diff options
Diffstat (limited to 'arch/powerpc/kvm/book3s_hv_rmhandlers.S')
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv_rmhandlers.S | 238 |
1 files changed, 213 insertions, 25 deletions
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index ffbb871c2bd8..868347ef09fd 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -86,6 +86,12 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) lbz r4, LPPACA_PMCINUSE(r3) cmpwi r4, 0 beq 23f /* skip if not */ +BEGIN_FTR_SECTION + ld r3, HSTATE_MMCR(r13) + andi. r4, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO + cmpwi r4, MMCR0_PMAO + beql kvmppc_fix_pmao +END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG) lwz r3, HSTATE_PMC(r13) lwz r4, HSTATE_PMC + 4(r13) lwz r5, HSTATE_PMC + 8(r13) @@ -242,6 +248,12 @@ kvm_novcpu_exit: */ .globl kvm_start_guest kvm_start_guest: + + /* Set runlatch bit the minute you wake up from nap */ + mfspr r1, SPRN_CTRLF + ori r1, r1, 1 + mtspr SPRN_CTRLT, r1 + ld r2,PACATOC(r13) li r0,KVM_HWTHREAD_IN_KVM @@ -280,8 +292,7 @@ kvm_start_guest: beq kvm_no_guest /* Set HSTATE_DSCR(r13) to something sensible */ - LOAD_REG_ADDR(r6, dscr_default) - ld r6, 0(r6) + ld r6, PACA_DSCR(r13) std r6, HSTATE_DSCR(r13) bl kvmppc_hv_entry @@ -309,6 +320,11 @@ kvm_no_guest: li r0, KVM_HWTHREAD_IN_NAP stb r0, HSTATE_HWTHREAD_STATE(r13) kvm_do_nap: + /* Clear the runlatch bit before napping */ + mfspr r2, SPRN_CTRLF + clrrdi r2, r2, 1 + mtspr SPRN_CTRLT, r2 + li r3, LPCR_PECE0 mfspr r4, SPRN_LPCR rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1 @@ -726,6 +742,12 @@ skip_tm: sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */ isync +BEGIN_FTR_SECTION + ld r3, VCPU_MMCR(r4) + andi. r5, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO + cmpwi r5, MMCR0_PMAO + beql kvmppc_fix_pmao +END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG) lwz r3, VCPU_PMC(r4) /* always load up guest PMU registers */ lwz r5, VCPU_PMC + 4(r4) /* to prevent information leak */ lwz r6, VCPU_PMC + 8(r4) @@ -1312,6 +1334,110 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) mr r3, r9 bl kvmppc_save_fp +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +BEGIN_FTR_SECTION + b 2f +END_FTR_SECTION_IFCLR(CPU_FTR_TM) + /* Turn on TM. */ + mfmsr r8 + li r0, 1 + rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG + mtmsrd r8 + + ld r5, VCPU_MSR(r9) + rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 + beq 1f /* TM not active in guest. */ + + li r3, TM_CAUSE_KVM_RESCHED + + /* Clear the MSR RI since r1, r13 are all going to be foobar. */ + li r5, 0 + mtmsrd r5, 1 + + /* All GPRs are volatile at this point. */ + TRECLAIM(R3) + + /* Temporarily store r13 and r9 so we have some regs to play with */ + SET_SCRATCH0(r13) + GET_PACA(r13) + std r9, PACATMSCRATCH(r13) + ld r9, HSTATE_KVM_VCPU(r13) + + /* Get a few more GPRs free. */ + std r29, VCPU_GPRS_TM(29)(r9) + std r30, VCPU_GPRS_TM(30)(r9) + std r31, VCPU_GPRS_TM(31)(r9) + + /* Save away PPR and DSCR soon so don't run with user values. */ + mfspr r31, SPRN_PPR + HMT_MEDIUM + mfspr r30, SPRN_DSCR + ld r29, HSTATE_DSCR(r13) + mtspr SPRN_DSCR, r29 + + /* Save all but r9, r13 & r29-r31 */ + reg = 0 + .rept 29 + .if (reg != 9) && (reg != 13) + std reg, VCPU_GPRS_TM(reg)(r9) + .endif + reg = reg + 1 + .endr + /* ... now save r13 */ + GET_SCRATCH0(r4) + std r4, VCPU_GPRS_TM(13)(r9) + /* ... and save r9 */ + ld r4, PACATMSCRATCH(r13) + std r4, VCPU_GPRS_TM(9)(r9) + + /* Reload stack pointer and TOC. */ + ld r1, HSTATE_HOST_R1(r13) + ld r2, PACATOC(r13) + + /* Set MSR RI now we have r1 and r13 back. */ + li r5, MSR_RI + mtmsrd r5, 1 + + /* Save away checkpinted SPRs. */ + std r31, VCPU_PPR_TM(r9) + std r30, VCPU_DSCR_TM(r9) + mflr r5 + mfcr r6 + mfctr r7 + mfspr r8, SPRN_AMR + mfspr r10, SPRN_TAR + std r5, VCPU_LR_TM(r9) + stw r6, VCPU_CR_TM(r9) + std r7, VCPU_CTR_TM(r9) + std