diff options
Diffstat (limited to 'hw')
130 files changed, 5352 insertions, 1129 deletions
diff --git a/hw/acpi.c b/hw/acpi.c index c7044b1fae..8071e7beba 100644 --- a/hw/acpi.c +++ b/hw/acpi.c @@ -50,6 +50,8 @@ int acpi_table_add(const char *t) char buf[1024], *p, *f; struct acpi_table_header acpi_hdr; unsigned long val; + uint32_t length; + struct acpi_table_header *acpi_hdr_p; size_t off; memset(&acpi_hdr, 0, sizeof(acpi_hdr)); @@ -108,7 +110,7 @@ int acpi_table_add(const char *t) buf[0] = '\0'; } - acpi_hdr.length = sizeof(acpi_hdr); + length = sizeof(acpi_hdr); f = buf; while (buf[0]) { @@ -120,7 +122,7 @@ int acpi_table_add(const char *t) fprintf(stderr, "Can't stat file '%s': %s\n", f, strerror(errno)); goto out; } - acpi_hdr.length += s.st_size; + length += s.st_size; if (!n) break; *n = ':'; @@ -131,12 +133,12 @@ int acpi_table_add(const char *t) acpi_tables_len = sizeof(uint16_t); acpi_tables = qemu_mallocz(acpi_tables_len); } + acpi_tables = qemu_realloc(acpi_tables, + acpi_tables_len + sizeof(uint16_t) + length); p = acpi_tables + acpi_tables_len; - acpi_tables_len += sizeof(uint16_t) + acpi_hdr.length; - acpi_tables = qemu_realloc(acpi_tables, acpi_tables_len); + acpi_tables_len += sizeof(uint16_t) + length; - acpi_hdr.length = cpu_to_le32(acpi_hdr.length); - *(uint16_t*)p = acpi_hdr.length; + *(uint16_t*)p = cpu_to_le32(length); p += sizeof(uint16_t); memcpy(p, &acpi_hdr, sizeof(acpi_hdr)); off = sizeof(acpi_hdr); @@ -157,7 +159,9 @@ int acpi_table_add(const char *t) goto out; } - do { + /* off < length is necessary because file size can be changed + under our foot */ + while(s.st_size && off < length) { int r; r = read(fd, p + off, s.st_size); if (r > 0) { @@ -167,15 +171,21 @@ int acpi_table_add(const char *t) close(fd); goto out; } - } while(s.st_size); + } close(fd); if (!n) break; f = n + 1; } + if (off < length) { + /* don't pass random value in process to guest */ + memset(p + off, 0, length - off); + } - ((struct acpi_table_header*)p)->checksum = acpi_checksum((uint8_t*)p, off); + acpi_hdr_p = (struct acpi_table_header*)p; + acpi_hdr_p->length = cpu_to_le32(length); + acpi_hdr_p->checksum = acpi_checksum((uint8_t*)p, length); /* increase number of tables */ (*(uint16_t*)acpi_tables) = cpu_to_le32(le32_to_cpu(*(uint16_t*)acpi_tables) + 1); diff --git a/hw/acpi_piix4.c b/hw/acpi_piix4.c index 24dfcf2039..66c7885d62 100644 --- a/hw/acpi_piix4.c +++ b/hw/acpi_piix4.c @@ -22,6 +22,7 @@ #include "pci.h" #include "acpi.h" #include "sysemu.h" +#include "range.h" //#define DEBUG @@ -37,6 +38,8 @@ #define PCI_BASE 0xae00 #define PCI_EJ_BASE 0xae08 +#define PIIX4_PCI_HOTPLUG_STATUS 2 + struct gpe_regs { uint16_t sts; /* status */ uint16_t en; /* enabled */ @@ -104,7 +107,9 @@ static void pm_update_sci(PIIX4PMState *s) (ACPI_BITMASK_RT_CLOCK_ENABLE | ACPI_BITMASK_POWER_BUTTON_ENABLE | ACPI_BITMASK_GLOBAL_LOCK_ENABLE | - ACPI_BITMASK_TIMER_ENABLE)) != 0); + ACPI_BITMASK_TIMER_ENABLE)) != 0) || + (((s->gpe.sts & s->gpe.en) & PIIX4_PCI_HOTPLUG_STATUS) != 0); + qemu_set_irq(s->irq, sci_level); /* schedule a timer interruption if needed */ if ((s->pmen & ACPI_BITMASK_TIMER_ENABLE) && @@ -459,7 +464,9 @@ static uint32_t gpe_read_val(uint16_t val, uint32_t addr) static uint32_t gpe_readb(void *opaque, uint32_t addr) { uint32_t val = 0; - struct gpe_regs *g = opaque; + PIIX4PMState *s = opaque; + struct gpe_regs *g = &s->gpe; + switch (addr) { case GPE_BASE: case GPE_BASE + 1: @@ -499,7 +506,9 @@ static void gpe_reset_val(uint16_t *cur, int addr, uint32_t val) static void gpe_writeb(void *opaque, uint32_t addr, uint32_t val) { - struct gpe_regs *g = opaque; + PIIX4PMState *s = opaque; + struct gpe_regs *g = &s->gpe; + switch (addr) { case GPE_BASE: case GPE_BASE + 1: @@ -511,7 +520,9 @@ static void gpe_writeb(void *opaque, uint32_t addr, uint32_t val) break; default: break; - } + } + + pm_update_sci(s); PIIX4_DPRINTF("gpe write %x <== %d\n", addr, val); } @@ -578,11 +589,10 @@ static int piix4_device_hotplug(DeviceState *qdev, PCIDevice *dev, int state); static void piix4_acpi_system_hot_add_init(PCIBus *bus, PIIX4PMState *s) { - struct gpe_regs *gpe = &s->gpe; struct pci_status *pci0_status = &s->pci0_status; - register_ioport_write(GPE_BASE, 4, 1, gpe_writeb, gpe); - register_ioport_read(GPE_BASE, 4, 1, gpe_readb, gpe); + register_ioport_write(GPE_BASE, 4, 1, gpe_writeb, s); + register_ioport_read(GPE_BASE, 4, 1, gpe_readb, s); register_ioport_write(PCI_BASE, 8, 4, pcihotplug_write, pci0_status); register_ioport_read(PCI_BASE, 8, 4, pcihotplug_read, pci0_status); @@ -595,13 +605,13 @@ static void piix4_acpi_system_hot_add_init(PCIBus *bus, PIIX4PMState *s) static void enable_device(PIIX4PMState *s, int slot) { - s->gpe.sts |= 2; + s->gpe.sts |= PIIX4_PCI_HOTPLUG_STATUS; s->pci0_status.up |= (1 << slot); } static void disable_device(PIIX4PMState *s, int slot) { - s->gpe.sts |= 2; + s->gpe.sts |= PIIX4_PCI_HOTPLUG_STATUS; s->pci0_status.down |= (1 << slot); } @@ -621,9 +631,8 @@ static int piix4_device_hotplug(DeviceState *qdev, PCIDevice *dev, int state) } else { disable_device(s, slot); } - if (s->gpe.en & 2) { - qemu_set_irq(s->irq, 1); - qemu_set_irq(s->irq, 0); - } + + pm_update_sci(s); + return 0; } diff --git a/hw/apic.c b/hw/apic.c index d686b510b0..63d62c7553 100644 --- a/hw/apic.c +++ b/hw/apic.c @@ -21,23 +21,7 @@ #include "qemu-timer.h" #include "host-utils.h" #include "sysbus.h" - -//#define DEBUG_APIC -//#define DEBUG_COALESCING - -#ifdef DEBUG_APIC -#define DPRINTF(fmt, ...) \ - do { printf("apic: " fmt , ## __VA_ARGS__); } while (0) -#else -#define DPRINTF(fmt, ...) -#endif - -#ifdef DEBUG_COALESCING -#define DPRINTF_C(fmt, ...) \ - do { printf("apic: " fmt , ## __VA_ARGS__); } while (0) -#else -#define DPRINTF_C(fmt, ...) -#endif +#include "trace.h" /* APIC Local Vector Table */ #define APIC_LVT_TIMER 0 @@ -168,8 +152,8 @@ static void apic_local_deliver(APICState *s, int vector) uint32_t lvt = s->lvt[vector]; int trigger_mode; - DPRINTF("%s: vector %d delivery mode %d\n", __func__, vector, - (lvt >> 8) & 7); + trace_apic_local_deliver(vector, (lvt >> 8) & 7); + if (lvt & APIC_LVT_MASKED) return; @@ -300,9 +284,9 @@ void apic_deliver_irq(uint8_t dest, uint8_t dest_mode, { uint32_t deliver_bitmask[MAX_APIC_WORDS]; - DPRINTF("%s: dest %d dest_mode %d delivery_mode %d vector %d" - " polarity %d trigger_mode %d\n", __func__, dest, dest_mode, - delivery_mode, vector_num, polarity, trigger_mode); + trace_apic_deliver_irq(dest, dest_mode, delivery_mode, vector_num, + polarity, trigger_mode); + apic_get_delivery_bitmask(deliver_bitmask, dest, dest_mode); apic_bus_deliver(deliver_bitmask, delivery_mode, vector_num, polarity, trigger_mode); @@ -312,7 +296,8 @@ void cpu_set_apic_base(DeviceState *d, uint64_t val) { APICState *s = DO_UPCAST(APICState, busdev.qdev, d); - DPRINTF("cpu_set_apic_base: %016" PRIx64 "\n", val); + trace_cpu_set_apic_base(val); + if (!s) return; s->apicbase = (val & 0xfffff000) | @@ -329,8 +314,8 @@ uint64_t cpu_get_apic_base(DeviceState *d) { APICState *s = DO_UPCAST(APICState, busdev.qdev, d); - DPRINTF("cpu_get_apic_base: %016" PRIx64 "\n", - s ? (uint64_t)s->apicbase: 0); + trace_cpu_get_apic_base(s ? (uint64_t)s->apicbase: 0); + return s ? s->apicbase : 0; } @@ -402,20 +387,23 @@ static void apic_update_irq(APICState *s) void apic_reset_irq_delivered(void) { - DPRINTF_C("%s: old coalescing %d\n", __func__, apic_irq_delivered); + trace_apic_reset_irq_delivered(apic_irq_delivered); + apic_irq_delivered = 0; } int apic_get_irq_delivered(void) { - DPRINTF_C("%s: returning coalescing %d\n", __func__, apic_irq_delivered); + trace_apic_get_irq_delivered(apic_irq_delivered); + return apic_irq_delivered; } static void apic_set_irq(APICState *s, int vector_num, int trigger_mode) { apic_irq_delivered += !get_bit(s->irr, vector_num); - DPRINTF_C("%s: coalescing %d\n", __func__, apic_irq_delivered); + + trace_apic_set_irq(apic_irq_delivered); set_bit(s->irr, vector_num); if (trigger_mode) @@ -769,7 +757,7 @@ static uint32_t apic_mem_readl(void *opaque, target_phys_addr_t addr) val = 0; break; } - DPRINTF("read: " TARGET_FMT_plx " = %08x\n", addr, val); + trace_apic_mem_readl(addr, val); return val; } @@ -805,7 +793,7 @@ static void apic_mem_writel(void *opaque, target_phys_addr_t addr, uint32_t val) } s = DO_UPCAST(APICState, busdev.qdev, d); - DPRINTF("write: " TARGET_FMT_plx " = %08x\n", addr, val); + trace_apic_mem_writel(addr, val); switch(index) { case 0x02: diff --git a/hw/bonito.c b/hw/bonito.c index 8b810321ad..dcf031134e 100644 --- a/hw/bonito.c +++ b/hw/bonito.c @@ -775,7 +775,6 @@ PCIBus *bonito_init(qemu_irq *pic) pci_bonito_map_irq, pic, 0x28, 32); pcihost->bus = b; qdev_init_nofail(dev); - pci_bus_set_mem_base(pcihost->bus, 0x10000000); d = pci_create_simple(b, PCI_DEVFN(0, 0), "Bonito"); s = DO_UPCAST(PCIBonitoState, dev, d); diff --git a/hw/cirrus_vga.c b/hw/cirrus_vga.c index bbd4b082d2..aadc56f692 100644 --- a/hw/cirrus_vga.c +++ b/hw/cirrus_vga.c @@ -280,63 +280,63 @@ static void cirrus_bitblt_fill_nop(CirrusVGAState *s, } #define ROP_NAME 0 -#define ROP_OP(d, s) d = 0 +#define ROP_FN(d, s) 0 #include "cirrus_vga_rop.h" #define ROP_NAME src_and_dst -#define ROP_OP(d, s) d = (s) & (d) +#define ROP_FN(d, s) (s) & (d) #include "cirrus_vga_rop.h" #define ROP_NAME src_and_notdst -#define ROP_OP(d, s) d = (s) & (~(d)) +#define ROP_FN(d, s) (s) & (~(d)) #include "cirrus_vga_rop.h" #define ROP_NAME notdst -#define ROP_OP(d, s) d = ~(d) +#define ROP_FN(d, s) ~(d) #include "cirrus_vga_rop.h" #define ROP_NAME src -#define ROP_OP(d, s) d = s +#define ROP_FN(d, s) s #include "cirrus_vga_rop.h" #define ROP_NAME 1 -#define ROP_OP(d, s) d = ~0 +#define ROP_FN(d, s) ~0 #include "cirrus_vga_rop.h" #define ROP_NAME notsrc_and_dst -#define ROP_OP(d, s) d = (~(s)) & (d) +#define ROP_FN(d, s) (~(s)) & (d) #include "cirrus_vga_rop.h" #define ROP_NAME src_xor_dst -#define ROP_OP(d, s) d = (s) ^ (d) +#define ROP_FN(d, s) (s) ^ (d) #include "cirrus_vga_rop.h" #define ROP_NAME src_or_dst -#define ROP_OP(d, s) d = (s) | (d) +#define ROP_FN(d, s) (s) | (d) #include "cirrus_vga_rop.h" #define ROP_NAME notsrc_or_notdst -#define ROP_OP(d, s) d = (~(s)) | (~(d)) +#define ROP_FN(d, s) (~(s)) | (~(d)) #include "cirrus_vga_rop.h" #define ROP_NAME src_notxor_dst -#define ROP_OP(d, s) d = ~((s) ^ (d)) +#define ROP_FN(d, s) ~((s) ^ (d)) #include "cirrus_vga_rop.h" #define ROP_NAME src_or_notdst -#define ROP_OP(d, s) d = (s) | (~(d)) +#define ROP_FN(d, s) (s) | (~(d)) #include "cirrus_vga_rop.h" #define ROP_NAME notsrc -#define ROP_OP(d, s) d = (~(s)) +#define ROP_FN(d, s) (~(s)) #include "cirrus_vga_rop.h" #define ROP_NAME notsrc_or_dst -#define ROP_OP(d, s) d = (~(s)) | (d) +#define ROP_FN(d, s) (~(s)) | (d) #include "cirrus_vga_rop.h" #define ROP_NAME notsrc_and_notdst -#define ROP_OP(d, s) d = (~(s)) & (~(d)) +#define ROP_FN(d, s) (~(s)) & (~(d)) #include "cirrus_vga_rop.h" static const cirrus_bitblt_rop_t cirrus_fwd_rop[16] = { diff --git a/hw/cirrus_vga_rop.h b/hw/cirrus_vga_rop.h index 39a7b7285b..9c7bb09286 100644 --- a/hw/cirrus_vga_rop.h +++ b/hw/cirrus_vga_rop.h @@ -22,6 +22,26 @@ * THE SOFTWARE. */ +static inline void glue(rop_8_,ROP_NAME)(uint8_t *dst, uint8_t src) +{ + *dst = ROP_FN(*dst, src); +} + +static inline void glue(rop_16_,ROP_NAME)(uint16_t *dst, uint16_t src) +{ + *dst = ROP_FN(*dst, src); +} + +static inline void glue(rop_32_,ROP_NAME)(uint32_t *dst, uint32_t src) +{ + *dst = ROP_FN(*dst, src); +} + +#define ROP_OP(d, s) glue(rop_8_,ROP_NAME)(d, s) +#define ROP_OP_16(d, s) glue(rop_16_,ROP_NAME)(d, s) +#define ROP_OP_32(d, s) glue(rop_32_,ROP_NAME)(d, s) +#undef ROP_FN + static void glue(cirrus_bitblt_rop_fwd_, ROP_NAME)(CirrusVGAState *s, uint8_t *dst,const uint8_t *src, @@ -39,7 +59,7 @@ glue(cirrus_bitblt_rop_fwd_, ROP_NAME)(CirrusVGAState *s, for (y = 0; y < bltheight; y++) { for (x = 0; x < bltwidth; x++) { - ROP_OP(*dst, *src); + ROP_OP(dst, *src); dst++; src++; } @@ -59,7 +79,7 @@ glue(cirrus_bitblt_rop_bkwd_, ROP_NAME)(CirrusVGAState *s, srcpitch += bltwidth; for (y = 0; y < bltheight; y++) { for (x = 0; x < bltwidth; x++) { - ROP_OP(*dst, *src); + ROP_OP(dst, *src); dst--; src--; } @@ -81,7 +101,7 @@ glue(glue(cirrus_bitblt_rop_fwd_transp_, ROP_NAME),_8)(CirrusVGAState *s, for (y = 0; y < bltheight; y++) { for (x = 0; x < bltwidth; x++) { p = *dst; - ROP_OP(p, *src); + ROP_OP(&p, *src); if (p != s->vga.gr[0x34]) *dst = p; dst++; src++; @@ -104,7 +124,7 @@ glue(glue(cirrus_bitblt_rop_bkwd_transp_, ROP_NAME),_8)(CirrusVGAState *s, for (y = 0; y < bltheight; y++) { for (x = 0; x < bltwidth; x++) { p = *dst; - ROP_OP(p, *src); + ROP_OP(&p, *src); if (p != s->vga.gr[0x34]) *dst = p; dst--; src--; @@ -128,8 +148,8 @@ glue(glue(cirrus_bitblt_rop_fwd_transp_, ROP_NAME),_16)(CirrusVGAState *s, for (x = 0; x < bltwidth; x+=2) { p1 = *dst; p2 = *(dst+1); - ROP_OP(p1, *src); - ROP_OP(p2, *(src+1)); + ROP_OP(&p1, *src); + ROP_OP(&p2, *(src + 1)); if ((p1 != s->vga.gr[0x34]) || (p2 != s->vga.gr[0x35])) { *dst = p1; *(dst+1) = p2; @@ -156,8 +176,8 @@ glue(glue(cirrus_bitblt_rop_bkwd_transp_, ROP_NAME),_16)(CirrusVGAState *s, for (x = 0; x < bltwidth; x+=2) { p1 = *(dst-1); p2 = *dst; - ROP_OP(p1, *(src-1)); - ROP_OP(p2, *src); + ROP_OP(&p1, *(src - 1)); + ROP_OP(&p2, *src); if ((p1 != s->vga.gr[0x34]) || (p2 != s->vga.gr[0x35])) { *(dst-1) = p1; *dst = p2; @@ -184,3 +204,5 @@ glue(glue(cirrus_bitblt_rop_bkwd_transp_, ROP_NAME),_16)(CirrusVGAState *s, #undef ROP_NAME #undef ROP_OP +#undef ROP_OP_16 +#undef ROP_OP_32 diff --git a/hw/cirrus_vga_rop2.h b/hw/cirrus_vga_rop2.h index 81a5b398e0..d28bcc6f25 100644 --- a/hw/cirrus_vga_rop2.h +++ b/hw/cirrus_vga_rop2.h @@ -23,15 +23,15 @@ */ #if DEPTH == 8 -#define PUTPIXEL() ROP_OP(d[0], col) +#define PUTPIXEL() ROP_OP(&d[0], col) #elif DEPTH == 16 -#define PUTPIXEL() ROP_OP(((uint16_t *)d)[0], col); +#define PUTPIXEL() ROP_OP_16((uint16_t *)&d[0], col) #elif DEPTH == 24 -#define PUTPIXEL() ROP_OP(d[0], col); \ - ROP_OP(d[1], (col >> 8)); \ - ROP_OP(d[2], (col >> 16)) +#define PUTPIXEL() ROP_OP(&d[0], col); \ + ROP_OP(&d[1], (col >> 8)); \ + ROP_OP(&d[2], (col >> 16)) #elif DEPTH == 32 -#define PUTPIXEL() ROP_OP(((uint32_t *)d)[0], col) +#define PUTPIXEL() ROP_OP_32(((uint32_t *)&d[0]), col) #else #error unsupported DEPTH #endif diff --git a/hw/device-hotplug.c b/hw/device-hotplug.c index c1a9a561d7..9704e2feb2 100644 --- a/hw/device-hotplug.c +++ b/hw/device-hotplug.c @@ -25,6 +25,7 @@ #include "hw.h" #include "boards.h" #include "net.h" +#include "blockdev.h" DriveInfo *add_init_drive(const char *optstr) { diff --git a/hw/e1000.c b/hw/e1000.c index 8d87492e0b..532efdc27d 100644 --- a/hw/e1000.c +++ b/hw/e1000.c @@ -55,6 +55,7 @@ static int debugflags = DBGBIT(TXERR) | DBGBIT(GENERAL); #define IOPORT_SIZE 0x40 #define PNPMMIO_SIZE 0x20000 +#define MIN_BUF_SIZE 60 /* Min. octets in an ethernet frame sans FCS */ /* * HW models: @@ -262,21 +263,20 @@ set_eecd(E1000State *s, int index, uint32_t val) s->eecd_state.old_eecd = val & (E1000_EECD_SK | E1000_EECD_CS | E1000_EECD_DI|E1000_EECD_FWE_MASK|E1000_EECD_REQ); + if (!(E1000_EECD_CS & val)) // CS inactive; nothing to do + return; + if (E1000_EECD_CS & (val ^ oldval)) { // CS rise edge; reset state + s->eecd_state.val_in = 0; + s->eecd_state.bitnum_in = 0; + s->eecd_state.bitnum_out = 0; + s->eecd_state.reading = 0; + } if (!(E1000_EECD_SK & (val ^ oldval))) // no clock edge return; if (!(E1000_EECD_SK & val)) { // falling edge s->eecd_state.bitnum_out++; return; } - if (!(val & E1000_EECD_CS)) { // rising, no CS (EEPROM reset) - memset(&s->eecd_state, 0, sizeof s->eecd_state); - /* - * restore old_eecd's E1000_EECD_SK (known to be on) - * to avoid false detection of a clock edge - */ - s->eecd_state.old_eecd = E1000_EECD_SK; - return; - } s->eecd_state.val_in <<= 1; if (val & E1000_EECD_DI) s->eecd_state.val_in |= 1; @@ -346,7 +346,7 @@ is_vlan_txd(uint32_t txd_lower) /* FCS aka Ethernet CRC-32. We don't get it from backends and can't * fill it in, just pad descriptor length by 4 bytes unless guest - * told us to trip it off the packet. */ + * told us to strip it off the packet. */ static inline int fcs_len(E1000State *s) { @@ -636,10 +636,19 @@ e1000_receive(VLANClientState *nc, const uint8_t *buf, size_t size) uint32_t rdh_start; uint16_t vlan_special = 0; uint8_t vlan_status = 0, vlan_offset = 0; + uint8_t min_buf[MIN_BUF_SIZE]; if (!(s->mac_reg[RCTL] & E1000_RCTL_EN)) return -1; + /* Pad to minimum Ethernet frame length */ + if (size < sizeof(min_buf)) { + memcpy(min_buf, buf, size); + memset(&min_buf[size], 0, sizeof(min_buf) - size); + buf = min_buf; + size = sizeof(min_buf); + } + if (size > s->rxbuf_size) { DBGOUT(RX, "packet too large for buffers (%lu > %d)\n", (unsigned long)size, s->rxbuf_size); @@ -691,9 +700,14 @@ e1000_receive(VLANClientState *nc, const uint8_t *buf, size_t size) s->mac_reg[GPRC]++; s->mac_reg[TPR]++; - n = s->mac_reg[TORL]; - if ((s->mac_reg[TORL] += size) < n) + /* TOR - Total Octets Received: + * This register includes bytes received in a packet from the <Destination + * Address> field through the <CRC> field, inclusively. + */ + n = s->mac_reg[TORL] + size + /* Always include FCS length. */ 4; + if (n < s->mac_reg[TORL]) s->mac_reg[TORH]++; + s->mac_reg[TORL] = n; n = E1000_ICS_RXT0; if ((rdt = s->mac_reg[RDT]) < s->mac_reg[RDH]) diff --git a/hw/eepro100.c b/hw/eepro100.c index 8cbc3aa7a2..41d792ad24 100644 --- a/hw/eepro100.c +++ b/hw/eepro100.c @@ -219,7 +219,8 @@ typedef enum { typedef struct { PCIDevice dev; - uint8_t mult[8]; /* multicast mask array */ + /* Hash register (multicast mask array, multiple individual addresses). */ + uint8_t mult[8]; int mmio_index; NICState *nic; NICConf conf; @@ -599,7 +600,7 @@ static void nic_reset(void *opaque) { EEPRO100State *s = opaque; TRACE(OTHER, logout("%p\n", s)); - /* TODO: Clearing of multicast table for selective reset, too? */ + /* TODO: Clearing of hash register for selective reset, too? */ memset(&s->mult[0], 0, sizeof(s->mult)); nic_selective_reset(s); } @@ -851,7 +852,14 @@ static void action_command(EEPRO100State *s) case CmdConfigure: cpu_physical_memory_read(s->cb_address + 8, &s->configuration[0], sizeof(s->configuration)); - TRACE(OTHER, logout("configuration: %s\n", nic_dump(&s->configuration[0], 16))); + TRACE(OTHER, logout("configuration: %s\n", + nic_dump(&s->configuration[0], 16))); + TRACE(OTHER, logout("configuration: %s\n", + nic_dump(&s->configuration[16], + ARRAY_SIZE(s->configuration) - 16))); + if (s->configuration[20] & BIT(6)) { + TRACE(OTHER, logout("Multiple IA bit\n")); + } break; case CmdMulticastList: set_multicast_list(s); @@ -1282,7 +1290,7 @@ static void eepro100_write_port(EEPRO100State * s, uint32_t val) static uint8_t eepro100_read1(EEPRO100State * s, uint32_t addr) { - uint8_t val; + uint8_t val = 0; if (addr <= sizeof(s->mem) - sizeof(val)) { memcpy(&val, &s->mem[addr], sizeof(val)); } @@ -1325,7 +1333,7 @@ static uint8_t eepro100_read1(EEPRO100State * s, uint32_t addr) static uint16_t eepro100_read2(EEPRO100State * s, uint32_t addr) { - uint16_t val; + uint16_t val = 0; if (addr <= sizeof(s->mem) - sizeof(val)) { memcpy(&val, &s->mem[addr], sizeof(val)); } @@ -1348,7 +1356,7 @@ static uint16_t eepro100_read2(EEPRO100State * s, uint32_t addr) static uint32_t eepro100_read4(EEPRO100State * s, uint32_t addr) { - uint32_t val; + uint32_t val = 0; if (addr <= sizeof(s->mem) - sizeof(val)) { memcpy(&val, &s->mem[addr], sizeof(val)); } @@ -1647,12 +1655,6 @@ static ssize_t nic_receive(VLANClientState *nc, const uint8_t * buf, size_t size static const uint8_t broadcast_macaddr[6] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; - /* TODO: check multiple IA bit. */ - if (s->configuration[20] & BIT(6)) { - missing("Multiple IA bit"); - return -1; - } - if (s->configuration[8] & 0x80) { /* CSMA is disabled. */ logout("%p received while CSMA is disabled\n", s); @@ -1702,6 +1704,16 @@ static ssize_t nic_receive(VLANClientState *nc, const uint8_t * buf, size_t size /* Promiscuous: receive all. */ TRACE(RXTX, logout("%p received frame in promiscuous mode, len=%zu\n", s, size)); rfd_status |= 0x0004; + } else if (s->configuration[20] & BIT(6)) { + /* Multiple IA bit set. */ + unsigned mcast_idx = compute_mcast_idx(buf); + assert(mcast_idx < 64); + if (s->mult[mcast_idx >> 3] & (1 << (mcast_idx & 7))) { + TRACE(RXTX, logout("%p accepted, multiple IA bit set\n", s)); + } else { + TRACE(RXTX, logout("%p frame ignored, multiple IA bit set\n", s)); + return -1; + } } else { TRACE(RXTX, logout("%p received frame, ignored, len=%zu,%s\n", s, size, nic_dump(buf, size))); diff --git a/hw/elf_ops.h b/hw/elf_ops.h index 27d1ab9bc2..0bd72350b4 100644 --- a/hw/elf_ops.h +++ b/hw/elf_ops.h @@ -153,6 +153,11 @@ static int glue(load_symbols, SZ)(struct elfhdr *ehdr, int fd, int must_swab, syms = qemu_realloc(syms, nsyms * sizeof(*syms)); qsort(syms, nsyms, sizeof(*syms), glue(symcmp, SZ)); + for (i = 0; i < nsyms - 1; i++) { + if (syms[i].st_size == 0) { + syms[i].st_size = syms[i + 1].st_value - syms[i].st_value; + } + } } else { qemu_free(syms); syms = NULL; diff --git a/hw/escc.c b/hw/escc.c index 6d2fd36b11..8714239780 100644 --- a/hw/escc.c +++ b/hw/escc.c @@ -65,6 +65,8 @@ * 2006-Aug-10 Igor Kovalenko : Renamed KBDQueue to SERIOQueue, implemented * serial mouse queue. * Implemented serial mouse protocol. + * + * 2010-May-23 Artyom Tarasenko: Reworked IUS logic */ #ifdef DEBUG_SERIAL @@ -279,7 +281,7 @@ static uint32_t get_queue(void *opaque) static int escc_update_irq_chn(ChannelState *s) { - if ((((s->wregs[W_INTR] & INTR_TXINT) && s->txint == 1) || + if ((((s->wregs[W_INTR] & INTR_TXINT) && (s->txint == 1)) || // tx ints enabled, pending ((((s->wregs[W_INTR] & INTR_RXMODEMSK) == INTR_RXINT1ST) || ((s->wregs[W_INTR] & INTR_RXMODEMSK) == INTR_RXINTALL)) && @@ -342,24 +344,22 @@ static void escc_reset(DeviceState *d) static inline void set_rxint(ChannelState *s) { s->rxint = 1; - if (!s->txint_under_svc) { - s->rxint_under_svc = 1; - if (s->chn == chn_a) { - if (s->wregs[W_MINTR] & MINTR_STATUSHI) - s->otherchn->rregs[R_IVEC] = IVEC_HIRXINTA; - else - s->otherchn->rregs[R_IVEC] = IVEC_LORXINTA; - } else { - if (s->wregs[W_MINTR] & MINTR_STATUSHI) - s->rregs[R_IVEC] = IVEC_HIRXINTB; - else - s->rregs[R_IVEC] = IVEC_LORXINTB; - } - } - if (s->chn == chn_a) + /* XXX: missing daisy chainnig: chn_b rx should have a lower priority + than chn_a rx/tx/special_condition service*/ + s->rxint_under_svc = 1; + if (s->chn == chn_a) { s->rregs[R_INTR] |= INTR_RXINTA; - else + if (s->wregs[W_MINTR] & MINTR_STATUSHI) + s->otherchn->rregs[R_IVEC] = IVEC_HIRXINTA; + else + s->otherchn->rregs[R_IVEC] = IVEC_LORXINTA; + } else { s->otherchn->rregs[R_INTR] |= INTR_RXINTB; + if (s->wregs[W_MINTR] & MINTR_STATUSHI) + s->rregs[R_IVEC] = IVEC_HIRXINTB; + else + s->rregs[R_IVEC] = IVEC_LORXINTB; + } escc_update_irq(s); } @@ -369,19 +369,17 @@ static inline void set_txint(ChannelState *s) if (!s->rxint_under_svc) { s->txint_under_svc = 1; if (s->chn == chn_a) { + s->rregs[R_INTR] |= INTR_TXINTA; if (s->wregs[W_MINTR] & MINTR_STATUSHI) s->otherchn->rregs[R_IVEC] = IVEC_HITXINTA; else s->otherchn->rregs[R_IVEC] = IVEC_LOTXINTA; } else { s->rregs[R_IVEC] = IVEC_TXINTB; + s->otherchn->rregs[R_INTR] |= INTR_TXINTB; } - } - if (s->chn == chn_a) - s->rregs[R_INTR] |= INTR_TXINTA; - else - s->otherchn->rregs[R_INTR] |= INTR_TXINTB; escc_update_irq(s); + } } static inline void clr_rxint(ChannelState *s) @@ -417,6 +415,7 @@ static inline void clr_txint(ChannelState *s) s->otherchn->rregs[R_IVEC] = IVEC_LONOINT; s->rregs[R_INTR] &= ~INTR_TXINTA; } else { + s->otherchn->rregs[R_INTR] &= ~INTR_TXINTB; if (s->wregs[W_MINTR] & MINTR_STATUSHI) s->rregs[R_IVEC] = IVEC_HINOINT; else @@ -515,10 +514,15 @@ static void escc_mem_writeb(void *opaque, target_phys_addr_t addr, uint32_t val) clr_txint(s); break; case CMD_CLR_IUS: - if (s->rxint_under_svc) - clr_rxint(s); - else if (s->txint_under_svc) - clr_txint(s); + if (s->rxint_under_svc) { + s->rxint_under_svc = 0; + if (s->txint) { + set_txint(s); + } + } else if (s->txint_under_svc) { + s->txint_under_svc = 0; + } + escc_update_irq(s); break; default: break; diff --git a/hw/esp.c b/hw/esp.c index 349052a024..910fd31665 100644 --- a/hw/esp.c +++ b/hw/esp.c @@ -80,6 +80,8 @@ struct ESPState { ESPDMAMemoryReadWriteFunc dma_memory_read; ESPDMAMemoryReadWriteFunc dma_memory_write; void *dma_opaque; + int dma_enabled; + void (*dma_cb)(ESPState *s); }; #define ESP_TCLO 0x0 @@ -167,6 +169,24 @@ static void esp_lower_irq(ESPState *s) } } +static void esp_dma_enable(void *opaque, int irq, int level) +{ + DeviceState *d = opaque; + ESPState *s = container_of(d, ESPState, busdev.qdev); + + if (level) { + s->dma_enabled = 1; + DPRINTF("Raise enable\n"); + if (s->dma_cb) { + s->dma_cb(s); + s->dma_cb = NULL; + } + } else { + DPRINTF("Lower enable\n"); + s->dma_enabled = 0; + } +} + static uint32_t get_cmd(ESPState *s, uint8_t *buf) { uint32_t dmalen; @@ -243,6 +263,10 @@ static void handle_satn(ESPState *s) uint8_t buf[32]; int len; + if (!s->dma_enabled) { + s->dma_cb = handle_satn; + return; + } len = get_cmd(s, buf); if (len) do_cmd(s, buf); @@ -253,6 +277,10 @@ static void handle_s_without_atn(ESPState *s) uint8_t buf[32]; int len; + if (!s->dma_enabled) { + s->dma_cb = handle_s_without_atn; + return; + } len = get_cmd(s, buf); if (len) { do_busid_cmd(s, buf, 0); @@ -261,6 +289,10 @@ static void handle_s_without_atn(ESPState *s) static void handle_satn_stop(ESPState *s) { + if (!s->dma_enabled) { + s->dma_cb = handle_satn_stop; + return; + } s->cmdlen = get_cmd(s, s->cmdbuf); if (s->cmdlen) { DPRINTF("Set ATN & Stop: cmdlen %d\n", s->cmdlen); @@ -431,6 +463,7 @@ static void esp_hard_reset(DeviceState *d) s->ti_wptr = 0; s->dma = 0; s->do_cmd = 0; + s->dma_cb = NULL; s->rregs[ESP_CFG1] = 7; } @@ -450,6 +483,18 @@ static void parent_esp_reset(void *opaque, int irq, int level) } } +static void esp_gpio_demux(void *opaque, int irq, int level) +{ + switch (irq) { + case 0: + parent_esp_reset(opaque, irq, level); + break; + case 1: + esp_dma_enable(opaque, irq, level); + break; + } +} + static uint32_t esp_mem_readb(void *opaque, target_phys_addr_t addr) { ESPState *s = opaque; @@ -646,7 +691,8 @@ static const VMStateDescription vmstate_esp = { void esp_init(target_phys_addr_t espaddr, int it_shift, ESPDMAMemoryReadWriteFunc dma_memory_read, ESPDMAMemoryReadWriteFunc dma_memory_write, - void *dma_opaque, qemu_irq irq, qemu_irq *reset) + void *dma_opaque, qemu_irq irq, qemu_irq *reset, + qemu_irq *dma_enable) { DeviceState *dev; SysBusDevice *s; @@ -658,11 +704,14 @@ void esp_init(target_phys_addr_t espaddr, int it_shift, esp->dma_memory_write = dma_memory_write; esp->dma_opaque = dma_opaque; esp->it_shift = it_shift; + /* XXX for now until rc4030 has been changed to use DMA enable signal */ + esp->dma_enabled = 1; qdev_init_nofail(dev); s = sysbus_from_qdev(dev); sysbus_connect_irq(s, 0, irq); sysbus_mmio_map(s, 0, espaddr); *reset = qdev_get_gpio_in(dev, 0); + *dma_enable = qdev_get_gpio_in(dev, 1); } static int esp_init1(SysBusDevice *dev) @@ -676,7 +725,7 @@ static int esp_init1(SysBusDevice *dev) esp_io_memory = cpu_register_io_memory(esp_mem_read, esp_mem_write, s); sysbus_init_mmio(dev, ESP_REGS << s->it_shift, esp_io_memory); - qdev_init_gpio_in(&dev->qdev, parent_esp_reset, 1); + qdev_init_gpio_in(&dev->qdev, esp_gpio_demux, 2); scsi_bus_new(&s->bus, &dev->qdev, 0, ESP_MAX_DEVS, esp_command_complete); return scsi_bus_legacy_handle_cmdline(&s->bus); diff --git a/hw/esp.h b/hw/esp.h index 605f953754..62bfd4d129 100644 --- a/hw/esp.h +++ b/hw/esp.h @@ -7,6 +7,7 @@ typedef void (*ESPDMAMemoryReadWriteFunc)(void *opaque, uint8_t *buf, int len); void esp_init(target_phys_addr_t espaddr, int it_shift, ESPDMAMemoryReadWriteFunc dma_memory_read, ESPDMAMemoryReadWriteFunc dma_memory_write, - void *dma_opaque, qemu_irq irq, qemu_irq *reset); + void *dma_opaque, qemu_irq irq, qemu_irq *reset, + qemu_irq *dma_enable); #endif diff --git a/hw/etraxfs.c b/hw/etraxfs.c index 46e2920c23..5ee5f979aa 100644 --- a/hw/etraxfs.c +++ b/hw/etraxfs.c @@ -31,6 +31,7 @@ #include "loader.h" #include "elf.h" #include "cris-boot.h" +#include "blockdev.h" #define FLASH_SIZE 0x2000000 #define INTMEM_SIZE (128 * 1024) diff --git a/hw/etraxfs_eth.c b/hw/etraxfs_eth.c index 187ece19ea..ade96f14ac 100644 --- a/hw/etraxfs_eth.c +++ b/hw/etraxfs_eth.c @@ -437,6 +437,7 @@ eth_writel (void *opaque, target_phys_addr_t addr, uint32_t value) eth_validate_duplex(eth); } eth->mdio_bus.mdc = !!(value & 4); + eth->regs[addr] = value; break; case RW_REC_CTRL: @@ -463,7 +464,7 @@ static int eth_match_groupaddr(struct fs_eth *eth, const unsigned char *sa) /* First bit on the wire of a MAC address signals multicast or physical address. */ - if (!m_individual && !sa[0] & 1) + if (!m_individual && !