* [PATCH v5 33/48] KVM: PPC: Book3S HV P9: Improve exit timing accounting coverage
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
The C conversion caused exit timing to become a bit cramped. Expand it
to cover more of the entry and exit code.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_interrupt.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index e419b23faa16..62cf0907e2a1 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -154,6 +154,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
if (hdec < 0)
return BOOK3S_INTERRUPT_HV_DECREMENTER;
+ start_timing(vcpu, &vcpu->arch.rm_entry);
+
if (vc->tb_offset) {
u64 new_tb = tb + vc->tb_offset;
mtspr(SPRN_TBU40, new_tb);
@@ -204,8 +206,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDEC, hdec);
- start_timing(vcpu, &vcpu->arch.rm_entry);
-
vcpu->arch.ceded = 0;
WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV);
@@ -349,8 +349,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
accumulate_time(vcpu, &vcpu->arch.rm_exit);
- end_timing(vcpu);
-
/* Advance host PURR/SPURR by the amount used by guest */
purr = mfspr(SPRN_PURR);
spurr = mfspr(SPRN_SPURR);
@@ -415,6 +413,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
switch_mmu_to_host_radix(kvm, host_pidr);
+ end_timing(vcpu);
+
return trap;
}
EXPORT_SYMBOL_GPL(kvmhv_vcpu_entry_p9);
--
2.23.0
^ permalink raw reply related
* [PATCH v5 34/48] KVM: PPC: Book3S HV P9: Move SPR loading after expiry time check
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
This is wasted work if the time limit is exceeded.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_interrupt.c | 36 ++++++++++++++++----------
1 file changed, 22 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index 62cf0907e2a1..29e2ae04b8d5 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -133,21 +133,16 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
u64 tb, purr, spurr;
u64 *exsave;
bool ri_set;
- unsigned long msr = mfmsr();
int trap;
- unsigned long host_hfscr = mfspr(SPRN_HFSCR);
- unsigned long host_ciabr = mfspr(SPRN_CIABR);
- unsigned long host_dawr0 = mfspr(SPRN_DAWR0);
- unsigned long host_dawrx0 = mfspr(SPRN_DAWRX0);
- unsigned long host_psscr = mfspr(SPRN_PSSCR);
- unsigned long host_pidr = mfspr(SPRN_PID);
- unsigned long host_dawr1 = 0;
- unsigned long host_dawrx1 = 0;
-
- if (cpu_has_feature(CPU_FTR_DAWR1)) {
- host_dawr1 = mfspr(SPRN_DAWR1);
- host_dawrx1 = mfspr(SPRN_DAWRX1);
- }
+ unsigned long msr;
+ unsigned long host_hfscr;
+ unsigned long host_ciabr;
+ unsigned long host_dawr0;
+ unsigned long host_dawrx0;
+ unsigned long host_psscr;
+ unsigned long host_pidr;
+ unsigned long host_dawr1;
+ unsigned long host_dawrx1;
tb = mftb();
hdec = time_limit - tb;
@@ -165,6 +160,19 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
vc->tb_offset_applied = vc->tb_offset;
}
+ msr = mfmsr();
+
+ host_hfscr = mfspr(SPRN_HFSCR);
+ host_ciabr = mfspr(SPRN_CIABR);
+ host_dawr0 = mfspr(SPRN_DAWR0);
+ host_dawrx0 = mfspr(SPRN_DAWRX0);
+ host_psscr = mfspr(SPRN_PSSCR);
+ host_pidr = mfspr(SPRN_PID);
+ if (cpu_has_feature(CPU_FTR_DAWR1)) {
+ host_dawr1 = mfspr(SPRN_DAWR1);
+ host_dawrx1 = mfspr(SPRN_DAWRX1);
+ }
+
if (vc->pcr)
mtspr(SPRN_PCR, vc->pcr | PCR_MASK);
mtspr(SPRN_DPDES, vc->dpdes);
--
2.23.0
^ permalink raw reply related
* [PATCH v5 35/48] KVM: PPC: Book3S HV P9: Add helpers for OS SPR handling
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
This is a first step to wrapping supervisor and user SPR saving and
loading up into helpers, which will then be called independently in
bare metal and nested HV cases in order to optimise SPR access.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 141 ++++++++++++++++++++++-------------
1 file changed, 89 insertions(+), 52 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 5953d1d72f2e..785925362630 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3492,6 +3492,89 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
trace_kvmppc_run_core(vc, 1);
}
+static void load_spr_state(struct kvm_vcpu *vcpu)
+{
+ mtspr(SPRN_DSCR, vcpu->arch.dscr);
+ mtspr(SPRN_IAMR, vcpu->arch.iamr);
+ mtspr(SPRN_PSPB, vcpu->arch.pspb);
+ mtspr(SPRN_FSCR, vcpu->arch.fscr);
+ mtspr(SPRN_TAR, vcpu->arch.tar);
+ mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
+ mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
+ mtspr(SPRN_BESCR, vcpu->arch.bescr);
+ mtspr(SPRN_WORT, vcpu->arch.wort);
+ mtspr(SPRN_TIDR, vcpu->arch.tid);
+ mtspr(SPRN_AMR, vcpu->arch.amr);
+ mtspr(SPRN_UAMOR, vcpu->arch.uamor);
+
+ /*
+ * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI]
+ * clear (or hstate set appropriately to catch those registers
+ * being clobbered if we take a MCE or SRESET), so those are done
+ * later.
+ */
+
+ if (!(vcpu->arch.ctrl & 1))
+ mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
+}
+
+static void store_spr_state(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.ctrl = mfspr(SPRN_CTRLF);
+
+ vcpu->arch.iamr = mfspr(SPRN_IAMR);
+ vcpu->arch.pspb = mfspr(SPRN_PSPB);
+ vcpu->arch.fscr = mfspr(SPRN_FSCR);
+ vcpu->arch.tar = mfspr(SPRN_TAR);
+ vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
+ vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
+ vcpu->arch.bescr = mfspr(SPRN_BESCR);
+ vcpu->arch.wort = mfspr(SPRN_WORT);
+ vcpu->arch.tid = mfspr(SPRN_TIDR);
+ vcpu->arch.amr = mfspr(SPRN_AMR);
+ vcpu->arch.uamor = mfspr(SPRN_UAMOR);
+ vcpu->arch.dscr = mfspr(SPRN_DSCR);
+}
+
+/*
+ * Privileged (non-hypervisor) host registers to save.
+ */
+struct p9_host_os_sprs {
+ unsigned long dscr;
+ unsigned long tidr;
+ unsigned long iamr;
+ unsigned long amr;
+ unsigned long fscr;
+};
+
+static void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs)
+{
+ host_os_sprs->dscr = mfspr(SPRN_DSCR);
+ host_os_sprs->tidr = mfspr(SPRN_TIDR);
+ host_os_sprs->iamr = mfspr(SPRN_IAMR);
+ host_os_sprs->amr = mfspr(SPRN_AMR);
+ host_os_sprs->fscr = mfspr(SPRN_FSCR);
+}
+
+/* vcpu guest regs must already be saved */
+static void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu,
+ struct p9_host_os_sprs *host_os_sprs)
+{
+ mtspr(SPRN_PSPB, 0);
+ mtspr(SPRN_WORT, 0);
+ mtspr(SPRN_UAMOR, 0);
+
+ mtspr(SPRN_DSCR, host_os_sprs->dscr);
+ mtspr(SPRN_TIDR, host_os_sprs->tidr);
+ mtspr(SPRN_IAMR, host_os_sprs->iamr);
+
+ if (host_os_sprs->amr != vcpu->arch.amr)
+ mtspr(SPRN_AMR, host_os_sprs->amr);
+
+ if (host_os_sprs->fscr != vcpu->arch.fscr)
+ mtspr(SPRN_FSCR, host_os_sprs->fscr);
+}
+
static inline bool hcall_is_xics(unsigned long req)
{
return req == H_EOI || req == H_CPPR || req == H_IPI ||
@@ -3506,11 +3589,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
unsigned long lpcr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
- unsigned long host_dscr = mfspr(SPRN_DSCR);
- unsigned long host_tidr = mfspr(SPRN_TIDR);
- unsigned long host_iamr = mfspr(SPRN_IAMR);
- unsigned long host_amr = mfspr(SPRN_AMR);
- unsigned long host_fscr = mfspr(SPRN_FSCR);
+ struct p9_host_os_sprs host_os_sprs;
s64 dec;
u64 tb, next_timer;
int trap, save_pmu;
@@ -3524,6 +3603,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
if (next_timer < time_limit)
time_limit = next_timer;
+ save_p9_host_os_sprs(&host_os_sprs);
+
kvmhv_save_host_pmu(); /* saves it to PACA kvm_hstate */
kvmppc_subcore_enter_guest();
@@ -3551,28 +3632,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
#endif
mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
- mtspr(SPRN_DSCR, vcpu->arch.dscr);
- mtspr(SPRN_IAMR, vcpu->arch.iamr);
- mtspr(SPRN_PSPB, vcpu->arch.pspb);
- mtspr(SPRN_FSCR, vcpu->arch.fscr);
- mtspr(SPRN_TAR, vcpu->arch.tar);
- mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
- mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
- mtspr(SPRN_BESCR, vcpu->arch.bescr);
- mtspr(SPRN_WORT, vcpu->arch.wort);
- mtspr(SPRN_TIDR, vcpu->arch.tid);
- mtspr(SPRN_AMR, vcpu->arch.amr);
- mtspr(SPRN_UAMOR, vcpu->arch.uamor);
-
- /*
- * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI]
- * clear (or hstate set appropriately to catch those registers
- * being clobbered if we take a MCE or SRESET), so those are done
- * later.
- */
-
- if (!(vcpu->arch.ctrl & 1))
- mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
+ load_spr_state(vcpu);
/*
* When setting DEC, we must always deal with irq_work_raise via NMI vs
@@ -3668,33 +3728,10 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vcpu->arch.dec_expires = dec + tb;
vcpu->cpu = -1;
vcpu->arch.thread_cpu = -1;
- vcpu->arch.ctrl = mfspr(SPRN_CTRLF);
-
- vcpu->arch.iamr = mfspr(SPRN_IAMR);
- vcpu->arch.pspb = mfspr(SPRN_PSPB);
- vcpu->arch.fscr = mfspr(SPRN_FSCR);
- vcpu->arch.tar = mfspr(SPRN_TAR);
- vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
- vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
- vcpu->arch.bescr = mfspr(SPRN_BESCR);
- vcpu->arch.wort = mfspr(SPRN_WORT);
- vcpu->arch.tid = mfspr(SPRN_TIDR);
- vcpu->arch.amr = mfspr(SPRN_AMR);
- vcpu->arch.uamor = mfspr(SPRN_UAMOR);
- vcpu->arch.dscr = mfspr(SPRN_DSCR);
-
- mtspr(SPRN_PSPB, 0);
- mtspr(SPRN_WORT, 0);
- mtspr(SPRN_UAMOR, 0);
- mtspr(SPRN_DSCR, host_dscr);
- mtspr(SPRN_TIDR, host_tidr);
- mtspr(SPRN_IAMR, host_iamr);
- if (host_amr != vcpu->arch.amr)
- mtspr(SPRN_AMR, host_amr);
+ store_spr_state(vcpu);
- if (host_fscr != vcpu->arch.fscr)
- mtspr(SPRN_FSCR, host_fscr);
+ restore_p9_host_os_sprs(vcpu, &host_os_sprs);
msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
store_fp_state(&vcpu->arch.fp);
--
2.23.0
^ permalink raw reply related
* [PATCH v5 36/48] KVM: PPC: Book3S HV P9: Switch to guest MMU context as late as possible
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
Move MMU context switch as late as reasonably possible to minimise code
running with guest context switched in. This becomes more important when
this code may run in real-mode, with later changes.
Move WARN_ON as early as possible so program check interrupts are less
likely to tangle everything up.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_interrupt.c | 40 +++++++++++++-------------
1 file changed, 20 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index 29e2ae04b8d5..4f3edf68d97b 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -149,8 +149,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
if (hdec < 0)
return BOOK3S_INTERRUPT_HV_DECREMENTER;
+ WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV);
+ WARN_ON_ONCE(!(vcpu->arch.shregs.msr & MSR_ME));
+
start_timing(vcpu, &vcpu->arch.rm_entry);
+ vcpu->arch.ceded = 0;
+
if (vc->tb_offset) {
u64 new_tb = tb + vc->tb_offset;
mtspr(SPRN_TBU40, new_tb);
@@ -199,26 +204,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_HFSCR, vcpu->arch.hfscr);
- mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0);
- mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1);
- mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2);
- mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3);
-
- mtspr(SPRN_AMOR, ~0UL);
-
- switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
-
- /*
- * P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
- * so set guest LPCR (with HDICE) before writing HDEC.
- */
- mtspr(SPRN_HDEC, hdec);
-
- vcpu->arch.ceded = 0;
-
- WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV);
- WARN_ON_ONCE(!(vcpu->arch.shregs.msr & MSR_ME));
-
mtspr(SPRN_HSRR0, vcpu->arch.regs.nip);
mtspr(SPRN_HSRR1, (vcpu->arch.shregs.msr & ~MSR_HV) | MSR_ME);
@@ -237,6 +222,21 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDSISR, HDSISR_CANARY);
+ mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0);
+ mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1);
+ mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2);
+ mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3);
+
+ mtspr(SPRN_AMOR, ~0UL);
+
+ switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
+
+ /*
+ * P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
+ * so set guest LPCR (with HDICE) before writing HDEC.
+ */
+ mtspr(SPRN_HDEC, hdec);
+
__mtmsrd(0, 1); /* clear RI */
mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
--
2.23.0
^ permalink raw reply related
* [PATCH v5 37/48] KVM: PPC: Book3S HV: Implement radix prefetch workaround by disabling MMU
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
Rather than partition the guest PID space + flush a rogue guest PID to
work around this problem, instead fix it by always disabling the MMU when
switching in or out of guest MMU context in HV mode.
This may be a bit less efficient, but it is a lot less complicated and
allows the P9 path to trivally implement the workaround too. Newer CPUs
are not subject to this issue.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/mmu_context.h | 6 ----
arch/powerpc/kvm/book3s_hv.c | 21 +++++++----
arch/powerpc/kvm/book3s_hv_interrupt.c | 16 ++++++---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 34 ------------------
arch/powerpc/mm/book3s64/radix_pgtable.c | 27 +++++---------
arch/powerpc/mm/book3s64/radix_tlb.c | 46 ------------------------
arch/powerpc/mm/mmu_context.c | 4 +--
7 files changed, 36 insertions(+), 118 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 652ce85f9410..bb5c7e5e142e 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -122,12 +122,6 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
}
#endif
-#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
-extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
-#else
-static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
-#endif
-
extern void switch_cop(struct mm_struct *next);
extern int use_cop(unsigned long acop, struct mm_struct *mm);
extern void drop_cop(unsigned long acop, struct mm_struct *mm);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 785925362630..50022c29a0fe 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -809,6 +809,9 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
*/
if (mflags != 0 && mflags != 3)
return H_UNSUPPORTED_FLAG_START;
+ if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG) &&
+ kvmhv_vcpu_is_radix(vcpu) && mflags == 3)
+ return H_UNSUPPORTED_FLAG_START;
return H_TOO_HARD;
default:
return H_TOO_HARD;
@@ -1668,6 +1671,14 @@ unsigned long kvmppc_filter_lpcr_hv(struct kvm *kvm, unsigned long lpcr)
lpcr &= ~LPCR_AIL;
if ((lpcr & LPCR_AIL) != LPCR_AIL_3)
lpcr &= ~LPCR_AIL; /* LPCR[AIL]=1/2 is disallowed */
+ /*
+ * On some POWER9s we force AIL off for radix guests to prevent
+ * executing in MSR[HV]=1 mode with the MMU enabled and PIDR set to
+ * guest, which can result in Q0 translations with LPID=0 PID=PIDR to
+ * be cached, which the host TLB management does not expect.
+ */
+ if (kvm_is_radix(kvm) && cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ lpcr &= ~LPCR_AIL;
/*
* On POWER9, allow userspace to enable large decrementer for the
@@ -4343,12 +4354,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
do {
- /*
- * The TLB prefetch bug fixup is only in the kvmppc_run_vcpu
- * path, which also handles hash and dependent threads mode.
- */
- if (kvm->arch.threads_indep && kvm_is_radix(kvm) &&
- !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ if (kvm->arch.threads_indep && kvm_is_radix(kvm))
r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
vcpu->arch.vcore->lpcr);
else
@@ -4979,6 +4985,9 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
if (!indep_threads_mode && !cpu_has_feature(CPU_FTR_HVMODE)) {
pr_warn("KVM: Ignoring indep_threads_mode=N in nested hypervisor\n");
kvm->arch.threads_indep = true;
+ } else if (!indep_threads_mode && cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
+ pr_warn("KVM: Ignoring indep_threads_mode=N on pre-DD2.2 POWER9\n");
+ kvm->arch.threads_indep = true;
} else {
kvm->arch.threads_indep = indep_threads_mode;
}
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index 4f3edf68d97b..cb2978c431c8 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -229,6 +229,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_AMOR, ~0UL);
+ if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ __mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+
switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
/*
@@ -237,7 +240,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDEC, hdec);
- __mtmsrd(0, 1); /* clear RI */
+ if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ __mtmsrd(0, 1); /* clear RI */
mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
@@ -352,9 +356,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
radix_clear_slb();
- __mtmsrd(msr, 0);
- mtspr(SPRN_CTRLT, 1);
-
accumulate_time(vcpu, &vcpu->arch.rm_exit);
/* Advance host PURR/SPURR by the amount used by guest */
@@ -421,6 +422,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
switch_mmu_to_host_radix(kvm, host_pidr);
+ /*
+ * If we are in real mode, only switch MMU on after the MMU is
+ * switched to host, to avoid the P9_RADIX_PREFETCH_BUG.
+ */
+ __mtmsrd(msr, 0);
+ mtspr(SPRN_CTRLT, 1);
+
end_timing(vcpu);
return trap;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 85c2595ead8d..9fd7e9e7fda6 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1710,40 +1710,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
eieio
tlbsync
ptesync
-
-BEGIN_FTR_SECTION
- /* Radix: Handle the case where the guest used an illegal PID */
- LOAD_REG_ADDR(r4, mmu_base_pid)
- lwz r3, VCPU_GUEST_PID(r9)
- lwz r5, 0(r4)
- cmpw cr0,r3,r5
- blt 2f
-
- /*
- * Illegal PID, the HW might have prefetched and cached in the TLB
- * some translations for the LPID 0 / guest PID combination which
- * Linux doesn't know about, so we need to flush that PID out of
- * the TLB. First we need to set LPIDR to 0 so tlbiel applies to
- * the right context.
- */
- li r0,0
- mtspr SPRN_LPID,r0
- isync
-
- /* Then do a congruence class local flush */
- ld r6,VCPU_KVM(r9)
- lwz r0,KVM_TLB_SETS(r6)
- mtctr r0
- li r7,0x400 /* IS field = 0b01 */
- ptesync
- sldi r0,r3,32 /* RS has PID */
-1: PPC_TLBIEL(7,0,2,1,1) /* RIC=2, PRS=1, R=1 */
- addi r7,r7,0x1000
- bdnz 1b
- ptesync
-END_FTR_SECTION_IFSET(CPU_FTR_P9_RADIX_PREFETCH_BUG)
-
-2:
#endif /* CONFIG_PPC_RADIX_MMU */
/*
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 98f0b243c1ab..1ea95891a79e 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -357,30 +357,19 @@ static void __init radix_init_pgtable(void)
}
/* Find out how many PID bits are supported */
- if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
- if (!mmu_pid_bits)
- mmu_pid_bits = 20;
- mmu_base_pid = 1;
- } else if (cpu_has_feature(CPU_FTR_HVMODE)) {
- if (!mmu_pid_bits)
- mmu_pid_bits = 20;
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ if (!cpu_has_feature(CPU_FTR_HVMODE) &&
+ cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
/*
- * When KVM is possible, we only use the top half of the
- * PID space to avoid collisions between host and guest PIDs
- * which can cause problems due to prefetch when exiting the
- * guest with AIL=3
+ * Older versions of KVM on these machines perfer if the
+ * guest only uses the low 19 PID bits.
*/
- mmu_base_pid = 1 << (mmu_pid_bits - 1);
-#else
- mmu_base_pid = 1;
-#endif
- } else {
- /* The guest uses the bottom half of the PID space */
if (!mmu_pid_bits)
mmu_pid_bits = 19;
- mmu_base_pid = 1;
+ } else {
+ if (!mmu_pid_bits)
+ mmu_pid_bits = 20;
}
+ mmu_base_pid = 1;
/*
* Allocate Partition table and process table for the
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 409e61210789..312236a6b085 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -1336,49 +1336,3 @@ void radix__flush_tlb_all(void)
: : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(0) : "memory");
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
-
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
-{
- unsigned long pid = mm->context.id;
-
- if (unlikely(pid == MMU_NO_CONTEXT))
- return;
-
- if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
- return;
-
- /*
- * If this context hasn't run on that CPU before and KVM is
- * around, there's a slim chance that the guest on another
- * CPU just brought in obsolete translation into the TLB of
- * this CPU due to a bad prefetch using the guest PID on
- * the way into the hypervisor.
- *
- * We work around this here. If KVM is possible, we check if
- * any sibling thread is in KVM. If it is, the window may exist
- * and thus we flush that PID from the core.
- *
- * A potential future improvement would be to mark which PIDs
- * have never been used on the system and avoid it if the PID
- * is new and the process has no other cpumask bit set.
