From e3d27b62110c1ccea4d015f7c5c92f92150668db Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:05 -0400 Subject: s390/sclp: detect the zPCI load/store interpretation facility Detect the zPCI Load/Store Interpretation facility. Reviewed-by: Eric Farman Reviewed-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-2-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/sclp.h | 1 + drivers/s390/char/sclp_early.c | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 236b34b75ddb..68ef0ddf6400 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -88,6 +88,7 @@ struct sclp_info { unsigned char has_sipl : 1; unsigned char has_dirq : 1; unsigned char has_iplcc : 1; + unsigned char has_zpci_lsi : 1; unsigned int ibc; unsigned int mtid; unsigned int mtid_cp; diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index dd313ff57df3..d5671c03d5cc 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -45,6 +45,7 @@ static void __init sclp_early_facilities_detect(void) sclp.has_gisaf = !!(sccb->fac118 & 0x08); sclp.has_hvs = !!(sccb->fac119 & 0x80); sclp.has_kss = !!(sccb->fac98 & 0x01); + sclp.has_zpci_lsi = !!(sccb->fac118 & 0x01); if (sccb->fac85 & 0x02) S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP; if (sccb->fac91 & 0x40) -- cgit From 9db153f4523069a89cab14ab9aa2438976f256fb Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:06 -0400 Subject: s390/sclp: detect the AISII facility Detect the Adapter Interruption Source ID Interpretation facility. Reviewed-by: Eric Farman Reviewed-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-3-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/sclp.h | 1 + drivers/s390/char/sclp_early.c | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 68ef0ddf6400..d05fbffa7692 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -89,6 +89,7 @@ struct sclp_info { unsigned char has_dirq : 1; unsigned char has_iplcc : 1; unsigned char has_zpci_lsi : 1; + unsigned char has_aisii : 1; unsigned int ibc; unsigned int mtid; unsigned int mtid_cp; diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index d5671c03d5cc..39c9bd7e1c26 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -45,6 +45,7 @@ static void __init sclp_early_facilities_detect(void) sclp.has_gisaf = !!(sccb->fac118 & 0x08); sclp.has_hvs = !!(sccb->fac119 & 0x80); sclp.has_kss = !!(sccb->fac98 & 0x01); + sclp.has_aisii = !!(sccb->fac118 & 0x40); sclp.has_zpci_lsi = !!(sccb->fac118 & 0x01); if (sccb->fac85 & 0x02) S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP; -- cgit From efef0db77c939f105f7dc92a736dd66628406822 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:07 -0400 Subject: s390/sclp: detect the AENI facility Detect the Adapter Event Notification Interpretation facility. Reviewed-by: Eric Farman Reviewed-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-4-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/sclp.h | 1 + drivers/s390/char/sclp_early.c | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index d05fbffa7692..b0e67414c492 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -90,6 +90,7 @@ struct sclp_info { unsigned char has_iplcc : 1; unsigned char has_zpci_lsi : 1; unsigned char has_aisii : 1; + unsigned char has_aeni : 1; unsigned int ibc; unsigned int mtid; unsigned int mtid_cp; diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index 39c9bd7e1c26..aefdf0b17dbe 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -46,6 +46,7 @@ static void __init sclp_early_facilities_detect(void) sclp.has_hvs = !!(sccb->fac119 & 0x80); sclp.has_kss = !!(sccb->fac98 & 0x01); sclp.has_aisii = !!(sccb->fac118 & 0x40); + sclp.has_aeni = !!(sccb->fac118 & 0x20); sclp.has_zpci_lsi = !!(sccb->fac118 & 0x01); if (sccb->fac85 & 0x02) S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP; -- cgit From b05a870c5e4e6a113b7f3fb61b5fa0869e40dd30 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:08 -0400 Subject: s390/sclp: detect the AISI facility Detect the Adapter Interruption Suppression Interpretation facility. Reviewed-by: Eric Farman Reviewed-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-5-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/sclp.h | 1 + drivers/s390/char/sclp_early.c | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index b0e67414c492..addefe8ccdba 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -91,6 +91,7 @@ struct sclp_info { unsigned char has_zpci_lsi : 1; unsigned char has_aisii : 1; unsigned char has_aeni : 1; + unsigned char has_aisi : 1; unsigned int ibc; unsigned int mtid; unsigned int mtid_cp; diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index aefdf0b17dbe..d15b0d541de3 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -47,6 +47,7 @@ static void __init sclp_early_facilities_detect(void) sclp.has_kss = !!(sccb->fac98 & 0x01); sclp.has_aisii = !!(sccb->fac118 & 0x40); sclp.has_aeni = !!(sccb->fac118 & 0x20); + sclp.has_aisi = !!(sccb->fac118 & 0x10); sclp.has_zpci_lsi = !!(sccb->fac118 & 0x01); if (sccb->fac85 & 0x02) S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP; -- cgit From d2197485a1883c60d044146b1ee69aac654c55e8 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:09 -0400 Subject: s390/airq: pass more TPI info to airq handlers A subsequent patch will introduce an airq handler that requires additional TPI information beyond directed vs floating, so pass the entire tpi_info structure via the handler. Only pci actually uses this information today, for the other airq handlers this is effectively a no-op. Reviewed-by: Eric Farman Reviewed-by: Claudio Imbrenda Reviewed-by: Pierre Morel Reviewed-by: Thomas Huth Acked-by: Christian Borntraeger Acked-by: Cornelia Huck Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-6-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/airq.h | 3 ++- arch/s390/kvm/interrupt.c | 4 +++- arch/s390/pci/pci_irq.c | 9 +++++++-- drivers/s390/cio/airq.c | 2 +- drivers/s390/cio/qdio_thinint.c | 6 ++++-- drivers/s390/crypto/ap_bus.c | 9 ++++++--- drivers/s390/virtio/virtio_ccw.c | 4 +++- 7 files changed, 26 insertions(+), 11 deletions(-) diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h index 01936fdfaddb..7918a7d09028 100644 --- a/arch/s390/include/asm/airq.h +++ b/arch/s390/include/asm/airq.h @@ -12,10 +12,11 @@ #include #include +#include struct airq_struct { struct hlist_node list; /* Handler queueing. */ - void (*handler)(struct airq_struct *airq, bool floating); + void (*handler)(struct airq_struct *airq, struct tpi_info *tpi_info); u8 *lsi_ptr; /* Local-Summary-Indicator pointer */ u8 lsi_mask; /* Local-Summary-Indicator mask */ u8 isc; /* Interrupt-subclass */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index af96dc0549a4..17ff475157d8 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -28,6 +28,7 @@ #include #include #include +#include #include "kvm-s390.h" #include "gaccess.h" #include "trace-s390.h" @@ -3311,7 +3312,8 @@ out: } EXPORT_SYMBOL_GPL(kvm_s390_gisc_unregister); -static void gib_alert_irq_handler(struct airq_struct *airq, bool floating) +static void gib_alert_irq_handler(struct airq_struct *airq, + struct tpi_info *tpi_info) { inc_irq_stat(IRQIO_GAL); process_gib_alert_list(); diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 500cd2dbdf53..b805c75252ed 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -11,6 +11,7 @@ #include #include +#include static enum {FLOATING, DIRECTED} irq_delivery; @@ -216,8 +217,11 @@ static void zpci_handle_fallback_irq(void) } } -static void zpci_directed_irq_handler(struct airq_struct *airq, bool floating) +static void zpci_directed_irq_handler(struct airq_struct *airq, + struct tpi_info *tpi_info) { + bool floating = !tpi_info->directed_irq; + if (floating) { inc_irq_stat(IRQIO_PCF); zpci_handle_fallback_irq(); @@ -227,7 +231,8 @@ static void zpci_directed_irq_handler(struct airq_struct *airq, bool floating) } } -static void zpci_floating_irq_handler(struct airq_struct *airq, bool floating) +static void zpci_floating_irq_handler(struct airq_struct *airq, + struct tpi_info *tpi_info) { unsigned long si, ai; struct airq_iv *aibv; diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c index c0ed364bf446..230eb5b5b64e 100644 --- a/drivers/s390/cio/airq.c +++ b/drivers/s390/cio/airq.c @@ -99,7 +99,7 @@ static irqreturn_t do_airq_interrupt(int irq, void *dummy) rcu_read_lock(); hlist_for_each_entry_rcu(airq, head, list) if ((*airq->lsi_ptr & airq->lsi_mask) != 0) - airq->handler(airq, !tpi_info->directed_irq); + airq->handler(airq, tpi_info); rcu_read_unlock(); return IRQ_HANDLED; diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c index 8e09bf3a2fcd..9b9335dd06db 100644 --- a/drivers/s390/cio/qdio_thinint.c +++ b/drivers/s390/cio/qdio_thinint.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "cio.h" #include "ioasm.h" @@ -93,9 +94,10 @@ static inline u32 clear_shared_ind(void) /** * tiqdio_thinint_handler - thin interrupt handler for qdio * @airq: pointer to adapter interrupt descriptor - * @floating: flag to recognize floating vs. directed interrupts (unused) + * @tpi_info: interrupt information (e.g. floating vs directed -- unused) */ -static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating) +static void tiqdio_thinint_handler(struct airq_struct *airq, + struct tpi_info *tpi_info) { u64 irq_time = S390_lowcore.int_clock; u32 si_used = clear_shared_ind(); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 5c13d2079d96..1b85f21c151b 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -131,7 +132,8 @@ static int ap_max_adapter_id = 63; static struct bus_type ap_bus_type; /* Adapter interrupt definitions */ -static void ap_interrupt_handler(struct airq_struct *airq, bool floating); +static void ap_interrupt_handler(struct airq_struct *airq, + struct tpi_info *tpi_info); static bool ap_irq_flag; @@ -452,9 +454,10 @@ static enum hrtimer_restart ap_poll_timeout(struct hrtimer *unused) /** * ap_interrupt_handler() - Schedule ap_tasklet on interrupt * @airq: pointer to adapter interrupt descriptor - * @floating: ignored + * @tpi_info: ignored */ -static void ap_interrupt_handler(struct airq_struct *airq, bool floating) +static void ap_interrupt_handler(struct airq_struct *airq, + struct tpi_info *tpi_info) { inc_irq_stat(IRQIO_APB); tasklet_schedule(&ap_tasklet); diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 97e51c34e6cf..58cca50996ee 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -33,6 +33,7 @@ #include #include #include +#include /* * virtio related functions @@ -204,7 +205,8 @@ static void drop_airq_indicator(struct virtqueue *vq, struct airq_info *info) write_unlock_irqrestore(&info->lock, flags); } -static void virtio_airq_handler(struct airq_struct *airq, bool floating) +static void virtio_airq_handler(struct airq_struct *airq, + struct tpi_info *tpi_info) { struct airq_info *info = container_of(airq, struct airq_info, airq); unsigned long ai; -- cgit From 932b646727f9df312980d175e339248cdf7812f0 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:10 -0400 Subject: s390/airq: allow for airq structure that uses an input vector When doing device passthrough where interrupts are being forwarded from host to guest, we wish to use a pinned section of guest memory as the vector (the same memory used by the guest as the vector). To accomplish this, add a new parameter for airq_iv_create which allows passing an existing vector to be used instead of allocating a new one. The caller is responsible for ensuring the vector is pinned in memory as well as for unpinning the memory when the vector is no longer needed. A subsequent patch will use this new parameter for zPCI interpretation. Reviewed-by: Thomas Huth Reviewed-by: Pierre Morel Reviewed-by: Claudio Imbrenda Acked-by: Cornelia Huck Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-7-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/airq.h | 4 +++- arch/s390/pci/pci_irq.c | 8 ++++---- drivers/s390/cio/airq.c | 10 +++++++--- drivers/s390/virtio/virtio_ccw.c | 2 +- 4 files changed, 15 insertions(+), 9 deletions(-) diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h index 7918a7d09028..e82e5626e139 100644 --- a/arch/s390/include/asm/airq.h +++ b/arch/s390/include/asm/airq.h @@ -47,8 +47,10 @@ struct airq_iv { #define AIRQ_IV_PTR 4 /* Allocate the ptr array */ #define AIRQ_IV_DATA 8 /* Allocate the data array */ #define AIRQ_IV_CACHELINE 16 /* Cacheline alignment for the vector */ +#define AIRQ_IV_GUESTVEC 32 /* Vector is a pinned guest page */ -struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags); +struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags, + unsigned long *vec); void airq_iv_release(struct airq_iv *iv); unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num); void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num); diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index b805c75252ed..87c7d121c255 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -296,7 +296,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) zdev->aisb = bit; /* Create adapter interrupt vector */ - zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK); + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK, NULL); if (!zdev->aibv) return -ENOMEM; @@ -419,7 +419,7 @@ static int __init zpci_directed_irq_init(void) union zpci_sic_iib iib = {{0}}; unsigned int cpu; - zpci_sbv = airq_iv_create(num_possible_cpus(), 0); + zpci_sbv = airq_iv_create(num_possible_cpus(), 0, NULL); if (!zpci_sbv) return -ENOMEM; @@ -441,7 +441,7 @@ static int __init zpci_directed_irq_init(void) zpci_ibv[cpu] = airq_iv_create(cache_line_size() * BITS_PER_BYTE, AIRQ_IV_DATA | AIRQ_IV_CACHELINE | - (!cpu ? AIRQ_IV_ALLOC : 0)); + (!cpu ? AIRQ_IV_ALLOC : 0), NULL); if (!zpci_ibv[cpu]) return -ENOMEM; } @@ -458,7 +458,7 @@ static int __init zpci_floating_irq_init(void) if (!zpci_ibv) return -ENOMEM; - zpci_sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC); + zpci_sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, NULL); if (!zpci_sbv) goto out_free; diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c index 230eb5b5b64e..34967e67249e 100644 --- a/drivers/s390/cio/airq.c +++ b/drivers/s390/cio/airq.c @@ -122,10 +122,12 @@ static inline unsigned long iv_size(unsigned long bits) * airq_iv_create - create an interrupt vector * @bits: number of bits in the interrupt vector * @flags: allocation flags + * @vec: pointer to pinned guest memory if AIRQ_IV_GUESTVEC * * Returns a pointer to an interrupt vector structure */ -struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags) +struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags, + unsigned long *vec) { struct airq_iv *iv; unsigned long size; @@ -146,6 +148,8 @@ struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags) &iv->vector_dma); if (!iv->vector) goto out_free; + } else if (flags & AIRQ_IV_GUESTVEC) { + iv->vector = vec; } else { iv->vector = cio_dma_zalloc(size); if (!iv->vector) @@ -185,7 +189,7 @@ out_free: kfree(iv->avail); if (iv->flags & AIRQ_IV_CACHELINE && iv->vector) dma_pool_free(airq_iv_cache, iv->vector, iv->vector_dma); - else + else if (!(iv->flags & AIRQ_IV_GUESTVEC)) cio_dma_free(iv->vector, size); kfree(iv); out: @@ -204,7 +208,7 @@ void airq_iv_release(struct airq_iv *iv) kfree(iv->bitlock); if (iv->flags & AIRQ_IV_CACHELINE) dma_pool_free(airq_iv_cache, iv->vector, iv->vector_dma); - else + else if (!(iv->flags & AIRQ_IV_GUESTVEC)) cio_dma_free(iv->vector, iv_size(iv->bits)); kfree(iv->avail); kfree(iv); diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 58cca50996ee..51bef226d33f 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -242,7 +242,7 @@ static struct airq_info *new_airq_info(int index) return NULL; rwlock_init(&info->lock); info->aiv = airq_iv_create(VIRTIO_IV_BITS, AIRQ_IV_ALLOC | AIRQ_IV_PTR - | AIRQ_IV_CACHELINE); + | AIRQ_IV_CACHELINE, NULL); if (!info->aiv) { kfree(info); return NULL; -- cgit From 062f002485d4d5f26f9e8fbce831fd28c4b75ca5 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:11 -0400 Subject: s390/pci: externalize the SIC operation controls and routine A subsequent patch will be issuing SIC from KVM -- export the necessary routine and make the operation control definitions available from a header. Because the routine will now be exported, let's rename __zpci_set_irq_ctrl to zpci_set_irq_ctrl and get rid of the zero'd iib wrapper function of the same name. Reviewed-by: Niklas Schnelle Reviewed-by: Claudio Imbrenda Reviewed-by: Pierre Morel Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-8-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/pci_insn.h | 17 +++++++++-------- arch/s390/pci/pci_insn.c | 3 ++- arch/s390/pci/pci_irq.c | 26 ++++++++++++-------------- 3 files changed, 23 insertions(+), 23 deletions(-) diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index 61cf9531f68f..5331082fa516 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -98,6 +98,14 @@ struct zpci_fib { u32 gd; } __packed __aligned(8); +/* Set Interruption Controls Operation Controls */ +#define SIC_IRQ_MODE_ALL 0 +#define SIC_IRQ_MODE_SINGLE 1 +#define SIC_IRQ_MODE_DIRECT 4 +#define SIC_IRQ_MODE_D_ALL 16 +#define SIC_IRQ_MODE_D_SINGLE 17 +#define SIC_IRQ_MODE_SET_CPU 18 + /* directed interruption information block */ struct zpci_diib { u32 : 1; @@ -134,13 +142,6 @@ int __zpci_store(u64 data, u64 req, u64 offset); int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len); int __zpci_store_block(const u64 *data, u64 req, u64 offset); void zpci_barrier(void); -int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib); - -static inline int zpci_set_irq_ctrl(u16 ctl, u8 isc) -{ - union zpci_sic_iib iib = {{0}}; - - return __zpci_set_irq_ctrl(ctl, isc, &iib); -} +int zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib); #endif diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index 1a822b7799f8..5798178aec9d 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -138,7 +138,7 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range) } /* Set Interruption Controls */ -int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib) +int zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib) { if (!test_facility(72)) return -EIO; @@ -149,6 +149,7 @@ int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib) return 0; } +EXPORT_SYMBOL_GPL(zpci_set_irq_ctrl); /* PCI Load */ static inline int ____pcilg(u64 *data, u64 req, u64 offset, u8 *status) diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 87c7d121c255..f2b3145b6697 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -15,13 +15,6 @@ static enum {FLOATING, DIRECTED} irq_delivery; -#define SIC_IRQ_MODE_ALL 0 -#define SIC_IRQ_MODE_SINGLE 1 -#define SIC_IRQ_MODE_DIRECT 4 -#define SIC_IRQ_MODE_D_ALL 16 -#define SIC_IRQ_MODE_D_SINGLE 17 -#define SIC_IRQ_MODE_SET_CPU 18 - /* * summary bit vector * FLOATING - summary bit per function @@ -154,6 +147,7 @@ static struct irq_chip zpci_irq_chip = { static void zpci_handle_cpu_local_irq(bool rescan) { struct airq_iv *dibv = zpci_ibv[smp_processor_id()]; + union zpci_sic_iib iib = {{0}}; unsigned long bit; int irqs_on = 0; @@ -165,7 +159,7 @@ static void zpci_handle_cpu_local_irq(bool rescan) /* End of second scan with interrupts on. */ break; /* First scan complete, reenable interrupts. */ - if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC)) + if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &iib)) break; bit = 0; continue; @@ -193,6 +187,7 @@ static void zpci_handle_remote_irq(void *data) static void zpci_handle_fallback_irq(void) { struct cpu_irq_data *cpu_data; + union zpci_sic_iib iib = {{0}}; unsigned long cpu; int irqs_on = 0; @@ -203,7 +198,7 @@ static void zpci_handle_fallback_irq(void) /* End of second scan with interrupts on. */ break; /* First scan complete, reenable interrupts. */ - if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC)) + if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib)) break; cpu = 0; continue; @@ -234,6 +229,7 @@ static void zpci_directed_irq_handler(struct airq_struct *airq, static void zpci_floating_irq_handler(struct airq_struct *airq, struct tpi_info *tpi_info) { + union zpci_sic_iib iib = {{0}}; unsigned long si, ai; struct airq_iv *aibv; int irqs_on = 0; @@ -247,7 +243,7 @@ static void zpci_floating_irq_handler(struct airq_struct *airq, /* End of second scan with interrupts on. */ break; /* First scan complete, reenable interrupts. */ - if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC)) + if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib)) break; si = 0; continue; @@ -407,11 +403,12 @@ static struct airq_struct zpci_airq = { static void __init cpu_enable_directed_irq(void *unused) { union zpci_sic_iib iib = {{0}}; + union zpci_sic_iib ziib = {{0}}; iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector; - __zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib); - zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC); + zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib); + zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &ziib); } static int __init zpci_directed_irq_init(void) @@ -426,7 +423,7 @@ static int __init zpci_directed_irq_init(void) iib.diib.isc = PCI_ISC; iib.diib.nr_cpus = num_possible_cpus(); iib.diib.disb_addr = virt_to_phys(zpci_sbv->vector); - __zpci_set_irq_ctrl(SIC_IRQ_MODE_DIRECT, 0, &iib); + zpci_set_irq_ctrl(SIC_IRQ_MODE_DIRECT, 0, &iib); zpci_ibv = kcalloc(num_possible_cpus(), sizeof(*zpci_ibv), GFP_KERNEL); @@ -471,6 +468,7 @@ out_free: int __init zpci_irq_init(void) { + union zpci_sic_iib iib = {{0}}; int rc; irq_delivery = sclp.has_dirq ? DIRECTED : FLOATING; @@ -502,7 +500,7 @@ int __init zpci_irq_init(void) * Enable floating IRQs (with suppression after one IRQ). When using * directed IRQs this enables the fallback path. */ - zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC); + zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib); return 0; out_airq: -- cgit From c68468ed3416ea88d7b14dabb1fa584c3a90cd85 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:12 -0400 Subject: s390/pci: stash associated GISA designation For passthrough devices, we will need to know the GISA designation of the guest if interpretation facilities are to be used. Setup to stash this in the zdev and set a default of 0 (no GISA designation) for now; a subsequent patch will set a valid GISA designation for passthrough devices. Also, extend mpcific routines to specify this stashed designation as part of the mpcific command. Reviewed-by: Pierre Morel Reviewed-by: Niklas Schnelle Reviewed-by: Christian Borntraeger Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-9-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/pci.h | 1 + arch/s390/include/asm/pci_clp.h | 3 ++- arch/s390/pci/pci.c | 6 ++++++ arch/s390/pci/pci_clp.c | 5 +++++ arch/s390/pci/pci_irq.c | 5 +++++ 5 files changed, 19 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index fdb9745ee998..42a4a312a6dd 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -123,6 +123,7 @@ struct zpci_dev { enum zpci_state state; u32 fid; /* function ID, used by sclp */ u32 fh; /* function handle, used by insn's */ + u32 gisa; /* GISA designation for passthrough */ u16 vfn; /* virtual function number */ u16 pchid; /* physical channel ID */ u8 pfgid; /* function group ID */ diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h index 1f4b666e85ee..f3286bc5ba6e 100644 --- a/arch/s390/include/asm/pci_clp.h +++ b/arch/s390/include/asm/pci_clp.h @@ -173,7 +173,8 @@ struct clp_req_set_pci { u16 reserved2; u8 oc; /* operation controls */ u8 ndas; /* number of dma spaces */ - u64 reserved3; + u32 reserved3; + u32 gisa; /* GISA designation */ } __packed; /* Set PCI function response */ diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index bc980fd313d5..c8b9d866434c 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -120,6 +120,7 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas, fib.pba = base; fib.pal = limit; fib.iota = iota | ZPCI_IOTA_RTTO_FLAG; + fib.gd = zdev->gisa; cc = zpci_mod_fc(req, &fib, &status); if (cc) zpci_dbg(3, "reg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status); @@ -133,6 +134,8 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas) struct zpci_fib fib = {0}; u8 cc, status; + fib.gd = zdev->gisa; + cc = zpci_mod_fc(req, &fib, &status); if (cc) zpci_dbg(3, "unreg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status); @@ -160,6 +163,7 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev) atomic64_set(&zdev->unmapped_pages, 0); fib.fmb_addr = virt_to_phys(zdev->fmb); + fib.gd = zdev->gisa; cc = zpci_mod_fc(req, &fib, &status); if (cc) { kmem_cache_free(zdev_fmb_cache, zdev->fmb); @@ -178,6 +182,8 @@ int zpci_fmb_disable_device(struct zpci_dev *zdev) if (!zdev->fmb) return -EINVAL; + fib.gd = zdev->gisa; + /* Function measurement is disabled if fmb address is zero */ cc = zpci_mod_fc(req, &fib, &status); if (cc == 3) /* Function already gone. */ diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 375e0a5120bc..d058c83467ef 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -229,12 +229,16 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as, u8 comma { struct clp_req_rsp_set_pci *rrb; int rc, retries = 100; + u32 gisa = 0; *fh = 0; rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) return -ENOMEM; + if (command != CLP_SET_DISABLE_PCI_FN) + gisa = zdev->gisa; + do { memset(rrb, 0, sizeof(*rrb)); rrb->request.hdr.len = sizeof(rrb->request); @@ -243,6 +247,7 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as, u8 comma rrb->request.fh = zdev->fh; rrb->request.oc = command; rrb->request.ndas = nr_dma_as; + rrb->request.gisa = gisa; rc = clp_req(rrb, CLP_LPS_PCI); if (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY) { diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index f2b3145b6697..a2b42a63a53b 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -43,6 +43,7 @@ static int zpci_set_airq(struct zpci_dev *zdev) fib.fmt0.aibvo = 0; /* each zdev has its own interrupt vector */ fib.fmt0.aisb = virt_to_phys(zpci_sbv->vector) + (zdev->aisb / 64) * 8; fib.fmt0.aisbo = zdev->aisb & 63; + fib.gd = zdev->gisa; return zpci_mod_fc(req, &fib, &status) ? -EIO : 0; } @@ -54,6 +55,8 @@ static int zpci_clear_airq(struct zpci_dev *zdev) struct zpci_fib fib = {0}; u8 cc, status; + fib.gd = zdev->gisa; + cc = zpci_mod_fc(req, &fib, &status); if (cc == 3 || (cc == 1 && status == 24)) /* Function already gone or IRQs already deregistered. */ @@ -72,6 +75,7 @@ static int zpci_set_directed_irq(struct zpci_dev *zdev) fib.fmt = 1; fib.fmt1.noi = zdev->msi_nr_irqs; fib.fmt1.dibvo = zdev->msi_first_bit; + fib.gd = zdev->gisa; return zpci_mod_fc(req, &fib, &status) ? -EIO : 0; } @@ -84,6 +88,7 @@ static int zpci_clear_directed_irq(struct zpci_dev *zdev) u8 cc, status; fib.fmt = 1; + fib.gd = zdev->gisa; cc = zpci_mod_fc(req, &fib, &status); if (cc == 3 || (cc == 1 && status == 24)) /* Function already gone or IRQs already deregistered. */ -- cgit From d10384677630aa18c3ee0e8db915336c9ad9dec0 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:13 -0400 Subject: s390/pci: stash dtsm and maxstbl Store information about what IOAT designation types are supported by underlying hardware as well as the largest store block size allowed. These values will be needed by passthrough. Reviewed-by: Niklas Schnelle Reviewed-by: Pierre Morel Reviewed-by: Christian Borntraeger Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-10-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/pci.h | 2 ++ arch/s390/include/asm/pci_clp.h | 6 ++++-- arch/s390/pci/pci_clp.c | 2 ++ 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 42a4a312a6dd..4c5b8fbc2079 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -126,9 +126,11 @@ struct zpci_dev { u32 gisa; /* GISA designation for passthrough */ u16 vfn; /* virtual function number */ u16 pchid; /* physical channel ID */ + u16 maxstbl; /* Maximum store block size */ u8 pfgid; /* function group ID */ u8 pft; /* pci function type */ u8 port; + u8 dtsm; /* Supported DT mask */ u8 rid_available : 1; u8 has_hp_slot : 1; u8 has_resources : 1; diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h index f3286bc5ba6e..d6189ed14f84 100644 --- a/arch/s390/include/asm/pci_clp.h +++ b/arch/s390/include/asm/pci_clp.h @@ -153,9 +153,11 @@ struct clp_rsp_query_pci_grp { u8 : 6; u8 frame : 1; u8 refresh : 1; /* TLB refresh mode */ - u16 reserved2; + u16 : 3; + u16 maxstbl : 13; /* Maximum store block size */ u16 mui; - u16 : 16; + u8 dtsm; /* Supported DT mask */ + u8 reserved3; u16 maxfaal; u16 : 4; u16 dnoi : 12; diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index d058c83467ef..ee367798e388 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -106,6 +106,8 @@ static void clp_store_query_pci_fngrp(struct zpci_dev *zdev, zdev->max_msi = response->noi; zdev->fmb_update = response->mui; zdev->version = response->version; + zdev->maxstbl = response->maxstbl; + zdev->dtsm = response->dtsm; switch (response->version) { case 1: -- cgit From c435c54639aa5513ab877c8b014dd83d4ce6b40e Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:14 -0400 Subject: vfio/pci: introduce CONFIG_VFIO_PCI_ZDEV_KVM The current contents of vfio-pci-zdev are today only useful in a KVM environment; let's tie everything currently under vfio-pci-zdev to this Kconfig statement and require KVM in this case, reducing complexity (e.g. symbol lookups). Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Reviewed-by: Pierre Morel Link: https://lore.kernel.org/r/20220606203325.110625-11-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- drivers/vfio/pci/Kconfig | 11 +++++++++++ drivers/vfio/pci/Makefile | 2 +- include/linux/vfio_pci_core.h | 2 +- 3 files changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index 4da1914425e1..f9d0c908e738 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -44,6 +44,17 @@ config VFIO_PCI_IGD To enable Intel IGD assignment through vfio-pci, say Y. endif +config VFIO_PCI_ZDEV_KVM + bool "VFIO PCI extensions for s390x KVM passthrough" + depends on S390 && KVM + default y + help + Support s390x-specific extensions to enable support for enhancements + to KVM passthrough capabilities, such as interpretive execution of + zPCI instructions. + + To enable s390x KVM vfio-pci extensions, say Y. + source "drivers/vfio/pci/mlx5/Kconfig" source "drivers/vfio/pci/hisilicon/Kconfig" diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 7052ebd893e0..24c524224da5 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o -vfio-pci-core-$(CONFIG_S390) += vfio_pci_zdev.o +vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o vfio-pci-y := vfio_pci.o diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 23c176d4b073..63af2897939c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -206,7 +206,7 @@ static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) } #endif -#ifdef CONFIG_S390 +#ifdef CONFIG_VFIO_PCI_ZDEV_KVM extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, struct vfio_info_cap *caps); #else -- cgit From 6438e30714abd1bf7408356d3e86127d1fb379c0 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:15 -0400 Subject: KVM: s390: pci: add basic kvm_zdev structure This structure will be used to carry kvm passthrough information related to zPCI devices. Reviewed-by: Niklas Schnelle Reviewed-by: Pierre Morel Reviewed-by: Christian Borntraeger Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-12-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/pci.h | 3 +++ arch/s390/kvm/Makefile | 1 + arch/s390/kvm/pci.c | 36 ++++++++++++++++++++++++++++++++++++ arch/s390/kvm/pci.h | 21 +++++++++++++++++++++ 4 files changed, 61 insertions(+) create mode 100644 arch/s390/kvm/pci.c create mode 100644 arch/s390/kvm/pci.h diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 4c5b8fbc2079..50f1851edfbe 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -97,6 +97,7 @@ struct zpci_bar_struct { }; struct s390_domain; +struct kvm_zdev; #define ZPCI_FUNCTIONS_PER_BUS 256 struct zpci_bus { @@ -189,7 +190,9 @@ struct zpci_dev { struct dentry *debugfs_dev; + /* IOMMU and passthrough */ struct s390_domain *s390_domain; /* s390 IOMMU domain data */ + struct kvm_zdev *kzdev; }; static inline bool zdev_enabled(struct zpci_dev *zdev) diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 26f4a74e5ce4..02217fb4ae10 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -10,4 +10,5 @@ ccflags-y := -Ivirt/kvm -Iarch/s390/kvm kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o +kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c new file mode 100644 index 000000000000..e27191ea27c4 --- /dev/null +++ b/arch/s390/kvm/pci.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * s390 kvm PCI passthrough support + * + * Copyright IBM Corp. 2022 + * + * Author(s): Matthew Rosato + */ + +#include +#include +#include "pci.h" + +static int kvm_s390_pci_dev_open(struct zpci_dev *zdev) +{ + struct kvm_zdev *kzdev; + + kzdev = kzalloc(sizeof(struct kvm_zdev), GFP_KERNEL); + if (!kzdev) + return -ENOMEM; + + kzdev->zdev = zdev; + zdev->kzdev = kzdev; + + return 0; +} + +static void kvm_s390_pci_dev_release(struct zpci_dev *zdev) +{ + struct kvm_zdev *kzdev; + + kzdev = zdev->kzdev; + WARN_ON(kzdev->zdev != zdev); + zdev->kzdev = NULL; + kfree(kzdev); +} diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h new file mode 100644 index 000000000000..ce93978e8913 --- /dev/null +++ b/arch/s390/kvm/pci.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * s390 kvm PCI passthrough support + * + * Copyright IBM Corp. 2022 + * + * Author(s): Matthew Rosato + */ + +#ifndef __KVM_S390_PCI_H +#define __KVM_S390_PCI_H + +#include +#include + +struct kvm_zdev { + struct zpci_dev *zdev; + struct kvm *kvm; +}; + +#endif /* __KVM_S390_PCI_H */ -- cgit From 98b1d33dac5fd09060486762c02fd1a78baeb1e0 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:16 -0400 Subject: KVM: s390: pci: do initial setup for AEN interpretation Initial setup for Adapter Event Notification Interpretation for zPCI passthrough devices. Specifically, allocate a structure for forwarding of adapter events and pass the address of this structure to firmware. Reviewed-by: Christian Borntraeger Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-13-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/pci.h | 4 + arch/s390/include/asm/pci_insn.h | 12 +++ arch/s390/kvm/interrupt.c | 14 ++++ arch/s390/kvm/kvm-s390.c | 11 +++ arch/s390/kvm/pci.c | 160 +++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/pci.h | 49 ++++++++++++ arch/s390/pci/pci.c | 6 ++ 7 files changed, 256 insertions(+) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 50f1851edfbe..322060a75d9f 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #define PCIBIOS_MIN_IO 0x1000 @@ -204,6 +205,9 @@ extern const struct attribute_group *zpci_attr_groups[]; extern unsigned int s390_pci_force_floating __initdata; extern unsigned int s390_pci_no_rid; +extern union zpci_sic_iib *zpci_aipb; +extern struct airq_iv *zpci_aif_sbv; + /* ----------------------------------------------------------------------------- Prototypes ----------------------------------------------------------------------------- */ diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index 5331082fa516..e5f57cfe1d45 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -101,6 +101,7 @@ struct zpci_fib { /* Set Interruption Controls Operation Controls */ #define SIC_IRQ_MODE_ALL 0 #define SIC_IRQ_MODE_SINGLE 1 +#define SIC_SET_AENI_CONTROLS 2 #define SIC_IRQ_MODE_DIRECT 4 #define SIC_IRQ_MODE_D_ALL 16 #define SIC_IRQ_MODE_D_SINGLE 17 @@ -127,9 +128,20 @@ struct zpci_cdiib { u64 : 64; } __packed __aligned(8); +/* adapter interruption parameters block */ +struct zpci_aipb { + u64 faisb; + u64 gait; + u16 : 13; + u16 afi : 3; + u32 : 32; + u16 faal; +} __packed __aligned(8); + union zpci_sic_iib { struct zpci_diib diib; struct zpci_cdiib cdiib; + struct zpci_aipb aipb; }; DECLARE_STATIC_KEY_FALSE(have_mio); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 17ff475157d8..37ff4358121a 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -32,6 +32,7 @@ #include "kvm-s390.h" #include "gaccess.h" #include "trace-s390.h" +#include "pci.h" #define PFAULT_INIT 0x0600 #define PFAULT_DONE 0x0680 @@ -3328,6 +3329,11 @@ void kvm_s390_gib_destroy(void) { if (!gib) return; + if (kvm_s390_pci_interp_allowed() && aift) { + mutex_lock(&aift->aift_lock); + kvm_s390_pci_aen_exit(); + mutex_unlock(&aift->aift_lock); + } chsc_sgib(0); unregister_adapter_interrupt(&gib_alert_irq); free_page((unsigned long)gib); @@ -3365,6 +3371,14 @@ int kvm_s390_gib_init(u8 nisc) goto out_unreg_gal; } + if (kvm_s390_pci_interp_allowed()) { + if (kvm_s390_pci_aen_init(nisc)) { + pr_err("Initializing AEN for PCI failed\n"); + rc = -EIO; + goto out_unreg_gal; + } + } + KVM_EVENT(3, "gib 0x%pK (nisc=%d) initialized", gib, gib->nisc); goto out; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 8fcb56141689..251eaaff9c67 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -47,6 +47,7 @@ #include #include "kvm-s390.h" #include "gaccess.h" +#include "pci.h" #define CREATE_TRACE_POINTS #include "trace.h" @@ -502,6 +503,14 @@ int kvm_arch_init(void *opaque) goto out; } + if (kvm_s390_pci_interp_allowed()) { + rc = kvm_s390_pci_init(); + if (rc) { + pr_err("Unable to allocate AIFT for PCI\n"); + goto out; + } + } + rc = kvm_s390_gib_init(GAL_ISC); if (rc) goto out; @@ -516,6 +525,8 @@ out: void kvm_arch_exit(void) { kvm_s390_gib_destroy(); + if (kvm_s390_pci_interp_allowed()) + kvm_s390_pci_exit(); debug_unregister(kvm_s390_dbf); debug_unregister(kvm_s390_dbf_uv); } diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index e27191ea27c4..d566551d3018 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -9,8 +9,149 @@ #include #include +#include +#include #include "pci.h" +struct zpci_aift *aift; + +static inline int __set_irq_noiib(u16 ctl, u8 isc) +{ + union zpci_sic_iib iib = {{0}}; + + return zpci_set_irq_ctrl(ctl, isc, &iib); +} + +void kvm_s390_pci_aen_exit(void) +{ + unsigned long flags; + struct kvm_zdev **gait_kzdev; + + lockdep_assert_held(&aift->aift_lock); + + /* + * Contents of the aipb remain registered for the life of the host + * kernel, the information preserved in zpci_aipb and zpci_aif_sbv + * in case we insert the KVM module again later. Clear the AIFT + * information and free anything not registered with underlying + * firmware. + */ + spin_lock_irqsave(&aift->gait_lock, flags); + gait_kzdev = aift->kzdev; + aift->gait = NULL; + aift->sbv = NULL; + aift->kzdev = NULL; + spin_unlock_irqrestore(&aift->gait_lock, flags); + + kfree(gait_kzdev); +} + +static int zpci_setup_aipb(u8 nisc) +{ + struct page *page; + int