Enable QEMU NVMe userspace driver on s390x
Subsystems (2)
v6 cover Enable QEMU NVMe userspace driver on s390x
Hi,
Recently on s390x we have enabled mmap support for vfio-pci devices [1]. This allows us to take advantage and use userspace drivers on s390x. However, on s390x we have special instructions for MMIO access. Starting with z15 (and newer platforms) we have new PCI Memory I/O (MIO) instructions which operate on virtually mapped PCI memory spaces, and can be used from userspace. On older platforms we would fallback to using existing system calls for MMIO access.
This patch series introduces support the PCI MIO instructions, and enables s390x support for the userspace NVMe driver on s390x. I would appreciate any review/feedback on the patches.
Thanks
Farhan
[1] https://lore.kernel.org/linux-s390/[email protected]/
ChangeLog
---------
v5 series https://lore.kernel.org/qemu-devel/[email protected]/
v5 -> v6
- Address Thomas's comments/nits (patch 1 and patch 2).
v4 series https://lore.kernel.org/qemu-devel/[email protected]/
v4 -> v5
- Fixup typo in PCI MMIO API (patch 2).
v3 series https://lore.kernel.org/qemu-devel/[email protected]/
v3 -> v4
- Use generic ld/st functions for non s390x PCI access suggested by Alex (patch 2).
- Removed R-b for patch 2 as the host PCI MMIO access API changed for non-s390x. Would appreciate review on this again.
v2 series https://mail.gnu.org/archive/html/qemu-devel/2025-03/msg06847.html
v2 -> v3
- Update the PCI MMIO APIs to reflect that its PCI MMIO access on host
as suggested by Stefan(patch 2)
- Move s390x ifdef check to s390x_pci_mmio.h as suggested by Philippe (patch 1)
- Add R-bs for the respective patches.
v1 series https://mail.gnu.org/archive/html/qemu-devel/2025-03/msg06596.html
v1 -> v2
- Add 8 and 16 bit reads/writes for completeness (patch 1)
- Introduce new QEMU PCI MMIO read/write API as suggested by Stefan (patch 2)
- Update NVMe userspace driver to use QEMU PCI MMIO functions (patch 3)
Farhan Ali (3):
util: Add functions for s390x mmio read/write
include: Add a header to define host PCI MMIO functions block/nvme: Use host PCI MMIO API
block/nvme.c | 41 +++++----- include/qemu/host-pci-mmio.h | 136 +++++++++++++++++++++++++++++++ include/qemu/s390x_pci_mmio.h | 24 ++++++ util/meson.build | 2 + util/s390x_pci_mmio.c | 146 ++++++++++++++++++++++++++++++++++ 5 files changed, 331 insertions(+), 18 deletions(-) create mode 100644 include/qemu/host-pci-mmio.h create mode 100644 include/qemu/s390x_pci_mmio.h create mode 100644 util/s390x_pci_mmio.c
Signature · 1 line
2.43.0
PATCH v6 1/3 util: Add functions for s390x mmio read/write
Starting with z15 (or newer) we can execute mmio
instructions from userspace. On older platforms
where we don't have these instructions available
we can fallback to using system calls to access
the PCI mapped resources.
This patch adds helper functions for mmio reads
and writes for s390x.