- */
- if (cpu_has_feature(CPU_FTR_HVMODE) && radix_enabled()) {
- int cpu = smp_processor_id();
- int sib = cpu_first_thread_sibling(cpu);
- bool flush = false;
-
- for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
- if (sib == cpu)
- continue;
- if (!cpu_possible(sib))
- continue;
- if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
- flush = true;
- }
- if (flush)
- _tlbiel_pid(pid, RIC_FLUSH_ALL);
- }
-}
-EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
-#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index 18f20da0d348..7479d39976c9 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -81,9 +81,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (cpu_has_feature(CPU_FTR_ALTIVEC))
asm volatile ("dssall");
- if (new_on_cpu)
- radix_kvm_prefetch_workaround(next);
- else
+ if (!new_on_cpu)
membarrier_arch_switch_mm(prev, next, tsk);
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v5 38/48] KVM: PPC: Book3S HV: Remove support for dependent threads mode on P9
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
Radix guest support will be removed from the P7/8 path, so disallow
dependent threads mode on P9.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/kvm_host.h | 1 -
arch/powerpc/kvm/book3s_hv.c | 27 +++++----------------------
2 files changed, 5 insertions(+), 23 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 05fb00d37609..dd017dfa4e65 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -304,7 +304,6 @@ struct kvm_arch {
u8 fwnmi_enabled;
u8 secure_guest;
u8 svm_enabled;
- bool threads_indep;
bool nested_enable;
bool dawr1_enabled;
pgd_t *pgtable;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 50022c29a0fe..ae5ad93a623f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -103,13 +103,9 @@ static int target_smt_mode;
module_param(target_smt_mode, int, 0644);
MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)");
-static bool indep_threads_mode = true;
-module_param(indep_threads_mode, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(indep_threads_mode, "Independent-threads mode (only on POWER9)");
-
static bool one_vm_per_core;
module_param(one_vm_per_core, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires indep_threads_mode=N)");
+MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires POWER8 or older)");
#ifdef CONFIG_KVM_XICS
static const struct kernel_param_ops module_param_ops = {
@@ -2258,7 +2254,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
*/
static int threads_per_vcore(struct kvm *kvm)
{
- if (kvm->arch.threads_indep)
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
return 1;
return threads_per_subcore;
}
@@ -4354,7 +4350,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
do {
- if (kvm->arch.threads_indep && kvm_is_radix(kvm))
+ if (kvm_is_radix(kvm))
r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
vcpu->arch.vcore->lpcr);
else
@@ -4978,21 +4974,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
/*
* Track that we now have a HV mode VM active. This blocks secondary
* CPU threads from coming online.
- * On POWER9, we only need to do this if the "indep_threads_mode"
- * module parameter has been set to N.
*/
- if (cpu_has_feature(CPU_FTR_ARCH_300)) {
- if (!indep_threads_mode && !cpu_has_feature(CPU_FTR_HVMODE)) {
- pr_warn("KVM: Ignoring indep_threads_mode=N in nested hypervisor\n");
- kvm->arch.threads_indep = true;
- } else if (!indep_threads_mode && cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
- pr_warn("KVM: Ignoring indep_threads_mode=N on pre-DD2.2 POWER9\n");
- kvm->arch.threads_indep = true;
- } else {
- kvm->arch.threads_indep = indep_threads_mode;
- }
- }
- if (!kvm->arch.threads_indep)
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
kvm_hv_vm_activated();
/*
@@ -5033,7 +5016,7 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
{
debugfs_remove_recursive(kvm->arch.debugfs_dir);
- if (!kvm->arch.threads_indep)
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
kvm_hv_vm_deactivated();
kvmppc_free_vcores(kvm);
--
2.23.0
^ permalink raw reply related
* [PATCH v5 39/48] KVM: PPC: Book3S HV: Remove radix guest support from P7/8 path
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
The P9 path now runs all supported radix guest combinations, so
remove radix guest support from the P7/8 path.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 79 +------------------------
1 file changed, 3 insertions(+), 76 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 9fd7e9e7fda6..3b68b4817d6d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -133,15 +133,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
/* Return the trap number on this thread as the return value */
mr r3, r12
- /*
- * If we came back from the guest via a relocation-on interrupt,
- * we will be in virtual mode at this point, which makes it a
- * little easier to get back to the caller.
- */
- mfmsr r0
- andi. r0, r0, MSR_IR /* in real mode? */
- bne .Lvirt_return
-
/* RFI into the highmem handler */
mfmsr r6
li r0, MSR_RI
@@ -151,11 +142,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtsrr1 r7
RFI_TO_KERNEL
- /* Virtual-mode return */
-.Lvirt_return:
- mtlr r8
- blr
-
kvmppc_primary_no_guest:
/* We handle this much like a ceded vcpu */
/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
@@ -899,11 +885,6 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
cmpdi r3, 512 /* 1 microsecond */
blt hdec_soon
- ld r6, VCPU_KVM(r4)
- lbz r0, KVM_RADIX(r6)
- cmpwi r0, 0
- bne 9f
-
/* For hash guest, clear out and reload the SLB */
BEGIN_MMU_FTR_SECTION
/* Radix host won't have populated the SLB, so no need to clear */
@@ -1389,11 +1370,7 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
patch_site 1b patch__call_kvm_flush_link_stack
/* For hash guest, read the guest SLB and save it away */
- ld r5, VCPU_KVM(r9)
- lbz r0, KVM_RADIX(r5)
li r5, 0
- cmpwi r0, 0
- bne 0f /* for radix, save 0 entries */
lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */
mtctr r0
li r6,0
@@ -1432,23 +1409,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
slbmte r6,r5
1: addi r8,r8,16
.endr
- b guest_bypass
-
-0: /*
- * Malicious or buggy radix guests may have inserted SLB entries
- * (only 0..3 because radix always runs with UPRT=1), so these must
- * be cleared here to avoid side-channels. slbmte is used rather
- * than slbia, as it won't clear cached translations.
- */
- li r0,0
- stw r0,VCPU_SLB_MAX(r9)
- slbmte r0,r0
- li r4,1
- slbmte r0,r4
- li r4,2
- slbmte r0,r4
- li r4,3
- slbmte r0,r4
guest_bypass:
stw r12, STACK_SLOT_TRAP(r1)
@@ -1694,24 +1654,6 @@ BEGIN_FTR_SECTION
mtspr SPRN_PID, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-#ifdef CONFIG_PPC_RADIX_MMU
- /*
- * Are we running hash or radix ?
- */
- ld r5, VCPU_KVM(r9)
- lbz r0, KVM_RADIX(r5)
- cmpwi cr2, r0, 0
- beq cr2, 2f
-
- /*
- * Radix: do eieio; tlbsync; ptesync sequence in case we
- * interrupted the guest between a tlbie and a ptesync.
- */
- eieio
- tlbsync
- ptesync
-#endif /* CONFIG_PPC_RADIX_MMU */
-
/*
* cp_abort is required if the processor supports local copy-paste
* to clear the copy buffer that was under control of the guest.
@@ -1970,8 +1912,6 @@ kvmppc_tm_emul:
* reflect the HDSI to the guest as a DSI.
*/
kvmppc_hdsi:
- ld r3, VCPU_KVM(r9)
- lbz r0, KVM_RADIX(r3)
mfspr r4, SPRN_HDAR
mfspr r6, SPRN_HDSISR
BEGIN_FTR_SECTION
@@ -1979,8 +1919,6 @@ BEGIN_FTR_SECTION
cmpdi r6, 0x7fff
beq 6f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
- cmpwi r0, 0
- bne .Lradix_hdsi /* on radix, just save DAR/DSISR/ASDR */
/* HPTE not found fault or protection fault? */
andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
beq 1f /* if not, send it to the guest */
@@ -2057,23 +1995,11 @@ fast_interrupt_c_return:
stb r0, HSTATE_IN_GUEST(r13)
b guest_exit_cont
-.Lradix_hdsi:
- std r4, VCPU_FAULT_DAR(r9)
- stw r6, VCPU_FAULT_DSISR(r9)
-.Lradix_hisi:
- mfspr r5, SPRN_ASDR
- std r5, VCPU_FAULT_GPA(r9)
- b guest_exit_cont
-
/*
* Similarly for an HISI, reflect it to the guest as an ISI unless
* it is an HPTE not found fault for a page that we have paged out.
*/
kvmppc_hisi:
- ld r3, VCPU_KVM(r9)
- lbz r0, KVM_RADIX(r3)
- cmpwi r0, 0
- bne .Lradix_hisi /* for radix, just save ASDR */
andis. r0, r11, SRR1_ISI_NOPT@h
beq 1f
andi. r0, r11, MSR_IR /* instruction relocation enabled? */
@@ -3217,15 +3143,16 @@ BEGIN_FTR_SECTION
mtspr SPRN_DAWRX1, r0
END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
- /* Clear hash and radix guest SLB. */
+ /* Clear guest SLB. */
slbmte r0, r0
PPC_SLBIA(6)
+ ptesync
BEGIN_MMU_FTR_SECTION
b 4f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
- ptesync
+ /* load host SLB entries */
ld r8, PACA_SLBSHADOWPTR(r13)
.rept SLB_NUM_BOLTED
li r3, SLBSHADOW_SAVEAREA
--
2.23.0
^ permalink raw reply related
* [PATCH v5 40/48] KVM: PPC: Book3S HV: Remove virt mode checks from real mode handlers
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Cédric Le Goater, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
Now that the P7/8 path no longer supports radix, real-mode handlers
do not need to deal with being called in virt mode.
This change effectively reverts commit acde25726bc6 ("KVM: PPC: Book3S
HV: Add radix checks in real-mode hypercall handlers").
It removes a few more real-mode tests in rm hcall handlers, which also
allows the indirect ops for the xive module to be removed from the
built-in xics rm handlers.
kvmppc_h_random is renamed to kvmppc_rm_h_random to be a bit more
descriptive of its function.
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/kvm_ppc.h | 10 +--
arch/powerpc/kvm/book3s.c | 11 +--
arch/powerpc/kvm/book3s_64_vio_hv.c | 12 ----
arch/powerpc/kvm/book3s_hv_builtin.c | 91 ++++++-------------------
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 +-
arch/powerpc/kvm/book3s_xive.c | 18 -----
arch/powerpc/kvm/book3s_xive.h | 7 --
arch/powerpc/kvm/book3s_xive_native.c | 10 ---
8 files changed, 23 insertions(+), 138 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index cbd8deba2e8a..896e309431fb 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -660,8 +660,6 @@ extern int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
u32 *priority);
extern int kvmppc_xive_int_on(struct kvm *kvm, u32 irq);
extern int kvmppc_xive_int_off(struct kvm *kvm, u32 irq);
-extern void kvmppc_xive_init_module(void);
-extern void kvmppc_xive_exit_module(void);
extern int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
struct kvm_vcpu *vcpu, u32 cpu);
@@ -687,8 +685,6 @@ static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
extern int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
struct kvm_vcpu *vcpu, u32 cpu);
extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu);
-extern void kvmppc_xive_native_init_module(void);
-extern void kvmppc_xive_native_exit_module(void);
extern int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
union kvmppc_one_reg *val);
extern int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu,
@@ -702,8 +698,6 @@ static inline int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
u32 *priority) { return -1; }
static inline int kvmppc_xive_int_on(struct kvm *kvm, u32 irq) { return -1; }
static inline int kvmppc_xive_int_off(struct kvm *kvm, u32 irq) { return -1; }
-static inline void kvmppc_xive_init_module(void) { }
-static inline void kvmppc_xive_exit_module(void) { }
static inline int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
@@ -726,8 +720,6 @@ static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
static inline int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
static inline void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { }
-static inline void kvmppc_xive_native_init_module(void) { }
-static inline void kvmppc_xive_native_exit_module(void) { }
static inline int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
union kvmppc_one_reg *val)
{ return 0; }
@@ -763,7 +755,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
unsigned long tce_value, unsigned long npages);
long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
unsigned int yield_count);
-long kvmppc_h_random(struct kvm_vcpu *vcpu);
+long kvmppc_rm_h_random(struct kvm_vcpu *vcpu);
void kvmhv_commence_exit(int trap);
void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu);
void kvmppc_subcore_enter_guest(void);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 1658f899e289..d3bd509b4093 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -1052,13 +1052,10 @@ static int kvmppc_book3s_init(void)
#ifdef CONFIG_KVM_XICS
#ifdef CONFIG_KVM_XIVE
if (xics_on_xive()) {
- kvmppc_xive_init_module();
kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
- if (kvmppc_xive_native_supported()) {
- kvmppc_xive_native_init_module();
+ if (kvmppc_xive_native_supported())
kvm_register_device_ops(&kvm_xive_native_ops,
KVM_DEV_TYPE_XIVE);
- }
} else
#endif
kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
@@ -1068,12 +1065,6 @@ static int kvmppc_book3s_init(void)
static void kvmppc_book3s_exit(void)
{
-#ifdef CONFIG_KVM_XICS
- if (xics_on_xive()) {
- kvmppc_xive_exit_module();
- kvmppc_xive_native_exit_module();
- }
-#endif
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
kvmppc_book3s_exit_pr();
#endif
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 083a4e037718..dc6591548f0c 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -391,10 +391,6 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */
- /* For radix, we might be in virtual mode, so punt */
- if (kvm_is_radix(vcpu->kvm))
- return H_TOO_HARD;
-
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -489,10 +485,6 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
bool prereg = false;
struct kvmppc_spapr_tce_iommu_table *stit;
- /* For radix, we might be in virtual mode, so punt */
- if (kvm_is_radix(vcpu->kvm))
- return H_TOO_HARD;
-
/*
* used to check for invalidations in progress
*/
@@ -602,10 +594,6 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
long i, ret;
struct kvmppc_spapr_tce_iommu_table *stit;
- /* For radix, we might be in virtual mode, so punt */
- if (kvm_is_radix(vcpu->kvm))
- return H_TOO_HARD;
-
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 7a0e33a9c980..8d669a0e15f8 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -34,21 +34,6 @@
#include "book3s_xics.h"
#include "book3s_xive.h"
-/*
- * The XIVE module will populate these when it loads
- */
-unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
-unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
-int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
- unsigned long mfrr);
-int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
-int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
-EXPORT_SYMBOL_GPL(__xive_vm_h_xirr);
-EXPORT_SYMBOL_GPL(__xive_vm_h_ipoll);
-EXPORT_SYMBOL_GPL(__xive_vm_h_ipi);
-EXPORT_SYMBOL_GPL(__xive_vm_h_cppr);
-EXPORT_SYMBOL_GPL(__xive_vm_h_eoi);
-
/*
* Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
* should be power of 2.
@@ -196,16 +181,9 @@ int kvmppc_hwrng_present(void)
}
EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
-long kvmppc_h_random(struct kvm_vcpu *vcpu)
+long kvmppc_rm_h_random(struct kvm_vcpu *vcpu)
{
- int r;
-
- /* Only need to do the expensive mfmsr() on radix */
- if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
- r = powernv_get_random_long(&vcpu->arch.regs.gpr[4]);
- else
- r = powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4]);
- if (r)
+ if (powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4]))
return H_SUCCESS;
return H_HARDWARE;
@@ -541,22 +519,13 @@ static long kvmppc_read_one_intr(bool *again)
}
#ifdef CONFIG_KVM_XICS
-static inline bool is_rm(void)
-{
- return !(mfmsr() & MSR_DR);
-}
-
unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
- if (xics_on_xive()) {
- if (is_rm())
- return xive_rm_h_xirr(vcpu);
- if (unlikely(!__xive_vm_h_xirr))
- return H_NOT_AVAILABLE;
- return __xive_vm_h_xirr(vcpu);
- } else
+ if (xics_on_xive())
+ return xive_rm_h_xirr(vcpu);
+ else
return xics_rm_h_xirr(vcpu);
}
@@ -565,13 +534,9 @@ unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu)
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
vcpu->arch.regs.gpr[5] = get_tb();
- if (xics_on_xive()) {
- if (is_rm())
- return xive_rm_h_xirr(vcpu);
- if (unlikely(!__xive_vm_h_xirr))
- return H_NOT_AVAILABLE;
- return __xive_vm_h_xirr(vcpu);
- } else
+ if (xics_on_xive())
+ return xive_rm_h_xirr(vcpu);
+ else
return xics_rm_h_xirr(vcpu);
}
@@ -579,13 +544,9 @@ unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
- if (xics_on_xive()) {
- if (is_rm())
- return xive_rm_h_ipoll(vcpu, server);
- if (unlikely(!__xive_vm_h_ipoll))
- return H_NOT_AVAILABLE;
- return __xive_vm_h_ipoll(vcpu, server);
- } else
+ if (xics_on_xive())
+ return xive_rm_h_ipoll(vcpu, server);
+ else
return H_TOO_HARD;
}
@@ -594,13 +555,9 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
- if (xics_on_xive()) {
- if (is_rm())
- return xive_rm_h_ipi(vcpu, server, mfrr);
- if (unlikely(!__xive_vm_h_ipi))
- return H_NOT_AVAILABLE;
- return __xive_vm_h_ipi(vcpu, server, mfrr);
- } else
+ if (xics_on_xive())
+ return xive_rm_h_ipi(vcpu, server, mfrr);
+ else
return xics_rm_h_ipi(vcpu, server, mfrr);
}
@@ -608,13 +565,9 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
- if (xics_on_xive()) {
- if (is_rm())
- return xive_rm_h_cppr(vcpu, cppr);
- if (unlikely(!__xive_vm_h_cppr))
- return H_NOT_AVAILABLE;
- return __xive_vm_h_cppr(vcpu, cppr);
- } else
+ if (xics_on_xive())
+ return xive_rm_h_cppr(vcpu, cppr);
+ else
return xics_rm_h_cppr(vcpu, cppr);
}
@@ -622,13 +575,9 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
- if (xics_on_xive()) {
- if (is_rm())
- return xive_rm_h_eoi(vcpu, xirr);
- if (unlikely(!__xive_vm_h_eoi))
- return H_NOT_AVAILABLE;
- return __xive_vm_h_eoi(vcpu, xirr);
- } else
+ if (xics_on_xive())
+ return xive_rm_h_eoi(vcpu, xirr);
+ else
return xics_rm_h_eoi(vcpu, xirr);
}
#endif /* CONFIG_KVM_XICS */
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 3b68b4817d6d..7a0e26c9fab9 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -2323,7 +2323,7 @@ hcall_real_table:
#else
.long 0 /* 0x2fc - H_XIRR_X*/
#endif
- .long DOTSYM(kvmppc_h_random) - hcall_real_table
+ .long DOTSYM(kvmppc_rm_h_random) - hcall_real_table
.globl hcall_real_table_end
hcall_real_table_end:
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 24c07094651a..9268d386b128 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -2352,21 +2352,3 @@ struct kvm_device_ops kvm_xive_ops = {
.get_attr = xive_get_attr,
.has_attr = xive_has_attr,
};
-
-void kvmppc_xive_init_module(void)
-{
- __xive_vm_h_xirr = xive_vm_h_xirr;
- __xive_vm_h_ipoll = xive_vm_h_ipoll;
- __xive_vm_h_ipi = xive_vm_h_ipi;
- __xive_vm_h_cppr = xive_vm_h_cppr;
- __xive_vm_h_eoi = xive_vm_h_eoi;
-}
-
-void kvmppc_xive_exit_module(void)
-{
- __xive_vm_h_xirr = NULL;
- __xive_vm_h_ipoll = NULL;
- __xive_vm_h_ipi = NULL;
- __xive_vm_h_cppr = NULL;
- __xive_vm_h_eoi = NULL;
-}
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index 86c24a4ad809..afe9eeac6d56 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -289,13 +289,6 @@ extern int xive_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
extern int xive_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
extern int xive_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
-extern unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
-extern unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
-extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
- unsigned long mfrr);
-extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
-extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
-
/*
* Common Xive routines for XICS-over-XIVE and XIVE native
*/
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 76800c84f2a3..1253666dd4d8 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -1281,13 +1281,3 @@ struct kvm_device_ops kvm_xive_native_ops = {
.has_attr = kvmppc_xive_native_has_attr,
.mmap = kvmppc_xive_native_mmap,
};
-
-void kvmppc_xive_native_init_module(void)
-{
- ;
-}
-
-void kvmppc_xive_native_exit_module(void)
-{
- ;
-}
--
2.23.0
^ permalink raw reply related
* [PATCH v5 41/48] KVM: PPC: Book3S HV: Remove unused nested HV tests in XICS emulation
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Cédric Le Goater, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
Commit f3c18e9342a44 ("KVM: PPC: Book3S HV: Use XICS hypercalls when
running as a nested hypervisor") added nested HV tests in XICS
hypercalls, but not all are required.
* icp_eoi is only called by kvmppc_deliver_irq_passthru which is only
called by kvmppc_check_passthru which is only caled by
kvmppc_read_one_intr.
* kvmppc_read_one_intr is only called by kvmppc_read_intr which is only
called by the L0 HV rmhandlers code.
* kvmhv_rm_send_ipi is called by:
- kvmhv_interrupt_vcore which is only called by kvmhv_commence_exit
which is only called by the L0 HV rmhandlers code.
- icp_send_hcore_msg which is only called by icp_rm_set_vcpu_irq.
- icp_rm_set_vcpu_irq which is only called by icp_rm_try_update
- icp_rm_set_vcpu_irq is not nested HV safe because it writes to
LPCR directly without a kvmhv_on_pseries test. Nested handlers
should not in general be using the rm handlers.
The important test seems to be in kvmppc_ipi_thread, which sends the
virt-mode H_IPI handler kick to use smp_call_function rather than
msgsnd.
Cc: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_builtin.c | 44 +++++-----------------------
arch/powerpc/kvm/book3s_hv_rm_xics.c | 15 ----------
2 files changed, 8 insertions(+), 51 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8d669a0e15f8..259492bb4153 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -199,15 +199,6 @@ void kvmhv_rm_send_ipi(int cpu)
void __iomem *xics_phys;
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
- /* For a nested hypervisor, use the XICS via hcall */
- if (kvmhv_on_pseries()) {
- unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
- plpar_hcall_raw(H_IPI, retbuf, get_hard_smp_processor_id(cpu),
- IPI_PRIORITY);
- return;
- }
-
/* On POWER9 we can use msgsnd for any destination cpu. */
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
msg |= get_hard_smp_processor_id(cpu);
@@ -420,19 +411,12 @@ static long kvmppc_read_one_intr(bool *again)
return 1;
/* Now read the interrupt from the ICP */
- if (kvmhv_on_pseries()) {
- unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
- rc = plpar_hcall_raw(H_XIRR, retbuf, 0xFF);
- xirr = cpu_to_be32(retbuf[0]);
- } else {
- xics_phys = local_paca->kvm_hstate.xics_phys;
- rc = 0;
- if (!xics_phys)
- rc = opal_int_get_xirr(&xirr, false);
- else
- xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
- }
+ xics_phys = local_paca->kvm_hstate.xics_phys;
+ rc = 0;
+ if (!xics_phys)
+ rc = opal_int_get_xirr(&xirr, false);
+ else
+ xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
if (rc < 0)
return 1;
@@ -461,13 +445,7 @@ static long kvmppc_read_one_intr(bool *again)
*/
if (xisr == XICS_IPI) {
rc = 0;
- if (kvmhv_on_pseries()) {
- unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
- plpar_hcall_raw(H_IPI, retbuf,
- hard_smp_processor_id(), 0xff);
- plpar_hcall_raw(H_EOI, retbuf, h_xirr);
- } else if (xics_phys) {
+ if (xics_phys) {
__raw_rm_writeb(0xff, xics_phys + XICS_MFRR);
__raw_rm_writel(xirr, xics_phys + XICS_XIRR);
} else {
@@ -493,13 +471,7 @@ static long kvmppc_read_one_intr(bool *again)
/* We raced with the host,
* we need to resend that IPI, bummer
*/
- if (kvmhv_on_pseries()) {
- unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
- plpar_hcall_raw(H_IPI, retbuf,
- hard_smp_processor_id(),
- IPI_PRIORITY);
- } else if (xics_phys)
+ if (xics_phys)
__raw_rm_writeb(IPI_PRIORITY,
xics_phys + XICS_MFRR);
else
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index c2c9c733f359..0a11ec88a0ae 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -141,13 +141,6 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
return;
}
- if (xive_enabled() && kvmhv_on_pseries()) {
- /* No XICS access or hypercalls available, too hard */
- this_icp->rm_action |= XICS_RM_KICK_VCPU;
- this_icp->rm_kick_target = vcpu;
- return;
- }
-
/*
* Check if the core is loaded,
* if not, find an available host core to post to wake the VCPU,
@@ -771,14 +764,6 @@ static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
void __iomem *xics_phys;
int64_t rc;
- if (kvmhv_on_pseries()) {
- unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
- iosync();
- plpar_hcall_raw(H_EOI, retbuf, hwirq);
- return;
- }
-
rc = pnv_opal_pci_msi_eoi(c, hwirq);
if (rc)
--
2.23.0
^ permalink raw reply related
* [PATCH v5 42/48] KVM: PPC: Book3S HV: Radix guests should not have userspace hcalls reflected to them
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
The reflection of sc 1 hcalls from PR=1 userspace is required to support
PR KVM. Radix guests don't support PR KVM nor do they support nested
hash guests, so this sc 1 reflection can be removed from radix guests.
