From aec982603aa8cc0a21143681feb5f60ecc69d718 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 6 Dec 2021 11:11:51 +0000 Subject: powerpc/fixmap: Fix VM debug warning on unmap Unmapping a fixmap entry is done by calling __set_fixmap() with FIXMAP_PAGE_CLEAR as flags. Today, powerpc __set_fixmap() calls map_kernel_page(). map_kernel_page() is not happy when called a second time for the same page. WARNING: CPU: 0 PID: 1 at arch/powerpc/mm/pgtable.c:194 set_pte_at+0xc/0x1e8 CPU: 0 PID: 1 Comm: swapper Not tainted 5.16.0-rc3-s3k-dev-01993-g350ff07feb7d-dirty #682 NIP: c0017cd4 LR: c00187f0 CTR: 00000010 REGS: e1011d50 TRAP: 0700 Not tainted (5.16.0-rc3-s3k-dev-01993-g350ff07feb7d-dirty) MSR: 00029032 CR: 42000208 XER: 00000000 GPR00: c0165fec e1011e10 c14c0000 c0ee2550 ff800000 c0f3d000 00000000 c001686c GPR08: 00001000 b00045a9 00000001 c0f58460 c0f50000 00000000 c0007e10 00000000 GPR16: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 GPR24: 00000000 00000000 c0ee2550 00000000 c0f57000 00000ff8 00000000 ff800000 NIP [c0017cd4] set_pte_at+0xc/0x1e8 LR [c00187f0] map_kernel_page+0x9c/0x100 Call Trace: [e1011e10] [c0736c68] vsnprintf+0x358/0x6c8 (unreliable) [e1011e30] [c0165fec] __set_fixmap+0x30/0x44 [e1011e40] [c0c13bdc] early_iounmap+0x11c/0x170 [e1011e70] [c0c06cb0] ioremap_legacy_serial_console+0x88/0xc0 [e1011e90] [c0c03634] do_one_initcall+0x80/0x178 [e1011ef0] [c0c0385c] kernel_init_freeable+0xb4/0x250 [e1011f20] [c0007e34] kernel_init+0x24/0x140 [e1011f30] [c0016268] ret_from_kernel_thread+0x5c/0x64 Instruction dump: 7fe3fb78 48019689 80010014 7c630034 83e1000c 5463d97e 7c0803a6 38210010 4e800020 81250000 712a0001 41820008 <0fe00000> 9421ffe0 93e1001c 48000030 Implement unmap_kernel_page() which clears an existing pte. Reported-by: Maxime Bizon Signed-off-by: Christophe Leroy Tested-by: Maxime Bizon Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/b0b752f6f6ecc60653e873f385c6f0dce4e9ab6a.1638789098.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/book3s/32/pgtable.h | 1 + arch/powerpc/include/asm/book3s/64/pgtable.h | 2 ++ arch/powerpc/include/asm/fixmap.h | 6 ++++-- arch/powerpc/include/asm/nohash/32/pgtable.h | 1 + arch/powerpc/include/asm/nohash/64/pgtable.h | 1 + arch/powerpc/mm/pgtable.c | 9 +++++++++ 6 files changed, 18 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 609c80f67194..f8b94f78403f 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -178,6 +178,7 @@ static inline bool pte_user(pte_t pte) #ifndef __ASSEMBLY__ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 33e073d6b0c4..875730d5af40 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1082,6 +1082,8 @@ static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t p return hash__map_kernel_page(ea, pa, prot); } +void unmap_kernel_page(unsigned long va); + static inline int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys) diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 947b5b9c4424..a832aeafe560 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -111,8 +111,10 @@ static inline void __set_fixmap(enum fixed_addresses idx, BUILD_BUG_ON(idx >= __end_of_fixed_addresses); else if (WARN_ON(idx >= __end_of_fixed_addresses)) return; - - map_kernel_page(__fix_to_virt(idx), phys, flags); + if (pgprot_val(flags)) + map_kernel_page(__fix_to_virt(idx), phys, flags); + else + unmap_kernel_page(__fix_to_virt(idx)); } #define __early_set_fixmap __set_fixmap diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index b67742e2a9b2..d959c2a73fbf 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -64,6 +64,7 @@ extern int icache_44x_need_flush; #ifndef __ASSEMBLY__ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index a3313e853e5e..2816d158280a 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -308,6 +308,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __swp_entry_to_pte(x) __pte((x).val) int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); extern int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index abb3198bd277..6ec5a7dd7913 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -206,6 +206,15 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, __set_pte_at(mm, addr, ptep, pte, 0); } +void unmap_kernel_page(unsigned long va) +{ + pmd_t *pmdp = pmd_off_k(va); + pte_t *ptep = pte_offset_kernel(pmdp, va); + + pte_clear(&init_mm, va, ptep); + flush_tlb_kernel_range(va, va + PAGE_SIZE); +} + /* * This is called when relaxing access to a