s390/kvm: avoid automatic sie reentry

Do not automatically restart the sie instruction in entry64.S after an
interrupt, return to the caller with a reason code instead. That allows
to deal with RCU and other conditions in C code.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>

diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index c7daeef..51d99ac 100644 (file)
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -47,7 +47,6 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
                 _TIF_MCCK_PENDING)
 _TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
                 _TIF_SYSCALL_TRACEPOINT)
-_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
 
 #define BASED(name) name-system_call(%r13)
 
@@ -81,25 +80,27 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
 #endif
        .endm
 
-       .macro  HANDLE_SIE_INTERCEPT scratch,pgmcheck
+       .macro  HANDLE_SIE_INTERCEPT scratch,reason
 #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
        tmhh    %r8,0x0001              # interrupting from user ?
-       jnz     .+52
+       jnz     .+62
        lgr     \scratch,%r9
-       slg     \scratch,BASED(.Lsie_loop)
-       clg     \scratch,BASED(.Lsie_length)
-       .if     \pgmcheck
+       slg     \scratch,BASED(.Lsie_critical)
+       clg     \scratch,BASED(.Lsie_critical_length)
+       .if     \reason==1
        # Some program interrupts are suppressing (e.g. protection).
        # We must also check the instruction after SIE in that case.
        # do_protection_exception will rewind to rewind_pad
-       jh      .+32
+       jh      .+42
        .else
-       jhe     .+32
+       jhe     .+42
        .endif
-       lg      %r9,BASED(.Lsie_loop)
-       LPP     BASED(.Lhost_id)        # set host id
-       lg      %r14,__SF_EMPTY(%r15)   # get control block pointer
+       lg      %r14,__SF_EMPTY(%r15)           # get control block pointer
+       LPP     __SF_EMPTY+16(%r15)             # set host id
        ni      __SIE_PROG0C+3(%r14),0xfe       # no longer in SIE
+       lctlg   %c1,%c1,__LC_USER_ASCE          # load primary asce
+       larl    %r9,sie_exit                    # skip forward to sie_exit
+       mvi     __SF_EMPTY+31(%r15),\reason     # set exit reason
 #endif
        .endm
 
@@ -452,7 +453,7 @@ ENTRY(io_int_handler)
        lg      %r12,__LC_THREAD_INFO
        larl    %r13,system_call
        lmg     %r8,%r9,__LC_IO_OLD_PSW
-       HANDLE_SIE_INTERCEPT %r14,0
+       HANDLE_SIE_INTERCEPT %r14,2
        SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
        tmhh    %r8,0x0001              # interrupting from user?
        jz      io_skip
@@ -597,7 +598,7 @@ ENTRY(ext_int_handler)
        lg      %r12,__LC_THREAD_INFO
        larl    %r13,system_call
        lmg     %r8,%r9,__LC_EXT_OLD_PSW
-       HANDLE_SIE_INTERCEPT %r14,0
+       HANDLE_SIE_INTERCEPT %r14,3
        SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
        tmhh    %r8,0x0001              # interrupting from user ?
        jz      ext_skip
@@ -645,7 +646,7 @@ ENTRY(mcck_int_handler)
        lg      %r12,__LC_THREAD_INFO
        larl    %r13,system_call
        lmg     %r8,%r9,__LC_MCK_OLD_PSW
-       HANDLE_SIE_INTERCEPT %r14,0
+       HANDLE_SIE_INTERCEPT %r14,4
        tm      __LC_MCCK_CODE,0x80     # system damage?
        jo      mcck_panic              # yes -> rest of mcck code invalid
        lghi    %r14,__LC_CPU_TIMER_SAVE_AREA
@@ -939,19 +940,8 @@ ENTRY(sie64a)
        stmg    %r6,%r14,__SF_GPRS(%r15)        # save kernel registers
        stg     %r2,__SF_EMPTY(%r15)            # save control block pointer
        stg     %r3,__SF_EMPTY+8(%r15)          # save guest register save area
-       xc      __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # host id == 0
+       xc      __SF_EMPTY+16(16,%r15),__SF_EMPTY+16(%r15) # host id & reason
        lmg     %r0,%r13,0(%r3)                 # load guest gprs 0-13
-# some program checks are suppressing. C code (e.g. do_protection_exception)
-# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
-# instructions in the sie_loop should not cause program interrupts. So
-# lets use a nop (47 00 00 00) as a landing pad.
-# See also HANDLE_SIE_INTERCEPT
-rewind_pad:
-       nop     0
-sie_loop:
-       lg      %r14,__LC_THREAD_INFO           # pointer thread_info struct
-       tm      __TI_flags+7(%r14),_TIF_EXIT_SIE
-       jnz     sie_exit
        lg      %r14,__LC_GMAP                  # get gmap pointer
        ltgr    %r14,%r14
        jz      sie_gmap
@@ -966,33 +956,33 @@ sie_gmap:
 sie_done:
        LPP     __SF_EMPTY+16(%r15)             # set host id
        ni      __SIE_PROG0C+3(%r14),0xfe       # no longer in SIE
-       lg      %r14,__LC_THREAD_INFO           # pointer thread_info struct
-sie_exit:
        lctlg   %c1,%c1,__LC_USER_ASCE          # load primary asce
+# some program checks are suppressing. C code (e.g. do_protection_exception)
+# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
+# instructions beween sie64a and sie_done should not cause program
+# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
+# See also HANDLE_SIE_INTERCEPT
+rewind_pad:
+       nop     0
+sie_exit:
        lg      %r14,__SF_EMPTY+8(%r15)         # load guest register save area
        stmg    %r0,%r13,0(%r14)                # save guest gprs 0-13
        lmg     %r6,%r14,__SF_GPRS(%r15)        # restore kernel registers
-       lghi    %r2,0
+       lg      %r2,__SF_EMPTY+24(%r15)         # return exit reason code
        br      %r14
 sie_fault:
-       lctlg   %c1,%c1,__LC_USER_ASCE          # load primary asce
-       lg      %r14,__LC_THREAD_INFO           # pointer thread_info struct
-       lg      %r14,__SF_EMPTY+8(%r15)         # load guest register save area
-       stmg    %r0,%r13,0(%r14)                # save guest gprs 0-13
-       lmg     %r6,%r14,__SF_GPRS(%r15)        # restore kernel registers
-       lghi    %r2,-EFAULT
-       br      %r14
+       lghi    %r14,-EFAULT
+       stg     %r14,__SF_EMPTY+24(%r15)        # set exit reason code
+       j       sie_exit
 
        .align  8
-.Lsie_loop:
-       .quad   sie_loop
-.Lsie_length:
-       .quad   sie_done - sie_loop
-.Lhost_id:
-       .quad   0
+.Lsie_critical:
+       .quad   sie_gmap
+.Lsie_critical_length:
+       .quad   sie_done - sie_gmap
 
        EX_TABLE(rewind_pad,sie_fault)
-       EX_TABLE(sie_loop,sie_fault)
+       EX_TABLE(sie_exit,sie_fault)
 #endif
 
                .section .rodata, "a"

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 08227c1..93444c4 100644 (file)
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -707,7 +707,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
        trace_kvm_s390_sie_enter(vcpu,
                                 atomic_read(&vcpu->arch.sie_block->cpuflags));
        rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs);
-       if (rc) {
+       if (rc > 0)
+               rc = 0;
+       if (rc < 0) {
                if (kvm_is_ucontrol(vcpu->kvm)) {
                        rc = SIE_INTERCEPT_UCONTROL;
                } else {