| Message ID | 20210202180028.876888-3-imbrenda@linux.ibm.com |
|---|---|
| State | New |
| Headers | show |
| Series | [v2,1/2] s390/kvm: extend kvm_s390_shadow_fault to return entry pointer | expand |
On Tue, 2 Feb 2021 19:00:28 +0100 Claudio Imbrenda <imbrenda@linux.ibm.com> wrote: > Correctly handle the MVPG instruction when issued by a VSIE guest. > > Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested > virtualization") Cc: stable@vger.kernel.org > Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com> > --- > arch/s390/kvm/vsie.c | 94 > +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 89 > insertions(+), 5 deletions(-) > > diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c > index 7db022141db3..2db49749e27b 100644 > --- a/arch/s390/kvm/vsie.c > +++ b/arch/s390/kvm/vsie.c > @@ -416,11 +416,6 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, > struct vsie_page *vsie_page) memcpy((void *)((u64)scb_o + 0xc0), > (void *)((u64)scb_s + 0xc0), 0xf0 - 0xc0); > break; > - case ICPT_PARTEXEC: > - /* MVPG only */ > - memcpy((void *)((u64)scb_o + 0xc0), > - (void *)((u64)scb_s + 0xc0), 0xd0 - 0xc0); > - break; > } > > if (scb_s->ihcpu != 0xffffU) > @@ -982,6 +977,91 @@ static int handle_stfle(struct kvm_vcpu *vcpu, > struct vsie_page *vsie_page) return 0; > } > > +static u64 vsie_get_register(struct kvm_vcpu *vcpu, struct vsie_page > *vsie_page, u8 reg) +{ > + reg &= 0xf; > + switch (reg) { > + case 15: > + return vsie_page->scb_s.gg15; > + case 14: > + return vsie_page->scb_s.gg14; > + default: > + return vcpu->run->s.regs.gprs[reg]; > + } > +} > + > +static int vsie_handle_mvpg(struct kvm_vcpu *vcpu, struct vsie_page > *vsie_page) +{ > + struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; > + unsigned long pei1, pei2, src, dest, mask = PAGE_MASK; > + u64 *pei_block = &vsie_page->scb_o->mcic; > + int edat, rc1, rc2; > + union ctlreg0 cr0; > + > + cr0.val = vcpu->arch.sie_block->gcr[0]; > + edat = cr0.edat && test_kvm_facility(vcpu->kvm, 8); > + if (psw_bits(scb_s->gpsw).eaba == PSW_BITS_AMODE_24BIT) > + mask = 0xfff000; > + else if (psw_bits(scb_s->gpsw).eaba == PSW_BITS_AMODE_31BIT) > + mask = 0x7ffff000; > + > + dest = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 16) > & mask; > + src = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 20) & > mask; + > + rc1 = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, dest, > &pei1); > + rc2 = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, src, > &pei2); > + /* > + * Either everything went well, or something non-critical > went wrong > + * e.g. beause of a race. In either case, simply retry. > + */ > + if (rc1 == -EAGAIN || rc2 == -EAGAIN || (!rc1 && !rc2)) { > + retry_vsie_icpt(vsie_page); > + return -EAGAIN; > + } > + /* Something more serious went wrong, propagate the error */ > + if (rc1 < 0) > + return rc1; > + if (rc2 < 0) > + return rc2; > + > + /* The only possible suppressing exception: just deliver it > */ > + if (rc1 == PGM_TRANSLATION_SPEC || rc2 == > PGM_TRANSLATION_SPEC) { > + clear_vsie_icpt(vsie_page); > + rc1 = kvm_s390_inject_program_int(vcpu, > PGM_TRANSLATION_SPEC); > + WARN_ON_ONCE(rc1); > + return 1; > + } > + > + /* > + * Forward the PEI intercept to the guest if it was a page > fault, or > + * also for segment and region table faults if EDAT applies. > + */ > + if (edat) { > + rc1 = rc1 == PGM_ASCE_TYPE ? rc1 : 0; > + rc2 = rc2 == PGM_ASCE_TYPE ? rc2 : 0; > + } I just noticed, this should actually be: if (edat) { rc1 = rc1 == PGM_ASCE_TYPE ? rc1 : 0; rc2 = rc2 == PGM_ASCE_TYPE ? rc2 : 0; } else { rc1 = rc1 != PGM_PAGE_TRANSLATION ? rc1 : 0; rc2 = rc2 != PGM_PAGE_TRANSLATION ? rc2 : 0; } I'll fix it in the next version > + if ((!rc1 || rc1 == PGM_PAGE_TRANSLATION) && (!rc2 || rc2 == > PGM_PAGE_TRANSLATION)) { > + pei_block[0] = pei1; > + pei_block[1] = pei2; > + return 1; > + } > + > + retry_vsie_icpt(vsie_page); > + > + /* > + * The host has edat, and the guest does not, or it was an > ASCE type > + * exception. The host needs to inject the appropriate DAT > interrupts > + * into the guest. > + */ > + if (rc1) > + return inject_fault(vcpu, rc1, dest, 1); > + if (rc2) > + return inject_fault(vcpu, rc2, src, 0); > + > + /* This should never be reached */ > + return 0; > +} > + > /* > * Run the vsie on a shadow scb and a shadow gmap, without any > further > * sanity checks, handling SIE faults. > @@ -1068,6 +1148,10 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, > struct vsie_page *vsie_page) if ((scb_s->ipa & 0xf000) != 0xf000) > scb_s->ipa += 0x1000; > break; > + case ICPT_PARTEXEC: > + if (scb_s->ipa == 0xb254) > + rc = vsie_handle_mvpg(vcpu, vsie_page); > + break; > } > return rc; > }
On 2/2/21 7:00 PM, Claudio Imbrenda wrote: > Correctly handle the MVPG instruction when issued by a VSIE guest. > > Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested virtualization") > Cc: stable@vger.kernel.org > Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com> So far the patch looks ok to me and way better to understand than v1, good job > --- > arch/s390/kvm/vsie.c | 94 +++++++++++++++++++++++++++++++++++++++++--- > 1 file changed, 89 insertions(+), 5 deletions(-) > > diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c > index 7db022141db3..2db49749e27b 100644 > --- a/arch/s390/kvm/vsie.c > +++ b/arch/s390/kvm/vsie.c > @@ -416,11 +416,6 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) > memcpy((void *)((u64)scb_o + 0xc0), > (void *)((u64)scb_s + 0xc0), 0xf0 - 0xc0); Magic offsets being magic Another item for my todo list. > break; > - case ICPT_PARTEXEC: > - /* MVPG only */ > - memcpy((void *)((u64)scb_o + 0xc0), > - (void *)((u64)scb_s + 0xc0), 0xd0 - 0xc0); > - break; > } > > if (scb_s->ihcpu != 0xffffU) > @@ -982,6 +977,91 @@ static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) > return 0; > } > > +static u64 vsie_get_register(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, u8 reg) > +{ > + reg &= 0xf; > + switch (reg) { > + case 15: > + return vsie_page->scb_s.gg15; > + case 14: > + return vsie_page->scb_s.gg14; > + default: > + return vcpu->run->s.regs.gprs[reg]; > + } > +} > + > +static int vsie_handle_mvpg(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) > +{ > + struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; > + unsigned long pei1, pei2, src, dest, mask = PAGE_MASK; > + u64 *pei_block = &vsie_page->scb_o->mcic; > + int edat, rc1, rc2; Can use a src/dst prefix or suffix please? 1/2 is confusing. > + union ctlreg0 cr0; > + > + cr0.val = vcpu->arch.sie_block->gcr[0]; > + edat = cr0.edat && test_kvm_facility(vcpu->kvm, 8); > + if (psw_bits(scb_s->gpsw).eaba == PSW_BITS_AMODE_24BIT) > + mask = 0xfff000; > + else if (psw_bits(scb_s->gpsw).eaba == PSW_BITS_AMODE_31BIT) > + mask = 0x7ffff000; > + > + dest = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 16) & mask; > + src = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 20) & mask; > + > + rc1 = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, dest, &pei1); > + rc2 = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, src, &pei2); > + /* > + * Either