size, rc; + + zpci_aipb = kzalloc(sizeof(union zpci_sic_iib), GFP_KERNEL); + if (!zpci_aipb) + return -ENOMEM; + + aift->sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, 0); + if (!aift->sbv) { + rc = -ENOMEM; + goto free_aipb; + } + zpci_aif_sbv = aift->sbv; + size = get_order(PAGE_ALIGN(ZPCI_NR_DEVICES * + sizeof(struct zpci_gaite))); + page = alloc_pages(GFP_KERNEL | __GFP_ZERO, size); + if (!page) { + rc = -ENOMEM; + goto free_sbv; + } + aift->gait = (struct zpci_gaite *)page_to_phys(page); + + zpci_aipb->aipb.faisb = virt_to_phys(aift->sbv->vector); + zpci_aipb->aipb.gait = virt_to_phys(aift->gait); + zpci_aipb->aipb.afi = nisc; + zpci_aipb->aipb.faal = ZPCI_NR_DEVICES; + + /* Setup Adapter Event Notification Interpretation */ + if (zpci_set_irq_ctrl(SIC_SET_AENI_CONTROLS, 0, zpci_aipb)) { + rc = -EIO; + goto free_gait; + } + + return 0; + +free_gait: + free_pages((unsigned long)aift->gait, size); +free_sbv: + airq_iv_release(aift->sbv); + zpci_aif_sbv = NULL; +free_aipb: + kfree(zpci_aipb); + zpci_aipb = NULL; + + return rc; +} + +static int zpci_reset_aipb(u8 nisc) +{ + /* + * AEN registration can only happen once per system boot. If + * an aipb already exists then AEN was already registered and + * we can re-use the aipb contents. This can only happen if + * the KVM module was removed and re-inserted. However, we must + * ensure that the same forwarding ISC is used as this is assigned + * during KVM module load. + */ + if (zpci_aipb->aipb.afi != nisc) + return -EINVAL; + + aift->sbv = zpci_aif_sbv; + aift->gait = (struct zpci_gaite *)zpci_aipb->aipb.gait; + + return 0; +} + +int kvm_s390_pci_aen_init(u8 nisc) +{ + int rc = 0; + + /* If already enabled for AEN, bail out now */ + if (aift->gait || aift->sbv) + return -EPERM; + + mutex_lock(&aift->aift_lock); + aift->kzdev = kcalloc(ZPCI_NR_DEVICES, sizeof(struct kvm_zdev), + GFP_KERNEL); + if (!aift->kzdev) { + rc = -ENOMEM; + goto unlock; + } + + if (!zpci_aipb) + rc = zpci_setup_aipb(nisc); + else + rc = zpci_reset_aipb(nisc); + if (rc) + goto free_zdev; + + /* Enable floating IRQs */ + if (__set_irq_noiib(SIC_IRQ_MODE_SINGLE, nisc)) { + rc = -EIO; + kvm_s390_pci_aen_exit(); + } + + goto unlock; + +free_zdev: + kfree(aift->kzdev); +unlock: + mutex_unlock(&aift->aift_lock); + return rc; +} + static int kvm_s390_pci_dev_open(struct zpci_dev *zdev) { struct kvm_zdev *kzdev; @@ -34,3 +175,22 @@ static void kvm_s390_pci_dev_release(struct zpci_dev *zdev) zdev->kzdev = NULL; kfree(kzdev); } + +int kvm_s390_pci_init(void) +{ + aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL); + if (!aift) + return -ENOMEM; + + spin_lock_init(&aift->gait_lock); + mutex_init(&aift->aift_lock); + + return 0; +} + +void kvm_s390_pci_exit(void) +{ + mutex_destroy(&aift->aift_lock); + + kfree(aift); +} diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index ce93978e8913..c357d900f8b0 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -12,10 +12,59 @@ #include #include +#include +#include +#include struct kvm_zdev { struct zpci_dev *zdev; struct kvm *kvm; }; +struct zpci_gaite { + u32 gisa; + u8 gisc; + u8 count; + u8 reserved; + u8 aisbo; + u64 aisb; +}; + +struct zpci_aift { + struct zpci_gaite *gait; + struct airq_iv *sbv; + struct kvm_zdev **kzdev; + spinlock_t gait_lock; /* Protects the gait, used during AEN forward */ + struct mutex aift_lock; /* Protects the other structures in aift */ +}; + +extern struct zpci_aift *aift; + +int kvm_s390_pci_aen_init(u8 nisc); +void kvm_s390_pci_aen_exit(void); + +int kvm_s390_pci_init(void); +void kvm_s390_pci_exit(void); + +static inline bool kvm_s390_pci_interp_allowed(void) +{ + struct cpuid cpu_id; + + get_cpu_id(&cpu_id); + switch (cpu_id.machine) { + case 0x2817: + case 0x2818: + case 0x2827: + case 0x2828: + case 0x2964: + case 0x2965: + /* No SHM on certain machines */ + return false; + default: + return (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) && + sclp.has_zpci_lsi && sclp.has_aeni && sclp.has_aisi && + sclp.has_aisii); + } +} + #endif /* __KVM_S390_PCI_H */ diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index c8b9d866434c..86cd4d8446b1 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -61,6 +61,12 @@ DEFINE_STATIC_KEY_FALSE(have_mio); static struct kmem_cache *zdev_fmb_cache; +/* AEN structures that must be preserved over KVM module re-insertion */ +union zpci_sic_iib *zpci_aipb; +EXPORT_SYMBOL_GPL(zpci_aipb); +struct airq_iv *zpci_aif_sbv; +EXPORT_SYMBOL_GPL(zpci_aif_sbv); + struct zpci_dev *get_zdev_by_fid(u32 fid) { struct zpci_dev *tmp, *zdev = NULL; -- cgit From 73f91b004321f2510fa79e66035dbbf1870fcf56 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:17 -0400 Subject: KVM: s390: pci: enable host forwarding of Adapter Event Notifications In cases where interrupts are not forwarded to the guest via firmware, KVM is responsible for ensuring delivery. When an interrupt presents with the forwarding bit, we must process the forwarding tables until all interrupts are delivered. Reviewed-by: Christian Borntraeger Reviewed-by: Pierre Morel Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-14-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/kvm_host.h | 1 + arch/s390/include/asm/tpi.h | 13 +++++++ arch/s390/kvm/interrupt.c | 78 +++++++++++++++++++++++++++++++++++++++- arch/s390/kvm/kvm-s390.c | 3 +- arch/s390/kvm/pci.h | 10 ++++++ 5 files changed, 103 insertions(+), 2 deletions(-) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 766028d54a3e..c1518a505060 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -759,6 +759,7 @@ struct kvm_vm_stat { u64 inject_pfault_done; u64 inject_service_signal; u64 inject_virtio; + u64 aen_forward; }; struct kvm_arch_memory_slot { diff --git a/arch/s390/include/asm/tpi.h b/arch/s390/include/asm/tpi.h index 1ac538b8cbf5..f76e5fdff23a 100644 --- a/arch/s390/include/asm/tpi.h +++ b/arch/s390/include/asm/tpi.h @@ -19,6 +19,19 @@ struct tpi_info { u32 :12; } __packed __aligned(4); +/* I/O-Interruption Code as stored by TPI for an Adapter I/O */ +struct tpi_adapter_info { + u32 aism:8; + u32 :22; + u32 error:1; + u32 forward:1; + u32 reserved; + u32 adapter_IO:1; + u32 directed_irq:1; + u32 isc:3; + u32 :27; +} __packed __aligned(4); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_S390_TPI_H */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 37ff4358121a..d8e1fce78b7c 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3313,11 +3313,87 @@ out: } EXPORT_SYMBOL_GPL(kvm_s390_gisc_unregister); +static void aen_host_forward(unsigned long si) +{ + struct kvm_s390_gisa_interrupt *gi; + struct zpci_gaite *gaite; + struct kvm *kvm; + + gaite = (struct zpci_gaite *)aift->gait + + (si * sizeof(struct zpci_gaite)); + if (gaite->count == 0) + return; + if (gaite->aisb != 0) + set_bit_inv(gaite->aisbo, (unsigned long *)gaite->aisb); + + kvm = kvm_s390_pci_si_to_kvm(aift, si); + if (!kvm) + return; + gi = &kvm->arch.gisa_int; + + if (!(gi->origin->g1.simm & AIS_MODE_MASK(gaite->gisc)) || + !(gi->origin->g1.nimm & AIS_MODE_MASK(gaite->gisc))) { + gisa_set_ipm_gisc(gi->origin, gaite->gisc); + if (hrtimer_active(&gi->timer)) + hrtimer_cancel(&gi->timer); + hrtimer_start(&gi->timer, 0, HRTIMER_MODE_REL); + kvm->stat.aen_forward++; + } +} + +static void aen_process_gait(u8 isc) +{ + bool found = false, first = true; + union zpci_sic_iib iib = {{0}}; + unsigned long si, flags; + + spin_lock_irqsave(&aift->gait_lock, flags); + + if (!aift->gait) { + spin_unlock_irqrestore(&aift->gait_lock, flags); + return; + } + + for (si = 0;;) { + /* Scan adapter summary indicator bit vector */ + si = airq_iv_scan(aift->sbv, si, airq_iv_end(aift->sbv)); + if (si == -1UL) { + if (first || found) { + /* Re-enable interrupts. */ + zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, isc, + &iib); + first = found = false; + } else { + /* Interrupts on and all bits processed */ + break; + } + found = false; + si = 0; + /* Scan again after re-enabling interrupts */ + continue; + } + found = true; + aen_host_forward(si); + } + + spin_unlock_irqrestore(&aift->gait_lock, flags); +} + static void gib_alert_irq_handler(struct airq_struct *airq, struct tpi_info *tpi_info) { + struct tpi_adapter_info *info = (struct tpi_adapter_info *)tpi_info; + inc_irq_stat(IRQIO_GAL); - process_gib_alert_list(); + + if ((info->forward || info->error) && + IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) { + aen_process_gait(info->isc); + if (info->aism != 0) + process_gib_alert_list(); + } else { + process_gib_alert_list(); + } } static struct airq_struct gib_alert_irq = { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 251eaaff9c67..d96c9be0480b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -64,7 +64,8 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { STATS_DESC_COUNTER(VM, inject_float_mchk), STATS_DESC_COUNTER(VM, inject_pfault_done), STATS_DESC_COUNTER(VM, inject_service_signal), - STATS_DESC_COUNTER(VM, inject_virtio) + STATS_DESC_COUNTER(VM, inject_virtio), + STATS_DESC_COUNTER(VM, aen_forward) }; const struct kvm_stats_header kvm_vm_stats_header = { diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index c357d900f8b0..9f7828d97605 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -40,6 +41,15 @@ struct zpci_aift { extern struct zpci_aift *aift; +static inline struct kvm *kvm_s390_pci_si_to_kvm(struct zpci_aift *aift, + unsigned long si) +{ + if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) || aift->kzdev == 0 || + aift->kzdev[si] == 0) + return 0; + return aift->kzdev[si]->kvm; +}; + int kvm_s390_pci_aen_init(u8 nisc); void kvm_s390_pci_aen_exit(void); -- cgit From 3f4bbb4342ec637b14d0e367e487fd38b31d8b48 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:18 -0400 Subject: KVM: s390: mechanism to enable guest zPCI Interpretation The guest must have access to certain facilities in order to allow interpretive execution of zPCI instructions and adapter event notifications. However, there are some cases where a guest might disable interpretation -- provide a mechanism via which we can defer enabling the associated zPCI interpretation facilities until the guest indicates it wishes to use them. Reviewed-by: Christian Borntraeger Reviewed-by: Pierre Morel Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-15-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/kvm_host.h | 4 ++++ arch/s390/kvm/kvm-s390.c | 38 ++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/kvm-s390.h | 10 ++++++++++ 3 files changed, 52 insertions(+) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index c1518a505060..8e381603b6a7 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -254,7 +254,10 @@ struct kvm_s390_sie_block { #define ECB2_IEP 0x20 #define ECB2_PFMFI 0x08 #define ECB2_ESCA 0x04 +#define ECB2_ZPCI_LSI 0x02 __u8 ecb2; /* 0x0062 */ +#define ECB3_AISI 0x20 +#define ECB3_AISII 0x10 #define ECB3_DEA 0x08 #define ECB3_AES 0x04 #define ECB3_RI 0x01 @@ -940,6 +943,7 @@ struct kvm_arch{ int use_cmma; int use_pfmfi; int use_skf; + int use_zpci_interp; int user_cpu_state_ctrl; int user_sigp; int user_stsi; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d96c9be0480b..a66da3f66114 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1031,6 +1031,42 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) return 0; } +static void kvm_s390_vcpu_pci_setup(struct kvm_vcpu *vcpu) +{ + /* Only set the ECB bits after guest requests zPCI interpretation */ + if (!vcpu->kvm->arch.use_zpci_interp) + return; + + vcpu->arch.sie_block->ecb2 |= ECB2_ZPCI_LSI; + vcpu->arch.sie_block->ecb3 |= ECB3_AISII + ECB3_AISI; +} + +void kvm_s390_vcpu_pci_enable_interp(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + unsigned long i; + + lockdep_assert_held(&kvm->lock); + + if (!kvm_s390_pci_interp_allowed()) + return; + + /* + * If host is configured for PCI and the necessary facilities are + * available, turn on interpretation for the life of this guest + */ + kvm->arch.use_zpci_interp = 1; + + kvm_s390_vcpu_block_all(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_s390_vcpu_pci_setup(vcpu); + kvm_s390_sync_request(KVM_REQ_VSIE_RESTART, vcpu); + } + + kvm_s390_vcpu_unblock_all(kvm); +} + static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) { unsigned long cx; @@ -3336,6 +3372,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) kvm_s390_vcpu_crypto_setup(vcpu); + kvm_s390_vcpu_pci_setup(vcpu); + mutex_lock(&vcpu->kvm->lock); if (kvm_s390_pv_is_protected(vcpu->kvm)) { rc = kvm_s390_pv_create_cpu(vcpu, &uvrc, &uvrrc); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 497d52a83c78..975cffaf13de 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -507,6 +507,16 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu, */ void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm); +/** + * kvm_s390_vcpu_pci_enable_interp + * + * Set the associated PCI attributes for each vcpu to allow for zPCI Load/Store + * interpretation as well as adapter interruption forwarding. + * + * @kvm: the KVM guest + */ +void kvm_s390_vcpu_pci_enable_interp(struct kvm *kvm); + /** * diag9c_forwarding_hz * -- cgit From 3c5a1b6f0a18520a0edd0600fef6f1a8553b8fdc Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:19 -0400 Subject: KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding These routines will be wired into a kvm ioctl in order to respond to requests to enable / disable a device for Adapter Event Notifications / Adapter Interuption Forwarding. Reviewed-by: Christian Borntraeger Acked-by: Niklas Schnelle Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-16-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 247 +++++++++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/pci.h | 1 + arch/s390/pci/pci_insn.c | 1 + include/linux/sched/user.h | 3 +- 4 files changed, 251 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index d566551d3018..b232c8cbaa81 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "pci.h" struct zpci_aift *aift; @@ -152,6 +153,252 @@ unlock: return rc; } +/* Modify PCI: Register floating adapter interruption forwarding */ +static int kvm_zpci_set_airq(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT); + struct zpci_fib fib = {}; + u8 status; + + fib.fmt0.isc = zdev->kzdev->fib.fmt0.isc; + fib.fmt0.sum = 1; /* enable summary notifications */ + fib.fmt0.noi = airq_iv_end(zdev->aibv); + fib.fmt0.aibv = virt_to_phys(zdev->aibv->vector); + fib.fmt0.aibvo = 0; + fib.fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8); + fib.fmt0.aisbo = zdev->aisb & 63; + fib.gd = zdev->gisa; + + return zpci_mod_fc(req, &fib, &status) ? -EIO : 0; +} + +/* Modify PCI: Unregister floating adapter interruption forwarding */ +static int kvm_zpci_clear_airq(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT); + struct zpci_fib fib = {}; + u8 cc, status; + + fib.gd = zdev->gisa; + + cc = zpci_mod_fc(req, &fib, &status); + if (cc == 3 || (cc == 1 && status == 24)) + /* Function already gone or IRQs already deregistered. */ + cc = 0; + + return cc ? -EIO : 0; +} + +static inline void unaccount_mem(unsigned long nr_pages) +{ + struct user_struct *user = get_uid(current_user()); + + if (user) + atomic_long_sub(nr_pages, &user->locked_vm); + if (current->mm) + atomic64_sub(nr_pages, ¤t->mm->pinned_vm); +} + +static inline int account_mem(unsigned long nr_pages) +{ + struct user_struct *user = get_uid(current_user()); + unsigned long page_limit, cur_pages, new_pages; + + page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + do { + cur_pages = atomic_long_read(&user->locked_vm); + new_pages = cur_pages + nr_pages; + if (new_pages > page_limit) + return -ENOMEM; + } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages, + new_pages) != cur_pages); + + atomic64_add(nr_pages, ¤t->mm->pinned_vm); + + return 0; +} + +static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, + bool assist) +{ + struct page *pages[1], *aibv_page, *aisb_page = NULL; + unsigned int msi_vecs, idx; + struct zpci_gaite *gaite; + unsigned long hva, bit; + struct kvm *kvm; + phys_addr_t gaddr; + int rc = 0, gisc, npages, pcount = 0; + + /* + * Interrupt forwarding is only applicable if the device is already + * enabled for interpretation + */ + if (zdev->gisa == 0) + return -EINVAL; + + kvm = zdev->kzdev->kvm; + msi_vecs = min_t(unsigned int, fib->fmt0.noi, zdev->max_msi); + + /* Get the associated forwarding ISC - if invalid, return the error */ + gisc = kvm_s390_gisc_register(kvm, fib->fmt0.isc); + if (gisc < 0) + return gisc; + + /* Replace AIBV address */ + idx = srcu_read_lock(&kvm->srcu); + hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aibv)); + npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, pages); + srcu_read_unlock(&kvm->srcu, idx); + if (npages < 1) { + rc = -EIO; + goto out; + } + aibv_page = pages[0]; + pcount++; + gaddr = page_to_phys(aibv_page) + (fib->fmt0.aibv & ~PAGE_MASK); + fib->fmt0.aibv = gaddr; + + /* Pin the guest AISB if one was specified */ + if (fib->fmt0.sum == 1) { + idx = srcu_read_lock(&kvm->srcu); + hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aisb)); + npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, + pages); + srcu_read_unlock(&kvm->srcu, idx); + if (npages < 1) { + rc = -EIO; + goto unpin1; + } + aisb_page = pages[0]; + pcount++; + } + + /* Account for pinned pages, roll back on failure */ + if (account_mem(pcount)) + goto unpin2; + + /* AISB must be allocated before we can fill in GAITE */ + mutex_lock(&aift->aift_lock); + bit = airq_iv_alloc_bit(aift->sbv); + if (bit == -1UL) + goto unlock; + zdev->aisb = bit; /* store the summary bit number */ + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | + AIRQ_IV_BITLOCK | + AIRQ_IV_GUESTVEC, + phys_to_virt(fib->fmt0.aibv)); + + spin_lock_irq(&aift->gait_lock); + gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * + sizeof(struct zpci_gaite)); + + /* If assist not requested, host will get all alerts */ + if (assist) + gaite->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa); + else + gaite->gisa = 0; + + gaite->gisc = fib->fmt0.isc; + gaite->count++; + gaite->aisbo = fib->fmt0.aisbo; + gaite->aisb = virt_to_phys(page_address(aisb_page) + (fib->fmt0.aisb & + ~PAGE_MASK)); + aift->kzdev[zdev->aisb] = zdev->kzdev; + spin_unlock_irq(&aift->gait_lock); + + /* Update guest FIB for re-issue */ + fib->fmt0.aisbo = zdev->aisb & 63; + fib->fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8); + fib->fmt0.isc = gisc; + + /* Save some guest fib values in the host for later use */ + zdev->kzdev->fib.fmt0.isc = fib->fmt0.isc; + zdev->kzdev->fib.fmt0.aibv = fib->fmt0.aibv; + mutex_unlock(&aift->aift_lock); + + /* Issue the clp to setup the irq now */ + rc = kvm_zpci_set_airq(zdev); + return rc; + +unlock: + mutex_unlock(&aift->aift_lock); +unpin2: + if (fib->fmt0.sum == 1) + unpin_user_page(aisb_page); +unpin1: + unpin_user_page(aibv_page); +out: + return rc; +} + +static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force) +{ + struct kvm_zdev *kzdev = zdev->kzdev; + struct zpci_gaite *gaite; + struct page *vpage = NULL, *spage = NULL; + int rc, pcount = 0; + u8 isc; + + if (zdev->gisa == 0) + return -EINVAL; + + mutex_lock(&aift->aift_lock); + + /* + * If the clear fails due to an error, leave now unless we know this + * device is about to go away (force) -- In that case clear the GAITE + * regardless. + */ + rc = kvm_zpci_clear_airq(zdev); + if (rc && !force) + goto out; + + if (zdev->kzdev->fib.fmt0.aibv == 0) + goto out; + spin_lock_irq(&aift->gait_lock); + gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * + sizeof(struct zpci_gaite)); + isc = gaite->gisc; + gaite->count--; + if (gaite->count == 0) { + /* Release guest AIBV and AISB */ + vpage = phys_to_page(kzdev->fib.fmt0.aibv); + if (gaite->aisb != 0) + spage = phys_to_page(gaite->aisb); + /* Clear the GAIT entry */ + gaite->aisb = 0; + gaite->gisc = 0; + gaite->aisbo = 0; + gaite->gisa = 0; + aift->kzdev[zdev->aisb] = 0; + /* Clear zdev info */ + airq_iv_free_bit(aift->sbv, zdev->aisb); + airq_iv_release(zdev->aibv); + zdev->aisb = 0; + zdev->aibv = NULL; + } + spin_unlock_irq(&aift->gait_lock); + kvm_s390_gisc_unregister(kzdev->kvm, isc); + kzdev->fib.fmt0.isc = 0; + kzdev->fib.fmt0.aibv = 0; + + if (vpage) { + unpin_user_page(vpage); + pcount++; + } + if (spage) { + unpin_user_page(spage); + pcount++; + } + if (pcount > 0) + unaccount_mem(pcount); +out: + mutex_unlock(&aift->aift_lock); + + return rc; +} + static int kvm_s390_pci_dev_open(struct zpci_dev *zdev) { struct kvm_zdev *kzdev; diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index 9f7828d97605..9d091033fc02 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -20,6 +20,7 @@ struct kvm_zdev { struct zpci_dev *zdev; struct kvm *kvm; + struct zpci_fib fib; }; struct zpci_gaite { diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index 5798178aec9d..56480be48244 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -92,6 +92,7 @@ u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status) return cc; } +EXPORT_SYMBOL_GPL(zpci_mod_fc); /* Refresh PCI Translations */ static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 00ed419dd464..f054d0360a75 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -24,7 +24,8 @@ struct user_struct { kuid_t uid; #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ - defined(CONFIG_NET) || defined(CONFIG_IO_URING) + defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \ + defined(CONFIG_VFIO_PCI_ZDEV_KVM) atomic_long_t locked_vm; #endif #ifdef CONFIG_WATCH_QUEUE -- cgit From 09340b2fca007509c3cbc34fdc97961e0abfc589 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:20 -0400 Subject: KVM: s390: pci: add routines to start/stop interpretive execution These routines will be invoked at the time an s390x vfio-pci device is associated with a KVM (or when the association is removed), allowing the zPCI device to enable or disable load/store intepretation mode; this requires the host zPCI device to inform firmware of the unique token (GISA designation) that is associated with the owning KVM. Signed-off-by: Matthew Rosato Acked-by: Pierre Morel Link: https://lore.kernel.org/r/20220606203325.110625-17-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/kvm_host.h | 18 +++++ arch/s390/include/asm/pci.h | 1 + arch/s390/kvm/kvm-s390.c | 15 ++++ arch/s390/kvm/pci.c | 162 +++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/pci.h | 5 ++ arch/s390/pci/pci.c | 4 + 6 files changed, 205 insertions(+) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 8e381603b6a7..6e83d746bae2 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -967,6 +968,8 @@ struct kvm_arch{ DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS); struct kvm_s390_gisa_interrupt gisa_int; struct kvm_s390_pv pv; + struct list_head kzdev_list; + spinlock_t kzdev_list_lock; }; #define KVM_HVA_ERR_BAD (-1UL) @@ -1017,4 +1020,19 @@ static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} +#define __KVM_HAVE_ARCH_VM_FREE +void kvm_arch_free_vm(struct kvm *kvm); + +#ifdef CONFIG_VFIO_PCI_ZDEV_KVM +int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm); +void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev); +#else +static inline int kvm_s390_pci_register_kvm(struct zpci_dev *dev, + struct kvm *kvm) +{ + return -EPERM; +} +static inline void kvm_s390_pci_unregister_kvm(struct zpci_dev *dev) {} +#endif + #endif diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 322060a75d9f..85eb0ef9d4c3 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -194,6 +194,7 @@ struct zpci_dev { /* IOMMU and passthrough */ struct s390_domain *s390_domain; /* s390 IOMMU domain data */ struct kvm_zdev *kzdev; + struct mutex kzdev_lock; }; static inline bool zdev_enabled(struct zpci_dev *zdev) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index a66da3f66114..4758bb731199 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2790,6 +2790,14 @@ static void sca_dispose(struct kvm *kvm) kvm->arch.sca = NULL; } +void kvm_arch_free_vm(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + kvm_s390_pci_clear_list(kvm); + + __kvm_arch_free_vm(kvm); +} + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { gfp_t alloc_flags = GFP_KERNEL_ACCOUNT; @@ -2872,6 +2880,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_s390_crypto_init(kvm); + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) { + mutex_lock(&kvm->lock); + kvm_s390_pci_init_list(kvm); + kvm_s390_vcpu_pci_enable_interp(kvm); + mutex_unlock(&kvm->lock); + } + mutex_init(&kvm->arch.float_int.ais_lock); spin_lock_init(&kvm->arch.float_int.lock); for (i = 0; i < FIRQ_LIST_COUNT; i++) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index b232c8cbaa81..24211741deb0 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -12,7 +12,9 @@ #include #include #include +#include #include "pci.h" +#include "kvm-s390.h" struct zpci_aift *aift; @@ -423,6 +425,166 @@ static void kvm_s390_pci_dev_release(struct zpci_dev *zdev) kfree(kzdev); } + +/* + * Register device with the specified KVM. If interpetation facilities are + * available, enable them and let userspace indicate whether or not they will + * be used (specify SHM bit to disable). + */ +int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm) +{ + int rc; + + if (!zdev) + return -EINVAL; + + mutex_lock(&zdev->kzdev_lock); + + if (zdev->kzdev || zdev->gisa != 0 || !kvm) { + mutex_unlock(&zdev->kzdev_lock); + return -EINVAL; + } + + kvm_get_kvm(kvm); + + mutex_lock(&kvm->lock); + + rc = kvm_s390_pci_dev_open(zdev); + if (rc) + goto err; + + /* + * If interpretation facilities aren't available, add the device to + * the kzdev list but don't enable for interpretation. + */ + if (!kvm_s390_pci_interp_allowed()) + goto out; + + /* + * If this is the first request to use an interpreted device, make the + * necessary vcpu changes + */ + if (!kvm->arch.use_zpci_interp) + kvm_s390_vcpu_pci_enable_interp(kvm); + + if (zdev_enabled(zdev)) { + rc = zpci_disable_device(zdev); + if (rc) + goto err; + } + + /* + * Store information about the identity of the kvm guest allowed to + * access this device via interpretation to be used by host CLP + */ + zdev->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa); + + rc = zpci_enable_device(zdev); + if (rc) + goto clear_gisa; + + /* Re-register the IOMMU that was already created */ + rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, + virt_to_phys(zdev->dma_table)); + if (rc) + goto clear_gisa; + +out: + zdev->kzdev->kvm = kvm; + + spin_lock(&kvm->arch.kzdev_list_lock); + list_add_tail(&zdev->kzdev->entry, &kvm->arch.kzdev_list); + spin_unlock(&kvm->arch.kzdev_list_lock); + + mutex_unlock(&kvm->lock); + mutex_unlock(&zdev->kzdev_lock); + return 0; + +clear_gisa: + zdev->gisa = 0; +err: + if (zdev->kzdev) + kvm_s390_pci_dev_release(zdev); + mutex_unlock(&kvm->lock); + mutex_unlock(&zdev->kzdev_lock); + kvm_put_kvm(kvm); + return rc; +} +EXPORT_SYMBOL_GPL(kvm_s390_pci_register_kvm); + +void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev) +{ + struct kvm *kvm; + + if (!zdev) + return; + + mutex_lock(&zdev->kzdev_lock); + + if (WARN_ON(!zdev->kzdev)) { + mutex_unlock(&zdev->kzdev_lock); + return; + } + + kvm = zdev->kzdev->kvm; + mutex_lock(&kvm->lock); + + /* + * A 0 gisa means interpretation was never enabled, just remove the + * device from the list. + */ + if (zdev->gisa == 0) + goto out; + + /* Forwarding must be turned off before interpretation */ + if (zdev->kzdev->fib.fmt0.aibv != 0) + kvm_s390_pci_aif_disable(zdev, true); + + /* Remove the host CLP guest designation */ + zdev->gisa = 0; + + if (zdev_enabled(zdev)) { + if (zpci_disable_device(zdev)) + goto out; + } + + if (zpci_enable_device(zdev)) + goto out; + + /* Re-register the IOMMU that was already created */ + zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, + virt_to_phys(zdev->dma_table)); + +out: + spin_lock(&kvm->arch.kzdev_list_lock); + list_del(&zdev->kzdev->entry); + spin_unlock(&kvm->arch.kzdev_list_lock); + kvm_s390_pci_dev_release(zdev); + + mutex_unlock(&kvm->lock); + mutex_unlock(&zdev->kzdev_lock); + + kvm_put_kvm(kvm); +} +EXPORT_SYMBOL_GPL(kvm_s390_pci_unregister_kvm); + +void kvm_s390_pci_init_list(struct kvm *kvm) +{ + spin_lock_init(&kvm->arch.kzdev_list_lock); + INIT_LIST_HEAD(&kvm->arch.kzdev_list); +} + +void kvm_s390_pci_clear_list(struct kvm *kvm) +{ + /* + * This list should already be empty, either via vfio device closures + * or kvm fd cleanup. + */ + spin_lock(&kvm->arch.kzdev_list_lock); + WARN_ON_ONCE(!list_empty(&kvm->arch.kzdev_list)); + spin_unlock(&kvm->arch.kzdev_list_lock); +} + int kvm_s390_pci_init(void) { aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL); diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index 9d091033fc02..fb2b91b76e0c 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -21,6 +22,7 @@ struct kvm_zdev { struct zpci_dev *zdev; struct kvm *kvm; struct zpci_fib fib; + struct list_head entry; }; struct zpci_gaite { @@ -54,6 +56,9 @@ static inline struct kvm *kvm_s390_pci_si_to_kvm(struct zpci_aift *aift, int kvm_s390_pci_aen_init(u8 nisc); void kvm_s390_pci_aen_exit(void); +void kvm_s390_pci_init_list(struct kvm *kvm); +void kvm_s390_pci_clear_list(struct kvm *kvm); + int kvm_s390_pci_init(void); void kvm_s390_pci_exit(void); diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 86cd4d8446b1..73cdc5539384 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -132,6 +132,7 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas, zpci_dbg(3, "reg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status); return cc; } +EXPORT_SYMBOL_GPL(zpci_register_ioat); /* Modify PCI: Unregister I/O address translation parameters */ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas) @@ -712,6 +713,7 @@ int zpci_enable_device(struct zpci_dev *zdev) zpci_update_fh(zdev, fh); return rc; } +EXPORT_SYMBOL_GPL(zpci_enable_device); int zpci_disable_device(struct zpci_dev *zdev) { @@ -735,6 +737,7 @@ int zpci_disable_device(struct zpci_dev *zdev) } return rc; } +EXPORT_SYMBOL_GPL(zpci_disable_device); /** * zpci_hot_reset_device - perform a reset of the given zPCI function @@ -828,6 +831,7 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state) kref_init(&zdev->kref); mutex_init(&zdev->lock); + mutex_init(&zdev->kzdev_lock); rc = zpci_init_iommu(zdev); if (rc) -- cgit From 8061d1c31f1a018281bc9877ecce44bfc779e21d Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:21 -0400 Subject: vfio-pci/zdev: add open/close device hooks During vfio-pci open_device, pass the KVM associated with the vfio group (if one exists). This is needed in order to pass a special indicator (GISA) to firmware to allow zPCI interpretation facilities to be used for only the specific KVM associated with the vfio-pci device. During vfio-pci close_device, unregister the notifier. Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Reviewed-by: Pierre Morel Link: https://lore.kernel.org/r/20220606203325.110625-18-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- drivers/vfio/pci/vfio_pci_core.c | 10 +++++++++- drivers/vfio/pci/vfio_pci_zdev.c | 24 ++++++++++++++++++++++++ include/linux/vfio_pci_core.h | 10 ++++++++++ 3 files changed, 43 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index a0d69ddaf90d..b1e5cfbadf38 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -316,10 +316,14 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) pci_write_config_word(pdev, PCI_COMMAND, cmd); } - ret = vfio_config_init(vdev); + ret = vfio_pci_zdev_open_device(vdev); if (ret) goto out_free_state; + ret = vfio_config_init(vdev); + if (ret) + goto out_free_zdev; + msix_pos = pdev->msix_cap; if (msix_pos) { u16 flags; @@ -340,6 +344,8 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) return 0; +out_free_zdev: + vfio_pci_zdev_close_device(vdev); out_free_state: kfree(vdev->pci_saved_state); vdev->pci_saved_state = NULL; @@ -418,6 +424,8 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev) vdev->needs_reset = true; + vfio_pci_zdev_close_device(vdev); + /* * If we have saved state, restore it. If we can reset the device, * even better. Resetting with current state seems better than diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index ea4c0d2b0663..686f2e75e392 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -136,3 +137,26 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, return ret; } + +int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) +{ + struct zpci_dev *zdev = to_zpci(vdev->pdev); + + if (!zdev) + return -ENODEV; + + if (!vdev->vdev.kvm) + return 0; + + return kvm_s390_pci_register_kvm(zdev, vdev->vdev.kvm); +} + +void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev) +{ + struct zpci_dev *zdev = to_zpci(vdev->pdev); + + if (!zdev || !vdev->vdev.kvm) + return; + + kvm_s390_pci_unregister_kvm(zdev); +} diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 63af2897939c..d5d9e17f0156 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -209,12 +209,22 @@ static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) #ifdef CONFIG_VFIO_PCI_ZDEV_KVM extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, struct vfio_info_cap *caps); +int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev); +void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev); #else static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, struct vfio_info_cap *caps) { return -ENODEV; } + +static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) +{ + return 0; +} + +static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev) +{} #endif /* Will be exported for vfio pci drivers usage */ -- cgit From faf3bfcb895037ae2a8b89d1048090c9e1291cae Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:22 -0400 Subject: vfio-pci/zdev: add function handle to clp base capability The function handle is a system-wide unique identifier for a zPCI device. With zPCI instruction interpretation, the host will no longer be executing the zPCI instructions on behalf of the guest. As a result, the guest needs to use the real function handle in order for firmware to associate the instruction with the proper PCI function. Let's provide that handle to the guest. Reviewed-by: Christian Borntraeger Reviewed-by: Pierre Morel Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Link: https://lore.kernel.org/r/20220606203325.110625-19-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- drivers/vfio/pci/vfio_pci_zdev.c | 5 +++-- include/uapi/linux/vfio_zdev.h | 3 +++ 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index 686f2e75e392..4f28cdd7ecd1 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -24,14 +24,15 @@ static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps) { struct vfio_device_info_cap_zpci_base cap = { .header.id = VFIO_DEVICE_INFO_CAP_ZPCI_BASE, - .header.version = 1, + .header.version = 2, .start_dma = zdev->start_dma, .end_dma = zdev->end_dma, .pchid = zdev->pchid, .vfn = zdev->vfn, .fmb_length = zdev->fmb_length, .pft = zdev->pft, - .gid = zdev->pfgid + .gid = zdev->pfgid, + .fh = zdev->fh }; return vfio_info_add_capability(caps, &cap.header, sizeof(cap)); diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h index b4309397b6b2..78c022af3d29 100644 --- a/include/uapi/linux/vfio_zdev.h +++ b/include/uapi/linux/vfio_zdev.h @@ -29,6 +29,9 @@ struct vfio_device_info_cap_zpci_base { __u16 fmb_length; /* Measurement Block Length (in bytes) */ __u8 pft; /* PCI Function Type */ __u8 gid; /* PCI function group ID */ + /* End of version 1 */ + __u32 fh; /* PCI function handle */ + /* End of version 2 */ }; /** -- cgit From ba6090ff8ae01b41288be87ed9f6bed3d8cf5961 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:23 -0400 Subject: vfio-pci/zdev: different maxstbl for interpreted devices When doing load/store interpretation, the maximum store block length is determined by the underlying firmware, not the host kernel API. Reflect that in the associated Query PCI Function Group clp capability and let userspace decide which is appropriate to present to the guest. Reviewed-by: Pierre Morel Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Link: https://lore.kernel.org/r/20220606203325.110625-20-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- drivers/vfio/pci/vfio_pci_zdev.c | 6 ++++-- include/uapi/linux/vfio_zdev.h | 4 ++++ 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index 4f28cdd7ecd1..e163aa9f6144 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -45,14 +45,16 @@ static int zpci_group_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps) { struct vfio_device_info_cap_zpci_group cap = { .header.id = VFIO_DEVICE_INFO_CAP_ZPCI_GROUP, - .header.version = 1, + .header.version = 2, .dasm = zdev->dma_mask, .msi_addr = zdev->msi_addr, .flags = VFIO_DEVICE_INFO_ZPCI_FLAG_REFRESH, .mui = zdev->fmb_update, .noi = zdev->max_msi, .maxstbl = ZPCI_MAX_WRITE_SIZE, - .version = zdev->version + .version = zdev->version, + .reserved = 0, + .imaxstbl = zdev->maxstbl }; return vfio_info_add_capability(caps, &cap.header, sizeof(cap)); diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h index 78c022af3d29..77f2aff1f27e 100644 --- a/include/uapi/linux/vfio_zdev.h +++ b/include/uapi/linux/vfio_zdev.h @@ -50,6 +50,10 @@ struct vfio_device_info_cap_zpci_group { __u16 noi; /* Maximum number of MSIs */ __u16 maxstbl; /* Maximum Store Block Length */ __u8 version; /* Supported PCI Version */ + /* End of version 1 */ + __u8 reserved; + __u16 imaxstbl; /* Maximum Interpreted Store Block Length */ + /* End of version 2 */ }; /** -- cgit From db1c875e0539518e3d5fe9876ef50975cf4476bb Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:24 -0400 Subject: KVM: s390: add KVM_S390_ZPCI_OP to manage guest zPCI devices The KVM_S390_ZPCI_OP ioctl provides a mechanism for managing hardware-assisted virtualization features for s390x zPCI passthrough. Add the first 2 operations, which can be used to enable/disable the specified device for Adapter Event Notification interpretation. Signed-off-by: Matthew Rosato Acked-by: Pierre Morel Reviewed-by: Thomas Huth Link: https://lore.kernel.org/r/20220606203325.110625-21-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- Documentation/virt/kvm/api.rst | 47 +++++++++++++++++++++++ arch/s390/kvm/kvm-s390.c | 16 ++++++++ arch/s390/kvm/pci.c | 85 ++++++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/pci.h | 2 + include/uapi/linux/kvm.h | 31 +++++++++++++++ 5 files changed, 181 insertions(+) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 11e00a46c610..d58354e9af8f 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5802,6 +5802,53 @@ of CPUID leaf 0xD on the host. This ioctl injects an event channel interrupt directly to the guest vCPU. +4.137 KVM_S390_ZPCI_OP +-------------------- + +:Capability: KVM_CAP_S390_ZPCI_OP +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_zpci_op (in) +:Returns: 0 on success, <0 on error + +Used to manage hardware-assisted virtualization features for zPCI devices. + +Parameters are specified via the following structure:: + + struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; + }; + +The type of operation is specified in the "op" field. +KVM_S390_ZPCIOP_REG_AEN is used to register the VM for adapter event +notification interpretation, which will allow firmware delivery of adapter +events directly to the vm, with KVM providing a backup delivery mechanism; +KVM_S390_ZPCIOP_DEREG_AEN is used to subsequently disable interpretation of +adapter event notifications. + +The target zPCI function must also be specified via the "fh" field. For the +KVM_S390_ZPCIOP_REG_AEN operation, additional information to establish firmware +delivery must be provided via the "reg_aen" struct. + +The "pad" and "reserved" fields may be used for future extensions and should be +set to 0s by userspace. + 5. The kvm_run structure ======================== diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 4758bb731199..f214e0fc62ed 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -618,6 +618,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_PROTECTED: r = is_prot_virt_host(); break; + case KVM_CAP_S390_ZPCI_OP: + r = kvm_s390_pci_interp_allowed(); + break; default: r = 0; } @@ -2629,6 +2632,19 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + case KVM_S390_ZPCI_OP: { + struct kvm_s390_zpci_op args; + + r = -EINVAL; + if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + break; + if (copy_from_user(&args, argp, sizeof(args))) { + r = -EFAULT; + break; + } + r = kvm_s390_pci_zpci_op(kvm, &args); + break; + } default: r = -ENOTTY; } diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 24211741deb0..4946fb7757d6 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -585,6 +585,91 @@ void kvm_s390_pci_clear_list(struct kvm *kvm) spin_unlock(&kvm->arch.kzdev_list_lock); } +static struct zpci_dev *get_zdev_from_kvm_by_fh(struct kvm *kvm, u32 fh) +{ + struct zpci_dev *zdev = NULL; + struct kvm_zdev *kzdev; + + spin_lock(&kvm->arch.kzdev_list_lock); + list_for_each_entry(kzdev, &kvm->arch.kzdev_list, entry) { + if (kzdev->zdev->fh == fh) { + zdev = kzdev->zdev; + break; + } + } + spin_unlock(&kvm->arch.kzdev_list_lock); + + return zdev; +} + +static int kvm_s390_pci_zpci_reg_aen(struct zpci_dev *zdev, + struct kvm_s390_zpci_op *args) +{ + struct zpci_fib fib = {}; + bool hostflag; + + fib.fmt0.aibv = args->u.reg_aen.ibv; + fib.fmt0.isc = args->u.reg_aen.isc; + fib.fmt0.noi = args->u.reg_aen.noi; + if (args->u.reg_aen.sb != 0) { + fib.fmt0.aisb = args->u.reg_aen.sb; + fib.fmt0.aisbo = args->u.reg_aen.sbo; + fib.fmt0.sum = 1; + } else { + fib.fmt0.aisb = 0; + fib.fmt0.aisbo = 0; + fib.fmt0.sum = 0; + } + + hostflag = !