Cause a privileged program check instead, which is less surprising.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 19 ++++++++++++++-----
1 file changed, 14 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ae5ad93a623f..f4d6ec6c4710 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1403,11 +1403,20 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
int i;
if (unlikely(vcpu->arch.shregs.msr & MSR_PR)) {
- /*
- * Guest userspace executed sc 1, reflect it back as a
- * syscall as it may be a PR KVM hcall.
- */
- kvmppc_core_queue_syscall(vcpu);
+ if (!kvmhv_vcpu_is_radix(vcpu)) {
+ /*
+ * Guest userspace executed sc 1, reflect it
+ * back as a syscall as it may be a PR KVM
+ * hcall.
+ */
+ kvmppc_core_queue_syscall(vcpu);
+ } else {
+ /*
+ * radix guests can not run PR KVM so send a
+ * program check.
+ */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+ }
r = RESUME_GUEST;
break;
}
--
2.23.0
^ permalink raw reply related
* [PATCH v5 43/48] KVM: PPC: Book3S HV P9: Allow all P9 processors to enable nested HV
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
All radix guests go via the P9 path now, so there is no need to limit
nested HV to processors that support "mixed mode" MMU. Remove the
restriction.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index f4d6ec6c4710..f4fa39f4cd4c 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -5446,7 +5446,7 @@ static int kvmhv_enable_nested(struct kvm *kvm)
{
if (!nested)
return -EPERM;
- if (!cpu_has_feature(CPU_FTR_ARCH_300) || no_mixing_hpt_and_radix)
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
return -ENODEV;
/* kvm == NULL means the caller is testing if the capability exists */
--
2.23.0
^ permalink raw reply related
* [PATCH v5 44/48] KVM: PPC: Book3S HV: small pseries_do_hcall cleanup
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
Functionality should not be changed.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 29 +++++++++++++++--------------
1 file changed, 15 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index f4fa39f4cd4c..8416ec0d88bc 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -925,6 +925,7 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
{
+ struct kvm *kvm = vcpu->kvm;
unsigned long req = kvmppc_get_gpr(vcpu, 3);
unsigned long target, ret = H_SUCCESS;
int yield_count;
@@ -940,7 +941,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
break;
case H_PROD:
target = kvmppc_get_gpr(vcpu, 4);
- tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
+ tvcpu = kvmppc_find_vcpu(kvm, target);
if (!tvcpu) {
ret = H_PARAMETER;
break;
@@ -954,7 +955,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
target = kvmppc_get_gpr(vcpu, 4);
if (target == -1)
break;
- tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
+ tvcpu = kvmppc_find_vcpu(kvm, target);
if (!tvcpu) {
ret = H_PARAMETER;
break;
@@ -970,12 +971,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
kvmppc_get_gpr(vcpu, 6));
break;
case H_RTAS:
- if (list_empty(&vcpu->kvm->arch.rtas_tokens))
+ if (list_empty(&kvm->arch.rtas_tokens))
return RESUME_HOST;
- idx = srcu_read_lock(&vcpu->kvm->srcu);
+ idx = srcu_read_lock(&kvm->srcu);
rc = kvmppc_rtas_hcall(vcpu);
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ srcu_read_unlock(&kvm->srcu, idx);
if (rc == -ENOENT)
return RESUME_HOST;
@@ -1062,12 +1063,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
case H_SET_PARTITION_TABLE:
ret = H_FUNCTION;
- if (nesting_enabled(vcpu->kvm))
+ if (nesting_enabled(kvm))
ret = kvmhv_set_partition_table(vcpu);
break;
case H_ENTER_NESTED:
ret = H_FUNCTION;
- if (!nesting_enabled(vcpu->kvm))
+ if (!nesting_enabled(kvm))
break;
ret = kvmhv_enter_nested_guest(vcpu);
if (ret == H_INTERRUPT) {
@@ -1082,12 +1083,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
break;
case H_TLB_INVALIDATE:
ret = H_FUNCTION;
- if (nesting_enabled(vcpu->kvm))
+ if (nesting_enabled(kvm))
ret = kvmhv_do_nested_tlbie(vcpu);
break;
case H_COPY_TOFROM_GUEST:
ret = H_FUNCTION;
- if (nesting_enabled(vcpu->kvm))
+ if (nesting_enabled(kvm))
ret = kvmhv_copy_tofrom_guest_nested(vcpu);
break;
case H_PAGE_INIT:
@@ -1098,7 +1099,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
case H_SVM_PAGE_IN:
ret = H_UNSUPPORTED;
if (kvmppc_get_srr1(vcpu) & MSR_S)
- ret = kvmppc_h_svm_page_in(vcpu->kvm,
+ ret = kvmppc_h_svm_page_in(kvm,
kvmppc_get_gpr(vcpu, 4),
kvmppc_get_gpr(vcpu, 5),
kvmppc_get_gpr(vcpu, 6));
@@ -1106,7 +1107,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
case H_SVM_PAGE_OUT:
ret = H_UNSUPPORTED;
if (kvmppc_get_srr1(vcpu) & MSR_S)
- ret = kvmppc_h_svm_page_out(vcpu->kvm,
+ ret = kvmppc_h_svm_page_out(kvm,
kvmppc_get_gpr(vcpu, 4),
kvmppc_get_gpr(vcpu, 5),
kvmppc_get_gpr(vcpu, 6));
@@ -1114,12 +1115,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
case H_SVM_INIT_START:
ret = H_UNSUPPORTED;
if (kvmppc_get_srr1(vcpu) & MSR_S)
- ret = kvmppc_h_svm_init_start(vcpu->kvm);
+ ret = kvmppc_h_svm_init_start(kvm);
break;
case H_SVM_INIT_DONE:
ret = H_UNSUPPORTED;
if (kvmppc_get_srr1(vcpu) & MSR_S)
- ret = kvmppc_h_svm_init_done(vcpu->kvm);
+ ret = kvmppc_h_svm_init_done(kvm);
break;
case H_SVM_INIT_ABORT:
/*
@@ -1129,7 +1130,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
* Instead the kvm->arch.secure_guest flag is checked inside
* kvmppc_h_svm_init_abort().
*/
- ret = kvmppc_h_svm_init_abort(vcpu->kvm);
+ ret = kvmppc_h_svm_init_abort(kvm);
break;
default:
--
2.23.0
^ permalink raw reply related
* [PATCH v5 45/48] KVM: PPC: Book3S HV: add virtual mode handlers for HPT hcalls and page faults
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
In order to support hash guests in the P9 path (which does not do real
mode hcalls or page fault handling), these real-mode hash specific
interrupts need to be implemented in virt mode.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 126 ++++++++++++++++++++++++++--
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 8 ++
2 files changed, 127 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8416ec0d88bc..6b34cd81000e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -937,6 +937,52 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
return RESUME_HOST;
switch (req) {
+ case H_REMOVE:
+ ret = kvmppc_h_remove(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_ENTER:
+ ret = kvmppc_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6),
+ kvmppc_get_gpr(vcpu, 7));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_READ:
+ ret = kvmppc_h_read(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_CLEAR_MOD:
+ ret = kvmppc_h_clear_mod(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_CLEAR_REF:
+ ret = kvmppc_h_clear_ref(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_PROTECT:
+ ret = kvmppc_h_protect(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_BULK_REMOVE:
+ ret = kvmppc_h_bulk_remove(vcpu);
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+
case H_CEDE:
break;
case H_PROD:
@@ -1136,6 +1182,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
default:
return RESUME_HOST;
}
+ WARN_ON_ONCE(ret == H_TOO_HARD);
kvmppc_set_gpr(vcpu, 3, ret);
vcpu->arch.hcall_needed = 0;
return RESUME_GUEST;
@@ -1443,19 +1490,84 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
* host page has been paged out. Any other HDSI/HISI interrupts
* have been handled already.
*/
- case BOOK3S_INTERRUPT_H_DATA_STORAGE:
- r = RESUME_PAGE_FAULT;
- if (vcpu->arch.fault_dsisr == HDSISR_CANARY)
+ case BOOK3S_INTERRUPT_H_DATA_STORAGE: {
+ unsigned long vsid;
+ long err;
+
+ if (vcpu->arch.fault_dsisr == HDSISR_CANARY) {
r = RESUME_GUEST; /* Just retry if it's the canary */
+ break;
+ }
+
+ if (kvm_is_radix(vcpu->kvm)) {
+ r = RESUME_PAGE_FAULT;
+ break;
+ }
+
+ if (!(vcpu->arch.fault_dsisr & (DSISR_NOHPTE | DSISR_PROTFAULT))) {
+ kvmppc_core_queue_data_storage(vcpu,
+ vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
+ r = RESUME_GUEST;
+ break;
+ }
+
+ if (!(vcpu->arch.shregs.msr & MSR_DR))
+ vsid = vcpu->kvm->arch.vrma_slb_v;
+ else
+ vsid = vcpu->arch.fault_gpa;
+
+ err = kvmppc_hpte_hv_fault(vcpu, vcpu->arch.fault_dar,
+ vsid, vcpu->arch.fault_dsisr, true);
+ if (err == 0) {
+ r = RESUME_GUEST;
+ } else if (err == -1 || err == -2) {
+ r = RESUME_PAGE_FAULT;
+ } else {
+ kvmppc_core_queue_data_storage(vcpu,
+ vcpu->arch.fault_dar, err);
+ r = RESUME_GUEST;
+ }
break;
- case BOOK3S_INTERRUPT_H_INST_STORAGE:
+ }
+ case BOOK3S_INTERRUPT_H_INST_STORAGE: {
+ unsigned long vsid;
+ long err;
+
vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
vcpu->arch.fault_dsisr = vcpu->arch.shregs.msr &
DSISR_SRR1_MATCH_64S;
- if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE)
- vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
- r = RESUME_PAGE_FAULT;
+ if (kvm_is_radix(vcpu->kvm)) {
+ if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE)
+ vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
+ r = RESUME_PAGE_FAULT;
+ break;
+ }
+
+ if (!(vcpu->arch.fault_dsisr & SRR1_ISI_NOPT)) {
+ kvmppc_core_queue_inst_storage(vcpu,
+ vcpu->arch.fault_dsisr);
+ r = RESUME_GUEST;
+ break;
+ }
+
+ if (!(vcpu->arch.shregs.msr & MSR_DR))
+ vsid = vcpu->kvm->arch.vrma_slb_v;
+ else
+ vsid = vcpu->arch.fault_gpa;
+
+ err = kvmppc_hpte_hv_fault(vcpu, vcpu->arch.fault_dar,
+ vsid, vcpu->arch.fault_dsisr, false);
+ if (err == 0) {
+ r = RESUME_GUEST;
+ } else if (err == -1) {
+ r = RESUME_PAGE_FAULT;
+ } else {
+ kvmppc_core_queue_inst_storage(vcpu, err);
+ r = RESUME_GUEST;
+ }
break;
+ }
+
/*
* This occurs if the guest executes an illegal instruction.
* If the guest debug is disabled, generate a program interrupt
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 7af7c70f1468..8cc73abbf42b 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -409,6 +409,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
vcpu->arch.pgdir, true,
&vcpu->arch.regs.gpr[4]);
}
+EXPORT_SYMBOL_GPL(kvmppc_h_enter);
#ifdef __BIG_ENDIAN__
#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token))
@@ -553,6 +554,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
return kvmppc_do_h_remove(vcpu->kvm, flags, pte_index, avpn,
&vcpu->arch.regs.gpr[4]);
}
+EXPORT_SYMBOL_GPL(kvmppc_h_remove);
long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
{
@@ -671,6 +673,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
return ret;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_bulk_remove);
long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index, unsigned long avpn)
@@ -741,6 +744,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
return H_SUCCESS;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_protect);
long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
@@ -781,6 +785,7 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
}
return H_SUCCESS;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_read);
long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
@@ -829,6 +834,7 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
return ret;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_clear_ref);
long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
@@ -876,6 +882,7 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
return ret;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_clear_mod);
static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long mmu_seq,
unsigned long gpa, int writing, unsigned long *hpa,
@@ -1294,3 +1301,4 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
return -1; /* send fault up to host kernel mode */
}
+EXPORT_SYMBOL_GPL(kvmppc_hpte_hv_fault);
--
2.23.0
^ permalink raw reply related
* [PATCH v5 46/48] KVM: PPC: Book3S HV P9: implement hash guest support
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
Guest entry/exit has to restore and save/clear the SLB, plus several
other bits to accommodate hash guests in the P9 path.
Radix host, hash guest support is removed from the P7/8 path.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 20 ++-
arch/powerpc/kvm/book3s_hv_interrupt.c | 156 +++++++++++++++++-------
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 4 +
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 14 +--
4 files changed, 132 insertions(+), 62 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6b34cd81000e..728e98bb61eb 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3847,7 +3847,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
}
kvmppc_xive_pull_vcpu(vcpu);
- vcpu->arch.slb_max = 0;
+ if (kvm_is_radix(vcpu->kvm))
+ vcpu->arch.slb_max = 0;
}
dec = mfspr(SPRN_DEC);
@@ -4079,7 +4080,6 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
/*
* This never fails for a radix guest, as none of the operations it does
* for a radix guest can fail or have a way to report failure.
- * kvmhv_run_single_vcpu() relies on this fact.
*/
static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu)
{
@@ -4258,8 +4258,15 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
vc->runner = vcpu;
/* See if the MMU is ready to go */
- if (!kvm->arch.mmu_ready)
- kvmhv_setup_mmu(vcpu);
+ if (!kvm->arch.mmu_ready) {
+ r = kvmhv_setup_mmu(vcpu);
+ if (r) {
+ run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ run->fail_entry.hardware_entry_failure_reason = 0;
+ vcpu->arch.ret = r;
+ return r;
+ }
+ }
if (need_resched())
cond_resched();
@@ -4272,7 +4279,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
preempt_disable();
pcpu = smp_processor_id();
vc->pcpu = pcpu;
- kvmppc_prepare_radix_vcpu(vcpu, pcpu);
+ if (kvm_is_radix(kvm))
+ kvmppc_prepare_radix_vcpu(vcpu, pcpu);
local_irq_disable();
hard_irq_disable();
@@ -4472,7 +4480,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
do {
- if (kvm_is_radix(kvm))
+ if (radix_enabled())
r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
vcpu->arch.vcore->lpcr);
else
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index cb2978c431c8..9b093167dd79 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -4,6 +4,7 @@
#include <asm/asm-prototypes.h>
#include <asm/dbell.h>
#include <asm/kvm_ppc.h>
+#include <asm/ppc-opcode.h>
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
@@ -55,6 +56,50 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator
#define accumulate_time(vcpu, next) do {} while (0)
#endif
+static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev)
+{
+ asm volatile("slbmfev %0,%1" : "=r" (*slbev) : "r" (idx));
+ asm volatile("slbmfee %0,%1" : "=r" (*slbee) : "r" (idx));
+}
+
+static inline void __mtslb(u64 slbee, u64 slbev)
+{
+ asm volatile("slbmte %0,%1" :: "r" (slbev), "r" (slbee));
+}
+
+static inline void mtslb(unsigned int idx, u64 slbee, u64 slbev)
+{
+ BUG_ON((slbee & 0xfff) != idx);
+
+ __mtslb(slbee, slbev);
+}
+
+static inline void slb_invalidate(unsigned int ih)
+{
+ asm volatile(PPC_SLBIA(%0) :: "i"(ih));
+}
+
+/*
+ * Malicious or buggy radix guests may have inserted SLB entries
+ * (only 0..3 because radix always runs with UPRT=1), so these must
+ * be cleared here to avoid side-channels. slbmte is used rather
+ * than slbia, as it won't clear cached translations.
+ */
+static void radix_clear_slb(void)
+{
+ u64 slbee, slbev;
+ int i;
+
+ for (i = 0; i < 4; i++) {
+ mfslb(i, &slbee, &slbev);
+ if (unlikely(slbee || slbev)) {
+ slbee = i;
+ slbev = 0;
+ mtslb(i, slbee, slbev);
+ }
+ }
+}
+
static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -80,6 +125,31 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6
kvmppc_check_need_tlb_flush(kvm, vc->pcpu, nested);
}
+static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr)
+{
+ struct kvm_nested_guest *nested = vcpu->arch.nested;
+ u32 lpid;
+ int i;
+
+ BUG_ON(nested);
+
+ lpid = kvm->arch.lpid;
+
+ mtspr(SPRN_LPID, lpid);
+ mtspr(SPRN_LPCR, lpcr);
+ mtspr(SPRN_PID, vcpu->arch.pid);
+
+ for (i = 0; i < vcpu->arch.slb_max; i++)
+ __mtslb(vcpu->arch.slb[i].orige, vcpu->arch.slb[i].origv);
+
+ isync();
+
+ /*
+ * TLBIEL is not virtualised for HPT guests, so check_need_tlb_flush
+ * is not required here.
+ */
+}
+
static void switch_mmu_to_host_radix(struct kvm *kvm, u32 pid)
{
isync();
@@ -91,37 +161,30 @@ static void switch_mmu_to_host_radix(struct kvm *kvm, u32 pid)
isync();
}
-static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev)
-{
- asm volatile("slbmfev %0,%1" : "=r" (*slbev) : "r" (idx));
- asm volatile("slbmfee %0,%1" : "=r" (*slbee) : "r" (idx));
-}
-
-static inline void mtslb(unsigned int idx, u64 slbee, u64 slbev)
-{
- BUG_ON((slbee & 0xfff) != idx);
-
- asm volatile("slbmte %0,%1" :: "r" (slbev), "r" (slbee));
-}
-
-/*
- * Malicious or buggy radix guests may have inserted SLB entries
- * (only 0..3 because radix always runs with UPRT=1), so these must
- * be cleared here to avoid side-channels. slbmte is used rather
- * than slbia, as it won't clear cached translations.
- */
-static void radix_clear_slb(void)
+static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu)
{
- u64 slbee, slbev;
- int i;
+ if (kvm_is_radix(kvm)) {
+ radix_clear_slb();
+ } else {
+ int i;
+ int nr = 0;
- for (i = 0; i < 4; i++) {
- mfslb(i, &slbee, &slbev);
- if (unlikely(slbee || slbev)) {
- slbee = i;
- slbev = 0;
- mtslb(i, slbee, slbev);
+ /*
+ * This must run before switching to host (radix host can't
+ * access all SLBs).
+ */
+ for (i = 0; i < vcpu->arch.slb_nr; i++) {
+ u64 slbee, slbev;
+ mfslb(i, &slbee, &slbev);
+ if (slbee & SLB_ESID_V) {
+ vcpu->arch.slb[nr].orige = slbee | i;
+ vcpu->arch.slb[nr].origv = slbev;
+ nr++;
+ }
}
+ vcpu->arch.slb_max = nr;
+ mtslb(0, 0, 0);
+ slb_invalidate(6);
}
}
@@ -229,10 +292,18 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_AMOR, ~0UL);
- if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
- __mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+ local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST_HV_FAST;
+ if (kvm_is_radix(kvm)) {
+ if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ __mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+ switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
+ if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ __mtmsrd(0, 1); /* clear RI */
- switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
+ } else {
+ __mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+ switch_mmu_to_guest_hpt(kvm, vcpu, lpcr);
+ }
/*
* P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
@@ -240,9 +311,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDEC, hdec);
- if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
- __mtmsrd(0, 1); /* clear RI */
-
mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
@@ -250,10 +318,7 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
accumulate_time(vcpu, &vcpu->arch.guest_time);
- local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST_HV_FAST;
kvmppc_p9_enter_guest(vcpu);
- // Radix host and guest means host never runs with guest MMU state
- local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE;
accumulate_time(vcpu, &vcpu->arch.rm_intr);
@@ -354,8 +419,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
#endif
}
- radix_clear_slb();
-
accumulate_time(vcpu, &vcpu->arch.rm_exit);
/* Advance host PURR/SPURR by the amount used by guest */
@@ -389,11 +452,14 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_DAWRX1, host_dawrx1);
}
- /*
- * Since this is radix, do a eieio; tlbsync; ptesync sequence in
- * case we interrupted the guest between a tlbie and a ptesync.
- */
- asm volatile("eieio; tlbsync; ptesync");
+ if (kvm_is_radix(kvm)) {
+ /*
+ * Since this is radix, do a eieio; tlbsync; ptesync sequence
+ * in case we interrupted the guest between a tlbie and a
+ * ptesync.
