From 171c4006fb1b42a084057a71c86776e9f1b8e62c Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Wed, 9 Jan 2013 18:49:51 +0100 Subject: [PATCH 1/4] s390/mm: fix pmd_pfn() for thp The pfn calculation in pmd_pfn() is broken for thp, because it uses HPAGE_SHIFT instead of the normal PAGE_SHIFT. This is fixed by removing the distinction between thp and normal pmds in that function, and always using PAGE_SHIFT. Reported-by: Christian Borntraeger Signed-off-by: Gerald Schaefer Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/pgtable.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index c928dc1938f..c1d7930a82f 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1387,10 +1387,7 @@ static inline int has_transparent_hugepage(void) static inline unsigned long pmd_pfn(pmd_t pmd) { - if (pmd_trans_huge(pmd)) - return pmd_val(pmd) >> HPAGE_SHIFT; - else - return pmd_val(pmd) >> PAGE_SHIFT; + return pmd_val(pmd) >> PAGE_SHIFT; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ From 7bdc229fad1d42beda70f1966042262470660082 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 11 Jan 2013 15:26:01 +0100 Subject: [PATCH 2/4] s390: use -fPIC for module compile The xfs module uses a lot of tracepoint, with TRACEPOINTS=y and a few debugging options the GOT table of the xfs module will get bigger than 4K. To get a working xfs module it needs to be compiled with -fPIC instead of -fpic. To play safe use -fPIC for all modules. Signed-off-by: Martin Schwidefsky --- arch/s390/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 4b8e08b56f4..7e3ce78d429 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -24,8 +24,8 @@ CHECKFLAGS += -D__s390__ -msize-long else LD_BFD := elf64-s390 LDFLAGS := -m elf64_s390 -KBUILD_AFLAGS_MODULE += -fpic -D__PIC__ -KBUILD_CFLAGS_MODULE += -fpic -D__PIC__ +KBUILD_AFLAGS_MODULE += -fPIC +KBUILD_CFLAGS_MODULE += -fPIC KBUILD_CFLAGS += -m64 KBUILD_AFLAGS += -m64 UTS_MACHINE := s390x From ed4f20943cd4c7b55105c04daedf8d63ab6d499c Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 14 Jan 2013 16:55:55 +0100 Subject: [PATCH 3/4] s390/time: fix sched_clock() overflow Converting a 64 Bit TOD format value to nanoseconds means that the value must be divided by 4.096. In order to achieve that we multiply with 125 and divide by 512. When used within sched_clock() this triggers an overflow after appr. 417 days. Resulting in a sched_clock() return value that is much smaller than previously and therefore may cause all sort of weird things in subsystems that rely on a monotonic sched_clock() behaviour. To fix this implement a tod_to_ns() helper function which converts TOD values without overflow and call this function from both places that open coded the conversion: sched_clock() and kvm_s390_handle_wait(). Cc: stable@kernel.org Reviewed-by: Martin Schwidefsky Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/timex.h | 28 ++++++++++++++++++++++++++++ arch/s390/kernel/time.c | 2 +- arch/s390/kvm/interrupt.c | 2 +- 3 files changed, 30 insertions(+), 2 deletions(-) diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index fba4d66788a..4c060bb5b8e 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -128,4 +128,32 @@ static inline unsigned long long get_clock_monotonic(void) return get_clock_xt() - sched_clock_base_cc; } +/** + * tod_to_ns - convert a TOD format value to nanoseconds + * @todval: to be converted TOD format value + * Returns: number of nanoseconds that correspond to the TOD format value + * + * Converting a 64 Bit TOD format value to nanoseconds means that the value + * must be divided by 4.096. In order to achieve that we multiply with 125 + * and divide by 512: + * + * ns = (todval * 125) >> 9; + * + * In order to avoid an overflow with the multiplication we can rewrite this. + * With a split todval == 2^32 * th + tl (th upper 