(args->u.reg_aen.flags & KVM_S390_ZPCIOP_REGAEN_HOST); + return kvm_s390_pci_aif_enable(zdev, &fib, hostflag); +} + +int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args) +{ + struct kvm_zdev *kzdev; + struct zpci_dev *zdev; + int r; + + zdev = get_zdev_from_kvm_by_fh(kvm, args->fh); + if (!zdev) + return -ENODEV; + + mutex_lock(&zdev->kzdev_lock); + mutex_lock(&kvm->lock); + + kzdev = zdev->kzdev; + if (!kzdev) { + r = -ENODEV; + goto out; + } + if (kzdev->kvm != kvm) { + r = -EPERM; + goto out; + } + + switch (args->op) { + case KVM_S390_ZPCIOP_REG_AEN: + /* Fail on unknown flags */ + if (args->u.reg_aen.flags & ~KVM_S390_ZPCIOP_REGAEN_HOST) { + r = -EINVAL; + break; + } + r = kvm_s390_pci_zpci_reg_aen(zdev, args); + break; + case KVM_S390_ZPCIOP_DEREG_AEN: + r = kvm_s390_pci_aif_disable(zdev, false); + break; + default: + r = -EINVAL; + } + +out: + mutex_unlock(&kvm->lock); + mutex_unlock(&zdev->kzdev_lock); + return r; +} + int kvm_s390_pci_init(void) { aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL); diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index fb2b91b76e0c..0351382e990f 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -59,6 +59,8 @@ void kvm_s390_pci_aen_exit(void); void kvm_s390_pci_init_list(struct kvm *kvm); void kvm_s390_pci_clear_list(struct kvm *kvm); +int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args); + int kvm_s390_pci_init(void); void kvm_s390_pci_exit(void); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5088bd9f1922..2f302e2287d1 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1157,6 +1157,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_TSC_CONTROL 214 #define KVM_CAP_SYSTEM_EVENT_DATA 215 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216 +#define KVM_CAP_S390_ZPCI_OP 221 #ifdef KVM_CAP_IRQ_ROUTING @@ -2118,4 +2119,34 @@ struct kvm_stats_desc { /* Available with KVM_CAP_XSAVE2 */ #define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) +/* Available with KVM_CAP_S390_ZPCI_OP */ +#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op) + +struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; +}; + +/* types for kvm_s390_zpci_op->op */ +#define KVM_S390_ZPCIOP_REG_AEN 0 +#define KVM_S390_ZPCIOP_DEREG_AEN 1 + +/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ +#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) + #endif /* __LINUX_KVM_H */ -- cgit From 4ac34b94a5342544baa72ce09fc5e825a9d35070 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:25 -0400 Subject: MAINTAINERS: additional files related kvm s390 pci passthrough Add entries from the s390 kvm subdirectory related to pci passthrough. Acked-by: Christian Borntraeger Signed-off-by: Matthew Rosato Reviewed-by: Thomas Huth Link: https://lore.kernel.org/r/20220606203325.110625-22-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index a6d3bd9d2a8d..3dd8657f5482 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17454,6 +17454,7 @@ M: Eric Farman L: linux-s390@vger.kernel.org L: kvm@vger.kernel.org S: Supported +F: arch/s390/kvm/pci* F: drivers/vfio/pci/vfio_pci_zdev.c F: include/uapi/linux/vfio_zdev.h -- cgit From b9df116cb7656c7e7f869cf9d05b54b3fb3f944b Mon Sep 17 00:00:00 2001 From: Jiang Jian Date: Wed, 22 Jun 2022 22:07:20 +0800 Subject: KVM: s390: drop unexpected word 'and' in the comments there is an unexpected word 'and' in the comments that need to be dropped file: arch/s390/kvm/interrupt.c line: 705 * Subsystem damage are the only two and and are indicated by changed to: * Subsystem damage are the only two and are indicated by Signed-off-by: Jiang Jian Link: https://lore.kernel.org/lkml/20220622140720.7617-1-jiangjian@cdjrlc.com/ Signed-off-by: Janosch Frank --- arch/s390/kvm/interrupt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index d8e1fce78b7c..b9c944b262c7 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -704,7 +704,7 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) /* * We indicate floating repressible conditions along with * other pending conditions. Channel Report Pending and Channel - * Subsystem damage are the only two and and are indicated by + * Subsystem damage are the only two and are indicated by * bits in mcic and masked in cr14. */ if (test_and_clear_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) { -- cgit From 1b6abe95b522b313569469498c8c648a5ee535ba Mon Sep 17 00:00:00 2001 From: Steffen Eiden Date: Wed, 18 May 2022 13:59:08 +0000 Subject: s390: Add attestation query information We have information about the supported attestation header version and plaintext attestation flag bits. Let's expose it via the sysfs files. Signed-off-by: Steffen Eiden Reviewed-by: Claudio Imbrenda Reviewed-by: Janosch Frank Link: https://lore.kernel.org/lkml/20220601100245.3189993-1-seiden@linux.ibm.com/ Signed-off-by: Janosch Frank --- arch/s390/boot/uv.c | 2 ++ arch/s390/include/asm/uv.h | 7 ++++++- arch/s390/kernel/uv.c | 20 ++++++++++++++++++++ 3 files changed, 28 insertions(+), 1 deletion(-) diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c index 67c737c1e580..a5fa667160b2 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -45,6 +45,8 @@ void uv_query_info(void) uv_info.supp_se_hdr_pcf = uvcb.supp_se_hdr_pcf; uv_info.conf_dump_storage_state_len = uvcb.conf_dump_storage_state_len; uv_info.conf_dump_finalize_len = uvcb.conf_dump_finalize_len; + uv_info.supp_att_req_hdr_ver = uvcb.supp_att_req_hdr_ver; + uv_info.supp_att_pflags = uvcb.supp_att_pflags; } #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 3e597bb634bd..18fe04c8547e 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -124,7 +124,10 @@ struct uv_cb_qui { u64 reservedc0; /* 0x00c0 */ u64 conf_dump_storage_state_len; /* 0x00c8 */ u64 conf_dump_finalize_len; /* 0x00d0 */ - u8 reservedd8[256 - 216]; /* 0x00d8 */ + u64 reservedd8; /* 0x00d8 */ + u64 supp_att_req_hdr_ver; /* 0x00e0 */ + u64 supp_att_pflags; /* 0x00e8 */ + u8 reservedf0[256 - 240]; /* 0x00f0 */ } __packed __aligned(8); /* Initialize Ultravisor */ @@ -350,6 +353,8 @@ struct uv_info { unsigned long supp_se_hdr_pcf; unsigned long conf_dump_storage_state_len; unsigned long conf_dump_finalize_len; + unsigned long supp_att_req_hdr_ver; + unsigned long supp_att_pflags; }; extern struct uv_info uv_info; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 84fe33b6af4d..c13d5a7b71f0 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -479,6 +479,24 @@ static ssize_t uv_query_max_guest_addr(struct kobject *kobj, static struct kobj_attribute uv_query_max_guest_addr_attr = __ATTR(max_address, 0444, uv_query_max_guest_addr, NULL); +static ssize_t uv_query_supp_att_req_hdr_ver(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return scnprintf(page, PAGE_SIZE, "%lx\n", uv_info.supp_att_req_hdr_ver); +} + +static struct kobj_attribute uv_query_supp_att_req_hdr_ver_attr = + __ATTR(supp_att_req_hdr_ver, 0444, uv_query_supp_att_req_hdr_ver, NULL); + +static ssize_t uv_query_supp_att_pflags(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return scnprintf(page, PAGE_SIZE, "%lx\n", uv_info.supp_att_pflags); +} + +static struct kobj_attribute uv_query_supp_att_pflags_attr = + __ATTR(supp_att_pflags, 0444, uv_query_supp_att_pflags, NULL); + static struct attribute *uv_query_attrs[] = { &uv_query_facilities_attr.attr, &uv_query_feature_indications_attr.attr, @@ -490,6 +508,8 @@ static struct attribute *uv_query_attrs[] = { &uv_query_dump_storage_state_len_attr.attr, &uv_query_dump_finalize_len_attr.attr, &uv_query_dump_cpu_len_attr.attr, + &uv_query_supp_att_req_hdr_ver_attr.attr, + &uv_query_supp_att_pflags_attr.attr, NULL, }; -- cgit From 6131fd198099d9cfde4cbcd6d60a07aa634a358c Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 12 Jul 2022 11:31:40 +0200 Subject: KVM: s390/pci: fix include duplicates remove the duplicate includes. While at it sort the includes. Reported-by: kernel test robot Fixes: 73f91b004321 ("KVM: s390: pci: enable host forwarding of Adapter Event Notifications") Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index 0351382e990f..3a3606c3a0fe 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -10,11 +10,10 @@ #ifndef __KVM_S390_PCI_H #define __KVM_S390_PCI_H -#include -#include -#include #include #include +#include +#include #include #include -- cgit From 5efab5cdf06b932ba7a53264b60f7d5c6ec87edf Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Tue, 12 Jul 2022 16:29:54 +0700 Subject: Documentation: kvm: extend KVM_S390_ZPCI_OP subheading underline Stephen Rothwell reported the htmldocs warning: Documentation/virt/kvm/api.rst:5959: WARNING: Title underline too short. 4.137 KVM_S390_ZPCI_OP -------------------- The warning is due to subheading underline on KVM_S390_ZPCI_OP section is short of 2 dashes. Extend the underline to fix the warning. Link: https://lore.kernel.org/linux-next/20220711205557.183c3b14@canb.auug.org.au/ Fixes: a0c4d1109d6cc5 ("KVM: s390: add KVM_S390_ZPCI_OP to manage guest zPCI devices") Reported-by: Stephen Rothwell Cc: Paolo Bonzini Cc: Jonathan Corbet Cc: Pierre Morel Cc: Thomas Huth Cc: Matthew Rosato Cc: Christian Borntraeger Cc: Janosch Frank Cc: kvm@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Bagas Sanjaya Link: https://lore.kernel.org/r/20220712092954.142027-4-bagasdotme@gmail.com Signed-off-by: Christian Borntraeger --- Documentation/virt/kvm/api.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 5abc0c1a5aff..5be5cc59869d 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5956,7 +5956,7 @@ KVM_PV_DUMP_CPU The length of the returned data is provided by uv_info.guest_cpu_stor_len. 4.137 KVM_S390_ZPCI_OP --------------------- +---------------------- :Capability: KVM_CAP_S390_ZPCI_OP :Architectures: s390 -- cgit From c0da6efc74b47a4dd3e722dfb9e664a253bc597a Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 11 Jul 2022 13:51:08 +0200 Subject: KVM: s390: Add facility 197 to the allow list z16 also provides facility 197 (The processor-activity-instrumentation extension 1). Let's add it to KVM. Signed-off-by: Christian Borntraeger Link: https://lore.kernel.org/r/20220711115108.6494-1-borntraeger@linux.ibm.com Acked-by: Thomas Huth Reviewed-by: Claudio Imbrenda --- arch/s390/tools/gen_facilities.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c index 530dd941d140..cb0aff5c0187 100644 --- a/arch/s390/tools/gen_facilities.c +++ b/arch/s390/tools/gen_facilities.c @@ -111,6 +111,7 @@ static struct facility_def facility_defs[] = { 193, /* bear enhancement facility */ 194, /* rdp enhancement facility */ 196, /* processor activity instrumentation facility */ + 197, /* processor activity instrumentation extension 1 */ -1 /* END */ } }, -- cgit From faa2f72cb3569256480c5540d242c84e99965160 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:02 +0200 Subject: KVM: s390: pv: leak the topmost page table when destroy fails Each secure guest must have a unique ASCE (address space control element); we must avoid that new guests use the same page for their ASCE, to avoid errors. Since the ASCE mostly consists of the address of the topmost page table (plus some flags), we must not return that memory to the pool unless the ASCE is no longer in use. Only a successful Destroy Secure Configuration UVC will make the ASCE reusable again. If the Destroy Configuration UVC fails, the ASCE cannot be reused for a secure guest (either for the ASCE or for other memory areas). To avoid a collision, it must not be used again. This is a permanent error and the page becomes in practice unusable, so we set it aside and leak it. On failure we already leak other memory that belongs to the ultravisor (i.e. the variable and base storage for a guest) and not leaking the topmost page table was an oversight. This error (and thus the leakage) should not happen unless the hardware is broken or KVM has some unknown serious bug. Signed-off-by: Claudio Imbrenda Fixes: 29b40f105ec8d55 ("KVM: s390: protvirt: Add initial vm and cpu lifecycle handling") Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220628135619.32410-2-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-2-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/include/asm/gmap.h | 2 ++ arch/s390/kvm/pv.c | 9 +++-- arch/s390/mm/gmap.c | 86 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 94 insertions(+), 3 deletions(-) diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index 40264f60b0da..f4073106e1f3 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -148,4 +148,6 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], unsigned long gaddr, unsigned long vmaddr); int gmap_mark_unmergeable(void); void s390_reset_acc(struct mm_struct *mm); +void s390_unlist_old_asce(struct gmap *gmap); +int s390_replace_asce(struct gmap *gmap); #endif /* _ASM_S390_GMAP_H */ diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index b4a499b10b67..f1733812a263 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -162,10 +162,13 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) atomic_set(&kvm->mm->context.is_protected, 0); KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc); WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc); - /* Inteded memory leak on "impossible" error */ - if (!cc) + /* Intended memory leak on "impossible" error */ + if (!cc) { kvm_s390_pv_dealloc_vm(kvm); - return cc ? -EIO : 0; + return 0; + } + s390_replace_asce(kvm->arch.gmap); + return -EIO; } int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index b8ae4a4aa2ba..85cab61d87a9 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2735,3 +2735,89 @@ void s390_reset_acc(struct mm_struct *mm) mmput(mm); } EXPORT_SYMBOL_GPL(s390_reset_acc); + +/** + * s390_unlist_old_asce - Remove the topmost level of page tables from the + * list of page tables of the gmap. + * @gmap: the gmap whose table is to be removed + * + * On s390x, KVM keeps a list of all pages containing the page tables of the + * gmap (the CRST list). This list is used at tear down time to free all + * pages that are now not needed anymore. + * + * This function removes the topmost page of the tree (the one pointed to by + * the ASCE) from the CRST list. + * + * This means that it will not be freed when the VM is torn down, and needs + * to be handled separately by the caller, unless a leak is actually + * intended. Notice that this function will only remove the page from the + * list, the page will still be used as a top level page table (and ASCE). + */ +void s390_unlist_old_asce(struct gmap *gmap) +{ + struct page *old; + + old = virt_to_page(gmap->table); + spin_lock(&gmap->guest_table_lock); + list_del(&old->lru); + /* + * Sometimes the topmost page might need to be "removed" multiple + * times, for example if the VM is rebooted into secure mode several + * times concurrently, or if s390_replace_asce fails after calling + * s390_remove_old_asce and is attempted again later. In that case + * the old asce has been removed from the list, and therefore it + * will not be freed when the VM terminates, but the ASCE is still + * in use and still pointed to. + * A subsequent call to replace_asce will follow the pointer and try + * to remove the same page from the list again. + * Therefore it's necessary that the page of the ASCE has valid + * pointers, so list_del can work (and do nothing) without + * dereferencing stale or invalid pointers. + */ + INIT_LIST_HEAD(&old->lru); + spin_unlock(&gmap->guest_table_lock); +} +EXPORT_SYMBOL_GPL(s390_unlist_old_asce); + +/** + * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy + * @gmap: the gmap whose ASCE needs to be replaced + * + * If the allocation of the new top level page table fails, the ASCE is not + * replaced. + * In any case, the old ASCE is always removed from the gmap CRST list. + * Therefore the caller has to make sure to save a pointer to it + * beforehand, unless a leak is actually intended. + */ +int s390_replace_asce(struct gmap *gmap) +{ + unsigned long asce; + struct page *page; + void *table; + + s390_unlist_old_asce(gmap); + + page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + if (!page) + return -ENOMEM; + table = page_to_virt(page); + memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT)); + + /* + * The caller has to deal with the old ASCE, but here we make sure + * the new one is properly added to the CRST list, so that + * it will be freed when the VM is torn down. + */ + spin_lock(&gmap->guest_table_lock); + list_add(&page->lru, &gmap->crst_list); + spin_unlock(&gmap->guest_table_lock); + + /* Set new table origin while preserving existing ASCE control bits */ + asce = (gmap->asce & ~_ASCE_ORIGIN) | __pa(table); + WRITE_ONCE(gmap->asce, asce); + WRITE_ONCE(gmap->mm->context.gmap_asce, asce); + WRITE_ONCE(gmap->table, table); + + return 0; +} +EXPORT_SYMBOL_GPL(s390_replace_asce); -- cgit From a52c25848e3143fbced80e6835de4034cc461fec Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:03 +0200 Subject: KVM: s390: pv: handle secure storage violations for protected guests A secure storage violation is triggered when a protected guest tries to access secure memory that has been mapped erroneously, or that belongs to a different protected guest or to the ultravisor. With upcoming patches, protected guests will be able to trigger secure storage violations in normal operation. This happens for example if a protected guest is rebooted with deferred destroy enabled and the new guest is also protected. When the new protected guest touches pages that have not yet been destroyed, and thus are accounted to the previous protected guest, a secure storage violation is raised. This patch adds handling of secure storage violations for protected guests. This exception is handled by first trying to destroy the page, because it is expected to belong to a defunct protected guest where a destroy should be possible. Note that a secure page can only be destroyed if its protected VM does not have any CPUs, which only happens when the protected VM is being terminated. If that fails, a normal export of the page is attempted. This means that pages that trigger the exception will be made non-secure (in one way or another) before attempting to use them again for a different secure guest. Signed-off-by: Claudio Imbrenda Acked-by: Janosch Frank Link: https://lore.kernel.org/r/20220628135619.32410-3-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-3-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/include/asm/uv.h | 1 + arch/s390/kernel/uv.