+ */
+ asm volatile("eieio; tlbsync; ptesync");
+ }
/*
* cp_abort is required if the processor supports local copy-paste
@@ -420,7 +486,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
/* HDEC must be at least as large as DEC, so decrementer_max fits */
mtspr(SPRN_HDEC, decrementer_max);
+ save_clear_guest_mmu(kvm, vcpu);
switch_mmu_to_host_radix(kvm, host_pidr);
+ local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE;
/*
* If we are in real mode, only switch MMU on after the MMU is
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 8cc73abbf42b..f487ebb3a70a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -57,6 +57,10 @@ static int global_invalidates(struct kvm *kvm)
else
global = 1;
+ /* LPID has been switched to host if in virt mode so can't do local */
+ if (!global && (mfmsr() & (MSR_IR|MSR_DR)))
+ global = 1;
+
if (!global) {
/* any other core might now have stale TLB entries... */
smp_wmb();
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 7a0e26c9fab9..acbe31d92efc 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -885,14 +885,11 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
cmpdi r3, 512 /* 1 microsecond */
blt hdec_soon
- /* For hash guest, clear out and reload the SLB */
-BEGIN_MMU_FTR_SECTION
- /* Radix host won't have populated the SLB, so no need to clear */
+ /* Clear out and reload the SLB */
li r6, 0
slbmte r6, r6
PPC_SLBIA(6)
ptesync
-END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
/* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
lwz r5,VCPU_SLB_MAX(r4)
@@ -1394,9 +1391,6 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
stw r5,VCPU_SLB_MAX(r9)
/* load host SLB entries */
-BEGIN_MMU_FTR_SECTION
- b guest_bypass
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
ld r8,PACA_SLBSHADOWPTR(r13)
.rept SLB_NUM_BOLTED
@@ -3148,10 +3142,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
PPC_SLBIA(6)
ptesync
-BEGIN_MMU_FTR_SECTION
- b 4f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
-
/* load host SLB entries */
ld r8, PACA_SLBSHADOWPTR(r13)
.rept SLB_NUM_BOLTED
@@ -3165,7 +3155,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
3: addi r8, r8, 16
.endr
-4: lwz r7, KVM_HOST_LPID(r10)
+ lwz r7, KVM_HOST_LPID(r10)
mtspr SPRN_LPID, r7
mtspr SPRN_PID, r0
ld r8, KVM_HOST_LPCR(r10)
--
2.23.0
^ permalink raw reply related
* [PATCH v5 47/48] KVM: PPC: Book3S HV P9: implement hash host / hash guest support
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
This additionally has to save and restore the host SLB, and also
ensure that the MMU is off while switching into the guest SLB.
P9 and later CPUs now always go via the P9 path.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_64_entry.S | 6 +++++
arch/powerpc/kvm/book3s_hv.c | 4 ++-
arch/powerpc/kvm/book3s_hv_interrupt.c | 35 ++++++++++++++++++++++----
3 files changed, 39 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 45743f5aff64..ee6345266280 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -347,6 +347,12 @@ kvmppc_p9_exit_interrupt:
* effort for a small bit of code. Lots of other things to do first.
*/
kvmppc_p9_bad_interrupt:
+BEGIN_MMU_FTR_SECTION
+ /*
+ * Hash host doesn't try to recover MMU (requires host SLB reload)
+ */
+ b .
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
/*
* Set GUEST_MODE_NONE so the handler won't branch to KVM, and clear
* MSR_RI in r12 ([H]SRR1) so the handler won't try to return.
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 728e98bb61eb..a25583204829 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4480,7 +4480,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
do {
- if (radix_enabled())
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
vcpu->arch.vcore->lpcr);
else
@@ -5569,6 +5569,8 @@ static int kvmhv_enable_nested(struct kvm *kvm)
return -EPERM;
if (!cpu_has_feature(CPU_FTR_ARCH_300))
return -ENODEV;
+ if (!radix_enabled())
+ return -ENODEV;
/* kvm == NULL means the caller is testing if the capability exists */
if (kvm)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index 9b093167dd79..f57abd3d0c47 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -150,7 +150,7 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64
*/
}
-static void switch_mmu_to_host_radix(struct kvm *kvm, u32 pid)
+static void switch_mmu_to_host(struct kvm *kvm, u32 pid)
{
isync();
mtspr(SPRN_PID, pid);
@@ -159,6 +159,23 @@ static void switch_mmu_to_host_radix(struct kvm *kvm, u32 pid)
isync();
mtspr(SPRN_LPCR, kvm->arch.host_lpcr);
isync();
+
+ if (!radix_enabled())
+ slb_restore_bolted_realmode();
+}
+
+static void save_clear_host_mmu(struct kvm *kvm)
+{
+ if (!radix_enabled()) {
+ /*
+ * Hash host could save and restore host SLB entries to
+ * reduce SLB fault overheads of VM exits, but for now the
+ * existing code clears all entries and restores just the
+ * bolted ones when switching back to host.
+ */
+ mtslb(0, 0, 0);
+ slb_invalidate(6);
+ }
}
static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu)
@@ -293,15 +310,23 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_AMOR, ~0UL);
local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST_HV_FAST;
+
+ /*
+ * Hash host, hash guest, or radix guest with prefetch bug, all have
+ * to disable the MMU before switching to guest MMU state.
+ */
+ if (!radix_enabled() || !kvm_is_radix(kvm) ||
+ cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ __mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+
+ save_clear_host_mmu(kvm);
+
if (kvm_is_radix(kvm)) {
- if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
- __mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
__mtmsrd(0, 1); /* clear RI */
} else {
- __mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
switch_mmu_to_guest_hpt(kvm, vcpu, lpcr);
}
@@ -487,7 +512,7 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_HDEC, decrementer_max);
save_clear_guest_mmu(kvm, vcpu);
- switch_mmu_to_host_radix(kvm, host_pidr);
+ switch_mmu_to_host(kvm, host_pidr);
local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE;
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v5 48/48] KVM: PPC: Book3S HV: remove ISA v3.0 and v3.1 support from P7/8 path
From: Nicholas Piggin @ 2021-04-01 15:03 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210401150325.442125-1-npiggin@gmail.com>
POWER9 and later processors always go via the P9 guest entry path now.
Remove the remaining support from the P7/8 path.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 62 ++--
arch/powerpc/kvm/book3s_hv_interrupts.S | 9 +-
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 404 +-----------------------
arch/powerpc/platforms/powernv/idle.c | 52 +--
4 files changed, 39 insertions(+), 488 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a25583204829..fb0113e31e86 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -130,9 +130,6 @@ static inline bool nesting_enabled(struct kvm *kvm)
return kvm->arch.nested_enable && kvm_is_radix(kvm);
}
-/* If set, the threads on each CPU core have to be in the same MMU mode */
-static bool no_mixing_hpt_and_radix __read_mostly;
-
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
/*
@@ -3110,9 +3107,6 @@ static void prepare_threads(struct kvmppc_vcore *vc)
for_each_runnable_thread(i, vcpu, vc) {
if (signal_pending(vcpu->arch.run_task))
vcpu->arch.ret = -EINTR;
- else if (no_mixing_hpt_and_radix &&
- kvm_is_radix(vc->kvm) != radix_enabled())
- vcpu->arch.ret = -EINVAL;
else if (vcpu->arch.vpa.update_pending ||
vcpu->arch.slb_shadow.update_pending ||
vcpu->arch.dtl.update_pending)
@@ -3319,6 +3313,9 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
int trap;
bool is_power8;
+ if (WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)))
+ return;
+
/*
* Remove from the list any threads that have a signal pending
* or need a VPA update done
@@ -3346,9 +3343,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
* Make sure we are running on primary threads, and that secondary
* threads are offline. Also check if the number of threads in this
* guest are greater than the current system threads per guest.
- * On POWER9, we need to be not in independent-threads mode if
- * this is a HPT guest on a radix host machine where the
- * CPU threads may not be in different MMU modes.
*/
if ((controlled_threads > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
@@ -3372,18 +3366,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
if (vc->num_threads < target_threads)
collect_piggybacks(&core_info, target_threads);
- /*
- * On radix, arrange for TLB flushing if necessary.
- * This has to be done before disabling interrupts since
- * it uses smp_call_function().
- */
- pcpu = smp_processor_id();
- if (kvm_is_radix(vc->kvm)) {
- for (sub = 0; sub < core_info.n_subcores; ++sub)
- for_each_runnable_thread(i, vcpu, core_info.vc[sub])
- kvmppc_prepare_radix_vcpu(vcpu, pcpu);
- }
-
/*
* Hard-disable interrupts, and check resched flag and signals.
* If we need to reschedule or deliver a signal, clean up
@@ -3416,8 +3398,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
cmd_bit = stat_bit = 0;
split = core_info.n_subcores;
sip = NULL;
- is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S)
- && !cpu_has_feature(CPU_FTR_ARCH_300);
+ is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S);
if (split > 1) {
sip = &split_info;
@@ -3711,8 +3692,7 @@ static inline bool hcall_is_xics(unsigned long req)
}
/*
- * Virtual-mode guest entry for POWER9 and later when the host and
- * guest are both using the radix MMU. The LPIDR has already been set.
+ * Guest entry for POWER9 and later CPUs.
*/
static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
unsigned long lpcr)
@@ -5732,11 +5712,25 @@ static int kvmhv_enable_dawr1(struct kvm *kvm)
static bool kvmppc_hash_v3_possible(void)
{
- if (radix_enabled() && no_mixing_hpt_and_radix)
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
return false;
- return cpu_has_feature(CPU_FTR_ARCH_300) &&
- cpu_has_feature(CPU_FTR_HVMODE);
+ if (!cpu_has_feature(CPU_FTR_HVMODE))
+ return false;
+
+ /*
+ * POWER9 chips before version 2.02 can't have some threads in
+ * HPT mode and some in radix mode on the same core.
+ */
+ if (radix_enabled()) {
+ unsigned int pvr = mfspr(SPRN_PVR);
+ if ((pvr >> 16) == PVR_POWER9 &&
+ (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) ||
+ ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101)))
+ return false;
+ }
+
+ return true;
}
static struct kvmppc_ops kvm_ops_hv = {
@@ -5880,18 +5874,6 @@ static int kvmppc_book3s_init_hv(void)
if (kvmppc_radix_possible())
r = kvmppc_radix_init();
- /*
- * POWER9 chips before version 2.02 can't have some threads in
- * HPT mode and some in radix mode on the same core.
- */
- if (cpu_has_feature(CPU_FTR_ARCH_300)) {
- unsigned int pvr = mfspr(SPRN_PVR);
- if ((pvr >> 16) == PVR_POWER9 &&
- (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) ||
- ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101)))
- no_mixing_hpt_and_radix = true;
- }
-
r = kvmppc_uvmem_init();
if (r < 0)
pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r);
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 327417d79eac..4444f83cb133 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -58,7 +58,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
/*
* Put whatever is in the decrementer into the
* hypervisor decrementer.
- * Because of a hardware deviation in P8 and P9,
+ * Because of a hardware deviation in P8,
* we need to set LPCR[HDICE] before writing HDEC.
*/
ld r5, HSTATE_KVM_VCORE(r13)
@@ -67,15 +67,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
ori r8, r9, LPCR_HDICE
mtspr SPRN_LPCR, r8
isync
- andis. r0, r9, LPCR_LD@h
mfspr r8,SPRN_DEC
mftb r7
-BEGIN_FTR_SECTION
- /* On POWER9, don't sign-extend if host LPCR[LD] bit is set */
- bne 32f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
extsw r8,r8
-32: mtspr SPRN_HDEC,r8
+ mtspr SPRN_HDEC,r8
add r8,r8,r7
std r8,HSTATE_DECEXP(r13)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index acbe31d92efc..0424d62631ad 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -25,7 +25,6 @@
#include <asm/export.h>
#include <asm/tm.h>
#include <asm/opal.h>
-#include <asm/xive-regs.h>
#include <asm/thread_info.h>
#include <asm/asm-compat.h>
#include <asm/feature-fixups.h>
@@ -34,9 +33,7 @@
/* Sign-extend HDEC if not on POWER9 */
#define EXTEND_HDEC(reg) \
-BEGIN_FTR_SECTION; \
- extsw reg, reg; \
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+ extsw reg, reg
/* Values in HSTATE_NAPPING(r13) */
#define NAPPING_CEDE 1
@@ -56,8 +53,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
#define STACK_SLOT_HFSCR (SFS-72)
#define STACK_SLOT_AMR (SFS-80)
#define STACK_SLOT_UAMOR (SFS-88)
-#define STACK_SLOT_DAWR1 (SFS-96)
-#define STACK_SLOT_DAWRX1 (SFS-104)
/*
* Call kvmppc_hv_entry in real mode.
@@ -333,7 +328,6 @@ kvm_secondary_got_guest:
LOAD_REG_ADDR(r6, decrementer_max)
ld r6, 0(r6)
mtspr SPRN_HDEC, r6
-BEGIN_FTR_SECTION
/* and set per-LPAR registers, if doing dynamic micro-threading */
ld r6, HSTATE_SPLIT_MODE(r13)
cmpdi r6, 0
@@ -345,7 +339,6 @@ BEGIN_FTR_SECTION
ld r0, KVM_SPLIT_LDBAR(r6)
mtspr SPRN_LDBAR, r0
isync
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
63:
/* Order load of vcpu after load of vcore */
lwsync
@@ -416,7 +409,6 @@ kvm_no_guest:
blr
53:
-BEGIN_FTR_SECTION
HMT_LOW
ld r5, HSTATE_KVM_VCORE(r13)
cmpdi r5, 0
@@ -431,14 +423,6 @@ BEGIN_FTR_SECTION
b kvm_unsplit_nap
60: HMT_MEDIUM
b kvm_secondary_got_guest
-FTR_SECTION_ELSE
- HMT_LOW
- ld r5, HSTATE_KVM_VCORE(r13)
- cmpdi r5, 0
- beq kvm_no_guest
- HMT_MEDIUM
- b kvm_secondary_got_guest
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
54: li r0, KVM_HWTHREAD_IN_KVM
stb r0, HSTATE_HWTHREAD_STATE(r13)
@@ -564,13 +548,11 @@ kvmppc_hv_entry:
bne 10f
lwz r7,KVM_LPID(r9)
-BEGIN_FTR_SECTION
ld r6,KVM_SDR1(r9)
li r0,LPID_RSVD /* switch to reserved LPID */
mtspr SPRN_LPID,r0
ptesync
mtspr SPRN_SDR1,r6 /* switch to partition page table */
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
mtspr SPRN_LPID,r7
isync
@@ -650,16 +632,6 @@ kvmppc_got_guest:
mtspr SPRN_SPURR,r8
/* Save host values of some registers */
-BEGIN_FTR_SECTION
- mfspr r5, SPRN_TIDR
- mfspr r6, SPRN_PSSCR
- mfspr r7, SPRN_PID
- std r5, STACK_SLOT_TID(r1)
- std r6, STACK_SLOT_PSSCR(r1)
- std r7, STACK_SLOT_PID(r1)
- mfspr r5, SPRN_HFSCR
- std r5, STACK_SLOT_HFSCR(r1)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
BEGIN_FTR_SECTION
mfspr r5, SPRN_CIABR
mfspr r6, SPRN_DAWR0
@@ -670,12 +642,6 @@ BEGIN_FTR_SECTION
std r7, STACK_SLOT_DAWRX0(r1)
std r8, STACK_SLOT_IAMR(r1)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
- mfspr r6, SPRN_DAWR1
- mfspr r7, SPRN_DAWRX1
- std r6, STACK_SLOT_DAWR1(r1)
- std r7, STACK_SLOT_DAWRX1(r1)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S | CPU_FTR_DAWR1)
mfspr r5, SPRN_AMR
std r5, STACK_SLOT_AMR(r1)
@@ -693,13 +659,9 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Branch around the call if both CPU_FTR_TM and
- * CPU_FTR_P9_TM_HV_ASSIST are off.
- */
BEGIN_FTR_SECTION
b 91f
-END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
*/
@@ -766,12 +728,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
ld r6, VCPU_DAWRX0(r4)
mtspr SPRN_DAWR0, r5
mtspr SPRN_DAWRX0, r6
-BEGIN_FTR_SECTION
- ld r5, VCPU_DAWR1(r4)
- ld r6, VCPU_DAWRX1(r4)
- mtspr SPRN_DAWR1, r5
- mtspr SPRN_DAWRX1, r6
-END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
1:
ld r7, VCPU_CIABR(r4)
ld r8, VCPU_TAR(r4)
@@ -789,7 +745,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
mtspr SPRN_BESCR, r6
mtspr SPRN_PID, r7
mtspr SPRN_WORT, r8
-BEGIN_FTR_SECTION
/* POWER8-only registers */
ld r5, VCPU_TCSCR(r4)
ld r6, VCPU_ACOP(r4)
@@ -800,18 +755,6 @@ BEGIN_FTR_SECTION
mtspr SPRN_CSIGR, r7
mtspr SPRN_TACR, r8
nop
-FTR_SECTION_ELSE
- /* POWER9-only registers */
- ld r5, VCPU_TID(r4)
- ld r6, VCPU_PSSCR(r4)
- lbz r8, HSTATE_FAKE_SUSPEND(r13)
- oris r6, r6, PSSCR_EC@h /* This makes stop trap to HV */
- rldimi r6, r8, PSSCR_FAKE_SUSPEND_LG, 63 - PSSCR_FAKE_SUSPEND_LG
- ld r7, VCPU_HFSCR(r4)
- mtspr SPRN_TIDR, r5
- mtspr SPRN_PSSCR, r6
- mtspr SPRN_HFSCR, r7
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
8:
ld r5, VCPU_SPRG0(r4)
@@ -904,93 +847,9 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
bdnz 1b
9:
-#ifdef CONFIG_KVM_XICS
- /* We are entering the guest on that thread, push VCPU to XIVE */
- ld r11, VCPU_XIVE_SAVED_STATE(r4)
- li r9, TM_QW1_OS
- lwz r8, VCPU_XIVE_CAM_WORD(r4)
- cmpwi r8, 0
- beq no_xive
- li r7, TM_QW1_OS + TM_WORD2
- mfmsr r0
- andi. r0, r0, MSR_DR /* in real mode? */
- beq 2f
- ld r10, HSTATE_XIVE_TIMA_VIRT(r13)
- cmpldi cr1, r10, 0
- beq cr1, no_xive
- eieio
- stdx r11,r9,r10
- stwx r8,r7,r10
- b 3f
-2: ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
- cmpldi cr1, r10, 0
- beq cr1, no_xive
- eieio
- stdcix r11,r9,r10
- stwcix r8,r7,r10
-3: li r9, 1
- stb r9, VCPU_XIVE_PUSHED(r4)
- eieio
-
- /*
- * We clear the irq_pending flag. There is a small chance of a
- * race vs. the escalation interrupt happening on another
- * processor setting it again, but the only consequence is to
- * cause a spurrious wakeup on the next H_CEDE which is not an
- * issue.
- */
- li r0,0
- stb r0, VCPU_IRQ_PENDING(r4)
-
- /*
- * In single escalation mode, if the escalation interrupt is
- * on, we mask it.
- */
- lbz r0, VCPU_XIVE_ESC_ON(r4)
- cmpwi cr1, r0,0
- beq cr1, 1f
- li r9, XIVE_ESB_SET_PQ_01
- beq 4f /* in real mode? */
- ld r10, VCPU_XIVE_ESC_VADDR(r4)
- ldx r0, r10, r9
- b 5f
-4: ld r10, VCPU_XIVE_ESC_RADDR(r4)
- ldcix r0, r10, r9
-5: sync
-
- /* We have a possible subtle race here: The escalation interrupt might
- * have fired and be on its way to the host queue while we mask it,
- * and if we unmask it early enough (re-cede right away), there is
- * a theorical possibility that it fires again, thus landing in the
- * target queue more than once which is a big no-no.
- *
- * Fortunately, solving this is rather easy. If the above load setting
- * PQ to 01 returns a previous value where P is set, then we know the
- * escalation interrupt is somewhere on its way to the host. In that
- * case we simply don't clear the xive_esc_on flag below. It will be
- * eventually cleared by the handler for the escalation interrupt.
- *
- * Then, when doing a cede, we check that flag again before re-enabling
- * the escalation interrupt, and if set, we abort the cede.
- */
- andi. r0, r0, XIVE_ESB_VAL_P
- bne- 1f
-
- /* Now P is 0, we can clear the flag */
- li r0, 0
- stb r0, VCPU_XIVE_ESC_ON(r4)
-1:
-no_xive:
-#endif /* CONFIG_KVM_XICS */
-
deliver_guest_interrupt: /* r4 = vcpu, r13 = paca */
/* Check if we can deliver an external or decrementer interrupt now */
ld r0, VCPU_PENDING_EXC(r4)
-BEGIN_FTR_SECTION
- /* On POWER9, also check for emulated doorbell interrupt */
- lbz r3, VCPU_DBELL_REQ(r4)
- or r0, r0, r3
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
cmpdi r0, 0
beq 71f
mr r3, r4
@@ -1063,12 +922,6 @@ BEGIN_FTR_SECTION
mtspr SPRN_PPR, r0
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-/* Move canary into DSISR to check for later */
-BEGIN_FTR_SECTION
- li r0, 0x7fff
- mtspr SPRN_HDSISR, r0
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
ld r6, VCPU_KVM(r4)
lbz r7, KVM_SECURE_GUEST(r6)
cmpdi r7, 0
@@ -1284,14 +1137,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/* Hypervisor doorbell - exit only if host IPI flag set */
cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL
bne 3f
-BEGIN_FTR_SECTION
- PPC_MSGSYNC
- lwsync
- /* always exit if we're running a nested guest */
- ld r0, VCPU_NESTED(r9)
- cmpdi r0, 0
- bne guest_exit_cont
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
lbz r0, HSTATE_HOST_IPI(r13)
cmpwi r0, 0
beq maybe_reenter_guest
@@ -1321,43 +1166,6 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
mr r4, r9
bl kvmhv_accumulate_time
#endif
-#ifdef CONFIG_KVM_XICS
- /* We are exiting, pull the VP from the XIVE */
- lbz r0, VCPU_XIVE_PUSHED(r9)
- cmpwi cr0, r0, 0
- beq 1f
- li r7, TM_SPC_PULL_OS_CTX
- li r6, TM_QW1_OS
- mfmsr r0
- andi. r0, r0, MSR_DR /* in real mode? */
- beq 2f
- ld r10, HSTATE_XIVE_TIMA_VIRT(r13)
- cmpldi cr0, r10, 0
- beq 1f
- /* First load to pull the context, we ignore the value */
- eieio
- lwzx r11, r7, r10
- /* Second load to recover the context state (Words 0 and 1) */
- ldx r11, r6, r10
- b 3f
-2: ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
- cmpldi cr0, r10, 0
- beq 1f
- /* First load to pull the context, we ignore the value */
- eieio
- lwzcix r11, r7, r10
- /* Second load to recover the context state (Words 0 and 1) */
- ldcix r11, r6, r10
-3: std r11, VCPU_XIVE_SAVED_STATE(r9)
- /* Fixup some of the state for the next load */
- li r10, 0
- li r0, 0xff
- stb r10, VCPU_XIVE_PUSHED(r9)
- stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
- stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
- eieio
-1:
-#endif /* CONFIG_KVM_XICS */
/*
* Possibly flush the link stack here, before we do a blr in
@@ -1412,12 +1220,6 @@ guest_bypass:
ld r3, HSTATE_KVM_VCORE(r13)
mfspr r5,SPRN_DEC
mftb r6
- /* On P9, if the guest has large decr enabled, don't sign extend */
-BEGIN_FTR_SECTION
- ld r4, VCORE_LPCR(r3)
- andis. r4, r4, LPCR_LD@h
- bne 16f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
extsw r5,r5
16: add r5,r5,r6
/* r5 is a guest timebase value here, convert to host TB */
@@ -1491,7 +1293,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
std r6, VCPU_BESCR(r9)
stw r7, VCPU_GUEST_PID(r9)
std r8, VCPU_WORT(r9)
-BEGIN_FTR_SECTION
mfspr r5, SPRN_TCSCR
mfspr r6, SPRN_ACOP
mfspr r7, SPRN_CSIGR
@@ -1500,17 +1301,6 @@ BEGIN_FTR_SECTION
std r6, VCPU_ACOP(r9)
std r7, VCPU_CSIGR(r9)
std r8, VCPU_TACR(r9)
-FTR_SECTION_ELSE
- mfspr r5, SPRN_TIDR
- mfspr r6, SPRN_PSSCR
- std r5, VCPU_TID(r9)
- rldicl r6, r6, 4, 50 /* r6 &= PSSCR_GUEST_VIS */
- rotldi r6, r6, 60
- std r6, VCPU_PSSCR(r9)
- /* Restore host HFSCR value */
- ld r7, STACK_SLOT_HFSCR(r1)
- mtspr SPRN_HFSCR, r7
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
/*
* Restore various registers to 0, where non-zero values
* set by the guest could disrupt the host.
