[SeaBIOS] [PATCH v4] Add pvscsi boot support
Evgeny Budilovsky
evgeny.budilovsky at ravellosystems.com
Mon Oct 14 17:03:36 CEST 2013
Testing was done on windows images (win 2008/2012) taken from esx with vmware
tools installed and boot disk configured to use pvscsi.
Also I've used linux (ubuntu 12.04) where pvscsi drivers are installed by
default and booted it using qemu cmd similar to this:
./x86_64-softmmu/qemu-system-x86_64 -snapshot -device pvscsi,id=pvscsi0 \
-device scsi-disk,bus=pvscsi0.0,drive=drive0 \
-drive id=drive0,if=none,file=ubuntu-12.04.qcow2 \
-bios roms/seabios/out/bios.bin
Signed-off-by: Evgeny Budilovsky <evgeny.budilovsky at ravellosystems.com>
---
Makefile | 2 +-
src/Kconfig | 12 ++
src/block.c | 1 +
src/block.h | 1 +
src/hw/blockcmd.c | 3 +
src/hw/pci_ids.h | 3 +
src/hw/pvscsi.c | 363 +++++++++++++++++++++++++++++++++++++++++++++++++++++
src/hw/pvscsi.h | 8 ++
src/post.c | 2 +
9 files changed, 394 insertions(+), 1 deletion(-)
create mode 100644 src/hw/pvscsi.c
create mode 100644 src/hw/pvscsi.h
diff --git a/Makefile b/Makefile
index 3218970..6c6302e 100644
--- a/Makefile
+++ b/Makefile
@@ -34,7 +34,7 @@ SRCBOTH=misc.c stacks.c output.c string.c x86.c block.c cdrom.c mouse.c kbd.c \
hw/usb-hid.c hw/usb-msc.c hw/usb-uas.c \
hw/blockcmd.c hw/floppy.c hw/ata.c hw/ahci.c hw/ramdisk.c \
hw/virtio-ring.c hw/virtio-pci.c hw/virtio-blk.c hw/virtio-scsi.c \
- hw/lsi-scsi.c hw/esp-scsi.c hw/megasas.c
+ hw/lsi-scsi.c hw/esp-scsi.c hw/megasas.c hw/pvscsi.c
SRC16=$(SRCBOTH) system.c disk.c font.c
SRC32FLAT=$(SRCBOTH) post.c memmap.c malloc.c pmm.c romfile.c optionroms.c \
boot.c bootsplash.c jpeg.c bmp.c \
diff --git a/src/Kconfig b/src/Kconfig
index c40cc61..38e24bf 100644
--- a/src/Kconfig
+++ b/src/Kconfig
@@ -161,6 +161,18 @@ menu "Hardware support"
default y
help
Support boot from virtio-scsi storage.
+ config PVSCSI
+ depends on DRIVES && QEMU_HARDWARE
+ bool "PVSCSI controllers"
+ default y
+ help
+ Support boot from Paravirtualized SCSI storage. This kind of storage
+ is mainly supported by VMware ESX hypervisor. It is commonly used
+ to allow fast storage access by communicating directly with the
+ underlying hypervisor. Enabling this type of boot will allow
+ booting directly from images imported from an ESX platform,
+ without the need to use slower emulation of storage controllers
+ such as IDE.