32 bits, tl lower 32 bits) + * we end up with + * + * ns = ((2^32 * th + tl) * 125 ) >> 9; + * -> ns = (2^23 * th * 125) + ((tl * 125) >> 9); + * + */ +static inline unsigned long long tod_to_ns(unsigned long long todval) +{ + unsigned long long ns; + + ns = ((todval >> 32) << 23) * 125; + ns += ((todval & 0xffffffff) * 125) >> 9; + return ns; +} + #endif diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index aff0e350d77..a5f4f5a1d24 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct clock_event_device, comparators); */ unsigned long long notrace __kprobes sched_clock(void) { - return (get_clock_monotonic() * 125) >> 9; + return tod_to_ns(get_clock_monotonic()); } /* diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c30615e605a..82c481ddef7 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -408,7 +408,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) return 0; } - sltime = ((vcpu->arch.sie_block->ckc - now)*125)>>9; + sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now); hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL); VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime); From 509d97b6f91b51e180ba26ddb1e2b7f6dfa80cba Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Tue, 15 Jan 2013 19:02:01 +0100 Subject: [PATCH 4/4] s390/chsc: fix SEI usage cbc0dd1 "s390/pci: CHSC PCI support for error and availability events" introduced a new SEI notification type as part of pci support. The way SEI was called with nt2 and nt0 consecutive broke the nt0 stuff used for channel subsystem notifications. The reason why this was broken with the mentioned patch is that you cannot selectively disable type 0 notifications (so even when asked for type 2 only, type 0 could be presented). The way to do it is to tell SEI which types of notification you can process and -this is the important part- look at the SEI result which notification type you actually received. Reviewed-by: Peter Oberparleiter Tested-by: Michael Holzheu Signed-off-by: Sebastian Ott Signed-off-by: Martin Schwidefsky --- drivers/s390/cio/chsc.c | 31 ++++++++++++------------------- 1 file changed, 12 insertions(+), 19 deletions(-) diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 68e80e2734a..10729bbcece 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -283,7 +283,7 @@ struct chsc_sei_nt2_area { u8 ccdf[PAGE_SIZE - 24 - 56]; /* content-code dependent field */ } __packed; -#define CHSC_SEI_NT0 0ULL +#define CHSC_SEI_NT0 (1ULL << 63) #define CHSC_SEI_NT2 (1ULL << 61) struct chsc_sei { @@ -291,7 +291,8 @@ struct chsc_sei { u32 reserved1; u64 ntsm; /* notification type mask */ struct chsc_header response; - u32 reserved2; + u32 :24; + u8 nt; union { struct chsc_sei_nt0_area nt0_area; struct chsc_sei_nt2_area nt2_area; @@ -496,17 +497,17 @@ static int __chsc_process_crw(struct chsc_sei *sei, u64 ntsm) css_schedule_eval_all(); } - switch (sei->ntsm) { - case CHSC_SEI_NT0: + switch (sei->nt) { + case 0: chsc_process_sei_nt0(&sei->u.nt0_area); - return 1; - case CHSC_SEI_NT2: + break; + case 2: chsc_process_sei_nt2(&sei->u.nt2_area); - return 1; + break; default: - CIO_CRW_EVENT(2, "chsc: unhandled nt (nt=%08Lx)\n", - sei->ntsm); - return 0; + CIO_CRW_EVENT(2, "chsc: unhandled nt=%d\n", + sei->nt); + break; } } else { CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n", @@ -537,15 +538,7 @@ static void chsc_process_crw(struct crw *crw0, struct crw *crw1, int overflow) sei = sei_page; CIO_TRACE_EVENT(2, "prcss"); - - /* - * The ntsm does not allow to select NT0 and NT2 together. We need to - * first check for NT2, than additionally for NT0... - */ -#ifdef CONFIG_PCI - if (!__chsc_process_crw(sei, CHSC_SEI_NT2)) -#endif - __chsc_process_crw(sei, CHSC_SEI_NT0); + __chsc_process_crw(sei, CHSC_SEI_NT0 | CHSC_SEI_NT2); } void chsc_chp_online(struct chp_id chpid)