@@ -1518,13 +1308,11 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
li r0, 0
mtspr SPRN_PSPB, r0
mtspr SPRN_WORT, r0
-BEGIN_FTR_SECTION
mtspr SPRN_TCSCR, r0
/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
li r0, 1
sldi r0, r0, 31
mtspr SPRN_MMCRS, r0
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
/* Save and restore AMR, IAMR and UAMOR before turning on the MMU */
ld r8, STACK_SLOT_IAMR(r1)
@@ -1581,13 +1369,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
bl kvmppc_save_fp
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Branch around the call if both CPU_FTR_TM and
- * CPU_FTR_P9_TM_HV_ASSIST are off.
- */
BEGIN_FTR_SECTION
b 91f
-END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
*/
@@ -1633,28 +1417,6 @@ BEGIN_FTR_SECTION
mtspr SPRN_DAWR0, r6
mtspr SPRN_DAWRX0, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
- ld r6, STACK_SLOT_DAWR1(r1)
- ld r7, STACK_SLOT_DAWRX1(r1)
- mtspr SPRN_DAWR1, r6
- mtspr SPRN_DAWRX1, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S | CPU_FTR_DAWR1)
-BEGIN_FTR_SECTION
- ld r5, STACK_SLOT_TID(r1)
- ld r6, STACK_SLOT_PSSCR(r1)
- ld r7, STACK_SLOT_PID(r1)
- mtspr SPRN_TIDR, r5
- mtspr SPRN_PSSCR, r6
- mtspr SPRN_PID, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
- /*
- * cp_abort is required if the processor supports local copy-paste
- * to clear the copy buffer that was under control of the guest.
- */
-BEGIN_FTR_SECTION
- PPC_CP_ABORT
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
/*
* POWER7/POWER8 guest -> host partition switch code.
@@ -1691,13 +1453,11 @@ kvmhv_switch_to_host:
/* Primary thread switches back to host partition */
lwz r7,KVM_HOST_LPID(r4)
-BEGIN_FTR_SECTION
ld r6,KVM_HOST_SDR1(r4)
li r8,LPID_RSVD /* switch to reserved LPID */
mtspr SPRN_LPID,r8
ptesync
mtspr SPRN_SDR1,r6 /* switch to host page table */
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
mtspr SPRN_LPID,r7
isync
@@ -1908,20 +1668,11 @@ kvmppc_tm_emul:
kvmppc_hdsi:
mfspr r4, SPRN_HDAR
mfspr r6, SPRN_HDSISR
-BEGIN_FTR_SECTION
- /* Look for DSISR canary. If we find it, retry instruction */
- cmpdi r6, 0x7fff
- beq 6f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
/* HPTE not found fault or protection fault? */
andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
beq 1f /* if not, send it to the guest */
andi. r0, r11, MSR_DR /* data relocation enabled? */
beq 3f
-BEGIN_FTR_SECTION
- mfspr r5, SPRN_ASDR /* on POWER9, use ASDR to get VSID */
- b 4f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
clrrdi r0, r4, 28
PPC_SLBFEE_DOT(R5, R0) /* if so, look up SLB */
li r0, BOOK3S_INTERRUPT_DATA_SEGMENT
@@ -1998,10 +1749,6 @@ kvmppc_hisi:
beq 1f
andi. r0, r11, MSR_IR /* instruction relocation enabled? */
beq 3f
-BEGIN_FTR_SECTION
- mfspr r5, SPRN_ASDR /* on POWER9, use ASDR to get VSID */
- b 4f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
clrrdi r0, r10, 28
PPC_SLBFEE_DOT(R5, R0) /* if so, look up SLB */
li r0, BOOK3S_INTERRUPT_INST_SEGMENT
@@ -2049,10 +1796,6 @@ hcall_try_real_mode:
andi. r0,r11,MSR_PR
/* sc 1 from userspace - reflect to guest syscall */
bne sc_1_fast_return
- /* sc 1 from nested guest - give it to L1 to handle */
- ld r0, VCPU_NESTED(r9)
- cmpdi r0, 0
- bne guest_exit_cont
clrrdi r3,r3,2
cmpldi r3,hcall_real_table_end - hcall_real_table
bge guest_exit_cont
@@ -2448,13 +2191,9 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
bl kvmppc_save_fp
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Branch around the call if both CPU_FTR_TM and
- * CPU_FTR_P9_TM_HV_ASSIST are off.
- */
BEGIN_FTR_SECTION
b 91f
-END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
*/
@@ -2474,15 +2213,8 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
mfspr r3, SPRN_DEC
mfspr r4, SPRN_HDEC
mftb r5
-BEGIN_FTR_SECTION
- /* On P9 check whether the guest has large decrementer mode enabled */
- ld r6, HSTATE_KVM_VCORE(r13)
- ld r6, VCORE_LPCR(r6)
- andis. r6, r6, LPCR_LD@h
- bne 68f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
extsw r3, r3
-68: EXTEND_HDEC(r4)
+ EXTEND_HDEC(r4)
cmpd r3, r4
ble 67f
mtspr SPRN_DEC, r4
@@ -2527,28 +2259,14 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
kvm_nap_sequence: /* desired LPCR value in r5 */
-BEGIN_FTR_SECTION
- /*
- * PSSCR bits: exit criterion = 1 (wakeup based on LPCR at sreset)
- * enable state loss = 1 (allow SMT mode switch)
- * requested level = 0 (just stop dispatching)
- */
- lis r3, (PSSCR_EC | PSSCR_ESL)@h
/* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */
li r4, LPCR_PECE_HVEE@higher
sldi r4, r4, 32
or r5, r5, r4
-FTR_SECTION_ELSE
- li r3, PNV_THREAD_NAP
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
mtspr SPRN_LPCR,r5
isync
-BEGIN_FTR_SECTION
- bl isa300_idle_stop_mayloss
-FTR_SECTION_ELSE
bl isa206_idle_insn_mayloss
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
mfspr r0, SPRN_CTRLF
ori r0, r0, 1
@@ -2567,10 +2285,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
beq kvm_end_cede
cmpwi r0, NAPPING_NOVCPU
beq kvm_novcpu_wakeup
-BEGIN_FTR_SECTION
cmpwi r0, NAPPING_UNSPLIT
beq kvm_unsplit_wakeup
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
twi 31,0,0 /* Nap state must not be zero */
33: mr r4, r3
@@ -2590,13 +2306,9 @@ kvm_end_cede:
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Branch around the call if both CPU_FTR_TM and
- * CPU_FTR_P9_TM_HV_ASSIST are off.
- */
BEGIN_FTR_SECTION
b 91f
-END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
*/
@@ -2686,47 +2398,7 @@ kvm_cede_prodded:
/* we've ceded but we want to give control to the host */
kvm_cede_exit:
ld r9, HSTATE_KVM_VCPU(r13)
-#ifdef CONFIG_KVM_XICS
- /* are we using XIVE with single escalation? */
- ld r10, VCPU_XIVE_ESC_VADDR(r9)
- cmpdi r10, 0
- beq 3f
- li r6, XIVE_ESB_SET_PQ_00
- /*
- * If we still have a pending escalation, abort the cede,
- * and we must set PQ to 10 rather than 00 so that we don't
- * potentially end up with two entries for the escalation
- * interrupt in the XIVE interrupt queue. In that case
- * we also don't want to set xive_esc_on to 1 here in
- * case we race with xive_esc_irq().
- */
- lbz r5, VCPU_XIVE_ESC_ON(r9)
- cmpwi r5, 0
- beq 4f
- li r0, 0
- stb r0, VCPU_CEDED(r9)
- /*
- * The escalation interrupts are special as we don't EOI them.
- * There is no need to use the load-after-store ordering offset
- * to set PQ to 10 as we won't use StoreEOI.
- */
- li r6, XIVE_ESB_SET_PQ_10
- b 5f
-4: li r0, 1
- stb r0, VCPU_XIVE_ESC_ON(r9)
- /* make sure store to xive_esc_on is seen before xive_esc_irq runs */
- sync
-5: /* Enable XIVE escalation */
- mfmsr r0
- andi. r0, r0, MSR_DR /* in real mode? */
- beq 1f
- ldx r0, r10, r6
- b 2f
-1: ld r10, VCPU_XIVE_ESC_RADDR(r9)
- ldcix r0, r10, r6
-2: sync
-#endif /* CONFIG_KVM_XICS */
-3: b guest_exit_cont
+ b guest_exit_cont
/* Try to do machine check recovery in real mode */
machine_check_realmode:
@@ -2803,10 +2475,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
PPC_MSGCLR(6)
/* see if it's a host IPI */
li r3, 1
-BEGIN_FTR_SECTION
- PPC_MSGSYNC
- lwsync
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
lbz r0, HSTATE_HOST_IPI(r13)
cmpwi r0, 0
bnelr
@@ -3115,70 +2783,12 @@ kvmppc_bad_host_intr:
std r3, STACK_FRAME_OVERHEAD-16(r1)
/*
- * On POWER9 do a minimal restore of the MMU and call C code,
- * which will print a message and panic.
* XXX On POWER7 and POWER8, we just spin here since we don't
* know what the other threads are doing (and we don't want to
* coordinate with them) - but at least we now have register state
* in memory that we might be able to look at from another CPU.
*/
-BEGIN_FTR_SECTION
b .
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
- ld r9, HSTATE_KVM_VCPU(r13)
- ld r10, VCPU_KVM(r9)
-
- li r0, 0
- mtspr SPRN_AMR, r0
- mtspr SPRN_IAMR, r0
- mtspr SPRN_CIABR, r0
- mtspr SPRN_DAWRX0, r0
-BEGIN_FTR_SECTION
- mtspr SPRN_DAWRX1, r0
-END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
-
- /* Clear guest SLB. */
- slbmte r0, r0
- PPC_SLBIA(6)
- ptesync
-
- /* load host SLB entries */
- ld r8, PACA_SLBSHADOWPTR(r13)
- .rept SLB_NUM_BOLTED
- li r3, SLBSHADOW_SAVEAREA
- LDX_BE r5, r8, r3
- addi r3, r3, 8
- LDX_BE r6, r8, r3
- andis. r7, r5, SLB_ESID_V@h
- beq 3f
- slbmte r6, r5
-3: addi r8, r8, 16
- .endr
-
- lwz r7, KVM_HOST_LPID(r10)
- mtspr SPRN_LPID, r7
- mtspr SPRN_PID, r0
- ld r8, KVM_HOST_LPCR(r10)
- mtspr SPRN_LPCR, r8
- isync
- li r0, KVM_GUEST_MODE_NONE
- stb r0, HSTATE_IN_GUEST(r13)
-
- /*
- * Turn on the MMU and jump to C code
- */
- bcl 20, 31, .+4
-5: mflr r3
- addi r3, r3, 9f - 5b
- li r4, -1
- rldimi r3, r4, 62, 0 /* ensure 0xc000000000000000 bits are set */
- ld r4, PACAKMSR(r13)
- mtspr SPRN_SRR0, r3
- mtspr SPRN_SRR1, r4
- RFI_TO_KERNEL
-9: addi r3, r1, STACK_FRAME_OVERHEAD
- bl kvmppc_bad_interrupt
- b 9b
/*
* This mimics the MSR transition on IRQ delivery. The new guest MSR is taken
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 999997d9e9a9..528a7e0cf83a 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -604,7 +604,7 @@ struct p9_sprs {
u64 uamor;
};
-static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
+static unsigned long power9_idle_stop(unsigned long psscr)
{
int cpu = raw_smp_processor_id();
int first = cpu_first_thread_sibling(cpu);
@@ -620,8 +620,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
/* EC=ESL=0 case */
- BUG_ON(!mmu_on);
-
/*
* Wake synchronously. SRESET via xscom may still cause
* a 0x100 powersave wakeup with SRR1 reason!
@@ -803,8 +801,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
__slb_restore_bolted_realmode();
out:
- if (mmu_on)
- mtmsr(MSR_KERNEL);
+ mtmsr(MSR_KERNEL);
return srr1;
}
@@ -895,7 +892,7 @@ struct p10_sprs {
*/
};
-static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on)
+static unsigned long power10_idle_stop(unsigned long psscr)
{
int cpu = raw_smp_processor_id();
int first = cpu_first_thread_sibling(cpu);
@@ -909,8 +906,6 @@ static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on)
if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
/* EC=ESL=0 case */
- BUG_ON(!mmu_on);
-
/*
* Wake synchronously. SRESET via xscom may still cause
* a 0x100 powersave wakeup with SRR1 reason!
@@ -991,8 +986,7 @@ static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on)
__slb_restore_bolted_realmode();
out:
- if (mmu_on)
- mtmsr(MSR_KERNEL);
+ mtmsr(MSR_KERNEL);
return srr1;
}
@@ -1002,40 +996,10 @@ static unsigned long arch300_offline_stop(unsigned long psscr)
{
unsigned long srr1;
-#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- __ppc64_runlatch_off();
if (cpu_has_feature(CPU_FTR_ARCH_31))
- srr1 = power10_idle_stop(psscr, true);
+ srr1 = power10_idle_stop(psscr);
else
- srr1 = power9_idle_stop(psscr, true);
- __ppc64_runlatch_on();
-#else
- /*
- * Tell KVM we're entering idle.
- * This does not have to be done in real mode because the P9 MMU
- * is independent per-thread. Some steppings share radix/hash mode
- * between threads, but in that case KVM has a barrier sync in real
- * mode before and after switching between radix and hash.
- *
- * kvm_start_guest must still be called in real mode though, hence
- * the false argument.
- */
- local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE;
-
- __ppc64_runlatch_off();
- if (cpu_has_feature(CPU_FTR_ARCH_31))
- srr1 = power10_idle_stop(psscr, false);
- else
- srr1 = power9_idle_stop(psscr, false);
- __ppc64_runlatch_on();
-
- local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL;
- /* Order setting hwthread_state vs. testing hwthread_req */
- smp_mb();
- if (local_paca->kvm_hstate.hwthread_req)
- srr1 = idle_kvm_start_guest(srr1);
- mtmsr(MSR_KERNEL);
-#endif
+ srr1 = power9_idle_stop(psscr);
return srr1;
}
@@ -1055,9 +1019,9 @@ void arch300_idle_type(unsigned long stop_psscr_val,
__ppc64_runlatch_off();
if (cpu_has_feature(CPU_FTR_ARCH_31))
- srr1 = power10_idle_stop(psscr, true);
+ srr1 = power10_idle_stop(psscr);
else
- srr1 = power9_idle_stop(psscr, true);
+ srr1 = power9_idle_stop(psscr);
__ppc64_runlatch_on();
fini_irq_for_idle_irqsoff();
--
2.23.0
^ permalink raw reply related
* [PATCH 1/1] powerpc/smp: Set numa node before updating mask
From: Srikar Dronamraju @ 2021-04-01 15:42 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Srikar Dronamraju, Peter Zijlstra,
Scott Cheloha, Geetika Moolchandani, Ingo Molnar, linuxppc-dev,
Valentin Schneider
Geethika reported a trace when doing a dlpar CPU add.
------------[ cut here ]------------
WARNING: CPU: 152 PID: 1134 at kernel/sched/topology.c:2057
CPU: 152 PID: 1134 Comm: kworker/152:1 Not tainted 5.12.0-rc5-master #5
Workqueue: events cpuset_hotplug_workfn
NIP: c0000000001cfc14 LR: c0000000001cfc10 CTR: c0000000007e3420
REGS: c0000034a08eb260 TRAP: 0700 Not tainted (5.12.0-rc5-master+)
MSR: 8000000000029033 <SF,EE,ME,IR,DR,RI,LE> CR: 28828422 XER: 00000020
CFAR: c0000000001fd888 IRQMASK: 0 #012GPR00: c0000000001cfc10
c0000034a08eb500 c000000001f35400 0000000000000027 #012GPR04:
c0000035abaa8010 c0000035abb30a00 0000000000000027 c0000035abaa8018
#012GPR08: 0000000000000023 c0000035abaaef48 00000035aa540000
c0000035a49dffe8 #012GPR12: 0000000028828424 c0000035bf1a1c80
0000000000000497 0000000000000004 #012GPR16: c00000000347a258
0000000000000140 c00000000203d468 c000000001a1a490 #012GPR20:
c000000001f9c160 c0000034adf70920 c0000034aec9fd20 0000000100087bd3
#012GPR24: 0000000100087bd3 c0000035b3de09f8 0000000000000030
c0000035b3de09f8 #012GPR28: 0000000000000028 c00000000347a280
c0000034aefe0b00 c0000000010a2a68
NIP [c0000000001cfc14] build_sched_domains+0x6a4/0x1500
LR [c0000000001cfc10] build_sched_domains+0x6a0/0x1500
Call Trace:
[c0000034a08eb500] [c0000000001cfc10] build_sched_domains+0x6a0/0x1500 (unreliable)
[c0000034a08eb640] [c0000000001d1e6c] partition_sched_domains_locked+0x3ec/0x530
[c0000034a08eb6e0] [c0000000002936d4] rebuild_sched_domains_locked+0x524/0xbf0
[c0000034a08eb7e0] [c000000000296bb0] rebuild_sched_domains+0x40/0x70
[c0000034a08eb810] [c000000000296e74] cpuset_hotplug_workfn+0x294/0xe20
[c0000034a08ebc30] [c000000000178dd0] process_one_work+0x300/0x670
[c0000034a08ebd10] [c0000000001791b8] worker_thread+0x78/0x520
[c0000034a08ebda0] [c000000000185090] kthread+0x1a0/0x1b0
[c0000034a08ebe10] [c00000000000ccec] ret_from_kernel_thread+0x5c/0x70
Instruction dump:
7d2903a6 4e800421 e8410018 7f67db78 7fe6fb78 7f45d378 7f84e378 7c681b78
3c62ff1a 3863c6f8 4802dc35 60000000 <0fe00000> 3920fff4 f9210070 e86100a0
---[ end trace 532d9066d3d4d7ec ]---
Some of the per-CPU masks use cpu_cpu_mask as a filter to limit the search
for related CPUs. On a dlpar add of a CPU, update cpu_cpu_mask before
updating the per-CPU masks. This will ensure the cpu_cpu_mask is updated
correctly before its used in setting the masks. Setting the numa_node will
ensure that when cpu_cpu_mask() gets called, the correct node number is
used. This code movement helped fix the above call trace.
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Geetika Moolchandani <Geetika.Moolchandani1@ibm.com>
Reported-by: Geetika Moolchandani <Geetika.Moolchandani1@ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
arch/powerpc/kernel/smp.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 5a4d59a1070d..1a99d75679a8 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1521,6 +1521,9 @@ void start_secondary(void *unused)
vdso_getcpu_init();
#endif
+ set_numa_node(numa_cpu_lookup_table[cpu]);
+ set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
+
/* Update topology CPU masks */
add_cpu_to_masks(cpu);
@@ -1539,9 +1542,6 @@ void start_secondary(void *unused)
shared_caches = true;
}
- set_numa_node(numa_cpu_lookup_table[cpu]);
- set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
-
smp_wmb();
notify_cpu_starting(cpu);
set_cpu_online(cpu, true);
--
2.27.0
^ permalink raw reply related
* [PATCH 02/20] iommu/fsl_pamu: remove fsl_pamu_get_domain_attr
From: Christoph Hellwig @ 2021-04-01 15:52 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210401155256.298656-1-hch@lst.de>
None of the values returned by this function are ever queried. Also
remove the DOMAIN_ATTR_FSL_PAMUV1 enum value that is not otherwise used.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Li Yang <leoyang.li@nxp.com>
---
drivers/iommu/fsl_pamu_domain.c | 30 ------------------------------
include/linux/iommu.h | 4 ----
2 files changed, 34 deletions(-)
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index 53380cf1fa452f..e587ec43f7e750 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -832,35 +832,6 @@ static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
return ret;
}
-static int fsl_pamu_get_domain_attr(struct iommu_domain *domain,
- enum iommu_attr attr_type, void *data)
-{
- struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
- int ret = 0;
-
- switch (attr_type) {
- case DOMAIN_ATTR_FSL_PAMU_STASH:
- memcpy(data, &dma_domain->dma_stash,
- sizeof(struct pamu_stash_attribute));
- break;
- case DOMAIN_ATTR_FSL_PAMU_ENABLE:
- *(int *)data = dma_domain->enabled;
- break;
- case DOMAIN_ATTR_FSL_PAMUV1:
- *(int *)data = DOMAIN_ATTR_FSL_PAMUV1;
- break;
- case DOMAIN_ATTR_WINDOWS:
- *(u32 *)data = dma_domain->win_cnt;
- break;
- default:
- pr_debug("Unsupported attribute type\n");
- ret = -EINVAL;
- break;
- }
-
- return ret;
-}
-
static struct iommu_group *get_device_iommu_group(struct device *dev)
{
struct iommu_group *group;
@@ -987,7 +958,6 @@ static const struct iommu_ops fsl_pamu_ops = {
.domain_window_enable = fsl_pamu_window_enable,
.iova_to_phys = fsl_pamu_iova_to_phys,
.domain_set_attr = fsl_pamu_set_domain_attr,
- .domain_get_attr = fsl_pamu_get_domain_attr,
.probe_device = fsl_pamu_probe_device,
.release_device = fsl_pamu_release_device,
.device_group = fsl_pamu_device_group,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 47c8b318d8f523..52874ae164dd60 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -104,9 +104,6 @@ enum iommu_cap {
* -the actual size of the mapped region of a window must be power
* of 2 starting with 4KB and physical address must be naturally
* aligned.