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++ arch/s390/mm/fault.c | 10 +++++++++ 3 files changed, 66 insertions(+) diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 18fe04c8547e..be3ef9dd6972 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -426,6 +426,7 @@ static inline int is_prot_virt_host(void) } int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); +int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr); int uv_destroy_owned_page(unsigned long paddr); int uv_convert_from_secure(unsigned long paddr); int uv_convert_owned_from_secure(unsigned long paddr); diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index c13d5a7b71f0..4c91a3dbc05b 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -334,6 +334,61 @@ int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr) } EXPORT_SYMBOL_GPL(gmap_convert_to_secure); +/** + * gmap_destroy_page - Destroy a guest page. + * @gmap: the gmap of the guest + * @gaddr: the guest address to destroy + * + * An attempt will be made to destroy the given guest page. If the attempt + * fails, an attempt is made to export the page. If both attempts fail, an + * appropriate error is returned. + */ +int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr) +{ + struct vm_area_struct *vma; + unsigned long uaddr; + struct page *page; + int rc; + + rc = -EFAULT; + mmap_read_lock(gmap->mm); + + uaddr = __gmap_translate(gmap, gaddr); + if (IS_ERR_VALUE(uaddr)) + goto out; + vma = vma_lookup(gmap->mm, uaddr); + if (!vma) + goto out; + /* + * Huge pages should not be able to become secure + */ + if (is_vm_hugetlb_page(vma)) + goto out; + + rc = 0; + /* we take an extra reference here */ + page = follow_page(vma, uaddr, FOLL_WRITE | FOLL_GET); + if (IS_ERR_OR_NULL(page)) + goto out; + rc = uv_destroy_owned_page(page_to_phys(page)); + /* + * Fault handlers can race; it is possible that two CPUs will fault + * on the same secure page. One CPU can destroy the page, reboot, + * re-enter secure mode and import it, while the second CPU was + * stuck at the beginning of the handler. At some point the second + * CPU will be able to progress, and it will not be able to destroy + * the page. In that case we do not want to terminate the process, + * we instead try to export the page. + */ + if (rc) + rc = uv_convert_owned_from_secure(page_to_phys(page)); + put_page(page); +out: + mmap_read_unlock(gmap->mm); + return rc; +} +EXPORT_SYMBOL_GPL(gmap_destroy_page); + /* * To be called with the page locked or with an extra reference! This will * prevent gmap_make_secure from touching the page concurrently. Having 2 diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b6187ad5..af1ac49168fb 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -837,6 +837,16 @@ NOKPROBE_SYMBOL(do_non_secure_storage_access); void do_secure_storage_violation(struct pt_regs *regs) { + unsigned long gaddr = regs->int_parm_long & __FAIL_ADDR_MASK; + struct gmap *gmap = (struct gmap *)S390_lowcore.gmap; + + /* + * If the VM has been rebooted, its address space might still contain + * secure pages from the previous boot. + * Clear the page so it can be reused. + */ + if (!gmap_destroy_page(gmap, gaddr)) + return; /* * Either KVM messed up the secure guest mapping or the same * page is mapped into multiple secure guests. -- cgit From b108f7f0a29b24a94e0c4f9af20f84afaa6ef245 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:04 +0200 Subject: KVM: s390: pv: handle secure storage exceptions for normal guests With upcoming patches, normal guests might touch secure pages. This patch extends the existing exception handler to convert the pages to non secure also when the exception is triggered by a normal guest. This can happen for example when a secure guest reboots; the first stage of a secure guest is non secure, and in general a secure guest can reboot into non-secure mode. If the secure memory of the previous boot has not been cleared up completely yet (which will be allowed to happen in an upcoming patch), a non-secure guest might touch secure memory, which will need to be handled properly. This means that gmap faults must be handled and not cause termination of the process. The handling is the same as userspace accesses, it's enough to translate the gmap address to a user address and then let the normal user fault code handle it. Signed-off-by: Claudio Imbrenda Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220628135619.32410-4-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-4-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/mm/fault.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index af1ac49168fb..ee7871f770fb 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -754,6 +754,7 @@ void do_secure_storage_access(struct pt_regs *regs) struct vm_area_struct *vma; struct mm_struct *mm; struct page *page; + struct gmap *gmap; int rc; /* @@ -783,6 +784,17 @@ void do_secure_storage_access(struct pt_regs *regs) } switch (get_fault_type(regs)) { + case GMAP_FAULT: + mm = current->mm; + gmap = (struct gmap *)S390_lowcore.gmap; + mmap_read_lock(mm); + addr = __gmap_translate(gmap, addr); + mmap_read_unlock(mm); + if (IS_ERR_VALUE(addr)) { + do_fault_error(regs, VM_ACCESS_FLAGS, VM_FAULT_BADMAP); + break; + } + fallthrough; case USER_FAULT: mm = current->mm; mmap_read_lock(mm); @@ -811,7 +823,6 @@ void do_secure_storage_access(struct pt_regs *regs) if (rc) BUG(); break; - case GMAP_FAULT: default: do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); WARN_ON_ONCE(1); -- cgit From 6f73517d0a99ba8ec972bf053456f1c2932598c0 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:05 +0200 Subject: KVM: s390: pv: refactor s390_reset_acc Refactor s390_reset_acc so that it can be reused in upcoming patches. We don't want to hold all the locks used in a walk_page_range for too long, and the destroy page UVC does take some time to complete. Therefore we quickly gather the pages to destroy, and then destroy them without holding all the locks. The new refactored function optionally allows to return early without completing if a fatal signal is pending (and return and appropriate error code). Two wrappers are provided to call the new function. Signed-off-by: Claudio Imbrenda Reviewed-by: Janosch Frank Reviewed-by: Nico Boehr Link: https://lore.kernel.org/r/20220628135619.32410-5-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-5-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/include/asm/gmap.h | 37 ++++++++++++++++- arch/s390/kvm/pv.c | 12 +++++- arch/s390/mm/gmap.c | 99 +++++++++++++++++++++++++++++++------------- 3 files changed, 116 insertions(+), 32 deletions(-) diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index f4073106e1f3..5cc46e0dde62 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -147,7 +147,42 @@ int gmap_mprotect_notify(struct gmap *, unsigned long start, void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], unsigned long gaddr, unsigned long vmaddr); int gmap_mark_unmergeable(void); -void s390_reset_acc(struct mm_struct *mm); void s390_unlist_old_asce(struct gmap *gmap); int s390_replace_asce(struct gmap *gmap); +void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns); +int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool interruptible); + +/** + * s390_uv_destroy_range - Destroy a range of pages in the given mm. + * @mm: the mm on which to operate on + * @start: the start of the range + * @end: the end of the range + * + * This function will call cond_sched, so it should not generate stalls, but + * it will otherwise only return when it completed. + */ +static inline void s390_uv_destroy_range(struct mm_struct *mm, unsigned long start, + unsigned long end) +{ + (void)__s390_uv_destroy_range(mm, start, end, false); +} + +/** + * s390_uv_destroy_range_interruptible - Destroy a range of pages in the + * given mm, but stop when a fatal signal is received. + * @mm: the mm on which to operate on + * @start: the start of the range + * @end: the end of the range + * + * This function will call cond_sched, so it should not generate stalls. If + * a fatal signal is received, it will return with -EINTR immediately, + * without finishing destroying the whole range. Upon successful + * completion, 0 is returned. + */ +static inline int s390_uv_destroy_range_interruptible(struct mm_struct *mm, unsigned long start, + unsigned long end) +{ + return __s390_uv_destroy_range(mm, start, end, true); +} #endif /* _ASM_S390_GMAP_H */ diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index f1733812a263..a556db3912a1 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -13,6 +13,8 @@ #include #include #include +#include +#include #include "kvm-s390.h" int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) @@ -153,8 +155,14 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) { int cc; - /* make all pages accessible before destroying the guest */ - s390_reset_acc(kvm->mm); + /* + * if the mm still has a mapping, make all its pages accessible + * before destroying the guest + */ + if (mmget_not_zero(kvm->mm)) { + s390_uv_destroy_range(kvm->mm, 0, TASK_SIZE); + mmput(kvm->mm); + } cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), UVC_CMD_DESTROY_SEC_CONF, rc, rrc); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 85cab61d87a9..62758cb5872f 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2697,44 +2697,85 @@ void s390_reset_cmma(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(s390_reset_cmma); -/* - * make inaccessible pages accessible again - */ -static int __s390_reset_acc(pte_t *ptep, unsigned long addr, - unsigned long next, struct mm_walk *walk) +#define GATHER_GET_PAGES 32 + +struct reset_walk_state { + unsigned long next; + unsigned long count; + unsigned long pfns[GATHER_GET_PAGES]; +}; + +static int s390_gather_pages(pte_t *ptep, unsigned long addr, + unsigned long next, struct mm_walk *walk) { + struct reset_walk_state *p = walk->private; pte_t pte = READ_ONCE(*ptep); - /* There is a reference through the mapping */ - if (pte_present(pte)) - WARN_ON_ONCE(uv_destroy_owned_page(pte_val(pte) & PAGE_MASK)); - - return 0; + if (pte_present(pte)) { + /* we have a reference from the mapping, take an extra one */ + get_page(phys_to_page(pte_val(pte))); + p->pfns[p->count] = phys_to_pfn(pte_val(pte)); + p->next = next; + p->count++; + } + return p->count >= GATHER_GET_PAGES; } -static const struct mm_walk_ops reset_acc_walk_ops = { - .pte_entry = __s390_reset_acc, +static const struct mm_walk_ops gather_pages_ops = { + .pte_entry = s390_gather_pages, }; -#include -void s390_reset_acc(struct mm_struct *mm) +/* + * Call the Destroy secure page UVC on each page in the given array of PFNs. + * Each page needs to have an extra reference, which will be released here. + */ +void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns) { - if (!mm_is_protected(mm)) - return; - /* - * we might be called during - * reset: we walk the pages and clear - * close of all kvm file descriptors: we walk the pages and clear - * exit of process on fd closure: vma already gone, do nothing - */ - if (!mmget_not_zero(mm)) - return; - mmap_read_lock(mm); - walk_page_range(mm, 0, TASK_SIZE, &reset_acc_walk_ops, NULL); - mmap_read_unlock(mm); - mmput(mm); + unsigned long i; + + for (i = 0; i < count; i++) { + /* we always have an extra reference */ + uv_destroy_owned_page(pfn_to_phys(pfns[i])); + /* get rid of the extra reference */ + put_page(pfn_to_page(pfns[i])); + cond_resched(); + } +} +EXPORT_SYMBOL_GPL(s390_uv_destroy_pfns); + +/** + * __s390_uv_destroy_range - Call the destroy secure page UVC on each page + * in the given range of the given address space. + * @mm: the mm to operate on + * @start: the start of the range + * @end: the end of the range + * @interruptible: if not 0, stop when a fatal signal is received + * + * Walk the given range of the given address space and call the destroy + * secure page UVC on each page. Optionally exit early if a fatal signal is + * pending. + * + * Return: 0 on success, -EINTR if the function stopped before completing + */ +int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool interruptible) +{ + struct reset_walk_state state = { .next = start }; + int r = 1; + + while (r > 0) { + state.count = 0; + mmap_read_lock(mm); + r = walk_page_range(mm, state.next, end, &gather_pages_ops, &state); + mmap_read_unlock(mm); + cond_resched(); + s390_uv_destroy_pfns(state.count, state.pfns); + if (interruptible && fatal_signal_pending(current)) + return -EINTR; + } + return 0; } -EXPORT_SYMBOL_GPL(s390_reset_acc); +EXPORT_SYMBOL_GPL(__s390_uv_destroy_range); /** * s390_unlist_old_asce - Remove the topmost level of page tables from the -- cgit From 07fbdf7f934795a9e1728fcb3bdce6e0d8039e0c Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:06 +0200 Subject: KVM: s390: pv: usage counter instead of flag Use the new protected_count field as a counter instead of the old is_protected flag. This will be used in upcoming patches. Increment the counter when a secure configuration is created, and decrement it when it is destroyed. Previously the flag was set when the set secure parameters UVC was performed. Signed-off-by: Claudio Imbrenda Acked-by: Janosch Frank Link: https://lore.kernel.org/r/20220628135619.32410-6-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-6-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/include/asm/mmu.h | 2 +- arch/s390/include/asm/mmu_context.h | 2 +- arch/s390/include/asm/pgtable.h | 2 +- arch/s390/kvm/pv.c | 12 +++++++----- 4 files changed, 10 insertions(+), 8 deletions(-) diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 82aae78e1315..1572b3634cdd 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -18,7 +18,7 @@ typedef struct { unsigned long asce_limit; unsigned long vdso_base; /* The mmu context belongs to a secure guest. */ - atomic_t is_protected; + atomic_t protected_count; /* * The following bitfields need a down_write on the mm * semaphore when they are written to. As they are only diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index c7937f369e62..2a38af5a00c2 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -26,7 +26,7 @@ static inline int init_new_context(struct task_struct *tsk, INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.flush_count, 0); - atomic_set(&mm->context.is_protected, 0); + atomic_set(&mm->context.protected_count, 0); mm->context.gmap_asce = 0; mm->context.flush_mm = 0; #ifdef CONFIG_PGSTE diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index a397b072a580..f16403ba81ec 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -525,7 +525,7 @@ static inline int mm_has_pgste(struct mm_struct *mm) static inline int mm_is_protected(struct mm_struct *mm) { #ifdef CONFIG_PGSTE - if (unlikely(atomic_read(&mm->context.is_protected))) + if (unlikely(atomic_read(&mm->context.protected_count))) return 1; #endif return 0; diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index a556db3912a1..59e0d5399113 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -167,7 +167,8 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), UVC_CMD_DESTROY_SEC_CONF, rc, rrc); WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); - atomic_set(&kvm->mm->context.is_protected, 0); + if (!cc) + atomic_dec(&kvm->mm->context.protected_count); KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc); WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc); /* Intended memory leak on "impossible" error */ @@ -209,11 +210,14 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) /* Outputs */ kvm->arch.pv.handle = uvcb.guest_handle; + atomic_inc(&kvm->mm->context.protected_count); if (cc) { - if (uvcb.header.rc & UVC_RC_NEED_DESTROY) + if (uvcb.header.rc & UVC_RC_NEED_DESTROY) { kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy); - else + } else { + atomic_dec(&kvm->mm->context.protected_count); kvm_s390_pv_dealloc_vm(kvm); + } return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; @@ -236,8 +240,6 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, *rrc = uvcb.header.rrc; KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x", *rc, *rrc); - if (!cc) - atomic_set(&kvm->mm->context.is_protected, 1); return cc ? -EINVAL : 0; } -- cgit From 72b1daff2671cef2c8cccc6c4e52f8d5ce4ebe58 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:07 +0200 Subject: KVM: s390: pv: add export before import Due to upcoming changes, it will be possible to temporarily have multiple protected VMs in the same address space, although only one will be actually active. In that scenario, it is necessary to perform an export of every page that is to be imported, since the hardware does not allow a page belonging to a protected guest to be imported into a different protected guest. This also applies to pages that are shared, and thus accessible by the host. Signed-off-by: Claudio Imbrenda Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220628135619.32410-7-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-7-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/kernel/uv.