--- include/qemu/s390x_pci_mmio.h | 24 ++++++ util/meson.build | 2 + util/s390x_pci_mmio.c | 146 ++++++++++++++++++++++++++++++++++ 3 files changed, 172 insertions(+) create mode 100644 include/qemu/s390x_pci_mmio.h create mode 100644 util/s390x_pci_mmio.c
include/qemu/s390x_pci_mmio.h new file +24 -0
@@ -0,0 +1,24 @@ +/* +* s390x PCI MMIO definitions +* +* Copyright 2025 IBM Corp. +* Author(s): Farhan Ali <[email protected]> +* +* SPDX-License-Identifier: GPL-2.0-or-later +*/ +#ifndef S390X_PCI_MMIO_H +#define S390X_PCI_MMIO_H + +#ifdef __s390x__ +uint8_t s390x_pci_mmio_read_8 (const void *ioaddr); +uint16_t s390x_pci_mmio_read_16 (const void *ioaddr); +uint32_t s390x_pci_mmio_read_32 (const void *ioaddr); +uint64_t s390x_pci_mmio_read_64 (const void *ioaddr); + +void s390x_pci_mmio_write_8 (void *ioaddr,uint8_t val); +void s390x_pci_mmio_write_16 (void *ioaddr,uint16_t val); +void s390x_pci_mmio_write_32 (void *ioaddr,uint32_t val); +void s390x_pci_mmio_write_64 (void *ioaddr,uint64_t val); +#endif /* __s390x__ */ + +#endif /* S390X_PCI_MMIO_H */
util/meson.build +2 -0
@@ -131,4 +131,6 @@ elif cpu in ['ppc', 'ppc64'] util_ss.add(files('cpuinfo-ppc.c')) elif cpu in ['riscv32', 'riscv64'] util_ss.add(files('cpuinfo-riscv.c')) +elif cpu == 's390x' + util_ss.add(files('s390x_pci_mmio.c')) endif
util/s390x_pci_mmio.c new file +146 -0
146 lines not on this page · raw message
Signature · 1 line
2.43.0
Re: [PATCH v6 1/3] util: Add functions for s390x mmio read/write
Quoted 12 lines · Farhan Ali
Starting with z15 (or newer) we can execute mmio instructions from userspace. On older platforms where we don't have these instructions available we can fallback to using system calls to access the PCI mapped resources.
This patch adds helper functions for mmio reads and writes for s390x.
Reviewed-by Stefan Hajnoczi <[email protected]>Reviewed-by Niklas Schnelle <[email protected]>Signed-off-by Farhan Ali <[email protected]>
Quoted 7 lines
--- include/qemu/s390x_pci_mmio.h | 24 ++++++ util/meson.build | 2 + util/s390x_pci_mmio.c | 146 ++++++++++++++++++++++++++++++++++ 3 files changed, 172 insertions(+)create mode 100644
include/qemu/s390x_pci_mmio.hcreate mode 100644util/s390x_pci_mmio.c
FWIW,
PATCH v6 2/3 include: Add a header to define host PCI MMIO functions
In reply to Farhan AliAdd a generic API for host PCI MMIO reads/writes (e.g. Linux VFIO BAR accesses). The functions access little endian memory and returns the result in host cpu endianness.
--- include/qemu/host-pci-mmio.h | 136 +++++++++++++++++++++++++++++++++++ 1 file changed, 136 insertions(+) create mode 100644 include/qemu/host-pci-mmio.h
include/qemu/host-pci-mmio.h new file +136 -0
@@ -0,0 +1,136 @@ +/* +* API for host PCI MMIO accesses (e.g. Linux VFIO BARs) +* +* Copyright 2025 IBM Corp. +* Author(s): Farhan Ali <[email protected]> +* +* SPDX-License-Identifier: GPL-2.0-or-later +*/ + +#ifndef HOST_PCI_MMIO_H +#define HOST_PCI_MMIO_H + +#include "qemu/bswap.h" +#include "qemu/s390x_pci_mmio.h" + +static inline uint8_t host_pci_ldub_p (const void *ioaddr) +{ +uint8_t ret =0 ; +#ifdef __s390x__ + ret =s390x_pci_mmio_read_8 (ioaddr); +#else + ret =ldub_p (ioaddr); +#endif + +return ret; +} + +static inline uint16_t host_pci_lduw_le_p (const void *ioaddr) +{ +uint16_t ret =0 ; +#ifdef __s390x__ + ret =le16_to_cpu (s390x_pci_mmio_read_16 (ioaddr)); +#else + ret =lduw_le_p (ioaddr); +#endif + +return ret; +} + +static inline uint32_t host_pci_ldl_le_p (const void *ioaddr) +{ +uint32_t ret =0 ; +#ifdef __s390x__ + ret =le32_to_cpu (s390x_pci_mmio_read_32 (ioaddr)); +#else + ret =ldl_le_p (ioaddr); +#endif + +return ret; +} + +static inline uint64_t host_pci_ldq_le_p (const void *ioaddr) +{ +uint64_t ret =0 ; +#ifdef __s390x__ + ret =le64_to_cpu (s390x_pci_mmio_read_64 (ioaddr)); +#else + ret =ldq_le_p (ioaddr); +#endif + +return ret; +} + +static inline void host_pci_stb_le_p (void *ioaddr,uint8_t val) +{ +#ifdef __s390x__ +s390x_pci_mmio_write_8 (ioaddr, val); +#else +stb_p (ioaddr, val); +#endif +} + +static inline void host_pci_stw_le_p (void *ioaddr,uint16_t val) +{ +#ifdef __s390x__ +s390x_pci_mmio_write_16 (ioaddr,cpu_to_le16 (val)); +#else +stw_le_p (ioaddr, val); +#endif +} + +static inline void host_pci_stl_le_p (void *ioaddr,uint32_t val) +{ +#ifdef __s390x__ +s390x_pci_mmio_write_32 (ioaddr,cpu_to_le32 (val)); +#else +stl_le_p (ioaddr, val); +#endif +} + +static inline void host_pci_stq_le_p (void *ioaddr,uint64_t val) +{ +#ifdef __s390x__ +s390x_pci_mmio_write_64 (ioaddr,cpu_to_le64 (val)); +#else +stq_le_p (ioaddr, val); +#endif +} + +static inline uint64_t host_pci_ldn_le_p (const void *ioaddr,int sz) +{ +switch (sz) { +case 1 : +return host_pci_ldub_p (ioaddr); +case 2 : +return host_pci_lduw_le_p (ioaddr); +case 4 : +return host_pci_ldl_le_p (ioaddr); +case 8 : +return host_pci_ldq_le_p (ioaddr); +default : +g_assert_not_reached (); + } +} + +static inline void host_pci_stn_le_p (void *ioaddr,int sz,uint64_t v) +{ +switch (sz) { +case 1 : +host_pci_stb_le_p (ioaddr, v); +break ; +case 2 : +host_pci_stw_le_p (ioaddr, v); +break ; +case 4 : +host_pci_stl_le_p (ioaddr, v); +break ; +case 8 : +host_pci_stq_le_p (ioaddr, v); +break ; +default : +g_assert_not_reached (); + } +} + +#endif
Signature · 1 line
2.43.0
Re: [PATCH v6 2/3] include: Add a header to define host PCI MMIO functions
Quoted 8 lines · Farhan Ali
Add a generic API for host PCI MMIO reads/writes (e.g. Linux VFIO BAR accesses). The functions access little endian memory and returns the result in host cpu endianness.
Reviewed-by Stefan Hajnoczi <[email protected]>Signed-off-by Farhan Ali <[email protected]>---
...
Quoted 11 lines
include/qemu/host-pci-mmio.h new file +11
-0+static inline uint8_t host_pci_ldub_p (const void *ioaddr) +{ +uint8_t ret =0 ; +#ifdef __s390x__ + ret =s390x_pci_mmio_read_8 (ioaddr); +#else + ret =ldub_p (ioaddr); +#endif + +return ret; +}
...
include/qemu/host-pci-mmio.h line 71
Quoted 8 lines
include/qemu/host-pci-mmio.h new file +8
-0+static inline void host_pci_stb_le_p (void *ioaddr,uint8_t val) +{ +#ifdef __s390x__ +s390x_pci_mmio_write_8 (ioaddr, val); +#else +stb_p (ioaddr, val); +#endif +}
Cosmetic nit: host_pci_ldub_p() does not have a "_le_" in its name, while host_pci_stb_le_p() has it. Could be fixed up while picking up the patch, so no need to respin just because of this.
Re: [PATCH v6 2/3] include: Add a header to define host PCI MMIO functions
Quoted 33 lines · Thomas Huth
Quoted 8 lines · Farhan Ali
Add a generic API for host PCI MMIO reads/writes (e.g. Linux VFIO BAR accesses). The functions access little endian memory and returns the result in host cpu endianness.
Reviewed-by Stefan Hajnoczi <[email protected]>Signed-off-by Farhan Ali <[email protected]>---
...
Quoted 11 lines
include/qemu/host-pci-mmio.h new file +11
-0+static inline uint8_t host_pci_ldub_p (const void *ioaddr) +{ + uint8_t ret = 0; +#ifdef __s390x__ + ret = s390x_pci_mmio_read_8(ioaddr); +#else + ret = ldub_p(ioaddr); +#endif + + return ret; +}...
include/qemu/host-pci-mmio.h line 71
Quoted 8 lines
include/qemu/host-pci-mmio.h new file +8
-0+static inline void host_pci_stb_le_p (void *ioaddr,uint8_t val) +{ +#ifdef __s390x__ + s390x_pci_mmio_write_8(ioaddr, val); +#else + stb_p(ioaddr, val); +#endif +}Cosmetic nit:
host_pci_ldub_p()does not have a "_le_" in its name, whilehost_pci_stb_le_p()has it. Could be fixed up while picking up the patch, so no need to respin just because of this.