PTE. It's also called in the page * fault path when we don't hit any of the major fault cases, ie, a minor -- cgit v1.2.3 From fb6433b48a178d4672cb26632454ee0b21056eaa Mon Sep 17 00:00:00 2001 From: Athira Rajeev Date: Sat, 22 Jan 2022 09:04:29 +0530 Subject: powerpc/perf: Fix power_pmu_disable to call clear_pmi_irq_pending only if PMI is pending Running selftest with CONFIG_PPC_IRQ_SOFT_MASK_DEBUG enabled in kernel triggered below warning: [ 172.851380] ------------[ cut here ]------------ [ 172.851391] WARNING: CPU: 8 PID: 2901 at arch/powerpc/include/asm/hw_irq.h:246 power_pmu_disable+0x270/0x280 [ 172.851402] Modules linked in: dm_mod bonding nft_ct nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables rfkill nfnetlink sunrpc xfs libcrc32c pseries_rng xts vmx_crypto uio_pdrv_genirq uio sch_fq_codel ip_tables ext4 mbcache jbd2 sd_mod t10_pi sg ibmvscsi ibmveth scsi_transport_srp fuse [ 172.851442] CPU: 8 PID: 2901 Comm: lost_exception_ Not tainted 5.16.0-rc5-03218-g798527287598 #2 [ 172.851451] NIP: c00000000013d600 LR: c00000000013d5a4 CTR: c00000000013b180 [ 172.851458] REGS: c000000017687860 TRAP: 0700 Not tainted (5.16.0-rc5-03218-g798527287598) [ 172.851465] MSR: 8000000000029033 CR: 48004884 XER: 20040000 [ 172.851482] CFAR: c00000000013d5b4 IRQMASK: 1 [ 172.851482] GPR00: c00000000013d5a4 c000000017687b00 c000000002a10600 0000000000000004 [ 172.851482] GPR04: 0000000082004000 c0000008ba08f0a8 0000000000000000 00000008b7ed0000 [ 172.851482] GPR08: 00000000446194f6 0000000000008000 c00000000013b118 c000000000d58e68 [ 172.851482] GPR12: c00000000013d390 c00000001ec54a80 0000000000000000 0000000000000000 [ 172.851482] GPR16: 0000000000000000 0000000000000000 c000000015d5c708 c0000000025396d0 [ 172.851482] GPR20: 0000000000000000 0000000000000000 c00000000a3bbf40 0000000000000003 [ 172.851482] GPR24: 0000000000000000 c0000008ba097400 c0000000161e0d00 c00000000a3bb600 [ 172.851482] GPR28: c000000015d5c700 0000000000000001 0000000082384090 c0000008ba0020d8 [ 172.851549] NIP [c00000000013d600] power_pmu_disable+0x270/0x280 [ 172.851557] LR [c00000000013d5a4] power_pmu_disable+0x214/0x280 [ 172.851565] Call Trace: [ 172.851568] [c000000017687b00] [c00000000013d5a4] power_pmu_disable+0x214/0x280 (unreliable) [ 172.851579] [c000000017687b40] [c0000000003403ac] perf_pmu_disable+0x4c/0x60 [ 172.851588] [c000000017687b60] [c0000000003445e4] __perf_event_task_sched_out+0x1d4/0x660 [ 172.851596] [c000000017687c50] [c000000000d1175c] __schedule+0xbcc/0x12a0 [ 172.851602] [c000000017687d60] [c000000000d11ea8] schedule+0x78/0x140 [ 172.851608] [c000000017687d90] [c0000000001a8080] sys_sched_yield+0x20/0x40 [ 172.851615] [c000000017687db0] [c0000000000334dc] system_call_exception+0x18c/0x380 [ 172.851622] [c000000017687e10] [c00000000000c74c] system_call_common+0xec/0x268 The warning indicates that MSR_EE being set(interrupt enabled) when there was an overflown PMC detected. This could happen in power_pmu_disable since it runs under interrupt soft disable condition ( local_irq_save ) and not with interrupts hard disabled. commit 2c9ac51b850d ("powerpc/perf: Fix PMU callbacks to clear pending PMI before resetting an overflown PMC") intended to clear PMI pending bit in Paca when disabling the PMU. It could happen that PMC gets overflown while code is in power_pmu_disable callback function. Hence add a check to see if PMI pending bit is set in Paca before clearing it via clear_pmi_pending. Fixes: 2c9ac51b850d ("powerpc/perf: Fix PMU callbacks to clear pending PMI before resetting an overflown PMC") Reported-by: Sachin Sant Signed-off-by: Athira Rajeev Tested-by: Sachin Sant Reviewed-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220122033429.25395-1-atrajeev@linux.vnet.ibm.com --- arch/powerpc/perf/core-book3s.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 32b98b7a1f86..b5b42cf0a703 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1355,9 +1355,20 @@ static void power_pmu_disable(struct pmu *pmu) * Otherwise provide a warning if there is PMI pending, but * no counter is found overflown. */ - if (any_pmc_overflown(cpuhw)) - clear_pmi_irq_pending(); - else + if (any_pmc_overflown(cpuhw)) { + /* + * Since power_pmu_disable runs under local_irq_save, it + * could happen that code hits a PMC overflow without PMI + * pending in paca. Hence only clear PMI pending if it was + * set. + * + * If a PMI is pending, then MSR[EE] must be disabled (because + * the masked