config ESP_SCSI
depends on DRIVES && QEMU_HARDWARE
bool "AMD PCscsi controllers"
diff --git a/src/block.c b/src/block.c
index cbcf9e1..2d01f6a 100644
--- a/src/block.c
+++ b/src/block.c
@@ -373,6 +373,7 @@ process_op(struct disk_op_s *op)
case DTYPE_LSI_SCSI:
case DTYPE_ESP_SCSI:
case DTYPE_MEGASAS:
+ case DTYPE_PVSCSI:
return process_scsi_op(op);
default:
op->count = 0;
diff --git a/src/block.h b/src/block.h
index 3492806..aea6a71 100644
--- a/src/block.h
+++ b/src/block.h
@@ -83,6 +83,7 @@ struct drive_s {
#define DTYPE_LSI_SCSI 0x0c
#define DTYPE_ESP_SCSI 0x0d
#define DTYPE_MEGASAS 0x0e
+#define DTYPE_PVSCSI 0x0f
#define MAXDESCSIZE 80
diff --git a/src/hw/blockcmd.c b/src/hw/blockcmd.c
index 7bdcf38..39d3caa 100644
--- a/src/hw/blockcmd.c
+++ b/src/hw/blockcmd.c
@@ -14,6 +14,7 @@
#include "esp-scsi.h" // esp_scsi_cmd_data
#include "lsi-scsi.h" // lsi_scsi_cmd_data
#include "megasas.h" // megasas_cmd_data
+#include "pvscsi.h" // pvscsi_cmd_data
#include "output.h" // dprintf
#include "std/disk.h" // DISK_RET_EPARAM
#include "string.h" // memset
@@ -44,6 +45,8 @@ cdb_cmd_data(struct disk_op_s *op, void *cdbcmd, u16 blocksize)
return esp_scsi_cmd_data(op, cdbcmd, blocksize);
case DTYPE_MEGASAS:
return megasas_cmd_data(op, cdbcmd, blocksize);
+ case DTYPE_PVSCSI:
+ return pvscsi_cmd_data(op, cdbcmd, blocksize);
default:
op->count = 0;
return DISK_RET_EPARAM;
diff --git a/src/hw/pci_ids.h b/src/hw/pci_ids.h
index 322d156..1cd4f72 100644
--- a/src/hw/pci_ids.h
+++ b/src/hw/pci_ids.h
@@ -2618,3 +2618,6 @@
#define PCI_VENDOR_ID_REDHAT_QUMRANET 0x1af4
#define PCI_DEVICE_ID_VIRTIO_BLK 0x1001
#define PCI_DEVICE_ID_VIRTIO_SCSI 0x1004
+
+#define PCI_VENDOR_ID_VMWARE 0x15ad
+#define PCI_DEVICE_ID_VMWARE_PVSCSI 0x07C0
diff --git a/src/hw/pvscsi.c b/src/hw/pvscsi.c
new file mode 100644
index 0000000..740a74b
--- /dev/null
+++ b/src/hw/pvscsi.c
@@ -0,0 +1,363 @@
+// QEMU VMWARE Paravirtualized SCSI boot support.
+//
+// Copyright (c) 2013 Ravello Systems LTD (http://ravellosystems.com)
+//
+// Authors:
+// Evgeny Budilovsky <evgeny.budilovsky at ravellosystems.com>
+//
+// This file may be distributed under the terms of the GNU LGPLv3 license.
+
+#include "biosvar.h" // GET_GLOBAL
+#include "block.h" // struct drive_s
+#include "blockcmd.h" // scsi_drive_setup
+#include "config.h" // CONFIG_*
+#include "malloc.h" // free
+#include "output.h" // dprintf
+#include "pci.h" // foreachpci
+#include "pci_ids.h" // PCI_DEVICE_ID_VMWARE_PVSCSI
+#include "pci_regs.h" // PCI_VENDOR_ID
+#include "std/disk.h" // DISK_RET_SUCCESS
+#include "string.h" // memset
+#include "util.h" // usleep
+#include "pvscsi.h"
+#include "virtio-ring.h" // PAGE_SHIFT, virt_to_phys
+
+#define MASK(n) ((1 << (n)) - 1)
+
+#define SIMPLE_QUEUE_TAG 0x20
+
+#define PVSCSI_INTR_CMPL_0 (1 << 0)
+#define PVSCSI_INTR_CMPL_1 (1 << 1)
+#define PVSCSI_INTR_CMPL_MASK MASK(2)
+
+#define PVSCSI_INTR_MSG_0 (1 << 2)
+#define PVSCSI_INTR_MSG_1 (1 << 3)
+#define PVSCSI_INTR_MSG_MASK (MASK(2) << 2)
+#define PVSCSI_INTR_ALL_SUPPORTED MASK(4)
+
+#define PVSCSI_FLAG_CMD_WITH_SG_LIST (1 << 0)
+#define PVSCSI_FLAG_CMD_OUT_OF_BAND_CDB (1 << 1)
+#define PVSCSI_FLAG_CMD_DIR_NONE (1 << 2)
+#define PVSCSI_FLAG_CMD_DIR_TOHOST (1 << 3)
+#define PVSCSI_FLAG_CMD_DIR_TODEVICE (1 << 4)
+
+enum PVSCSIRegOffset {
+ PVSCSI_REG_OFFSET_COMMAND = 0x0,
+ PVSCSI_REG_OFFSET_COMMAND_DATA = 0x4,
+ PVSCSI_REG_OFFSET_COMMAND_STATUS = 0x8,
+ PVSCSI_REG_OFFSET_LAST_STS_0 = 0x100,
+ PVSCSI_REG_OFFSET_LAST_STS_1 = 0x104,
+ PVSCSI_REG_OFFSET_LAST_STS_2 = 0x108,
+ PVSCSI_REG_OFFSET_LAST_STS_3 = 0x10c,
+ PVSCSI_REG_OFFSET_INTR_STATUS = 0x100c,
+ PVSCSI_REG_OFFSET_INTR_MASK = 0x2010,
+ PVSCSI_REG_OFFSET_KICK_NON_RW_IO = 0x3014,
+ PVSCSI_REG_OFFSET_DEBUG = 0x3018,
+ PVSCSI_REG_OFFSET_KICK_RW_IO = 0x4018,
+};
+
+enum PVSCSICommands {
+ PVSCSI_CMD_FIRST = 0,
+ PVSCSI_CMD_ADAPTER_RESET = 1,
+ PVSCSI_CMD_ISSUE_SCSI = 2,
+ PVSCSI_CMD_SETUP_RINGS = 3,
+ PVSCSI_CMD_RESET_BUS = 4,
+ PVSCSI_CMD_RESET_DEVICE = 5,
+ PVSCSI_CMD_ABORT_CMD = 6,
+ PVSCSI_CMD_CONFIG = 7,
+ PVSCSI_CMD_SETUP_MSG_RING = 8,
+ PVSCSI_CMD_DEVICE_UNPLUG = 9,
+ PVSCSI_CMD_LAST = 10
+};
+
+#define PVSCSI_SETUP_RINGS_MAX_NUM_PAGES 32
+struct PVSCSICmdDescSetupRings {
+ u32 reqRingNumPages;
+ u32 cmpRingNumPages;
+ u64 ringsStatePPN;
+ u64 reqRingPPNs[PVSCSI_SETUP_RINGS_MAX_NUM_PAGES];
+ u64 cmpRingPPNs[PVSCSI_SETUP_RINGS_MAX_NUM_PAGES];
+} PACKED;
+
+struct PVSCSIRingCmpDesc {
+ u64 context;
+ u64 dataLen;
+ u32 senseLen;
+ u16 hostStatus;
+ u16 scsiStatus;
+ u32 pad[2];
+} PACKED;
+
+struct PVSCSIRingsState {
+ u32 reqProdIdx;
+ u32 reqConsIdx;
+ u32 reqNumEntriesLog2;
+
+ u32 cmpProdIdx;
+ u32 cmpConsIdx;
+ u32 cmpNumEntriesLog2;
+
+ u8 pad[104];
+
+ u32 msgProdIdx;
+ u32 msgConsIdx;
+ u32 msgNumEntriesLog2;
+} PACKED;
+
+struct PVSCSIRingReqDesc {
+ u64 context;
+ u64 dataAddr;
+ u64 dataLen;
+ u64 senseAddr;
+ u32 senseLen;
+ u32 flags;
+ u8 cdb[16];
+ u8 cdbLen;
+ u8 lun[8];
+ u8 tag;
+ u8 bus;
+ u8 target;
+ u8 vcpuHint;
+ u8 unused[59];
+} PACKED;
+
+struct pvscsi_ring_dsc_s {
+ struct PVSCSIRingsState *ring_state;
+ struct PVSCSIRingReqDesc *ring_reqs;
+ struct PVSCSIRingCmpDesc *ring_cmps;
+};
+
+struct pvscsi_lun_s {
+ struct drive_s drive;
+ struct pci_device *pci;
+ u32 iobase;
+ u8 target;
+ u8 lun;
+ struct pvscsi_ring_dsc_s *ring_dsc;
+};
+
+static void
+pvscsi_write_cmd_desc(u32 iobase, u32 cmd, const void *desc, size_t len)
+{
+ const u32 *ptr = desc;
+ size_t i;
+
+ len /= sizeof(*ptr);
+ pci_writel(iobase + PVSCSI_REG_OFFSET_COMMAND, cmd);
+ for (i = 0; i < len; i++)
+ pci_writel(iobase + PVSCSI_REG_OFFSET_COMMAND_DATA, ptr[i]);
+}
+
+static void
+pvscsi_kick_rw_io(u32 iobase)
+{
+ pci_writel(iobase + PVSCSI_REG_OFFSET_KICK_RW_IO, 0);
+}
+
+static void
+pvscsi_wait_intr_cmpl(u32 iobase)
+{
+ while (!(pci_readl(iobase + PVSCSI_REG_OFFSET_INTR_STATUS) & PVSCSI_INTR_CMPL_MASK))
+ usleep(5);
+ pci_writel(iobase + PVSCSI_REG_OFFSET_INTR_STATUS, PVSCSI_INTR_CMPL_MASK);
+
+}
+
+static void
+pvscsi_init_rings(u32 iobase, struct pvscsi_ring_dsc_s **ring_dsc)
+{
+ struct PVSCSICmdDescSetupRings cmd = {0,};
+
+ struct pvscsi_ring_dsc_s *dsc = memalign_low(sizeof(*dsc), PAGE_SIZE);
+ if (!dsc) {
+ warn_noalloc();
+ return;
+ }
+
+ dsc->ring_state =
+ (struct PVSCSIRingsState *)memalign_low(PAGE_SIZE, PAGE_SIZE);
+ dsc->ring_reqs =
+ (struct PVSCSIRingReqDesc *)memalign_low(PAGE_SIZE, PAGE_SIZE);
+ dsc->ring_cmps =
+ (struct PVSCSIRingCmpDesc *)memalign_low(PAGE_SIZE, PAGE_SIZE);
+ if (!dsc->ring_state || !dsc->ring_reqs || !dsc->ring_cmps) {
+ warn_noalloc();
+ return;
+ }
+ memset(dsc->ring_state, 0, PAGE_SIZE);
+ memset(dsc->ring_reqs, 0, PAGE_SIZE);
+ memset(dsc->ring_cmps, 0, PAGE_SIZE);
+
+ cmd.reqRingNumPages = 1;
+ cmd.cmpRingNumPages = 1;
+ cmd.ringsStatePPN = virt_to_phys(dsc->ring_state) >> PAGE_SHIFT;
+ cmd.reqRingPPNs[0] = virt_to_phys(dsc->ring_reqs) >> PAGE_SHIFT;
+ cmd.cmpRingPPNs[0] = virt_to_phys(dsc->ring_cmps) >> PAGE_SHIFT;
+
+ pvscsi_write_cmd_desc(iobase, PVSCSI_CMD_SETUP_RINGS,
+ &cmd, sizeof(cmd));
+ *ring_dsc = dsc;
+}
+
+static void pvscsi_fill_req(struct PVSCSIRingsState *s,
+ struct PVSCSIRingReqDesc *req,
+ u16 target, u16 lun, void *cdbcmd, u16 blocksize,
+ struct disk_op_s *op)
+{
+ SET_LOWFLAT(req->bus, 0);
+ SET_LOWFLAT(req->target, target);
+ memset(LOWFLAT2LOW(&req->lun[0]), 0, sizeof(req->lun));
+ SET_LOWFLAT(req->lun[1], lun);
+ SET_LOWFLAT(req->senseLen, 0);
+ SET_LOWFLAT(req->senseAddr, 0);
+ SET_LOWFLAT(req->cdbLen, 16);
+ SET_LOWFLAT(req->vcpuHint, 0);
+ memcpy(LOWFLAT2LOW(&req->cdb[0]), cdbcmd, 16);
+ SET_LOWFLAT(req->tag, SIMPLE_QUEUE_TAG);
+ SET_LOWFLAT(req->flags,
+ cdb_is_read(cdbcmd, blocksize) ?
+ PVSCSI_FLAG_CMD_DIR_TOHOST : PVSCSI_FLAG_CMD_DIR_TODEVICE);
+
+ SET_LOWFLAT(req->dataLen, op->count * blocksize);
+ SET_LOWFLAT(req->dataAddr, (u32)op->buf_fl);
+ SET_LOWFLAT(s->reqProdIdx, GET_LOWFLAT(s->reqProdIdx) + 1);
+
+}
+
+static u32
+pvscsi_get_rsp(struct PVSCSIRingsState *s,
+ struct PVSCSIRingCmpDesc *rsp)
+{
+ u32 status = GET_LOWFLAT(rsp->hostStatus);
+ SET_LOWFLAT(s->cmpConsIdx, GET_LOWFLAT(s->cmpConsIdx)+1);
+ return status;
+}
+
+static int
+pvscsi_cmd(struct pvscsi_lun_s *plun, struct disk_op_s *op,
+ void *cdbcmd, u16 target, u16 lun, u16 blocksize)
+{
+ struct pvscsi_ring_dsc_s *ring_dsc = GET_GLOBAL(plun->ring_dsc);
+ struct PVSCSIRingsState *s = GET_LOWFLAT(ring_dsc->ring_state);
+ u32 req_entries = GET_LOWFLAT(s->reqNumEntriesLog2);
+ u32 cmp_entries = GET_LOWFLAT(s->cmpNumEntriesLog2);
+ struct PVSCSIRingReqDesc *req;
+ struct PVSCSIRingCmpDesc *rsp;
+ u32 status;
+
+ if (GET_LOWFLAT(s->reqProdIdx) - GET_LOWFLAT(s->cmpConsIdx) >= 1 << req_entries) {
+ dprintf(1, "pvscsi: ring full: reqProdIdx=%d cmpConsIdx=%d\n",
+ GET_LOWFLAT(s->reqProdIdx), GET_LOWFLAT(s->cmpConsIdx));
+ return DISK_RET_EBADTRACK;
+ }
+
+ req = GET_LOWFLAT(ring_dsc->ring_reqs) + (GET_LOWFLAT(s->reqProdIdx) & MASK(req_entries));
+ pvscsi_fill_req(s, req, target, lun, cdbcmd, blocksize, op);
+
+ pvscsi_kick_rw_io(GET_GLOBAL(plun->iobase));
+ pvscsi_wait_intr_cmpl(GET_GLOBAL(plun->iobase));
+
+ rsp = GET_LOWFLAT(ring_dsc->ring_cmps) + (GET_LOWFLAT(s->cmpConsIdx) & MASK(cmp_entries));
+ status = pvscsi_get_rsp(s, rsp);
+
+ return status == 0 ? DISK_RET_SUCCESS : DISK_RET_EBADTRACK;
+}
+
+int
+pvscsi_cmd_data(struct disk_op_s *op, void *cdbcmd, u16 blocksize)
+{
+ if (!CONFIG_PVSCSI)
+ return DISK_RET_EBADTRACK;
+
+ struct pvscsi_lun_s *plun =
+ container_of(op->drive_g, struct pvscsi_lun_s, drive);
+
+ return pvscsi_cmd(plun, op, cdbcmd,
+ GET_GLOBAL(plun->target), GET_GLOBAL(plun->lun),
+ blocksize);
+
+}
+
+static int
+pvscsi_add_lun(struct pci_device *pci, u32 iobase,
+ struct pvscsi_ring_dsc_s *ring_dsc, u8 target, u8 lun)
+{
+ struct pvscsi_lun_s *plun = malloc_fseg(sizeof(*plun));
+ if (!plun) {
+ warn_noalloc();
+ return -1;
+ }
+ memset(plun, 0, sizeof(*plun));
+ plun->drive.type = DTYPE_PVSCSI;
+ plun->drive.cntl_id = pci->bdf;
+ plun->pci = pci;
+ plun->target = target;
+ plun->lun = lun;
+ plun->iobase = iobase;
+ plun->ring_dsc = ring_dsc;
+