r8, VCPU_AMR_TM(r9) + std r10, VCPU_TAR_TM(r9) + + /* Restore r12 as trap number. */ + lwz r12, VCPU_TRAP(r9) + + /* Save FP/VSX. */ + addi r3, r9, VCPU_FPRS_TM + bl .store_fp_state + addi r3, r9, VCPU_VRS_TM + bl .store_vr_state + mfspr r6, SPRN_VRSAVE + stw r6, VCPU_VRSAVE_TM(r9) +1: + /* + * We need to save these SPRs after the treclaim so that the software + * error code is recorded correctly in the TEXASR. Also the user may + * change these outside of a transaction, so they must always be + * context switched. + */ + mfspr r5, SPRN_TFHAR + mfspr r6, SPRN_TFIAR + mfspr r7, SPRN_TEXASR + std r5, VCPU_TFHAR(r9) + std r6, VCPU_TFIAR(r9) + std r7, VCPU_TEXASR(r9) +2: +#endif + /* Increment yield count if they have a VPA */ ld r8, VCPU_VPA(r9) /* do they have a VPA? */ cmpdi r8, 0 @@ -1324,6 +1450,30 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) 25: /* Save PMU registers if requested */ /* r8 and cr0.eq are live here */ +BEGIN_FTR_SECTION + /* + * POWER8 seems to have a hardware bug where setting + * MMCR0[PMAE] along with MMCR0[PMC1CE] and/or MMCR0[PMCjCE] + * when some counters are already negative doesn't seem + * to cause a performance monitor alert (and hence interrupt). + * The effect of this is that when saving the PMU state, + * if there is no PMU alert pending when we read MMCR0 + * before freezing the counters, but one becomes pending + * before we read the counters, we lose it. + * To work around this, we need a way to freeze the counters + * before reading MMCR0. Normally, freezing the counters + * is done by writing MMCR0 (to set MMCR0[FC]) which + * unavoidably writes MMCR0[PMA0] as well. On POWER8, + * we can also freeze the counters using MMCR2, by writing + * 1s to all the counter freeze condition bits (there are + * 9 bits each for 6 counters). + */ + li r3, -1 /* set all freeze bits */ + clrrdi r3, r3, 10 + mfspr r10, SPRN_MMCR2 + mtspr SPRN_MMCR2, r3 + isync +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) li r3, 1 sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ mfspr r4, SPRN_MMCR0 /* save MMCR0 */ @@ -1347,6 +1497,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) std r4, VCPU_MMCR(r9) std r5, VCPU_MMCR + 8(r9) std r6, VCPU_MMCR + 16(r9) +BEGIN_FTR_SECTION + std r10, VCPU_MMCR + 24(r9) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) std r7, VCPU_SIAR(r9) std r8, VCPU_SDAR(r9) mfspr r3, SPRN_PMC1 @@ -1370,12 +1523,10 @@ BEGIN_FTR_SECTION stw r11, VCPU_PMC + 28(r9) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) BEGIN_FTR_SECTION - mfspr r4, SPRN_MMCR2 mfspr r5, SPRN_SIER mfspr r6, SPRN_SPMC1 mfspr r7, SPRN_SPMC2 mfspr r8, SPRN_MMCRS - std r4, VCPU_MMCR + 24(r9) std r5, VCPU_SIER(r9) stw r6, VCPU_PMC + 24(r9) stw r7, VCPU_PMC + 28(r9) @@ -1647,7 +1798,7 @@ kvmppc_hdsi: /* Search the hash table. */ mr r3, r9 /* vcpu pointer */ li r7, 1 /* data fault */ - bl .kvmppc_hpte_hv_fault + bl kvmppc_hpte_hv_fault ld r9, HSTATE_KVM_VCPU(r13) ld r10, VCPU_PC(r9) ld r11, VCPU_MSR(r9) @@ -1721,7 +1872,7 @@ kvmppc_hisi: mr r4, r10 mr r6, r11 li r7, 0 /* instruction fault */ - bl .kvmppc_hpte_hv_fault + bl kvmppc_hpte_hv_fault ld r9, HSTATE_KVM_VCPU(r13) ld r10, VCPU_PC(r9) ld r11, VCPU_MSR(r9) @@ -1795,16 +1946,16 @@ hcall_real_fallback: .globl hcall_real_table hcall_real_table: .long 0 /* 0 - unused */ - .long .kvmppc_h_remove - hcall_real_table - .long .kvmppc_h_enter - hcall_real_table - .long .kvmppc_h_read - hcall_real_table + .long DOTSYM(kvmppc_h_remove) - hcall_real_table + .long DOTSYM(kvmppc_h_enter) - hcall_real_table + .long DOTSYM(kvmppc_h_read) - hcall_real_table .long 0 /* 0x10 - H_CLEAR_MOD */ .long 0 /* 0x14 - H_CLEAR_REF */ - .long .kvmppc_h_protect - hcall_real_table - .long .kvmppc_h_get_tce - hcall_real_table - .long .kvmppc_h_put_tce - hcall_real_table + .long DOTSYM(kvmppc_h_protect) - hcall_real_table + .long DOTSYM(kvmppc_h_get_tce) - hcall_real_table + .long DOTSYM(kvmppc_h_put_tce) - hcall_real_table .long 0 /* 0x24 - H_SET_SPRG0 */ - .long .kvmppc_h_set_dabr - hcall_real_table + .long DOTSYM(kvmppc_h_set_dabr) - hcall_real_table .long 0 /* 0x2c */ .long 0 /* 0x30 */ .long 0 /* 0x34 */ @@ -1820,11 +1971,11 @@ hcall_real_table: .long 0 /* 0x5c */ .long 0 /* 0x60 */ #ifdef CONFIG_KVM_XICS - .long .kvmppc_rm_h_eoi - hcall_real_table - .long .kvmppc_rm_h_cppr - hcall_real_table - .long .kvmppc_rm_h_ipi - hcall_real_table + .long DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table + .long DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table + .long DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table .long 0 /* 0x70 - H_IPOLL */ - .long .kvmppc_rm_h_xirr - hcall_real_table + .long DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table #else .long 0 /* 0x64 - H_EOI */ .long 0 /* 0x68 - H_CPPR */ @@ -1858,7 +2009,7 @@ hcall_real_table: .long 0 /* 0xd4 */ .long 0 /* 0xd8 */ .long 0 /* 0xdc */ - .long .kvmppc_h_cede - hcall_real_table + .long DOTSYM(kvmppc_h_cede) - hcall_real_table .long 0 /* 0xe4 */ .long 0 /* 0xe8 */ .long 0 /* 0xec */ @@ -1875,11 +2026,11 @@ hcall_real_table: .long 0 /* 0x118 */ .long 0 /* 0x11c */ .long 0 /* 0x120 */ - .long .kvmppc_h_bulk_remove - hcall_real_table + .long DOTSYM(kvmppc_h_bulk_remove) - hcall_real_table .long 0 /* 0x128 */ .long 0 /* 0x12c */ .long 0 /* 0x130 */ - .long .kvmppc_h_set_xdabr - hcall_real_table + .long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table hcall_real_table_end: ignore_hdec: @@ -1999,8 +2150,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) /* * Take a nap until a decrementer or external or doobell interrupt - * occurs, with PECE1, PECE0 and PECEDP set in LPCR + * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the + * runlatch bit before napping. */ + mfspr r2, SPRN_CTRLF + clrrdi r2, r2, 1 + mtspr SPRN_CTRLT, r2 + li r0,1 stb r0,HSTATE_HWTHREAD_REQ(r13) mfspr r5,SPRN_LPCR @@ -2099,16 +2255,30 @@ kvm_cede_exit: /* Try to handle a machine check in real mode */ machine_check_realmode: mr r3, r9 /* get vcpu pointer */ - bl .kvmppc_realmode_machine_check + bl kvmppc_realmode_machine_check nop - cmpdi r3, 0 /* continue exiting from guest? */ + cmpdi r3, 0 /* Did we handle MCE ? */ ld r9, HSTATE_KVM_VCPU(r13) li r12, BOOK3S_INTERRUPT_MACHINE_CHECK - beq mc_cont + /* + * Deliver unhandled/fatal (e.g. UE) MCE errors to guest through + * machine check interrupt (set HSRR0 to 0x200). And for handled + * errors (no-fatal), just go back to guest execution with current + * HSRR0 instead of exiting guest. This new approach will inject + * machine check to guest for fatal error causing guest to crash. + * + * The old code used to return to host for unhandled errors which + * was causing guest to hang with soft lockups inside guest and + * makes it difficult to recover guest instance. + */ + ld r10, VCPU_PC(r9) + ld r11, VCPU_MSR(r9) + bne 2f /* Continue guest execution. */ /* If not, deliver a machine check. SRR0/1 are already set */ li r10, BOOK3S_INTERRUPT_MACHINE_CHECK + ld r11, VCPU_MSR(r9) bl kvmppc_msr_interrupt - b fast_interrupt_c_return +2: b fast_interrupt_c_return /* * Check the reason we woke from nap, and take appropriate action. @@ -2311,3 +2481,21 @@ kvmppc_msr_interrupt: li r0, 1 1: rldimi r11, r0, MSR_TS_S_LG, 63 - MSR_TS_T_LG blr + +/* + * This works around a hardware bug on POWER8E processors, where + * writing a 1 to the MMCR0[PMAO] bit doesn't generate a + * performance monitor interrupt. Instead, when we need to have + * an interrupt pending, we have to arrange for a counter to overflow. + */ +kvmppc_fix_pmao: + li r3, 0 + mtspr SPRN_MMCR2, r3 + lis r3, (MMCR0_PMXE | MMCR0_FCECE)@h + ori r3, r3, MMCR0_PMCjCE | MMCR0_C56RUN + mtspr SPRN_MMCR0, r3 + lis r3, 0x7fff + ori r3, r3, 0xffff + mtspr SPRN_PMC6, r3 + isync + blr |