- * DOMAIN_ATTR_FSL_PAMUV1 corresponds to the above mentioned contraints.
- * The caller can invoke iommu_domain_get_attr to check if the underlying
- * iommu implementation supports these constraints.
*/
enum iommu_attr {
@@ -115,7 +112,6 @@ enum iommu_attr {
DOMAIN_ATTR_WINDOWS,
DOMAIN_ATTR_FSL_PAMU_STASH,
DOMAIN_ATTR_FSL_PAMU_ENABLE,
- DOMAIN_ATTR_FSL_PAMUV1,
DOMAIN_ATTR_NESTING, /* two stages of translation */
DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
DOMAIN_ATTR_IO_PGTABLE_CFG,
--
2.30.1
^ permalink raw reply related
* [PATCH 03/20] iommu/fsl_pamu: remove support for setting DOMAIN_ATTR_GEOMETRY
From: Christoph Hellwig @ 2021-04-01 15:52 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210401155256.298656-1-hch@lst.de>
The default geometry is the same as the one set by qman_port given
that FSL_PAMU depends on having 64-bit physical and thus DMA addresses.
Remove the support to update the geometry and remove the now pointless
geom_size field.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Li Yang <leoyang.li@nxp.com>
---
drivers/iommu/fsl_pamu_domain.c | 55 +++--------------------------
drivers/iommu/fsl_pamu_domain.h | 6 ----
drivers/soc/fsl/qbman/qman_portal.c | 12 -------
3 files changed, 5 insertions(+), 68 deletions(-)
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index e587ec43f7e750..7bd08ddad07779 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -62,7 +62,7 @@ static phys_addr_t get_phys_addr(struct fsl_dma_domain *dma_domain, dma_addr_t i
geom = &dma_domain->iommu_domain.geometry;
- if (!win_cnt || !dma_domain->geom_size) {
+ if (!win_cnt) {
pr_debug("Number of windows/geometry not configured for the domain\n");
return 0;
}
@@ -72,7 +72,7 @@ static phys_addr_t get_phys_addr(struct fsl_dma_domain *dma_domain, dma_addr_t i
dma_addr_t subwin_iova;
u32 wnd;
- subwin_size = dma_domain->geom_size >> ilog2(win_cnt);
+ subwin_size = (geom->aperture_end + 1) >> ilog2(win_cnt);
subwin_iova = iova & ~(subwin_size - 1);
wnd = (subwin_iova - geom->aperture_start) >> ilog2(subwin_size);
win_ptr = &dma_domain->win_arr[wnd];
@@ -234,7 +234,7 @@ static int pamu_set_liodn(int liodn, struct device *dev,
get_ome_index(&omi_index, dev);
window_addr = geom_attr->aperture_start;
- window_size = dma_domain->geom_size;
+ window_size = geom_attr->aperture_end + 1;
spin_lock_irqsave(&iommu_lock, flags);
ret = pamu_disable_liodn(liodn);
@@ -303,7 +303,6 @@ static struct fsl_dma_domain *iommu_alloc_dma_domain(void)
domain->stash_id = ~(u32)0;
domain->snoop_id = ~(u32)0;
domain->win_cnt = pamu_get_max_subwin_cnt();
- domain->geom_size = 0;
INIT_LIST_HEAD(&domain->devices);
@@ -502,7 +501,8 @@ static int fsl_pamu_window_enable(struct iommu_domain *domain, u32 wnd_nr,
return -EINVAL;
}
- win_size = dma_domain->geom_size >> ilog2(dma_domain->win_cnt);
+ win_size = (domain->geometry.aperture_end + 1) >>
+ ilog2(dma_domain->win_cnt);
if (size > win_size) {
pr_debug("Invalid window size\n");
spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
@@ -665,41 +665,6 @@ static void fsl_pamu_detach_device(struct iommu_domain *domain,
pr_debug("missing fsl,liodn property at %pOF\n", dev->of_node);
}
-static int configure_domain_geometry(struct iommu_domain *domain, void *data)
-{
- struct iommu_domain_geometry *geom_attr = data;
- struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
- dma_addr_t geom_size;
- unsigned long flags;
-
- geom_size = geom_attr->aperture_end - geom_attr->aperture_start + 1;
- /*
- * Sanity check the geometry size. Also, we do not support
- * DMA outside of the geometry.
- */
- if (check_size(geom_size, geom_attr->aperture_start) ||
- !geom_attr->force_aperture) {
- pr_debug("Invalid PAMU geometry attributes\n");
- return -EINVAL;
- }
-
- spin_lock_irqsave(&dma_domain->domain_lock, flags);
- if (dma_domain->enabled) {
- pr_debug("Can't set geometry attributes as domain is active\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EBUSY;
- }
-
- /* Copy the domain geometry information */
- memcpy(&domain->geometry, geom_attr,
- sizeof(struct iommu_domain_geometry));
- dma_domain->geom_size = geom_size;
-
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
-
- return 0;
-}
-
/* Set the domain stash attribute */
static int configure_domain_stash(struct fsl_dma_domain *dma_domain, void *data)
{
@@ -769,13 +734,6 @@ static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count)
return -EBUSY;
}
- /* Ensure that the geometry has been set for the domain */
- if (!dma_domain->geom_size) {
- pr_debug("Please configure geometry before setting the number of windows\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EINVAL;
- }
-
/*
* Ensure we have valid window count i.e. it should be less than
* maximum permissible limit and should be a power of two.
@@ -811,9 +769,6 @@ static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
int ret = 0;
switch (attr_type) {
- case DOMAIN_ATTR_GEOMETRY:
- ret = configure_domain_geometry(domain, data);
- break;
case DOMAIN_ATTR_FSL_PAMU_STASH:
ret = configure_domain_stash(dma_domain, data);
break;
diff --git a/drivers/iommu/fsl_pamu_domain.h b/drivers/iommu/fsl_pamu_domain.h
index 2865d42782e802..53d359d66fe577 100644
--- a/drivers/iommu/fsl_pamu_domain.h
+++ b/drivers/iommu/fsl_pamu_domain.h
@@ -17,12 +17,6 @@ struct dma_window {
};
struct fsl_dma_domain {
- /*
- * Indicates the geometry size for the domain.
- * This would be set when the geometry is
- * configured for the domain.
- */
- dma_addr_t geom_size;
/*
* Number of windows assocaited with this domain.
* During domain initialization, it is set to the
diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c
index 5685b67068931a..c958e6310d3094 100644
--- a/drivers/soc/fsl/qbman/qman_portal.c
+++ b/drivers/soc/fsl/qbman/qman_portal.c
@@ -47,7 +47,6 @@ static void portal_set_cpu(struct qm_portal_config *pcfg, int cpu)
#ifdef CONFIG_FSL_PAMU
struct device *dev = pcfg->dev;
int window_count = 1;
- struct iommu_domain_geometry geom_attr;
struct pamu_stash_attribute stash_attr;
int ret;
@@ -56,17 +55,6 @@ static void portal_set_cpu(struct qm_portal_config *pcfg, int cpu)
dev_err(dev, "%s(): iommu_domain_alloc() failed", __func__);
goto no_iommu;
}
- geom_attr.aperture_start = 0;
- geom_attr.aperture_end =
- ((dma_addr_t)1 << min(8 * sizeof(dma_addr_t), (size_t)36)) - 1;
- geom_attr.force_aperture = true;
- ret = iommu_domain_set_attr(pcfg->iommu_domain, DOMAIN_ATTR_GEOMETRY,
- &geom_attr);
- if (ret < 0) {
- dev_err(dev, "%s(): iommu_domain_set_attr() = %d", __func__,
- ret);
- goto out_domain_free;
- }
ret = iommu_domain_set_attr(pcfg->iommu_domain, DOMAIN_ATTR_WINDOWS,
&window_count);
if (ret < 0) {
--
2.30.1
^ permalink raw reply related
* [PATCH 05/20] iommu/fsl_pamu: remove support for multiple windows
From: Christoph Hellwig @ 2021-04-01 15:52 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210401155256.298656-1-hch@lst.de>
The only domains allocated forces use of a single window. Remove all
the code related to multiple window support, as well as the need for
qman_portal to force a single window.
Remove the now unused DOMAIN_ATTR_WINDOWS iommu_attr.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Li Yang <leoyang.li@nxp.com>
---
drivers/iommu/fsl_pamu.c | 264 +-------------------------
drivers/iommu/fsl_pamu.h | 10 +-
drivers/iommu/fsl_pamu_domain.c | 275 +++++-----------------------
drivers/iommu/fsl_pamu_domain.h | 16 +-
drivers/soc/fsl/qbman/qman_portal.c | 7 -
include/linux/iommu.h | 1 -
6 files changed, 60 insertions(+), 513 deletions(-)
diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
index b9a974d9783113..3e1647cd5ad47a 100644
--- a/drivers/iommu/fsl_pamu.c
+++ b/drivers/iommu/fsl_pamu.c
@@ -63,19 +63,6 @@ static const struct of_device_id l3_device_ids[] = {
/* maximum subwindows permitted per liodn */
static u32 max_subwindow_count;
-/* Pool for fspi allocation */
-static struct gen_pool *spaace_pool;
-
-/**
- * pamu_get_max_subwin_cnt() - Return the maximum supported
- * subwindow count per liodn.
- *
- */
-u32 pamu_get_max_subwin_cnt(void)
-{
- return max_subwindow_count;
-}
-
/**
* pamu_get_ppaace() - Return the primary PACCE
* @liodn: liodn PAACT index for desired PAACE
@@ -155,13 +142,6 @@ static unsigned int map_addrspace_size_to_wse(phys_addr_t addrspace_size)
return fls64(addrspace_size) - 2;
}
-/* Derive the PAACE window count encoding for the subwindow count */
-static unsigned int map_subwindow_cnt_to_wce(u32 subwindow_cnt)
-{
- /* window count is 2^(WCE+1) bytes */
- return __ffs(subwindow_cnt) - 1;
-}
-
/*
* Set the PAACE type as primary and set the coherency required domain
* attribute
@@ -174,89 +154,11 @@ static void pamu_init_ppaace(struct paace *ppaace)
PAACE_M_COHERENCE_REQ);
}
-/*
- * Set the PAACE type as secondary and set the coherency required domain
- * attribute.
- */
-static void pamu_init_spaace(struct paace *spaace)
-{
- set_bf(spaace->addr_bitfields, PAACE_AF_PT, PAACE_PT_SECONDARY);
- set_bf(spaace->domain_attr.to_host.coherency_required, PAACE_DA_HOST_CR,
- PAACE_M_COHERENCE_REQ);
-}
-
-/*
- * Return the spaace (corresponding to the secondary window index)
- * for a particular ppaace.
- */
-static struct paace *pamu_get_spaace(struct paace *paace, u32 wnum)
-{
- u32 subwin_cnt;
- struct paace *spaace = NULL;
-
- subwin_cnt = 1UL << (get_bf(paace->impl_attr, PAACE_IA_WCE) + 1);
-
- if (wnum < subwin_cnt)
- spaace = &spaact[paace->fspi + wnum];
- else
- pr_debug("secondary paace out of bounds\n");
-
- return spaace;
-}
-
-/**
- * pamu_get_fspi_and_allocate() - Allocates fspi index and reserves subwindows
- * required for primary PAACE in the secondary
- * PAACE table.
- * @subwin_cnt: Number of subwindows to be reserved.
- *
- * A PPAACE entry may have a number of associated subwindows. A subwindow
- * corresponds to a SPAACE entry in the SPAACT table. Each PAACE entry stores
- * the index (fspi) of the first SPAACE entry in the SPAACT table. This
- * function returns the index of the first SPAACE entry. The remaining
- * SPAACE entries are reserved contiguously from that index.
- *
- * Returns a valid fspi index in the range of 0 - SPAACE_NUMBER_ENTRIES on success.
- * If no SPAACE entry is available or the allocator can not reserve the required
- * number of contiguous entries function returns ULONG_MAX indicating a failure.
- *
- */
-static unsigned long pamu_get_fspi_and_allocate(u32 subwin_cnt)
-{
- unsigned long spaace_addr;
-
- spaace_addr = gen_pool_alloc(spaace_pool, subwin_cnt * sizeof(struct paace));
- if (!spaace_addr)
- return ULONG_MAX;
-
- return (spaace_addr - (unsigned long)spaact) / (sizeof(struct paace));
-}
-
-/* Release the subwindows reserved for a particular LIODN */
-void pamu_free_subwins(int liodn)
-{
- struct paace *ppaace;
- u32 subwin_cnt, size;
-
- ppaace = pamu_get_ppaace(liodn);
- if (!ppaace) {
- pr_debug("Invalid liodn entry\n");
- return;
- }
-
- if (get_bf(ppaace->addr_bitfields, PPAACE_AF_MW)) {
- subwin_cnt = 1UL << (get_bf(ppaace->impl_attr, PAACE_IA_WCE) + 1);
- size = (subwin_cnt - 1) * sizeof(struct paace);
- gen_pool_free(spaace_pool, (unsigned long)&spaact[ppaace->fspi], size);
- set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0);
- }
-}
-
/*
* Function used for updating stash destination for the coressponding
* LIODN.
*/
-int pamu_update_paace_stash(int liodn, u32 subwin, u32 value)
+int pamu_update_paace_stash(int liodn, u32 value)
{
struct paace *paace;
@@ -265,11 +167,6 @@ int pamu_update_paace_stash(int liodn, u32 subwin, u32 value)
pr_debug("Invalid liodn entry\n");
return -ENOENT;
}
- if (subwin) {
- paace = pamu_get_spaace(paace, subwin - 1);
- if (!paace)
- return -ENOENT;
- }
set_bf(paace->impl_attr, PAACE_IA_CID, value);
mb();
@@ -277,31 +174,6 @@ int pamu_update_paace_stash(int liodn, u32 subwin, u32 value)
return 0;
}
-/* Disable a subwindow corresponding to the LIODN */
-int pamu_disable_spaace(int liodn, u32 subwin)
-{
- struct paace *paace;
-
- paace = pamu_get_ppaace(liodn);
- if (!paace) {
- pr_debug("Invalid liodn entry\n");
- return -ENOENT;
- }
- if (subwin) {
- paace = pamu_get_spaace(paace, subwin - 1);
- if (!paace)
- return -ENOENT;
- set_bf(paace->addr_bitfields, PAACE_AF_V, PAACE_V_INVALID);
- } else {
- set_bf(paace->addr_bitfields, PAACE_AF_AP,
- PAACE_AP_PERMS_DENIED);
- }
-
- mb();
-
- return 0;
-}
-
/**
* pamu_config_paace() - Sets up PPAACE entry for specified liodn
*
@@ -314,17 +186,15 @@ int pamu_disable_spaace(int liodn, u32 subwin)
* stashid not defined
* @snoopid: snoop id for hardware coherency -- if ~snoopid == 0 then
* snoopid not defined
- * @subwin_cnt: number of sub-windows
* @prot: window permissions
*
* Returns 0 upon success else error code < 0 returned
*/
int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
u32 omi, unsigned long rpn, u32 snoopid, u32 stashid,
- u32 subwin_cnt, int prot)
+ int prot)
{
struct paace *ppaace;
- unsigned long fspi;
if ((win_size & (win_size - 1)) || win_size < PAMU_PAGE_SIZE) {
pr_debug("window size too small or not a power of two %pa\n",
@@ -368,116 +238,12 @@ int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
if (~snoopid != 0)
ppaace->domain_attr.to_host.snpid = snoopid;
- if (subwin_cnt) {
- /* The first entry is in the primary PAACE instead */
- fspi = pamu_get_fspi_and_allocate(subwin_cnt - 1);
- if (fspi == ULONG_MAX) {
- pr_debug("spaace indexes exhausted\n");
- return -EINVAL;
- }
-
- /* window count is 2^(WCE+1) bytes */
- set_bf(ppaace->impl_attr, PAACE_IA_WCE,
- map_subwindow_cnt_to_wce(subwin_cnt));
- set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0x1);
- ppaace->fspi = fspi;
- } else {
- set_bf(ppaace->impl_attr, PAACE_IA_ATM, PAACE_ATM_WINDOW_XLATE);
- ppaace->twbah = rpn >> 20;
- set_bf(ppaace->win_bitfields, PAACE_WIN_TWBAL, rpn);
- set_bf(ppaace->addr_bitfields, PAACE_AF_AP, prot);
- set_bf(ppaace->impl_attr, PAACE_IA_WCE, 0);
- set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0);
- }
- mb();
-
- return 0;
-}
-
-/**
- * pamu_config_spaace() - Sets up SPAACE entry for specified subwindow
- *
- * @liodn: Logical IO device number
- * @subwin_cnt: number of sub-windows associated with dma-window
- * @subwin: subwindow index
- * @subwin_size: size of subwindow
- * @omi: Operation mapping index
- * @rpn: real (true physical) page number
- * @snoopid: snoop id for hardware coherency -- if ~snoopid == 0 then
- * snoopid not defined
- * @stashid: cache stash id for associated cpu
- * @enable: enable/disable subwindow after reconfiguration
- * @prot: sub window permissions
- *
- * Returns 0 upon success else error code < 0 returned
- */
-int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin,
- phys_addr_t subwin_size, u32 omi, unsigned long rpn,
- u32 snoopid, u32 stashid, int enable, int prot)
-{
- struct paace *paace;
-
- /* setup sub-windows */
- if (!subwin_cnt) {
- pr_debug("Invalid subwindow count\n");
- return -EINVAL;
- }
-
- paace = pamu_get_ppaace(liodn);
- if (subwin > 0 && subwin < subwin_cnt && paace) {
- paace = pamu_get_spaace(paace, subwin - 1);
-
- if (paace && !(paace->addr_bitfields & PAACE_V_VALID)) {
- pamu_init_spaace(paace);
- set_bf(paace->addr_bitfields, SPAACE_AF_LIODN, liodn);
- }
- }
-
- if (!paace) {
- pr_debug("Invalid liodn entry\n");
- return -ENOENT;
- }
-
- if ((subwin_size & (subwin_size - 1)) || subwin_size < PAMU_PAGE_SIZE) {
- pr_debug("subwindow size out of range, or not a power of 2\n");
- return -EINVAL;
- }
-
- if (rpn == ULONG_MAX) {
- pr_debug("real page number out of range\n");
- return -EINVAL;
- }
-
- /* window size is 2^(WSE+1) bytes */
- set_bf(paace->win_bitfields, PAACE_WIN_SWSE,
- map_addrspace_size_to_wse(subwin_size));
-
- set_bf(paace->impl_attr, PAACE_IA_ATM, PAACE_ATM_WINDOW_XLATE);
- paace->twbah = rpn >> 20;
- set_bf(paace->win_bitfields, PAACE_WIN_TWBAL, rpn);
- set_bf(paace->addr_bitfields, PAACE_AF_AP, prot);
-
- /* configure snoop id */
- if (~snoopid != 0)
- paace->domain_attr.to_host.snpid = snoopid;
-
- /* set up operation mapping if it's configured */
- if (omi < OME_NUMBER_ENTRIES) {
- set_bf(paace->impl_attr, PAACE_IA_OTM, PAACE_OTM_INDEXED);
- paace->op_encode.index_ot.omi = omi;
- } else if (~omi != 0) {
- pr_debug("bad operation mapping index: %d\n", omi);
- return -EINVAL;
- }
-
- if (~stashid != 0)
- set_bf(paace->impl_attr, PAACE_IA_CID, stashid);
-
- smp_wmb();
-
- if (enable)
- set_bf(paace->addr_bitfields, PAACE_AF_V, PAACE_V_VALID);
-
+ set_bf(ppaace->impl_attr, PAACE_IA_ATM, PAACE_ATM_WINDOW_XLATE);
+ ppaace->twbah = rpn >> 20;
+ set_bf(ppaace->win_bitfields, PAACE_WIN_TWBAL, rpn);
+ set_bf(ppaace->addr_bitfields, PAACE_AF_AP, prot);
+ set_bf(ppaace->impl_attr, PAACE_IA_WCE, 0);
+ set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0);
mb();
return 0;
@@ -1129,17 +895,6 @@ static int fsl_pamu_probe(struct platform_device *pdev)
spaact_phys = virt_to_phys(spaact);
omt_phys = virt_to_phys(omt);
- spaace_pool = gen_pool_create(ilog2(sizeof(struct paace)), -1);
- if (!spaace_pool) {
- ret = -ENOMEM;
- dev_err(dev, "Failed to allocate spaace gen pool\n");
- goto error;
- }
-
- ret = gen_pool_add(spaace_pool, (unsigned long)spaact, SPAACT_SIZE, -1);
- if (ret)
- goto error_genpool;
-
pamubypenr = in_be32(&guts_regs->pamubypenr);
for (pamu_reg_off = 0, pamu_counter = 0x80000000; pamu_reg_off < size;
@@ -1167,9 +922,6 @@ static int fsl_pamu_probe(struct platform_device *pdev)
return 0;
-error_genpool:
- gen_pool_destroy(spaace_pool);
-
error:
if (irq != NO_IRQ)
free_irq(irq, data);
diff --git a/drivers/iommu/fsl_pamu.h b/drivers/iommu/fsl_pamu.h
index e1496ba96160fd..04fd843d718dd1 100644
--- a/drivers/iommu/fsl_pamu.h
+++ b/drivers/iommu/fsl_pamu.h
@@ -383,18 +383,12 @@ struct ome {
int pamu_domain_init(void);
int pamu_enable_liodn(int liodn);
int pamu_disable_liodn(int liodn);
-void pamu_free_subwins(int liodn);
int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
u32 omi, unsigned long rpn, u32 snoopid, uint32_t stashid,
- u32 subwin_cnt, int prot);
-int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin_addr,
- phys_addr_t subwin_size, u32 omi, unsigned long rpn,
- uint32_t snoopid, u32 stashid, int enable, int prot);
+ int prot);
u32 get_stash_id(u32 stash_dest_hint, u32 vcpu);
void get_ome_index(u32 *omi_index, struct device *dev);
-int pamu_update_paace_stash(int liodn, u32 subwin, u32 value);
-int pamu_disable_spaace(int liodn, u32 subwin);
-u32 pamu_get_max_subwin_cnt(void);
+int pamu_update_paace_stash(int liodn, u32 value);
#endif /* __FSL_PAMU_H */
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index a4da5597755d3d..e6bdd38fc18409 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -56,65 +56,19 @@ static int __init iommu_init_mempool(void)
static phys_addr_t get_phys_addr(struct fsl_dma_domain *dma_domain, dma_addr_t iova)
{
- u32 win_cnt = dma_domain->win_cnt;
struct dma_window *win_ptr = &dma_domain->win_arr[0];
struct iommu_domain_geometry *geom;
geom = &dma_domain->iommu_domain.geometry;
- if (!win_cnt) {
- pr_debug("Number of windows/geometry not configured for the domain\n");
- return 0;
- }
-
- if (win_cnt > 1) {
- u64 subwin_size;
- dma_addr_t subwin_iova;
- u32 wnd;
