Merge tag 'block-pull-request' of https://gitlab.com/stefanha/qemu into staging

Pull request

Farhan Ali's s390x host PCI support for the block/nvme.c driver.

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCgAdFiEEhpWov9P5fNqsNXdanKSrs4Grc8gFAmgcviUACgkQnKSrs4Gr
# c8hRswgAupxH5Zhx50F7GzwZyu9TCF2sphEPd2VuFVxze8Sg6mXnJq5BFTjv9IuC
# 0trPppfDyKFKujDk+FA3pl9bT45btm0xctNbFYNRS3HXrVUyMQLy73MlFF2twa5g
# U3uiX2d7DAYOdi5O1Cn3bhlByDh4qSko7YyUDFKio+WU57cdJxEd+pUqwyVXrU3E
# AMC2ZmJdKFGGC+tWxBIAuWNc5apq9yzbiywR8z62/Z2IC+Bym0RpvCbdklqcZb8O
# tpGxDKN8bY6s+hy1NZmA8eBA/iCiu6SUFmNpoe2vSwCFEk9R3gi+UNcuTVt3FaWO
# lgzoZSOelmI3JkF0UBqvKsPXt3fdJw==
# =KII7
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 08 May 2025 10:22:29 EDT
# gpg:                using RSA key 8695A8BFD3F97CDAAC35775A9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>" [ultimate]
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>" [ultimate]
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* tag 'block-pull-request' of https://gitlab.com/stefanha/qemu:
  block/nvme: Use host PCI MMIO API
  include: Add a header to define host PCI MMIO functions
  util: Add functions for s390x mmio read/write