everything went well, or something non-critical went wrong > + * e.g. beause of a race. In either case, simply retry. > + */ > + if (rc1 == -EAGAIN || rc2 == -EAGAIN || (!rc1 && !rc2)) { > + retry_vsie_icpt(vsie_page); > + return -EAGAIN; > + } > + /* Something more serious went wrong, propagate the error */ > + if (rc1 < 0) > + return rc1; > + if (rc2 < 0) > + return rc2; > + > + /* The only possible suppressing exception: just deliver it */ > + if (rc1 == PGM_TRANSLATION_SPEC || rc2 == PGM_TRANSLATION_SPEC) { > + clear_vsie_icpt(vsie_page); > + rc1 = kvm_s390_inject_program_int(vcpu, PGM_TRANSLATION_SPEC); > + WARN_ON_ONCE(rc1); > + return 1; > + } > + > + /* > + * Forward the PEI intercept to the guest if it was a page fault, or > + * also for segment and region table faults if EDAT applies. > + */ > + if (edat) { > + rc1 = rc1 == PGM_ASCE_TYPE ? rc1 : 0; > + rc2 = rc2 == PGM_ASCE_TYPE ? rc2 : 0; > + } > + if ((!rc1 || rc1 == PGM_PAGE_TRANSLATION) && (!rc2 || rc2 == PGM_PAGE_TRANSLATION)) { > + pei_block[0] = pei1; > + pei_block[1] = pei2; > + return 1; > + } > + > + retry_vsie_icpt(vsie_page); > + > + /* > + * The host has edat, and the guest does not, or it was an ASCE type > + * exception. The host needs to inject the appropriate DAT interrupts > + * into the guest. > + */ > + if (rc1) > + return inject_fault(vcpu, rc1, dest, 1); > + if (rc2)> + return inject_fault(vcpu, rc2, src, 0); > + > + /* This should never be reached */ BUG()? > + return 0; > +} > + > /* > * Run the vsie on a shadow scb and a shadow gmap, without any further > * sanity checks, handling SIE faults. > @@ -1068,6 +1148,10 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) > if ((scb_s->ipa & 0xf000) != 0xf000) > scb_s->ipa += 0x1000; > break; > + case ICPT_PARTEXEC: > + if (scb_s->ipa == 0xb254) > + rc = vsie_handle_mvpg(vcpu, vsie_page); > + break; > } > return rc; > } >
On Thu, 4 Feb 2021 18:10:01 +0100 Janosch Frank <frankja@linux.ibm.com> wrote: > On 2/2/21 7:00 PM, Claudio Imbrenda wrote: > > Correctly handle the MVPG instruction when issued by a VSIE guest. > > > > Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested > > virtualization") Cc: stable@vger.kernel.org > > Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com> > > So far the patch looks ok to me and way better to understand than v1, > good job > > > --- > > arch/s390/kvm/vsie.c | 94 > > +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 89 > > insertions(+), 5 deletions(-) > > > > diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c > > index 7db022141db3..2db49749e27b 100644 > > --- a/arch/s390/kvm/vsie.c > > +++ b/arch/s390/kvm/vsie.c > > @@ -416,11 +416,6 @@ static void unshadow_scb(struct kvm_vcpu > > *vcpu, struct vsie_page *vsie_page) memcpy((void *)((u64)scb_o + > > 0xc0), (void *)((u64)scb_s + 0xc0), 0xf0 - 0xc0); > > Magic offsets being magic > Another item for my todo list. > > > break; > > - case ICPT_PARTEXEC: > > - /* MVPG only */ > > - memcpy((void *)((u64)scb_o + 0xc0), > > - (void *)((u64)scb_s + 0xc0), 0xd0 - 0xc0); > > - break; > > } > > > > if (scb_s->ihcpu != 0xffffU) > > @@ -982,6 +977,91 @@ static int handle_stfle(struct kvm_vcpu *vcpu, > > struct vsie_page *vsie_page) return 0; > > } > > > > +static u64 vsie_get_register(struct kvm_vcpu *vcpu, struct > > vsie_page *vsie_page, u8 reg) +{ > > + reg &= 0xf; > > + switch (reg) { > > + case 15: > > + return vsie_page->scb_s.gg15; > > + case 14: > > + return vsie_page->scb_s.gg14; > > + default: > > + return