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 4c91a3dbc05b..f9810d2a267c 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -234,6 +234,32 @@ static int make_secure_pte(pte_t *ptep, unsigned long addr, return uvcb->rc == 0x10a ? -ENXIO : -EINVAL; } +/** + * should_export_before_import - Determine whether an export is needed + * before an import-like operation + * @uvcb: the Ultravisor control block of the UVC to be performed + * @mm: the mm of the process + * + * Returns whether an export is needed before every import-like operation. + * This is needed for shared pages, which don't trigger a secure storage + * exception when accessed from a different guest. + * + * Although considered as one, the Unpin Page UVC is not an actual import, + * so it is not affected. + * + * No export is needed also when there is only one protected VM, because the + * page cannot belong to the wrong VM in that case (there is no "other VM" + * it can belong to). + * + * Return: true if an export is needed before every import, otherwise false. + */ +static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm) +{ + if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED) + return false; + return atomic_read(&mm->context.protected_count) > 1; +} + /* * Requests the Ultravisor to make a page accessible to a guest. * If it's brought in the first time, it will be cleared. If @@ -277,6 +303,8 @@ again: lock_page(page); ptep = get_locked_pte(gmap->mm, uaddr, &ptelock); + if (should_export_before_import(uvcb, gmap->mm)) + uv_convert_from_secure(page_to_phys(page)); rc = make_secure_pte(ptep, uaddr, page, uvcb); pte_unmap_unlock(ptep, ptelock); unlock_page(page); -- cgit From e40df9efd68a621734fe03efc68b8f3e8da47cf8 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:08 +0200 Subject: KVM: s390: pv: clear the state without memset Do not use memset to clean the whole struct kvm_s390_pv; instead, explicitly clear the fields that need to be cleared. Upcoming patches will introduce new fields in the struct kvm_s390_pv that will not need to be cleared. Signed-off-by: Claudio Imbrenda Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220628135619.32410-8-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-8-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/kvm/pv.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 59e0d5399113..d18c5ccfa5dc 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -17,6 +17,14 @@ #include #include "kvm-s390.h" +static void kvm_s390_clear_pv_state(struct kvm *kvm) +{ + kvm->arch.pv.handle = 0; + kvm->arch.pv.guest_len = 0; + kvm->arch.pv.stor_base = 0; + kvm->arch.pv.stor_var = NULL; +} + int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) { int cc; @@ -111,7 +119,7 @@ static void kvm_s390_pv_dealloc_vm(struct kvm *kvm) vfree(kvm->arch.pv.stor_var); free_pages(kvm->arch.pv.stor_base, get_order(uv_info.guest_base_stor_len)); - memset(&kvm->arch.pv, 0, sizeof(kvm->arch.pv)); + kvm_s390_clear_pv_state(kvm); } static int kvm_s390_pv_alloc_vm(struct kvm *kvm) -- cgit From be48d86f77f0cbceecadf10fda6330d82a0a77b7 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:09 +0200 Subject: KVM: s390: pv: Add kvm_s390_cpus_from_pv to kvm-s390.h and add documentation Future changes make it necessary to call this function from pv.c. While we are at it, let's properly document kvm_s390_cpus_from_pv() and kvm_s390_cpus_to_pv(). Signed-off-by: Claudio Imbrenda Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220628135619.32410-9-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-9-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/kvm/kvm-s390.c | 36 ++++++++++++++++++++++++++++++------ arch/s390/kvm/kvm-s390.h | 1 + 2 files changed, 31 insertions(+), 6 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 18b0a6f0cd9c..d10c3b163cdc 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2237,12 +2237,25 @@ out: return r; } -static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) +/** + * kvm_s390_cpus_from_pv - Convert all protected vCPUs in a protected VM to + * non protected. + * @kvm: the VM whose protected vCPUs are to be converted + * @rc: return value for the RC field of the UVC (in case of error) + * @rrc: return value for the RRC field of the UVC (in case of error) + * + * Does not stop in case of error, tries to convert as many + * CPUs as possible. In case of error, the RC and RRC of the last error are + * returned. + * + * Return: 0 in case of success, otherwise -EIO + */ +int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc) { struct kvm_vcpu *vcpu; - u16 rc, rrc; - int ret = 0; unsigned long i; + u16 _rc, _rrc; + int ret = 0; /* * We ignore failures and try to destroy as many CPUs as possible. @@ -2254,9 +2267,9 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) */ kvm_for_each_vcpu(i, vcpu, kvm) { mutex_lock(&vcpu->mutex); - if (kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc) && !ret) { - *rcp = rc; - *rrcp = rrc; + if (kvm_s390_pv_destroy_cpu(vcpu, &_rc, &_rrc) && !ret) { + *rc = _rc; + *rrc = _rrc; ret = -EIO; } mutex_unlock(&vcpu->mutex); @@ -2267,6 +2280,17 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) return ret; } +/** + * kvm_s390_cpus_to_pv - Convert all non-protected vCPUs in a protected VM + * to protected. + * @kvm: the VM whose protected vCPUs are to be converted + * @rc: return value for the RC field of the UVC (in case of error) + * @rrc: return value for the RRC field of the UVC (in case of error) + * + * Tries to undo the conversion in case of error. + * + * Return: 0 in case of success, otherwise -EIO + */ static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc) { unsigned long i; diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index cf4f4d1713ea..f6fd668f887e 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -379,6 +379,7 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu); void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm); __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu); +int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc); /* implemented in diag.c */ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); -- cgit From ca2fd0609b5ddd15fe57c917a41508a7a9fc17e1 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:10 +0200 Subject: KVM: s390: pv: add mmu_notifier Add an mmu_notifier for protected VMs. The callback function is triggered when the mm is torn down, and will attempt to convert all protected vCPUs to non-protected. This allows the mm teardown to use the destroy page UVC instead of export. Also make KVM select CONFIG_MMU_NOTIFIER, needed to use mmu_notifiers. Signed-off-by: Claudio Imbrenda Acked-by: Janosch Frank Reviewed-by: Nico Boehr Link: https://lore.kernel.org/r/20220628135619.32410-10-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-10-imbrenda@linux.ibm.com> [frankja@linux.ibm.com: Conflict resolution for mmu_notifier.h include and struct kvm_s390_pv] Signed-off-by: Janosch Frank --- arch/s390/include/asm/kvm_host.h | 2 ++ arch/s390/kvm/Kconfig | 1 + arch/s390/kvm/kvm-s390.c | 10 ++++++++++ arch/s390/kvm/pv.c | 26 ++++++++++++++++++++++++++ 4 files changed, 39 insertions(+) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index fca4fcf72a2a..6f9fc8bb0303 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -929,6 +930,7 @@ struct kvm_s390_pv { unsigned long stor_base; void *stor_var; bool dumping; + struct mmu_notifier mmu_notifier; }; struct kvm_arch{ diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 2e84d3922f7c..33f4ff909476 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -34,6 +34,7 @@ config KVM select SRCU select KVM_VFIO select INTERVAL_TREE + select MMU_NOTIFIER help Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d10c3b163cdc..5b77c43fbb01 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -3198,6 +3199,15 @@ void kvm_arch_destroy_vm(struct kvm *kvm) */ if (kvm_s390_pv_get_handle(kvm)) kvm_s390_pv_deinit_vm(kvm, &rc, &rrc); + /* + * Remove the mmu notifier only when the whole KVM VM is torn down, + * and only if one was registered to begin with. If the VM is + * currently not protected, but has been previously been protected, + * then it's possible that the notifier is still registered. + */ + if (kvm->arch.pv.mmu_notifier.ops) + mmu_notifier_unregister(&kvm->arch.pv.mmu_notifier, kvm->mm); + debug_unregister(kvm->arch.dbf); free_page((unsigned long)kvm->arch.sie_page2); if (!kvm_is_ucontrol(kvm)) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index d18c5ccfa5dc..c063d1a9cf04 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "kvm-s390.h" static void kvm_s390_clear_pv_state(struct kvm *kvm) @@ -188,6 +189,26 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return -EIO; } +static void kvm_s390_pv_mmu_notifier_release(struct mmu_notifier *subscription, + struct mm_struct *mm) +{ + struct kvm *kvm = container_of(subscription, struct kvm, arch.pv.mmu_notifier); + u16 dummy; + + /* + * No locking is needed since this is the last thread of the last user of this + * struct mm. + * When the struct kvm gets deinitialized, this notifier is also + * unregistered. This means that if this notifier runs, then the + * struct kvm is still valid. + */ + kvm_s390_cpus_from_pv(kvm, &dummy, &dummy); +} + +static const struct mmu_notifier_ops kvm_s390_pv_mmu_notifier_ops = { + .release = kvm_s390_pv_mmu_notifier_release, +}; + int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) { struct uv_cb_cgc uvcb = { @@ -229,6 +250,11 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; + /* Add the notifier only once. No races because we hold kvm->lock */ + if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) { + kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops; + mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm); + } return 0; } -- cgit From 9bf811dae443794594615625577277852edc181b Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:11 +0200 Subject: s390/mm: KVM: pv: when tearing down, try to destroy protected pages When ptep_get_and_clear_full is called for a mm teardown, we will now attempt to destroy the secure pages. This will be faster than export. In case it was not a teardown, or if for some reason the destroy page UVC failed, we try with an export page, like before. Signed-off-by: Claudio Imbrenda Acked-by: Janosch Frank Reviewed-by: Nico Boehr Link: https://lore.kernel.org/r/20220628135619.32410-11-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-11-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/include/asm/pgtable.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index f16403ba81ec..cf81acf3879c 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1182,9 +1182,22 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, } else { res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID)); } - /* At this point the reference through the mapping is still present */ - if (mm_is_protected(mm) && pte_present(res)) - uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK); + /* Nothing to do */ + if (!mm_is_protected(mm) || !pte_present(res)) + return res; + /* + * At this point the reference through the mapping is still present. + * The notifier should have destroyed all protected vCPUs at this + * point, so the destroy should be successful. + */ + if (full && !uv_destroy_owned_page(pte_val(res) & PAGE_MASK)) + return res; + /* + * If something went wrong and the page could not be destroyed, or + * if this is not a mm teardown, the slower export is used as + * fallback instead. + */ + uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK); return res; } -- cgit From da15fbc646f377ebfe992c13053b93783fea0db2 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:12 +0200 Subject: KVM: s390: pv: refactoring of kvm_s390_pv_deinit_vm Refactor kvm_s390_pv_deinit_vm to improve readability and simplify the improvements that are coming in subsequent patches. No functional change intended. Signed-off-by: Claudio Imbrenda Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220628135619.32410-12-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-12-imbrenda@linux.ibm.com> [frankja@linux.ibm.com: Dropped commit message line regarding review] Signed-off-by: Janosch Frank --- arch/s390/kvm/pv.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index c063d1a9cf04..4b64bf5bc3b0 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -176,17 +176,17 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), UVC_CMD_DESTROY_SEC_CONF, rc, rrc); WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); - if (!cc) - atomic_dec(&kvm->mm->context.protected_count); - KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc); - WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc); - /* Intended memory leak on "impossible" error */ if (!cc) { + atomic_dec(&kvm->mm->context.protected_count); kvm_s390_pv_dealloc_vm(kvm); - return 0; + } else { + /* Intended memory leak on "impossible" error */ + s390_replace_asce(kvm->arch.gmap); } - s390_replace_asce(kvm->arch.gmap); - return -EIO; + KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc); + WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc); + + return cc ? -EIO : 0; } static void kvm_s390_pv_mmu_notifier_release(struct mmu_notifier *subscription, -- cgit From 7746f735f55205176a447e737fe15a5ba7a4d2d4 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 28 Jun 2022 15:56:13 +0200 Subject: KVM: s390: pv: destroy the configuration before its memory Move the Destroy Secure Configuration UVC before the loop to destroy the memory. If the protected VM has memory, it will be cleaned up and made accessible by the Destroy Secure Configuration UVC. The struct page for the relevant pages will still have the protected bit set, so the loop is still needed to clean that up. Switching the order of those two operations does not change the outcome, but it is significantly faster. Signed-off-by: Claudio Imbrenda Reviewed-by: Nico Boehr Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220628135619.32410-13-imbrenda@linux.ibm.com Message-Id: <20220628135619.32410-13-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/kvm/pv.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 4b64bf5bc3b0..7cb7799a0acb 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -164,6 +164,9 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) { int cc; + cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_DESTROY_SEC_CONF, rc, rrc); + WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); /* * if the mm still has a mapping, make all its pages accessible * before destroying the guest @@ -173,9 +176,6 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) mmput(kvm->mm); } - cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), - UVC_CMD_DESTROY_SEC_CONF, rc, rrc); - WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); if (!cc) { atomic_dec(&kvm->mm->context.protected_count); kvm_s390_pv_dealloc_vm(kvm); -- cgit From c3f0e5fd2d33d80c5a5a8b5e5d2bab2841709cc8 Mon Sep 17 00:00:00 2001 From: Nico Boehr Date: Mon, 18 Jul 2022 15:04:34 +0200 Subject: KVM: s390: pv: don't present the ecall interrupt twice When the SIGP interpretation facility is present and a VCPU sends an ecall to another VCPU in enabled wait, the sending VCPU receives a 56 intercept (partial execution), so KVM can wake up the receiving CPU. Note that the SIGP interpretation facility will take care of the interrupt delivery and KVM's only job is to wake the receiving VCPU. For PV, the sending VCPU will receive a 108 intercept (pv notify) and should continue like in the non-PV case, i.e. wake the receiving VCPU. For PV and non-PV guests the interrupt delivery will occur through the SIGP interpretation facility on SIE entry when SIE finds the X bit in the status field set. However, in handle_pv_notification(), there was no special handling for SIGP, which leads to interrupt injection being requested by KVM for the next SIE entry. This results in the interrupt being delivered twice: once by the SIGP interpretation facility and once by KVM through the IICTL. Add the necessary special handling in handle_pv_notification(), similar to handle_partial_execution(), which simply wakes the receiving VCPU and leave interrupt delivery to the SIGP interpretation facility. In contrast to external calls, emergency calls are not interpreted but also cause a 108 intercept, which is why we still need to call handle_instruction() for SIGP orders other than ecall. Since kvm_s390_handle_sigp_pei() is now called for all SIGP orders which cause a 108 intercept - even if they are actually handled by handle_instruction() - move the tracepoint in kvm_s390_handle_sigp_pei() to avoid possibly confusing trace messages. Signed-off-by: Nico Boehr Cc: # 5.7 Fixes: da24a0cc58ed ("KVM: s390: protvirt: Instruction emulation") Reviewed-by: Claudio Imbrenda Reviewed-by: Janosch Frank Reviewed-by: Christian Borntraeger Link: https://lore.kernel.org/r/20220718130434.73302-1-nrb@linux.ibm.com Message-Id: <20220718130434.73302-1-nrb@linux.ibm.com> Signed-off-by: Claudio Imbrenda --- arch/s390/kvm/intercept.c | 15 +++++++++++++++ arch/s390/kvm/sigp.c | 4 ++-- 2 files changed, 17 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 8bd42a20d924..88112065d941 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -528,12 +528,27 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu) static int handle_pv_notification(struct kvm_vcpu *vcpu) { + int ret; + if (vcpu->arch.sie_block->ipa == 0xb210) return handle_pv_spx(vcpu); if (vcpu->arch.sie_block->ipa == 0xb220) return handle_pv_sclp(vcpu); if (vcpu->arch.sie_block->ipa == 0xb9a4) return handle_pv_uvc(vcpu); + if (vcpu->arch.sie_block->ipa >> 8 == 0xae) { + /* + * Besides external call, other SIGP orders also cause a + * 108 (pv notify) intercept. In contrast to external call, + * these orders need to be emulated and hence the appropriate + * place to handle them is in handle_instruction(). + * So first try kvm_s390_handle_sigp_pei() and if that isn't + * successful, go on with handle_instruction(). + */ + ret = kvm_s390_handle_sigp_pei(vcpu); + if (!ret) + return ret; + } return handle_instruction(vcpu); } diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 8aaee2892ec3..cb747bf6c798 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -480,9 +480,9 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu) struct kvm_vcpu *dest_vcpu; u8 order_code = kvm_s390_get_base_disp_rs(vcpu, NULL); - trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); - if (order_code == SIGP_EXTERNAL_CALL) { + trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); + dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr); BUG_ON(dest_vcpu == NULL); -- cgit From 0130337ec45bffd26ba3e782850da3b68f1eef9d Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Wed, 4 May 2022 14:29:08 +0200 Subject: KVM: s390: Cleanup ipte lock access and SIIF facility checks We can check if SIIF is enabled by testing the sclp_info struct instead of testing the sie control block eca variable as that facility is always enabled if available. Also let's cleanup all the ipte related struct member accesses which currently happen by referencing the KVM struct via the VCPU struct. Making the KVM struct the parameter to the ipte_* functions removes one level of indirection which makes the code more readable. Signed-off-by: Pierre Morel Reviewed-by: Janosch Frank Reviewed-by: David Hildenbrand Reviewed-by: Nico Boehr Link: https://lore.kernel.org/all/20220711084148.25017-2-pmorel@linux.ibm.com/ Signed-off-by: Janosch Frank --- arch/s390/kvm/gaccess.c | 96 ++++++++++++++++++++++++------------------------- arch/s390/kvm/gaccess.h | 6 ++-- arch/s390/kvm/priv.c | 6 ++-- 3 files changed, 54 insertions(+), 