Quoted 3 lines
Reviewed-by Thomas Huth <[email protected]>
Thanks Thomas! if there are no other concerns with the patches would these patches go through the s390x tree or the block tree?
Thanks
Farhan
Re: [PATCH v6 2/3] include: Add a header to define host PCI MMIO functions
Quoted 36 lines · Farhan Ali
Quoted 35 lines · Thomas Huth
Quoted 8 lines · Farhan Ali
Add a generic API for host PCI MMIO reads/writes (e.g. Linux VFIO BAR accesses). The functions access little endian memory and returns the result in host cpu endianness.
Reviewed-by Stefan Hajnoczi <[email protected]>Signed-off-by Farhan Ali <[email protected]>---
...
Quoted 11 lines
include/qemu/host-pci-mmio.h new file +11
-0+static inline uint8_t host_pci_ldub_p (const void *ioaddr) +{ +uint8_t ret =0 ; +#ifdef __s390x__ + ret =s390x_pci_mmio_read_8 (ioaddr); +#else + ret =ldub_p (ioaddr); +#endif + +return ret; +}...
include/qemu/host-pci-mmio.h line 71
Quoted 8 lines
include/qemu/host-pci-mmio.h new file +8
-0+static inline void host_pci_stb_le_p (void *ioaddr,uint8_t val) +{ +#ifdef __s390x__ +s390x_pci_mmio_write_8 (ioaddr, val); +#else +stb_p (ioaddr, val); +#endif +}Cosmetic nit:
host_pci_ldub_p()does not have a "_le_" in its name, whilehost_pci_stb_le_p()has it. Could be fixed up while picking up the patch, so no need to respin just because of this.
Quoted 6 lines
Quoted 3 lines
Reviewed-by Thomas Huth <[email protected]>Thanks Thomas! if there are no other concerns with the patches would these patches go through the s390x tree or the block tree?
I can merge them through my block tree once there are no more code review comments from others.
Stefan
PATCH v6 3/3 block/nvme: Use host PCI MMIO API
In reply to Farhan AliUse the host PCI MMIO functions to read/write to NVMe registers, rather than directly accessing them.
--- block/nvme.c | 41 +++++++++++++++++++++++------------------ 1 file changed, 23 insertions(+), 18 deletions(-)
block/nvme.c +23 -18
@@ -18,6 +18,7 @@#include "qobject/qstring.h" #include "qemu/defer-call.h" #include "qemu/error-report.h" +#include "qemu/host-pci-mmio.h" #include "qemu/main-loop.h" #include "qemu/module.h" #include "qemu/cutils.h"
@@ -60,7 +61,7 @@ typedef struct {uint8_t *queue;uint64_t iova;/* Hardware MMIO register */ -volatile uint32_t *doorbell; +uint32_t *doorbell; } NVMeQueue; typedef struct {
@@ -100,7 +101,7 @@ struct BDRVNVMeState {QEMUVFIOState *vfio;void *bar0_wo_map;/* Memory mapped registers */ -volatile struct { +struct {uint32_t sq_tail;uint32_t cq_head; } *doorbells;
@@ -292,7 +293,7 @@ static void nvme_kick(NVMeQueuePair *q)assert (!(q->sq.tail &0xFF00 ));/* Fence the write to submission queue entry before notifying the device. */ smp_wmb (); - *q->sq.doorbell =cpu_to_le32 (q->sq.tail); +host_pci_stl_le_p (q->sq.doorbell, q->sq.tail); q->inflight += q->need_kick; q->need_kick =0 ; }
@@ -441,7 +442,7 @@ static bool nvme_process_completion(NVMeQueuePair *q)if (progress) {/* Notify the device so it can post more completions. */ smp_mb_release (); - *q->cq.doorbell =cpu_to_le32 (q->cq.head); +host_pci_stl_le_p (q->cq.doorbell, q->cq.head);nvme_wake_free_req_locked (q); }