PMI handler disabling EE). So it is safe to + * call clear_pmi_irq_pending(). + */ + if (pmi_irq_pending()) + clear_pmi_irq_pending(); + } else WARN_ON(pmi_irq_pending()); val = mmcra = cpuhw->mmcr.mmcra; -- cgit v1.2.3 From 22f7ff0dea9491e90b6fe808ed40c30bd791e5c2 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 22 Jan 2022 20:55:30 +1000 Subject: KVM: PPC: Book3S HV Nested: Fix nested HFSCR being clobbered with multiple vCPUs The L0 is storing HFSCR requested by the L1 for the L2 in struct kvm_nested_guest when the L1 requests a vCPU enter L2. kvm_nested_guest is not a per-vCPU structure. Hilarity ensues. Fix it by moving the nested hfscr into the vCPU structure together with the other per-vCPU nested fields. Fixes: 8b210a880b35 ("KVM: PPC: Book3S HV Nested: Make nested HFSCR state accessible") Cc: stable@vger.kernel.org # v5.15+ Signed-off-by: Nicholas Piggin Reviewed-by: Fabiano Rosas Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220122105530.3477250-1-npiggin@gmail.com --- arch/powerpc/include/asm/kvm_book3s_64.h | 1 - arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/kvm/book3s_hv.c | 3 +-- arch/powerpc/kvm/book3s_hv_nested.c | 2 +- 4 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index fe07558173ef..827038a33064 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -39,7 +39,6 @@ struct kvm_nested_guest { pgd_t *shadow_pgtable; /* our page table for this guest */ u64 l1_gr_to_hr; /* L1's addr of part'n-scoped table */ u64 process_table; /* process table entry for this guest */ - u64 hfscr; /* HFSCR that the L1 requested for this nested guest */ long refcnt; /* number of pointers to this struct */ struct mutex tlb_lock; /* serialize page faults and tlbies */ struct kvm_nested_guest *next; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index a770443cd6e0..d9bf60bf0816 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -818,6 +818,7 @@ struct kvm_vcpu_arch { /* For support of nested guests */ struct kvm_nested_guest *nested; + u64 nested_hfscr; /* HFSCR that the L1 requested for the nested guest */ u32 nested_vcpu_id; gpa_t nested_io_gpr; #endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index d1817cd9a691..84c89f08ae9a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1816,7 +1816,6 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) { - struct kvm_nested_guest *nested = vcpu->arch.nested; int r; int srcu_idx; @@ -1922,7 +1921,7 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) * it into a HEAI. */ if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) || - (nested->hfscr & (1UL << cause))) { + (vcpu->arch.nested_hfscr & (1UL << cause))) { vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST; /* diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 8f8daaeeb3b7..9d373f8963ee 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -363,7 +363,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* set L1 state to L2 state */ vcpu->arch.nested = l2; vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token; - l2->hfscr = l2_hv.hfscr; + vcpu->arch.nested_hfscr = l2_hv.hfscr; vcpu->arch.regs = l2_regs; /* Guest must always run with ME enabled, HV disabled. */ -- cgit v1.2.3 From 8defc2a5dd8f4c0cb19ecbaca8d3e89ab98524da Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 25 Jan 2022 00:39:28 +1000 Subject: powerpc/64s/interrupt: Fix decrementer storm The decrementer exception can fail to be cleared when the interrupt returns in the case where the decrementer wraps with the next timer still beyond decrementer_max. This results in a decrementer interrupt storm. This is triggerable with small decrementer system with hard and soft watchdogs disabled. Fix this by always programming the decrementer if there was no timer. Fixes: 0faf20a1ad16 ("powerpc/64s/interrupt: Don't enable MSR[EE] in irq handlers unless perf is in use") Reported-by: Alexey Kardashevskiy Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220124143930.3923442-1-npiggin@gmail.com --- arch/powerpc/kernel/time.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 62361cc7281c..cd0b8b71ecdd 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -649,8 +649,9 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) __this_cpu_inc(irq_stat.timer_irqs_event); } else { now = *next_tb - now; - if (now <= decrementer_max) - set_dec_or_work(now); + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); __this_cpu_inc(irq_stat.timer_irqs_others); } -- cgit v1.2.3