54 deletions(-) diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 227ed0009354..082ec5f2c3a5 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -262,77 +262,77 @@ struct aste { /* .. more fields there */ }; -int ipte_lock_held(struct kvm_vcpu *vcpu) +int ipte_lock_held(struct kvm *kvm) { - if (vcpu->arch.sie_block->eca & ECA_SII) { + if (sclp.has_siif) { int rc; - read_lock(&vcpu->kvm->arch.sca_lock); - rc = kvm_s390_get_ipte_control(vcpu->kvm)->kh != 0; - read_unlock(&vcpu->kvm->arch.sca_lock); + read_lock(&kvm->arch.sca_lock); + rc = kvm_s390_get_ipte_control(kvm)->kh != 0; + read_unlock(&kvm->arch.sca_lock); return rc; } - return vcpu->kvm->arch.ipte_lock_count != 0; + return kvm->arch.ipte_lock_count != 0; } -static void ipte_lock_simple(struct kvm_vcpu *vcpu) +static void ipte_lock_simple(struct kvm *kvm) { union ipte_control old, new, *ic; - mutex_lock(&vcpu->kvm->arch.ipte_mutex); - vcpu->kvm->arch.ipte_lock_count++; - if (vcpu->kvm->arch.ipte_lock_count > 1) + mutex_lock(&kvm->arch.ipte_mutex); + kvm->arch.ipte_lock_count++; + if (kvm->arch.ipte_lock_count > 1) goto out; retry: - read_lock(&vcpu->kvm->arch.sca_lock); - ic = kvm_s390_get_ipte_control(vcpu->kvm); + read_lock(&kvm->arch.sca_lock); + ic = kvm_s390_get_ipte_control(kvm); do { old = READ_ONCE(*ic); if (old.k) { - read_unlock(&vcpu->kvm->arch.sca_lock); + read_unlock(&kvm->arch.sca_lock); cond_resched(); goto retry; } new = old; new.k = 1; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); - read_unlock(&vcpu->kvm->arch.sca_lock); + read_unlock(&kvm->arch.sca_lock); out: - mutex_unlock(&vcpu->kvm->arch.ipte_mutex); + mutex_unlock(&kvm->arch.ipte_mutex); } -static void ipte_unlock_simple(struct kvm_vcpu *vcpu) +static void ipte_unlock_simple(struct kvm *kvm) { union ipte_control old, new, *ic; - mutex_lock(&vcpu->kvm->arch.ipte_mutex); - vcpu->kvm->arch.ipte_lock_count--; - if (vcpu->kvm->arch.ipte_lock_count) + mutex_lock(&kvm->arch.ipte_mutex); + kvm->arch.ipte_lock_count--; + if (kvm->arch.ipte_lock_count) goto out; - read_lock(&vcpu->kvm->arch.sca_lock); - ic = kvm_s390_get_ipte_control(vcpu->kvm); + read_lock(&kvm->arch.sca_lock); + ic = kvm_s390_get_ipte_control(kvm); do { old = READ_ONCE(*ic); new = old; new.k = 0; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); - read_unlock(&vcpu->kvm->arch.sca_lock); - wake_up(&vcpu->kvm->arch.ipte_wq); + read_unlock(&kvm->arch.sca_lock); + wake_up(&kvm->arch.ipte_wq); out: - mutex_unlock(&vcpu->kvm->arch.ipte_mutex); + mutex_unlock(&kvm->arch.ipte_mutex); } -static void ipte_lock_siif(struct kvm_vcpu *vcpu) +static void ipte_lock_siif(struct kvm *kvm) { union ipte_control old, new, *ic; retry: - read_lock(&vcpu->kvm->arch.sca_lock); - ic = kvm_s390_get_ipte_control(vcpu->kvm); + read_lock(&kvm->arch.sca_lock); + ic = kvm_s390_get_ipte_control(kvm); do { old = READ_ONCE(*ic); if (old.kg) { - read_unlock(&vcpu->kvm->arch.sca_lock); + read_unlock(&kvm->arch.sca_lock); cond_resched(); goto retry; } @@ -340,15 +340,15 @@ retry: new.k = 1; new.kh++; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); - read_unlock(&vcpu->kvm->arch.sca_lock); + read_unlock(&kvm->arch.sca_lock); } -static void ipte_unlock_siif(struct kvm_vcpu *vcpu) +static void ipte_unlock_siif(struct kvm *kvm) { union ipte_control old, new, *ic; - read_lock(&vcpu->kvm->arch.sca_lock); - ic = kvm_s390_get_ipte_control(vcpu->kvm); + read_lock(&kvm->arch.sca_lock); + ic = kvm_s390_get_ipte_control(kvm); do { old = READ_ONCE(*ic); new = old; @@ -356,25 +356,25 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu) if (!new.kh) new.k = 0; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); - read_unlock(&vcpu->kvm->arch.sca_lock); + read_unlock(&kvm->arch.sca_lock); if (!new.kh) - wake_up(&vcpu->kvm->arch.ipte_wq); + wake_up(&kvm->arch.ipte_wq); } -void ipte_lock(struct kvm_vcpu *vcpu) +void ipte_lock(struct kvm *kvm) { - if (vcpu->arch.sie_block->eca & ECA_SII) - ipte_lock_siif(vcpu); + if (sclp.has_siif) + ipte_lock_siif(kvm); else - ipte_lock_simple(vcpu); + ipte_lock_simple(kvm); } -void ipte_unlock(struct kvm_vcpu *vcpu) +void ipte_unlock(struct kvm *kvm) { - if (vcpu->arch.sie_block->eca & ECA_SII) - ipte_unlock_siif(vcpu); + if (sclp.has_siif) + ipte_unlock_siif(kvm); else - ipte_unlock_simple(vcpu); + ipte_unlock_simple(kvm); } static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, u8 ar, @@ -1086,7 +1086,7 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, try_storage_prot_override = storage_prot_override_applicable(vcpu); need_ipte_lock = psw_bits(*psw).dat && !asce.r; if (need_ipte_lock) - ipte_lock(vcpu); + ipte_lock(vcpu->kvm); /* * Since we do the access further down ultimately via a move instruction * that does key checking and returns an error in case of a protection @@ -1127,7 +1127,7 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, } out_unlock: if (need_ipte_lock) - ipte_unlock(vcpu); + ipte_unlock(vcpu->kvm); if (nr_pages > ARRAY_SIZE(gpa_array)) vfree(gpas); return rc; @@ -1199,10 +1199,10 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, rc = get_vcpu_asce(vcpu, &asce, gva, ar, mode); if (rc) return rc; - ipte_lock(vcpu); + ipte_lock(vcpu->kvm); rc = guest_range_to_gpas(vcpu, gva, ar, NULL, length, asce, mode, access_key); - ipte_unlock(vcpu); + ipte_unlock(vcpu->kvm); return rc; } @@ -1465,7 +1465,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, * tables/pointers we read stay valid - unshadowing is however * always possible - only guest_table_lock protects us. */ - ipte_lock(vcpu); + ipte_lock(vcpu->kvm); rc = gmap_shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake); if (rc) @@ -1499,7 +1499,7 @@ shadow_page: pte.p |= dat_protection; if (!rc) rc = gmap_shadow_page(sg, saddr, __pte(pte.val)); - ipte_unlock(vcpu); + ipte_unlock(vcpu->kvm); mmap_read_unlock(sg->mm); return rc; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 1124ff282012..9408d6cc8e2c 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -440,9 +440,9 @@ int read_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, return access_guest_real(vcpu, gra, data, len, 0); } -void ipte_lock(struct kvm_vcpu *vcpu); -void ipte_unlock(struct kvm_vcpu *vcpu); -int ipte_lock_held(struct kvm_vcpu *vcpu); +void ipte_lock(struct kvm *kvm); +void ipte_unlock(struct kvm *kvm); +int ipte_lock_held(struct kvm *kvm); int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra); /* MVPG PEI indication bits */ diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 83bb5cf97282..12c464c7cddf 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -442,7 +442,7 @@ static int handle_ipte_interlock(struct kvm_vcpu *vcpu) vcpu->stat.instruction_ipte_interlock++; if (psw_bits(vcpu->arch.sie_block->gpsw).pstate) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu)); + wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu->kvm)); kvm_s390_retry_instr(vcpu); VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation"); return 0; @@ -1471,7 +1471,7 @@ static int handle_tprot(struct kvm_vcpu *vcpu) access_key = (operand2 & 0xf0) >> 4; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) - ipte_lock(vcpu); + ipte_lock(vcpu->kvm); ret = guest_translate_address_with_key(vcpu, address, ar, &gpa, GACC_STORE, access_key); @@ -1508,7 +1508,7 @@ static int handle_tprot(struct kvm_vcpu *vcpu) } if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) - ipte_unlock(vcpu); + ipte_unlock(vcpu->kvm); return ret; } -- cgit From 24fe0195bc19306b2769b43b3e22bd35bd6fb061 Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Thu, 14 Jul 2022 12:18:23 +0200 Subject: KVM: s390: guest support for topology function We report a topology change to the guest for any CPU hotplug. The reporting to the guest is done using the Multiprocessor Topology-Change-Report (MTCR) bit of the utility entry in the guest's SCA which will be cleared during the interpretation of PTF. On every vCPU creation we set the MCTR bit to let the guest know the next time it uses the PTF with command 2 instruction that the topology changed and that it should use the STSI(15.1.x) instruction to get the topology details. STSI(15.1.x) gives information on the CPU configuration topology. Let's accept the interception of STSI with the function code 15 and let the userland part of the hypervisor handle it when userland supports the CPU Topology facility. Signed-off-by: Pierre Morel Reviewed-by: Nico Boehr Reviewed-by: Janis Schoetterl-Glausch Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220714101824.101601-2-pmorel@linux.ibm.com Message-Id: <20220714101824.101601-2-pmorel@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/include/asm/kvm_host.h | 18 +++++++++++++++--- arch/s390/kvm/kvm-s390.c | 31 +++++++++++++++++++++++++++++++ arch/s390/kvm/priv.c | 20 ++++++++++++++++---- arch/s390/kvm/vsie.c | 8 ++++++++ 4 files changed, 70 insertions(+), 7 deletions(-) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 6f9fc8bb0303..f39092e0ceaa 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -95,19 +95,30 @@ union ipte_control { }; }; +union sca_utility { + __u16 val; + struct { + __u16 mtcr : 1; + __u16 reserved : 15; + }; +}; + struct bsca_block { union ipte_control ipte_control; __u64 reserved[5]; __u64 mcn; - __u64 reserved2; + union sca_utility utility; + __u8 reserved2[6]; struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS]; }; struct esca_block { union ipte_control ipte_control; - __u64 reserved1[7]; + __u64 reserved1[6]; + union sca_utility utility; + __u8 reserved2[6]; __u64 mcn[4]; - __u64 reserved2[20]; + __u64 reserved3[20]; struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS]; }; @@ -251,6 +262,7 @@ struct kvm_s390_sie_block { #define ECB_SPECI 0x08 #define ECB_SRSI 0x04 #define ECB_HOSTPROTINT 0x02 +#define ECB_PTF 0x01 __u8 ecb; /* 0x0061 */ #define ECB2_CMMA 0x80 #define ECB2_IEP 0x20 diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5b77c43fbb01..5d18b66a08c9 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1763,6 +1763,32 @@ static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) return ret; } +/** + * kvm_s390_update_topology_change_report - update CPU topology change report + * @kvm: guest KVM description + * @val: set or clear the MTCR bit + * + * Updates the Multiprocessor Topology-Change-Report bit to signal + * the guest with a topology change. + * This is only relevant if the topology facility is present. + * + * The SCA version, bsca or esca, doesn't matter as offset is the same. + */ +static void kvm_s390_update_topology_change_report(struct kvm *kvm, bool val) +{ + union sca_utility new, old; + struct bsca_block *sca; + + read_lock(&kvm->arch.sca_lock); + sca = kvm->arch.sca; + do { + old = READ_ONCE(sca->utility); + new = old; + new.mtcr = val; + } while (cmpxchg(&sca->utility.val, old.val, new.val) != old.val); + read_unlock(&kvm->arch.sca_lock); +} + static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { int ret; @@ -3172,6 +3198,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_clear_async_pf_completion_queue(vcpu); if (!kvm_is_ucontrol(vcpu->kvm)) sca_del_vcpu(vcpu); + kvm_s390_update_topology_change_report(vcpu->kvm, 1); if (kvm_is_ucontrol(vcpu->kvm)) gmap_remove(vcpu->arch.gmap); @@ -3574,6 +3601,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->ecb |= ECB_HOSTPROTINT; if (test_kvm_facility(vcpu->kvm, 9)) vcpu->arch.sie_block->ecb |= ECB_SRSI; + if (test_kvm_facility(vcpu->kvm, 11)) + vcpu->arch.sie_block->ecb |= ECB_PTF; if (test_kvm_facility(vcpu->kvm, 73)) vcpu->arch.sie_block->ecb |= ECB_TE; if (!kvm_is_ucontrol(vcpu->kvm)) @@ -3707,6 +3736,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) rc = kvm_s390_vcpu_setup(vcpu); if (rc) goto out_ucontrol_uninit; + + kvm_s390_update_topology_change_report(vcpu->kvm, 1); return 0; out_ucontrol_uninit: diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 12c464c7cddf..3335fa09b6f1 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -873,10 +873,18 @@ static int handle_stsi(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - if (fc > 3) { - kvm_s390_set_psw_cc(vcpu, 3); - return 0; - } + /* Bailout forbidden function codes */ + if (fc > 3 && fc != 15) + goto out_no_data; + + /* + * fc 15 is provided only with + * - PTF/CPU topology support through facility 15 + * - KVM_CAP_S390_USER_STSI + */ + if (fc == 15 && (!test_kvm_facility(vcpu->kvm, 11) || + !vcpu->kvm->arch.user_stsi)) + goto out_no_data; if (vcpu->run->s.regs.gprs[0] & 0x0fffff00 || vcpu->run->s.regs.gprs[1] & 0xffff0000) @@ -910,6 +918,10 @@ static int handle_stsi(struct kvm_vcpu *vcpu) goto out_no_data; handle_stsi_3_2_2(vcpu, (void *) mem); break; + case 15: /* fc 15 is fully handled in userspace */ + insert_stsi_usr_data(vcpu, operand2, ar, fc, sel1, sel2); + trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); + return -EREMOTE; } if (kvm_s390_pv_cpu_is_protected(vcpu)) { memcpy((void *)sida_origin(vcpu->arch.sie_block), (void *)mem, diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index dada78b92691..94138f8f0c1c 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -503,6 +503,14 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) /* Host-protection-interruption introduced with ESOP */ if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP)) scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT; + /* + * CPU Topology + * This facility only uses the utility field of the SCA and none of + * the cpu entries that are problematic with the other interpretation + * facilities so we can pass it through + */ + if (test_kvm_facility(vcpu->kvm, 11)) + scb_s->ecb |= scb_o->ecb & ECB_PTF; /* transactional execution */ if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) { /* remap the prefix is tx is toggled on */ -- cgit From f5ecfee94493475783074e86ded10a0499d779fc Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Thu, 14 Jul 2022 21:43:34 +0200 Subject: KVM: s390: resetting the Topology-Change-Report During a subsystem reset the Topology-Change-Report is cleared. Let's give userland the possibility to clear the MTCR in the case of a subsystem reset. To migrate the MTCR, we give userland the possibility to query the MTCR state. We indicate KVM support for the CPU topology facility with a new KVM capability: KVM_CAP_S390_CPU_TOPOLOGY. Signed-off-by: Pierre Morel Reviewed-by: Janis Schoetterl-Glausch Reviewed-by: Janosch Frank Message-Id: <20220714194334.127812-1-pmorel@linux.ibm.com> Link: https://lore.kernel.org/all/20220714194334.127812-1-pmorel@linux.ibm.com/ [frankja@linux.ibm.com: Simple conflict resolution in Documentation/virt/kvm/api.rst] Signed-off-by: Janosch Frank --- Documentation/virt/kvm/api.rst | 25 ++++++++++++++++++++ arch/s390/include/uapi/asm/kvm.h | 1 + arch/s390/kvm/kvm-s390.c | 51 ++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 4 files changed, 78 insertions(+) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 5be5cc59869d..3c4551a2f6d0 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8269,6 +8269,31 @@ The capability has no effect if the nx_huge_pages module parameter is not set. This capability may only be set before any vCPUs are created. +8.39 KVM_CAP_S390_CPU_TOPOLOGY +------------------------------ + +:Capability: KVM_CAP_S390_CPU_TOPOLOGY +:Architectures: s390 +:Type: vm + +This capability indicates that KVM will provide the S390 CPU Topology +facility which consist of the interpretation of the PTF instruction for +the function code 2 along with interception and forwarding of both the +PTF instruction with function codes 0 or 1 and the STSI(15,1,x) +instruction to the userland hypervisor. + +The stfle facility 11, CPU Topology facility, should not be indicated +to the guest without this capability. + +When this capability is present, KVM provides a new attribute group +on vm fd, KVM_S390_VM_CPU_TOPOLOGY. +This new attribute allows to get, set or clear the Modified Change +Topology Report (MTCR) bit of the SCA through the kvm_device_attr +structure. + +When getting the Modified Change Topology Report value, the attr->addr +must point to a byte where the value will be stored or retrieved from. + 9. Known KVM API problems ========================= diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 7a6b14874d65..a73cf01a1606 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -74,6 +74,7 @@ struct kvm_s390_io_adapter_req { #define KVM_S390_VM_CRYPTO 2 #define KVM_S390_VM_CPU_MODEL 3 #define KVM_S390_VM_MIGRATION 4 +#define KVM_S390_VM_CPU_TOPOLOGY 5 /* kvm attributes for mem_ctrl */ #define KVM_S390_VM_MEM_ENABLE_CMMA 0 diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5d18b66a08c9..edfd4bbd0cba 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -642,6 +642,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_ZPCI_OP: r = kvm_s390_pci_interp_allowed(); break; + case KVM_CAP_S390_CPU_TOPOLOGY: + r = test_facility(11); + break; default: r = 0; } @@ -853,6 +856,20 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) icpt_operexc_on_all_vcpus(kvm); r = 0; break; + case KVM_CAP_S390_CPU_TOPOLOGY: + r = -EINVAL; + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) { + r = -EBUSY; + } else if (test_facility(11)) { + set_kvm_facility(kvm->arch.model.fac_mask, 11); + set_kvm_facility(kvm->arch.model.fac_list, 11); + r = 0; + } + mutex_unlock(&kvm->lock); + VM_EVENT(kvm, 3, "ENABLE: CAP_S390_CPU_TOPOLOGY %s", + r ? "(not available)" : "(success)"); + break; default: r = -EINVAL; break; @@ -1789,6 +1806,31 @@ static void kvm_s390_update_topology_change_report(struct kvm *kvm, bool val) read_unlock(&kvm->arch.sca_lock); } +static int kvm_s390_set_topo_change_indication(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + if (!test_kvm_facility(kvm, 11)) + return -ENXIO; + + kvm_s390_update_topology_change_report(kvm, !!attr->attr); + return 0; +} + +static int kvm_s390_get_topo_change_indication(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + u8 topo; + + if (!test_kvm_facility(kvm, 11)) + return -ENXIO; + + read_lock(&kvm->arch.sca_lock); + topo = ((struct bsca_block *)kvm->arch.sca)->utility.mtcr; + read_unlock(&kvm->arch.sca_lock); + + return put_user(topo, (u8 __user *)attr->addr); +} + static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { int ret; @@ -1809,6 +1851,9 @@ static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MIGRATION: ret = kvm_s390_vm_set_migration(kvm, attr); break; + case KVM_S390_VM_CPU_TOPOLOGY: + ret = kvm_s390_set_topo_change_indication(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1834,6 +1879,9 @@ static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MIGRATION: ret = kvm_s390_vm_get_migration(kvm, attr); break; + case KVM_S390_VM_CPU_TOPOLOGY: + ret = kvm_s390_get_topo_change_indication(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1907,6 +1955,9 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MIGRATION: ret = 0; break; + case KVM_S390_VM_CPU_TOPOLOGY: + ret = test_kvm_facility(kvm, 11) ? 0 : -ENXIO; + break; default: ret = -ENXIO; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 20817dd7f2f1..7e06194129e3 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1168,6 +1168,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_X86_NOTIFY_VMEXIT 219 #define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220 #define KVM_CAP_S390_ZPCI_OP 221 +#define KVM_CAP_S390_CPU_TOPOLOGY 222 #ifdef KVM_CAP_IRQ_ROUTING -- cgit