@@ -460,7 +461,7 @@ static void nvme_process_completion_bh(void *opaque)* so notify the device that it has space to fill in more completions now. */ smp_mb_release (); - *q->cq.doorbell =cpu_to_le32 (q->cq.head); +host_pci_stl_le_p (q->cq.doorbell, q->cq.head);nvme_wake_free_req_locked (q);nvme_process_completion (q);
@@ -749,9 +750,10 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,int ret;uint64_t cap;uint32_t ver; +uint32_t cc;uint64_t timeout_ms;uint64_t deadline, now; -volatile NvmeBar *regs =NULL ; +NvmeBar *regs =NULL ;qemu_co_mutex_init (&s->dma_map_lock);qemu_co_queue_init (&s->dma_flush_queue);
@@ -779,7 +781,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,/* Perform initialize sequence as described in NVMe spec "7.6.1 * Initialization". */ - cap =le64_to_cpu (regs->cap); + cap =host_pci_ldq_le_p (®s->cap);trace_nvme_controller_capability_raw (cap);trace_nvme_controller_capability ("Maximum Queue Entries Supported" ,1 +NVME_CAP_MQES (cap));
@@ -805,16 +807,17 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, bs->bl.request_alignment = s->page_size; timeout_ms =MIN (500 *NVME_CAP_TO (cap),30000 ); - ver =le32_to_cpu (regs->vs); + ver =host_pci_ldl_le_p (®s->vs);trace_nvme_controller_spec_version (extract32 (ver,16 ,16 ),extract32 (ver,8 ,8 ),extract32 (ver,0 ,8 ));/* Reset device to get a clean state. */ - regs->cc =cpu_to_le32 (le32_to_cpu (regs->cc) &0xFE ); + cc =host_pci_ldl_le_p (®s->cc); +host_pci_stl_le_p (®s->cc, cc &0xFE );/* Wait for CSTS.RDY = 0. */ deadline =qemu_clock_get_ns (QEMU_CLOCK_REALTIME ) + timeout_ms *SCALE_MS ; -while (NVME_CSTS_RDY (le32_to_cpu (regs->csts))) { +while (NVME_CSTS_RDY (host_pci_ldl_le_p (®s->csts))) {if (qemu_clock_get_ns (QEMU_CLOCK_REALTIME ) > deadline) { error_setg(errp, "Timeout while waiting for device to reset (%" PRId64 " ms)",
@@ -843,19 +846,21 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, s->queues[INDEX_ADMIN ] = q; s->queue_count =1 ;QEMU_BUILD_BUG_ON ((NVME_QUEUE_SIZE -1 ) &0xF000 ); - regs->aqa =cpu_to_le32 (((NVME_QUEUE_SIZE -1 ) <<AQA_ACQS_SHIFT ) | - ((NVME_QUEUE_SIZE -1 ) <<AQA_ASQS_SHIFT )); - regs->asq =cpu_to_le64 (q->sq.iova); - regs->acq =cpu_to_le64 (q->cq.iova); +host_pci_stl_le_p (®s->aqa, + ((NVME_QUEUE_SIZE -1 ) <<AQA_ACQS_SHIFT ) | + ((NVME_QUEUE_SIZE -1 ) <<AQA_ASQS_SHIFT )); +host_pci_stq_le_p (®s->asq, q->sq.iova); +host_pci_stq_le_p (®s->acq, q->cq.iova);/* After setting up all control registers we can enable device now. */ - regs->cc =cpu_to_le32 ((ctz32 (NVME_CQ_ENTRY_BYTES ) <<CC_IOCQES_SHIFT ) | - (ctz32 (NVME_SQ_ENTRY_BYTES ) <<CC_IOSQES_SHIFT ) | -CC_EN_MASK ); +host_pci_stl_le_p (®s->cc, + (ctz32 (NVME_CQ_ENTRY_BYTES ) <<CC_IOCQES_SHIFT ) | + (ctz32 (NVME_SQ_ENTRY_BYTES ) <<CC_IOSQES_SHIFT ) | +CC_EN_MASK );/* Wait for CSTS.RDY = 1. */ now =qemu_clock_get_ns (QEMU_CLOCK_REALTIME ); deadline = now + timeout_ms *SCALE_MS ; -while (!NVME_CSTS_RDY (le32_to_cpu (regs->csts))) { +while (!NVME_CSTS_RDY (host_pci_ldl_le_p (®s->csts))) {if (qemu_clock_get_ns (QEMU_CLOCK_REALTIME ) > deadline) { error_setg(errp, "Timeout while waiting for device to start (%" PRId64 " ms)",
Signature · 1 line
2.43.0