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

5 files changed, 331 insertions, 18 deletions

diff --git a/block/nvme.c b/block/nvme.c
index bbf7c23dcd..8df53ee4ca 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -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(&regs->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(&regs->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(&regs->cc);
+    host_pci_stl_le_p(&regs->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(&regs->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(&regs->aqa,
+                        ((NVME_QUEUE_SIZE - 1) << AQA_ACQS_SHIFT) |
+                        ((NVME_QUEUE_SIZE - 1) << AQA_ASQS_SHIFT));
+    host_pci_stq_le_p(&regs->asq, q->sq.iova);
+    host_pci_stq_le_p(&regs->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(&regs->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(&regs->csts))) {
         if (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) > deadline) {
             error_setg(errp, "Timeout while waiting for device to start (%"
                              PRId64 " ms)",
diff --git a/include/qemu/host-pci-mmio.h b/include/qemu/host-pci-mmio.h
new file mode 100644
index 0000000000..a8ed9938ac
--- /dev/null
+++ b/include/qemu/host-pci-mmio.h
@@ -0,0 +1,136 @@
+/*
+ * API for host PCI MMIO accesses (e.g. Linux VFIO BARs)
+ *
+ * Copyright 2025 IBM Corp.
+ * Author(s): Farhan Ali <alifm@linux.ibm.com>
+ *
+ * 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_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_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
diff --git a/include/qemu/s390x_pci_mmio.h b/include/qemu/s390x_pci_mmio.h
new file mode 100644
index 0000000000..c5f63ecefa
--- /dev/null
+++ b/include/qemu/s390x_pci_mmio.h
@@ -0,0 +1,24 @@
+/*
+ * s390x PCI MMIO definitions
+ *
+ * Copyright 2025 IBM Corp.
+ * Author(s): Farhan Ali <alifm@linux.ibm.com>
+ *
+ * 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 */
diff --git a/util/meson.build b/util/meson.build
index e5cd327e27..1adff96ebd 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -133,4 +133,6 @@ 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
diff --git a/util/s390x_pci_mmio.c b/util/s390x_pci_mmio.c
new file mode 100644
index 0000000000..5ab24fa474
--- /dev/null
+++ b/util/s390x_pci_mmio.c
@@ -0,0 +1,146 @@
+/*
+ * s390x PCI MMIO definitions
+ *
+ * Copyright 2025 IBM Corp.
+ * Author(s): Farhan Ali <alifm@linux.ibm.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include <sys/syscall.h>
+#include "qemu/s390x_pci_mmio.h"
+#include "elf.h"
+
+union register_pair {
+    unsigned __int128 pair;
+    struct {
+        uint64_t even;
+        uint64_t odd;
+    };
+};
+
+static bool is_mio_supported;
+
+static __attribute__((constructor)) void check_is_mio_supported(void)
+{
+    is_mio_supported = !!(qemu_getauxval(AT_HWCAP) & HWCAP_S390_PCI_MIO);
+}
+
+static uint64_t s390x_pcilgi(const void *ioaddr, size_t len)
+{
+    union register_pair ioaddr_len = { .even = (uint64_t)ioaddr,
+                                       .odd = len };
+    uint64_t val;
+    int cc;
+
+    asm volatile(
+        /* pcilgi */
+        ".insn   rre,0xb9d60000,%[val],%[ioaddr_len]\n"
+        "ipm     %[cc]\n"
+        "srl     %[cc],28\n"
+        : [cc] "=d"(cc), [val] "=d"(val),
+        [ioaddr_len] "+d"(ioaddr_len.pair) :: "cc");
+
+    if (cc) {
+        val = -1ULL;
+    }
+
+    return val;
+}
+
+static void s390x_pcistgi(void *ioaddr, uint64_t val, size_t len)
+{
+    union register_pair ioaddr_len = {.even = (uint64_t)ioaddr, .odd = len};
+
+    asm volatile (
+        /* pcistgi */
+        ".insn   rre,0xb9d40000,%[val],%[ioaddr_len]\n"
+        : [ioaddr_len] "+d" (ioaddr_len.pair)
+        : [val] "d" (val)
+        : "cc", "memory");
+}
+
+uint8_t s390x_pci_mmio_read_8(const void *ioaddr)
+{
+    uint8_t val = 0;
+
+    if (is_mio_supported) {
+        val = s390x_pcilgi(ioaddr, sizeof(val));
+    } else {
+        syscall(__NR_s390_pci_mmio_read, ioaddr, &val, sizeof(val));
+    }
+    return val;
+}
+
+uint16_t s390x_pci_mmio_read_16(const void *ioaddr)
+{
+    uint16_t val = 0;
+
+    if (is_mio_supported) {
+        val = s390x_pcilgi(ioaddr, sizeof(val));
+    } else {
+        syscall(__NR_s390_pci_mmio_read, ioaddr, &val, sizeof(val));
+    }
+    return val;
+}
+
+uint32_t s390x_pci_mmio_read_32(const void *ioaddr)
+{
+    uint32_t val = 0;
+
+    if (is_mio_supported) {
+        val = s390x_pcilgi(ioaddr, sizeof(val));
+    } else {
+        syscall(__NR_s390_pci_mmio_read, ioaddr, &val, sizeof(val));
+    }
+    return val;
+}
+
+uint64_t s390x_pci_mmio_read_64(const void *ioaddr)
+{
+    uint64_t val = 0;
+
+    if (is_mio_supported) {
+        val = s390x_pcilgi(ioaddr, sizeof(val));
+    } else {
+        syscall(__NR_s390_pci_mmio_read, ioaddr, &val, sizeof(val));
+    }
+    return val;
+}
+
+void s390x_pci_mmio_write_8(void *ioaddr, uint8_t val)
+{
+    if (is_mio_supported) {
+        s390x_pcistgi(ioaddr, val, sizeof(val));
+    } else {
+        syscall(__NR_s390_pci_mmio_write, ioaddr, &val, sizeof(val));
+    }
+}
+
+void s390x_pci_mmio_write_16(void *ioaddr, uint16_t val)
+{
+    if (is_mio_supported) {
+        s390x_pcistgi(ioaddr, val, sizeof(val));
+    } else {
+        syscall(__NR_s390_pci_mmio_write, ioaddr, &val, sizeof(val));
+    }
+}
+
+void s390x_pci_mmio_write_32(void *ioaddr, uint32_t val)
+{
+    if (is_mio_supported) {
+        s390x_pcistgi(ioaddr, val, sizeof(val));
+    } else {
+        syscall(__NR_s390_pci_mmio_write, ioaddr, &val, sizeof(val));
+    }
+}
+
+void s390x_pci_mmio_write_64(void *ioaddr, uint64_t val)
+{
+    if (is_mio_supported) {
+        s390x_pcistgi(ioaddr, val, sizeof(val));
+    } else {
+        syscall(__NR_s390_pci_mmio_write, ioaddr, &val, sizeof(val));
+    }
+}