-
- subwin_size = (geom->aperture_end + 1) >> ilog2(win_cnt);
- subwin_iova = iova & ~(subwin_size - 1);
- wnd = (subwin_iova - geom->aperture_start) >> ilog2(subwin_size);
- win_ptr = &dma_domain->win_arr[wnd];
- }
-
if (win_ptr->valid)
return win_ptr->paddr + (iova & (win_ptr->size - 1));
return 0;
}
-static int map_subwins(int liodn, struct fsl_dma_domain *dma_domain)
-{
- struct dma_window *sub_win_ptr = &dma_domain->win_arr[0];
- int i, ret;
- unsigned long rpn, flags;
-
- for (i = 0; i < dma_domain->win_cnt; i++) {
- if (sub_win_ptr[i].valid) {
- rpn = sub_win_ptr[i].paddr >> PAMU_PAGE_SHIFT;
- spin_lock_irqsave(&iommu_lock, flags);
- ret = pamu_config_spaace(liodn, dma_domain->win_cnt, i,
- sub_win_ptr[i].size,
- ~(u32)0,
- rpn,
- dma_domain->snoop_id,
- dma_domain->stash_id,
- (i > 0) ? 1 : 0,
- sub_win_ptr[i].prot);
- spin_unlock_irqrestore(&iommu_lock, flags);
- if (ret) {
- pr_debug("SPAACE configuration failed for liodn %d\n",
- liodn);
- return ret;
- }
- }
- }
-
- return ret;
-}
-
-static int map_win(int liodn, struct fsl_dma_domain *dma_domain)
+/* Map the DMA window corresponding to the LIODN */
+static int map_liodn(int liodn, struct fsl_dma_domain *dma_domain)
{
int ret;
struct dma_window *wnd = &dma_domain->win_arr[0];
@@ -127,7 +81,7 @@ static int map_win(int liodn, struct fsl_dma_domain *dma_domain)
~(u32)0,
wnd->paddr >> PAMU_PAGE_SHIFT,
dma_domain->snoop_id, dma_domain->stash_id,
- 0, wnd->prot);
+ wnd->prot);
spin_unlock_irqrestore(&iommu_lock, flags);
if (ret)
pr_debug("PAACE configuration failed for liodn %d\n", liodn);
@@ -135,50 +89,27 @@ static int map_win(int liodn, struct fsl_dma_domain *dma_domain)
return ret;
}
-/* Map the DMA window corresponding to the LIODN */
-static int map_liodn(int liodn, struct fsl_dma_domain *dma_domain)
-{
- if (dma_domain->win_cnt > 1)
- return map_subwins(liodn, dma_domain);
- else
- return map_win(liodn, dma_domain);
-}
-
/* Update window/subwindow mapping for the LIODN */
static int update_liodn(int liodn, struct fsl_dma_domain *dma_domain, u32 wnd_nr)
{
int ret;
struct dma_window *wnd = &dma_domain->win_arr[wnd_nr];
+ phys_addr_t wnd_addr;
unsigned long flags;
spin_lock_irqsave(&iommu_lock, flags);
- if (dma_domain->win_cnt > 1) {
- ret = pamu_config_spaace(liodn, dma_domain->win_cnt, wnd_nr,
- wnd->size,
- ~(u32)0,
- wnd->paddr >> PAMU_PAGE_SHIFT,
- dma_domain->snoop_id,
- dma_domain->stash_id,
- (wnd_nr > 0) ? 1 : 0,
- wnd->prot);
- if (ret)
- pr_debug("Subwindow reconfiguration failed for liodn %d\n",
- liodn);
- } else {
- phys_addr_t wnd_addr;
- wnd_addr = dma_domain->iommu_domain.geometry.aperture_start;
+ wnd_addr = dma_domain->iommu_domain.geometry.aperture_start;
- ret = pamu_config_ppaace(liodn, wnd_addr,
- wnd->size,
- ~(u32)0,
- wnd->paddr >> PAMU_PAGE_SHIFT,
- dma_domain->snoop_id, dma_domain->stash_id,
- 0, wnd->prot);
- if (ret)
- pr_debug("Window reconfiguration failed for liodn %d\n",
- liodn);
- }
+ ret = pamu_config_ppaace(liodn, wnd_addr,
+ wnd->size,
+ ~(u32)0,
+ wnd->paddr >> PAMU_PAGE_SHIFT,
+ dma_domain->snoop_id, dma_domain->stash_id,
+ wnd->prot);
+ if (ret)
+ pr_debug("Window reconfiguration failed for liodn %d\n",
+ liodn);
spin_unlock_irqrestore(&iommu_lock, flags);
@@ -192,21 +123,12 @@ static int update_liodn_stash(int liodn, struct fsl_dma_domain *dma_domain,
unsigned long flags;
spin_lock_irqsave(&iommu_lock, flags);
- if (!dma_domain->win_arr) {
- pr_debug("Windows not configured, stash destination update failed for liodn %d\n",
- liodn);
+ ret = pamu_update_paace_stash(liodn, val);
+ if (ret) {
+ pr_debug("Failed to update SPAACE %d field for liodn %d\n ",
+ i, liodn);
spin_unlock_irqrestore(&iommu_lock, flags);
- return -EINVAL;
- }
-
- for (i = 0; i < dma_domain->win_cnt; i++) {
- ret = pamu_update_paace_stash(liodn, i, val);
- if (ret) {
- pr_debug("Failed to update SPAACE %d field for liodn %d\n ",
- i, liodn);
- spin_unlock_irqrestore(&iommu_lock, flags);
- return ret;
- }
+ return ret;
}
spin_unlock_irqrestore(&iommu_lock, flags);
@@ -217,14 +139,12 @@ static int update_liodn_stash(int liodn, struct fsl_dma_domain *dma_domain,
/* Set the geometry parameters for a LIODN */
static int pamu_set_liodn(int liodn, struct device *dev,
struct fsl_dma_domain *dma_domain,
- struct iommu_domain_geometry *geom_attr,
- u32 win_cnt)
+ struct iommu_domain_geometry *geom_attr)
{
phys_addr_t window_addr, window_size;
- phys_addr_t subwin_size;
- int ret = 0, i;
u32 omi_index = ~(u32)0;
unsigned long flags;
+ int ret;
/*
* Configure the omi_index at the geometry setup time.
@@ -241,34 +161,14 @@ static int pamu_set_liodn(int liodn, struct device *dev,
if (!ret)
ret = pamu_config_ppaace(liodn, window_addr, window_size, omi_index,
0, dma_domain->snoop_id,
- dma_domain->stash_id, win_cnt, 0);
+ dma_domain->stash_id, 0);
spin_unlock_irqrestore(&iommu_lock, flags);
if (ret) {
- pr_debug("PAACE configuration failed for liodn %d, win_cnt =%d\n",
- liodn, win_cnt);
+ pr_debug("PAACE configuration failed for liodn %d\n",
+ liodn);
return ret;
}
- if (win_cnt > 1) {
- subwin_size = window_size >> ilog2(win_cnt);
- for (i = 0; i < win_cnt; i++) {
- spin_lock_irqsave(&iommu_lock, flags);
- ret = pamu_disable_spaace(liodn, i);
- if (!ret)
- ret = pamu_config_spaace(liodn, win_cnt, i,
- subwin_size, omi_index,
- 0, dma_domain->snoop_id,
- dma_domain->stash_id,
- 0, 0);
- spin_unlock_irqrestore(&iommu_lock, flags);
- if (ret) {
- pr_debug("SPAACE configuration failed for liodn %d\n",
- liodn);
- return ret;
- }
- }
- }
-
return ret;
}
@@ -292,14 +192,12 @@ static int check_size(u64 size, dma_addr_t iova)
return 0;
}
-static void remove_device_ref(struct device_domain_info *info, u32 win_cnt)
+static void remove_device_ref(struct device_domain_info *info)
{
unsigned long flags;
list_del(&info->link);
spin_lock_irqsave(&iommu_lock, flags);
- if (win_cnt > 1)
- pamu_free_subwins(info->liodn);
pamu_disable_liodn(info->liodn);
spin_unlock_irqrestore(&iommu_lock, flags);
spin_lock_irqsave(&device_domain_lock, flags);
@@ -317,7 +215,7 @@ static void detach_device(struct device *dev, struct fsl_dma_domain *dma_domain)
/* Remove the device from the domain device list */
list_for_each_entry_safe(info, tmp, &dma_domain->devices, link) {
if (!dev || (info->dev == dev))
- remove_device_ref(info, dma_domain->win_cnt);
+ remove_device_ref(info);
}
spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
}
@@ -399,7 +297,6 @@ static struct iommu_domain *fsl_pamu_domain_alloc(unsigned type)
dma_domain->stash_id = ~(u32)0;
dma_domain->snoop_id = ~(u32)0;
- dma_domain->win_cnt = pamu_get_max_subwin_cnt();
INIT_LIST_HEAD(&dma_domain->devices);
spin_lock_init(&dma_domain->domain_lock);
@@ -411,24 +308,6 @@ static struct iommu_domain *fsl_pamu_domain_alloc(unsigned type)
return &dma_domain->iommu_domain;
}
-/* Configure geometry settings for all LIODNs associated with domain */
-static int pamu_set_domain_geometry(struct fsl_dma_domain *dma_domain,
- struct iommu_domain_geometry *geom_attr,
- u32 win_cnt)
-{
- struct device_domain_info *info;
- int ret = 0;
-
- list_for_each_entry(info, &dma_domain->devices, link) {
- ret = pamu_set_liodn(info->liodn, info->dev, dma_domain,
- geom_attr, win_cnt);
- if (ret)
- break;
- }
-
- return ret;
-}
-
/* Update stash destination for all LIODNs associated with the domain */
static int update_domain_stash(struct fsl_dma_domain *dma_domain, u32 val)
{
@@ -475,39 +354,30 @@ static int fsl_pamu_window_enable(struct iommu_domain *domain, u32 wnd_nr,
pamu_prot |= PAACE_AP_PERMS_UPDATE;
spin_lock_irqsave(&dma_domain->domain_lock, flags);
- if (!dma_domain->win_arr) {
- pr_debug("Number of windows not configured\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -ENODEV;
- }
-
- if (wnd_nr >= dma_domain->win_cnt) {
+ if (wnd_nr > 0) {
pr_debug("Invalid window index\n");
spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
return -EINVAL;
}
- win_size = (domain->geometry.aperture_end + 1) >>
- ilog2(dma_domain->win_cnt);
+ win_size = (domain->geometry.aperture_end + 1) >> ilog2(1);
if (size > win_size) {
pr_debug("Invalid window size\n");
spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
return -EINVAL;
}
- if (dma_domain->win_cnt == 1) {
- if (dma_domain->enabled) {
- pr_debug("Disable the window before updating the mapping\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EBUSY;
- }
+ if (dma_domain->enabled) {
+ pr_debug("Disable the window before updating the mapping\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EBUSY;
+ }
- ret = check_size(size, domain->geometry.aperture_start);
- if (ret) {
- pr_debug("Aperture start not aligned to the size\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EINVAL;
- }
+ ret = check_size(size, domain->geometry.aperture_start);
+ if (ret) {
+ pr_debug("Aperture start not aligned to the size\n");
+ spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+ return -EINVAL;
}
wnd = &dma_domain->win_arr[wnd_nr];
@@ -560,22 +430,18 @@ static int handle_attach_device(struct fsl_dma_domain *dma_domain,
* for the domain. If yes, set the geometry for
* the LIODN.
*/
- if (dma_domain->win_arr) {
- u32 win_cnt = dma_domain->win_cnt > 1 ? dma_domain->win_cnt : 0;
-
- ret = pamu_set_liodn(liodn[i], dev, dma_domain,
- &domain->geometry, win_cnt);
+ ret = pamu_set_liodn(liodn[i], dev, dma_domain,
+ &domain->geometry);
+ if (ret)
+ break;
+ if (dma_domain->mapped) {
+ /*
+ * Create window/subwindow mapping for
+ * the LIODN.
+ */
+ ret = map_liodn(liodn[i], dma_domain);
if (ret)
break;
- if (dma_domain->mapped) {
- /*
- * Create window/subwindow mapping for
- * the LIODN.
- */
- ret = map_liodn(liodn[i], dma_domain);
- if (ret)
- break;
- }
}
}
spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
@@ -706,48 +572,6 @@ static int configure_domain_dma_state(struct fsl_dma_domain *dma_domain, bool en
return 0;
}
-static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count)
-{
- struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
- unsigned long flags;
- int ret;
-
- spin_lock_irqsave(&dma_domain->domain_lock, flags);
- /* Ensure domain is inactive i.e. DMA should be disabled for the domain */
- if (dma_domain->enabled) {
- pr_debug("Can't set geometry attributes as domain is active\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EBUSY;
- }
-
- /*
- * Ensure we have valid window count i.e. it should be less than
- * maximum permissible limit and should be a power of two.
- */
- if (w_count > pamu_get_max_subwin_cnt() || !is_power_of_2(w_count)) {
- pr_debug("Invalid window count\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EINVAL;
- }
-
- ret = pamu_set_domain_geometry(dma_domain, &domain->geometry,
- w_count > 1 ? w_count : 0);
- if (!ret) {
- kfree(dma_domain->win_arr);
- dma_domain->win_arr = kcalloc(w_count,
- sizeof(*dma_domain->win_arr),
- GFP_ATOMIC);
- if (!dma_domain->win_arr) {
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -ENOMEM;
- }
- dma_domain->win_cnt = w_count;
- }
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
-
- return ret;
-}
-
static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
enum iommu_attr attr_type, void *data)
{
@@ -761,9 +585,6 @@ static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
case DOMAIN_ATTR_FSL_PAMU_ENABLE:
ret = configure_domain_dma_state(dma_domain, *(int *)data);
break;
- case DOMAIN_ATTR_WINDOWS:
- ret = fsl_pamu_set_windows(domain, *(u32 *)data);
- break;
default:
pr_debug("Unsupported attribute type\n");
ret = -EINVAL;
diff --git a/drivers/iommu/fsl_pamu_domain.h b/drivers/iommu/fsl_pamu_domain.h
index 53d359d66fe577..d3523ee9999d83 100644
--- a/drivers/iommu/fsl_pamu_domain.h
+++ b/drivers/iommu/fsl_pamu_domain.h
@@ -17,23 +17,11 @@ struct dma_window {
};
struct fsl_dma_domain {
- /*
- * Number of windows assocaited with this domain.
- * During domain initialization, it is set to the
- * the maximum number of subwindows allowed for a LIODN.
- * Minimum value for this is 1 indicating a single PAMU
- * window, without any sub windows. Value can be set/
- * queried by set_attr/get_attr API for DOMAIN_ATTR_WINDOWS.
- * Value can only be set once the geometry has been configured.
- */
- u32 win_cnt;
/*
* win_arr contains information of the configured
- * windows for a domain. This is allocated only
- * when the number of windows for the domain are
- * set.
+ * windows for a domain.
*/
- struct dma_window *win_arr;
+ struct dma_window win_arr[1];
/* list of devices associated with the domain */
struct list_head devices;
/* dma_domain states:
diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c
index c958e6310d3094..3d56ec4b373b4b 100644
--- a/drivers/soc/fsl/qbman/qman_portal.c
+++ b/drivers/soc/fsl/qbman/qman_portal.c
@@ -55,13 +55,6 @@ static void portal_set_cpu(struct qm_portal_config *pcfg, int cpu)
dev_err(dev, "%s(): iommu_domain_alloc() failed", __func__);
goto no_iommu;
}
- ret = iommu_domain_set_attr(pcfg->iommu_domain, DOMAIN_ATTR_WINDOWS,
- &window_count);
- if (ret < 0) {
- dev_err(dev, "%s(): iommu_domain_set_attr() = %d", __func__,
- ret);
- goto out_domain_free;
- }
stash_attr.cpu = cpu;
stash_attr.cache = PAMU_ATTR_CACHE_L1;
ret = iommu_domain_set_attr(pcfg->iommu_domain,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 52874ae164dd60..861c3558c878bf 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -109,7 +109,6 @@ enum iommu_cap {
enum iommu_attr {
DOMAIN_ATTR_GEOMETRY,
DOMAIN_ATTR_PAGING,
- DOMAIN_ATTR_WINDOWS,
DOMAIN_ATTR_FSL_PAMU_STASH,
DOMAIN_ATTR_FSL_PAMU_ENABLE,
DOMAIN_ATTR_NESTING, /* two stages of translation */
--
2.30.1
^ permalink raw reply related
* [PATCH 04/20] iommu/fsl_pamu: merge iommu_alloc_dma_domain into fsl_pamu_domain_alloc
From: Christoph Hellwig @ 2021-04-01 15:52 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210401155256.298656-1-hch@lst.de>
Keep the functionality to allocate the domain together.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Li Yang <leoyang.li@nxp.com>
---
drivers/iommu/fsl_pamu_domain.c | 34 ++++++++++-----------------------
1 file changed, 10 insertions(+), 24 deletions(-)
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index 7bd08ddad07779..a4da5597755d3d 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -292,25 +292,6 @@ static int check_size(u64 size, dma_addr_t iova)
return 0;
}
-static struct fsl_dma_domain *iommu_alloc_dma_domain(void)
-{
- struct fsl_dma_domain *domain;
-
- domain = kmem_cache_zalloc(fsl_pamu_domain_cache, GFP_KERNEL);
- if (!domain)
- return NULL;
-
- domain->stash_id = ~(u32)0;
- domain->snoop_id = ~(u32)0;
- domain->win_cnt = pamu_get_max_subwin_cnt();
-
- INIT_LIST_HEAD(&domain->devices);
-
- spin_lock_init(&domain->domain_lock);
-
- return domain;
-}
-
static void remove_device_ref(struct device_domain_info *info, u32 win_cnt)
{
unsigned long flags;
@@ -412,12 +393,17 @@ static struct iommu_domain *fsl_pamu_domain_alloc(unsigned type)
if (type != IOMMU_DOMAIN_UNMANAGED)
return NULL;
- dma_domain = iommu_alloc_dma_domain();
- if (!dma_domain) {
- pr_debug("dma_domain allocation failed\n");
+ dma_domain = kmem_cache_zalloc(fsl_pamu_domain_cache, GFP_KERNEL);
+ if (!dma_domain)
return NULL;
- }
- /* defaul geometry 64 GB i.e. maximum system address */
+
+ dma_domain->stash_id = ~(u32)0;
+ dma_domain->snoop_id = ~(u32)0;
+ dma_domain->win_cnt = pamu_get_max_subwin_cnt();
+ INIT_LIST_HEAD(&dma_domain->devices);
+ spin_lock_init(&dma_domain->domain_lock);
+
+ /* default geometry 64 GB i.e. maximum system address */
dma_domain->iommu_domain. geometry.aperture_start = 0;
dma_domain->iommu_domain.geometry.aperture_end = (1ULL << 36) - 1;
dma_domain->iommu_domain.geometry.force_aperture = true;
--
2.30.1
^ permalink raw reply related
* [PATCH 06/20] iommu/fsl_pamu: remove ->domain_window_enable
From: Christoph Hellwig @ 2021-04-01 15:52 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210401155256.298656-1-hch@lst.de>
The only thing that fsl_pamu_window_enable does for the current caller
is to fill in the prot value in the only dma_window structure, and to
propagate a few values from the iommu_domain_geometry struture into the
dma_window. Remove the dma_window entirely, hardcode the prot value and
otherwise use the iommu_domain_geometry structure instead.
Remove the now unused ->domain_window_enable iommu method.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Li Yang <leoyang.li@nxp.com>
---
drivers/iommu/fsl_pamu_domain.c | 182 +++-------------------------
drivers/iommu/fsl_pamu_domain.h | 15 ---
drivers/iommu/iommu.c | 11 --
drivers/soc/fsl/qbman/qman_portal.c | 7 --
include/linux/iommu.h | 17 ---
5 files changed, 14 insertions(+), 218 deletions(-)
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index e6bdd38fc18409..689035e9d40955 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -54,34 +54,18 @@ static int __init iommu_init_mempool(void)
return 0;
}
-static phys_addr_t get_phys_addr(struct fsl_dma_domain *dma_domain, dma_addr_t iova)
-{
- struct dma_window *win_ptr = &dma_domain->win_arr[0];
- struct iommu_domain_geometry *geom;
-
- geom = &dma_domain->iommu_domain.geometry;
-
- if (win_ptr->valid)
- return win_ptr->paddr + (iova & (win_ptr->size - 1));
-
- return 0;
-}
-
/* Map the DMA window corresponding to the LIODN */
static int map_liodn(int liodn, struct fsl_dma_domain *dma_domain)
{
int ret;
- struct dma_window *wnd = &dma_domain->win_arr[0];
- phys_addr_t wnd_addr = dma_domain->iommu_domain.geometry.aperture_start;
+ struct iommu_domain_geometry *geom = &dma_domain->iommu_domain.geometry;
unsigned long flags;
spin_lock_irqsave(&iommu_lock, flags);
- ret = pamu_config_ppaace(liodn, wnd_addr,
- wnd->size,
- ~(u32)0,
- wnd->paddr >> PAMU_PAGE_SHIFT,
- dma_domain->snoop_id, dma_domain->stash_id,
- wnd->prot);
+ ret = pamu_config_ppaace(liodn, geom->aperture_start,
+ geom->aperture_end + 1, ~(u32)0,
+ 0, dma_domain->snoop_id, dma_domain->stash_id,
+ PAACE_AP_PERMS_QUERY | PAACE_AP_PERMS_UPDATE);
spin_unlock_irqrestore(&iommu_lock, flags);
if (ret)
pr_debug("PAACE configuration failed for liodn %d\n", liodn);
@@ -89,33 +73,6 @@ static int map_liodn(int liodn, struct fsl_dma_domain *dma_domain)
return ret;
}
-/* Update window/subwindow mapping for the LIODN */
-static int update_liodn(int liodn, struct fsl_dma_domain *dma_domain, u32 wnd_nr)
-{
- int ret;
- struct dma_window *wnd = &dma_domain->win_arr[wnd_nr];
- phys_addr_t wnd_addr;
- unsigned long flags;
-
- spin_lock_irqsave(&iommu_lock, flags);
-
- wnd_addr = dma_domain->iommu_domain.geometry.aperture_start;
-
- ret = pamu_config_ppaace(liodn, wnd_addr,
- wnd->size,
- ~(u32)0,
- wnd->paddr >> PAMU_PAGE_SHIFT,
- dma_domain->snoop_id, dma_domain->stash_id,
- wnd->prot);
- if (ret)
- pr_debug("Window reconfiguration failed for liodn %d\n",
- liodn);
-
- spin_unlock_irqrestore(&iommu_lock, flags);
-
- return ret;
-}
-
static int update_liodn_stash(int liodn, struct fsl_dma_domain *dma_domain,
u32 val)
{
@@ -172,26 +129,6 @@ static int pamu_set_liodn(int liodn, struct device *dev,
return ret;
}
-static int check_size(u64 size, dma_addr_t iova)
-{
- /*
- * Size must be a power of two and at least be equal
- * to PAMU page size.