vcpu->run->s.regs.gprs[reg]; > > + } > > +} > > + > > +static int vsie_handle_mvpg(struct kvm_vcpu *vcpu, struct > > vsie_page *vsie_page) +{ > > + struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; > > + unsigned long pei1, pei2, src, dest, mask = PAGE_MASK; > > + u64 *pei_block = &vsie_page->scb_o->mcic; > > + int edat, rc1, rc2; > > Can use a src/dst prefix or suffix please? > 1/2 is confusing. will do > > + union ctlreg0 cr0; > > + > > + cr0.val = vcpu->arch.sie_block->gcr[0]; > > + edat = cr0.edat && test_kvm_facility(vcpu->kvm, 8); > > + if (psw_bits(scb_s->gpsw).eaba == PSW_BITS_AMODE_24BIT) > > + mask = 0xfff000; > > + else if (psw_bits(scb_s->gpsw).eaba == > > PSW_BITS_AMODE_31BIT) > > + mask = 0x7ffff000; > > + > > + dest = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> > > 16) & mask; > > + src = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 20) > > & mask; + > > + rc1 = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, dest, > > &pei1); > > + rc2 = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, src, > > &pei2); > > + /* > > + * Either everything went well, or something non-critical > > went wrong > > + * e.g. beause of a race. In either case, simply retry. > > + */ > > + if (rc1 == -EAGAIN || rc2 == -EAGAIN || (!rc1 && !rc2)) { > > + retry_vsie_icpt(vsie_page); > > + return -EAGAIN; > > + } > > + /* Something more serious went wrong, propagate the error > > */ > > + if (rc1 < 0) > > + return rc1; > > + if (rc2 < 0) > > + return rc2; > > + > > + /* The only possible suppressing exception: just deliver > > it */ > > + if (rc1 == PGM_TRANSLATION_SPEC || rc2 == > > PGM_TRANSLATION_SPEC) { > > + clear_vsie_icpt(vsie_page); > > + rc1 = kvm_s390_inject_program_int(vcpu, > > PGM_TRANSLATION_SPEC); > > + WARN_ON_ONCE(rc1); > > + return 1; > > + } > > + > > + /* > > + * Forward the PEI intercept to the guest if it was a page > > fault, or > > + * also for segment and region table faults if EDAT > > applies. > > + */ > > + if (edat) { > > + rc1 = rc1 == PGM_ASCE_TYPE ? rc1 : 0; > > + rc2 = rc2 == PGM_ASCE_TYPE ? rc2 : 0; > > + } > > + if ((!rc1 || rc1 == PGM_PAGE_TRANSLATION) && (!rc2 || rc2 > > == PGM_PAGE_TRANSLATION)) { > > + pei_block[0] = pei1; > > + pei_block[1] = pei2; > > + return 1; > > + } > > + > > + retry_vsie_icpt(vsie_page); > > + > > + /* > > + * The host has edat, and the guest does not, or it was an > > ASCE type > > + * exception. The host needs to inject the appropriate DAT > > interrupts > > + * into the guest. > > + */ > > + if (rc1) > > + return inject_fault(vcpu, rc1, dest, 1); > > + if (rc2)> + return inject_fault(vcpu, rc2, > > src, 0); + > > + /* This should never be reached */ > > BUG()? look at the code, if it's reached, it's a bug in the compiler :) maybe I should rewrite it so that there won't be any unreachable code at all > > + return 0; > > +} > > + > > /* > > * Run the vsie on a shadow scb and a shadow gmap, without any > > further > > * sanity checks, handling SIE faults. > > @@ -1068,6 +1148,10 @@ static int do_vsie_run(struct kvm_vcpu > > *vcpu, struct vsie_page *vsie_page) if ((scb_s->ipa & 0xf000) != > > 0xf000) scb_s->ipa += 0x1000; > > break; > > + case ICPT_PARTEXEC: > > + if (scb_s->ipa == 0xb254) > > + rc = vsie_handle_mvpg(vcpu, vsie_page); > > + break; > > } > > return rc; > > } > > >
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 7db022141db3..2db49749e27b 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -416,11 +416,6 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) memcpy((void *)((u64)scb_o + 0xc0), (void *)((u64)scb_s + 0xc0), 0xf0 - 0xc0); break; - case ICPT_PARTEXEC: - /* MVPG only */ - memcpy((void *)((u64)scb_o + 0xc0), - (void *)((u64)scb_s + 0xc0), 0xd0 - 0xc0); - break; } if (scb_s->ihcpu != 0xffffU) @@ -982,6 +977,91 @@ static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) return 0; } +static u64 vsie_get_register(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, u8 reg) +{ + reg &= 0xf; + switch (reg) { + case 15: + return vsie_page->scb_s.gg15; + case 14: + return vsie_page->scb_s.gg14; + default: + return vcpu->run->s.regs.gprs[reg]; + } +} + +static int vsie_handle_mvpg(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) +{ + struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; + unsigned long pei1, pei2, src, dest, mask = PAGE_MASK; + u64 *pei_block = &vsie_page->scb_o->mcic; + int edat, rc1, rc2; + union ctlreg0 cr0; + + cr0.val = vcpu->arch.sie_block->gcr[0]; + edat = cr0.edat && test_kvm_facility(vcpu->kvm, 8); + if (psw_bits(scb_s->gpsw).eaba == PSW_BITS_AMODE_24BIT) + mask = 0xfff000; + else if (psw_bits(scb_s->gpsw).eaba == PSW_BITS_AMODE_31BIT) + mask = 0x7ffff000; + + dest = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 16) & mask; + src = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 20) & mask; + + rc1 = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, dest, &pei1); + rc2 = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, src, &pei2); + /* + * Either everything went well, or something non-critical went wrong + * e.g. beause of a race. In either case, simply retry. + */ + if (rc1 == -EAGAIN || rc2 == -EAGAIN || (!rc1 && !rc2)) { + retry_vsie_icpt(vsie_page); + return -EAGAIN; + } + /* Something more serious went wrong, propagate the error */ + if (rc1 < 0) + return rc1; + if (rc2 < 0) + return rc2; + + /* The only possible suppressing exception: just deliver it */ + if (rc1 == PGM_TRANSLATION_SPEC || rc2 == PGM_TRANSLATION_SPEC) { + clear_vsie_icpt(vsie_page); + rc1 = kvm_s390_inject_program_int(vcpu, PGM_TRANSLATION_SPEC); + WARN_ON_ONCE(rc1); + return 1; + } + + /* + * Forward the PEI intercept to the guest if it was a page fault, or + * also for segment and region table faults if EDAT applies. + */ + if (edat) { + rc1 = rc1 == PGM_ASCE_TYPE ? rc1 : 0; + rc2 = rc2 == PGM_ASCE_TYPE ? rc2 : 0; + } + if ((!rc1 || rc1 == PGM_PAGE_TRANSLATION) && (!rc2 || rc2 == PGM_PAGE_TRANSLATION)) { + pei_block[0] = pei1; + pei_block[1] = pei2; + return 1; + } + + retry_vsie_icpt(vsie_page); + + /* + * The host has edat, and the guest does not, or it was an ASCE type + * exception. The host needs to inject the appropriate DAT interrupts + * into the guest. + */ + if (rc1) + return inject_fault(vcpu, rc1, dest, 1); + if (rc2) + return inject_fault(vcpu, rc2, src, 0); + + /* This should never be reached */ + return 0; +} + /* * Run the vsie on a shadow scb and a shadow gmap, without any further * sanity checks, handling SIE faults. @@ -1068,6 +1148,10 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if ((scb_s->ipa & 0xf000) != 0xf000) scb_s->ipa += 0x1000; break; + case ICPT_PARTEXEC: + if (scb_s->ipa == 0xb254) + rc = vsie_handle_mvpg(vcpu, vsie_page); + break; } return rc; }
Correctly handle the MVPG instruction when issued by a VSIE guest. Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested virtualization") Cc: stable@vger.kernel.org Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com> --- arch/s390/kvm/vsie.c | 94 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 89 insertions(+), 5 deletions(-)