+ char *name = znprintf(16, "pvscsi %02x:%02x.%x %d:%d",
+ pci_bdf_to_bus(pci->bdf), pci_bdf_to_dev(pci->bdf),
+ pci_bdf_to_fn(pci->bdf), target, lun);
+ int prio = bootprio_find_scsi_device(pci, target, lun);
+ int ret = scsi_drive_setup(&plun->drive, name, prio);
+ free(name);
+ if (ret)
+ goto fail;
+ return 0;
+
+fail:
+ free(plun);
+ return -1;
+}
+
+static void
+pvscsi_scan_target(struct pci_device *pci, u32 iobase,
+ struct pvscsi_ring_dsc_s *ring_dsc, u8 target)
+{
+ /* TODO: send REPORT LUNS. For now, only LUN 0 is recognized. */
+ pvscsi_add_lun(pci, iobase, ring_dsc, target, 0);
+}
+
+static void
+init_pvscsi(struct pci_device *pci)
+{
+ struct pvscsi_ring_dsc_s *ring_dsc = NULL;
+ int i;
+ u16 bdf = pci->bdf;
+ u32 iobase = pci_config_readl(pci->bdf, PCI_BASE_ADDRESS_0)
+ & PCI_BASE_ADDRESS_MEM_MASK;
+
+ pci_config_maskw(bdf, PCI_COMMAND, 0, PCI_COMMAND_MASTER);
+
+ dprintf(1, "found pvscsi at %02x:%02x.%x, io @ %x\n",
+ pci_bdf_to_bus(bdf), pci_bdf_to_dev(bdf),
+ pci_bdf_to_fn(bdf), iobase);
+
+ pvscsi_write_cmd_desc(iobase, PVSCSI_CMD_ADAPTER_RESET, NULL, 0);
+
+ pvscsi_init_rings(iobase, &ring_dsc);
+ for (i = 0; i < 7; i++)
+ pvscsi_scan_target(pci, iobase, ring_dsc, i);
+
+ return;
+
+}
+
+void
+pvscsi_setup(void)
+{
+ ASSERT32FLAT();
+ if (! CONFIG_PVSCSI)
+ return;
+
+ dprintf(3, "init pvscsi\n");
+
+ struct pci_device *pci;
+ foreachpci(pci) {
+ if (pci->vendor != PCI_VENDOR_ID_VMWARE
+ || pci->device != PCI_DEVICE_ID_VMWARE_PVSCSI)
+ continue;
+ init_pvscsi(pci);
+ }
+}
diff --git a/src/hw/pvscsi.h b/src/hw/pvscsi.h
new file mode 100644
index 0000000..fde9f0b
--- /dev/null
+++ b/src/hw/pvscsi.h
@@ -0,0 +1,8 @@
+#ifndef _PVSCSI_H_
+#define _PVSCSI_H_
+
+struct disk_op_s;
+int pvscsi_cmd_data(struct disk_op_s *op, void *cdbcmd, u16 blocksize);
+void pvscsi_setup(void);
+
+#endif /* _PVSCSI_H_ */
diff --git a/src/post.c b/src/post.c
index acd2362..b634686 100644
--- a/src/post.c
+++ b/src/post.c
@@ -15,6 +15,7 @@
#include "hw/esp-scsi.h" // esp_scsi_setup
#include "hw/lsi-scsi.h" // lsi_scsi_setup
#include "hw/megasas.h" // megasas_setup
+#include "hw/pvscsi.h" // pvscsi_setup
#include "hw/pic.h" // pic_setup
#include "hw/ps2port.h" // ps2port_setup
#include "hw/rtc.h" // rtc_write
@@ -147,6 +148,7 @@ device_hardware_setup(void)
lsi_scsi_setup();
esp_scsi_setup();
megasas_setup();
+ pvscsi_setup();
}
static void
--
1.7.9.5
More information about the SeaBIOS
mailing list