- */
- if ((size & (size - 1)) || size < PAMU_PAGE_SIZE) {
- pr_debug("Size too small or not a power of two\n");
- return -EINVAL;
- }
-
- /* iova must be page size aligned */
- if (iova & (size - 1)) {
- pr_debug("Address is not aligned with window size\n");
- return -EINVAL;
- }
-
- return 0;
-}
-
static void remove_device_ref(struct device_domain_info *info)
{
unsigned long flags;
@@ -257,13 +194,10 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d
static phys_addr_t fsl_pamu_iova_to_phys(struct iommu_domain *domain,
dma_addr_t iova)
{
- struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
-
if (iova < domain->geometry.aperture_start ||
iova > domain->geometry.aperture_end)
return 0;
-
- return get_phys_addr(dma_domain, iova);
+ return iova;
}
static bool fsl_pamu_capable(enum iommu_cap cap)
@@ -279,7 +213,6 @@ static void fsl_pamu_domain_free(struct iommu_domain *domain)
detach_device(NULL, dma_domain);
dma_domain->enabled = 0;
- dma_domain->mapped = 0;
kmem_cache_free(fsl_pamu_domain_cache, dma_domain);
}
@@ -323,84 +256,6 @@ static int update_domain_stash(struct fsl_dma_domain *dma_domain, u32 val)
return ret;
}
-/* Update domain mappings for all LIODNs associated with the domain */
-static int update_domain_mapping(struct fsl_dma_domain *dma_domain, u32 wnd_nr)
-{
- struct device_domain_info *info;
- int ret = 0;
-
- list_for_each_entry(info, &dma_domain->devices, link) {
- ret = update_liodn(info->liodn, dma_domain, wnd_nr);
- if (ret)
- break;
- }
- return ret;
-}
-
-
-static int fsl_pamu_window_enable(struct iommu_domain *domain, u32 wnd_nr,
- phys_addr_t paddr, u64 size, int prot)
-{
- struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
- struct dma_window *wnd;
- int pamu_prot = 0;
- int ret;
- unsigned long flags;
- u64 win_size;
-
- if (prot & IOMMU_READ)
- pamu_prot |= PAACE_AP_PERMS_QUERY;
- if (prot & IOMMU_WRITE)
- pamu_prot |= PAACE_AP_PERMS_UPDATE;
-
- spin_lock_irqsave(&dma_domain->domain_lock, flags);
- if (wnd_nr > 0) {
- pr_debug("Invalid window index\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EINVAL;
- }
-
- win_size = (domain->geometry.aperture_end + 1) >> ilog2(1);
- if (size > win_size) {
- pr_debug("Invalid window size\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EINVAL;
- }
-
- if (dma_domain->enabled) {
- pr_debug("Disable the window before updating the mapping\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EBUSY;
- }
-
- ret = check_size(size, domain->geometry.aperture_start);
- if (ret) {
- pr_debug("Aperture start not aligned to the size\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EINVAL;
- }
-
- wnd = &dma_domain->win_arr[wnd_nr];
- if (!wnd->valid) {
- wnd->paddr = paddr;
- wnd->size = size;
- wnd->prot = pamu_prot;
-
- ret = update_domain_mapping(dma_domain, wnd_nr);
- if (!ret) {
- wnd->valid = 1;
- dma_domain->mapped++;
- }
- } else {
- pr_debug("Disable the window before updating the mapping\n");
- ret = -EBUSY;
- }
-
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
-
- return ret;
-}
-
/*
* Attach the LIODN to the DMA domain and configure the geometry
* and window mappings.
@@ -434,15 +289,14 @@ static int handle_attach_device(struct fsl_dma_domain *dma_domain,
&domain->geometry);
if (ret)
break;
- if (dma_domain->mapped) {
- /*
- * Create window/subwindow mapping for
- * the LIODN.
- */
- ret = map_liodn(liodn[i], dma_domain);
- if (ret)
- break;
- }
+
+ /*
+ * Create window/subwindow mapping for
+ * the LIODN.
+ */
+ ret = map_liodn(liodn[i], dma_domain);
+ if (ret)
+ break;
}
spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
@@ -552,13 +406,6 @@ static int configure_domain_dma_state(struct fsl_dma_domain *dma_domain, bool en
int ret;
spin_lock_irqsave(&dma_domain->domain_lock, flags);
-
- if (enable && !dma_domain->mapped) {
- pr_debug("Can't enable DMA domain without valid mapping\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -ENODEV;
- }
-
dma_domain->enabled = enable;
list_for_each_entry(info, &dma_domain->devices, link) {
ret = (enable) ? pamu_enable_liodn(info->liodn) :
@@ -717,7 +564,6 @@ static const struct iommu_ops fsl_pamu_ops = {
.domain_free = fsl_pamu_domain_free,
.attach_dev = fsl_pamu_attach_device,
.detach_dev = fsl_pamu_detach_device,
- .domain_window_enable = fsl_pamu_window_enable,
.iova_to_phys = fsl_pamu_iova_to_phys,
.domain_set_attr = fsl_pamu_set_domain_attr,
.probe_device = fsl_pamu_probe_device,
diff --git a/drivers/iommu/fsl_pamu_domain.h b/drivers/iommu/fsl_pamu_domain.h
index d3523ee9999d83..13ee06e0ef0136 100644
--- a/drivers/iommu/fsl_pamu_domain.h
+++ b/drivers/iommu/fsl_pamu_domain.h
@@ -9,24 +9,10 @@
#include "fsl_pamu.h"
-struct dma_window {
- phys_addr_t paddr;
- u64 size;
- int valid;
- int prot;
-};
-
struct fsl_dma_domain {
- /*
- * win_arr contains information of the configured
- * windows for a domain.
- */
- struct dma_window win_arr[1];
/* list of devices associated with the domain */
struct list_head devices;
/* dma_domain states:
- * mapped - A particular mapping has been created
- * within the configured geometry.
* enabled - DMA has been enabled for the given
* domain. This translates to setting of the
* valid bit for the primary PAACE in the PAMU
@@ -35,7 +21,6 @@ struct fsl_dma_domain {
* enabled for it.
*
*/
- int mapped;
int enabled;
/* stash_id obtained from the stash attribute details */
u32 stash_id;
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d0b0a15dba8413..b212bf0261820b 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2610,17 +2610,6 @@ size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
}
-int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
- phys_addr_t paddr, u64 size, int prot)
-{
- if (unlikely(domain->ops->domain_window_enable == NULL))
- return -ENODEV;
-
- return domain->ops->domain_window_enable(domain, wnd_nr, paddr, size,
- prot);
-}
-EXPORT_SYMBOL_GPL(iommu_domain_window_enable);
-
/**
* report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
* @domain: the iommu domain where the fault has happened
diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c
index 3d56ec4b373b4b..9ee1663f422cbf 100644
--- a/drivers/soc/fsl/qbman/qman_portal.c
+++ b/drivers/soc/fsl/qbman/qman_portal.c
@@ -65,13 +65,6 @@ static void portal_set_cpu(struct qm_portal_config *pcfg, int cpu)
__func__, ret);
goto out_domain_free;
}
- ret = iommu_domain_window_enable(pcfg->iommu_domain, 0, 0, 1ULL << 36,
- IOMMU_READ | IOMMU_WRITE);
- if (ret < 0) {
- dev_err(dev, "%s(): iommu_domain_window_enable() = %d",
- __func__, ret);
- goto out_domain_free;
- }
ret = iommu_attach_device(pcfg->iommu_domain, dev);
if (ret < 0) {
dev_err(dev, "%s(): iommu_device_attach() = %d", __func__,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 861c3558c878bf..f7baa81887a8bc 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -203,7 +203,6 @@ struct iommu_iotlb_gather {
* @get_resv_regions: Request list of reserved regions for a device
* @put_resv_regions: Free list of reserved regions for a device
* @apply_resv_region: Temporary helper call-back for iova reserved ranges
- * @domain_window_enable: Configure and enable a particular window for a domain
* @of_xlate: add OF master IDs to iommu grouping
* @is_attach_deferred: Check if domain attach should be deferred from iommu
* driver init to device driver init (default no)
@@ -261,10 +260,6 @@ struct iommu_ops {
struct iommu_domain *domain,
struct iommu_resv_region *region);
- /* Window handling functions */
- int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr,
- phys_addr_t paddr, u64 size, int prot);
-
int (*of_xlate)(struct device *dev, struct of_phandle_args *args);
bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev);
@@ -505,11 +500,6 @@ extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr,
extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr,
void *data);
-/* Window handling function prototypes */
-extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
- phys_addr_t offset, u64 size,
- int prot);
-
extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
unsigned long iova, int flags);
@@ -735,13 +725,6 @@ static inline void iommu_iotlb_sync(struct iommu_domain *domain,
{
}
-static inline int iommu_domain_window_enable(struct iommu_domain *domain,
- u32 wnd_nr, phys_addr_t paddr,
- u64 size, int prot)
-{
- return -ENODEV;
-}
-
static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
{
return 0;
--
2.30.1
^ permalink raw reply related
* [PATCH 01/20] iommu: remove the unused domain_window_disable method
From: Christoph Hellwig @ 2021-04-01 15:52 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210401155256.298656-1-hch@lst.de>
domain_window_disable is wired up by fsl_pamu, but never actually called.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Li Yang <leoyang.li@nxp.com>
---
drivers/iommu/fsl_pamu_domain.c | 48 ---------------------------------
include/linux/iommu.h | 2 --
2 files changed, 50 deletions(-)
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index b2110767caf49c..53380cf1fa452f 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -473,53 +473,6 @@ static int update_domain_mapping(struct fsl_dma_domain *dma_domain, u32 wnd_nr)
return ret;
}
-static int disable_domain_win(struct fsl_dma_domain *dma_domain, u32 wnd_nr)
-{
- struct device_domain_info *info;
- int ret = 0;
-
- list_for_each_entry(info, &dma_domain->devices, link) {
- if (dma_domain->win_cnt == 1 && dma_domain->enabled) {
- ret = pamu_disable_liodn(info->liodn);
- if (!ret)
- dma_domain->enabled = 0;
- } else {
- ret = pamu_disable_spaace(info->liodn, wnd_nr);
- }
- }
-
- return ret;
-}
-
-static void fsl_pamu_window_disable(struct iommu_domain *domain, u32 wnd_nr)
-{
- struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
- unsigned long flags;
- int ret;
-
- spin_lock_irqsave(&dma_domain->domain_lock, flags);
- if (!dma_domain->win_arr) {
- pr_debug("Number of windows not configured\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return;
- }
-
- if (wnd_nr >= dma_domain->win_cnt) {
- pr_debug("Invalid window index\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return;
- }
-
- if (dma_domain->win_arr[wnd_nr].valid) {
- ret = disable_domain_win(dma_domain, wnd_nr);
- if (!ret) {
- dma_domain->win_arr[wnd_nr].valid = 0;
- dma_domain->mapped--;
- }
- }
-
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
-}
static int fsl_pamu_window_enable(struct iommu_domain *domain, u32 wnd_nr,
phys_addr_t paddr, u64 size, int prot)
@@ -1032,7 +985,6 @@ static const struct iommu_ops fsl_pamu_ops = {
.attach_dev = fsl_pamu_attach_device,
.detach_dev = fsl_pamu_detach_device,
.domain_window_enable = fsl_pamu_window_enable,
- .domain_window_disable = fsl_pamu_window_disable,
.iova_to_phys = fsl_pamu_iova_to_phys,
.domain_set_attr = fsl_pamu_set_domain_attr,
.domain_get_attr = fsl_pamu_get_domain_attr,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 5e7fe519430af4..47c8b318d8f523 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -209,7 +209,6 @@ struct iommu_iotlb_gather {
* @put_resv_regions: Free list of reserved regions for a device
* @apply_resv_region: Temporary helper call-back for iova reserved ranges
* @domain_window_enable: Configure and enable a particular window for a domain
- * @domain_window_disable: Disable a particular window for a domain
* @of_xlate: add OF master IDs to iommu grouping
* @is_attach_deferred: Check if domain attach should be deferred from iommu
* driver init to device driver init (default no)
@@ -270,7 +269,6 @@ struct iommu_ops {
/* Window handling functions */
int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr,
phys_addr_t paddr, u64 size, int prot);
- void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr);
int (*of_xlate)(struct device *dev, struct of_phandle_args *args);
bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev);
--
2.30.1
^ permalink raw reply related
* cleanup unused or almost unused IOMMU APIs and the FSL PAMU driver v3
From: Christoph Hellwig @ 2021-04-01 15:52 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
Hi all,
there are a bunch of IOMMU APIs that are entirely unused, or only used as
a private communication channel between the FSL PAMU driver and it's only
consumer, the qbman portal driver.
So this series drops a huge chunk of entirely unused FSL PAMU
functionality, then drops all kinds of unused IOMMU APIs, and then
replaces what is left of the iommu_attrs with properly typed, smaller
and easier to use specific APIs.
Changes since v2:
- remove a comment fragment a little bit earlier
- fix the aperture end passed to pamu_config_ppaace
- fix a few trivial typos
- remove more unused arguments to pamu_config_ppaace
- do not accidentally enable lazy flushing for non-dma domains
Changes since v1:
- use a different way to control strict flushing behavior (from Robin)
- remove the iommu_cmd_line wrappers
- simplify the pagetbl quirks a little more
- slightly improved patch ordering
- better changelogs
Diffstat:
arch/powerpc/include/asm/fsl_pamu_stash.h | 12
drivers/gpu/drm/msm/adreno/adreno_gpu.c | 5
drivers/iommu/amd/iommu.c | 23
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 75 ---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 1
drivers/iommu/arm/arm-smmu/arm-smmu.c | 111 +---
drivers/iommu/arm/arm-smmu/arm-smmu.h | 2
drivers/iommu/dma-iommu.c | 9
drivers/iommu/fsl_pamu.c | 293 -----------
drivers/iommu/fsl_pamu.h | 12
drivers/iommu/fsl_pamu_domain.c | 688 ++--------------------------
drivers/iommu/fsl_pamu_domain.h | 46 -
drivers/iommu/intel/iommu.c | 95 ---
drivers/iommu/iommu.c | 118 +---
drivers/soc/fsl/qbman/qman_portal.c | 55 --
drivers/vfio/vfio_iommu_type1.c | 31 -
drivers/vhost/vdpa.c | 10
include/linux/io-pgtable.h | 4
include/linux/iommu.h | 76 ---
19 files changed, 203 insertions(+), 1463 deletions(-)
^ permalink raw reply
* [PATCH 07/20] iommu/fsl_pamu: replace DOMAIN_ATTR_FSL_PAMU_STASH with a direct call
From: Christoph Hellwig @ 2021-04-01 15:52 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210401155256.298656-1-hch@lst.de>
Add a fsl_pamu_configure_l1_stash API that qman_portal can call directly
instead of indirecting through the iommu attr API.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Li Yang <leoyang.li@nxp.com>
---
arch/powerpc/include/asm/fsl_pamu_stash.h | 12 +++---------
drivers/iommu/fsl_pamu_domain.c | 16 +++-------------
drivers/iommu/fsl_pamu_domain.h | 2 --
drivers/soc/fsl/qbman/qman_portal.c | 18 +++---------------
include/linux/iommu.h | 1 -
5 files changed, 9 insertions(+), 40 deletions(-)
diff --git a/arch/powerpc/include/asm/fsl_pamu_stash.h b/arch/powerpc/include/asm/fsl_pamu_stash.h
index 30a31ad2123d86..c0fbadb70b5dad 100644
--- a/arch/powerpc/include/asm/fsl_pamu_stash.h
+++ b/arch/powerpc/include/asm/fsl_pamu_stash.h
@@ -7,6 +7,8 @@
#ifndef __FSL_PAMU_STASH_H
#define __FSL_PAMU_STASH_H
+struct iommu_domain;
+
/* cache stash targets */
enum pamu_stash_target {
PAMU_ATTR_CACHE_L1 = 1,
@@ -14,14 +16,6 @@ enum pamu_stash_target {
PAMU_ATTR_CACHE_L3,
};
-/*
- * This attribute allows configuring stashig specific parameters
- * in the PAMU hardware.
- */
-
-struct pamu_stash_attribute {
- u32 cpu; /* cpu number */
- u32 cache; /* cache to stash to: L1,L2,L3 */
-};
+int fsl_pamu_configure_l1_stash(struct iommu_domain *domain, u32 cpu);
#endif /* __FSL_PAMU_STASH_H */
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index 689035e9d40955..557a152c1d2c49 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -372,27 +372,20 @@ static void fsl_pamu_detach_device(struct iommu_domain *domain,
}
/* Set the domain stash attribute */
-static int configure_domain_stash(struct fsl_dma_domain *dma_domain, void *data)
+int fsl_pamu_configure_l1_stash(struct iommu_domain *domain, u32 cpu)
{
- struct pamu_stash_attribute *stash_attr = data;
+ struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
unsigned long flags;
int ret;
spin_lock_irqsave(&dma_domain->domain_lock, flags);
-
- memcpy(&dma_domain->dma_stash, stash_attr,
- sizeof(struct pamu_stash_attribute));
-
- dma_domain->stash_id = get_stash_id(stash_attr->cache,
- stash_attr->cpu);
+ dma_domain->stash_id = get_stash_id(PAMU_ATTR_CACHE_L1, cpu);
if (dma_domain->stash_id == ~(u32)0) {
pr_debug("Invalid stash attributes\n");
spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
return -EINVAL;
}
-
ret = update_domain_stash(dma_domain, dma_domain->stash_id);
-
spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
return ret;
@@ -426,9 +419,6 @@ static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
int ret = 0;
switch (attr_type) {
- case DOMAIN_ATTR_FSL_PAMU_STASH:
- ret = configure_domain_stash(dma_domain, data);
- break;
case DOMAIN_ATTR_FSL_PAMU_ENABLE:
ret = configure_domain_dma_state(dma_domain, *(int *)data);
break;
diff --git a/drivers/iommu/fsl_pamu_domain.h b/drivers/iommu/fsl_pamu_domain.h
index 13ee06e0ef0136..cd488004acd1b3 100644
--- a/drivers/iommu/fsl_pamu_domain.h
+++ b/drivers/iommu/fsl_pamu_domain.h
@@ -22,9 +22,7 @@ struct fsl_dma_domain {
*
*/
int enabled;
- /* stash_id obtained from the stash attribute details */
u32 stash_id;
- struct pamu_stash_attribute dma_stash;
u32 snoop_id;
struct iommu_domain iommu_domain;
spinlock_t domain_lock;
diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c
index 9ee1663f422cbf..798b3a1ffd0b9c 100644
--- a/drivers/soc/fsl/qbman/qman_portal.c
+++ b/drivers/soc/fsl/qbman/qman_portal.c
@@ -47,7 +47,6 @@ static void portal_set_cpu(struct qm_portal_config *pcfg, int cpu)
#ifdef CONFIG_FSL_PAMU
struct device *dev = pcfg->dev;
int window_count = 1;
- struct pamu_stash_attribute stash_attr;
int ret;
pcfg->iommu_domain = iommu_domain_alloc(&platform_bus_type);
@@ -55,13 +54,9 @@ static void portal_set_cpu(struct qm_portal_config *pcfg, int cpu)
dev_err(dev, "%s(): iommu_domain_alloc() failed", __func__);
goto no_iommu;
}
- stash_attr.cpu = cpu;
- stash_attr.cache = PAMU_ATTR_CACHE_L1;
- ret = iommu_domain_set_attr(pcfg->iommu_domain,
- DOMAIN_ATTR_FSL_PAMU_STASH,
- &stash_attr);
+ ret = fsl_pamu_configure_l1_stash(pcfg->iommu_domain, cpu);
if (ret < 0) {
- dev_err(dev, "%s(): iommu_domain_set_attr() = %d",
+ dev_err(dev, "%s(): fsl_pamu_configure_l1_stash() = %d",
__func__, ret);
goto out_domain_free;
}
@@ -143,15 +138,8 @@ static void qman_portal_update_sdest(const struct qm_portal_config *pcfg,
unsigned int cpu)
{
#ifdef CONFIG_FSL_PAMU /* TODO */
- struct pamu_stash_attribute stash_attr;
- int ret;
-
if (pcfg->iommu_domain) {
- stash_attr.cpu = cpu;
- stash_attr.cache = PAMU_ATTR_CACHE_L1;
- ret = iommu_domain_set_attr(pcfg->iommu_domain,
- DOMAIN_ATTR_FSL_PAMU_STASH, &stash_attr);
- if (ret < 0) {
+ if (fsl_pamu_configure_l1_stash(pcfg->iommu_domain, cpu) < 0) {
dev_err(pcfg->dev,
"Failed to update pamu stash setting\n");
return;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index f7baa81887a8bc..208e570e8d99e7 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -109,7 +109,6 @@ enum iommu_cap {
enum iommu_attr {
DOMAIN_ATTR_GEOMETRY,
DOMAIN_ATTR_PAGING,
- DOMAIN_ATTR_FSL_PAMU_STASH,
DOMAIN_ATTR_FSL_PAMU_ENABLE,
DOMAIN_ATTR_NESTING, /* two stages of translation */
DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
--
2.30.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox