uses the plugin system to limit the run rate and sleep if its
> >> > > running too fast. The longer term goal is to deprecate the icount clock
> >> > > alignment feature from the core code and leave icount to just provide
> >> > > the deterministic execution needed for record/replay and reverse
> >> > > debugging.
> >> > >
> >> > > > ---
> >> > > > accel/tcg/cpu-exec.c | 4 +---
> >> > > > accel/tcg/icount-common.c | 4 ++--
> >> > > > 2 files changed, 3 insertions(+), 5 deletions(-)
> >> > > >
> >> > > > diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c
> >> > > > index 8163295f34..4c2baf8ed4 100644
> >> > > > --- a/accel/tcg/cpu-exec.c
> >> > > > +++ b/accel/tcg/cpu-exec.c
> >> > > > @@ -95,11 +95,10 @@ static void align_clocks(SyncClocks *sc, CPUState *cpu)
> >> > > > static void print_delay(const SyncClocks *sc)
> >> > > > {
> >> > > > static float threshold_delay;
> >> > > > - static int64_t last_realtime_clock;
> >> > > > static int nb_prints;
> >> > > >
> >> > > > if (icount_align_option &&
> >> > > > - sc->realtime_clock - last_realtime_clock >= MAX_DELAY_PRINT_RATE &&
> >> > > > + sc->diff_clk >= MAX_DELAY_PRINT_RATE &&
> >> > > > nb_prints < MAX_NB_PRINTS) {
> >> > > > if ((-sc->diff_clk / (float)1000000000LL > threshold_delay) ||
> >> > > > (-sc->diff_clk / (float)1000000000LL <
> >> > > > @@ -109,7 +108,6 @@ static void print_delay(const SyncClocks *sc)
> >> > > > threshold_delay - 1,
> >> > > > threshold_delay);
> >> > > > nb_prints++;
> >> > > > - last_realtime_clock = sc->realtime_clock;
> >> > > > }
> >> > > > }
> >> > > > }
> >> > > > diff --git a/accel/tcg/icount-common.c b/accel/tcg/icount-common.c
> >> > > > index 8d3d3a7e9d..f07f8baf4d 100644
> >> > > > --- a/accel/tcg/icount-common.c
> >> > > > +++ b/accel/tcg/icount-common.c
> >> > > > @@ -46,8 +46,8 @@
> >> > > > * is TCG-specific, and does not need to be built for other accels.
> >> > > > */
> >> > > > static bool icount_sleep = true;
> >> > > > -/* Arbitrarily pick 1MIPS as the minimum allowable speed. */
> >> > > > -#define MAX_ICOUNT_SHIFT 10
> >> > > > +/* Arbitrarily pick the minimum allowable speed. */
> >> > > > +#define MAX_ICOUNT_SHIFT 30
> >> > > >
> >> > > > /* Do not count executed instructions */
> >> > > > ICountMode use_icount = ICOUNT_DISABLED;
> >> > >
> >> > > --
> >> > > Alex Bennée
> >> > > Virtualisation Tech Lead @ Linaro
> >> >
> >> > --
> >> > Alex Bennée
> >> > Virtualisation Tech Lead @ Linaro
> >>
> >> Can you give me your command line please?
> >>
> >> --
> >> Alex Bennée
> >> Virtualisation Tech Lead @ Linaro
>
> --
> Alex Bennée
> Virtualisation Tech Lead @ Linaro
--
Alex Bennée
Virtualisation Tech Lead @ Linaro