(sa[0] & 1)) return 0; /* Calculate the hash index for the GA registers. */ diff --git a/hw/fdc.c b/hw/fdc.c index 2d50bd6a39..c159dcb630 100644 --- a/hw/fdc.c +++ b/hw/fdc.c @@ -34,6 +34,7 @@ #include "isa.h" #include "sysbus.h" #include "qdev-addr.h" +#include "blockdev.h" /********************************************************/ /* debug Floppy devices */ diff --git a/hw/fdc.h b/hw/fdc.h index b6b3772592..242730af8c 100644 --- a/hw/fdc.h +++ b/hw/fdc.h @@ -2,7 +2,6 @@ #define HW_FDC_H /* fdc.c */ -#include "blockdev.h" #define MAX_FD 2 typedef struct FDCtrl FDCtrl; diff --git a/hw/file-op-9p.h b/hw/file-op-9p.h index a741c93527..21d60b5855 100644 --- a/hw/file-op-9p.h +++ b/hw/file-op-9p.h @@ -24,8 +24,19 @@ typedef enum { - SM_PASSTHROUGH = 1, /* uid/gid set on fileserver files */ - SM_MAPPED, /* uid/gid part of xattr */ + /* + * Server will try to set uid/gid. + * On failure ignore the error. + */ + SM_NONE = 0, + /* + * uid/gid set on fileserver files + */ + SM_PASSTHROUGH = 1, + /* + * uid/gid part of xattr + */ + SM_MAPPED, } SecModel; typedef struct FsCred @@ -36,11 +47,14 @@ typedef struct FsCred dev_t fc_rdev; } FsCred; +struct xattr_operations; + typedef struct FsContext { char *fs_root; SecModel fs_sm; uid_t uid; + struct xattr_operations **xops; } FsContext; extern void cred_init(FsCred *); @@ -52,7 +66,7 @@ typedef struct FileOperations int (*chmod)(FsContext *, const char *, FsCred *); int (*chown)(FsContext *, const char *, FsCred *); int (*mknod)(FsContext *, const char *, FsCred *); - int (*utime)(FsContext *, const char *, const struct utimbuf *); + int (*utimensat)(FsContext *, const char *, const struct timespec *); int (*remove)(FsContext *, const char *); int (*symlink)(FsContext *, const char *, const char *, FsCred *); int (*link)(FsContext *, const char *, const char *); @@ -66,14 +80,28 @@ typedef struct FileOperations off_t (*telldir)(FsContext *, DIR *); struct dirent *(*readdir)(FsContext *, DIR *); void (*seekdir)(FsContext *, DIR *, off_t); - ssize_t (*readv)(FsContext *, int, const struct iovec *, int); - ssize_t (*writev)(FsContext *, int, const struct iovec *, int); - off_t (*lseek)(FsContext *, int, off_t, int); + ssize_t (*preadv)(FsContext *, int, const struct iovec *, int, off_t); + ssize_t (*pwritev)(FsContext *, int, const struct iovec *, int, off_t); int (*mkdir)(FsContext *, const char *, FsCred *); int (*fstat)(FsContext *, int, struct stat *); int (*rename)(FsContext *, const char *, const char *); int (*truncate)(FsContext *, const char *, off_t); int (*fsync)(FsContext *, int); + int (*statfs)(FsContext *s, const char *path, struct statfs *stbuf); + ssize_t (*lgetxattr)(FsContext *, const char *, + const char *, void *, size_t); + ssize_t (*llistxattr)(FsContext *, const char *, void *, size_t); + int (*lsetxattr)(FsContext *, const char *, + const char *, void *, size_t, int); + int (*lremovexattr)(FsContext *, const char *, const char *); void *opaque; } FileOperations; + +static inline const char *rpath(FsContext *ctx, const char *path) +{ + /* FIXME: so wrong... */ + static char buffer[4096]; + snprintf(buffer, sizeof(buffer), "%s/%s", ctx->fs_root, path); + return buffer; +} #endif diff --git a/hw/fmopl.c b/hw/fmopl.c index d1161f848f..3df1806a91 100644 --- a/hw/fmopl.c +++ b/hw/fmopl.c @@ -1342,8 +1342,9 @@ unsigned char OPLRead(FM_OPL *OPL,int a) { if(OPL->keyboardhandler_r) return OPL->keyboardhandler_r(OPL->keyboard_param); - else + else { LOG(LOG_WAR,("OPL:read unmapped KEYBOARD port\n")); + } } return 0; #if 0 @@ -1355,8 +1356,9 @@ unsigned char OPLRead(FM_OPL *OPL,int a) { if(OPL->porthandler_r) return OPL->porthandler_r(OPL->port_param); - else + else { LOG(LOG_WAR,("OPL:read unmapped I/O port\n")); + } } return 0; case 0x1a: /* PCM-DATA */ diff --git a/hw/gumstix.c b/hw/gumstix.c index c343a166e8..af8b464b88 100644 --- a/hw/gumstix.c +++ b/hw/gumstix.c @@ -38,6 +38,7 @@ #include "sysemu.h" #include "devices.h" #include "boards.h" +#include "blockdev.h" static const int sector_len = 128 * 1024; diff --git a/hw/hw.h b/hw/hw.h index c2de6fe8c4..4405092b54 100644 --- a/hw/hw.h +++ b/hw/hw.h @@ -264,6 +264,8 @@ int register_savevm_live(DeviceState *dev, void *opaque); void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque); +void register_device_unmigratable(DeviceState *dev, const char *idstr, + void *opaque); typedef void QEMUResetHandler(void *opaque); @@ -313,6 +315,11 @@ typedef struct { bool (*field_exists)(void *opaque, int version_id); } VMStateField; +typedef struct VMStateSubsection { + const VMStateDescription *vmsd; + bool (*needed)(void *opaque); +} VMStateSubsection; + struct VMStateDescription { const char *name; int version_id; @@ -323,6 +330,7 @@ struct VMStateDescription { int (*post_load)(void *opaque, int version_id); void (*pre_save)(void *opaque); VMStateField *fields; + const VMStateSubsection *subsections; }; extern const VMStateInfo vmstate_info_int8; diff --git a/hw/ide/core.c b/hw/ide/core.c index af52c2cb2d..06b6e14e56 100644 --- a/hw/ide/core.c +++ b/hw/ide/core.c @@ -30,6 +30,7 @@ #include "qemu-timer.h" #include "sysemu.h" #include "dma.h" +#include "blockdev.h" #include <hw/ide/internal.h> @@ -138,6 +139,7 @@ static void ide_identify(IDEState *s) put_le16(p + 61, s->nb_sectors >> 16); put_le16(p + 62, 0x07); /* single word dma0-2 supported */ put_le16(p + 63, 0x07); /* mdma0-2 supported */ + put_le16(p + 64, 0x03); /* pio3-4 supported */ put_le16(p + 65, 120); put_le16(p + 66, 120); put_le16(p + 67, 120); @@ -198,13 +200,12 @@ static void ide_atapi_identify(IDEState *s) put_le16(p + 53, 7); /* words 64-70, 54-58, 88 valid */ put_le16(p + 62, 7); /* single word dma0-2 supported */ put_le16(p + 63, 7); /* mdma0-2 supported */ - put_le16(p + 64, 0x3f); /* PIO modes supported */ #else put_le16(p + 49, 1 << 9); /* LBA supported, no DMA */ put_le16(p + 53, 3); /* words 64-70, 54-58 valid */ put_le16(p + 63, 0x103); /* DMA modes XXX: may be incorrect */ - put_le16(p + 64, 1); /* PIO modes */ #endif + put_le16(p + 64, 3); /* pio3-4 supported */ put_le16(p + 65, 0xb4); /* minimum DMA multiword tx cycle time */ put_le16(p + 66, 0xb4); /* recommended DMA multiword tx cycle time */ put_le16(p + 67, 0x12c); /* minimum PIO cycle time without flow control */ @@ -1643,6 +1644,21 @@ static void ide_atapi_cmd(IDEState *s) ide_atapi_cmd_reply(s, len, max_len); break; } + case GPCMD_GET_EVENT_STATUS_NOTIFICATION: + max_len = ube16_to_cpu(packet + 7); + + if (packet[1] & 0x01) { /* polling */ + /* We don't support any event class (yet). */ + cpu_to_ube16(buf, 0x00); /* No event descriptor returned */ + buf[2] = 0x80; /* No Event Available (NEA) */ + buf[3] = 0x00; /* Empty supported event classes */ + ide_atapi_cmd_reply(s, 4, max_len); + } else { /* asynchronous mode */ + /* Only polling is supported, asynchronous mode is not. */ + ide_atapi_cmd_error(s, SENSE_ILLEGAL_REQUEST, + ASC_INV_FIELD_IN_CMD_PACKET); + } + break; default: ide_atapi_cmd_error(s, SENSE_ILLEGAL_REQUEST, ASC_ILLEGAL_OPCODE); @@ -2629,7 +2645,12 @@ int ide_init_drive(IDEState *s, BlockDriverState *bs, if (bdrv_get_type_hint(bs) == BDRV_TYPE_CDROM) { s->drive_kind = IDE_CD; bdrv_set_change_cb(bs, cdrom_change_cb, s); + bs->buffer_alignment = 2048; } else { + if (!bdrv_is_inserted(s->bs)) { + error_report("Device needs media, but drive is empty"); + return -1; + } if (bdrv_is_read_only(bs)) { error_report("Can't use a read-only drive"); return -1; @@ -2659,7 +2680,8 @@ static void ide_init1(IDEBus *bus, int unit) s->bus = bus; s->unit = unit; s->drive_serial = drive_serial++; - s->io_buffer = qemu_blockalign(s->bs, IDE_DMA_BUF_SECTORS*512 + 4); + /* we need at least 2k alignment for accessing CDROMs using O_DIRECT */ + s->io_buffer = qemu_memalign(2048, IDE_DMA_BUF_SECTORS*512 + 4); s->io_buffer_total_len = IDE_DMA_BUF_SECTORS*512 + 4; s->smart_selftest_data = qemu_blockalign(s->bs, 512); s->sector_write_timer = qemu_new_timer(vm_clock, @@ -2729,6 +2751,7 @@ static EndTransferFunc* transfer_end_table[] = { ide_transfer_stop, ide_atapi_cmd_reply_end, ide_atapi_cmd, + ide_dummy_transfer_stop, }; static int transfer_end_table_idx(EndTransferFunc *fn) @@ -2752,26 +2775,28 @@ static int ide_drive_post_load(void *opaque, int version_id) s->cdrom_changed = 1; } } + return 0; +} + +static int ide_drive_pio_post_load(void *opaque, int version_id) +{ + IDEState *s = opaque; - if (s->cur_io_buffer_len) { - s->end_transfer_func = transfer_end_table[s->end_transfer_fn_idx]; - s->data_ptr = s->io_buffer + s->cur_io_buffer_offset; - s->data_end = s->data_ptr + s->cur_io_buffer_len; + if (s->end_transfer_fn_idx > ARRAY_SIZE(transfer_end_table)) { + return -EINVAL; } - + s->end_transfer_func = transfer_end_table[s->end_transfer_fn_idx]; + s->data_ptr = s->io_buffer + s->cur_io_buffer_offset; + s->data_end = s->data_ptr + s->cur_io_buffer_len; + return 0; } -static void ide_drive_pre_save(void *opaque) +static void ide_drive_pio_pre_save(void *opaque) { IDEState *s = opaque; int idx; - s->cur_io_buffer_len = 0; - - if (!(s->status & DRQ_STAT)) - return; - s->cur_io_buffer_offset = s->data_ptr - s->io_buffer; s->cur_io_buffer_len = s->data_end - s->data_ptr; @@ -2785,12 +2810,38 @@ static void ide_drive_pre_save(void *opaque) } } +static bool ide_drive_pio_state_needed(void *opaque) +{ + IDEState *s = opaque; + + return (s->status & DRQ_STAT) != 0; +} + +const VMStateDescription vmstate_ide_drive_pio_state = { + .name = "ide_drive/pio_state", + .version_id = 1, + .minimum_version_id = 1, + .minimum_version_id_old = 1, + .pre_save = ide_drive_pio_pre_save, + .post_load = ide_drive_pio_post_load, + .fields = (VMStateField []) { + VMSTATE_INT32(req_nb_sectors, IDEState), + VMSTATE_VARRAY_INT32(io_buffer, IDEState, io_buffer_total_len, 1, + vmstate_info_uint8, uint8_t), + VMSTATE_INT32(cur_io_buffer_offset, IDEState), + VMSTATE_INT32(cur_io_buffer_len, IDEState), + VMSTATE_UINT8(end_transfer_fn_idx, IDEState), + VMSTATE_INT32(elementary_transfer_size, IDEState), + VMSTATE_INT32(packet_transfer_size, IDEState), + VMSTATE_END_OF_LIST() + } +}; + const VMStateDescription vmstate_ide_drive = { .name = "ide_drive", - .version_id = 4, + .version_id = 3, .minimum_version_id = 0, .minimum_version_id_old = 0, - .pre_save = ide_drive_pre_save, .post_load = ide_drive_post_load, .fields = (VMStateField []) { VMSTATE_INT32(mult_sectors, IDEState), @@ -2813,15 +2864,15 @@ const VMStateDescription vmstate_ide_drive = { VMSTATE_UINT8(sense_key, IDEState), VMSTATE_UINT8(asc, IDEState), VMSTATE_UINT8_V(cdrom_changed, IDEState, 3), - VMSTATE_INT32_V(req_nb_sectors, IDEState, 4), - VMSTATE_VARRAY_INT32(io_buffer, IDEState, io_buffer_total_len, 4, - vmstate_info_uint8, uint8_t), - VMSTATE_INT32_V(cur_io_buffer_offset, IDEState, 4), - VMSTATE_INT32_V(cur_io_buffer_len, IDEState, 4), - VMSTATE_UINT8_V(end_transfer_fn_idx, IDEState, 4), - VMSTATE_INT32_V(elementary_transfer_size, IDEState, 4), - VMSTATE_INT32_V(packet_transfer_size, IDEState, 4), VMSTATE_END_OF_LIST() + }, + .subsections = (VMStateSubsection []) { + { + .vmsd = &vmstate_ide_drive_pio_state, + .needed = ide_drive_pio_state_needed, + }, { + /* empty */ + } } }; diff --git a/hw/ide/pci.c b/hw/ide/pci.c index 4d95cc5e22..ec90f266e9 100644 --- a/hw/ide/pci.c +++ b/hw/ide/pci.c @@ -40,8 +40,27 @@ void bmdma_cmd_writeb(void *opaque, uint32_t addr, uint32_t val) printf("%s: 0x%08x\n", __func__, val); #endif if (!(val & BM_CMD_START)) { - /* XXX: do it better */ - ide_dma_cancel(bm); + /* + * We can't cancel Scatter Gather DMA in the middle of the + * operation or a partial (not full) DMA transfer would reach + * the storage so we wait for completion instead (we beahve + * like if the DMA was completed by the time the guest trying + * to cancel dma with bmdma_cmd_writeb with BM_CMD_START not + * set). + * + * In the future we'll be able to safely cancel the I/O if the + * whole DMA operation will be submitted to disk with a single + * aio operation with preadv/pwritev. + */ + if (bm->aiocb) { + qemu_aio_flush(); +#ifdef DEBUG_IDE + if (bm->aiocb) + printf("ide_dma_cancel: aiocb still pending"); + if (bm->status & BM_STATUS_DMAING) + printf("ide_dma_cancel: BM_STATUS_DMAING still pending"); +#endif + } bm->cmd = val & 0x09; } else { if (!(bm->status & BM_STATUS_DMAING)) { @@ -121,9 +140,31 @@ void bmdma_addr_writel(void *opaque, uint32_t addr, uint32_t val) bm->cur_addr = bm->addr; } +static bool ide_bmdma_current_needed(void *opaque) +{ + BMDMAState *bm = opaque; + + return (bm->cur_prd_len != 0); +} + +static const VMStateDescription vmstate_bmdma_current = { + .name = "ide bmdma_current", + .version_id = 1, + .minimum_version_id = 1, + .minimum_version_id_old = 1, + .fields = (VMStateField []) { + VMSTATE_UINT32(cur_addr, BMDMAState), + VMSTATE_UINT32(cur_prd_last, BMDMAState), + VMSTATE_UINT32(cur_prd_addr, BMDMAState), + VMSTATE_UINT32(cur_prd_len, BMDMAState), + VMSTATE_END_OF_LIST() + } +}; + + static const VMStateDescription vmstate_bmdma = { .name = "ide bmdma", - .version_id = 4, + .version_id = 3, .minimum_version_id = 0, .minimum_version_id_old = 0, .fields = (VMStateField []) { @@ -133,11 +174,15 @@ static const VMStateDescription vmstate_bmdma = { VMSTATE_INT64(sector_num, BMDMAState), VMSTATE_UINT32(nsector, BMDMAState), VMSTATE_UINT8(unit, BMDMAState), - VMSTATE_UINT32_V(cur_addr, BMDMAState, 4), - VMSTATE_UINT32_V(cur_prd_last, BMDMAState, 4), - VMSTATE_UINT32_V(cur_prd_addr, BMDMAState, 4), - VMSTATE_UINT32_V(cur_prd_len, BMDMAState, 4), VMSTATE_END_OF_LIST() + }, + .subsections = (VMStateSubsection []) { + { + .vmsd = &vmstate_bmdma_current, + .needed = ide_bmdma_current_needed, + }, { + /* empty */ + } } }; @@ -156,7 +201,7 @@ static int ide_pci_post_load(void *opaque, int version_id) const VMStateDescription vmstate_ide_pci = { .name = "ide", - .version_id = 4, + .version_id = 3, .minimum_version_id = 0, .minimum_version_id_old = 0, .post_load = ide_pci_post_load, diff --git a/hw/ide/qdev.c b/hw/ide/qdev.c index 53468edcbc..080876035f 100644 --- a/hw/ide/qdev.c +++ b/hw/ide/qdev.c @@ -20,6 +20,7 @@ #include "dma.h" #include "qemu-error.h" #include <hw/ide/internal.h> +#include "blockdev.h" /* --------------------------------- */ diff --git a/hw/ide/via.c b/hw/ide/via.c index a403e8cd98..b2c7cad622 100644 --- a/hw/ide/via.c +++ b/hw/ide/via.c @@ -150,7 +150,6 @@ static int vt82c686b_ide_initfn(PCIDevice *dev) pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_IDE); pci_config_set_prog_interface(pci_conf, 0x8a); /* legacy ATA mode */ pci_config_set_revision(pci_conf,0x06); /* Revision 0.6 */ - pci_conf[PCI_HEADER_TYPE] = PCI_HEADER_TYPE_NORMAL; /* header_type */ pci_set_long(pci_conf + PCI_CAPABILITY_LIST, 0x000000c0); qemu_register_reset(via_reset, d); diff --git a/hw/ivshmem.c b/hw/ivshmem.c new file mode 100644 index 0000000000..06dce70e78 --- /dev/null +++ b/hw/ivshmem.c @@ -0,0 +1,829 @@ +/* + * Inter-VM Shared Memory PCI device. + * + * Author: + * Cam Macdonell <cam@cs.ualberta.ca> + * + * Based On: cirrus_vga.c + * Copyright (c) 2004 Fabrice Bellard + * Copyright (c) 2004 Makoto Suzuki (suzu) + * + * and rtl8139.c + * Copyright (c) 2006 Igor Kovalenko + * + * This code is licensed under the GNU GPL v2. + */ +#include "hw.h" +#include "pc.h" +#include "pci.h" +#include "msix.h" +#include "kvm.h" + +#include <sys/mman.h> +#include <sys/types.h> + +#define IVSHMEM_IOEVENTFD 0 +#define IVSHMEM_MSI 1 + +#define IVSHMEM_PEER 0 +#define IVSHMEM_MASTER 1 + +#define IVSHMEM_REG_BAR_SIZE 0x100 + +//#define DEBUG_IVSHMEM +#ifdef DEBUG_IVSHMEM +#define IVSHMEM_DPRINTF(fmt, ...) \ + do {printf("IVSHMEM: " fmt, ## __VA_ARGS__); } while (0) +#else +#define IVSHMEM_DPRINTF(fmt, ...) +#endif + +typedef struct Peer { + int nb_eventfds; + int *eventfds; +} Peer; + +typedef struct EventfdEntry { + PCIDevice *pdev; + int vector; +} EventfdEntry; + +typedef struct IVShmemState { + PCIDevice dev; + uint32_t intrmask; + uint32_t intrstatus; + uint32_t doorbell; + + CharDriverState **eventfd_chr; + CharDriverState *server_chr; + int ivshmem_mmio_io_addr; + + pcibus_t mmio_addr; + pcibus_t shm_pci_addr; + uint64_t ivshmem_offset; + uint64_t ivshmem_size; /* size of shared memory region */ + int shm_fd; /* shared memory file descriptor */ + + Peer *peers; + int nb_peers; /* how many guests we have space for */ + int max_peer; /* maximum numbered peer */ + + int vm_id; + uint32_t vectors; + uint32_t features; + EventfdEntry *eventfd_table; + + char * shmobj; + char * sizearg; + char * role; + int role_val; /* scalar to avoid multiple string comparisons */ +} IVShmemState; + +/* registers for the Inter-VM shared memory device */ +enum ivshmem_registers { + INTRMASK = 0, + INTRSTATUS = 4, + IVPOSITION = 8, + DOORBELL = 12, +}; + +static inline uint32_t ivshmem_has_feature(IVShmemState *ivs, + unsigned int feature) { + return (ivs->features & (1 << feature)); +} + +static inline bool is_power_of_two(uint64_t x) { + return (x & (x - 1)) == 0; +} + +static void ivshmem_map(PCIDevice *pci_dev, int region_num, + pcibus_t addr, pcibus_t size, int type) +{ + IVShmemState *s = DO_UPCAST(IVShmemState, dev, pci_dev); + + s->shm_pci_addr = addr; + + if (s->ivshmem_offset > 0) { + cpu_register_physical_memory(s->shm_pci_addr, s->ivshmem_size, + s->ivshmem_offset); + } + + IVSHMEM_DPRINTF("guest pci addr = %" FMT_PCIBUS ", guest h/w addr = %" + PRIu64 ", size = %" FMT_PCIBUS "\n", addr, s->ivshmem_offset, size); + +} + +/* accessing registers - based on rtl8139 */ +static void ivshmem_update_irq(IVShmemState *s, int val) +{ + int isr; + isr = (s->intrstatus & s->intrmask) & 0xffffffff; + + /* don't print ISR resets */ + if (isr) { + IVSHMEM_DPRINTF("Set IRQ to %d (%04x %04x)\n", + isr ? 1 : 0, s->intrstatus, s->intrmask); + } + + qemu_set_irq(s->dev.irq[0], (isr != 0)); +} + +static void ivshmem_IntrMask_write(IVShmemState *s, uint32_t val) +{ + IVSHMEM_DPRINTF("IntrMask write(w) val = 0x%04x\n", val); + + s->intrmask = val; + + ivshmem_update_irq(s, val); +} + +static uint32_t ivshmem_IntrMask_read(IVShmemState *s) +{ + uint32_t ret = s->intrmask; + + IVSHMEM_DPRINTF("intrmask read(w) val = 0x%04x\n", ret); + + return ret; +} + +static void ivshmem_IntrStatus_write(IVShmemState *s, uint32_t val) +{ + IVSHMEM_DPRINTF("IntrStatus write(w) val = 0x%04x\n", val); + + s->intrstatus = val; + + ivshmem_update_irq(s, val); + return; +} + +static uint32_t ivshmem_IntrStatus_read(IVShmemState *s) +{ + uint32_t ret = s->intrstatus; + + /* reading ISR clears all interrupts */ + s->intrstatus = 0; + + ivshmem_update_irq(s, 0); + + return ret; +} + +static void ivshmem_io_writew(void *opaque, target_phys_addr_t addr, + uint32_t val) +{ + + IVSHMEM_DPRINTF("We shouldn't be writing words\n"); +} + +static void ivshmem_io_writel(void *opaque, target_phys_addr_t addr, + uint32_t val) +{ + IVShmemState *s = opaque; + + uint64_t write_one = 1; + uint16_t dest = val >> 16; + uint16_t vector = val & 0xff; + + addr &= 0xfc; + + IVSHMEM_DPRINTF("writing to addr " TARGET_FMT_plx "\n", addr); + switch (addr) + { + case INTRMASK: + ivshmem_IntrMask_write(s, val); + break; + + case INTRSTATUS: + ivshmem_IntrStatus_write(s, val); + break; + + case DOORBELL: + /* check that dest VM ID is reasonable */ + if (dest > s->max_peer) { + IVSHMEM_DPRINTF("Invalid destination VM ID (%d)\n", dest); + break; + } + + /* check doorbell range */ + if (vector < s->peers[dest].nb_eventfds) { + IVSHMEM_DPRINTF("Writing %" PRId64 " to VM %d on vector %d\n", + write_one, dest, vector); + if (write(s->peers[dest].eventfds[vector], + &(write_one), 8) != 8) { + IVSHMEM_DPRINTF("error writing to eventfd\n"); + } + } + break; + default: + IVSHMEM_DPRINTF("Invalid VM Doorbell VM %d\n", dest); + } +} + +static void ivshmem_io_writeb(void *opaque, target_phys_addr_t addr, + uint32_t val) +{ + IVSHMEM_DPRINTF("We shouldn't be writing bytes\n"); +} + +static uint32_t ivshmem_io_readw(void *opaque, target_phys_addr_t addr) +{ + + IVSHMEM_DPRINTF("We shouldn't be reading words\n"); + return 0; +} + +static uint32_t ivshmem_io_readl(void *opaque, target_phys_addr_t addr) +{ + + IVShmemState *s = opaque; + uint32_t ret; + + switch (addr) + { + case INTRMASK: + ret = ivshmem_IntrMask_read(s); + break; + + case INTRSTATUS: + ret = ivshmem_IntrStatus_read(s); + break; + + case IVPOSITION: + /* return my VM ID if the memory is mapped */ + if (s->shm_fd > 0) { + ret = s->vm_id; + } else { + ret = -1; + } + break; + + default: + IVSHMEM_DPRINTF("why are we reading " TARGET_FMT_plx "\n", addr); + ret = 0; + } + + return ret; +} + +static uint32_t ivshmem_io_readb(void *opaque, target_phys_addr_t addr) +{ + IVSHMEM_DPRINTF("We shouldn't be reading bytes\n"); + + return 0; +} + +static CPUReadMemoryFunc * const ivshmem_mmio_read[3] = { + ivshmem_io_readb, + ivshmem_io_readw, + ivshmem_io_readl, +}; + +static CPUWriteMemoryFunc * const ivshmem_mmio_write[3] = { + ivshmem_io_writeb, + ivshmem_io_writew, + ivshmem_io_writel, +}; + +static void ivshmem_receive(void *opaque, const uint8_t *buf, int size) +{ + IVShmemState *s = opaque; + + ivshmem_IntrStatus_write(s, *buf); + + IVSHMEM_DPRINTF("ivshmem_receive 0x%02x\n", *buf); +} + +static int ivshmem_can_receive(void * opaque) +{ + return 8; +} + +static void ivshmem_event(void *opaque, int event) +{ + IVSHMEM_DPRINTF("ivshmem_event %d\n", event); +} + +static void fake_irqfd(void *opaque, const uint8_t *buf, int size) { + + EventfdEntry *entry = opaque; + PCIDevice *pdev = entry->pdev; + + IVSHMEM_DPRINTF("interrupt on vector %p %d\n", pdev, entry->vector); + msix_notify(pdev, entry->vector); +} + +static CharDriverState* create_eventfd_chr_device(void * opaque, int eventfd, + int vector) +{ + /* create a event character device based on the passed eventfd */ + IVShmemState *s = opaque; + CharDriverState * chr; + + chr = qemu_chr_open_eventfd(eventfd); + + if (chr == NULL) { + fprintf(stderr, "creating eventfd for eventfd %d failed\n", eventfd); + exit(-1); + } + + /* if MSI is supported we need multiple interrupts */ + if (ivshmem_has_feature(s, IVSHMEM_MSI)) { + s->eventfd_table[vector].pdev = &s->dev; + s->eventfd_table[vector].vector = vector; + + qemu_chr_add_handlers(chr, ivshmem_can_receive, fake_irqfd, + ivshmem_event, &s->eventfd_table[vector]); + } else { + qemu_chr_add_handlers(chr, ivshmem_can_receive, ivshmem_receive, + ivshmem_event, s); + } + + return chr; + +} + +static int check_shm_size(IVShmemState *s, int fd) { + /* check that the guest isn't going to try and map more memory than the + * the object has allocated return -1 to indicate error */ + + struct stat buf; + + fstat(fd, &buf); + + if (s->ivshmem_size > buf.st_size) { + fprintf(stderr, + "IVSHMEM ERROR: Requested memory size greater" + " than shared object size (%" PRIu64 " > %" PRIu64")\n", + s->ivshmem_size, (uint64_t)buf.st_size); + return -1; + } else { + return 0; + } +} + +/* create the shared memory BAR when we are not using the server, so we can + * create the BAR and map the memory immediately */ +static void create_shared_memory_BAR(IVShmemState *s, int fd) { + + void * ptr; + + s->shm_fd = fd; + + ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); + + s->ivshmem_offset = qemu_ram_alloc_from_ptr(&s->dev.qdev, "ivshmem.bar2", + s->ivshmem_size, ptr); + + /* region for shared memory */ + pci_register_bar(&s->dev, 2, s->ivshmem_size, + PCI_BASE_ADDRESS_SPACE_MEMORY, ivshmem_map); +} + +static void close_guest_eventfds(IVShmemState *s, int posn) +{ + int i, guest_curr_max; + + guest_curr_max = s->peers[posn].nb_eventfds; + + for (i = 0; i < guest_curr_max; i++) { + kvm_set_ioeventfd_mmio_long(s->peers[posn].eventfds[i], + s->mmio_addr + DOORBELL, (posn << 16) | i, 0); + close(s->peers[posn].eventfds[i]); + } + + qemu_free(s->peers[posn].eventfds); + s->peers[posn].nb_eventfds = 0; +} + +static void setup_ioeventfds(IVShmemState *s) { + + int i, j; + + for (i = 0; i <= s->max_peer; i++) { + for (j = 0; j < s->peers[i].nb_eventfds; j++) { + kvm_set_ioeventfd_mmio_long(s->peers[i].eventfds[j], + s->mmio_addr + DOORBELL, (i << 16) | j, 1); + } + } +} + +/* this function increase the dynamic storage need to store data about other + * guests */ +static void increase_dynamic_storage(IVShmemState *s, int new_min_size) { + + int j, old_nb_alloc; + + old_nb_alloc = s->nb_peers; + + while (new_min_size >= s->nb_peers) + s->nb_peers = s->nb_peers * 2; + + IVSHMEM_DPRINTF("bumping storage to %d guests\n", s->nb_peers); + s->peers = qemu_realloc(s->peers, s->nb_peers * sizeof(Peer)); + + /* zero out new pointers */ + for (j = old_nb_alloc; j < s->nb_peers; j++) { + s->peers[j].eventfds = NULL; + s->peers[j].nb_eventfds = 0; + } +} + +static void ivshmem_read(void *opaque, const uint8_t * buf, int flags) +{ + IVShmemState *s = opaque; + int incoming_fd, tmp_fd; + int guest_max_eventfd; + long incoming_posn; + + memcpy(&incoming_posn, buf, sizeof(long)); + /* pick off s->server_chr->msgfd and store it, posn should accompany msg */ + tmp_fd = qemu_chr_get_msgfd(s->server_chr); + IVSHMEM_DPRINTF("posn is %ld, fd is %d\n", incoming_posn, tmp_fd); + + /* make sure we have enough space for this guest */ + if (incoming_posn >= s->nb_peers) { + increase_dynamic_storage(s, incoming_posn); + } + + if (tmp_fd == -1) { + /* if posn is positive and unseen before then this is our posn*/ + if ((incoming_posn >= 0) && + (s->peers[incoming_posn].eventfds == NULL)) { + /* receive our posn */ + s->vm_id = incoming_posn; + return; + } else { + /* otherwise an fd == -1 means an existing guest has gone away */ + IVSHMEM_DPRINTF("posn %ld has gone away\n", incoming_posn); + close_guest_eventfds(s, incoming_posn); + return; + } + } + + /* because of the implementation of get_msgfd, we need a dup */ + incoming_fd = dup(tmp_fd); + + if (incoming_fd == -1) { + fprintf(stderr, "could not allocate file descriptor %s\n", + strerror(errno)); + return; + } + + /* if the position is -1, then it's shared memory region fd */ + if (incoming_posn == -1) { + + void * map_ptr; + + s->max_peer = 0; + + if (check_shm_size(s, incoming_fd) == -1) { + exit(-1); + } + + /* mmap the region and map into the BAR2 */ + map_ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED, + incoming_fd, 0); + s->ivshmem_offset = qemu_ram_alloc_from_ptr(&s->dev.qdev, + "ivshmem.bar2", s->ivshmem_size, map_ptr); + + IVSHMEM_DPRINTF("guest pci addr = %" FMT_PCIBUS ", guest h/w addr = %" + PRIu64 ", size = %" PRIu64 "\n", s->shm_pci_addr, + s->ivshmem_offset, s->ivshmem_size); + + if (s->shm_pci_addr > 0) { + /* map memory into BAR2 */ + cpu_register_physical_memory(s->shm_pci_addr, s->ivshmem_size, + s->ivshmem_offset); + } + + /* only store the fd if it is successfully mapped */ + s->shm_fd = incoming_fd; + + return; + } + + /* each guest has an array of eventfds, and we keep track of how many + * guests for each VM */ + guest_max_eventfd = s->peers[incoming_posn].nb_eventfds; + + if (guest_max_eventfd == 0) { + /* one eventfd per MSI vector */ + s->peers[incoming_posn].eventfds = (int *) qemu_malloc(s->vectors * + sizeof(int)); + } + + /* this is an eventfd for a particular guest VM */ + IVSHMEM_DPRINTF("eventfds[%ld][%d] = %d\n", incoming_posn, + guest_max_eventfd, incoming_fd); + s->peers[incoming_posn].eventfds[guest_max_eventfd] = incoming_fd; + + /* increment count for particular guest */ + s->peers[incoming_posn].nb_eventfds++; + + /* keep track of the maximum VM ID */ + if (incoming_posn > s->max_peer) { + s->max_peer = incoming_posn; + } + + if (incoming_posn == s->vm_id) { + s->eventfd_chr[guest_max_eventfd] = create_eventfd_chr_device(s, + s->peers[s->vm_id].eventfds[guest_max_eventfd], + guest_max_eventfd); + } + + if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) { + if (kvm_set_ioeventfd_mmio_long(incoming_fd, s->mmio_addr + DOORBELL, + (incoming_posn << 16) | guest_max_eventfd, 1) < 0) { + fprintf(stderr, "ivshmem: ioeventfd not available\n"); + } + } + + return; +} + +static void ivshmem_reset(DeviceState *d) +{ + IVShmemState *s = DO_UPCAST(IVShmemState, dev.qdev, d); + + s->intrstatus = 0; + return; +} + +static void ivshmem_mmio_map(PCIDevice *pci_dev, int region_num, + pcibus_t addr, pcibus_t size, int type) +{ + IVShmemState *s = DO_UPCAST(IVShmemState, dev, pci_dev); + + s->mmio_addr = addr; + cpu_register_physical_memory(addr + 0, IVSHMEM_REG_BAR_SIZE, + s->ivshmem_mmio_io_addr); + + if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) { + setup_ioeventfds(s); + } +} + +static uint64_t ivshmem_get_size(IVShmemState * s) { + + uint64_t value; + char *ptr; + + value = strtoull(s->sizearg, &ptr, 10); + switch (*ptr) { + case 0: case 'M': case 'm': + value <<= 20; + break; + case 'G': case 'g': + value <<= 30; + break; + default: + fprintf(stderr, "qemu: invalid ram size: %s\n", s->sizearg); + exit(1); + } + + /* BARs must be a power of 2 */ + if (!is_power_of_two(value)) { + fprintf(stderr, "ivshmem: size must be power of 2\n"); + exit(1); + } + + return value; +} + +static void ivshmem_setup_msi(IVShmemState * s) { + + int i; + + /* allocate the MSI-X vectors */ + + if (!msix_init(&s->dev, s->vectors, 1, 0)) { + pci_register_bar(&s->dev, 1, + msix_bar_size(&s->dev), + PCI_BASE_ADDRESS_SPACE_MEMORY, + msix_mmio_map); + IVSHMEM_DPRINTF("msix initialized (%d vectors)\n", s->vectors); + } else { + IVSHMEM_DPRINTF("msix initialization failed\n"); + exit(1); + } + + /* 'activate' the vectors */ + for (i = 0; i < s->vectors; i++) { + msix_vector_use(&s->dev, i); + } + + /* allocate Qemu char devices for receiving interrupts */ + s->eventfd_table = qemu_mallocz(s->vectors * sizeof(EventfdEntry)); +} + +static void ivshmem_save(QEMUFile* f, void *opaque) +{ + IVShmemState *proxy = opaque; + + IVSHMEM_DPRINTF("ivshmem_save\n"); + pci_device_save(&proxy->dev, f); + + if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) { + msix_save(&proxy->dev, f); + } else { + qemu_put_be32(f, proxy->intrstatus); + qemu_put_be32(f, proxy->intrmask); + } + +} + +static int ivshmem_load(QEMUFile* f, void *opaque, int version_id) +{ + IVSHMEM_DPRINTF("ivshmem_load\n"); + + IVShmemState *proxy = opaque; + int ret, i; + + if (version_id > 0) { + return -EINVAL; + } + + if (proxy->role_val == IVSHMEM_PEER) { + fprintf(stderr, "ivshmem: 'peer' devices are not migratable\n"); + return -EINVAL; + } + + ret = pci_device_load(&proxy->dev, f); + if (ret) { + return ret; + } + + if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) { + msix_load(&proxy->dev, f); + for (i = 0; i < proxy->vectors; i++) { + msix_vector_use(&proxy->dev, i); + } + } else { + proxy->intrstatus = qemu_get_be32(f); + proxy->intrmask = qemu_get_be32(f); + } + + return 0; +} + +static int pci_ivshmem_init(PCIDevice *dev) +{ + IVShmemState *s = DO_UPCAST(IVShmemState, dev, dev); + uint8_t *pci_conf; + + if (s->sizearg == NULL) + s->ivshmem_size = 4 << 20; /* 4 MB default */ + else { + s->ivshmem_size = ivshmem_get_size(s); + } + + register_savevm(&s->dev.qdev, "ivshmem", 0, 0, ivshmem_save, ivshmem_load, + dev); + + /* IRQFD requires MSI */ + if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) && + !ivshmem_has_feature(s, IVSHMEM_MSI)) { + fprintf(stderr, "ivshmem: ioeventfd/irqfd requires MSI\n"); + exit(1); + } + + /* check that role is reasonable */ + if (s->role) { + if (strncmp(s->role, "peer", 5) == 0) { + s->role_val = IVSHMEM_PEER; + } else if (strncmp(s->role, "master", 7) == 0) { + s->role_val = IVSHMEM_MASTER; + } else { + fprintf(stderr, "ivshmem: 'role' must be 'peer' or 'master'\n"); + exit(1); + } + } else { + s->role_val = IVSHMEM_MASTER; /* default */ + } + + if (s->role_val == IVSHMEM_PEER) { + register_device_unmigratable(&s->dev.qdev, "ivshmem", s); + } + + pci_conf = s->dev.config; + pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_REDHAT_QUMRANET); + pci_conf[0x02] = 0x10; + pci_conf[0x03] = 0x11; + pci_conf[PCI_COMMAND] = PCI_COMMAND_IO | PCI_COMMAND_MEMORY; + pci_config_set_class(pci_conf, PCI_CLASS_MEMORY_RAM); + pci_conf[PCI_HEADER_TYPE] = PCI_HEADER_TYPE_NORMAL; + + pci_config_set_interrupt_pin(pci_conf, 1); + + s->shm_pci_addr = 0; + s->ivshmem_offset = 0; + s->shm_fd = 0; + + s->ivshmem_mmio_io_addr = cpu_register_io_memory(ivshmem_mmio_read, + ivshmem_mmio_write, s); + /* region for registers*/ + pci_register_bar(&s->dev, 0, IVSHMEM_REG_BAR_SIZE, + PCI_BASE_ADDRESS_SPACE_MEMORY, ivshmem_mmio_map); + + if ((s->server_chr != NULL) && + (strncmp(s->server_chr->filename, "unix:", 5) == 0)) { + /* if we get a UNIX socket as the parameter we will talk + * to the ivshmem server to receive the memory region */ + + if (s->shmobj != NULL) { + fprintf(stderr, "WARNING: do not specify both 'chardev' " + "and 'shm' with ivshmem\n"); + } + + IVSHMEM_DPRINTF("using shared memory server (socket = %s)\n", + s->server_chr->filename); + + if (ivshmem_has_feature(s, IVSHMEM_MSI)) { + ivshmem_setup_msi(s); + } + + /* we allocate enough space for 16 guests and grow as needed */ + s->nb_peers = 16; + s->vm_id = -1; + + /* allocate/initialize space for interrupt handling */ + s->peers = qemu_mallocz(s->nb_peers * sizeof(Peer)); + + pci_register_bar(&s->dev, 2, s->ivshmem_size, + PCI_BASE_ADDRESS_SPACE_MEMORY, ivshmem_map); + + s->eventfd_chr = qemu_mallocz(s->vectors * sizeof(CharDriverState *)); + + qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive, ivshmem_read, + ivshmem_event, s); + } else { + /* just map the file immediately, we're not using a server */ + int fd; + + if (s->shmobj == NULL) { + fprintf(stderr, "Must specify 'chardev' or 'shm' to ivshmem\n"); + } + + IVSHMEM_DPRINTF("using shm_open (shm object = %s)\n", s->shmobj); + + /* try opening with O_EXCL and if it succeeds zero the memory + * by truncating to 0 */ + if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR|O_EXCL, + S_IRWXU|S_IRWXG|S_IRWXO)) > 0) { + /* truncate file to length PCI device's memory */ + if (ftruncate(fd, s->ivshmem_size) != 0) { + fprintf(stderr, "ivshmem: could not truncate shared file\n"); + } + + } else if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR, + S_IRWXU|S_IRWXG|S_IRWXO)) < 0) { + fprintf(stderr, "ivshmem: could not open shared file\n"); + exit(-1); + + } + + if (check_shm_size(s, fd) == -1) { + exit(-1); + } + + create_shared_memory_BAR(s, fd); + + } + + return 0; +} + +static int pci_ivshmem_uninit(PCIDevice *dev) +{ + IVShmemState *s = DO_UPCAST(IVShmemState, dev, dev); + + cpu_unregister_io_memory(s->ivshmem_mmio_io_addr); + unregister_savevm(&dev->qdev, "ivshmem", s); + + return 0; +} + +static PCIDeviceInfo ivshmem_info = { + .qdev.name = "ivshmem", + .qdev.size = sizeof(IVShmemState), + .qdev.reset = ivshmem_reset, + .init = pci_ivshmem_init, + .exit = pci_ivshmem_uninit, + .qdev.props = (Property[]) { + DEFINE_PROP_CHR("chardev", IVShmemState, server_chr), + DEFINE_PROP_STRING("size", IVShmemState, sizearg), + DEFINE_PROP_UINT32("vectors", IVShmemState, vectors, 1), + DEFINE_PROP_BIT("ioeventfd", IVShmemState, features, IVSHMEM_IOEVENTFD, false), + DEFINE_PROP_BIT("msi", IVShmemState, features, IVSHMEM_MSI, true), + DEFINE_PROP_STRING("shm", IVShmemState, shmobj), + DEFINE_PROP_STRING("role", IVShmemState, role), + DEFINE_PROP_END_OF_LIST(), + } +}; + +static void ivshmem_register_devices(void) +{ + pci_qdev_register(&ivshmem_info); +} + +device_init(ivshmem_register_devices) diff --git a/hw/jazz_led.c b/hw/jazz_led.c index 18780e9371..4cb680c3e4 100644 --- a/hw/jazz_led.c +++ b/hw/jazz_led.c @@ -29,6 +29,15 @@ //#define DEBUG_LED +#ifdef DEBUG_LED +#define DPRINTF(fmt, ...) \ +do { printf("jazz led: " fmt , ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) do {} while (0) +#endif +#define BADF(fmt, ...) \ +do { fprintf(stderr, "jazz led ERROR: " fmt , ## __VA_ARGS__);} while (0) + typedef enum { REDRAW_NONE = 0, REDRAW_SEGMENTS = 1, REDRAW_BACKGROUND = 2, } screen_state_t; @@ -49,12 +58,12 @@ static uint32_t led_readb(void *opaque, target_phys_addr_t addr) val = s->segments; break; default: -#ifdef DEBUG_LED - printf("jazz led: invalid read [0x%x]\n", relative_addr); -#endif + BADF("invalid read at [" TARGET_FMT_plx "]\n", addr); val = 0; } + DPRINTF("read addr=" TARGET_FMT_plx " val=0x%02x\n", addr, val); + return val; } @@ -92,15 +101,15 @@ static void led_writeb(void *opaque, target_phys_addr_t addr, uint32_t val) { LedState *s = opaque; + DPRINTF("write addr=" TARGET_FMT_plx " val=0x%02x\n", addr, val); + switch (addr) { case 0: s->segments = val; s->state |= REDRAW_SEGMENTS; break; default: -#ifdef DEBUG_LED - printf("jazz led: invalid write of 0x%02x at [0x%x]\n", val, relative_addr); -#endif + BADF("invalid write of 0x%08x at [" TARGET_FMT_plx "]\n", val, addr); break; } } diff --git a/hw/loader.c b/hw/loader.c index 79a6f95186..49ac1fa1cc 100644 --- a/hw/loader.c +++ b/hw/loader.c @@ -733,11 +733,6 @@ int rom_copy(uint8_t *dest, target_phys_addr_t addr, size_t size) s = rom->data; l = rom->romsize; - if (rom->addr < addr) { - d = dest; - s += (addr - rom->addr); - l -= (addr - rom->addr); - } if ((d + l) > (dest + size)) { l = dest - d; } diff --git a/hw/lsi53c895a.c b/hw/lsi53c895a.c index bd7b661426..f97335eaa9 100644 --- a/hw/lsi53c895a.c +++ b/hw/lsi53c895a.c @@ -600,7 +600,7 @@ static void lsi_queue_command(LSIState *s) { lsi_request *p = s->current; - DPRINTF("Queueing tag=0x%x\n", s->current_tag); + DPRINTF("Queueing tag=0x%x\n", p->tag); assert(s->current != NULL); assert(s->current->dma_len == 0); QTAILQ_INSERT_TAIL(&s->queue, s->current, next); @@ -864,6 +864,7 @@ static void lsi_do_msgout(LSIState *s) case 0x01: len = lsi_get_msgbyte(s); msg = lsi_get_msgbyte(s); + (void)len; /* avoid a warning about unused variable*/ DPRINTF("Extended message 0x%x (len %d)\n", msg, len); switch (msg) { case 1: @@ -880,7 +881,7 @@ static void lsi_do_msgout(LSIState *s) break; case 0x20: /* SIMPLE queue */ s->select_tag |= lsi_get_msgbyte(s) | LSI_TAG_VALID; - DPRINTF("SIMPLE queue tag=0x%x\n", s->current_tag & 0xff); + DPRINTF("SIMPLE queue tag=0x%x\n", s->select_tag & 0xff); break; case 0x21: /* HEAD of queue */ BADF("HEAD queue not implemented\n"); diff --git a/hw/mainstone.c b/hw/mainstone.c index cba7e63b3c..efa2959c72 100644 --- a/hw/mainstone.c +++ b/hw/mainstone.c @@ -17,6 +17,7 @@ #include "mainstone.h" #include "sysemu.h" #include "flash.h" +#include "blockdev.h" static struct keymap map[0xE0] = { [0 ... 0xDF] = { -1, -1 }, diff --git a/hw/mips_fulong2e.c b/hw/mips_fulong2e.c index a9bbff64b3..07eb9eeba1 100644 --- a/hw/mips_fulong2e.c +++ b/hw/mips_fulong2e.c @@ -37,6 +37,7 @@ #include "elf.h" #include "vt82c686.h" #include "mc146818rtc.h" +#include "blockdev.h" #define DEBUG_FULONG2E_INIT @@ -75,7 +76,8 @@ static struct _loaderparams { const char *initrd_filename; } loaderparams; -static void prom_set(uint32_t* prom_buf, int index, const char *string, ...) +static void GCC_FMT_ATTR(3, 4) prom_set(uint32_t* prom_buf, int index, + const char *string, ...) { va_list ap; int32_t table_addr; @@ -140,13 +142,13 @@ static int64_t load_kernel (CPUState *env) prom_size = ENVP_NB_ENTRIES * (sizeof(int32_t) + ENVP_ENTRY_SIZE); prom_buf = qemu_malloc(prom_size); - prom_set(prom_buf, index++, loaderparams.kernel_filename); + prom_set(prom_buf, index++, "%s", loaderparams.kernel_filename); if (initrd_size > 0) { - prom_set(prom_buf, index++, "rd_start=0x" PRIx64 " rd_size=%li %s", + prom_set(prom_buf, index++, "rd_start=0x%" PRIx64 " rd_size=%li %s", cpu_mips_phys_to_kseg0(NULL, initrd_offset), initrd_size, loaderparams.kernel_cmdline); } else { - prom_set(prom_buf, index++, loaderparams.kernel_cmdline); + prom_set(prom_buf, index++, "%s", loaderparams.kernel_cmdline); } /* Setup minimum environment variables */ @@ -219,8 +221,8 @@ uint8_t eeprom_spd[0x80] = { #ifdef HAS_AUDIO static void audio_init (PCIBus *pci_bus) { - vt82c686b_ac97_init(pci_bus, (FULONG2E_VIA_SLOT << 3) + 5); - vt82c686b_mc97_init(pci_bus, (FULONG2E_VIA_SLOT << 3) + 6); + vt82c686b_ac97_init(pci_bus, PCI_DEVFN(FULONG2E_VIA_SLOT, 5)); + vt82c686b_mc97_init(pci_bus, PCI_DEVFN(FULONG2E_VIA_SLOT, 6)); } #endif @@ -257,19 +259,17 @@ static void mips_fulong2e_init(ram_addr_t ram_size, const char *boot_device, { char *filename; unsigned long ram_offset, bios_offset; - unsigned long bios_size; + long bios_size; int64_t kernel_entry; qemu_irq *i8259; qemu_irq *cpu_exit_irq; int via_devfn; PCIBus *pci_bus; - ISADevice *isa_dev; uint8_t *eeprom_buf; i2c_bus *smbus; int i; DriveInfo *hd[MAX_IDE_BUS * MAX_IDE_DEVS]; DeviceState *eeprom; - ISADevice *rtc_state; CPUState *env; /* init CPUs */ @@ -295,7 +295,7 @@ static void mips_fulong2e_init(ram_addr_t ram_size, const char *boot_device, ram_offset = qemu_ram_alloc(NULL, "fulong2e.ram", ram_size); bios_offset = qemu_ram_alloc(NULL, "fulong2e.bios", bios_size); - cpu_register_physical_memory(0, ram_size, IO_MEM_RAM); + cpu_register_physical_memory(0, ram_size, ram_offset); cpu_register_physical_memory(0x1fc00000LL, bios_size, bios_offset | IO_MEM_ROM); @@ -349,18 +349,18 @@ static void mips_fulong2e_init(ram_addr_t ram_size, const char *boot_device, hd[i] = drive_get(IF_IDE, i / MAX_IDE_DEVS, i % MAX_IDE_DEVS); } - via_devfn = vt82c686b_init(pci_bus, FULONG2E_VIA_SLOT << 3); + via_devfn = vt82c686b_init(pci_bus, PCI_DEVFN(FULONG2E_VIA_SLOT, 0)); if (via_devfn < 0) { fprintf(stderr, "vt82c686b_init error \n"); exit(1); } isa_bus_irqs(i8259); - vt82c686b_ide_init(pci_bus, hd, (FULONG2E_VIA_SLOT << 3) + 1); - usb_uhci_vt82c686b_init(pci_bus, (FULONG2E_VIA_SLOT << 3) + 2); - usb_uhci_vt82c686b_init(pci_bus, (FULONG2E_VIA_SLOT << 3) + 3); + vt82c686b_ide_init(pci_bus, hd, PCI_DEVFN(FULONG2E_VIA_SLOT, 1)); + usb_uhci_vt82c686b_init(pci_bus, PCI_DEVFN(FULONG2E_VIA_SLOT, 2)); + usb_uhci_vt82c686b_init(pci_bus, PCI_DEVFN(FULONG2E_VIA_SLOT, 3)); - smbus = vt82c686b_pm_init(pci_bus, (FULONG2E_VIA_SLOT << 3) + 4, + smbus = vt82c686b_pm_init(pci_bus, PCI_DEVFN(FULONG2E_VIA_SLOT, 4), 0xeee1, NULL); eeprom_buf = qemu_mallocz(8 * 256); /* XXX: make this persistent */ memcpy(eeprom_buf, eeprom_spd, sizeof(eeprom_spd)); @@ -376,9 +376,9 @@ static void mips_fulong2e_init(ram_addr_t ram_size, const char *boot_device, DMA_init(0, cpu_exit_irq); /* Super I/O */ - isa_dev = isa_create_simple("i8042"); + isa_create_simple("i8042"); - rtc_state = rtc_init(2000, NULL); + rtc_init(2000, NULL); for(i = 0; i < MAX_SERIAL_PORTS; i++) { if (serial_hds[i]) { diff --git a/hw/mips_int.c b/hw/mips_int.c index c30954caaf..477f6abf95 100644 --- a/hw/mips_int.c +++ b/hw/mips_int.c @@ -24,22 +24,6 @@ #include "mips_cpudevs.h" #include "cpu.h" -/* Raise IRQ to CPU if necessary. It must be called every time the active - IRQ may change */ -void cpu_mips_update_irq(CPUState *env) -{ - if ((env->CP0_Status & (1 << CP0St_IE)) && - !(env->CP0_Status & (1 << CP0St_EXL)) && - !(env->CP0_Status & (1 << CP0St_ERL)) && - !(env->hflags & MIPS_HFLAG_DM)) { - if ((env->CP0_Status & env->CP0_Cause & CP0Ca_IP_mask) && - !(env->interrupt_request & CPU_INTERRUPT_HARD)) { - cpu_interrupt(env, CPU_INTERRUPT_HARD); - } - } else - cpu_reset_interrupt(env, CPU_INTERRUPT_HARD); -} - static void cpu_mips_irq_request(void *opaque, int irq, int level) { CPUState *env = (CPUState *)opaque; @@ -52,7 +36,12 @@ static void cpu_mips_irq_request(void *opaque, int irq, int level) } else { env->CP0_Cause &= ~(1 << (irq + CP0Ca_IP)); } - cpu_mips_update_irq(env); + + if (env->CP0_Cause & CP0Ca_IP_mask) { + cpu_interrupt(env, CPU_INTERRUPT_HARD); + } else { + cpu_reset_interrupt(env, CPU_INTERRUPT_HARD); + } } void cpu_mips_irq_init_cpu(CPUState *env) @@ -65,3 +54,12 @@ void cpu_mips_irq_init_cpu(CPUState *env) env->irq[i] = qi[i]; } } + +void cpu_mips_soft_irq(CPUState *env, int irq, int level) +{ + if (irq < 0 || irq > 2) { + return; + } + + qemu_set_irq(env->irq[irq], level); +} diff --git a/hw/mips_jazz.c b/hw/mips_jazz.c index 71b05a203c..66397c0c9a 100644 --- a/hw/mips_jazz.c +++ b/hw/mips_jazz.c @@ -36,6 +36,7 @@ #include "mips-bios.h" #include "loader.h" #include "mc146818rtc.h" +#include "blockdev.h" enum jazz_model_e { @@ -136,7 +137,7 @@ void mips_jazz_init (ram_addr_t ram_size, NICInfo *nd; PITState *pit; DriveInfo *fds[MAX_FD]; - qemu_irq esp_reset; + qemu_irq esp_reset, dma_enable; qemu_irq *cpu_exit_irq; ram_addr_t ram_offset; ram_addr_t bios_offset; @@ -244,7 +245,7 @@ void mips_jazz_init (ram_addr_t ram_size, /* SCSI adapter */ esp_init(0x80002000, 0, rc4030_dma_read, rc4030_dma_write, dmas[0], - rc4030[5], &esp_reset); + rc4030[5], &esp_reset, &dma_enable); /* Floppy */ if (drive_get_max_bus(IF_FLOPPY) >= MAX_FD) { diff --git a/hw/mips_malta.c b/hw/mips_malta.c index 11e220a944..80260714ec 100644 --- a/hw/mips_malta.c +++ b/hw/mips_malta.c @@ -45,6 +45,7 @@ #include "loader.h" #include "elf.h" #include "mc146818rtc.h" +#include "blockdev.h" //#define DEBUG_BOARD_INIT @@ -653,7 +654,8 @@ static void write_bootloader (CPUState *env, uint8_t *base, } -static void prom_set(uint32_t* prom_buf, int index, const char *string, ...) +static void GCC_FMT_ATTR(3, 4) prom_set(uint32_t* prom_buf, int index, + const char *string, ...) { va_list ap; int32_t table_addr; @@ -727,13 +729,13 @@ static int64_t load_kernel (void) prom_size = ENVP_NB_ENTRIES * (sizeof(int32_t) + ENVP_ENTRY_SIZE); prom_buf = qemu_malloc(prom_size); - prom_set(prom_buf, prom_index++, loaderparams.kernel_filename); + prom_set(prom_buf, prom_index++, "%s", loaderparams.kernel_filename); if (initrd_size > 0) { prom_set(prom_buf, prom_index++, "rd_start=0x%" PRIx64 " rd_size=%li %s", cpu_mips_phys_to_kseg0(NULL, initrd_offset), initrd_size, loaderparams.kernel_cmdline); } else { - prom_set(prom_buf, prom_index++, loaderparams.kernel_cmdline); + prom_set(prom_buf, prom_index++, "%s", loaderparams.kernel_cmdline); } prom_set(prom_buf, prom_index++, "memsize"); @@ -782,11 +784,7 @@ void mips_malta_init (ram_addr_t ram_size, target_long bios_size; int64_t kernel_entry; PCIBus *pci_bus; - ISADevice *isa_dev; CPUState *env; - ISADevice *rtc_state; - FDCtrl *floppy_controller; - MaltaFPGAState *malta_fpga; qemu_irq *i8259; qemu_irq *cpu_exit_irq; int piix4_devfn; @@ -849,7 +847,7 @@ void mips_malta_init (ram_addr_t ram_size, be = 0; #endif /* FPGA */ - malta_fpga = malta_fpga_init(0x1f000000LL, env->irq[2], serial_hds[2]); + malta_fpga_init(0x1f000000LL, env->irq[2], serial_hds[2]); /* Load firmware in flash / BIOS unless we boot directly into a kernel. */ if (kernel_filename) { @@ -955,9 +953,9 @@ void mips_malta_init (ram_addr_t ram_size, DMA_init(0, cpu_exit_irq); /* Super I/O */ - isa_dev = isa_create_simple("i8042"); - - rtc_state = rtc_init(2000, NULL); + isa_create_simple("i8042"); + + rtc_init(2000, NULL); serial_isa_init(0, serial_hds[0]); serial_isa_init(1, serial_hds[1]); if (parallel_hds[0]) @@ -965,7 +963,7 @@ void mips_malta_init (ram_addr_t ram_size, for(i = 0; i < MAX_FD; i++) { fd[i] = drive_get(IF_FLOPPY, 0, i); } - floppy_controller = fdctrl_init_isa(fd); + fdctrl_init_isa(fd); /* Sound card */ audio_init(pci_bus); diff --git a/hw/mips_r4k.c b/hw/mips_r4k.c index 61cd33a93c..aa348904ad 100644 --- a/hw/mips_r4k.c +++ b/hw/mips_r4k.c @@ -22,6 +22,7 @@ #include "loader.h" #include "elf.h" #include "mc146818rtc.h" +#include "blockdev.h" #define MAX_IDE_BUS 2 @@ -166,7 +167,6 @@ void mips_r4k_init (ram_addr_t ram_size, int bios_size; CPUState *env; ResetData *reset_info; - ISADevice *rtc_state; int i; qemu_irq *i8259; DriveInfo *hd[MAX_IDE_BUS * MAX_IDE_DEVS]; @@ -267,7 +267,7 @@ void mips_r4k_init (ram_addr_t ram_size, isa_bus_new(NULL); isa_bus_irqs(i8259); - rtc_state = rtc_init(2000, NULL); + rtc_init(2000, NULL); /* Register 64 KB of ISA IO space at 0x14000000 */ #ifdef TARGET_WORDS_BIGENDIAN diff --git a/hw/mipsnet.c b/hw/mipsnet.c index a95b3ce07b..c5e54ffc35 100644 --- a/hw/mipsnet.c +++ b/hw/mipsnet.c @@ -81,7 +81,7 @@ static ssize_t mipsnet_receive(VLANClientState *nc, const uint8_t *buf, size_t s MIPSnetState *s = DO_UPCAST(NICState, nc, nc)->opaque; #ifdef DEBUG_MIPSNET_RECEIVE - printf("mipsnet: receiving len=%d\n", size); + printf("mipsnet: receiving len=%zu\n", size); #endif if (!mipsnet_can_receive(nc)) return -1; diff --git a/hw/msix.c b/hw/msix.c index b202ff7d85..f66d2550a7 100644 --- a/hw/msix.c +++ b/hw/msix.c @@ -14,6 +14,7 @@ #include "hw.h" #include "msix.h" #include "pci.h" +#include "range.h" /* MSI-X capability structure */ #define MSIX_TABLE_OFFSET 4 diff --git a/hw/multiboot.c b/hw/multiboot.c index dc980e6498..f9097a2f60 100644 --- a/hw/multiboot.c +++ b/hw/multiboot.c @@ -252,7 +252,7 @@ int load_multiboot(void *fw_cfg, do { char *next_space; - uint32_t mb_mod_length; + int mb_mod_length; uint32_t offs = mbs.mb_buf_size; next_initrd = strchr(initrd_filename, ','); diff --git a/hw/musicpal.c b/hw/musicpal.c index 33180a2656..56f27669d2 100644 --- a/hw/musicpal.c +++ b/hw/musicpal.c @@ -18,6 +18,7 @@ #include "flash.h" #include "console.h" #include "i2c.h" +#include "blockdev.h" #define MP_MISC_BASE 0x80002000 #define MP_MISC_SIZE 0x00001000 diff --git a/hw/omap.h b/hw/omap.h index 18eb72b82f..fe32ca5c4c 100644 --- a/hw/omap.h +++ b/hw/omap.h @@ -664,10 +664,12 @@ void omap_synctimer_reset(struct omap_synctimer_s *s); struct omap_uart_s; struct omap_uart_s *omap_uart_init(target_phys_addr_t base, qemu_irq irq, omap_clk fclk, omap_clk iclk, - qemu_irq txdma, qemu_irq rxdma, CharDriverState *chr); + qemu_irq txdma, qemu_irq rxdma, + const char *label, CharDriverState *chr); struct omap_uart_s *omap2_uart_init(struct omap_target_agent_s *ta, qemu_irq irq, omap_clk fclk, omap_clk iclk, - qemu_irq txdma, qemu_irq rxdma, CharDriverState *chr); + qemu_irq txdma, qemu_irq rxdma, + const char *label, CharDriverState *chr); void omap_uart_reset(struct omap_uart_s *s); void omap_uart_attach(struct omap_uart_s *s, CharDriverState *chr); diff --git a/hw/omap1.c b/hw/omap1.c index cf0d428692..f4966f74b6 100644 --- a/hw/omap1.c +++ b/hw/omap1.c @@ -25,6 +25,8 @@ #include "soc_dma.h" /* We use pc-style serial ports. */ #include "pc.h" +#include "blockdev.h" +#include "range.h" /* Should signal the TCMI/GPMC */ uint32_t omap_badwidth_read8(void *opaque, target_phys_addr_t addr) @@ -3668,37 +3670,38 @@ static const struct dma_irq_map omap1_dma_irq_map[] = { static int omap_validate_emiff_addr(struct omap_mpu_state_s *s, target_phys_addr_t addr) { - return addr >= OMAP_EMIFF_BASE && addr < OMAP_EMIFF_BASE + s->sdram_size; + return range_covers_byte(OMAP_EMIFF_BASE, s->sdram_size, addr); } static int omap_validate_emifs_addr(struct omap_mpu_state_s *s, target_phys_addr_t addr) { - return addr >= OMAP_EMIFS_BASE && addr < OMAP_EMIFF_BASE; + return range_covers_byte(OMAP_EMIFS_BASE, OMAP_EMIFF_BASE - OMAP_EMIFS_BASE, + addr); } static int omap_validate_imif_addr(struct omap_mpu_state_s *s, target_phys_addr_t addr) { - return addr >= OMAP_IMIF_BASE && addr < OMAP_IMIF_BASE + s->sram_size; + return range_covers_byte(OMAP_IMIF_BASE, s->sram_size, addr); } static int omap_validate_tipb_addr(struct omap_mpu_state_s *s, target_phys_addr_t addr) { - return addr >= 0xfffb0000 && addr < 0xffff0000; + return range_covers_byte(0xfffb0000, 0xffff0000 - 0xfffb0000, addr); } static int omap_validate_local_addr(struct omap_mpu_state_s *s, target_phys_addr_t addr) { - return addr >= OMAP_LOCALBUS_BASE && addr < OMAP_LOCALBUS_BASE + 0x1000000; + return range_covers_byte(OMAP_LOCALBUS_BASE, 0x1000000, addr); } static int omap_validate_tipb_mpui_addr(struct omap_mpu_state_s *s, target_phys_addr_t addr) { - return addr >= 0xe1010000 && addr < 0xe1020004; + return range_covers_byte(0xe1010000, 0xe1020004 - 0xe1010000, addr); } struct omap_mpu_state_s *omap310_mpu_init(unsigned long sdram_size, @@ -3808,16 +3811,19 @@ struct omap_mpu_state_s *omap310_mpu_init(unsigned long sdram_size, omap_findclk(s, "uart1_ck"), omap_findclk(s, "uart1_ck"), s->drq[OMAP_DMA_UART1_TX], s->drq[OMAP_DMA_UART1_RX], + "uart1", serial_hds[0]); s->uart[1] = omap_uart_init(0xfffb0800, s->irq[1][OMAP_INT_UART2], omap_findclk(s, "uart2_ck"), omap_findclk(s, "uart2_ck"), s->drq[OMAP_DMA_UART2_TX], s->drq[OMAP_DMA_UART2_RX], + "uart2", serial_hds[0] ? serial_hds[1] : NULL); s->uart[2] = omap_uart_init(0xfffb9800, s->irq[0][OMAP_INT_UART3], omap_findclk(s, "uart3_ck"), omap_findclk(s, "uart3_ck"), s->drq[OMAP_DMA_UART3_TX], s->drq[OMAP_DMA_UART3_RX], + "uart3", serial_hds[0] && serial_hds[1] ? serial_hds[2] : NULL); omap_dpll_init(&s->dpll[0], 0xfffecf00, omap_findclk(s, "dpll1")); diff --git a/hw/omap2.c b/hw/omap2.c index 179075e996..e35a56e043 100644 --- a/hw/omap2.c +++ b/hw/omap2.c @@ -2291,13 +2291,16 @@ struct omap_mpu_state_s *omap2420_mpu_init(unsigned long sdram_size, omap_findclk(s, "uart1_fclk"), omap_findclk(s, "uart1_iclk"), s->drq[OMAP24XX_DMA_UART1_TX], - s->drq[OMAP24XX_DMA_UART1_RX], serial_hds[0]); + s->drq[OMAP24XX_DMA_UART1_RX], + "uart1", + serial_hds[0]); s->uart[1] = omap2_uart_init(omap_l4ta(s->l4, 20), s->irq[0][OMAP_INT_24XX_UART2_IRQ], omap_findclk(s, "uart2_fclk"), omap_findclk(s, "uart2_iclk"), s->drq[OMAP24XX_DMA_UART2_TX], s->drq[OMAP24XX_DMA_UART2_RX], + "uart2", serial_hds[0] ? serial_hds[1] : NULL); s->uart[2] = omap2_uart_init(omap_l4ta(s->l4, 21), s->irq[0][OMAP_INT_24XX_UART3_IRQ], @@ -2305,6 +2308,7 @@ struct omap_mpu_state_s *omap2420_mpu_init(unsigned long sdram_size, omap_findclk(s, "uart3_iclk"), s->drq[OMAP24XX_DMA_UART3_TX], s->drq[OMAP24XX_DMA_UART3_RX], + "uart3", serial_hds[0] && serial_hds[1] ? serial_hds[2] : NULL); s->gptimer[0] = omap_gp_timer_init(omap_l4ta(s->l4, 7), diff --git a/hw/omap_clk.c b/hw/omap_clk.c index 6bcabef8ac..10c9c4308c 100644 --- a/hw/omap_clk.c +++ b/hw/omap_clk.c @@ -20,6 +20,7 @@ */ #include "hw.h" #include "omap.h" +#include "qemu-timer.h" /* for muldiv64() */ struct clk { const char *name; diff --git a/hw/omap_i2c.c b/hw/omap_i2c.c index d7c18882da..d133977e7f 100644 --- a/hw/omap_i2c.c +++ b/hw/omap_i2c.c @@ -190,8 +190,9 @@ static uint32_t omap_i2c_read(void *opaque, target_phys_addr_t addr) if (s->rxlen > 2) s->fifo >>= 16; s->rxlen -= 2; - } else - /* XXX: remote access (qualifier) error - what's that? */; + } else { + /* XXX: remote access (qualifier) error - what's that? */ + } if (!s->rxlen) { s->stat &= ~(1 << 3); /* RRDY */ if (((s->control >> 10) & 1) && /* MST */ diff --git a/hw/omap_mmc.c b/hw/omap_mmc.c index 15cbf06c87..9d167ff535 100644 --- a/hw/omap_mmc.c +++ b/hw/omap_mmc.c @@ -559,8 +559,9 @@ static void omap_mmc_cover_cb(void *opaque, int line, int level) if (!host->cdet_state && level) { host->status |= 0x0002; omap_mmc_interrupts_update(host); - if (host->cdet_wakeup) - /* TODO: Assert wake-up */; + if (host->cdet_wakeup) { + /* TODO: Assert wake-up */ + } } if (host->cdet_state != level) { diff --git a/hw/omap_sx1.c b/hw/omap_sx1.c index c3f197393d..44dc514f3f 100644 --- a/hw/omap_sx1.c +++ b/hw/omap_sx1.c @@ -32,6 +32,7 @@ #include "boards.h" #include "arm-misc.h" #include "flash.h" +#include "blockdev.h" /*****************************************************************************/ /* Siemens SX1 Cellphone V1 */ diff --git a/hw/omap_uart.c b/hw/omap_uart.c index 395bf0ccbb..cc66cd9d94 100644 --- a/hw/omap_uart.c +++ b/hw/omap_uart.c @@ -51,7 +51,8 @@ void omap_uart_reset(struct omap_uart_s *s) struct omap_uart_s *omap_uart_init(target_phys_addr_t base, qemu_irq irq, omap_clk fclk, omap_clk iclk, - qemu_irq txdma, qemu_irq rxdma, CharDriverState *chr) + qemu_irq txdma, qemu_irq rxdma, + const char *label, CharDriverState *chr) { struct omap_uart_s *s = (struct omap_uart_s *) qemu_mallocz(sizeof(struct omap_uart_s)); @@ -61,11 +62,11 @@ struct omap_uart_s *omap_uart_init(target_phys_addr_t base, s->irq = irq; #ifdef TARGET_WORDS_BIGENDIAN s->serial = serial_mm_init(base, 2, irq, omap_clk_getrate(fclk)/16, - chr ?: qemu_chr_open("null", "null", NULL), 1, + chr ?: qemu_chr_open(label, "null", NULL), 1, 1); #else s->serial = serial_mm_init(base, 2, irq, omap_clk_getrate(fclk)/16, - chr ?: qemu_chr_open("null", "null", NULL), 1, + chr ?: qemu_chr_open(label, "null", NULL), 1, 0); #endif return s; @@ -162,11 +163,12 @@ static CPUWriteMemoryFunc * const omap_uart_writefn[] = { struct omap_uart_s *omap2_uart_init(struct omap_target_agent_s *ta, qemu_irq irq, omap_clk fclk, omap_clk iclk, - qemu_irq txdma, qemu_irq rxdma, CharDriverState *chr) + qemu_irq txdma, qemu_irq rxdma, + const char *label, CharDriverState *chr) { target_phys_addr_t base = omap_l4_attach(ta, 0, 0); struct omap_uart_s *s = omap_uart_init(base, irq, - fclk, iclk, txdma, rxdma, chr); + fclk, iclk, txdma, rxdma, label, chr); int iomemtype = cpu_register_io_memory(omap_uart_readfn, omap_uart_writefn, s); diff --git a/hw/pc.c b/hw/pc.c index a96187f5b5..69b13bf62c 100644 --- a/hw/pc.c +++ b/hw/pc.c @@ -39,6 +39,7 @@ #include "msix.h" #include "sysbus.h" #include "sysemu.h" +#include "blockdev.h" /* output Bochs bios info messages */ //#define DEBUG_BIOS @@ -916,8 +917,10 @@ void pc_memory_init(ram_addr_t ram_size, below_4g_mem_size - 0x100000, ram_addr + 0x100000); #if TARGET_PHYS_ADDR_BITS > 32 - cpu_register_physical_memory(0x100000000ULL, above_4g_mem_size, - ram_addr + below_4g_mem_size); + if (above_4g_mem_size > 0) { + cpu_register_physical_memory(0x100000000ULL, above_4g_mem_size, + ram_addr + below_4g_mem_size); + } #endif /* BIOS load */ diff --git a/hw/pc_piix.c b/hw/pc_piix.c index 519e8a5ccb..12359a75c9 100644 --- a/hw/pc_piix.c +++ b/hw/pc_piix.c @@ -34,6 +34,7 @@ #include "kvm.h" #include "sysemu.h" #include "sysbus.h" +#include "blockdev.h" #define MAX_IDE_BUS 2 @@ -103,6 +104,7 @@ static void pc_init1(ram_addr_t ram_size, pci_bus = i440fx_init(&i440fx_state, &piix3_devfn, isa_irq, ram_size); } else { pci_bus = NULL; + i440fx_state = NULL; isa_bus_new(NULL); } isa_bus_irqs(isa_irq); @@ -226,7 +228,7 @@ static QEMUMachine pc_machine_v0_12 = { .compat_props = (GlobalProperty[]) { { .driver = "virtio-serial-pci", - .property = "max_nr_ports", + .property = "max_ports", .value = stringify(1), },{ .driver = "virtio-serial-pci", @@ -249,7 +251,7 @@ static QEMUMachine pc_machine_v0_11 = { .value = stringify(0), },{ .driver = "virtio-serial-pci", - .property = "max_nr_ports", + .property = "max_ports", .value = stringify(1), },{ .driver = "virtio-serial-pci", @@ -288,7 +290,7 @@ static QEMUMachine pc_machine_v0_10 = { .value = stringify(PCI_CLASS_DISPLAY_OTHER), },{ .driver = "virtio-serial-pci", - .property = "max_nr_ports", + .property = "max_ports", .value = stringify(1), },{ .driver = "virtio-serial-pci", diff --git a/hw/pci-hotplug.c b/hw/pci-hotplug.c index c38f47fbf1..716133c376 100644 --- a/hw/pci-hotplug.c +++ b/hw/pci-hotplug.c @@ -31,6 +31,7 @@ #include "scsi.h" #include "virtio-blk.h" #include "qemu-config.h" +#include "blockdev.h" #if defined(TARGET_I386) static PCIDevice *qemu_pci_hot_add_nic(Monitor *mon, @@ -51,7 +52,7 @@ static PCIDevice *qemu_pci_hot_add_nic(Monitor *mon, return NULL; } - opts = qemu_opts_parse(&qemu_net_opts, opts_str ? opts_str : "", 0); + opts = qemu_opts_parse(qemu_find_opts("net"), opts_str ? opts_str : "", 0); if (!opts) { return NULL; } diff --git a/hw/pci.c b/hw/pci.c index 5386f5a083..962886e767 100644 --- a/hw/pci.c +++ b/hw/pci.c @@ -32,6 +32,7 @@ #include "sysemu.h" #include "loader.h" #include "qemu-objects.h" +#include "range.h" //#define DEBUG_PCI #ifdef DEBUG_PCI @@ -585,7 +586,7 @@ static int pci_init_multifunction(PCIBus *bus, PCIDevice *dev) } /* - * multifuction bit is interpreted in two ways as follows. + * multifunction bit is interpreted in two ways as follows. * - all functions must set the bit to 1. * Example: Intel X53 * - function 0 must set the bit, but the rest function (> 0) diff --git a/hw/pci.h b/hw/pci.h index d6c522b8dd..7100804e7c 100644 --- a/hw/pci.h +++ b/hw/pci.h @@ -448,33 +448,4 @@ static inline uint32_t pci_config_size(const PCIDevice *d) return pci_is_express(d) ? PCIE_CONFIG_SPACE_SIZE : PCI_CONFIG_SPACE_SIZE; } -/* These are not pci specific. Should move into a separate header. - * Only pci.c uses them, so keep them here for now. - */ - -/* Get last byte of a range from offset + length. - * Undefined for ranges that wrap around 0. */ -static inline uint64_t range_get_last(uint64_t offset, uint64_t len) -{ - return offset + len - 1; -} - -/* Check whether a given range covers a given byte. */ -static inline int range_covers_byte(uint64_t offset, uint64_t len, - uint64_t byte) -{ - return offset <= byte && byte <= range_get_last(offset, len); -} - -/* Check whether 2 given ranges overlap. - * Undefined if ranges that wrap around 0. */ -static inline int ranges_overlap(uint64_t first1, uint64_t len1, - uint64_t first2, uint64_t len2) -{ - uint64_t last1 = range_get_last(first1, len1); - uint64_t last2 = range_get_last(first2, len2); - - return !(last2 < first1 || last1 < first2); -} - #endif diff --git a/hw/pckbd.c b/hw/pckbd.c index 0533b1d9e3..6e4e4062ad 100644 --- a/hw/pckbd.c +++ b/hw/pckbd.c @@ -56,7 +56,9 @@ #define KBD_CCMD_WRITE_MOUSE 0xD4 /* Write the following byte to the mouse */ #define KBD_CCMD_DISABLE_A20 0xDD /* HP vectra only ? */ #define KBD_CCMD_ENABLE_A20 0xDF /* HP vectra only ? */ -#define KBD_CCMD_RESET 0xFE +#define KBD_CCMD_PULSE_BITS_3_0 0xF0 /* Pulse bits 3-0 of the output port P2. */ +#define KBD_CCMD_RESET 0xFE /* Pulse bit 0 of the output port P2 = CPU reset. */ +#define KBD_CCMD_NO_OP 0xFF /* Pulse no bits of the output port P2. */ /* Keyboard Commands */ #define KBD_CMD_SET_LEDS 0xED /* Set keyboard leds */ @@ -238,6 +240,21 @@ static void kbd_write_command(void *opaque, uint32_t addr, uint32_t val) KBDState *s = opaque; DPRINTF("kbd: write cmd=0x%02x\n", val); + + /* Bits 3-0 of the output port P2 of the keyboard controller may be pulsed + * low for approximately 6 micro seconds. Bits 3-0 of the KBD_CCMD_PULSE + * command specify the output port bits to be pulsed. + * 0: Bit should be pulsed. 1: Bit should not be modified. + * The only useful version of this command is pulsing bit 0, + * which does a CPU reset. + */ + if((val & KBD_CCMD_PULSE_BITS_3_0) == KBD_CCMD_PULSE_BITS_3_0) { + if(!(val & 1)) + val = KBD_CCMD_RESET; + else + val = KBD_CCMD_NO_OP; + } + switch(val) { case KBD_CCMD_READ_MODE: kbd_queue(s, s->mode, 0); @@ -294,8 +311,8 @@ static void kbd_write_command(void *opaque, uint32_t addr, uint32_t val) case KBD_CCMD_RESET: qemu_system_reset_request(); break; - case 0xff: - /* ignore that - I don't know what is its use */ + case KBD_CCMD_NO_OP: + /* ignore that */ break; default: fprintf(stderr, "qemu: unsupported keyboard cmd=0x%02x\n", val); diff --git a/hw/pcmcia.h b/hw/pcmcia.h index 360292395b..50648c973f 100644 --- a/hw/pcmcia.h +++ b/hw/pcmcia.h @@ -1,7 +1,6 @@ /* PCMCIA/Cardbus */ #include "qemu-common.h" -#include "blockdev.h" typedef struct { qemu_irq irq; diff --git a/hw/petalogix_s3adsp1800_mmu.c b/hw/petalogix_s3adsp1800_mmu.c index 70b6a36e1e..42de45963b 100644 --- a/hw/petalogix_s3adsp1800_mmu.c +++ b/hw/petalogix_s3adsp1800_mmu.c @@ -34,6 +34,7 @@ #include "xilinx.h" #include "loader.h" #include "elf.h" +#include "blockdev.h" #define LMB_BRAM_SIZE (128 * 1024) #define FLASH_SIZE (16 * 1024 * 1024) @@ -179,11 +180,22 @@ petalogix_s3adsp1800_init(ram_addr_t ram_size, } /* Always boot into physical ram. */ boot_info.bootstrap_pc = ddr_base + (entry & 0x0fffffff); + + /* If it wasn't an ELF image, try an u-boot image. */ + if (kernel_size < 0) { + target_phys_addr_t uentry, loadaddr; + + kernel_size = load_uimage(kernel_filename, &uentry, &loadaddr, 0); + boot_info.bootstrap_pc = uentry; + high = (loadaddr + kernel_size + 3) & ~3; + } + + /* Not an ELF image nor an u-boot image, try a RAW image. */ if (kernel_size < 0) { - /* If we failed loading ELF's try a raw image. */ kernel_size = load_image_targphys(kernel_filename, ddr_base, ram_size); boot_info.bootstrap_pc = ddr_base; + high = (ddr_base + kernel_size + 3) & ~3; } boot_info.cmdline = high + 4096; diff --git a/hw/piix_pci.c b/hw/piix_pci.c index f152a0ff06..b5589b9035 100644 --- a/hw/piix_pci.c +++ b/hw/piix_pci.c @@ -28,6 +28,7 @@ #include "pci_host.h" #include "isa.h" #include "sysbus.h" +#include "range.h" /* * I440FX chipset data sheet. diff --git a/hw/ppc.c b/hw/ppc.c index 2a77eb9bff..968aec1b16 100644 --- a/hw/ppc.c +++ b/hw/ppc.c @@ -28,6 +28,8 @@ #include "nvram.h" #include "qemu-log.h" #include "loader.h" +#include "kvm.h" +#include "kvm_ppc.h" //#define PPC_DEBUG_IRQ //#define PPC_DEBUG_TB @@ -50,6 +52,8 @@ static void cpu_ppc_tb_start (CPUState *env); static void ppc_set_irq (CPUState *env, int n_IRQ, int level) { + unsigned int old_pending = env->pending_interrupts; + if (level) { env->pending_interrupts |= 1 << n_IRQ; cpu_interrupt(env, CPU_INTERRUPT_HARD); @@ -58,6 +62,13 @@ static void ppc_set_irq (CPUState *env, int n_IRQ, int level) if (env->pending_interrupts == 0) cpu_reset_interrupt(env, CPU_INTERRUPT_HARD); } + + if (old_pending != env->pending_interrupts) { +#ifdef CONFIG_KVM + kvmppc_set_interrupt(env, n_IRQ, level); +#endif + } + LOG_IRQ("%s: %p n_IRQ %d level %d => pending %08" PRIx32 "req %08x\n", __func__, env, n_IRQ, level, env->pending_interrupts, env->interrupt_request); @@ -758,6 +769,9 @@ struct ppcemb_timer_t { struct QEMUTimer *fit_timer; uint64_t wdt_next; /* Tick for next WDT interrupt */ struct QEMUTimer *wdt_timer; + + /* 405 have the PIT, 440 have a DECR. */ + unsigned int decr_excp; }; /* Fixed interval timer */ @@ -840,7 +854,7 @@ static void cpu_4xx_pit_cb (void *opaque) ppcemb_timer = tb_env->opaque; env->spr[SPR_40x_TSR] |= 1 << 27; if ((env->spr[SPR_40x_TCR] >> 26) & 0x1) - ppc_set_irq(env, PPC_INTERRUPT_PIT, 1); + ppc_set_irq(env, ppcemb_timer->decr_excp, 1); start_stop_pit(env, tb_env, 1); LOG_TB("%s: ar %d ir %d TCR " TARGET_FMT_lx " TSR " TARGET_FMT_lx " " "%016" PRIx64 "\n", __func__, @@ -937,10 +951,15 @@ target_ulong load_40x_pit (CPUState *env) void store_booke_tsr (CPUState *env, target_ulong val) { + ppc_tb_t *tb_env = env->tb_env; + ppcemb_timer_t *ppcemb_timer; + + ppcemb_timer = tb_env->opaque; + LOG_TB("%s: val " TARGET_FMT_lx "\n", __func__, val); env->spr[SPR_40x_TSR] &= ~(val & 0xFC000000); if (val & 0x80000000) - ppc_set_irq(env, PPC_INTERRUPT_PIT, 0); + ppc_set_irq(env, ppcemb_timer->decr_excp, 0); } void store_booke_tcr (CPUState *env, target_ulong val) @@ -966,7 +985,8 @@ static void ppc_emb_set_tb_clk (void *opaque, uint32_t freq) /* XXX: we should also update all timers */ } -clk_setup_cb ppc_emb_timers_init (CPUState *env, uint32_t freq) +clk_setup_cb ppc_emb_timers_init (CPUState *env, uint32_t freq, + unsigned int decr_excp) { ppc_tb_t *tb_env; ppcemb_timer_t *ppcemb_timer; @@ -985,6 +1005,7 @@ clk_setup_cb ppc_emb_timers_init (CPUState *env, uint32_t freq) qemu_new_timer(vm_clock, &cpu_4xx_fit_cb, env); ppcemb_timer->wdt_timer = qemu_new_timer(vm_clock, &cpu_4xx_wdt_cb, env); + ppcemb_timer->decr_excp = decr_excp; } return &ppc_emb_set_tb_clk; diff --git a/hw/ppc.h b/hw/ppc.h index de13092ae4..34f54cf5da 100644 --- a/hw/ppc.h +++ b/hw/ppc.h @@ -19,7 +19,9 @@ int ppc_dcr_init (CPUState *env, int (*dcr_read_error)(int dcrn), int (*dcr_write_error)(int dcrn)); int ppc_dcr_register (CPUState *env, int dcrn, void *opaque, dcr_read_cb drc_read, dcr_write_cb dcr_write); -clk_setup_cb ppc_emb_timers_init (CPUState *env, uint32_t freq); +clk_setup_cb ppc_emb_timers_init (CPUState *env, uint32_t freq, + unsigned int decr_excp); + /* Embedded PowerPC reset */ void ppc40x_core_reset (CPUState *env); void ppc40x_chip_reset (CPUState *env); @@ -47,5 +49,8 @@ enum { #define FW_CFG_PPC_HEIGHT (FW_CFG_ARCH_LOCAL + 0x01) #define FW_CFG_PPC_DEPTH (FW_CFG_ARCH_LOCAL + 0x02) #define FW_CFG_PPC_TBFREQ (FW_CFG_ARCH_LOCAL + 0x03) +#define FW_CFG_PPC_IS_KVM (FW_CFG_ARCH_LOCAL + 0x05) +#define FW_CFG_PPC_KVM_HC (FW_CFG_ARCH_LOCAL + 0x06) +#define FW_CFG_PPC_KVM_PID (FW_CFG_ARCH_LOCAL + 0x07) #define PPC_SERIAL_MM_BAUDBASE 399193 diff --git a/hw/ppc405_boards.c b/hw/ppc405_boards.c index 40ff1b34ea..c5897a9d4d 100644 --- a/hw/ppc405_boards.c +++ b/hw/ppc405_boards.c @@ -31,6 +31,7 @@ #include "boards.h" #include "qemu-log.h" #include "loader.h" +#include "blockdev.h" #define BIOS_FILENAME "ppc405_rom.bin" #define BIOS_SIZE (2048 * 1024) @@ -181,10 +182,12 @@ static void ref405ep_init (ram_addr_t ram_size, qemu_irq *pic; ram_addr_t sram_offset, bios_offset, bdloc; target_phys_addr_t ram_bases[2], ram_sizes[2]; - target_ulong sram_size, bios_size; + target_ulong sram_size; + long bios_size; //int phy_addr = 0; //static int phy_addr = 1; - target_ulong kernel_base, kernel_size, initrd_base, initrd_size; + target_ulong kernel_base, initrd_base; + long kernel_size, initrd_size; int linux_boot; int fl_idx, fl_sectors, len; DriveInfo *dinfo; @@ -220,8 +223,8 @@ static void ref405ep_init (ram_addr_t ram_size, bios_offset = qemu_ram_alloc(NULL, "ef405ep.bios", bios_size); fl_sectors = (bios_size + 65535) >> 16; #ifdef DEBUG_BOARD_INIT - printf("Register parallel flash %d size " TARGET_FMT_lx - " at offset %08lx addr " TARGET_FMT_lx " '%s' %d\n", + printf("Register parallel flash %d size %lx" + " at offset %08lx addr %lx '%s' %d\n", fl_idx, bios_size, bios_offset, -bios_size, bdrv_get_device_name(dinfo->bdrv), fl_sectors); #endif @@ -307,7 +310,7 @@ static void ref405ep_init (ram_addr_t ram_size, kernel_filename); exit(1); } - printf("Load kernel size " TARGET_FMT_ld " at " TARGET_FMT_lx, + printf("Load kernel size %ld at " TARGET_FMT_lx, kernel_size, kernel_base); /* load initrd */ if (initrd_filename) { @@ -498,12 +501,12 @@ static void taihu_405ep_init(ram_addr_t ram_size, const char *cpu_model) { char *filename; - CPUPPCState *env; qemu_irq *pic; ram_addr_t bios_offset; target_phys_addr_t ram_bases[2], ram_sizes[2]; - target_ulong bios_size; - target_ulong kernel_base, kernel_size, initrd_base, initrd_size; + long bios_size; + target_ulong kernel_base, initrd_base; + long kernel_size, initrd_size; int linux_boot; int fl_idx, fl_sectors; DriveInfo *dinfo; @@ -517,8 +520,8 @@ static void taihu_405ep_init(ram_addr_t ram_size, #ifdef DEBUG_BOARD_INIT printf("%s: register cpu\n", __func__); #endif - env = ppc405ep_init(ram_bases, ram_sizes, 33333333, &pic, - kernel_filename == NULL ? 0 : 1); + ppc405ep_init(ram_bases, ram_sizes, 33333333, &pic, + kernel_filename == NULL ? 0 : 1); /* allocate and load BIOS */ #ifdef DEBUG_BOARD_INIT printf("%s: register BIOS\n", __func__); @@ -533,8 +536,8 @@ static void taihu_405ep_init(ram_addr_t ram_size, fl_sectors = (bios_size + 65535) >> 16; bios_offset = qemu_ram_alloc(NULL, "taihu_405ep.bios", bios_size); #ifdef DEBUG_BOARD_INIT - printf("Register parallel flash %d size " TARGET_FMT_lx - " at offset %08lx addr " TARGET_FMT_lx " '%s' %d\n", + printf("Register parallel flash %d size %lx" + " at offset %08lx addr %lx '%s' %d\n", fl_idx, bios_size, bios_offset, -bios_size, bdrv_get_device_name(dinfo->bdrv), fl_sectors); #endif @@ -575,7 +578,7 @@ static void taihu_405ep_init(ram_addr_t ram_size, bios_size = 32 * 1024 * 1024; fl_sectors = (bios_size + 65535) >> 16; #ifdef DEBUG_BOARD_INIT - printf("Register parallel flash %d size " TARGET_FMT_lx + printf("Register parallel flash %d size %lx" " at offset %08lx addr " TARGET_FMT_lx " '%s'\n", fl_idx, bios_size, bios_offset, (target_ulong)0xfc000000, bdrv_get_device_name(dinfo->bdrv)); diff --git a/hw/ppc405_uc.c b/hw/ppc405_uc.c index b884ea5fbd..3600737412 100644 --- a/hw/ppc405_uc.c +++ b/hw/ppc405_uc.c @@ -630,18 +630,11 @@ struct ppc405_dma_t { static uint32_t dcr_read_dma (void *opaque, int dcrn) { - ppc405_dma_t *dma; - - dma = opaque; - return 0; } static void dcr_write_dma (void *opaque, int dcrn, uint32_t val) { - ppc405_dma_t *dma; - - dma = opaque; } static void ppc405_dma_reset (void *opaque) @@ -739,9 +732,6 @@ struct ppc405_gpio_t { static uint32_t ppc405_gpio_readb (void *opaque, target_phys_addr_t addr) { - ppc405_gpio_t *gpio; - - gpio = opaque; #ifdef DEBUG_GPIO printf("%s: addr " TARGET_FMT_plx "\n", __func__, addr); #endif @@ -752,9 +742,6 @@ static uint32_t ppc405_gpio_readb (void *opaque, target_phys_addr_t addr) static void ppc405_gpio_writeb (void *opaque, target_phys_addr_t addr, uint32_t value) { - ppc405_gpio_t *gpio; - - gpio = opaque; #ifdef DEBUG_GPIO printf("%s: addr " TARGET_FMT_plx " val %08" PRIx32 "\n", __func__, addr, value); @@ -763,9 +750,6 @@ static void ppc405_gpio_writeb (void *opaque, static uint32_t ppc405_gpio_readw (void *opaque, target_phys_addr_t addr) { - ppc405_gpio_t *gpio; - - gpio = opaque; #ifdef DEBUG_GPIO printf("%s: addr " TARGET_FMT_plx "\n", __func__, addr); #endif @@ -776,9 +760,6 @@ static uint32_t ppc405_gpio_readw (void *opaque, target_phys_addr_t addr) static void ppc405_gpio_writew (void *opaque, target_phys_addr_t addr, uint32_t value) { - ppc405_gpio_t *gpio; - - gpio = opaque; #ifdef DEBUG_GPIO printf("%s: addr " TARGET_FMT_plx " val %08" PRIx32 "\n", __func__, addr, value); @@ -787,9 +768,6 @@ static void ppc405_gpio_writew (void *opaque, static uint32_t ppc405_gpio_readl (void *opaque, target_phys_addr_t addr) { - ppc405_gpio_t *gpio; - - gpio = opaque; #ifdef DEBUG_GPIO printf("%s: addr " TARGET_FMT_plx "\n", __func__, addr); #endif @@ -800,9 +778,6 @@ static uint32_t ppc405_gpio_readl (void *opaque, target_phys_addr_t addr) static void ppc405_gpio_writel (void *opaque, target_phys_addr_t addr, uint32_t value) { - ppc405_gpio_t *gpio; - - gpio = opaque; #ifdef DEBUG_GPIO printf("%s: addr " TARGET_FMT_plx " val %08" PRIx32 "\n", __func__, addr, value); @@ -823,9 +798,6 @@ static CPUWriteMemoryFunc * const ppc405_gpio_write[] = { static void ppc405_gpio_reset (void *opaque) { - ppc405_gpio_t *gpio; - - gpio = opaque; } static void ppc405_gpio_init(target_phys_addr_t base) diff --git a/hw/ppc440_bamboo.c b/hw/ppc440_bamboo.c index 6ca873ee7e..34ddf45477 100644 --- a/hw/ppc440_bamboo.c +++ b/hw/ppc440_bamboo.c @@ -27,6 +27,11 @@ #define BINARY_DEVICE_TREE_FILE "bamboo.dtb" +/* from u-boot */ +#define KERNEL_ADDR 0x1000000 +#define FDT_ADDR 0x1800000 +#define RAMDISK_ADDR 0x1900000 + static int bamboo_load_device_tree(target_phys_addr_t addr, uint32_t ramsize, target_phys_addr_t initrd_base, @@ -98,10 +103,8 @@ static void bamboo_init(ram_addr_t ram_size, uint64_t elf_lowaddr; target_phys_addr_t entry = 0; target_phys_addr_t loadaddr = 0; - target_long kernel_size = 0; - target_ulong initrd_base = 0; target_long initrd_size = 0; - target_ulong dt_base = 0; + int success; int i; /* Setup CPU. */ @@ -118,15 +121,15 @@ static void bamboo_init(ram_addr_t ram_size, /* Load kernel. */ if (kernel_filename) { - kernel_size = load_uimage(kernel_filename, &entry, &loadaddr, NULL); - if (kernel_size < 0) { - kernel_size = load_elf(kernel_filename, NULL, NULL, &elf_entry, - &elf_lowaddr, NULL, 1, ELF_MACHINE, 0); + success = load_uimage(kernel_filename, &entry, &loadaddr, NULL); + if (success < 0) { + success = load_elf(kernel_filename, NULL, NULL, &elf_entry, + &elf_lowaddr, NULL, 1, ELF_MACHINE, 0); entry = elf_entry; loadaddr = elf_lowaddr; } /* XXX try again as binary */ - if (kernel_size < 0) { + if (success < 0) { fprintf(stderr, "qemu: could not load kernel '%s'\n", kernel_filename); exit(1); @@ -135,26 +138,20 @@ static void bamboo_init(ram_addr_t ram_size, /* Load initrd. */ if (initrd_filename) { - initrd_base = kernel_size + loadaddr; - initrd_size = load_image_targphys(initrd_filename, initrd_base, - ram_size - initrd_base); + initrd_size = load_image_targphys(initrd_filename, RAMDISK_ADDR, + ram_size - RAMDISK_ADDR); if (initrd_size < 0) { - fprintf(stderr, "qemu: could not load initial ram disk '%s'\n", - initrd_filename); + fprintf(stderr, "qemu: could not load ram disk '%s' at %x\n", + initrd_filename, RAMDISK_ADDR); exit(1); } } /* If we're loading a kernel directly, we must load the device tree too. */ if (kernel_filename) { - if (initrd_base) - dt_base = initrd_base + initrd_size; - else - dt_base = kernel_size + loadaddr; - - if (bamboo_load_device_tree(dt_base, ram_size, - initrd_base, initrd_size, kernel_cmdline) < 0) { + if (bamboo_load_device_tree(FDT_ADDR, ram_size, RAMDISK_ADDR, + initrd_size, kernel_cmdline) < 0) { fprintf(stderr, "couldn't load device tree\n"); exit(1); } @@ -163,7 +160,7 @@ static void bamboo_init(ram_addr_t ram_size, /* Set initial guest state. */ env->gpr[1] = (16<<20) - 8; - env->gpr[3] = dt_base; + env->gpr[3] = FDT_ADDR; env->nip = entry; /* XXX we currently depend on KVM to create some initial TLB entries. */ } @@ -186,7 +183,7 @@ static QEMUMachine bamboo_machine_v0_12 = { .compat_props = (GlobalProperty[]) { { .driver = "virtio-serial-pci", - .property = "max_nr_ports", + .property = "max_ports", .value = stringify(1), },{ .driver = "virtio-serial-pci", diff --git a/hw/ppc4xx_devs.c b/hw/ppc4xx_devs.c index b15db81b6a..5f581fe2c4 100644 --- a/hw/ppc4xx_devs.c +++ b/hw/ppc4xx_devs.c @@ -56,7 +56,7 @@ CPUState *ppc4xx_init (const char *cpu_model, cpu_clk->cb = NULL; /* We don't care about CPU clock frequency changes */ cpu_clk->opaque = env; /* Set time-base frequency to sysclk */ - tb_clk->cb = ppc_emb_timers_init(env, sysclk); + tb_clk->cb = ppc_emb_timers_init(env, sysclk, PPC_INTERRUPT_PIT); tb_clk->opaque = env; ppc_dcr_init(env, NULL, NULL); /* Register qemu callbacks */ @@ -619,7 +619,6 @@ static void sdram_reset (void *opaque) /* We pre-initialize RAM banks */ sdram->status = 0x00000000; sdram->cfg = 0x00800000; - sdram_unmap_bcr(sdram); } void ppc4xx_sdram_init (CPUState *env, qemu_irq irq, int nbanks, @@ -684,7 +683,7 @@ ram_addr_t ppc4xx_sdram_adjust(ram_addr_t ram_size, int nr_banks, } ram_size -= size_left; - if (ram_size) + if (size_left) printf("Truncating memory to %d MiB to fit SDRAM controller limits.\n", (int)(ram_size >> 20)); diff --git a/hw/ppc_mac.h b/hw/ppc_mac.h index 89f96bbc34..ea8759324c 100644 --- a/hw/ppc_mac.h +++ b/hw/ppc_mac.h @@ -30,7 +30,6 @@ #define BIOS_SIZE (1024 * 1024) #define BIOS_FILENAME "ppc_rom.bin" -#define VGABIOS_FILENAME "video.x" #define NVRAM_SIZE 0x2000 #define PROM_FILENAME "openbios-ppc" #define PROM_ADDR 0xfff00000 diff --git a/hw/ppc_newworld.c b/hw/ppc_newworld.c index fbba9b6fb2..4369337b21 100644 --- a/hw/ppc_newworld.c +++ b/hw/ppc_newworld.c @@ -66,9 +66,9 @@ #include "kvm.h" #include "kvm_ppc.h" #include "hw/usb.h" +#include "blockdev.h" #define MAX_IDE_BUS 2 -#define VGA_BIOS_SIZE 65536 #define CFG_ADDR 0xf0000510 /* debug UniNorth */ @@ -128,24 +128,24 @@ static void ppc_core99_init (ram_addr_t ram_size, const char *initrd_filename, const char *cpu_model) { - CPUState *env = NULL, *envs[MAX_CPUS]; + CPUState *env = NULL; char *filename; qemu_irq *pic, **openpic_irqs; int unin_memory; int linux_boot, i; - ram_addr_t ram_offset, bios_offset, vga_bios_offset; - uint32_t kernel_base, kernel_size, initrd_base, initrd_size; + ram_addr_t ram_offset, bios_offset; + uint32_t kernel_base, initrd_base; + long kernel_size, initrd_size; PCIBus *pci_bus; MacIONVRAMState *nvr; int nvram_mem_index; - int vga_bios_size, bios_size; + int bios_size; int pic_mem_index, dbdma_mem_index, cuda_mem_index, escc_mem_index; int ide_mem_index[3]; int ppc_boot_device; DriveInfo *hd[MAX_IDE_BUS * MAX_IDE_DEVS]; void *fw_cfg; void *dbdma; - uint8_t *vga_bios_ptr; int machine_arch; linux_boot = (kernel_filename != NULL); @@ -165,11 +165,7 @@ static void ppc_core99_init (ram_addr_t ram_size, } /* Set time-base frequency to 100 Mhz */ cpu_ppc_tb_init(env, 100UL * 1000UL * 1000UL); -#if 0 - env->osi_call = vga_osi_call; -#endif qemu_register_reset((QEMUResetHandler*)&cpu_reset, env); - envs[i] = env; } /* allocate RAM */ @@ -197,36 +193,6 @@ static void ppc_core99_init (ram_addr_t ram_size, exit(1); } - /* allocate and load VGA BIOS */ - vga_bios_offset = qemu_ram_alloc(NULL, "ppc_core99.vbios", VGA_BIOS_SIZE); - vga_bios_ptr = qemu_get_ram_ptr(vga_bios_offset); - filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, VGABIOS_FILENAME); - if (filename) { - vga_bios_size = load_image(filename, vga_bios_ptr + 8); - qemu_free(filename); - } else { - vga_bios_size = -1; - } - if (vga_bios_size < 0) { - /* if no bios is present, we can still work */ - fprintf(stderr, "qemu: warning: could not load VGA bios '%s'\n", - VGABIOS_FILENAME); - vga_bios_size = 0; - } else { - /* set a specific header (XXX: find real Apple format for NDRV - drivers) */ - vga_bios_ptr[0] = 'N'; - vga_bios_ptr[1] = 'D'; - vga_bios_ptr[2] = 'R'; - vga_bios_ptr[3] = 'V'; - cpu_to_be32w((uint32_t *)(vga_bios_ptr + 4), vga_bios_size); - vga_bios_size += 8; - - /* Round to page boundary */ - vga_bios_size = (vga_bios_size + TARGET_PAGE_SIZE - 1) & - TARGET_PAGE_MASK; - } - if (linux_boot) { uint64_t lowaddr = 0; int bswap_needed; @@ -350,7 +316,7 @@ static void ppc_core99_init (ram_addr_t ram_size, machine_arch = ARCH_MAC99; } /* init basic PC hardware */ - pci_vga_init(pci_bus, vga_bios_offset, vga_bios_size); + pci_vga_init(pci_bus, 0, 0); escc_mem_index = escc_init(0x80013000, pic[0x25], pic[0x24], serial_hds[0], serial_hds[1], ESCC_CLOCK, 4); @@ -426,9 +392,16 @@ static void ppc_core99_init (ram_addr_t ram_size, fw_cfg_add_i16(fw_cfg, FW_CFG_PPC_HEIGHT, graphic_height); fw_cfg_add_i16(fw_cfg, FW_CFG_PPC_DEPTH, graphic_depth); + fw_cfg_add_i32(fw_cfg, FW_CFG_PPC_IS_KVM, kvm_enabled()); if (kvm_enabled()) { #ifdef CONFIG_KVM + uint8_t *hypercall; + fw_cfg_add_i32(fw_cfg, FW_CFG_PPC_TBFREQ, kvmppc_get_tbfreq()); + hypercall = qemu_malloc(16); + kvmppc_get_hypercall(env, hypercall, 16); + fw_cfg_add_bytes(fw_cfg, FW_CFG_PPC_KVM_HC, hypercall, 16); + fw_cfg_add_i32(fw_cfg, FW_CFG_PPC_KVM_PID, getpid()); #endif } else { fw_cfg_add_i32(fw_cfg, FW_CFG_PPC_TBFREQ, get_ticks_per_sec()); diff --git a/hw/ppc_oldworld.c b/hw/ppc_oldworld.c index 6b3ab89611..a2f9ddf738 100644 --- a/hw/ppc_oldworld.c +++ b/hw/ppc_oldworld.c @@ -1,3 +1,4 @@ + /* * QEMU OldWorld PowerMac (currently ~G3 Beige) hardware System Emulator * @@ -41,81 +42,11 @@ #include "elf.h" #include "kvm.h" #include "kvm_ppc.h" +#include "blockdev.h" #define MAX_IDE_BUS 2 -#define VGA_BIOS_SIZE 65536 #define CFG_ADDR 0xf0000510 -/* temporary frame buffer OSI calls for the video.x driver. The right - solution is to modify the driver to use VGA PCI I/Os */ -/* XXX: to be removed. This is no way related to emulation */ -static int vga_osi_call (CPUState *env) -{ - static int vga_vbl_enabled; - int linesize; - -#if 0 - printf("osi_call R5=%016" PRIx64 "\n", ppc_dump_gpr(env, 5)); -#endif - - /* same handler as PearPC, coming from the original MOL video - driver. */ - switch(env->gpr[5]) { - case 4: - break; - case 28: /* set_vmode */ - if (env->gpr[6] != 1 || env->gpr[7] != 0) - env->gpr[3] = 1; - else - env->gpr[3] = 0; - break; - case 29: /* get_vmode_info */ - if (env->gpr[6] != 0) { - if (env->gpr[6] != 1 || env->gpr[7] != 0) { - env->gpr[3] = 1; - break; - } - } - env->gpr[3] = 0; - env->gpr[4] = (1 << 16) | 1; /* num_vmodes, cur_vmode */ - env->gpr[5] = (1 << 16) | 0; /* num_depths, cur_depth_mode */ - env->gpr[6] = (graphic_width << 16) | graphic_height; /* w, h */ - env->gpr[7] = 85 << 16; /* refresh rate */ - env->gpr[8] = (graphic_depth + 7) & ~7; /* depth (round to byte) */ - linesize = ((graphic_depth + 7) >> 3) * graphic_width; - linesize = (linesize + 3) & ~3; - env->gpr[9] = (linesize << 16) | 0; /* row_bytes, offset */ - break; - case 31: /* set_video power */ - env->gpr[3] = 0; - break; - case 39: /* video_ctrl */ - if (env->gpr[6] == 0 || env->gpr[6] == 1) - vga_vbl_enabled = env->gpr[6]; - env->gpr[3] = 0; - break; - case 47: - break; - case 59: /* set_color */ - /* R6 = index, R7 = RGB */ - env->gpr[3] = 0; - break; - case 64: /* get color */ - /* R6 = index */ - env->gpr[3] = 0; - break; - case 116: /* set hwcursor */ - /* R6 = x, R7 = y, R8 = visible, R9 = data */ - break; - default: - fprintf(stderr, "unsupported OSI call R5=%016" PRIx64 "\n", - ppc_dump_gpr(env, 5)); - break; - } - - return 1; /* osi_call handled */ -} - static int fw_cfg_boot_set(void *opaque, const char *boot_device) { fw_cfg_add_i16(opaque, FW_CFG_BOOT_DEVICE, boot_device[0]); @@ -135,23 +66,22 @@ static void ppc_heathrow_init (ram_addr_t ram_size, const char *initrd_filename, const char *cpu_model) { - CPUState *env = NULL, *envs[MAX_CPUS]; + CPUState *env = NULL; char *filename; qemu_irq *pic, **heathrow_irqs; int linux_boot, i; - ram_addr_t ram_offset, bios_offset, vga_bios_offset; + ram_addr_t ram_offset, bios_offset; uint32_t kernel_base, initrd_base; int32_t kernel_size, initrd_size; PCIBus *pci_bus; MacIONVRAMState *nvr; - int vga_bios_size, bios_size; + int bios_size; int pic_mem_index, nvram_mem_index, dbdma_mem_index, cuda_mem_index; int escc_mem_index, ide_mem_index[2]; uint16_t ppc_boot_device; DriveInfo *hd[MAX_IDE_BUS * MAX_IDE_DEVS]; void *fw_cfg; void *dbdma; - uint8_t *vga_bios_ptr; linux_boot = (kernel_filename != NULL); @@ -166,9 +96,7 @@ static void ppc_heathrow_init (ram_addr_t ram_size, } /* Set time-base frequency to 16.6 Mhz */ cpu_ppc_tb_init(env, 16600000UL); - env->osi_call = vga_osi_call; qemu_register_reset((QEMUResetHandler*)&cpu_reset, env); - envs[i] = env; } /* allocate RAM */ @@ -202,36 +130,6 @@ static void ppc_heathrow_init (ram_addr_t ram_size, exit(1); } - /* allocate and load VGA BIOS */ - vga_bios_offset = qemu_ram_alloc(NULL, "ppc_heathrow.vbios", VGA_BIOS_SIZE); - vga_bios_ptr = qemu_get_ram_ptr(vga_bios_offset); - filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, VGABIOS_FILENAME); - if (filename) { - vga_bios_size = load_image(filename, vga_bios_ptr + 8); - qemu_free(filename); - } else { - vga_bios_size = -1; - } - if (vga_bios_size < 0) { - /* if no bios is present, we can still work */ - fprintf(stderr, "qemu: warning: could not load VGA bios '%s'\n", - VGABIOS_FILENAME); - vga_bios_size = 0; - } else { - /* set a specific header (XXX: find real Apple format for NDRV - drivers) */ - vga_bios_ptr[0] = 'N'; - vga_bios_ptr[1] = 'D'; - vga_bios_ptr[2] = 'R'; - vga_bios_ptr[3] = 'V'; - cpu_to_be32w((uint32_t *)(vga_bios_ptr + 4), vga_bios_size); - vga_bios_size += 8; - - /* Round to page boundary */ - vga_bios_size = (vga_bios_size + TARGET_PAGE_SIZE - 1) & - TARGET_PAGE_MASK; - } - if (linux_boot) { uint64_t lowaddr = 0; int bswap_needed; @@ -329,7 +227,7 @@ static void ppc_heathrow_init (ram_addr_t ram_size, } pic = heathrow_pic_init(&pic_mem_index, 1, heathrow_irqs); pci_bus = pci_grackle_init(0xfec00000, pic); - pci_vga_init(pci_bus, vga_bios_offset, vga_bios_size); + pci_vga_init(pci_bus, 0, 0); escc_mem_index = escc_init(0x80013000, pic[0x0f], pic[0x10], serial_hds[0], serial_hds[1], ESCC_CLOCK, 4); @@ -398,9 +296,16 @@ static void ppc_heathrow_init (ram_addr_t ram_size, fw_cfg_add_i16(fw_cfg, FW_CFG_PPC_HEIGHT, graphic_height); fw_cfg_add_i16(fw_cfg, FW_CFG_PPC_DEPTH, graphic_depth); + fw_cfg_add_i32(fw_cfg, FW_CFG_PPC_IS_KVM, kvm_enabled()); if (kvm_enabled()) { #ifdef CONFIG_KVM + uint8_t *hypercall; + fw_cfg_add_i32(fw_cfg, FW_CFG_PPC_TBFREQ, kvmppc_get_tbfreq()); + hypercall = qemu_malloc(16); + kvmppc_get_hypercall(env, hypercall, 16); + fw_cfg_add_bytes(fw_cfg, FW_CFG_PPC_KVM_HC, hypercall, 16); + fw_cfg_add_i32(fw_cfg, FW_CFG_PPC_KVM_PID, getpid()); #endif } else { fw_cfg_add_i32(fw_cfg, FW_CFG_PPC_TBFREQ, get_ticks_per_sec()); diff --git a/hw/ppc_prep.c b/hw/ppc_prep.c index fc3e17a0c3..a6915f7e68 100644 --- a/hw/ppc_prep.c +++ b/hw/ppc_prep.c @@ -37,6 +37,7 @@ #include "ide.h" #include "loader.h" #include "mc146818rtc.h" +#include "blockdev.h" //#define HARD_DEBUG_PPC_IO //#define DEBUG_PPC_IO @@ -564,14 +565,15 @@ static void ppc_prep_init (ram_addr_t ram_size, const char *initrd_filename, const char *cpu_model) { - CPUState *env = NULL, *envs[MAX_CPUS]; + CPUState *env = NULL; char *filename; nvram_t nvram; M48t59State *m48t59; int PPC_io_memory; int linux_boot, i, nb_nics1, bios_size; ram_addr_t ram_offset, bios_offset; - uint32_t kernel_base, kernel_size, initrd_base, initrd_size; + uint32_t kernel_base, initrd_base; + long kernel_size, initrd_size; PCIBus *pci_bus; qemu_irq *i8259; qemu_irq *cpu_exit_irq; @@ -600,7 +602,6 @@ static void ppc_prep_init (ram_addr_t ram_size, cpu_ppc_tb_init(env, 100UL * 1000UL * 1000UL); } qemu_register_reset((QEMUResetHandler*)&cpu_reset, env); - envs[i] = env; } /* allocate RAM */ diff --git a/hw/ppce500_mpc8544ds.c b/hw/ppce500_mpc8544ds.c index 1422fad072..59d20d30ae 100644 --- a/hw/ppce500_mpc8544ds.c +++ b/hw/ppce500_mpc8544ds.c @@ -176,7 +176,6 @@ static void mpc8544ds_init(ram_addr_t ram_size, int i=0; unsigned int pci_irq_nrs[4] = {1, 2, 3, 4}; qemu_irq *irqs, *mpic, *pci_irqs; - SerialState * serial[2]; /* Setup CPU */ env = cpu_ppc_init("e500v2_v30"); @@ -200,15 +199,15 @@ static void mpc8544ds_init(ram_addr_t ram_size, /* Serial */ if (serial_hds[0]) { - serial[0] = serial_mm_init(MPC8544_SERIAL0_REGS_BASE, - 0, mpic[12+26], 399193, - serial_hds[0], 1, 1); + serial_mm_init(MPC8544_SERIAL0_REGS_BASE, + 0, mpic[12+26], 399193, + serial_hds[0], 1, 1); } if (serial_hds[1]) { - serial[0] = serial_mm_init(MPC8544_SERIAL1_REGS_BASE, - 0, mpic[12+26], 399193, - serial_hds[0], 1, 1); + serial_mm_init(MPC8544_SERIAL1_REGS_BASE, + 0, mpic[12+26], 399193, + serial_hds[0], 1, 1); } /* PCI */ diff --git a/hw/pxa2xx.c b/hw/pxa2xx.c index 953e9ee1d1..6e046450df 100644 --- a/hw/pxa2xx.c +++ b/hw/pxa2xx.c @@ -15,6 +15,7 @@ #include "ssi.h" #include "qemu-timer.h" #include "qemu-char.h" +#include "blockdev.h" static struct { target_phys_addr_t io_base; @@ -124,7 +125,7 @@ static void pxa2xx_pm_write(void *opaque, target_phys_addr_t addr, break; default: /* Read-write registers */ - if (addr >= PMCR && addr <= PCMD31 && !(addr & 3)) { + if (!(addr & 3)) { s->pm_regs[addr >> 2] = value; break; } @@ -635,6 +636,7 @@ static void pxa2xx_ssp_fifo_update(PXA2xxSSPState *s) { s->sssr &= ~(0xf << 12); /* Clear RFL */ s->sssr &= ~(0xf << 8); /* Clear TFL */ + s->sssr &= ~SSSR_TFS; s->sssr &= ~SSSR_TNF; if (s->enable) { s->sssr |= ((s->rx_level - 1) & 0xf) << 12; @@ -642,14 +644,13 @@ static void pxa2xx_ssp_fifo_update(PXA2xxSSPState *s) s->sssr |= SSSR_RFS; else s->sssr &= ~SSSR_RFS; - if (0 <= SSCR1_TFT(s->sscr[1])) - s->sssr |= SSSR_TFS; - else - s->sssr &= ~SSSR_TFS; if (s->rx_level) s->sssr |= SSSR_RNE; else s->sssr &= ~SSSR_RNE; + /* TX FIFO is never filled, so it is always in underrun + condition if SSP is enabled */ + s->sssr |= SSSR_TFS; s->sssr |= SSSR_TNF; } @@ -1876,8 +1877,9 @@ static void pxa2xx_fir_write(void *opaque, target_phys_addr_t addr, s->control[0] = value; if (!(value & (1 << 4))) /* RXE */ s->rx_len = s->rx_start = 0; - if (!(value & (1 << 3))) /* TXE */ - /* Nop */; + if (!(value & (1 << 3))) { /* TXE */ + /* Nop */ + } s->enable = value & 1; /* ITR */ if (!s->enable) s->status[0] = 0; diff --git a/hw/qdev-properties.c b/hw/qdev-properties.c index 9219cd7a60..a493087a52 100644 --- a/hw/qdev-properties.c +++ b/hw/qdev-properties.c @@ -1,6 +1,7 @@ #include "net.h" #include "qdev.h" #include "qerror.h" +#include "blockdev.h" void *qdev_get_prop_ptr(DeviceState *dev, Property *prop) { @@ -772,5 +773,5 @@ static int qdev_add_one_global(QemuOpts *opts, void *opaque) void qemu_add_globals(void) { - qemu_opts_foreach(&qemu_global_opts, qdev_add_one_global, NULL, 0); + qemu_opts_foreach(qemu_find_opts("global"), qdev_add_one_global, NULL, 0); } diff --git a/hw/qdev.c b/hw/qdev.c index e99c73f0d9..35858cb81b 100644 --- a/hw/qdev.c +++ b/hw/qdev.c @@ -29,6 +29,7 @@ #include "qdev.h" #include "sysemu.h" #include "monitor.h" +#include "blockdev.h" static int qdev_hotplug = 0; @@ -792,7 +793,7 @@ int do_device_add(Monitor *mon, const QDict *qdict, QObject **ret_data) { QemuOpts *opts; - opts = qemu_opts_from_qdict(&qemu_device_opts, qdict); + opts = qemu_opts_from_qdict(qemu_find_opts("device"), qdict); if (!opts) { return -1; } diff --git a/hw/qdev.h b/hw/qdev.h index 678f8b7d1d..579328afc2 100644 --- a/hw/qdev.h +++ b/hw/qdev.h @@ -2,7 +2,6 @@ #define QDEV_H #include "hw.h" -#include "blockdev.h" #include "qemu-queue.h" #include "qemu-char.h" #include "qemu-option.h" diff --git a/hw/r2d.c b/hw/r2d.c index 8c1fbad4ba..a58f653e52 100644 --- a/hw/r2d.c +++ b/hw/r2d.c @@ -36,6 +36,7 @@ #include "loader.h" #include "usb.h" #include "flash.h" +#include "blockdev.h" #define FLASH_BASE 0x00000000 #define FLASH_SIZE 0x02000000 diff --git a/hw/rc4030.c b/hw/rc4030.c index 223137323b..abbc3eb4e2 100644 --- a/hw/rc4030.c +++ b/hw/rc4030.c @@ -749,7 +749,10 @@ static void rc4030_do_dma(void *opaque, int n, uint8_t *buf, int len, int is_wri printf("rc4030 dma: Copying %d bytes %s host %p\n", len, is_write ? "from" : "to", buf); for (i = 0; i < len; i += 16) { - int n = min(16, len - i); + int n = 16; + if (n > len - i) { + n = len - i; + } for (j = 0; j < n; j++) printf("%02x ", buf[i + j]); while (j++ < 16) diff --git a/hw/realview.c b/hw/realview.c index 70bcdb846d..e9fcbc9a6d 100644 --- a/hw/realview.c +++ b/hw/realview.c @@ -18,6 +18,7 @@ #include "boards.h" #include "bitbang_i2c.h" #include "sysbus.h" +#include "blockdev.h" #define SMP_BOOT_ADDR 0xe0000000 diff --git a/hw/s390-virtio-bus.c b/hw/s390-virtio-bus.c index fe6884d47d..784dc01b97 100644 --- a/hw/s390-virtio-bus.c +++ b/hw/s390-virtio-bus.c @@ -27,6 +27,7 @@ #include "elf.h" #include "hw/virtio.h" #include "hw/virtio-serial.h" +#include "hw/virtio-net.h" #include "hw/sysbus.h" #include "kvm.h" @@ -110,7 +111,7 @@ static int s390_virtio_net_init(VirtIOS390Device *dev) { VirtIODevice *vdev; - vdev = virtio_net_init((DeviceState *)dev, &dev->nic); + vdev = virtio_net_init((DeviceState *)dev, &dev->nic, &dev->net); if (!vdev) { return -1; } @@ -327,6 +328,11 @@ static VirtIOS390DeviceInfo s390_virtio_net = { .qdev.size = sizeof(VirtIOS390Device), .qdev.props = (Property[]) { DEFINE_NIC_PROPERTIES(VirtIOS390Device, nic), + DEFINE_PROP_UINT32("x-txtimer", VirtIOS390Device, + net.txtimer, TX_TIMER_INTERVAL), + DEFINE_PROP_INT32("x-txburst", VirtIOS390Device, + net.txburst, TX_BURST), + DEFINE_PROP_STRING("tx", VirtIOS390Device, net.tx), DEFINE_PROP_END_OF_LIST(), }, }; diff --git a/hw/s390-virtio-bus.h b/hw/s390-virtio-bus.h index 333fea8963..41558c9c67 100644 --- a/hw/s390-virtio-bus.h +++ b/hw/s390-virtio-bus.h @@ -43,6 +43,7 @@ typedef struct VirtIOS390Device { uint32_t host_features; /* Max. number of ports we can have for a the virtio-serial device */ uint32_t max_virtserial_ports; + virtio_net_conf net; } VirtIOS390Device; typedef struct VirtIOS390Bus { diff --git a/hw/scsi-bus.c b/hw/scsi-bus.c index d69c74c4ef..5a3fd4b7ac 100644 --- a/hw/scsi-bus.c +++ b/hw/scsi-bus.c @@ -3,6 +3,7 @@ #include "scsi.h" #include "scsi-defs.h" #include "qdev.h" +#include "blockdev.h" static struct BusInfo scsi_bus_info = { .name = "SCSI", @@ -142,6 +143,7 @@ SCSIRequest *scsi_req_alloc(size_t size, SCSIDevice *d, uint32_t tag, uint32_t l req->tag = tag; req->lun = lun; req->status = -1; + req->enqueued = true; QTAILQ_INSERT_TAIL(&d->requests, req, next); return req; } @@ -158,9 +160,17 @@ SCSIRequest *scsi_req_find(SCSIDevice *d, uint32_t tag) return NULL; } +static void scsi_req_dequeue(SCSIRequest *req) +{ + if (req->enqueued) { + QTAILQ_REMOVE(&req->dev->requests, req, next); + req->enqueued = false; + } +} + void scsi_req_free(SCSIRequest *req) { - QTAILQ_REMOVE(&req->dev->requests, req, next); + scsi_req_dequeue(req); qemu_free(req); } @@ -198,6 +208,8 @@ static int scsi_req_length(SCSIRequest *req, uint8_t *cmd) case SEEK_6: case WRITE_FILEMARKS: case SPACE: + case RESERVE: + case RELEASE: case ERASE: case ALLOW_MEDIUM_REMOVAL: case VERIFY: @@ -309,7 +321,6 @@ static void scsi_req_xfer_mode(SCSIRequest *req) case WRITE_BUFFER: case FORMAT_UNIT: case REASSIGN_BLOCKS: - case RESERVE: case SEARCH_EQUAL: case SEARCH_HIGH: case SEARCH_LOW: @@ -512,6 +523,7 @@ void scsi_req_print(SCSIRequest *req) void scsi_req_complete(SCSIRequest *req) { assert(req->status != -1); + scsi_req_dequeue(req); req->bus->complete(req->bus, SCSI_REASON_DONE, req->tag, req->status); diff --git a/hw/scsi-disk.c b/hw/scsi-disk.c index c30709c550..9628b39a21 100644 --- a/hw/scsi-disk.c +++ b/hw/scsi-disk.c @@ -36,6 +36,7 @@ do { fprintf(stderr, "scsi-disk: " fmt , ## __VA_ARGS__); } while (0) #include "scsi.h" #include "scsi-defs.h" #include "sysemu.h" +#include "blockdev.h" #define SCSI_DMA_BUF_SIZE 131072 #define SCSI_MAX_INQUIRY_LEN 256 @@ -69,14 +70,15 @@ struct SCSIDiskState char *serial; }; -static SCSIDiskReq *scsi_new_request(SCSIDevice *d, uint32_t tag, uint32_t lun) +static SCSIDiskReq *scsi_new_request(SCSIDiskState *s, uint32_t tag, + uint32_t lun) { SCSIRequest *req; SCSIDiskReq *r; - req = scsi_req_alloc(sizeof(SCSIDiskReq), d, tag, lun); + req = scsi_req_alloc(sizeof(SCSIDiskReq), &s->qdev, tag, lun); r = DO_UPCAST(SCSIDiskReq, req, req); - r->iov.iov_base = qemu_memalign(512, SCSI_DMA_BUF_SIZE); + r->iov.iov_base = qemu_blockalign(s->bs, SCSI_DMA_BUF_SIZE); return r; } @@ -134,7 +136,7 @@ static void scsi_read_complete(void * opaque, int ret) scsi_command_complete(r, CHECK_CONDITION, NO_SENSE); return; } - DPRINTF("Data ready tag=0x%x len=%" PRId64 "\n", r->req.tag, r->iov.iov_len); + DPRINTF("Data ready tag=0x%x len=%zd\n", r->req.tag, r->iov.iov_len); r->req.bus->complete(r->req.bus, SCSI_REASON_DATA, r->req.tag, r->iov.iov_len); } @@ -154,7 +156,7 @@ static void scsi_read_data(SCSIDevice *d, uint32_t tag) return; } if (r->sector_count == (uint32_t)-1) { - DPRINTF("Read buf_len=%" PRId64 "\n", r->iov.iov_len); + DPRINTF("Read buf_len=%zd\n", r->iov.iov_len); r->sector_count = 0; r->req.bus->complete(r->req.bus, SCSI_REASON_DATA, r->req.tag, r->iov.iov_len); return; @@ -485,16 +487,26 @@ static int scsi_disk_emulate_inquiry(SCSIRequest *req, uint8_t *outbuf) return buflen; } -static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p) +static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p, + int page_control) { SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, req->dev); BlockDriverState *bdrv = s->bs; int cylinders, heads, secs; + /* + * If Changeable Values are requested, a mask denoting those mode parameters + * that are changeable shall be returned. As we currently don't support + * parameter changes via MODE_SELECT all bits are returned set to zero. + * The buffer was already menset to zero by the caller of this function. + */ switch (page) { case 4: /* Rigid disk device geometry page. */ p[0] = 4; p[1] = 0x16; + if (page_control == 1) { /* Changeable Values */ + return p[1] + 2; + } /* if a geometry hint is available, use it */ bdrv_get_geometry_hint(bdrv, &cylinders, &heads, &secs); p[2] = (cylinders >> 16) & 0xff; @@ -519,11 +531,14 @@ static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p) /* Medium rotation rate [rpm], 5400 rpm */ p[20] = (5400 >> 8) & 0xff; p[21] = 5400 & 0xff; - return 0x16; + return p[1] + 2; case 5: /* Flexible disk device geometry page. */ p[0] = 5; p[1] = 0x1e; + if (page_control == 1) { /* Changeable Values */ + return p[1] + 2; + } /* Transfer rate [kbit/s], 5Mbit/s */ p[2] = 5000 >> 8; p[3] = 5000 & 0xff; @@ -555,21 +570,27 @@ static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p) /* Medium rotation rate [rpm], 5400 rpm */ p[28] = (5400 >> 8) & 0xff; p[29] = 5400 & 0xff; - return 0x1e; + return p[1] + 2; case 8: /* Caching page. */ p[0] = 8; p[1] = 0x12; + if (page_control == 1) { /* Changeable Values */ + return p[1] + 2; + } if (bdrv_enable_write_cache(s->bs)) { p[2] = 4; /* WCE */ } - return 20; + return p[1] + 2; case 0x2a: /* CD Capabilities and Mechanical Status page. */ if (bdrv_get_type_hint(bdrv) != BDRV_TYPE_CDROM) return 0; p[0] = 0x2a; p[1] = 0x14; + if (page_control == 1) { /* Changeable Values */ + return p[1] + 2; + } p[2] = 3; // CD-R & CD-RW read p[3] = 0; // Writing not supported p[4] = 0x7f; /* Audio, composite, digital out, @@ -593,7 +614,7 @@ static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p) p[19] = (16 * 176) & 0xff; p[20] = (16 * 176) >> 8; // 16x write speed current p[21] = (16 * 176) & 0xff; - return 22; + return p[1] + 2; default: return 0; @@ -604,29 +625,46 @@ static int scsi_disk_emulate_mode_sense(SCSIRequest *req, uint8_t *outbuf) { SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, req->dev); uint64_t nb_sectors; - int page, dbd, buflen; + int page, dbd, buflen, page_control; uint8_t *p; + uint8_t dev_specific_param; dbd = req->cmd.buf[1] & 0x8; page = req->cmd.buf[2] & 0x3f; - DPRINTF("Mode Sense (page %d, len %zd)\n", page, req->cmd.xfer); + page_control = (req->cmd.buf[2] & 0xc0) >> 6; + DPRINTF("Mode Sense(%d) (page %d, xfer %zd, page_control %d)\n", + (req->cmd.buf[0] == MODE_SENSE) ? 6 : 10, page, req->cmd.xfer, page_control); memset(outbuf, 0, req->cmd.xfer); p = outbuf; - p[1] = 0; /* Default media type. */ - p[3] = 0; /* Block descriptor length. */ if (bdrv_is_read_only(s->bs)) { - p[2] = 0x80; /* Readonly. */ + dev_specific_param = 0x80; /* Readonly. */ + } else { + dev_specific_param = 0x00; + } + + if (req->cmd.buf[0] == MODE_SENSE) { + p[1] = 0; /* Default media type. */ + p[2] = dev_specific_param; + p[3] = 0; /* Block descriptor length. */ + p += 4; + } else { /* MODE_SENSE_10 */ + p[2] = 0; /* Default media type. */ + p[3] = dev_specific_param; + p[6] = p[7] = 0; /* Block descriptor length. */ + p += 8; } - p += 4; bdrv_get_geometry(s->bs, &nb_sectors); - if ((~dbd) & nb_sectors) { - outbuf[3] = 8; /* Block descriptor length */ + if (!dbd && nb_sectors) { + if (req->cmd.buf[0] == MODE_SENSE) { + outbuf[3] = 8; /* Block descriptor length */ + } else { /* MODE_SENSE_10 */ + outbuf[7] = 8; /* Block descriptor length */ + } nb_sectors /= s->cluster_size; - nb_sectors--; if (nb_sectors > 0xffffff) - nb_sectors = 0xffffff; + nb_sectors = 0; p[0] = 0; /* media density code */ p[1] = (nb_sectors >> 16) & 0xff; p[2] = (nb_sectors >> 8) & 0xff; @@ -638,21 +676,37 @@ static int scsi_disk_emulate_mode_sense(SCSIRequest *req, uint8_t *outbuf) p += 8; } + if (page_control == 3) { /* Saved Values */ + return -1; /* ILLEGAL_REQUEST */ + } + switch (page) { case 0x04: case 0x05: case 0x08: case 0x2a: - p += mode_sense_page(req, page, p); + p += mode_sense_page(req, page, p, page_control); break; case 0x3f: - p += mode_sense_page(req, 0x08, p); - p += mode_sense_page(req, 0x2a, p); + p += mode_sense_page(req, 0x08, p, page_control); + p += mode_sense_page(req, 0x2a, p, page_control); break; + default: + return -1; /* ILLEGAL_REQUEST */ } buflen = p - outbuf; - outbuf[0] = buflen - 4; + /* + * The mode data length field specifies the length in bytes of the + * following data that is available to be transferred. The mode data + * length does not include itself. + */ + if (req->cmd.buf[0] == MODE_SENSE) { + outbuf[0] = buflen - 1; + } else { /* MODE_SENSE_10 */ + outbuf[0] = ((buflen - 2) >> 8) & 0xff; + outbuf[1] = (buflen - 2) & 0xff; + } if (buflen > req->cmd.xfer) buflen = req->cmd.xfer; return buflen; @@ -839,6 +893,12 @@ static int scsi_disk_emulate_command(SCSIRequest *req, uint8_t *outbuf) break; case VERIFY: break; + case REZERO_UNIT: + DPRINTF("Rezero Unit\n"); + if (!bdrv_is_inserted(s->bs)) { + goto not_ready; + } + break; default: goto illegal_request; } @@ -880,7 +940,7 @@ static int32_t scsi_send_command(SCSIDevice *d, uint32_t tag, } /* ??? Tags are not unique for different luns. We only implement a single lun, so this should not matter. */ - r = scsi_new_request(d, tag, lun); + r = scsi_new_request(s, tag, lun); outbuf = (uint8_t *)r->iov.iov_base; is_write = 0; DPRINTF("Command: lun=%d tag=0x%x data=0x%02x", lun, tag, buf[0]); @@ -958,6 +1018,7 @@ static int32_t scsi_send_command(SCSIDevice *d, uint32_t tag, case SERVICE_ACTION_IN: case REPORT_LUNS: case VERIFY: + case REZERO_UNIT: rc = scsi_disk_emulate_command(&r->req, outbuf); if (rc > 0) { r->iov.iov_len = rc; @@ -981,13 +1042,40 @@ static int32_t scsi_send_command(SCSIDevice *d, uint32_t tag, case WRITE_10: case WRITE_12: case WRITE_16: - DPRINTF("Write (sector %" PRId64 ", count %d)\n", lba, len); + case WRITE_VERIFY: + case WRITE_VERIFY_12: + case WRITE_VERIFY_16: + DPRINTF("Write %s(sector %" PRId64 ", count %d)\n", + (command & 0xe) == 0xe ? "And Verify " : "", lba, len); if (lba > s->max_lba) goto illegal_lba; r->sector = lba * s->cluster_size; r->sector_count = len * s->cluster_size; is_write = 1; break; + case MODE_SELECT: + DPRINTF("Mode Select(6) (len %d)\n", len); + /* We don't support mode parameter changes. + Allow the mode parameter header + block descriptors only. */ + if (len > 12) { + goto fail; + } + break; + case MODE_SELECT_10: + DPRINTF("Mode Select(10) (len %d)\n", len); + /* We don't support mode parameter changes. + Allow the mode parameter header + block descriptors only. */ + if (len > 16) { + goto fail; + } + break; + case SEEK_6: + case SEEK_10: + DPRINTF("Seek(%d) (sector %" PRId64 ")\n", command == SEEK_6 ? 6 : 10, lba); + if (lba > s->max_lba) { + goto illegal_lba; + } + break; default: DPRINTF("Unknown SCSI command (%2.2x)\n", buf[0]); fail: @@ -1059,6 +1147,11 @@ static int scsi_disk_initfn(SCSIDevice *dev) s->bs = s->qdev.conf.bs; is_cd = bdrv_get_type_hint(s->bs) == BDRV_TYPE_CDROM; + if (!is_cd && !bdrv_is_inserted(s->bs)) { + error_report("Device needs media, but drive is empty"); + return -1; + } + if (bdrv_get_on_error(s->bs, 1) != BLOCK_ERR_REPORT) { error_report("Device doesn't support drive option rerror"); return -1; @@ -1085,6 +1178,7 @@ static int scsi_disk_initfn(SCSIDevice *dev) s->qdev.blocksize = s->qdev.conf.logical_block_size; } s->cluster_size = s->qdev.blocksize / 512; + s->bs->buffer_alignment = s->qdev.blocksize; s->qdev.type = TYPE_DISK; qemu_add_vm_change_state_handler(scsi_dma_restart_cb, s); diff --git a/hw/scsi-generic.c b/hw/scsi-generic.c index a8b4176d80..7212091695 100644 --- a/hw/scsi-generic.c +++ b/hw/scsi-generic.c @@ -14,6 +14,7 @@ #include "qemu-common.h" #include "qemu-error.h" #include "scsi.h" +#include "blockdev.h" #ifdef __linux__ @@ -163,7 +164,7 @@ static void scsi_read_complete(void * opaque, int ret) int len; if (ret) { - DPRINTF("IO error\n"); + DPRINTF("IO error ret %d\n", ret); scsi_command_complete(r, ret); return; } @@ -235,7 +236,7 @@ static void scsi_write_complete(void * opaque, int ret) if (r->req.cmd.buf[0] == MODE_SELECT && r->req.cmd.buf[4] == 12 && s->qdev.type == TYPE_TAPE) { s->qdev.blocksize = (r->buf[9] << 16) | (r->buf[10] << 8) | r->buf[11]; - DPRINTF("block size %d\n", s->blocksize); + DPRINTF("block size %d\n", s->qdev.blocksize); } scsi_command_complete(r, ret); @@ -350,8 +351,18 @@ static int32_t scsi_send_command(SCSIDevice *d, uint32_t tag, } scsi_req_fixup(&r->req); - DPRINTF("Command: lun=%d tag=0x%x data=0x%02x len %d\n", lun, tag, - cmd[0], r->req.cmd.xfer); + DPRINTF("Command: lun=%d tag=0x%x len %zd data=0x%02x", lun, tag, + r->req.cmd.xfer, cmd[0]); + +#ifdef DEBUG_SCSI + { + int i; + for (i = 1; i < r->req.cmd.len; i++) { + printf(" 0x%02x", cmd[i]); + } + printf("\n"); + } +#endif if (r->req.cmd.xfer == 0) { if (r->buf != NULL) @@ -444,15 +455,31 @@ static int get_stream_blocksize(BlockDriverState *bdrv) return (buf[9] << 16) | (buf[10] << 8) | buf[11]; } -static void scsi_destroy(SCSIDevice *d) +static void scsi_generic_purge_requests(SCSIGenericState *s) { - SCSIGenericState *s = DO_UPCAST(SCSIGenericState, qdev, d); SCSIGenericReq *r; while (!QTAILQ_EMPTY(&s->qdev.requests)) { r = DO_UPCAST(SCSIGenericReq, req, QTAILQ_FIRST(&s->qdev.requests)); + if (r->req.aiocb) { + bdrv_aio_cancel(r->req.aiocb); + } scsi_remove_request(r); } +} + +static void scsi_generic_reset(DeviceState *dev) +{ + SCSIGenericState *s = DO_UPCAST(SCSIGenericState, qdev.qdev, dev); + + scsi_generic_purge_requests(s); +} + +static void scsi_destroy(SCSIDevice *d) +{ + SCSIGenericState *s = DO_UPCAST(SCSIGenericState, qdev, d); + + scsi_generic_purge_requests(s); blockdev_mark_auto_del(s->qdev.conf.bs); } @@ -526,6 +553,7 @@ static SCSIDeviceInfo scsi_generic_info = { .qdev.name = "scsi-generic", .qdev.desc = "pass through generic scsi device (/dev/sg*)", .qdev.size = sizeof(SCSIGenericState), + .qdev.reset = scsi_generic_reset, .init = scsi_generic_initfn, .destroy = scsi_destroy, .send_command = scsi_send_command, diff --git a/hw/scsi.h b/hw/scsi.h index 4fbf1d5dfd..cb06d6d824 100644 --- a/hw/scsi.h +++ b/hw/scsi.h @@ -43,6 +43,7 @@ typedef struct SCSIRequest { enum SCSIXferMode mode; } cmd; BlockDriverAIOCB *aiocb; + bool enqueued; QTAILQ_ENTRY(SCSIRequest) next; } SCSIRequest; diff --git a/hw/sd.c b/hw/sd.c index c928120abd..601545b2d9 100644 --- a/hw/sd.c +++ b/hw/sd.c @@ -31,6 +31,7 @@ #include "hw.h" #include "block.h" +#include "block_int.h" #include "sd.h" //#define DEBUG_SD 1 @@ -440,7 +441,7 @@ SDState *sd_init(BlockDriverState *bs, int is_spi) SDState *sd; sd = (SDState *) qemu_mallocz(sizeof(SDState)); - sd->buf = qemu_memalign(512, 512); + sd->buf = qemu_blockalign(bs, 512); sd->spi = is_spi; sd->enable = 1; sd_reset(sd, bs); diff --git a/hw/serial.c b/hw/serial.c index b66d13ad41..9ebc452aea 100644 --- a/hw/serial.c +++ b/hw/serial.c @@ -99,6 +99,14 @@ #define RECV_FIFO 1 #define MAX_XMIT_RETRY 4 +#ifdef DEBUG_SERIAL +#define DPRINTF(fmt, ...) \ +do { fprintf(stderr, "serial: " fmt , ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ +do {} while (0) +#endif + typedef struct SerialFIFO { uint8_t data[UART_FIFO_LENGTH]; uint8_t count; @@ -267,10 +275,9 @@ static void serial_update_parameters(SerialState *s) ssp.stop_bits = stop_bits; s->char_transmit_time = (get_ticks_per_sec() / speed) * frame_size; qemu_chr_ioctl(s->chr, CHR_IOCTL_SERIAL_SET_PARAMS, &ssp); -#if 0 - printf("speed=%d parity=%c data=%d stop=%d\n", + + DPRINTF("speed=%d parity=%c data=%d stop=%d\n", speed, parity, data_bits, stop_bits); -#endif } static void serial_update_msl(SerialState *s) @@ -360,9 +367,7 @@ static void serial_ioport_write(void *opaque, uint32_t addr, uint32_t val) SerialState *s = opaque; addr &= 7; -#ifdef DEBUG_SERIAL - printf("serial: write addr=0x%02x val=0x%02x\n", addr, val); -#endif + DPRINTF("write addr=0x%02x val=0x%02x\n", addr, val); switch(addr) { default: case 0: @@ -583,9 +588,7 @@ static uint32_t serial_ioport_read(void *opaque, uint32_t addr) ret = s->scr; break; } -#ifdef DEBUG_SERIAL - printf("serial: read addr=0x%02x val=0x%02x\n", addr, ret); -#endif + DPRINTF("read addr=0x%02x val=0x%02x\n", addr, ret); return ret; } @@ -651,9 +654,7 @@ static void serial_receive1(void *opaque, const uint8_t *buf, int size) static void serial_event(void *opaque, int event) { SerialState *s = opaque; -#ifdef DEBUG_SERIAL - printf("serial: event %x\n", event); -#endif + DPRINTF("event %x\n", event); if (event == CHR_EVENT_BREAK) serial_receive_break(s); } @@ -673,6 +674,7 @@ static int serial_post_load(void *opaque, int version_id) } /* Initialize fcr via setter to perform essential side-effects */ serial_ioport_write(s, 0x02, s->fcr_vmstate); + serial_update_parameters(s); return 0; } diff --git a/hw/sh_intc.c b/hw/sh_intc.c index da36d32b1d..d3f5ea57d5 100644 --- a/hw/sh_intc.c +++ b/hw/sh_intc.c @@ -431,9 +431,8 @@ int sh_intc_init(struct intc_desc *desc, desc->nr_prio_regs = nr_prio_regs; i = sizeof(struct intc_source) * nr_sources; - desc->sources = qemu_malloc(i); + desc->sources = qemu_mallocz(i); - memset(desc->sources, 0, i); for (i = 0; i < desc->nr_sources; i++) { struct intc_source *source = desc->sources + i; diff --git a/hw/slavio_timer.c b/hw/slavio_timer.c index d7875536b6..c125de4b62 100644 --- a/hw/slavio_timer.c +++ b/hw/slavio_timer.c @@ -377,12 +377,12 @@ static void slavio_timer_reset(DeviceState *d) curr_timer->limit = 0; curr_timer->count = 0; curr_timer->reached = 0; - if (i < s->num_cpus) { + if (i <= s->num_cpus) { ptimer_set_limit(curr_timer->timer, LIMIT_TO_PERIODS(TIMER_MAX_COUNT32), 1); ptimer_run(curr_timer->timer, 0); + curr_timer->running = 1; } - curr_timer->running = 1; } s->cputimer_mode = 0; } diff --git a/hw/sm501.c b/hw/sm501.c index 8e6932d747..705e0a5c76 100644 --- a/hw/sm501.c +++ b/hw/sm501.c @@ -29,6 +29,7 @@ #include "devices.h" #include "sysbus.h" #include "qdev-addr.h" +#include "range.h" /* * Status: 2010/05/07 @@ -814,7 +815,7 @@ static uint32_t sm501_palette_read(void *opaque, target_phys_addr_t addr) /* TODO : consider BYTE/WORD access */ /* TODO : consider endian */ - assert(0 <= addr && addr < 0x400 * 3); + assert(range_covers_byte(0, 0x400 * 3, addr)); return *(uint32_t*)&s->dc_palette[addr]; } @@ -828,7 +829,7 @@ static void sm501_palette_write(void *opaque, /* TODO : consider BYTE/WORD access */ /* TODO : consider endian */ - assert(0 <= addr && addr < 0x400 * 3); + assert(range_covers_byte(0, 0x400 * 3, addr)); *(uint32_t*)&s->dc_palette[addr] = value; } diff --git a/hw/soc_dma.c b/hw/soc_dma.c index e116e6373a..23ec51695a 100644 --- a/hw/soc_dma.c +++ b/hw/soc_dma.c @@ -192,12 +192,13 @@ static void soc_dma_ch_freq_update(struct dma_s *s) if (s->enabled_count) /* We completely ignore channel priorities and stuff */ s->channel_freq = s->soc.freq / s->enabled_count; - else + else { /* TODO: Signal that we want to disable the functional clock and let * the platform code decide what to do with it, i.e. check that * auto-idle is enabled in the clock controller and if we are stopping * the clock, do the same with any parent clocks that had only one - * user keeping them on and auto-idle enabled. */; + * user keeping them on and auto-idle enabled. */ + } } void soc_dma_set_request(struct soc_dma_ch_s *ch, int level) diff --git a/hw/sparc32_dma.c b/hw/sparc32_dma.c index b52170787b..984ffc3e53 100644 --- a/hw/sparc32_dma.c +++ b/hw/sparc32_dma.c @@ -58,6 +58,7 @@ #define DMA_INTR 1 #define DMA_INTREN 0x10 #define DMA_WRITE_MEM 0x100 +#define DMA_EN 0x200 #define DMA_LOADED 0x04000000 #define DMA_DRAIN_FIFO 0x40 #define DMA_RESET 0x80 @@ -72,7 +73,12 @@ struct DMAState { uint32_t dmaregs[DMA_REGS]; qemu_irq irq; void *iommu; - qemu_irq dev_reset; + qemu_irq gpio[2]; +}; + +enum { + GPIO_RESET = 0, + GPIO_DMA, }; /* Note: on sparc, the lance 16 bit bus is swapped */ @@ -201,12 +207,21 @@ static void dma_mem_writel(void *opaque, target_phys_addr_t addr, uint32_t val) } } if (val & DMA_RESET) { - qemu_irq_raise(s->dev_reset); - qemu_irq_lower(s->dev_reset); + qemu_irq_raise(s->gpio[GPIO_RESET]); + qemu_irq_lower(s->gpio[GPIO_RESET]); } else if (val & DMA_DRAIN_FIFO) { val &= ~DMA_DRAIN_FIFO; } else if (val == 0) val = DMA_DRAIN_FIFO; + + if (val & DMA_EN && !(s->dmaregs[0] & DMA_EN)) { + DPRINTF("Raise DMA enable\n"); + qemu_irq_raise(s->gpio[GPIO_DMA]); + } else if (!(val & DMA_EN) && !!(s->dmaregs[0] & DMA_EN)) { + DPRINTF("Lower DMA enable\n"); + qemu_irq_lower(s->gpio[GPIO_DMA]); + } + val &= ~DMA_CSR_RO_MASK; val |= DMA_VER; s->dmaregs[0] = (s->dmaregs[0] & DMA_CSR_RO_MASK) | val; @@ -262,7 +277,7 @@ static int sparc32_dma_init1(SysBusDevice *dev) sysbus_init_mmio(dev, DMA_SIZE, dma_io_memory); qdev_init_gpio_in(&dev->qdev, dma_set_irq, 1); - qdev_init_gpio_out(&dev->qdev, &s->dev_reset, 1); + qdev_init_gpio_out(&dev->qdev, s->gpio, 2); return 0; } diff --git a/hw/spitz.c b/hw/spitz.c index ccf2a091fb..a064460936 100644 --- a/hw/spitz.c +++ b/hw/spitz.c @@ -22,6 +22,7 @@ #include "block.h" #include "audio/audio.h" #include "boards.h" +#include "blockdev.h" #undef REG_FMT #define REG_FMT "0x%02lx" diff --git a/hw/sun4m.c b/hw/sun4m.c index 208c8a86df..0392109230 100644 --- a/hw/sun4m.c +++ b/hw/sun4m.c @@ -40,6 +40,7 @@ #include "qdev-addr.h" #include "loader.h" #include "elf.h" +#include "blockdev.h" //#define DEBUG_IRQ @@ -89,6 +90,7 @@ #define MAX_CPUS 16 #define MAX_PILS 16 +#define MAX_VSIMMS 4 #define ESCC_CLOCK 4915200 @@ -98,6 +100,10 @@ struct sun4m_hwdef { target_phys_addr_t serial_base, fd_base; target_phys_addr_t afx_base, idreg_base, dma_base, esp_base, le_base; target_phys_addr_t tcx_base, cs_base, apc_base, aux1_base, aux2_base; + target_phys_addr_t bpp_base, dbri_base, sx_base; + struct { + target_phys_addr_t reg_base, vram_base; + } vsimm[MAX_VSIMMS]; target_phys_addr_t ecc_base; uint32_t ecc_version; uint8_t nvram_machine_id; @@ -804,12 +810,13 @@ static void sun4m_hw_init(const struct sun4m_hwdef *hwdef, ram_addr_t RAM_size, void *iommu, *espdma, *ledma, *nvram; qemu_irq *cpu_irqs[MAX_CPUS], slavio_irq[32], slavio_cpu_irq[MAX_CPUS], espdma_irq, ledma_irq; - qemu_irq esp_reset; + qemu_irq esp_reset, dma_enable; qemu_irq fdc_tc; qemu_irq *cpu_halt; unsigned long kernel_size; DriveInfo *fd[MAX_FD]; void *fw_cfg; + unsigned int num_vsimms; /* init CPUs */ if (!cpu_model) @@ -872,8 +879,22 @@ static void sun4m_hw_init(const struct sun4m_hwdef *hwdef, ram_addr_t RAM_size, fprintf(stderr, "qemu: Unsupported depth: %d\n", graphic_depth); exit (1); } - tcx_init(hwdef->tcx_base, 0x00100000, graphic_width, graphic_height, - graphic_depth); + num_vsimms = 0; + if (num_vsimms == 0) { + tcx_init(hwdef->tcx_base, 0x00100000, graphic_width, graphic_height, + graphic_depth); + } + + for (i = num_vsimms; i < MAX_VSIMMS; i++) { + /* vsimm registers probed by OBP */ + if (hwdef->vsimm[i].reg_base) { + empty_slot_init(hwdef->vsimm[i].reg_base, 0x2000); + } + } + + if (hwdef->sx_base) { + empty_slot_init(hwdef->sx_base, 0x2000); + } lance_init(&nd_table[0], hwdef->le_base, ledma, ledma_irq); @@ -909,17 +930,31 @@ static void sun4m_hw_init(const struct sun4m_hwdef *hwdef, ram_addr_t RAM_size, exit(1); } - esp_reset = qdev_get_gpio_in(espdma, 0); esp_init(hwdef->esp_base, 2, espdma_memory_read, espdma_memory_write, - espdma, espdma_irq, &esp_reset); + espdma, espdma_irq, &esp_reset, &dma_enable); + qdev_connect_gpio_out(espdma, 0, esp_reset); + qdev_connect_gpio_out(espdma, 1, dma_enable); if (hwdef->cs_base) { sysbus_create_simple("SUNW,CS4231", hwdef->cs_base, slavio_irq[5]); } + if (hwdef->dbri_base) { + /* ISDN chip with attached CS4215 audio codec */ + /* prom space */ + empty_slot_init(hwdef->dbri_base+0x1000, 0x30); + /* reg space */ + empty_slot_init(hwdef->dbri_base+0x10000, 0x100); + } + + if (hwdef->bpp_base) { + /* parallel port */ + empty_slot_init(hwdef->bpp_base, 0x20); + } + kernel_size = sun4m_load_kernel(kernel_filename, initrd_filename, RAM_size); @@ -945,8 +980,11 @@ static void sun4m_hw_init(const struct sun4m_hwdef *hwdef, ram_addr_t RAM_size, fw_cfg_add_bytes(fw_cfg, FW_CFG_CMDLINE_DATA, (uint8_t*)strdup(kernel_cmdline), strlen(kernel_cmdline) + 1); + fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, + strlen(kernel_cmdline) + 1); } else { fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_CMDLINE, 0); + fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, 0); } fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, INITRD_LOAD_ADDR); fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, 0); // not used @@ -1063,9 +1101,25 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .dma_base = 0xef0400000ULL, .esp_base = 0xef0800000ULL, .le_base = 0xef0c00000ULL, + .bpp_base = 0xef4800000ULL, .apc_base = 0xefa000000ULL, // XXX should not exist .aux1_base = 0xff1800000ULL, .aux2_base = 0xff1a01000ULL, + .dbri_base = 0xee0000000ULL, + .sx_base = 0xf80000000ULL, + .vsimm = { + { + .reg_base = 0x9c000000ULL, + .vram_base = 0xfc000000ULL + }, { + .reg_base = 0x90000000ULL, + .vram_base = 0xf0000000ULL + }, { + .reg_base = 0x94000000ULL + }, { + .reg_base = 0x98000000ULL + } + }, .ecc_base = 0xf00000000ULL, .ecc_version = 0x20000000, // version 0, implementation 2 .nvram_machine_id = 0x72, @@ -1441,7 +1495,7 @@ static void sun4d_hw_init(const struct sun4d_hwdef *hwdef, ram_addr_t RAM_size, void *iounits[MAX_IOUNITS], *espdma, *ledma, *nvram; qemu_irq *cpu_irqs[MAX_CPUS], sbi_irq[32], sbi_cpu_irq[MAX_CPUS], espdma_irq, ledma_irq; - qemu_irq esp_reset; + qemu_irq esp_reset, dma_enable; unsigned long kernel_size; void *fw_cfg; DeviceState *dev; @@ -1508,10 +1562,12 @@ static void sun4d_hw_init(const struct sun4d_hwdef *hwdef, ram_addr_t RAM_size, exit(1); } - esp_reset = qdev_get_gpio_in(espdma, 0); esp_init(hwdef->esp_base, 2, espdma_memory_read, espdma_memory_write, - espdma, espdma_irq, &esp_reset); + espdma, espdma_irq, &esp_reset, &dma_enable); + + qdev_connect_gpio_out(espdma, 0, esp_reset); + qdev_connect_gpio_out(espdma, 1, dma_enable); kernel_size = sun4m_load_kernel(kernel_filename, initrd_filename, RAM_size); @@ -1630,7 +1686,7 @@ static void sun4c_hw_init(const struct sun4c_hwdef *hwdef, ram_addr_t RAM_size, { void *iommu, *espdma, *ledma, *nvram; qemu_irq *cpu_irqs, slavio_irq[8], espdma_irq, ledma_irq; - qemu_irq esp_reset; + qemu_irq esp_reset, dma_enable; qemu_irq fdc_tc; unsigned long kernel_size; DriveInfo *fd[MAX_FD]; @@ -1698,10 +1754,12 @@ static void sun4c_hw_init(const struct sun4c_hwdef *hwdef, ram_addr_t RAM_size, exit(1); } - esp_reset = qdev_get_gpio_in(espdma, 0); esp_init(hwdef->esp_base, 2, espdma_memory_read, espdma_memory_write, - espdma, espdma_irq, &esp_reset); + espdma, espdma_irq, &esp_reset, &dma_enable); + + qdev_connect_gpio_out(espdma, 0, esp_reset); + qdev_connect_gpio_out(espdma, 1, dma_enable); kernel_size = sun4m_load_kernel(kernel_filename, initrd_filename, RAM_size); diff --git a/hw/sun4u.c b/hw/sun4u.c index 31c0c4c482..45a46d673c 100644 --- a/hw/sun4u.c +++ b/hw/sun4u.c @@ -37,6 +37,7 @@ #include "ide.h" #include "loader.h" #include "elf.h" +#include "blockdev.h" //#define DEBUG_IRQ //#define DEBUG_EBUS diff --git a/hw/syborg_virtio.c b/hw/syborg_virtio.c index abf0370107..4dfd1a87b9 100644 --- a/hw/syborg_virtio.c +++ b/hw/syborg_virtio.c @@ -68,6 +68,7 @@ typedef struct { uint32_t id; NICConf nic; uint32_t host_features; + virtio_net_conf net; } SyborgVirtIOProxy; static uint32_t syborg_virtio_readl(void *opaque, target_phys_addr_t offset) @@ -284,7 +285,7 @@ static int syborg_virtio_net_init(SysBusDevice *dev) VirtIODevice *vdev; SyborgVirtIOProxy *proxy = FROM_SYSBUS(SyborgVirtIOProxy, dev); - vdev = virtio_net_init(&dev->qdev, &proxy->nic); + vdev = virtio_net_init(&dev->qdev, &proxy->nic, &proxy->net); return syborg_virtio_init(proxy, vdev); } @@ -295,6 +296,11 @@ static SysBusDeviceInfo syborg_virtio_net_info = { .qdev.props = (Property[]) { DEFINE_NIC_PROPERTIES(SyborgVirtIOProxy, nic), DEFINE_VIRTIO_NET_FEATURES(SyborgVirtIOProxy, host_features), + DEFINE_PROP_UINT32("x-txtimer", SyborgVirtIOProxy, + net.txtimer, TX_TIMER_INTERVAL), + DEFINE_PROP_INT32("x-txburst", SyborgVirtIOProxy, + net.txburst, TX_BURST), + DEFINE_PROP_STRING("tx", SyborgVirtIOProxy, net.tx), DEFINE_PROP_END_OF_LIST(), } }; diff --git a/hw/sysbus.c b/hw/sysbus.c index 1f7f138416..d817721420 100644 --- a/hw/sysbus.c +++ b/hw/sysbus.c @@ -82,7 +82,8 @@ void sysbus_pass_irq(SysBusDevice *dev, SysBusDevice *target) } } -void sysbus_init_mmio(SysBusDevice *dev, target_phys_addr_t size, int iofunc) +void sysbus_init_mmio(SysBusDevice *dev, target_phys_addr_t size, + ram_addr_t iofunc) { int n; diff --git a/hw/sysbus.h b/hw/sysbus.h index 1a8f289c75..5980901845 100644 --- a/hw/sysbus.h +++ b/hw/sysbus.h @@ -21,7 +21,7 @@ struct SysBusDevice { target_phys_addr_t addr; target_phys_addr_t size; mmio_mapfunc cb; - int iofunc; + ram_addr_t iofunc; } mmio[QDEV_MAX_MMIO]; }; @@ -39,7 +39,8 @@ typedef struct { void sysbus_register_dev(const char *name, size_t size, sysbus_initfn init); void sysbus_register_withprop(SysBusDeviceInfo *info); void *sysbus_new(void); -void sysbus_init_mmio(SysBusDevice *dev, target_phys_addr_t size, int iofunc); +void sysbus_init_mmio(SysBusDevice *dev, target_phys_addr_t size, + ram_addr_t iofunc); void sysbus_init_mmio_cb(SysBusDevice *dev, target_phys_addr_t size, mmio_mapfunc cb); void sysbus_init_irq(SysBusDevice *dev, qemu_irq *p); diff --git a/hw/tc6393xb_template.h b/hw/tc6393xb_template.h index 37bf8336be..1ccf6e8dfe 100644 --- a/hw/tc6393xb_template.h +++ b/hw/tc6393xb_template.h @@ -38,12 +38,10 @@ static void glue(tc6393xb_draw_graphic, BITS)(TC6393xbState *s) { int i; - int w_display; uint16_t *data_buffer; uint8_t *data_display; data_buffer = s->vram_ptr; - w_display = s->scr_width * BITS / 8; data_display = ds_get_data(s->ds); for(i = 0; i < s->scr_height; i++) { #if (BITS == 16) diff --git a/hw/tosa.c b/hw/tosa.c index ba6d9e73bf..cc8ce6d641 100644 --- a/hw/tosa.c +++ b/hw/tosa.c @@ -19,6 +19,7 @@ #include "boards.h" #include "i2c.h" #include "ssi.h" +#include "blockdev.h" #define TOSA_RAM 0x04000000 #define TOSA_ROM 0x00800000 diff --git a/hw/usb-msd.c b/hw/usb-msd.c index 65e9624e54..0a95d8d506 100644 --- a/hw/usb-msd.c +++ b/hw/usb-msd.c @@ -15,6 +15,7 @@ #include "console.h" #include "monitor.h" #include "sysemu.h" +#include "blockdev.h" //#define DEBUG_MSD @@ -575,7 +576,7 @@ static USBDevice *usb_msd_init(const char *filename) /* parse -usbdevice disk: syntax into drive opts */ snprintf(id, sizeof(id), "usb%d", nr++); - opts = qemu_opts_create(&qemu_drive_opts, id, 0); + opts = qemu_opts_create(qemu_find_opts("drive"), id, 0); p1 = strchr(filename, ':'); if (p1++) { diff --git a/hw/usb-net.c b/hw/usb-net.c index a43bd17636..70f9263291 100644 --- a/hw/usb-net.c +++ b/hw/usb-net.c @@ -1472,7 +1472,7 @@ static USBDevice *usb_net_init(const char *cmdline) QemuOpts *opts; int idx; - opts = qemu_opts_parse(&qemu_net_opts, cmdline, 0); + opts = qemu_opts_parse(qemu_find_opts("net"), cmdline, 0); if (!opts) { return NULL; } diff --git a/hw/usb-wacom.c b/hw/usb-wacom.c index fe052eb756..47f26cd0a3 100644 --- a/hw/usb-wacom.c +++ b/hw/usb-wacom.c @@ -160,6 +160,7 @@ static int usb_mouse_poll(USBWacomState *s, uint8_t *buf, int len) if (!s->mouse_grabbed) { s->eh_entry = qemu_add_mouse_event_handler(usb_mouse_event, s, 0, "QEMU PenPartner tablet"); + qemu_activate_mouse_event_handler(s->eh_entry); s->mouse_grabbed = 1; } @@ -197,6 +198,7 @@ static int usb_wacom_poll(USBWacomState *s, uint8_t *buf, int len) if (!s->mouse_grabbed) { s->eh_entry = qemu_add_mouse_event_handler(usb_wacom_event, s, 1, "QEMU PenPartner tablet"); + qemu_activate_mouse_event_handler(s->eh_entry); s->mouse_grabbed = 1; } @@ -334,8 +336,10 @@ static int usb_wacom_handle_control(USBDevice *dev, int request, int value, ret = 0; break; case WACOM_SET_REPORT: - qemu_remove_mouse_event_handler(s->eh_entry); - s->mouse_grabbed = 0; + if (s->mouse_grabbed) { + qemu_remove_mouse_event_handler(s->eh_entry); + s->mouse_grabbed = 0; + } s->mode = data[0]; ret = 0; break; @@ -397,7 +401,10 @@ static void usb_wacom_handle_destroy(USBDevice *dev) { USBWacomState *s = (USBWacomState *) dev; - qemu_remove_mouse_event_handler(s->eh_entry); + if (s->mouse_grabbed) { + qemu_remove_mouse_event_handler(s->eh_entry); + s->mouse_grabbed = 0; + } } static int usb_wacom_initfn(USBDevice *dev) diff --git a/hw/versatilepb.c b/hw/versatilepb.c index 1d049f2342..c51ee02c4d 100644 --- a/hw/versatilepb.c +++ b/hw/versatilepb.c @@ -16,6 +16,7 @@ #include "pci.h" #include "usb-ohci.h" #include "boards.h" +#include "blockdev.h" /* Primary interrupt controller. */ diff --git a/hw/vga.c b/hw/vga.c index b5c7ee7fe3..966185e03b 100644 --- a/hw/vga.c +++ b/hw/vga.c @@ -2313,13 +2313,6 @@ void vga_init(VGACommonState *s) register_ioport_write(0x1ce, 1, 2, vbe_ioport_write_index, s); register_ioport_write(0x1cf, 1, 2, vbe_ioport_write_data, s); - - /* old Bochs IO ports */ - register_ioport_read(0xff80, 1, 2, vbe_ioport_read_index, s); - register_ioport_read(0xff81, 1, 2, vbe_ioport_read_data, s); - - register_ioport_write(0xff80, 1, 2, vbe_ioport_write_index, s); - register_ioport_write(0xff81, 1, 2, vbe_ioport_write_data, s); #else register_ioport_read(0x1ce, 1, 2, vbe_ioport_read_index, s); register_ioport_read(0x1d0, 1, 2, vbe_ioport_read_data, s); diff --git a/hw/vhost.c b/hw/vhost.c index 65709d005d..8586f66bac 100644 --- a/hw/vhost.c +++ b/hw/vhost.c @@ -11,11 +11,9 @@ */ #include <sys/ioctl.h> -#include <sys/eventfd.h> #include "vhost.h" #include "hw/hw.h" -/* For range_get_last */ -#include "pci.h" +#include "range.h" #include <linux/vhost.h> static void vhost_dev_sync_region(struct vhost_dev *dev, @@ -456,11 +454,6 @@ static int vhost_virtqueue_init(struct vhost_dev *dev, }; struct VirtQueue *vvq = virtio_get_queue(vdev, idx); - if (!vdev->binding->set_guest_notifier) { - fprintf(stderr, "binding does not support guest notifiers\n"); - return -ENOSYS; - } - if (!vdev->binding->set_host_notifier) { fprintf(stderr, "binding does not support host notifiers\n"); return -ENOSYS; @@ -513,12 +506,6 @@ static int vhost_virtqueue_init(struct vhost_dev *dev, r = -errno; goto fail_alloc; } - r = vdev->binding->set_guest_notifier(vdev->binding_opaque, idx, true); - if (r < 0) { - fprintf(stderr, "Error binding guest notifier: %d\n", -r); - goto fail_guest_notifier; - } - r = vdev->binding->set_host_notifier(vdev->binding_opaque, idx, true); if (r < 0) { fprintf(stderr, "Error binding host notifier: %d\n", -r); @@ -528,12 +515,14 @@ static int vhost_virtqueue_init(struct vhost_dev *dev, file.fd = event_notifier_get_fd(virtio_queue_get_host_notifier(vvq)); r = ioctl(dev->control, VHOST_SET_VRING_KICK, &file); if (r) { + r = -errno; goto fail_kick; } file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq)); r = ioctl(dev->control, VHOST_SET_VRING_CALL, &file); if (r) { + r = -errno; goto fail_call; } @@ -543,8 +532,6 @@ fail_call: fail_kick: vdev->binding->set_host_notifier(vdev->binding_opaque, idx, false); fail_host_notifier: - vdev->binding->set_guest_notifier(vdev->binding_opaque, idx, false); -fail_guest_notifier: fail_alloc: cpu_physical_memory_unmap(vq->ring, virtio_queue_get_ring_size(vdev, idx), 0, 0); @@ -570,13 +557,6 @@ static void vhost_virtqueue_cleanup(struct vhost_dev *dev, .index = idx, }; int r; - r = vdev->binding->set_guest_notifier(vdev->binding_opaque, idx, false); - if (r < 0) { - fprintf(stderr, "vhost VQ %d guest cleanup failed: %d\n", idx, r); - fflush(stderr); - } - assert (r >= 0); - r = vdev->binding->set_host_notifier(vdev->binding_opaque, idx, false); if (r < 0) { fprintf(stderr, "vhost VQ %d host cleanup failed: %d\n", idx, r); @@ -649,15 +629,26 @@ void vhost_dev_cleanup(struct vhost_dev *hdev) int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) { int i, r; + if (!vdev->binding->set_guest_notifiers) { + fprintf(stderr, "binding does not support guest notifiers\n"); + r = -ENOSYS; + goto fail; + } + + r = vdev->binding->set_guest_notifiers(vdev->binding_opaque, true); + if (r < 0) { + fprintf(stderr, "Error binding guest notifier: %d\n", -r); + goto fail_notifiers; + } r = vhost_dev_set_features(hdev, hdev->log_enabled); if (r < 0) { - goto fail; + goto fail_features; } r = ioctl(hdev->control, VHOST_SET_MEM_TABLE, hdev->mem); if (r < 0) { r = -errno; - goto fail; + goto fail_mem; } for (i = 0; i < hdev->nvqs; ++i) { r = vhost_virtqueue_init(hdev, @@ -677,13 +668,14 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) (uint64_t)(unsigned long)hdev->log); if (r < 0) { r = -errno; - goto fail_vq; + goto fail_log; } } hdev->started = true; return 0; +fail_log: fail_vq: while (--i >= 0) { vhost_virtqueue_cleanup(hdev, @@ -691,13 +683,18 @@ fail_vq: hdev->vqs + i, i); } +fail_mem: +fail_features: + vdev->binding->set_guest_notifiers(vdev->binding_opaque, false); +fail_notifiers: fail: return r; } void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) { - int i; + int i, r; + for (i = 0; i < hdev->nvqs; ++i) { vhost_virtqueue_cleanup(hdev, vdev, @@ -706,6 +703,13 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) } vhost_client_sync_dirty_bitmap(&hdev->client, 0, (target_phys_addr_t)~0x0ull); + r = vdev->binding->set_guest_notifiers(vdev->binding_opaque, false); + if (r < 0) { + fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", r); + fflush(stderr); + } + assert (r >= 0); + hdev->started = false; qemu_free(hdev->log); hdev->log_size = 0; diff --git a/hw/vhost_net.c b/hw/vhost_net.c index 606aa0c1c9..c068be1f54 100644 --- a/hw/vhost_net.c +++ b/hw/vhost_net.c @@ -20,7 +20,6 @@ #ifdef CONFIG_VHOST_NET #include <linux/vhost.h> -#include <sys/eventfd.h> #include <sys/socket.h> #include <linux/kvm.h> #include <fcntl.h> @@ -51,7 +50,9 @@ unsigned vhost_net_get_features(struct vhost_net *net, unsigned features) if (!(net->dev.features & (1 << VIRTIO_RING_F_INDIRECT_DESC))) { features &= ~(1 << VIRTIO_RING_F_INDIRECT_DESC); } - features &= ~(1 << VIRTIO_NET_F_MRG_RXBUF); + if (!(net->dev.features & (1 << VIRTIO_NET_F_MRG_RXBUF))) { + features &= ~(1 << VIRTIO_NET_F_MRG_RXBUF); + } return features; } @@ -64,6 +65,9 @@ void vhost_net_ack_features(struct vhost_net *net, unsigned features) if (features & (1 << VIRTIO_RING_F_INDIRECT_DESC)) { net->dev.acked_features |= (1 << VIRTIO_RING_F_INDIRECT_DESC); } + if (features & (1 << VIRTIO_NET_F_MRG_RXBUF)) { + net->dev.acked_features |= (1 << VIRTIO_NET_F_MRG_RXBUF); + } } static int vhost_net_get_fd(VLANClientState *backend) @@ -98,6 +102,10 @@ struct vhost_net *vhost_net_init(VLANClientState *backend, int devfd) if (r < 0) { goto fail; } + if (!tap_has_vnet_hdr_len(backend, + sizeof(struct virtio_net_hdr_mrg_rxbuf))) { + net->dev.features &= ~(1 << VIRTIO_NET_F_MRG_RXBUF); + } if (~net->dev.features & net->dev.backend_features) { fprintf(stderr, "vhost lacks feature mask %" PRIu64 " for backend\n", (uint64_t)(~net->dev.features & net->dev.backend_features)); @@ -118,6 +126,10 @@ int vhost_net_start(struct vhost_net *net, { struct vhost_vring_file file = { }; int r; + if (net->dev.acked_features & (1 << VIRTIO_NET_F_MRG_RXBUF)) { + tap_set_vnet_hdr_len(net->vc, + sizeof(struct virtio_net_hdr_mrg_rxbuf)); + } net->dev.nvqs = 2; net->dev.vqs = net->vqs; @@ -139,12 +151,15 @@ int vhost_net_start(struct vhost_net *net, return 0; fail: file.fd = -1; - while (--file.index >= 0) { + while (file.index-- > 0) { int r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file); assert(r >= 0); } net->vc->info->poll(net->vc, true); vhost_dev_stop(&net->dev, dev); + if (net->dev.acked_features & (1 << VIRTIO_NET_F_MRG_RXBUF)) { + tap_set_vnet_hdr_len(net->vc, sizeof(struct virtio_net_hdr)); + } return r; } @@ -159,11 +174,17 @@ void vhost_net_stop(struct vhost_net *net, } net->vc->info->poll(net->vc, true); vhost_dev_stop(&net->dev, dev); + if (net->dev.acked_features & (1 << VIRTIO_NET_F_MRG_RXBUF)) { + tap_set_vnet_hdr_len(net->vc, sizeof(struct virtio_net_hdr)); + } } void vhost_net_cleanup(struct vhost_net *net) { vhost_dev_cleanup(&net->dev); + if (net->dev.acked_features & (1 << VIRTIO_NET_F_MRG_RXBUF)) { + tap_set_vnet_hdr_len(net->vc, sizeof(struct virtio_net_hdr)); + } qemu_free(net); } #else diff --git a/hw/virtex_ml507.c b/hw/virtex_ml507.c new file mode 100644 index 0000000000..fa605158e7 --- /dev/null +++ b/hw/virtex_ml507.c @@ -0,0 +1,276 @@ +/* + * Model of Xilinx Virtex5 ML507 PPC-440 refdesign. + * + * Copyright (c) 2010 Edgar E. Iglesias. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "sysbus.h" +#include "hw.h" +#include "pc.h" +#include "net.h" +#include "flash.h" +#include "sysemu.h" +#include "devices.h" +#include "boards.h" +#include "device_tree.h" +#include "loader.h" +#include "elf.h" +#include "qemu-log.h" + +#include "ppc.h" +#include "ppc4xx.h" +#include "ppc440.h" +#include "ppc405.h" + +#include "blockdev.h" +#include "xilinx.h" + +#define EPAPR_MAGIC (0x45504150) +#define FLASH_SIZE (16 * 1024 * 1024) + +static struct boot_info +{ + uint32_t bootstrap_pc; + uint32_t cmdline; + uint32_t fdt; + uint32_t ima_size; + void *vfdt; +} boot_info; + +/* Create reset TLB entries for BookE, spanning the 32bit addr space. */ +static void mmubooke_create_initial_mapping(CPUState *env, + target_ulong va, + target_phys_addr_t pa) +{ + ppcemb_tlb_t *tlb = &env->tlb[0].tlbe; + + tlb->attr = 0; + tlb->prot = PAGE_VALID | ((PAGE_READ | PAGE_WRITE | PAGE_EXEC) << 4); + tlb->size = 1 << 31; /* up to 0x80000000 */ + tlb->EPN = va & TARGET_PAGE_MASK; + tlb->RPN = pa & TARGET_PAGE_MASK; + tlb->PID = 0; + + tlb = &env->tlb[1].tlbe; + tlb->attr = 0; + tlb->prot = PAGE_VALID | ((PAGE_READ | PAGE_WRITE | PAGE_EXEC) << 4); + tlb->size = 1 << 31; /* up to 0xffffffff */ + tlb->EPN = 0x80000000 & TARGET_PAGE_MASK; + tlb->RPN = 0x80000000 & TARGET_PAGE_MASK; + tlb->PID = 0; +} + +static CPUState *ppc440_init_xilinx(ram_addr_t *ram_size, + int do_init, + const char *cpu_model, + clk_setup_t *cpu_clk, clk_setup_t *tb_clk, + uint32_t sysclk) +{ + CPUState *env; + qemu_irq *irqs; + + env = cpu_init(cpu_model); + if (!env) { + fprintf(stderr, "Unable to initialize CPU!\n"); + exit(1); + } + + cpu_clk->cb = NULL; /* We don't care about CPU clock frequency changes */ + cpu_clk->opaque = env; + /* Set time-base frequency to sysclk */ + tb_clk->cb = ppc_emb_timers_init(env, sysclk, PPC_INTERRUPT_DECR); + tb_clk->opaque = env; + + ppc_dcr_init(env, NULL, NULL); + + /* interrupt controller */ + irqs = qemu_mallocz(sizeof(qemu_irq) * PPCUIC_OUTPUT_NB); + irqs[PPCUIC_OUTPUT_INT] = ((qemu_irq *)env->irq_inputs)[PPC40x_INPUT_INT]; + irqs[PPCUIC_OUTPUT_CINT] = ((qemu_irq *)env->irq_inputs)[PPC40x_INPUT_CINT]; + ppcuic_init(env, irqs, 0x0C0, 0, 1); + return env; +} + +static void main_cpu_reset(void *opaque) +{ + CPUState *env = opaque; + struct boot_info *bi = env->load_info; + + cpu_reset(env); + /* Linux Kernel Parameters (passing device tree): + * r3: pointer to the fdt + * r4: 0 + * r5: 0 + * r6: epapr magic + * r7: size of IMA in bytes + * r8: 0 + * r9: 0 + */ + env->gpr[1] = (16<<20) - 8; + /* Provide a device-tree. */ + env->gpr[3] = bi->fdt; + env->nip = bi->bootstrap_pc; + + /* Create a mapping for the kernel. */ + mmubooke_create_initial_mapping(env, 0, 0); + env->gpr[6] = tswap32(EPAPR_MAGIC); + env->gpr[7] = bi->ima_size; +} + +#define BINARY_DEVICE_TREE_FILE "virtex-ml507.dtb" +static int xilinx_load_device_tree(target_phys_addr_t addr, + uint32_t ramsize, + target_phys_addr_t initrd_base, + target_phys_addr_t initrd_size, + const char *kernel_cmdline) +{ + char *path; + int fdt_size; +#ifdef CONFIG_FDT + void *fdt; + int r; + + /* Try the local "ppc.dtb" override. */ + fdt = load_device_tree("ppc.dtb", &fdt_size); + if (!fdt) { + path = qemu_find_file(QEMU_FILE_TYPE_BIOS, BINARY_DEVICE_TREE_FILE); + if (path) { + fdt = load_device_tree(path, &fdt_size); + qemu_free(path); + } + if (!fdt) { + return 0; + } + } + + r = qemu_devtree_setprop_string(fdt, "/chosen", "bootargs", kernel_cmdline); + if (r < 0) + fprintf(stderr, "couldn't set /chosen/bootargs\n"); + cpu_physical_memory_write (addr, (void *)fdt, fdt_size); +#else + /* We lack libfdt so we cannot manipulate the fdt. Just pass on the blob + to the kernel. */ + fdt_size = load_image_targphys("ppc.dtb", addr, 0x10000); + if (fdt_size < 0) { + path = qemu_find_file(QEMU_FILE_TYPE_BIOS, BINARY_DEVICE_TREE_FILE); + if (path) { + fdt_size = load_image_targphys(path, addr, 0x10000); + qemu_free(path); + } + } + + if (kernel_cmdline) { + fprintf(stderr, + "Warning: missing libfdt, cannot pass cmdline to kernel!\n"); + } +#endif + return fdt_size; +} + +static void virtex_init(ram_addr_t ram_size, + const char *boot_device, + const char *kernel_filename, + const char *kernel_cmdline, + const char *initrd_filename, const char *cpu_model) +{ + DeviceState *dev; + CPUState *env; + target_phys_addr_t ram_base = 0; + DriveInfo *dinfo; + ram_addr_t phys_ram; + ram_addr_t phys_flash; + qemu_irq irq[32], *cpu_irq; + clk_setup_t clk_setup[7]; + int kernel_size; + int i; + + /* init CPUs */ + if (cpu_model == NULL) { + cpu_model = "440-Xilinx"; + } + + memset(clk_setup, 0, sizeof(clk_setup)); + env = ppc440_init_xilinx(&ram_size, 1, cpu_model, &clk_setup[0], + &clk_setup[1], 400000000); + qemu_register_reset(main_cpu_reset, env); + + phys_ram = qemu_ram_alloc(NULL, "ram", ram_size); + cpu_register_physical_memory(ram_base, ram_size, phys_ram | IO_MEM_RAM); + + phys_flash = qemu_ram_alloc(NULL, "virtex.flash", FLASH_SIZE); + dinfo = drive_get(IF_PFLASH, 0, 0); + pflash_cfi01_register(0xfc000000, phys_flash, + dinfo ? dinfo->bdrv : NULL, (64 * 1024), + FLASH_SIZE >> 16, + 1, 0x89, 0x18, 0x0000, 0x0, 1); + + cpu_irq = (qemu_irq *) &env->irq_inputs[PPC40x_INPUT_INT]; + dev = xilinx_intc_create(0x81800000, cpu_irq[0], 0); + for (i = 0; i < 32; i++) { + irq[i] = qdev_get_gpio_in(dev, i); + } + + serial_mm_init(0x83e01003ULL, 2, irq[9], 115200, serial_hds[0], 1, 0); + + /* 2 timers at irq 2 @ 62 Mhz. */ + xilinx_timer_create(0x83c00000, irq[3], 2, 62 * 1000000); + + if (kernel_filename) { + uint64_t entry, low, high; + target_phys_addr_t boot_offset; + + /* Boots a kernel elf binary. */ + kernel_size = load_elf(kernel_filename, NULL, NULL, + &entry, &low, &high, 1, ELF_MACHINE, 0); + boot_info.bootstrap_pc = entry & 0x00ffffff; + + if (kernel_size < 0) { + boot_offset = 0x1200000; + /* If we failed loading ELF's try a raw image. */ + kernel_size = load_image_targphys(kernel_filename, + boot_offset, + ram_size); + boot_info.bootstrap_pc = boot_offset; + high = boot_info.bootstrap_pc + kernel_size + 8192; + } + + boot_info.ima_size = kernel_size; + + /* Provide a device-tree. */ + boot_info.fdt = high + (8192 * 2); + boot_info.fdt &= ~8191; + xilinx_load_device_tree(boot_info.fdt, ram_size, 0, 0, kernel_cmdline); + } + env->load_info = &boot_info; +} + +static QEMUMachine virtex_machine = { + .name = "virtex-ml507", + .desc = "Xilinx Virtex ML507 reference design", + .init = virtex_init, +}; + +static void virtex_machine_init(void) +{ + qemu_register_machine(&virtex_machine); +} + +machine_init(virtex_machine_init); diff --git a/hw/virtio-9p-debug.c b/hw/virtio-9p-debug.c index e4ab4bca5f..cff5b07297 100644 --- a/hw/virtio-9p-debug.c +++ b/hw/virtio-9p-debug.c @@ -169,15 +169,37 @@ static void pprint_stat(V9fsPDU *pdu, int rx, size_t *offsetp, const char *name) pprint_str(pdu, rx, offsetp, ", uid"); pprint_str(pdu, rx, offsetp, ", gid"); pprint_str(pdu, rx, offsetp, ", muid"); - if (dotu) { - pprint_str(pdu, rx, offsetp, ", extension"); - pprint_int32(pdu, rx, offsetp, ", uid"); - pprint_int32(pdu, rx, offsetp, ", gid"); - pprint_int32(pdu, rx, offsetp, ", muid"); - } + pprint_str(pdu, rx, offsetp, ", extension"); + pprint_int32(pdu, rx, offsetp, ", uid"); + pprint_int32(pdu, rx, offsetp, ", gid"); + pprint_int32(pdu, rx, offsetp, ", muid"); + fprintf(llogfile, "}"); +} + +static void pprint_stat_dotl(V9fsPDU *pdu, int rx, size_t *offsetp, + const char *name) +{ + fprintf(llogfile, "%s={", name); + pprint_qid(pdu, rx, offsetp, "qid"); + pprint_int32(pdu, rx, offsetp, ", st_mode"); + pprint_int64(pdu, rx, offsetp, ", st_nlink"); + pprint_int32(pdu, rx, offsetp, ", st_uid"); + pprint_int32(pdu, rx, offsetp, ", st_gid"); + pprint_int64(pdu, rx, offsetp, ", st_rdev"); + pprint_int64(pdu, rx, offsetp, ", st_size"); + pprint_int64(pdu, rx, offsetp, ", st_blksize"); + pprint_int64(pdu, rx, offsetp, ", st_blocks"); + pprint_int64(pdu, rx, offsetp, ", atime"); + pprint_int64(pdu, rx, offsetp, ", atime_nsec"); + pprint_int64(pdu, rx, offsetp, ", mtime"); + pprint_int64(pdu, rx, offsetp, ", mtime_nsec"); + pprint_int64(pdu, rx, offsetp, ", ctime"); + pprint_int64(pdu, rx, offsetp, ", ctime_nsec"); fprintf(llogfile, "}"); } + + static void pprint_strs(V9fsPDU *pdu, int rx, size_t *offsetp, const char *name) { int sg_count = get_sg_count(pdu, rx); @@ -327,7 +349,33 @@ void pprint_pdu(V9fsPDU *pdu) llogfile = fopen("/tmp/pdu.log", "w"); } + BUG_ON(!llogfile); + switch (pdu->id) { + case P9_TREADDIR: + fprintf(llogfile, "TREADDIR: ("); + pprint_int32(pdu, 0, &offset, "fid"); + pprint_int64(pdu, 0, &offset, ", initial offset"); + pprint_int32(pdu, 0, &offset, ", max count"); + break; + case P9_RREADDIR: + fprintf(llogfile, "RREADDIR: ("); + pprint_int32(pdu, 1, &offset, "count"); +#ifdef DEBUG_DATA + pprint_data(pdu, 1, &offset, ", data"); +#endif + break; + case P9_TMKDIR: + fprintf(llogfile, "TMKDIR: ("); + pprint_int32(pdu, 0, &offset, "fid"); + pprint_str(pdu, 0, &offset, "name"); + pprint_int32(pdu, 0, &offset, "mode"); + pprint_int32(pdu, 0, &offset, "gid"); + break; + case P9_RMKDIR: + fprintf(llogfile, "RMKDIR: ("); + pprint_qid(pdu, 0, &offset, "qid"); + break; case P9_TVERSION: fprintf(llogfile, "TVERSION: ("); pprint_int32(pdu, 0, &offset, "msize"); @@ -338,14 +386,20 @@ void pprint_pdu(V9fsPDU *pdu) pprint_int32(pdu, 1, &offset, "msize"); pprint_str(pdu, 1, &offset, ", version"); break; + case P9_TGETATTR: + fprintf(llogfile, "TGETATTR: ("); + pprint_int32(pdu, 0, &offset, "fid"); + break; + case P9_RGETATTR: + fprintf(llogfile, "RGETATTR: ("); + pprint_stat_dotl(pdu, 1, &offset, "getattr"); + break; case P9_TAUTH: fprintf(llogfile, "TAUTH: ("); pprint_int32(pdu, 0, &offset, "afid"); pprint_str(pdu, 0, &offset, ", uname"); pprint_str(pdu, 0, &offset, ", aname"); - if (dotu) { - pprint_int32(pdu, 0, &offset, ", n_uname"); - } + pprint_int32(pdu, 0, &offset, ", n_uname"); break; case P9_RAUTH: fprintf(llogfile, "RAUTH: ("); @@ -357,9 +411,7 @@ void pprint_pdu(V9fsPDU *pdu) pprint_int32(pdu, 0, &offset, ", afid"); pprint_str(pdu, 0, &offset, ", uname"); pprint_str(pdu, 0, &offset, ", aname"); - if (dotu) { - pprint_int32(pdu, 0, &offset, ", n_uname"); - } + pprint_int32(pdu, 0, &offset, ", n_uname"); break; case P9_RATTACH: fprintf(llogfile, "RATTACH: ("); @@ -371,9 +423,7 @@ void pprint_pdu(V9fsPDU *pdu) case P9_RERROR: fprintf(llogfile, "RERROR: ("); pprint_str(pdu, 1, &offset, "ename"); - if (dotu) { - pprint_int32(pdu, 1, &offset, ", ecode"); - } + pprint_int32(pdu, 1, &offset, ", ecode"); break; case P9_TFLUSH: fprintf(llogfile, "TFLUSH: ("); @@ -408,15 +458,58 @@ void pprint_pdu(V9fsPDU *pdu) pprint_str(pdu, 0, &offset, ", name"); pprint_int32(pdu, 0, &offset, ", perm"); pprint_int8(pdu, 0, &offset, ", mode"); - if (dotu) { - pprint_str(pdu, 0, &offset, ", extension"); - } + pprint_str(pdu, 0, &offset, ", extension"); break; case P9_RCREATE: fprintf(llogfile, "RCREATE: ("); pprint_qid(pdu, 1, &offset, "qid"); pprint_int32(pdu, 1, &offset, ", iounit"); break; + case P9_TSYMLINK: + fprintf(llogfile, "TSYMLINK: ("); + pprint_int32(pdu, 0, &offset, "fid"); + pprint_str(pdu, 0, &offset, ", name"); + pprint_str(pdu, 0, &offset, ", symname"); + pprint_int32(pdu, 0, &offset, ", gid"); + break; + case P9_RSYMLINK: + fprintf(llogfile, "RSYMLINK: ("); + pprint_qid(pdu, 1, &offset, "qid"); + break; + case P9_TLCREATE: + fprintf(llogfile, "TLCREATE: ("); + pprint_int32(pdu, 0, &offset, "dfid"); + pprint_str(pdu, 0, &offset, ", name"); + pprint_int32(pdu, 0, &offset, ", flags"); + pprint_int32(pdu, 0, &offset, ", mode"); + pprint_int32(pdu, 0, &offset, ", gid"); + break; + case P9_RLCREATE: + fprintf(llogfile, "RLCREATE: ("); + pprint_qid(pdu, 1, &offset, "qid"); + pprint_int32(pdu, 1, &offset, ", iounit"); + break; + case P9_TMKNOD: + fprintf(llogfile, "TMKNOD: ("); + pprint_int32(pdu, 0, &offset, "fid"); + pprint_str(pdu, 0, &offset, "name"); + pprint_int32(pdu, 0, &offset, "mode"); + pprint_int32(pdu, 0, &offset, "major"); + pprint_int32(pdu, 0, &offset, "minor"); + pprint_int32(pdu, 0, &offset, "gid"); + break; + case P9_RMKNOD: + fprintf(llogfile, "RMKNOD: )"); + pprint_qid(pdu, 0, &offset, "qid"); + break; + case P9_TREADLINK: + fprintf(llogfile, "TREADLINK: ("); + pprint_int32(pdu, 0, &offset, "fid"); + break; + case P9_RREADLINK: + fprintf(llogfile, "RREADLINK: ("); + pprint_str(pdu, 0, &offset, "target"); + break; case P9_TREAD: fprintf(llogfile, "TREAD: ("); pprint_int32(pdu, 0, &offset, "fid"); @@ -450,6 +543,22 @@ void pprint_pdu(V9fsPDU *pdu) case P9_RCLUNK: fprintf(llogfile, "RCLUNK: ("); break; + case P9_TFSYNC: + fprintf(llogfile, "TFSYNC: ("); + pprint_int32(pdu, 0, &offset, "fid"); + break; + case P9_RFSYNC: + fprintf(llogfile, "RFSYNC: ("); + break; + case P9_TLINK: + fprintf(llogfile, "TLINK: ("); + pprint_int32(pdu, 0, &offset, "fid"); + pprint_str(pdu, 0, &offset, ", oldpath"); + pprint_str(pdu, 0, &offset, ", newpath"); + break; + case P9_RLINK: + fprintf(llogfile, "RLINK: ("); + break; case P9_TREMOVE: fprintf(llogfile, "TREMOVE: ("); pprint_int32(pdu, 0, &offset, "fid"); @@ -475,6 +584,56 @@ void pprint_pdu(V9fsPDU *pdu) case P9_RWSTAT: fprintf(llogfile, "RWSTAT: ("); break; + case P9_TXATTRWALK: + fprintf(llogfile, "TXATTRWALK: ("); + pprint_int32(pdu, 0, &offset, "fid"); + pprint_int32(pdu, 0, &offset, ", newfid"); + pprint_str(pdu, 0, &offset, ", xattr name"); + break; + case P9_RXATTRWALK: + fprintf(llogfile, "RXATTRWALK: ("); + pprint_int64(pdu, 1, &offset, "xattrsize"); + case P9_TXATTRCREATE: + fprintf(llogfile, "TXATTRCREATE: ("); + pprint_int32(pdu, 0, &offset, "fid"); + pprint_str(pdu, 0, &offset, ", name"); + pprint_int64(pdu, 0, &offset, ", xattrsize"); + pprint_int32(pdu, 0, &offset, ", flags"); + break; + case P9_RXATTRCREATE: + fprintf(llogfile, "RXATTRCREATE: ("); + break; + case P9_TLOCK: + fprintf(llogfile, "TLOCK: ("); + pprint_int32(pdu, 0, &offset, "fid"); + pprint_int8(pdu, 0, &offset, ", type"); + pprint_int32(pdu, 0, &offset, ", flags"); + pprint_int64(pdu, 0, &offset, ", start"); + pprint_int64(pdu, 0, &offset, ", length"); + pprint_int32(pdu, 0, &offset, ", proc_id"); + pprint_str(pdu, 0, &offset, ", client_id"); + break; + case P9_RLOCK: + fprintf(llogfile, "RLOCK: ("); + pprint_int8(pdu, 0, &offset, "status"); + break; + case P9_TGETLOCK: + fprintf(llogfile, "TGETLOCK: ("); + pprint_int32(pdu, 0, &offset, "fid"); + pprint_int8(pdu, 0, &offset, ", type"); + pprint_int64(pdu, 0, &offset, ", start"); + pprint_int64(pdu, 0, &offset, ", length"); + pprint_int32(pdu, 0, &offset, ", proc_id"); + pprint_str(pdu, 0, &offset, ", client_id"); + break; + case P9_RGETLOCK: + fprintf(llogfile, "RGETLOCK: ("); + pprint_int8(pdu, 0, &offset, "type"); + pprint_int64(pdu, 0, &offset, ", start"); + pprint_int64(pdu, 0, &offset, ", length"); + pprint_int32(pdu, 0, &offset, ", proc_id"); + pprint_str(pdu, 0, &offset, ", client_id"); + break; default: fprintf(llogfile, "unknown(%d): (", pdu->id); break; diff --git a/hw/virtio-9p-debug.h b/hw/virtio-9p-debug.h index 0104be5eb3..d9a249118d 100644 --- a/hw/virtio-9p-debug.h +++ b/hw/virtio-9p-debug.h @@ -1,7 +1,6 @@ #ifndef _QEMU_VIRTIO_9P_DEBUG_H #define _QEMU_VIRTIO_9P_DEBUG_H -extern int dotu; void pprint_pdu(V9fsPDU *pdu); #endif diff --git a/hw/virtio-9p-local.c b/hw/virtio-9p-local.c index 04f7f6f501..0d520201b4 100644 --- a/hw/virtio-9p-local.c +++ b/hw/virtio-9p-local.c @@ -12,6 +12,7 @@ */ #include "virtio.h" #include "virtio-9p.h" +#include "virtio-9p-xattr.h" #include <arpa/inet.h> #include <pwd.h> #include <grp.h> @@ -19,14 +20,6 @@ #include <sys/un.h> #include <attr/xattr.h> -static const char *rpath(FsContext *ctx, const char *path) -{ - /* FIXME: so wrong... */ - static char buffer[4096]; - snprintf(buffer, sizeof(buffer), "%s/%s", ctx->fs_root, path); - return buffer; -} - static int local_lstat(FsContext *fs_ctx, const char *path, struct stat *stbuf) { @@ -101,8 +94,14 @@ static int local_post_create_passthrough(FsContext *fs_ctx, const char *path, if (chmod(rpath(fs_ctx, path), credp->fc_mode & 07777) < 0) { return -1; } - if (chown(rpath(fs_ctx, path), credp->fc_uid, credp->fc_gid) < 0) { - return -1; + if (lchown(rpath(fs_ctx, path), credp->fc_uid, credp->fc_gid) < 0) { + /* + * If we fail to change ownership and if we are + * using security model none. Ignore the error + */ + if (fs_ctx->fs_sm != SM_NONE) { + return -1; + } } return 0; } @@ -122,7 +121,8 @@ static ssize_t local_readlink(FsContext *fs_ctx, const char *path, } while (tsize == -1 && errno == EINTR); close(fd); return tsize; - } else if (fs_ctx->fs_sm == SM_PASSTHROUGH) { + } else if ((fs_ctx->fs_sm == SM_PASSTHROUGH) || + (fs_ctx->fs_sm == SM_NONE)) { tsize = readlink(rpath(fs_ctx, path), buf, bufsz); } return tsize; @@ -168,28 +168,42 @@ static void local_seekdir(FsContext *ctx, DIR *dir, off_t off) return seekdir(dir, off); } -static ssize_t local_readv(FsContext *ctx, int fd, const struct iovec *iov, - int iovcnt) +static ssize_t local_preadv(FsContext *ctx, int fd, const struct iovec *iov, + int iovcnt, off_t offset) { - return readv(fd, iov, iovcnt); -} - -static off_t local_lseek(FsContext *ctx, int fd, off_t offset, int whence) -{ - return lseek(fd, offset, whence); +#ifdef CONFIG_PREADV + return preadv(fd, iov, iovcnt, offset); +#else + int err = lseek(fd, offset, SEEK_SET); + if (err == -1) { + return err; + } else { + return readv(fd, iov, iovcnt); + } +#endif } -static ssize_t local_writev(FsContext *ctx, int fd, const struct iovec *iov, - int iovcnt) +static ssize_t local_pwritev(FsContext *ctx, int fd, const struct iovec *iov, + int iovcnt, off_t offset) { - return writev(fd, iov, iovcnt); +#ifdef CONFIG_PREADV + return pwritev(fd, iov, iovcnt, offset); +#else + int err = lseek(fd, offset, SEEK_SET); + if (err == -1) { + return err; + } else { + return writev(fd, iov, iovcnt); + } +#endif } static int local_chmod(FsContext *fs_ctx, const char *path, FsCred *credp) { if (fs_ctx->fs_sm == SM_MAPPED) { return local_set_xattr(rpath(fs_ctx, path), credp); - } else if (fs_ctx->fs_sm == SM_PASSTHROUGH) { + } else if ((fs_ctx->fs_sm == SM_PASSTHROUGH) || + (fs_ctx->fs_sm == SM_NONE)) { return chmod(rpath(fs_ctx, path), credp->fc_mode); } return -1; @@ -211,7 +225,8 @@ static int local_mknod(FsContext *fs_ctx, const char *path, FsCred *credp) serrno = errno; goto err_end; } - } else if (fs_ctx->fs_sm == SM_PASSTHROUGH) { + } else if ((fs_ctx->fs_sm == SM_PASSTHROUGH) || + (fs_ctx->fs_sm == SM_NONE)) { err = mknod(rpath(fs_ctx, path), credp->fc_mode, credp->fc_rdev); if (err == -1) { return err; @@ -247,7 +262,8 @@ static int local_mkdir(FsContext *fs_ctx, const char *path, FsCred *credp) serrno = errno; goto err_end; } - } else if (fs_ctx->fs_sm == SM_PASSTHROUGH) { + } else if ((fs_ctx->fs_sm == SM_PASSTHROUGH) || + (fs_ctx->fs_sm == SM_NONE)) { err = mkdir(rpath(fs_ctx, path), credp->fc_mode); if (err == -1) { return err; @@ -316,7 +332,8 @@ static int local_open2(FsContext *fs_ctx, const char *path, int flags, serrno = errno; goto err_end; } - } else if (fs_ctx->fs_sm == SM_PASSTHROUGH) { + } else if ((fs_ctx->fs_sm == SM_PASSTHROUGH) || + (fs_ctx->fs_sm == SM_NONE)) { fd = open(rpath(fs_ctx, path), flags, credp->fc_mode); if (fd == -1) { return fd; @@ -372,15 +389,23 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath, serrno = errno; goto err_end; } - } else if (fs_ctx->fs_sm == SM_PASSTHROUGH) { + } else if ((fs_ctx->fs_sm == SM_PASSTHROUGH) || + (fs_ctx->fs_sm == SM_NONE)) { err = symlink(oldpath, rpath(fs_ctx, newpath)); if (err) { return err; } err = lchown(rpath(fs_ctx, newpath), credp->fc_uid, credp->fc_gid); if (err == -1) { - serrno = errno; - goto err_end; + /* + * If we fail to change ownership and if we are + * using security model none. Ignore the error + */ + if (fs_ctx->fs_sm != SM_NONE) { + serrno = errno; + goto err_end; + } else + err = 0; } } return err; @@ -426,9 +451,6 @@ static int local_rename(FsContext *ctx, const char *oldpath, int err; tmp = qemu_strdup(rpath(ctx, oldpath)); - if (tmp == NULL) { - return -1; - } err = rename(tmp, rpath(ctx, newpath)); if (err == -1) { @@ -445,18 +467,22 @@ static int local_rename(FsContext *ctx, const char *oldpath, static int local_chown(FsContext *fs_ctx, const char *path, FsCred *credp) { - if (fs_ctx->fs_sm == SM_MAPPED) { + if ((credp->fc_uid == -1 && credp->fc_gid == -1) || + (fs_ctx->fs_sm == SM_PASSTHROUGH)) { + return lchown(rpath(fs_ctx, path), credp->fc_uid, credp->fc_gid); + } else if (fs_ctx->fs_sm == SM_MAPPED) { return local_set_xattr(rpath(fs_ctx, path), credp); - } else if (fs_ctx->fs_sm == SM_PASSTHROUGH) { + } else if ((fs_ctx->fs_sm == SM_PASSTHROUGH) || + (fs_ctx->fs_sm == SM_NONE)) { return lchown(rpath(fs_ctx, path), credp->fc_uid, credp->fc_gid); } return -1; } -static int local_utime(FsContext *ctx, const char *path, - const struct utimbuf *buf) +static int local_utimensat(FsContext *s, const char *path, + const struct timespec *buf) { - return utime(rpath(ctx, path), buf); + return utimensat(AT_FDCWD, rpath(s, path), buf, AT_SYMLINK_NOFOLLOW); } static int local_remove(FsContext *ctx, const char *path) @@ -469,6 +495,36 @@ static int local_fsync(FsContext *ctx, int fd) return fsync(fd); } +static int local_statfs(FsContext *s, const char *path, struct statfs *stbuf) +{ + return statfs(rpath(s, path), stbuf); +} + +static ssize_t local_lgetxattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + return v9fs_get_xattr(ctx, path, name, value, size); +} + +static ssize_t local_llistxattr(FsContext *ctx, const char *path, + void *value, size_t size) +{ + return v9fs_list_xattr(ctx, path, value, size); +} + +static int local_lsetxattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags) +{ + return v9fs_set_xattr(ctx, path, name, value, size, flags); +} + +static int local_lremovexattr(FsContext *ctx, + const char *path, const char *name) +{ + return v9fs_remove_xattr(ctx, path, name); +} + + FileOperations local_ops = { .lstat = local_lstat, .readlink = local_readlink, @@ -480,9 +536,8 @@ FileOperations local_ops = { .telldir = local_telldir, .readdir = local_readdir, .seekdir = local_seekdir, - .readv = local_readv, - .lseek = local_lseek, - .writev = local_writev, + .preadv = local_preadv, + .pwritev = local_pwritev, .chmod = local_chmod, .mknod = local_mknod, .mkdir = local_mkdir, @@ -493,7 +548,12 @@ FileOperations local_ops = { .truncate = local_truncate, .rename = local_rename, .chown = local_chown, - .utime = local_utime, + .utimensat = local_utimensat, .remove = local_remove, .fsync = local_fsync, + .statfs = local_statfs, + .lgetxattr = local_lgetxattr, + .llistxattr = local_llistxattr, + .lsetxattr = local_lsetxattr, + .lremovexattr = local_lremovexattr, }; diff --git a/hw/virtio-9p-posix-acl.c b/hw/virtio-9p-posix-acl.c new file mode 100644 index 0000000000..3978d0cf71 --- /dev/null +++ b/hw/virtio-9p-posix-acl.c @@ -0,0 +1,140 @@ +/* + * Virtio 9p system.posix* xattr callback + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include <sys/types.h> +#include <attr/xattr.h> +#include "virtio.h" +#include "virtio-9p.h" +#include "file-op-9p.h" +#include "virtio-9p-xattr.h" + +#define MAP_ACL_ACCESS "user.virtfs.system.posix_acl_access" +#define MAP_ACL_DEFAULT "user.virtfs.system.posix_acl_default" +#define ACL_ACCESS "system.posix_acl_access" +#define ACL_DEFAULT "system.posix_acl_default" + +static ssize_t mp_pacl_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + return lgetxattr(rpath(ctx, path), MAP_ACL_ACCESS, value, size); +} + +static ssize_t mp_pacl_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t osize) +{ + ssize_t len = sizeof(ACL_ACCESS); + + if (!value) { + return len; + } + + if (osize < len) { + errno = ERANGE; + return -1; + } + + strncpy(value, ACL_ACCESS, len); + return 0; +} + +static int mp_pacl_setxattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags) +{ + return lsetxattr(rpath(ctx, path), MAP_ACL_ACCESS, value, size, flags); +} + +static int mp_pacl_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + int ret; + ret = lremovexattr(rpath(ctx, path), MAP_ACL_ACCESS); + if (ret == -1 && errno == ENODATA) { + /* + * We don't get ENODATA error when trying to remote a + * posix acl that is not present. So don't throw the error + * even in case of mapped security model + */ + errno = 0; + ret = 0; + } + return ret; +} + +static ssize_t mp_dacl_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + return lgetxattr(rpath(ctx, path), MAP_ACL_DEFAULT, value, size); +} + +static ssize_t mp_dacl_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t osize) +{ + ssize_t len = sizeof(ACL_DEFAULT); + + if (!value) { + return len; + } + + if (osize < len) { + errno = ERANGE; + return -1; + } + + strncpy(value, ACL_DEFAULT, len); + return 0; +} + +static int mp_dacl_setxattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags) +{ + return lsetxattr(rpath(ctx, path), MAP_ACL_DEFAULT, value, size, flags); +} + +static int mp_dacl_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + return lremovexattr(rpath(ctx, path), MAP_ACL_DEFAULT); +} + + +XattrOperations mapped_pacl_xattr = { + .name = "system.posix_acl_access", + .getxattr = mp_pacl_getxattr, + .setxattr = mp_pacl_setxattr, + .listxattr = mp_pacl_listxattr, + .removexattr = mp_pacl_removexattr, +}; + +XattrOperations mapped_dacl_xattr = { + .name = "system.posix_acl_default", + .getxattr = mp_dacl_getxattr, + .setxattr = mp_dacl_setxattr, + .listxattr = mp_dacl_listxattr, + .removexattr = mp_dacl_removexattr, +}; + +XattrOperations passthrough_acl_xattr = { + .name = "system.posix_acl_", + .getxattr = pt_getxattr, + .setxattr = pt_setxattr, + .listxattr = pt_listxattr, + .removexattr = pt_removexattr, +}; + +XattrOperations none_acl_xattr = { + .name = "system.posix_acl_", + .getxattr = notsup_getxattr, + .setxattr = notsup_setxattr, + .listxattr = notsup_listxattr, + .removexattr = notsup_removexattr, +}; diff --git a/hw/virtio-9p-xattr-user.c b/hw/virtio-9p-xattr-user.c new file mode 100644 index 0000000000..faa02a1911 --- /dev/null +++ b/hw/virtio-9p-xattr-user.c @@ -0,0 +1,109 @@ +/* + * Virtio 9p user. xattr callback + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include <sys/types.h> +#include "virtio.h" +#include "virtio-9p.h" +#include "file-op-9p.h" +#include "virtio-9p-xattr.h" + + +static ssize_t mp_user_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + if (strncmp(name, "user.virtfs.", 12) == 0) { + /* + * Don't allow fetch of user.virtfs namesapce + * in case of mapped security + */ + errno = ENOATTR; + return -1; + } + return lgetxattr(rpath(ctx, path), name, value, size); +} + +static ssize_t mp_user_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t size) +{ + int name_size = strlen(name) + 1; + if (strncmp(name, "user.virtfs.", 12) == 0) { + + /* check if it is a mapped posix acl */ + if (strncmp(name, "user.virtfs.system.posix_acl_", 29) == 0) { + /* adjust the name and size */ + name += 12; + name_size -= 12; + } else { + /* + * Don't allow fetch of user.virtfs namesapce + * in case of mapped security + */ + return 0; + } + } + if (!value) { + return name_size; + } + + if (size < name_size) { + errno = ERANGE; + return -1; + } + + strncpy(value, name, name_size); + return name_size; +} + +static int mp_user_setxattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags) +{ + if (strncmp(name, "user.virtfs.", 12) == 0) { + /* + * Don't allow fetch of user.virtfs namesapce + * in case of mapped security + */ + errno = EACCES; + return -1; + } + return lsetxattr(rpath(ctx, path), name, value, size, flags); +} + +static int mp_user_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + if (strncmp(name, "user.virtfs.", 12) == 0) { + /* + * Don't allow fetch of user.virtfs namesapce + * in case of mapped security + */ + errno = EACCES; + return -1; + } + return lremovexattr(rpath(ctx, path), name); +} + +XattrOperations mapped_user_xattr = { + .name = "user.", + .getxattr = mp_user_getxattr, + .setxattr = mp_user_setxattr, + .listxattr = mp_user_listxattr, + .removexattr = mp_user_removexattr, +}; + +XattrOperations passthrough_user_xattr = { + .name = "user.", + .getxattr = pt_getxattr, + .setxattr = pt_setxattr, + .listxattr = pt_listxattr, + .removexattr = pt_removexattr, +}; diff --git a/hw/virtio-9p-xattr.c b/hw/virtio-9p-xattr.c new file mode 100644 index 0000000000..175f372c39 --- /dev/null +++ b/hw/virtio-9p-xattr.c @@ -0,0 +1,156 @@ +/* + * Virtio 9p xattr callback + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "virtio.h" +#include "virtio-9p.h" +#include "file-op-9p.h" +#include "virtio-9p-xattr.h" + + +static XattrOperations *get_xattr_operations(XattrOperations **h, + const char *name) +{ + XattrOperations *xops; + for (xops = *(h)++; xops != NULL; xops = *(h)++) { + if (!strncmp(name, xops->name, strlen(xops->name))) { + return xops; + } + } + return NULL; +} + +ssize_t v9fs_get_xattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + XattrOperations *xops = get_xattr_operations(ctx->xops, name); + if (xops) { + return xops->getxattr(ctx, path, name, value, size); + } + errno = -EOPNOTSUPP; + return -1; +} + +ssize_t pt_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t size) +{ + int name_size = strlen(name) + 1; + if (!value) { + return name_size; + } + + if (size < name_size) { + errno = ERANGE; + return -1; + } + + strncpy(value, name, name_size); + return name_size; +} + + +/* + * Get the list and pass to each layer to find out whether + * to send the data or not + */ +ssize_t v9fs_list_xattr(FsContext *ctx, const char *path, + void *value, size_t vsize) +{ + ssize_t size = 0; + void *ovalue = value; + XattrOperations *xops; + char *orig_value, *orig_value_start; + ssize_t xattr_len, parsed_len = 0, attr_len; + + /* Get the actual len */ + xattr_len = llistxattr(rpath(ctx, path), value, 0); + + /* Now fetch the xattr and find the actual size */ + orig_value = qemu_malloc(xattr_len); + xattr_len = llistxattr(rpath(ctx, path), orig_value, xattr_len); + + /* store the orig pointer */ + orig_value_start = orig_value; + while (xattr_len > parsed_len) { + xops = get_xattr_operations(ctx->xops, orig_value); + if (!xops) { + goto next_entry; + } + + if (!value) { + size += xops->listxattr(ctx, path, orig_value, value, vsize); + } else { + size = xops->listxattr(ctx, path, orig_value, value, vsize); + if (size < 0) { + goto err_out; + } + value += size; + vsize -= size; + } +next_entry: + /* Got the next entry */ + attr_len = strlen(orig_value) + 1; + parsed_len += attr_len; + orig_value += attr_len; + } + if (value) { + size = value - ovalue; + } + +err_out: + qemu_free(orig_value_start); + return size; +} + +int v9fs_set_xattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags) +{ + XattrOperations *xops = get_xattr_operations(ctx->xops, name); + if (xops) { + return xops->setxattr(ctx, path, name, value, size, flags); + } + errno = -EOPNOTSUPP; + return -1; + +} + +int v9fs_remove_xattr(FsContext *ctx, + const char *path, const char *name) +{ + XattrOperations *xops = get_xattr_operations(ctx->xops, name); + if (xops) { + return xops->removexattr(ctx, path, name); + } + errno = -EOPNOTSUPP; + return -1; + +} + +XattrOperations *mapped_xattr_ops[] = { + &mapped_user_xattr, + &mapped_pacl_xattr, + &mapped_dacl_xattr, + NULL, +}; + +XattrOperations *passthrough_xattr_ops[] = { + &passthrough_user_xattr, + &passthrough_acl_xattr, + NULL, +}; + +/* for .user none model should be same as passthrough */ +XattrOperations *none_xattr_ops[] = { + &passthrough_user_xattr, + &none_acl_xattr, + NULL, +}; diff --git a/hw/virtio-9p-xattr.h b/hw/virtio-9p-xattr.h new file mode 100644 index 0000000000..a6e31a152f --- /dev/null +++ b/hw/virtio-9p-xattr.h @@ -0,0 +1,103 @@ +/* + * Virtio 9p + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#ifndef _QEMU_VIRTIO_9P_XATTR_H +#define _QEMU_VIRTIO_9P_XATTR_H + +#include <attr/xattr.h> + +typedef struct xattr_operations +{ + const char *name; + ssize_t (*getxattr)(FsContext *ctx, const char *path, + const char *name, void *value, size_t size); + ssize_t (*listxattr)(FsContext *ctx, const char *path, + char *name, void *value, size_t size); + int (*setxattr)(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags); + int (*removexattr)(FsContext *ctx, + const char *path, const char *name); +} XattrOperations; + + +extern XattrOperations mapped_user_xattr; +extern XattrOperations passthrough_user_xattr; + +extern XattrOperations mapped_pacl_xattr; +extern XattrOperations mapped_dacl_xattr; +extern XattrOperations passthrough_acl_xattr; +extern XattrOperations none_acl_xattr; + +extern XattrOperations *mapped_xattr_ops[]; +extern XattrOperations *passthrough_xattr_ops[]; +extern XattrOperations *none_xattr_ops[]; + +extern ssize_t v9fs_get_xattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size); +extern ssize_t v9fs_list_xattr(FsContext *ctx, const char *path, + void *value, size_t vsize); +extern int v9fs_set_xattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags); +extern int v9fs_remove_xattr(FsContext *ctx, + const char *path, const char *name); +extern ssize_t pt_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t size); + +static inline ssize_t pt_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + return lgetxattr(rpath(ctx, path), name, value, size); +} + +static inline int pt_setxattr(FsContext *ctx, const char *path, + const char *name, void *value, + size_t size, int flags) +{ + return lsetxattr(rpath(ctx, path), name, value, size, flags); +} + +static inline int pt_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + return lremovexattr(rpath(ctx, path), name); +} + +static inline ssize_t notsup_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, + size_t size) +{ + errno = ENOTSUP; + return -1; +} + +static inline int notsup_setxattr(FsContext *ctx, const char *path, + const char *name, void *value, + size_t size, int flags) +{ + errno = ENOTSUP; + return -1; +} + +static inline ssize_t notsup_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t size) +{ + return 0; +} + +static inline int notsup_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + errno = ENOTSUP; + return -1; +} + +#endif diff --git a/hw/virtio-9p.c b/hw/virtio-9p.c index f8c85c3d28..daade77ed9 100644 --- a/hw/virtio-9p.c +++ b/hw/virtio-9p.c @@ -17,8 +17,8 @@ #include "virtio-9p.h" #include "fsdev/qemu-fsdev.h" #include "virtio-9p-debug.h" +#include "virtio-9p-xattr.h" -int dotu = 1; int debug_9p_pdu; enum { @@ -135,21 +135,16 @@ static void v9fs_do_seekdir(V9fsState *s, DIR *dir, off_t off) return s->ops->seekdir(&s->ctx, dir, off); } -static int v9fs_do_readv(V9fsState *s, int fd, const struct iovec *iov, - int iovcnt) +static int v9fs_do_preadv(V9fsState *s, int fd, const struct iovec *iov, + int iovcnt, int64_t offset) { - return s->ops->readv(&s->ctx, fd, iov, iovcnt); + return s->ops->preadv(&s->ctx, fd, iov, iovcnt, offset); } -static off_t v9fs_do_lseek(V9fsState *s, int fd, off_t offset, int whence) +static int v9fs_do_pwritev(V9fsState *s, int fd, const struct iovec *iov, + int iovcnt, int64_t offset) { - return s->ops->lseek(&s->ctx, fd, offset, whence); -} - -static int v9fs_do_writev(V9fsState *s, int fd, const struct iovec *iov, - int iovcnt) -{ - return s->ops->writev(&s->ctx, fd, iov, iovcnt); + return s->ops->pwritev(&s->ctx, fd, iov, iovcnt, offset); } static int v9fs_do_chmod(V9fsState *s, V9fsString *path, mode_t mode) @@ -160,26 +155,29 @@ static int v9fs_do_chmod(V9fsState *s, V9fsString *path, mode_t mode) return s->ops->chmod(&s->ctx, path->data, &cred); } -static int v9fs_do_mknod(V9fsState *s, V9fsCreateState *vs, mode_t mode, - dev_t dev) +static int v9fs_do_mknod(V9fsState *s, char *name, + mode_t mode, dev_t dev, uid_t uid, gid_t gid) { FsCred cred; cred_init(&cred); - cred.fc_uid = vs->fidp->uid; + cred.fc_uid = uid; + cred.fc_gid = gid; cred.fc_mode = mode; cred.fc_rdev = dev; - return s->ops->mknod(&s->ctx, vs->fullname.data, &cred); + return s->ops->mknod(&s->ctx, name, &cred); } -static int v9fs_do_mkdir(V9fsState *s, V9fsCreateState *vs) +static int v9fs_do_mkdir(V9fsState *s, char *name, mode_t mode, + uid_t uid, gid_t gid) { FsCred cred; cred_init(&cred); - cred.fc_uid = vs->fidp->uid; - cred.fc_mode = vs->perm & 0777; + cred.fc_uid = uid; + cred.fc_gid = gid; + cred.fc_mode = mode; - return s->ops->mkdir(&s->ctx, vs->fullname.data, &cred); + return s->ops->mkdir(&s->ctx, name, &cred); } static int v9fs_do_fstat(V9fsState *s, int fd, struct stat *stbuf) @@ -187,28 +185,30 @@ static int v9fs_do_fstat(V9fsState *s, int fd, struct stat *stbuf) return s->ops->fstat(&s->ctx, fd, stbuf); } -static int v9fs_do_open2(V9fsState *s, V9fsCreateState *vs) +static int v9fs_do_open2(V9fsState *s, char *fullname, uid_t uid, gid_t gid, + int flags, int mode) { FsCred cred; - int flags; cred_init(&cred); - cred.fc_uid = vs->fidp->uid; - cred.fc_mode = vs->perm & 0777; - flags = omode_to_uflags(vs->mode) | O_CREAT; + cred.fc_uid = uid; + cred.fc_gid = gid; + cred.fc_mode = mode & 07777; + flags = flags; - return s->ops->open2(&s->ctx, vs->fullname.data, flags, &cred); + return s->ops->open2(&s->ctx, fullname, flags, &cred); } -static int v9fs_do_symlink(V9fsState *s, V9fsCreateState *vs) +static int v9fs_do_symlink(V9fsState *s, V9fsFidState *fidp, + const char *oldpath, const char *newpath, gid_t gid) { FsCred cred; cred_init(&cred); - cred.fc_uid = vs->fidp->uid; - cred.fc_mode = vs->perm | 0777; + cred.fc_uid = fidp->uid; + cred.fc_gid = gid; + cred.fc_mode = 0777; - return s->ops->symlink(&s->ctx, vs->extension.data, vs->fullname.data, - &cred); + return s->ops->symlink(&s->ctx, oldpath, newpath, &cred); } static int v9fs_do_link(V9fsState *s, V9fsString *oldpath, V9fsString *newpath) @@ -237,10 +237,10 @@ static int v9fs_do_chown(V9fsState *s, V9fsString *path, uid_t uid, gid_t gid) return s->ops->chown(&s->ctx, path->data, &cred); } -static int v9fs_do_utime(V9fsState *s, V9fsString *path, - const struct utimbuf *buf) +static int v9fs_do_utimensat(V9fsState *s, V9fsString *path, + const struct timespec times[2]) { - return s->ops->utime(&s->ctx, path->data, buf); + return s->ops->utimensat(&s->ctx, path->data, times); } static int v9fs_do_remove(V9fsState *s, V9fsString *path) @@ -253,6 +253,42 @@ static int v9fs_do_fsync(V9fsState *s, int fd) return s->ops->fsync(&s->ctx, fd); } +static int v9fs_do_statfs(V9fsState *s, V9fsString *path, struct statfs *stbuf) +{ + return s->ops->statfs(&s->ctx, path->data, stbuf); +} + +static ssize_t v9fs_do_lgetxattr(V9fsState *s, V9fsString *path, + V9fsString *xattr_name, + void *value, size_t size) +{ + return s->ops->lgetxattr(&s->ctx, path->data, + xattr_name->data, value, size); +} + +static ssize_t v9fs_do_llistxattr(V9fsState *s, V9fsString *path, + void *value, size_t size) +{ + return s->ops->llistxattr(&s->ctx, path->data, + value, size); +} + +static int v9fs_do_lsetxattr(V9fsState *s, V9fsString *path, + V9fsString *xattr_name, + void *value, size_t size, int flags) +{ + return s->ops->lsetxattr(&s->ctx, path->data, + xattr_name->data, value, size, flags); +} + +static int v9fs_do_lremovexattr(V9fsState *s, V9fsString *path, + V9fsString *xattr_name) +{ + return s->ops->lremovexattr(&s->ctx, path->data, + xattr_name->data); +} + + static void v9fs_string_init(V9fsString *str) { str->data = NULL; @@ -285,6 +321,14 @@ static int number_to_string(void *arg, char type) } while (num); break; } + case 'U': { + unsigned long num = *(unsigned long *)arg; + do { + ret++; + num = num/10; + } while (num); + break; + } default: printf("Number_to_string: Unknown number format\n"); return -1; @@ -293,7 +337,8 @@ static int number_to_string(void *arg, char type) return ret; } -static int v9fs_string_alloc_printf(char **strp, const char *fmt, va_list ap) +static int GCC_FMT_ATTR(2, 0) +v9fs_string_alloc_printf(char **strp, const char *fmt, va_list ap) { va_list ap2; char *iter = (char *)fmt; @@ -301,6 +346,7 @@ static int v9fs_string_alloc_printf(char **strp, const char *fmt, va_list ap) int nr_args = 0; char *arg_char_ptr; unsigned int arg_uint; + unsigned long arg_ulong; /* Find the number of %'s that denotes an argument */ for (iter = strstr(iter, "%"); iter; iter = strstr(iter, "%")) { @@ -326,6 +372,14 @@ static int v9fs_string_alloc_printf(char **strp, const char *fmt, va_list ap) arg_uint = va_arg(ap2, unsigned int); len += number_to_string((void *)&arg_uint, 'u'); break; + case 'l': + if (*++iter == 'u') { + arg_ulong = va_arg(ap2, unsigned long); + len += number_to_string((void *)&arg_ulong, 'U'); + } else { + return -1; + } + break; case 's': arg_char_ptr = va_arg(ap2, char *); len += strlen(arg_char_ptr); @@ -347,7 +401,8 @@ alloc_print: return vsprintf(*strp, fmt, ap); } -static void v9fs_string_sprintf(V9fsString *str, const char *fmt, ...) +static void GCC_FMT_ATTR(2, 3) +v9fs_string_sprintf(V9fsString *str, const char *fmt, ...) { va_list ap; int err; @@ -398,8 +453,7 @@ static V9fsFidState *alloc_fid(V9fsState *s, int32_t fid) f = qemu_mallocz(sizeof(V9fsFidState)); f->fid = fid; - f->fd = -1; - f->dir = NULL; + f->fid_type = P9_FID_NONE; f->next = s->fid_list; s->fid_list = f; @@ -407,8 +461,43 @@ static V9fsFidState *alloc_fid(V9fsState *s, int32_t fid) return f; } +static int v9fs_xattr_fid_clunk(V9fsState *s, V9fsFidState *fidp) +{ + int retval = 0; + + if (fidp->fs.xattr.copied_len == -1) { + /* getxattr/listxattr fid */ + goto free_value; + } + /* + * if this is fid for setxattr. clunk should + * result in setxattr localcall + */ + if (fidp->fs.xattr.len != fidp->fs.xattr.copied_len) { + /* clunk after partial write */ + retval = -EINVAL; + goto free_out; + } + if (fidp->fs.xattr.len) { + retval = v9fs_do_lsetxattr(s, &fidp->path, &fidp->fs.xattr.name, + fidp->fs.xattr.value, + fidp->fs.xattr.len, + fidp->fs.xattr.flags); + } else { + retval = v9fs_do_lremovexattr(s, &fidp->path, &fidp->fs.xattr.name); + } +free_out: + v9fs_string_free(&fidp->fs.xattr.name); +free_value: + if (fidp->fs.xattr.value) { + qemu_free(fidp->fs.xattr.value); + } + return retval; +} + static int free_fid(V9fsState *s, int32_t fid) { + int retval = 0; V9fsFidState **fidpp, *fidp; for (fidpp = &s->fid_list; *fidpp; fidpp = &(*fidpp)->next) { @@ -424,16 +513,17 @@ static int free_fid(V9fsState *s, int32_t fid) fidp = *fidpp; *fidpp = fidp->next; - if (fidp->fd != -1) { - v9fs_do_close(s, fidp->fd); - } - if (fidp->dir) { - v9fs_do_closedir(s, fidp->dir); + if (fidp->fid_type == P9_FID_FILE) { + v9fs_do_close(s, fidp->fs.fd); + } else if (fidp->fid_type == P9_FID_DIR) { + v9fs_do_closedir(s, fidp->fs.dir); + } else if (fidp->fid_type == P9_FID_XATTR) { + retval = v9fs_xattr_fid_clunk(s, fidp); } v9fs_string_free(&fidp->path); qemu_free(fidp); - return 0; + return retval; } #define P9_QID_TYPE_DIR 0x80 @@ -660,6 +750,15 @@ static size_t pdu_unmarshal(V9fsPDU *pdu, size_t offset, const char *fmt, ...) &statp->n_muid); break; } + case 'I': { + V9fsIattr *iattr = va_arg(ap, V9fsIattr *); + offset += pdu_unmarshal(pdu, offset, "ddddqqqqq", + &iattr->valid, &iattr->mode, + &iattr->uid, &iattr->gid, &iattr->size, + &iattr->atime_sec, &iattr->atime_nsec, + &iattr->mtime_sec, &iattr->mtime_nsec); + break; + } default: break; } @@ -731,6 +830,21 @@ static size_t pdu_marshal(V9fsPDU *pdu, size_t offset, const char *fmt, ...) statp->n_gid, statp->n_muid); break; } + case 'A': { + V9fsStatDotl *statp = va_arg(ap, V9fsStatDotl *); + offset += pdu_marshal(pdu, offset, "qQdddqqqqqqqqqqqqqqq", + statp->st_result_mask, + &statp->qid, statp->st_mode, + statp->st_uid, statp->st_gid, + statp->st_nlink, statp->st_rdev, + statp->st_size, statp->st_blksize, statp->st_blocks, + statp->st_atime_sec, statp->st_atime_nsec, + statp->st_mtime_sec, statp->st_mtime_nsec, + statp->st_ctime_sec, statp->st_ctime_nsec, + statp->st_btime_sec, statp->st_btime_nsec, + statp->st_gen, statp->st_data_version); + break; + } default: break; } @@ -745,19 +859,24 @@ static void complete_pdu(V9fsState *s, V9fsPDU *pdu, ssize_t len) int8_t id = pdu->id + 1; /* Response */ if (len < 0) { - V9fsString str; int err = -len; + len = 7; - str.data = strerror(err); - str.size = strlen(str.data); + if (s->proto_version != V9FS_PROTO_2000L) { + V9fsString str; - len = 7; - len += pdu_marshal(pdu, len, "s", &str); - if (dotu) { - len += pdu_marshal(pdu, len, "d", err); + str.data = strerror(err); + str.size = strlen(str.data); + + len += pdu_marshal(pdu, len, "s", &str); + id = P9_RERROR; } - id = P9_RERROR; + len += pdu_marshal(pdu, len, "d", err); + + if (s->proto_version == V9FS_PROTO_2000L) { + id = P9_RLERROR; + } } /* fill out the header */ @@ -785,22 +904,20 @@ static mode_t v9mode_to_mode(uint32_t mode, V9fsString *extension) ret |= S_IFDIR; } - if (dotu) { - if (mode & P9_STAT_MODE_SYMLINK) { - ret |= S_IFLNK; - } - if (mode & P9_STAT_MODE_SOCKET) { - ret |= S_IFSOCK; - } - if (mode & P9_STAT_MODE_NAMED_PIPE) { - ret |= S_IFIFO; - } - if (mode & P9_STAT_MODE_DEVICE) { - if (extension && extension->data[0] == 'c') { - ret |= S_IFCHR; - } else { - ret |= S_IFBLK; - } + if (mode & P9_STAT_MODE_SYMLINK) { + ret |= S_IFLNK; + } + if (mode & P9_STAT_MODE_SOCKET) { + ret |= S_IFSOCK; + } + if (mode & P9_STAT_MODE_NAMED_PIPE) { + ret |= S_IFIFO; + } + if (mode & P9_STAT_MODE_DEVICE) { + if (extension && extension->data[0] == 'c') { + ret |= S_IFCHR; + } else { + ret |= S_IFBLK; } } @@ -863,34 +980,32 @@ static uint32_t stat_to_v9mode(const struct stat *stbuf) mode |= P9_STAT_MODE_DIR; } - if (dotu) { - if (S_ISLNK(stbuf->st_mode)) { - mode |= P9_STAT_MODE_SYMLINK; - } + if (S_ISLNK(stbuf->st_mode)) { + mode |= P9_STAT_MODE_SYMLINK; + } - if (S_ISSOCK(stbuf->st_mode)) { - mode |= P9_STAT_MODE_SOCKET; - } + if (S_ISSOCK(stbuf->st_mode)) { + mode |= P9_STAT_MODE_SOCKET; + } - if (S_ISFIFO(stbuf->st_mode)) { - mode |= P9_STAT_MODE_NAMED_PIPE; - } + if (S_ISFIFO(stbuf->st_mode)) { + mode |= P9_STAT_MODE_NAMED_PIPE; + } - if (S_ISBLK(stbuf->st_mode) || S_ISCHR(stbuf->st_mode)) { - mode |= P9_STAT_MODE_DEVICE; - } + if (S_ISBLK(stbuf->st_mode) || S_ISCHR(stbuf->st_mode)) { + mode |= P9_STAT_MODE_DEVICE; + } - if (stbuf->st_mode & S_ISUID) { - mode |= P9_STAT_MODE_SETUID; - } + if (stbuf->st_mode & S_ISUID) { + mode |= P9_STAT_MODE_SETUID; + } - if (stbuf->st_mode & S_ISGID) { - mode |= P9_STAT_MODE_SETGID; - } + if (stbuf->st_mode & S_ISGID) { + mode |= P9_STAT_MODE_SETGID; + } - if (stbuf->st_mode & S_ISVTX) { - mode |= P9_STAT_MODE_SETVTX; - } + if (stbuf->st_mode & S_ISVTX) { + mode |= P9_STAT_MODE_SETVTX; } return mode; @@ -915,29 +1030,27 @@ static int stat_to_v9stat(V9fsState *s, V9fsString *name, v9fs_string_null(&v9stat->gid); v9fs_string_null(&v9stat->muid); - if (dotu) { - v9stat->n_uid = stbuf->st_uid; - v9stat->n_gid = stbuf->st_gid; - v9stat->n_muid = 0; + v9stat->n_uid = stbuf->st_uid; + v9stat->n_gid = stbuf->st_gid; + v9stat->n_muid = 0; - v9fs_string_null(&v9stat->extension); + v9fs_string_null(&v9stat->extension); - if (v9stat->mode & P9_STAT_MODE_SYMLINK) { - err = v9fs_do_readlink(s, name, &v9stat->extension); - if (err == -1) { - err = -errno; - return err; - } - v9stat->extension.data[err] = 0; - v9stat->extension.size = err; - } else if (v9stat->mode & P9_STAT_MODE_DEVICE) { - v9fs_string_sprintf(&v9stat->extension, "%c %u %u", - S_ISCHR(stbuf->st_mode) ? 'c' : 'b', - major(stbuf->st_rdev), minor(stbuf->st_rdev)); - } else if (S_ISDIR(stbuf->st_mode) || S_ISREG(stbuf->st_mode)) { - v9fs_string_sprintf(&v9stat->extension, "%s %u", - "HARDLINKCOUNT", stbuf->st_nlink); + if (v9stat->mode & P9_STAT_MODE_SYMLINK) { + err = v9fs_do_readlink(s, name, &v9stat->extension); + if (err == -1) { + err = -errno; + return err; } + v9stat->extension.data[err] = 0; + v9stat->extension.size = err; + } else if (v9stat->mode & P9_STAT_MODE_DEVICE) { + v9fs_string_sprintf(&v9stat->extension, "%c %u %u", + S_ISCHR(stbuf->st_mode) ? 'c' : 'b', + major(stbuf->st_rdev), minor(stbuf->st_rdev)); + } else if (S_ISDIR(stbuf->st_mode) || S_ISREG(stbuf->st_mode)) { + v9fs_string_sprintf(&v9stat->extension, "%s %lu", + "HARDLINKCOUNT", (unsigned long)stbuf->st_nlink); } str = strrchr(name->data, '/'); @@ -958,6 +1071,51 @@ static int stat_to_v9stat(V9fsState *s, V9fsString *name, return 0; } +#define P9_STATS_MODE 0x00000001ULL +#define P9_STATS_NLINK 0x00000002ULL +#define P9_STATS_UID 0x00000004ULL +#define P9_STATS_GID 0x00000008ULL +#define P9_STATS_RDEV 0x00000010ULL +#define P9_STATS_ATIME 0x00000020ULL +#define P9_STATS_MTIME 0x00000040ULL +#define P9_STATS_CTIME 0x00000080ULL +#define P9_STATS_INO 0x00000100ULL +#define P9_STATS_SIZE 0x00000200ULL +#define P9_STATS_BLOCKS 0x00000400ULL + +#define P9_STATS_BTIME 0x00000800ULL +#define P9_STATS_GEN 0x00001000ULL +#define P9_STATS_DATA_VERSION 0x00002000ULL + +#define P9_STATS_BASIC 0x000007ffULL /* Mask for fields up to BLOCKS */ +#define P9_STATS_ALL 0x00003fffULL /* Mask for All fields above */ + + +static void stat_to_v9stat_dotl(V9fsState *s, const struct stat *stbuf, + V9fsStatDotl *v9lstat) +{ + memset(v9lstat, 0, sizeof(*v9lstat)); + + v9lstat->st_mode = stbuf->st_mode; + v9lstat->st_nlink = stbuf->st_nlink; + v9lstat->st_uid = stbuf->st_uid; + v9lstat->st_gid = stbuf->st_gid; + v9lstat->st_rdev = stbuf->st_rdev; + v9lstat->st_size = stbuf->st_size; + v9lstat->st_blksize = stbuf->st_blksize; + v9lstat->st_blocks = stbuf->st_blocks; + v9lstat->st_atime_sec = stbuf->st_atime; + v9lstat->st_atime_nsec = stbuf->st_atim.tv_nsec; + v9lstat->st_mtime_sec = stbuf->st_mtime; + v9lstat->st_mtime_nsec = stbuf->st_mtim.tv_nsec; + v9lstat->st_ctime_sec = stbuf->st_ctime; + v9lstat->st_ctime_nsec = stbuf->st_ctim.tv_nsec; + /* Currently we only support BASIC fields in stat */ + v9lstat->st_result_mask = P9_STATS_BASIC; + + stat_to_qid(stbuf, &v9lstat->qid); +} + static struct iovec *adjust_sg(struct iovec *sg, int len, int *iovcnt) { while (len && *iovcnt) { @@ -1019,17 +1177,20 @@ static void v9fs_fix_path(V9fsString *dst, V9fsString *src, int len) static void v9fs_version(V9fsState *s, V9fsPDU *pdu) { - int32_t msize; V9fsString version; size_t offset = 7; - pdu_unmarshal(pdu, offset, "ds", &msize, &version); + pdu_unmarshal(pdu, offset, "ds", &s->msize, &version); - if (strcmp(version.data, "9P2000.u")) { + if (!strcmp(version.data, "9P2000.u")) { + s->proto_version = V9FS_PROTO_2000U; + } else if (!strcmp(version.data, "9P2000.L")) { + s->proto_version = V9FS_PROTO_2000L; + } else { v9fs_string_sprintf(&version, "unknown"); } - offset += pdu_marshal(pdu, offset, "ds", msize, &version); + offset += pdu_marshal(pdu, offset, "ds", s->msize, &version); complete_pdu(s, pdu, offset); v9fs_string_free(&version); @@ -1121,6 +1282,202 @@ out: qemu_free(vs); } +static void v9fs_getattr_post_lstat(V9fsState *s, V9fsStatStateDotl *vs, + int err) +{ + if (err == -1) { + err = -errno; + goto out; + } + + stat_to_v9stat_dotl(s, &vs->stbuf, &vs->v9stat_dotl); + vs->offset += pdu_marshal(vs->pdu, vs->offset, "A", &vs->v9stat_dotl); + err = vs->offset; + +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + +static void v9fs_getattr(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid; + V9fsStatStateDotl *vs; + ssize_t err = 0; + V9fsFidState *fidp; + uint64_t request_mask; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + memset(&vs->v9stat_dotl, 0, sizeof(vs->v9stat_dotl)); + + pdu_unmarshal(vs->pdu, vs->offset, "dq", &fid, &request_mask); + + fidp = lookup_fid(s, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out; + } + + /* Currently we only support BASIC fields in stat, so there is no + * need to look at request_mask. + */ + err = v9fs_do_lstat(s, &fidp->path, &vs->stbuf); + v9fs_getattr_post_lstat(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + +/* From Linux kernel code */ +#define ATTR_MODE (1 << 0) +#define ATTR_UID (1 << 1) +#define ATTR_GID (1 << 2) +#define ATTR_SIZE (1 << 3) +#define ATTR_ATIME (1 << 4) +#define ATTR_MTIME (1 << 5) +#define ATTR_CTIME (1 << 6) +#define ATTR_MASK 127 +#define ATTR_ATIME_SET (1 << 7) +#define ATTR_MTIME_SET (1 << 8) + +static void v9fs_setattr_post_truncate(V9fsState *s, V9fsSetattrState *vs, + int err) +{ + if (err == -1) { + err = -errno; + goto out; + } + err = vs->offset; + +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + +static void v9fs_setattr_post_chown(V9fsState *s, V9fsSetattrState *vs, int err) +{ + if (err == -1) { + err = -errno; + goto out; + } + + if (vs->v9iattr.valid & (ATTR_SIZE)) { + err = v9fs_do_truncate(s, &vs->fidp->path, vs->v9iattr.size); + } + v9fs_setattr_post_truncate(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + +static void v9fs_setattr_post_utimensat(V9fsState *s, V9fsSetattrState *vs, + int err) +{ + if (err == -1) { + err = -errno; + goto out; + } + + /* If the only valid entry in iattr is ctime we can call + * chown(-1,-1) to update the ctime of the file + */ + if ((vs->v9iattr.valid & (ATTR_UID | ATTR_GID)) || + ((vs->v9iattr.valid & ATTR_CTIME) + && !((vs->v9iattr.valid & ATTR_MASK) & ~ATTR_CTIME))) { + if (!(vs->v9iattr.valid & ATTR_UID)) { + vs->v9iattr.uid = -1; + } + if (!(vs->v9iattr.valid & ATTR_GID)) { + vs->v9iattr.gid = -1; + } + err = v9fs_do_chown(s, &vs->fidp->path, vs->v9iattr.uid, + vs->v9iattr.gid); + } + v9fs_setattr_post_chown(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + +static void v9fs_setattr_post_chmod(V9fsState *s, V9fsSetattrState *vs, int err) +{ + if (err == -1) { + err = -errno; + goto out; + } + + if (vs->v9iattr.valid & (ATTR_ATIME | ATTR_MTIME)) { + struct timespec times[2]; + if (vs->v9iattr.valid & ATTR_ATIME) { + if (vs->v9iattr.valid & ATTR_ATIME_SET) { + times[0].tv_sec = vs->v9iattr.atime_sec; + times[0].tv_nsec = vs->v9iattr.atime_nsec; + } else { + times[0].tv_nsec = UTIME_NOW; + } + } else { + times[0].tv_nsec = UTIME_OMIT; + } + + if (vs->v9iattr.valid & ATTR_MTIME) { + if (vs->v9iattr.valid & ATTR_MTIME_SET) { + times[1].tv_sec = vs->v9iattr.mtime_sec; + times[1].tv_nsec = vs->v9iattr.mtime_nsec; + } else { + times[1].tv_nsec = UTIME_NOW; + } + } else { + times[1].tv_nsec = UTIME_OMIT; + } + err = v9fs_do_utimensat(s, &vs->fidp->path, times); + } + v9fs_setattr_post_utimensat(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + +static void v9fs_setattr(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid; + V9fsSetattrState *vs; + int err = 0; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + pdu_unmarshal(pdu, vs->offset, "dI", &fid, &vs->v9iattr); + + vs->fidp = lookup_fid(s, fid); + if (vs->fidp == NULL) { + err = -EINVAL; + goto out; + } + + if (vs->v9iattr.valid & ATTR_MODE) { + err = v9fs_do_chmod(s, &vs->fidp->path, vs->v9iattr.mode); + } + + v9fs_setattr_post_chmod(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + static void v9fs_walk_complete(V9fsState *s, V9fsWalkState *vs, int err) { complete_pdu(s, vs->pdu, err); @@ -1241,8 +1598,7 @@ static void v9fs_walk(V9fsState *s, V9fsPDU *pdu) /* FIXME: is this really valid? */ if (fid == newfid) { - BUG_ON(vs->fidp->fd != -1); - BUG_ON(vs->fidp->dir); + BUG_ON(vs->fidp->fid_type != P9_FID_NONE); v9fs_string_init(&vs->path); vs->name_idx = 0; @@ -1284,13 +1640,33 @@ out: v9fs_walk_complete(s, vs, err); } +static int32_t get_iounit(V9fsState *s, V9fsString *name) +{ + struct statfs stbuf; + int32_t iounit = 0; + + /* + * iounit should be multiples of f_bsize (host filesystem block size + * and as well as less than (client msize - P9_IOHDRSZ)) + */ + if (!v9fs_do_statfs(s, name, &stbuf)) { + iounit = stbuf.f_bsize; + iounit *= (s->msize - P9_IOHDRSZ)/stbuf.f_bsize; + } + + if (!iounit) { + iounit = s->msize - P9_IOHDRSZ; + } + return iounit; +} + static void v9fs_open_post_opendir(V9fsState *s, V9fsOpenState *vs, int err) { - if (vs->fidp->dir == NULL) { + if (vs->fidp->fs.dir == NULL) { err = -errno; goto out; } - + vs->fidp->fid_type = P9_FID_DIR; vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid, 0); err = vs->offset; out: @@ -1299,15 +1675,25 @@ out: } +static void v9fs_open_post_getiounit(V9fsState *s, V9fsOpenState *vs) +{ + int err; + vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid, vs->iounit); + err = vs->offset; + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + static void v9fs_open_post_open(V9fsState *s, V9fsOpenState *vs, int err) { - if (vs->fidp->fd == -1) { + if (vs->fidp->fs.fd == -1) { err = -errno; goto out; } - - vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid, 0); - err = vs->offset; + vs->fidp->fid_type = P9_FID_FILE; + vs->iounit = get_iounit(s, &vs->fidp->path); + v9fs_open_post_getiounit(s, vs); + return; out: complete_pdu(s, vs->pdu, err); qemu_free(vs); @@ -1315,6 +1701,8 @@ out: static void v9fs_open_post_lstat(V9fsState *s, V9fsOpenState *vs, int err) { + int flags; + if (err) { err = -errno; goto out; @@ -1323,11 +1711,18 @@ static void v9fs_open_post_lstat(V9fsState *s, V9fsOpenState *vs, int err) stat_to_qid(&vs->stbuf, &vs->qid); if (S_ISDIR(vs->stbuf.st_mode)) { - vs->fidp->dir = v9fs_do_opendir(s, &vs->fidp->path); + vs->fidp->fs.dir = v9fs_do_opendir(s, &vs->fidp->path); v9fs_open_post_opendir(s, vs, err); } else { - vs->fidp->fd = v9fs_do_open(s, &vs->fidp->path, - omode_to_uflags(vs->mode)); + if (s->proto_version == V9FS_PROTO_2000L) { + flags = vs->mode; + flags &= ~(O_NOCTTY | O_ASYNC | O_CREAT); + /* Ignore direct disk access hint until the server supports it. */ + flags &= ~O_DIRECT; + } else { + flags = omode_to_uflags(vs->mode); + } + vs->fidp->fs.fd = v9fs_do_open(s, &vs->fidp->path, flags); v9fs_open_post_open(s, vs, err); } return; @@ -1342,12 +1737,16 @@ static void v9fs_open(V9fsState *s, V9fsPDU *pdu) V9fsOpenState *vs; ssize_t err = 0; - vs = qemu_malloc(sizeof(*vs)); vs->pdu = pdu; vs->offset = 7; + vs->mode = 0; - pdu_unmarshal(vs->pdu, vs->offset, "db", &fid, &vs->mode); + if (s->proto_version == V9FS_PROTO_2000L) { + pdu_unmarshal(vs->pdu, vs->offset, "dd", &fid, &vs->mode); + } else { + pdu_unmarshal(vs->pdu, vs->offset, "db", &fid, &vs->mode); + } vs->fidp = lookup_fid(s, fid); if (vs->fidp == NULL) { @@ -1355,8 +1754,7 @@ static void v9fs_open(V9fsState *s, V9fsPDU *pdu) goto out; } - BUG_ON(vs->fidp->fd != -1); - BUG_ON(vs->fidp->dir); + BUG_ON(vs->fidp->fid_type != P9_FID_NONE); err = v9fs_do_lstat(s, &vs->fidp->path, &vs->stbuf); @@ -1367,6 +1765,122 @@ out: qemu_free(vs); } +static void v9fs_post_lcreate(V9fsState *s, V9fsLcreateState *vs, int err) +{ + if (err == 0) { + v9fs_string_copy(&vs->fidp->path, &vs->fullname); + stat_to_qid(&vs->stbuf, &vs->qid); + vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid, + &vs->iounit); + err = vs->offset; + } else { + vs->fidp->fid_type = P9_FID_NONE; + err = -errno; + if (vs->fidp->fs.fd > 0) { + close(vs->fidp->fs.fd); + } + } + + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + v9fs_string_free(&vs->fullname); + qemu_free(vs); +} + +static void v9fs_lcreate_post_get_iounit(V9fsState *s, V9fsLcreateState *vs, + int err) +{ + if (err) { + err = -errno; + goto out; + } + err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf); + +out: + v9fs_post_lcreate(s, vs, err); +} + +static void v9fs_lcreate_post_do_open2(V9fsState *s, V9fsLcreateState *vs, + int err) +{ + if (vs->fidp->fs.fd == -1) { + err = -errno; + goto out; + } + vs->fidp->fid_type = P9_FID_FILE; + vs->iounit = get_iounit(s, &vs->fullname); + v9fs_lcreate_post_get_iounit(s, vs, err); + return; + +out: + v9fs_post_lcreate(s, vs, err); +} + +static void v9fs_lcreate(V9fsState *s, V9fsPDU *pdu) +{ + int32_t dfid, flags, mode; + gid_t gid; + V9fsLcreateState *vs; + ssize_t err = 0; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + v9fs_string_init(&vs->fullname); + + pdu_unmarshal(vs->pdu, vs->offset, "dsddd", &dfid, &vs->name, &flags, + &mode, &gid); + + vs->fidp = lookup_fid(s, dfid); + if (vs->fidp == NULL) { + err = -ENOENT; + goto out; + } + + v9fs_string_sprintf(&vs->fullname, "%s/%s", vs->fidp->path.data, + vs->name.data); + + /* Ignore direct disk access hint until the server supports it. */ + flags &= ~O_DIRECT; + + vs->fidp->fs.fd = v9fs_do_open2(s, vs->fullname.data, vs->fidp->uid, + gid, flags, mode); + v9fs_lcreate_post_do_open2(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_post_do_fsync(V9fsState *s, V9fsPDU *pdu, int err) +{ + if (err == -1) { + err = -errno; + } + complete_pdu(s, pdu, err); +} + +static void v9fs_fsync(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid; + size_t offset = 7; + V9fsFidState *fidp; + int err; + + pdu_unmarshal(pdu, offset, "d", &fid); + fidp = lookup_fid(s, fid); + if (fidp == NULL) { + err = -ENOENT; + v9fs_post_do_fsync(s, pdu, err); + return; + } + err = v9fs_do_fsync(s, fidp->fs.fd); + v9fs_post_do_fsync(s, pdu, err); +} + static void v9fs_clunk(V9fsState *s, V9fsPDU *pdu) { int32_t fid; @@ -1420,7 +1934,7 @@ static void v9fs_read_post_dir_lstat(V9fsState *s, V9fsReadState *vs, &vs->v9stat); if ((vs->len != (vs->v9stat.size + 2)) || ((vs->count + vs->len) > vs->max_count)) { - v9fs_do_seekdir(s, vs->fidp->dir, vs->dir_pos); + v9fs_do_seekdir(s, vs->fidp->fs.dir, vs->dir_pos); v9fs_read_post_seekdir(s, vs, err); return; } @@ -1428,11 +1942,11 @@ static void v9fs_read_post_dir_lstat(V9fsState *s, V9fsReadState *vs, v9fs_stat_free(&vs->v9stat); v9fs_string_free(&vs->name); vs->dir_pos = vs->dent->d_off; - vs->dent = v9fs_do_readdir(s, vs->fidp->dir); + vs->dent = v9fs_do_readdir(s, vs->fidp->fs.dir); v9fs_read_post_readdir(s, vs, err); return; out: - v9fs_do_seekdir(s, vs->fidp->dir, vs->dir_pos); + v9fs_do_seekdir(s, vs->fidp->fs.dir, vs->dir_pos); v9fs_read_post_seekdir(s, vs, err); return; @@ -1460,7 +1974,7 @@ static void v9fs_read_post_readdir(V9fsState *s, V9fsReadState *vs, ssize_t err) static void v9fs_read_post_telldir(V9fsState *s, V9fsReadState *vs, ssize_t err) { - vs->dent = v9fs_do_readdir(s, vs->fidp->dir); + vs->dent = v9fs_do_readdir(s, vs->fidp->fs.dir); v9fs_read_post_readdir(s, vs, err); return; } @@ -1468,12 +1982,12 @@ static void v9fs_read_post_telldir(V9fsState *s, V9fsReadState *vs, ssize_t err) static void v9fs_read_post_rewinddir(V9fsState *s, V9fsReadState *vs, ssize_t err) { - vs->dir_pos = v9fs_do_telldir(s, vs->fidp->dir); + vs->dir_pos = v9fs_do_telldir(s, vs->fidp->fs.dir); v9fs_read_post_telldir(s, vs, err); return; } -static void v9fs_read_post_readv(V9fsState *s, V9fsReadState *vs, ssize_t err) +static void v9fs_read_post_preadv(V9fsState *s, V9fsReadState *vs, ssize_t err) { if (err < 0) { /* IO error return the error */ @@ -1487,12 +2001,16 @@ static void v9fs_read_post_readv(V9fsState *s, V9fsReadState *vs, ssize_t err) if (0) { print_sg(vs->sg, vs->cnt); } - vs->len = v9fs_do_readv(s, vs->fidp->fd, vs->sg, vs->cnt); + vs->len = v9fs_do_preadv(s, vs->fidp->fs.fd, vs->sg, vs->cnt, + vs->off); + if (vs->len > 0) { + vs->off += vs->len; + } } while (vs->len == -1 && errno == EINTR); if (vs->len == -1) { err = -errno; } - v9fs_read_post_readv(s, vs, err); + v9fs_read_post_preadv(s, vs, err); return; } vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->total); @@ -1504,28 +2022,27 @@ out: qemu_free(vs); } -static void v9fs_read_post_lseek(V9fsState *s, V9fsReadState *vs, ssize_t err) +static void v9fs_xattr_read(V9fsState *s, V9fsReadState *vs) { - if (err == -1) { - err = -errno; - goto out; - } - vs->sg = cap_sg(vs->sg, vs->count, &vs->cnt); - - if (vs->total < vs->count) { - do { - if (0) { - print_sg(vs->sg, vs->cnt); - } - vs->len = v9fs_do_readv(s, vs->fidp->fd, vs->sg, vs->cnt); - } while (vs->len == -1 && errno == EINTR); - if (vs->len == -1) { - err = -errno; - } - v9fs_read_post_readv(s, vs, err); - return; + ssize_t err = 0; + int read_count; + int64_t xattr_len; + + xattr_len = vs->fidp->fs.xattr.len; + read_count = xattr_len - vs->off; + if (read_count > vs->count) { + read_count = vs->count; + } else if (read_count < 0) { + /* + * read beyond XATTR value + */ + read_count = 0; } -out: + vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", read_count); + vs->offset += pdu_pack(vs->pdu, vs->offset, + ((char *)vs->fidp->fs.xattr.value) + vs->off, + read_count); + err = vs->offset; complete_pdu(s, vs->pdu, err); qemu_free(vs); } @@ -1551,19 +2068,30 @@ static void v9fs_read(V9fsState *s, V9fsPDU *pdu) goto out; } - if (vs->fidp->dir) { + if (vs->fidp->fid_type == P9_FID_DIR) { vs->max_count = vs->count; vs->count = 0; if (vs->off == 0) { - v9fs_do_rewinddir(s, vs->fidp->dir); + v9fs_do_rewinddir(s, vs->fidp->fs.dir); } v9fs_read_post_rewinddir(s, vs, err); return; - } else if (vs->fidp->fd != -1) { + } else if (vs->fidp->fid_type == P9_FID_FILE) { vs->sg = vs->iov; pdu_marshal(vs->pdu, vs->offset + 4, "v", vs->sg, &vs->cnt); - err = v9fs_do_lseek(s, vs->fidp->fd, vs->off, SEEK_SET); - v9fs_read_post_lseek(s, vs, err); + vs->sg = cap_sg(vs->sg, vs->count, &vs->cnt); + if (vs->total <= vs->count) { + vs->len = v9fs_do_preadv(s, vs->fidp->fs.fd, vs->sg, vs->cnt, + vs->off); + if (vs->len > 0) { + vs->off += vs->len; + } + err = vs->len; + v9fs_read_post_preadv(s, vs, err); + } + return; + } else if (vs->fidp->fid_type == P9_FID_XATTR) { + v9fs_xattr_read(s, vs); return; } else { err = -EINVAL; @@ -1573,7 +2101,128 @@ out: qemu_free(vs); } -static void v9fs_write_post_writev(V9fsState *s, V9fsWriteState *vs, +typedef struct V9fsReadDirState { + V9fsPDU *pdu; + V9fsFidState *fidp; + V9fsQID qid; + off_t saved_dir_pos; + struct dirent *dent; + int32_t count; + int32_t max_count; + size_t offset; + int64_t initial_offset; + V9fsString name; +} V9fsReadDirState; + +static void v9fs_readdir_post_seekdir(V9fsState *s, V9fsReadDirState *vs) +{ + vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->count); + vs->offset += vs->count; + complete_pdu(s, vs->pdu, vs->offset); + qemu_free(vs); + return; +} + +/* Size of each dirent on the wire: size of qid (13) + size of offset (8) + * size of type (1) + size of name.size (2) + strlen(name.data) + */ +#define V9_READDIR_DATA_SZ (24 + strlen(vs->name.data)) + +static void v9fs_readdir_post_readdir(V9fsState *s, V9fsReadDirState *vs) +{ + int len; + size_t size; + + if (vs->dent) { + v9fs_string_init(&vs->name); + v9fs_string_sprintf(&vs->name, "%s", vs->dent->d_name); + + if ((vs->count + V9_READDIR_DATA_SZ) > vs->max_count) { + /* Ran out of buffer. Set dir back to old position and return */ + v9fs_do_seekdir(s, vs->fidp->fs.dir, vs->saved_dir_pos); + v9fs_readdir_post_seekdir(s, vs); + return; + } + + /* Fill up just the path field of qid because the client uses + * only that. To fill the entire qid structure we will have + * to stat each dirent found, which is expensive + */ + size = MIN(sizeof(vs->dent->d_ino), sizeof(vs->qid.path)); + memcpy(&vs->qid.path, &vs->dent->d_ino, size); + /* Fill the other fields with dummy values */ + vs->qid.type = 0; + vs->qid.version = 0; + + len = pdu_marshal(vs->pdu, vs->offset+4+vs->count, "Qqbs", + &vs->qid, vs->dent->d_off, + vs->dent->d_type, &vs->name); + vs->count += len; + v9fs_string_free(&vs->name); + vs->saved_dir_pos = vs->dent->d_off; + vs->dent = v9fs_do_readdir(s, vs->fidp->fs.dir); + v9fs_readdir_post_readdir(s, vs); + return; + } + + vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->count); + vs->offset += vs->count; + complete_pdu(s, vs->pdu, vs->offset); + qemu_free(vs); + return; +} + +static void v9fs_readdir_post_telldir(V9fsState *s, V9fsReadDirState *vs) +{ + vs->dent = v9fs_do_readdir(s, vs->fidp->fs.dir); + v9fs_readdir_post_readdir(s, vs); + return; +} + +static void v9fs_readdir_post_setdir(V9fsState *s, V9fsReadDirState *vs) +{ + vs->saved_dir_pos = v9fs_do_telldir(s, vs->fidp->fs.dir); + v9fs_readdir_post_telldir(s, vs); + return; +} + +static void v9fs_readdir(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid; + V9fsReadDirState *vs; + ssize_t err = 0; + size_t offset = 7; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + vs->count = 0; + + pdu_unmarshal(vs->pdu, offset, "dqd", &fid, &vs->initial_offset, + &vs->max_count); + + vs->fidp = lookup_fid(s, fid); + if (vs->fidp == NULL || !(vs->fidp->fs.dir)) { + err = -EINVAL; + goto out; + } + + if (vs->initial_offset == 0) { + v9fs_do_rewinddir(s, vs->fidp->fs.dir); + } else { + v9fs_do_seekdir(s, vs->fidp->fs.dir, vs->initial_offset); + } + + v9fs_readdir_post_setdir(s, vs); + return; + +out: + complete_pdu(s, pdu, err); + qemu_free(vs); + return; +} + +static void v9fs_write_post_pwritev(V9fsState *s, V9fsWriteState *vs, ssize_t err) { if (err < 0) { @@ -1588,44 +2237,62 @@ static void v9fs_write_post_writev(V9fsState *s, V9fsWriteState *vs, if (0) { print_sg(vs->sg, vs->cnt); } - vs->len = v9fs_do_writev(s, vs->fidp->fd, vs->sg, vs->cnt); + vs->len = v9fs_do_pwritev(s, vs->fidp->fs.fd, vs->sg, vs->cnt, + vs->off); + if (vs->len > 0) { + vs->off += vs->len; + } } while (vs->len == -1 && errno == EINTR); if (vs->len == -1) { err = -errno; } - v9fs_write_post_writev(s, vs, err); + v9fs_write_post_pwritev(s, vs, err); return; } vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->total); - err = vs->offset; out: complete_pdu(s, vs->pdu, err); qemu_free(vs); } -static void v9fs_write_post_lseek(V9fsState *s, V9fsWriteState *vs, ssize_t err) +static void v9fs_xattr_write(V9fsState *s, V9fsWriteState *vs) { - if (err == -1) { - err = -errno; + int i, to_copy; + ssize_t err = 0; + int write_count; + int64_t xattr_len; + + xattr_len = vs->fidp->fs.xattr.len; + write_count = xattr_len - vs->off; + if (write_count > vs->count) { + write_count = vs->count; + } else if (write_count < 0) { + /* + * write beyond XATTR value len specified in + * xattrcreate + */ + err = -ENOSPC; goto out; } - vs->sg = cap_sg(vs->sg, vs->count, &vs->cnt); - - if (vs->total < vs->count) { - do { - if (0) { - print_sg(vs->sg, vs->cnt); - } - vs->len = v9fs_do_writev(s, vs->fidp->fd, vs->sg, vs->cnt); - } while (vs->len == -1 && errno == EINTR); - if (vs->len == -1) { - err = -errno; + vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", write_count); + err = vs->offset; + vs->fidp->fs.xattr.copied_len += write_count; + /* + * Now copy the content from sg list + */ + for (i = 0; i < vs->cnt; i++) { + if (write_count > vs->sg[i].iov_len) { + to_copy = vs->sg[i].iov_len; + } else { + to_copy = write_count; } - v9fs_write_post_writev(s, vs, err); - return; + memcpy((char *)vs->fidp->fs.xattr.value + vs->off, + vs->sg[i].iov_base, to_copy); + /* updating vs->off since we are not using below */ + vs->off += to_copy; + write_count -= to_copy; } - out: complete_pdu(s, vs->pdu, err); qemu_free(vs); @@ -1646,7 +2313,7 @@ static void v9fs_write(V9fsState *s, V9fsPDU *pdu) vs->len = 0; pdu_unmarshal(vs->pdu, vs->offset, "dqdv", &fid, &vs->off, &vs->count, - vs->sg, &vs->cnt); + vs->sg, &vs->cnt); vs->fidp = lookup_fid(s, fid); if (vs->fidp == NULL) { @@ -1654,30 +2321,58 @@ static void v9fs_write(V9fsState *s, V9fsPDU *pdu) goto out; } - if (vs->fidp->fd == -1) { + if (vs->fidp->fid_type == P9_FID_FILE) { + if (vs->fidp->fs.fd == -1) { + err = -EINVAL; + goto out; + } + } else if (vs->fidp->fid_type == P9_FID_XATTR) { + /* + * setxattr operation + */ + v9fs_xattr_write(s, vs); + return; + } else { err = -EINVAL; goto out; } + vs->sg = cap_sg(vs->sg, vs->count, &vs->cnt); + if (vs->total <= vs->count) { + vs->len = v9fs_do_pwritev(s, vs->fidp->fs.fd, vs->sg, vs->cnt, vs->off); + if (vs->len > 0) { + vs->off += vs->len; + } + err = vs->len; + v9fs_write_post_pwritev(s, vs, err); + } + return; +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} - err = v9fs_do_lseek(s, vs->fidp->fd, vs->off, SEEK_SET); +static void v9fs_create_post_getiounit(V9fsState *s, V9fsCreateState *vs) +{ + int err; + v9fs_string_copy(&vs->fidp->path, &vs->fullname); + stat_to_qid(&vs->stbuf, &vs->qid); - v9fs_write_post_lseek(s, vs, err); - return; + vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid, vs->iounit); + err = vs->offset; -out: complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + v9fs_string_free(&vs->extension); + v9fs_string_free(&vs->fullname); qemu_free(vs); } static void v9fs_post_create(V9fsState *s, V9fsCreateState *vs, int err) { if (err == 0) { - v9fs_string_copy(&vs->fidp->path, &vs->fullname); - stat_to_qid(&vs->stbuf, &vs->qid); - - vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid, 0); - - err = vs->offset; + vs->iounit = get_iounit(s, &vs->fidp->path); + v9fs_create_post_getiounit(s, vs); + return; } complete_pdu(s, vs->pdu, err); @@ -1698,9 +2393,10 @@ static void v9fs_create_post_perms(V9fsState *s, V9fsCreateState *vs, int err) static void v9fs_create_post_opendir(V9fsState *s, V9fsCreateState *vs, int err) { - if (!vs->fidp->dir) { + if (!vs->fidp->fs.dir) { err = -errno; } + vs->fidp->fid_type = P9_FID_DIR; v9fs_post_create(s, vs, err); } @@ -1712,7 +2408,7 @@ static void v9fs_create_post_dir_lstat(V9fsState *s, V9fsCreateState *vs, goto out; } - vs->fidp->dir = v9fs_do_opendir(s, &vs->fullname); + vs->fidp->fs.dir = v9fs_do_opendir(s, &vs->fullname); v9fs_create_post_opendir(s, vs, err); return; @@ -1738,22 +2434,22 @@ out: static void v9fs_create_post_fstat(V9fsState *s, V9fsCreateState *vs, int err) { if (err) { - vs->fidp->fd = -1; + vs->fidp->fid_type = P9_FID_NONE; + close(vs->fidp->fs.fd); err = -errno; } - v9fs_post_create(s, vs, err); return; } static void v9fs_create_post_open2(V9fsState *s, V9fsCreateState *vs, int err) { - if (vs->fidp->fd == -1) { + if (vs->fidp->fs.fd == -1) { err = -errno; goto out; } - - err = v9fs_do_fstat(s, vs->fidp->fd, &vs->stbuf); + vs->fidp->fid_type = P9_FID_FILE; + err = v9fs_do_fstat(s, vs->fidp->fs.fd, &vs->stbuf); v9fs_create_post_fstat(s, vs, err); return; @@ -1772,10 +2468,12 @@ static void v9fs_create_post_lstat(V9fsState *s, V9fsCreateState *vs, int err) } if (vs->perm & P9_STAT_MODE_DIR) { - err = v9fs_do_mkdir(s, vs); + err = v9fs_do_mkdir(s, vs->fullname.data, vs->perm & 0777, + vs->fidp->uid, -1); v9fs_create_post_mkdir(s, vs, err); } else if (vs->perm & P9_STAT_MODE_SYMLINK) { - err = v9fs_do_symlink(s, vs); + err = v9fs_do_symlink(s, vs->fidp, vs->extension.data, + vs->fullname.data, -1); v9fs_create_post_perms(s, vs, err); } else if (vs->perm & P9_STAT_MODE_LINK) { int32_t nfid = atoi(vs->extension.data); @@ -1810,16 +2508,21 @@ static void v9fs_create_post_lstat(V9fsState *s, V9fsCreateState *vs, int err) } nmode |= vs->perm & 0777; - err = v9fs_do_mknod(s, vs, nmode, makedev(major, minor)); + err = v9fs_do_mknod(s, vs->fullname.data, nmode, + makedev(major, minor), vs->fidp->uid, -1); v9fs_create_post_perms(s, vs, err); } else if (vs->perm & P9_STAT_MODE_NAMED_PIPE) { - err = v9fs_do_mknod(s, vs, S_IFIFO | (vs->perm & 0777), 0); + err = v9fs_do_mknod(s, vs->fullname.data, S_IFIFO | (vs->perm & 0777), + 0, vs->fidp->uid, -1); v9fs_post_create(s, vs, err); } else if (vs->perm & P9_STAT_MODE_SOCKET) { - err = v9fs_do_mknod(s, vs, S_IFSOCK | (vs->perm & 0777), 0); + err = v9fs_do_mknod(s, vs->fullname.data, S_IFSOCK | (vs->perm & 0777), + 0, vs->fidp->uid, -1); v9fs_post_create(s, vs, err); } else { - vs->fidp->fd = v9fs_do_open2(s, vs); + vs->fidp->fs.fd = v9fs_do_open2(s, vs->fullname.data, vs->fidp->uid, + -1, omode_to_uflags(vs->mode)|O_CREAT, vs->perm); + v9fs_create_post_open2(s, vs, err); } @@ -1864,23 +2567,124 @@ out: qemu_free(vs); } +static void v9fs_post_symlink(V9fsState *s, V9fsSymlinkState *vs, int err) +{ + if (err == 0) { + stat_to_qid(&vs->stbuf, &vs->qid); + vs->offset += pdu_marshal(vs->pdu, vs->offset, "Q", &vs->qid); + err = vs->offset; + } else { + err = -errno; + } + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + v9fs_string_free(&vs->symname); + v9fs_string_free(&vs->fullname); + qemu_free(vs); +} + +static void v9fs_symlink_post_do_symlink(V9fsState *s, V9fsSymlinkState *vs, + int err) +{ + if (err) { + goto out; + } + err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf); +out: + v9fs_post_symlink(s, vs, err); +} + +static void v9fs_symlink(V9fsState *s, V9fsPDU *pdu) +{ + int32_t dfid; + V9fsSymlinkState *vs; + int err = 0; + gid_t gid; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + v9fs_string_init(&vs->fullname); + + pdu_unmarshal(vs->pdu, vs->offset, "dssd", &dfid, &vs->name, + &vs->symname, &gid); + + vs->dfidp = lookup_fid(s, dfid); + if (vs->dfidp == NULL) { + err = -EINVAL; + goto out; + } + + v9fs_string_sprintf(&vs->fullname, "%s/%s", vs->dfidp->path.data, + vs->name.data); + err = v9fs_do_symlink(s, vs->dfidp, vs->symname.data, + vs->fullname.data, gid); + v9fs_symlink_post_do_symlink(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + v9fs_string_free(&vs->symname); + qemu_free(vs); +} + static void v9fs_flush(V9fsState *s, V9fsPDU *pdu) { /* A nop call with no return */ complete_pdu(s, pdu, 7); } +static void v9fs_link(V9fsState *s, V9fsPDU *pdu) +{ + int32_t dfid, oldfid; + V9fsFidState *dfidp, *oldfidp; + V9fsString name, fullname; + size_t offset = 7; + int err = 0; + + v9fs_string_init(&fullname); + + pdu_unmarshal(pdu, offset, "dds", &dfid, &oldfid, &name); + + dfidp = lookup_fid(s, dfid); + if (dfidp == NULL) { + err = -errno; + goto out; + } + + oldfidp = lookup_fid(s, oldfid); + if (oldfidp == NULL) { + err = -errno; + goto out; + } + + v9fs_string_sprintf(&fullname, "%s/%s", dfidp->path.data, name.data); + err = offset; + err = v9fs_do_link(s, &oldfidp->path, &fullname); + if (err) { + err = -errno; + } + v9fs_string_free(&fullname); + +out: + v9fs_string_free(&name); + complete_pdu(s, pdu, err); +} + static void v9fs_remove_post_remove(V9fsState *s, V9fsRemoveState *vs, int err) { - /* For TREMOVE we need to clunk the fid even on failed remove */ - err = free_fid(s, vs->fidp->fid); if (err < 0) { - goto out; + err = -errno; + } else { + err = vs->offset; } - err = vs->offset; -out: + /* For TREMOVE we need to clunk the fid even on failed remove */ + free_fid(s, vs->fidp->fid); + complete_pdu(s, vs->pdu, err); qemu_free(vs); } @@ -1931,11 +2735,6 @@ static void v9fs_wstat_post_rename(V9fsState *s, V9fsWstatState *vs, int err) if (err < 0) { goto out; } - - if (vs->v9stat.name.size != 0) { - v9fs_string_free(&vs->nname); - } - if (vs->v9stat.length != -1) { if (v9fs_do_truncate(s, &vs->fidp->path, vs->v9stat.length) < 0) { err = -errno; @@ -1950,17 +2749,29 @@ out: qemu_free(vs); } -static void v9fs_wstat_post_chown(V9fsState *s, V9fsWstatState *vs, int err) +static int v9fs_complete_rename(V9fsState *s, V9fsRenameState *vs) { - V9fsFidState *fidp; - if (err < 0) { - goto out; - } + int err = 0; + char *old_name, *new_name; + char *end; - if (vs->v9stat.name.size != 0) { - char *old_name, *new_name; - char *end; + if (vs->newdirfid != -1) { + V9fsFidState *dirfidp; + dirfidp = lookup_fid(s, vs->newdirfid); + if (dirfidp == NULL) { + err = -ENOENT; + goto out; + } + + BUG_ON(dirfidp->fid_type != P9_FID_NONE); + + new_name = qemu_mallocz(dirfidp->path.size + vs->name.size + 2); + + strcpy(new_name, dirfidp->path.data); + strcat(new_name, "/"); + strcat(new_name + dirfidp->path.size, vs->name.data); + } else { old_name = vs->fidp->path.data; end = strrchr(old_name, '/'); if (end) { @@ -1968,44 +2779,74 @@ static void v9fs_wstat_post_chown(V9fsState *s, V9fsWstatState *vs, int err) } else { end = old_name; } + new_name = qemu_mallocz(end - old_name + vs->name.size + 1); - new_name = qemu_malloc(end - old_name + vs->v9stat.name.size + 1); + strncat(new_name, old_name, end - old_name); + strncat(new_name + (end - old_name), vs->name.data, vs->name.size); + } - memset(new_name, 0, end - old_name + vs->v9stat.name.size + 1); - memcpy(new_name, old_name, end - old_name); - memcpy(new_name + (end - old_name), vs->v9stat.name.data, - vs->v9stat.name.size); - vs->nname.data = new_name; - vs->nname.size = strlen(new_name); + v9fs_string_free(&vs->name); + vs->name.data = qemu_strdup(new_name); + vs->name.size = strlen(new_name); - if (strcmp(new_name, vs->fidp->path.data) != 0) { - if (v9fs_do_rename(s, &vs->fidp->path, &vs->nname)) { - err = -errno; - } else { - /* - * Fixup fid's pointing to the old name to - * start pointing to the new name - */ - for (fidp = s->fid_list; fidp; fidp = fidp->next) { - - if (vs->fidp == fidp) { - /* - * we replace name of this fid towards the end - * so that our below strcmp will work - */ - continue; - } - if (!strncmp(vs->fidp->path.data, fidp->path.data, - strlen(vs->fidp->path.data))) { - /* replace the name */ - v9fs_fix_path(&fidp->path, &vs->nname, - strlen(vs->fidp->path.data)); - } + if (strcmp(new_name, vs->fidp->path.data) != 0) { + if (v9fs_do_rename(s, &vs->fidp->path, &vs->name)) { + err = -errno; + } else { + V9fsFidState *fidp; + /* + * Fixup fid's pointing to the old name to + * start pointing to the new name + */ + for (fidp = s->fid_list; fidp; fidp = fidp->next) { + if (vs->fidp == fidp) { + /* + * we replace name of this fid towards the end + * so that our below strcmp will work + */ + continue; + } + if (!strncmp(vs->fidp->path.data, fidp->path.data, + strlen(vs->fidp->path.data))) { + /* replace the name */ + v9fs_fix_path(&fidp->path, &vs->name, + strlen(vs->fidp->path.data)); } - v9fs_string_copy(&vs->fidp->path, &vs->nname); } + v9fs_string_copy(&vs->fidp->path, &vs->name); } } +out: + v9fs_string_free(&vs->name); + return err; +} + +static void v9fs_rename_post_rename(V9fsState *s, V9fsRenameState *vs, int err) +{ + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + +static void v9fs_wstat_post_chown(V9fsState *s, V9fsWstatState *vs, int err) +{ + if (err < 0) { + goto out; + } + + if (vs->v9stat.name.size != 0) { + V9fsRenameState *vr; + + vr = qemu_mallocz(sizeof(V9fsRenameState)); + vr->newdirfid = -1; + vr->pdu = vs->pdu; + vr->fidp = vs->fidp; + vr->offset = vs->offset; + vr->name.size = vs->v9stat.name.size; + vr->name.data = qemu_strdup(vs->v9stat.name.data); + + err = v9fs_complete_rename(s, vr); + qemu_free(vr); + } v9fs_wstat_post_rename(s, vs, err); return; @@ -2015,6 +2856,34 @@ out: qemu_free(vs); } +static void v9fs_rename(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid; + V9fsRenameState *vs; + ssize_t err = 0; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + pdu_unmarshal(vs->pdu, vs->offset, "dds", &fid, &vs->newdirfid, &vs->name); + + vs->fidp = lookup_fid(s, fid); + if (vs->fidp == NULL) { + err = -ENOENT; + goto out; + } + + BUG_ON(vs->fidp->fid_type != P9_FID_NONE); + + err = v9fs_complete_rename(s, vs); + v9fs_rename_post_rename(s, vs, err); + return; +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + static void v9fs_wstat_post_utime(V9fsState *s, V9fsWstatState *vs, int err) { if (err < 0) { @@ -2042,11 +2911,22 @@ static void v9fs_wstat_post_chmod(V9fsState *s, V9fsWstatState *vs, int err) goto out; } - if (vs->v9stat.mtime != -1) { - struct utimbuf tb; - tb.actime = 0; - tb.modtime = vs->v9stat.mtime; - if (v9fs_do_utime(s, &vs->fidp->path, &tb)) { + if (vs->v9stat.mtime != -1 || vs->v9stat.atime != -1) { + struct timespec times[2]; + if (vs->v9stat.atime != -1) { + times[0].tv_sec = vs->v9stat.atime; + times[0].tv_nsec = 0; + } else { + times[0].tv_nsec = UTIME_OMIT; + } + if (vs->v9stat.mtime != -1) { + times[1].tv_sec = vs->v9stat.mtime; + times[1].tv_nsec = 0; + } else { + times[1].tv_nsec = UTIME_OMIT; + } + + if (v9fs_do_utimensat(s, &vs->fidp->path, times)) { err = -errno; } } @@ -2121,7 +3001,7 @@ static void v9fs_wstat(V9fsState *s, V9fsPDU *pdu) /* do we need to sync the file? */ if (donttouch_stat(&vs->v9stat)) { - err = v9fs_do_fsync(s, vs->fidp->fd); + err = v9fs_do_fsync(s, vs->fidp->fs.fd); v9fs_wstat_post_fsync(s, vs, err); return; } @@ -2141,21 +3021,565 @@ out: qemu_free(vs); } +static void v9fs_statfs_post_statfs(V9fsState *s, V9fsStatfsState *vs, int err) +{ + int32_t bsize_factor; + + if (err) { + err = -errno; + goto out; + } + + /* + * compute bsize factor based on host file system block size + * and client msize + */ + bsize_factor = (s->msize - P9_IOHDRSZ)/vs->stbuf.f_bsize; + if (!bsize_factor) { + bsize_factor = 1; + } + vs->v9statfs.f_type = vs->stbuf.f_type; + vs->v9statfs.f_bsize = vs->stbuf.f_bsize; + vs->v9statfs.f_bsize *= bsize_factor; + /* + * f_bsize is adjusted(multiplied) by bsize factor, so we need to + * adjust(divide) the number of blocks, free blocks and available + * blocks by bsize factor + */ + vs->v9statfs.f_blocks = vs->stbuf.f_blocks/bsize_factor; + vs->v9statfs.f_bfree = vs->stbuf.f_bfree/bsize_factor; + vs->v9statfs.f_bavail = vs->stbuf.f_bavail/bsize_factor; + vs->v9statfs.f_files = vs->stbuf.f_files; + vs->v9statfs.f_ffree = vs->stbuf.f_ffree; + vs->v9statfs.fsid_val = (unsigned int) vs->stbuf.f_fsid.__val[0] | + (unsigned long long)vs->stbuf.f_fsid.__val[1] << 32; + vs->v9statfs.f_namelen = vs->stbuf.f_namelen; + + vs->offset += pdu_marshal(vs->pdu, vs->offset, "ddqqqqqqd", + vs->v9statfs.f_type, vs->v9statfs.f_bsize, vs->v9statfs.f_blocks, + vs->v9statfs.f_bfree, vs->v9statfs.f_bavail, vs->v9statfs.f_files, + vs->v9statfs.f_ffree, vs->v9statfs.fsid_val, + vs->v9statfs.f_namelen); + +out: + complete_pdu(s, vs->pdu, vs->offset); + qemu_free(vs); +} + +static void v9fs_statfs(V9fsState *s, V9fsPDU *pdu) +{ + V9fsStatfsState *vs; + ssize_t err = 0; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + memset(&vs->v9statfs, 0, sizeof(vs->v9statfs)); + + pdu_unmarshal(vs->pdu, vs->offset, "d", &vs->fid); + + vs->fidp = lookup_fid(s, vs->fid); + if (vs->fidp == NULL) { + err = -ENOENT; + goto out; + } + + err = v9fs_do_statfs(s, &vs->fidp->path, &vs->stbuf); + v9fs_statfs_post_statfs(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + +static void v9fs_mknod_post_lstat(V9fsState *s, V9fsMkState *vs, int err) +{ + if (err == -1) { + err = -errno; + goto out; + } + + stat_to_qid(&vs->stbuf, &vs->qid); + vs->offset += pdu_marshal(vs->pdu, vs->offset, "Q", &vs->qid); + err = vs->offset; +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->fullname); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_mknod_post_mknod(V9fsState *s, V9fsMkState *vs, int err) +{ + if (err == -1) { + err = -errno; + goto out; + } + + err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf); + v9fs_mknod_post_lstat(s, vs, err); + return; +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->fullname); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_mknod(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid; + V9fsMkState *vs; + int err = 0; + V9fsFidState *fidp; + gid_t gid; + int mode; + int major, minor; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + v9fs_string_init(&vs->fullname); + pdu_unmarshal(vs->pdu, vs->offset, "dsdddd", &fid, &vs->name, &mode, + &major, &minor, &gid); + + fidp = lookup_fid(s, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out; + } + + v9fs_string_sprintf(&vs->fullname, "%s/%s", fidp->path.data, vs->name.data); + err = v9fs_do_mknod(s, vs->fullname.data, mode, makedev(major, minor), + fidp->uid, gid); + v9fs_mknod_post_mknod(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->fullname); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +/* + * Implement posix byte range locking code + * Server side handling of locking code is very simple, because 9p server in + * QEMU can handle only one client. And most of the lock handling + * (like conflict, merging) etc is done by the VFS layer itself, so no need to + * do any thing in * qemu 9p server side lock code path. + * So when a TLOCK request comes, always return success + */ + +static void v9fs_lock(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid, err = 0; + V9fsLockState *vs; + + vs = qemu_mallocz(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + vs->flock = qemu_malloc(sizeof(*vs->flock)); + pdu_unmarshal(vs->pdu, vs->offset, "dbdqqds", &fid, &vs->flock->type, + &vs->flock->flags, &vs->flock->start, &vs->flock->length, + &vs->flock->proc_id, &vs->flock->client_id); + + vs->status = P9_LOCK_ERROR; + + /* We support only block flag now (that too ignored currently) */ + if (vs->flock->flags & ~P9_LOCK_FLAGS_BLOCK) { + err = -EINVAL; + goto out; + } + vs->fidp = lookup_fid(s, fid); + if (vs->fidp == NULL) { + err = -ENOENT; + goto out; + } + + err = v9fs_do_fstat(s, vs->fidp->fs.fd, &vs->stbuf); + if (err < 0) { + err = -errno; + goto out; + } + vs->status = P9_LOCK_SUCCESS; +out: + vs->offset += pdu_marshal(vs->pdu, vs->offset, "b", vs->status); + complete_pdu(s, vs->pdu, err); + qemu_free(vs->flock); + qemu_free(vs); +} + +/* + * When a TGETLOCK request comes, always return success because all lock + * handling is done by client's VFS layer. + */ + +static void v9fs_getlock(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid, err = 0; + V9fsGetlockState *vs; + + vs = qemu_mallocz(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + vs->glock = qemu_malloc(sizeof(*vs->glock)); + pdu_unmarshal(vs->pdu, vs->offset, "dbqqds", &fid, &vs->glock->type, + &vs->glock->start, &vs->glock->length, &vs->glock->proc_id, + &vs->glock->client_id); + + vs->fidp = lookup_fid(s, fid); + if (vs->fidp == NULL) { + err = -ENOENT; + goto out; + } + + err = v9fs_do_fstat(s, vs->fidp->fs.fd, &vs->stbuf); + if (err < 0) { + err = -errno; + goto out; + } + vs->glock->type = F_UNLCK; + vs->offset += pdu_marshal(vs->pdu, vs->offset, "bqqds", vs->glock->type, + vs->glock->start, vs->glock->length, vs->glock->proc_id, + &vs->glock->client_id); +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs->glock); + qemu_free(vs); +} + +static void v9fs_mkdir_post_lstat(V9fsState *s, V9fsMkState *vs, int err) +{ + if (err == -1) { + err = -errno; + goto out; + } + + stat_to_qid(&vs->stbuf, &vs->qid); + vs->offset += pdu_marshal(vs->pdu, vs->offset, "Q", &vs->qid); + err = vs->offset; +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->fullname); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_mkdir_post_mkdir(V9fsState *s, V9fsMkState *vs, int err) +{ + if (err == -1) { + err = -errno; + goto out; + } + + err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf); + v9fs_mkdir_post_lstat(s, vs, err); + return; +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->fullname); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_mkdir(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid; + V9fsMkState *vs; + int err = 0; + V9fsFidState *fidp; + gid_t gid; + int mode; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + v9fs_string_init(&vs->fullname); + pdu_unmarshal(vs->pdu, vs->offset, "dsdd", &fid, &vs->name, &mode, + &gid); + + fidp = lookup_fid(s, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out; + } + + v9fs_string_sprintf(&vs->fullname, "%s/%s", fidp->path.data, vs->name.data); + err = v9fs_do_mkdir(s, vs->fullname.data, mode, fidp->uid, gid); + v9fs_mkdir_post_mkdir(s, vs, err); + return; + +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->fullname); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_post_xattr_getvalue(V9fsState *s, V9fsXattrState *vs, int err) +{ + + if (err < 0) { + err = -errno; + free_fid(s, vs->xattr_fidp->fid); + goto out; + } + vs->offset += pdu_marshal(vs->pdu, vs->offset, "q", vs->size); + err = vs->offset; +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + qemu_free(vs); + return; +} + +static void v9fs_post_xattr_check(V9fsState *s, V9fsXattrState *vs, ssize_t err) +{ + if (err < 0) { + err = -errno; + free_fid(s, vs->xattr_fidp->fid); + goto out; + } + /* + * Read the xattr value + */ + vs->xattr_fidp->fs.xattr.len = vs->size; + vs->xattr_fidp->fid_type = P9_FID_XATTR; + vs->xattr_fidp->fs.xattr.copied_len = -1; + if (vs->size) { + vs->xattr_fidp->fs.xattr.value = qemu_malloc(vs->size); + err = v9fs_do_lgetxattr(s, &vs->xattr_fidp->path, + &vs->name, vs->xattr_fidp->fs.xattr.value, + vs->xattr_fidp->fs.xattr.len); + } + v9fs_post_xattr_getvalue(s, vs, err); + return; +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_post_lxattr_getvalue(V9fsState *s, + V9fsXattrState *vs, int err) +{ + if (err < 0) { + err = -errno; + free_fid(s, vs->xattr_fidp->fid); + goto out; + } + vs->offset += pdu_marshal(vs->pdu, vs->offset, "q", vs->size); + err = vs->offset; +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + qemu_free(vs); + return; +} + +static void v9fs_post_lxattr_check(V9fsState *s, + V9fsXattrState *vs, ssize_t err) +{ + if (err < 0) { + err = -errno; + free_fid(s, vs->xattr_fidp->fid); + goto out; + } + /* + * Read the xattr value + */ + vs->xattr_fidp->fs.xattr.len = vs->size; + vs->xattr_fidp->fid_type = P9_FID_XATTR; + vs->xattr_fidp->fs.xattr.copied_len = -1; + if (vs->size) { + vs->xattr_fidp->fs.xattr.value = qemu_malloc(vs->size); + err = v9fs_do_llistxattr(s, &vs->xattr_fidp->path, + vs->xattr_fidp->fs.xattr.value, + vs->xattr_fidp->fs.xattr.len); + } + v9fs_post_lxattr_getvalue(s, vs, err); + return; +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_xattrwalk(V9fsState *s, V9fsPDU *pdu) +{ + ssize_t err = 0; + V9fsXattrState *vs; + int32_t fid, newfid; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + pdu_unmarshal(vs->pdu, vs->offset, "dds", &fid, &newfid, &vs->name); + vs->file_fidp = lookup_fid(s, fid); + if (vs->file_fidp == NULL) { + err = -ENOENT; + goto out; + } + + vs->xattr_fidp = alloc_fid(s, newfid); + if (vs->xattr_fidp == NULL) { + err = -EINVAL; + goto out; + } + + v9fs_string_copy(&vs->xattr_fidp->path, &vs->file_fidp->path); + if (vs->name.data[0] == 0) { + /* + * listxattr request. Get the size first + */ + vs->size = v9fs_do_llistxattr(s, &vs->xattr_fidp->path, + NULL, 0); + if (vs->size < 0) { + err = vs->size; + } + v9fs_post_lxattr_check(s, vs, err); + return; + } else { + /* + * specific xattr fid. We check for xattr + * presence also collect the xattr size + */ + vs->size = v9fs_do_lgetxattr(s, &vs->xattr_fidp->path, + &vs->name, NULL, 0); + if (vs->size < 0) { + err = vs->size; + } + v9fs_post_xattr_check(s, vs, err); + return; + } +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_xattrcreate(V9fsState *s, V9fsPDU *pdu) +{ + int flags; + int32_t fid; + ssize_t err = 0; + V9fsXattrState *vs; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + pdu_unmarshal(vs->pdu, vs->offset, "dsqd", + &fid, &vs->name, &vs->size, &flags); + + vs->file_fidp = lookup_fid(s, fid); + if (vs->file_fidp == NULL) { + err = -EINVAL; + goto out; + } + + /* Make the file fid point to xattr */ + vs->xattr_fidp = vs->file_fidp; + vs->xattr_fidp->fid_type = P9_FID_XATTR; + vs->xattr_fidp->fs.xattr.copied_len = 0; + vs->xattr_fidp->fs.xattr.len = vs->size; + vs->xattr_fidp->fs.xattr.flags = flags; + v9fs_string_init(&vs->xattr_fidp->fs.xattr.name); + v9fs_string_copy(&vs->xattr_fidp->fs.xattr.name, &vs->name); + if (vs->size) + vs->xattr_fidp->fs.xattr.value = qemu_malloc(vs->size); + else + vs->xattr_fidp->fs.xattr.value = NULL; + +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->name); + qemu_free(vs); +} + +static void v9fs_readlink_post_readlink(V9fsState *s, V9fsReadLinkState *vs, + int err) +{ + if (err < 0) { + err = -errno; + goto out; + } + vs->offset += pdu_marshal(vs->pdu, vs->offset, "s", &vs->target); + err = vs->offset; +out: + complete_pdu(s, vs->pdu, err); + v9fs_string_free(&vs->target); + qemu_free(vs); +} + +static void v9fs_readlink(V9fsState *s, V9fsPDU *pdu) +{ + int32_t fid; + V9fsReadLinkState *vs; + int err = 0; + V9fsFidState *fidp; + + vs = qemu_malloc(sizeof(*vs)); + vs->pdu = pdu; + vs->offset = 7; + + pdu_unmarshal(vs->pdu, vs->offset, "d", &fid); + + fidp = lookup_fid(s, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out; + } + + v9fs_string_init(&vs->target); + err = v9fs_do_readlink(s, &fidp->path, &vs->target); + v9fs_readlink_post_readlink(s, vs, err); + return; +out: + complete_pdu(s, vs->pdu, err); + qemu_free(vs); +} + typedef void (pdu_handler_t)(V9fsState *s, V9fsPDU *pdu); static pdu_handler_t *pdu_handlers[] = { + [P9_TREADDIR] = v9fs_readdir, + [P9_TSTATFS] = v9fs_statfs, + [P9_TGETATTR] = v9fs_getattr, + [P9_TSETATTR] = v9fs_setattr, + [P9_TXATTRWALK] = v9fs_xattrwalk, + [P9_TXATTRCREATE] = v9fs_xattrcreate, + [P9_TMKNOD] = v9fs_mknod, + [P9_TRENAME] = v9fs_rename, + [P9_TLOCK] = v9fs_lock, + [P9_TGETLOCK] = v9fs_getlock, + [P9_TREADLINK] = v9fs_readlink, + [P9_TMKDIR] = v9fs_mkdir, [P9_TVERSION] = v9fs_version, + [P9_TLOPEN] = v9fs_open, [P9_TATTACH] = v9fs_attach, [P9_TSTAT] = v9fs_stat, [P9_TWALK] = v9fs_walk, [P9_TCLUNK] = v9fs_clunk, + [P9_TFSYNC] = v9fs_fsync, [P9_TOPEN] = v9fs_open, [P9_TREAD] = v9fs_read, #if 0 [P9_TAUTH] = v9fs_auth, #endif [P9_TFLUSH] = v9fs_flush, + [P9_TLINK] = v9fs_link, + [P9_TSYMLINK] = v9fs_symlink, [P9_TCREATE] = v9fs_create, + [P9_TLCREATE] = v9fs_lcreate, [P9_TWRITE] = v9fs_write, [P9_TWSTAT] = v9fs_wstat, [P9_TREMOVE] = v9fs_remove, @@ -2252,8 +3676,8 @@ VirtIODevice *virtio_9p_init(DeviceState *dev, V9fsConf *conf) if (!fse) { /* We don't have a fsdev identified by fsdev_id */ - fprintf(stderr, "Virtio-9p device couldn't find fsdev " - "with the id %s\n", conf->fsdev_id); + fprintf(stderr, "Virtio-9p device couldn't find fsdev with the " + "id = %s\n", conf->fsdev_id ? conf->fsdev_id : "NULL"); exit(1); } @@ -2268,17 +3692,26 @@ VirtIODevice *virtio_9p_init(DeviceState *dev, V9fsConf *conf) if (!strcmp(fse->security_model, "passthrough")) { /* Files on the Fileserver set to client user credentials */ s->ctx.fs_sm = SM_PASSTHROUGH; + s->ctx.xops = passthrough_xattr_ops; } else if (!strcmp(fse->security_model, "mapped")) { /* Files on the fileserver are set to QEMU credentials. * Client user credentials are saved in extended attributes. */ s->ctx.fs_sm = SM_MAPPED; + s->ctx.xops = mapped_xattr_ops; + } else if (!strcmp(fse->security_model, "none")) { + /* + * Files on the fileserver are set to QEMU credentials. + */ + s->ctx.fs_sm = SM_NONE; + s->ctx.xops = none_xattr_ops; } else { - /* user haven't specified a correct security option */ - fprintf(stderr, "one of the following must be specified as the" + fprintf(stderr, "Default to security_model=none. You may want" + " enable advanced security model using " "security option:\n\t security_model=passthrough \n\t " "security_model=mapped\n"); - return NULL; + s->ctx.fs_sm = SM_NONE; + s->ctx.xops = none_xattr_ops; } if (lstat(fse->path, &stat)) { diff --git a/hw/virtio-9p.h b/hw/virtio-9p.h index 67f808761f..6c233192e3 100644 --- a/hw/virtio-9p.h +++ b/hw/virtio-9p.h @@ -13,6 +13,42 @@ #define VIRTIO_9P_MOUNT_TAG 0 enum { + P9_TLERROR = 6, + P9_RLERROR, + P9_TSTATFS = 8, + P9_RSTATFS, + P9_TLOPEN = 12, + P9_RLOPEN, + P9_TLCREATE = 14, + P9_RLCREATE, + P9_TSYMLINK = 16, + P9_RSYMLINK, + P9_TMKNOD = 18, + P9_RMKNOD, + P9_TRENAME = 20, + P9_RRENAME, + P9_TREADLINK = 22, + P9_RREADLINK, + P9_TGETATTR = 24, + P9_RGETATTR, + P9_TSETATTR = 26, + P9_RSETATTR, + P9_TXATTRWALK = 30, + P9_RXATTRWALK, + P9_TXATTRCREATE = 32, + P9_RXATTRCREATE, + P9_TREADDIR = 40, + P9_RREADDIR, + P9_TFSYNC = 50, + P9_RFSYNC, + P9_TLOCK = 52, + P9_RLOCK, + P9_TGETLOCK = 54, + P9_RGETLOCK, + P9_TLINK = 70, + P9_RLINK, + P9_TMKDIR = 72, + P9_RMKDIR, P9_TVERSION = 100, P9_RVERSION, P9_TAUTH = 102, @@ -57,10 +93,21 @@ enum { P9_QTFILE = 0x00, }; +enum p9_proto_version { + V9FS_PROTO_2000U = 0x01, + V9FS_PROTO_2000L = 0x02, +}; + #define P9_NOTAG (u16)(~0) #define P9_NOFID (u32)(~0) #define P9_MAXWELEM 16 +/* + * ample room for Twrite/Rread header + * size[4] Tread/Twrite tag[2] fid[4] offset[8] count[4] + */ +#define P9_IOHDRSZ 24 + typedef struct V9fsPDU V9fsPDU; struct V9fsPDU @@ -122,12 +169,32 @@ typedef struct V9fsStat int32_t n_muid; } V9fsStat; +enum { + P9_FID_NONE = 0, + P9_FID_FILE, + P9_FID_DIR, + P9_FID_XATTR, +}; + +typedef struct V9fsXattr +{ + int64_t copied_len; + int64_t len; + void *value; + V9fsString name; + int flags; +} V9fsXattr; + struct V9fsFidState { + int fid_type; int32_t fid; V9fsString path; - int fd; - DIR *dir; + union { + int fd; + DIR *dir; + V9fsXattr xattr; + } fs; uid_t uid; V9fsFidState *next; }; @@ -144,6 +211,8 @@ typedef struct V9fsState uint16_t tag_len; uint8_t *tag; size_t config_size; + enum p9_proto_version proto_version; + int32_t msize; } V9fsState; typedef struct V9fsCreateState { @@ -157,8 +226,20 @@ typedef struct V9fsCreateState { V9fsString name; V9fsString extension; V9fsString fullname; + int iounit; } V9fsCreateState; +typedef struct V9fsLcreateState { + V9fsPDU *pdu; + size_t offset; + V9fsFidState *fidp; + V9fsQID qid; + int32_t iounit; + struct stat stbuf; + V9fsString name; + V9fsString fullname; +} V9fsLcreateState; + typedef struct V9fsStatState { V9fsPDU *pdu; size_t offset; @@ -167,6 +248,37 @@ typedef struct V9fsStatState { struct stat stbuf; } V9fsStatState; +typedef struct V9fsStatDotl { + uint64_t st_result_mask; + V9fsQID qid; + uint32_t st_mode; + uint32_t st_uid; + uint32_t st_gid; + uint64_t st_nlink; + uint64_t st_rdev; + uint64_t st_size; + uint64_t st_blksize; + uint64_t st_blocks; + uint64_t st_atime_sec; + uint64_t st_atime_nsec; + uint64_t st_mtime_sec; + uint64_t st_mtime_nsec; + uint64_t st_ctime_sec; + uint64_t st_ctime_nsec; + uint64_t st_btime_sec; + uint64_t st_btime_nsec; + uint64_t st_gen; + uint64_t st_data_version; +} V9fsStatDotl; + +typedef struct V9fsStatStateDotl { + V9fsPDU *pdu; + size_t offset; + V9fsStatDotl v9stat_dotl; + struct stat stbuf; +} V9fsStatStateDotl; + + typedef struct V9fsWalkState { V9fsPDU *pdu; size_t offset; @@ -183,10 +295,11 @@ typedef struct V9fsWalkState { typedef struct V9fsOpenState { V9fsPDU *pdu; size_t offset; - int8_t mode; + int32_t mode; V9fsFidState *fidp; V9fsQID qid; struct stat stbuf; + int iounit; } V9fsOpenState; typedef struct V9fsReadState { @@ -235,9 +348,41 @@ typedef struct V9fsWstatState V9fsStat v9stat; V9fsFidState *fidp; struct stat stbuf; - V9fsString nname; } V9fsWstatState; +typedef struct V9fsSymlinkState +{ + V9fsPDU *pdu; + size_t offset; + V9fsString name; + V9fsString symname; + V9fsString fullname; + V9fsFidState *dfidp; + V9fsQID qid; + struct stat stbuf; +} V9fsSymlinkState; + +typedef struct V9fsIattr +{ + int32_t valid; + int32_t mode; + int32_t uid; + int32_t gid; + int64_t size; + int64_t atime_sec; + int64_t atime_nsec; + int64_t mtime_sec; + int64_t mtime_nsec; +} V9fsIattr; + +typedef struct V9fsSetattrState +{ + V9fsPDU *pdu; + size_t offset; + V9fsIattr v9iattr; + V9fsFidState *fidp; +} V9fsSetattrState; + struct virtio_9p_config { /* number of characters in tag */ @@ -246,6 +391,110 @@ struct virtio_9p_config uint8_t tag[0]; } __attribute__((packed)); +typedef struct V9fsStatfs +{ + uint32_t f_type; + uint32_t f_bsize; + uint64_t f_blocks; + uint64_t f_bfree; + uint64_t f_bavail; + uint64_t f_files; + uint64_t f_ffree; + uint64_t fsid_val; + uint32_t f_namelen; +} V9fsStatfs; + +typedef struct V9fsStatfsState { + V9fsPDU *pdu; + size_t offset; + int32_t fid; + V9fsStatfs v9statfs; + V9fsFidState *fidp; + struct statfs stbuf; +} V9fsStatfsState; + +typedef struct V9fsMkState { + V9fsPDU *pdu; + size_t offset; + V9fsQID qid; + struct stat stbuf; + V9fsString name; + V9fsString fullname; +} V9fsMkState; + +typedef struct V9fsRenameState { + V9fsPDU *pdu; + V9fsFidState *fidp; + size_t offset; + int32_t newdirfid; + V9fsString name; +} V9fsRenameState; + +typedef struct V9fsXattrState +{ + V9fsPDU *pdu; + size_t offset; + V9fsFidState *file_fidp; + V9fsFidState *xattr_fidp; + V9fsString name; + int64_t size; + int flags; + void *value; +} V9fsXattrState; + +#define P9_LOCK_SUCCESS 0 +#define P9_LOCK_BLOCKED 1 +#define P9_LOCK_ERROR 2 +#define P9_LOCK_GRACE 3 + +#define P9_LOCK_FLAGS_BLOCK 1 +#define P9_LOCK_FLAGS_RECLAIM 2 + +typedef struct V9fsFlock +{ + uint8_t type; + uint32_t flags; + uint64_t start; /* absolute offset */ + uint64_t length; + uint32_t proc_id; + V9fsString client_id; +} V9fsFlock; + +typedef struct V9fsLockState +{ + V9fsPDU *pdu; + size_t offset; + int8_t status; + struct stat stbuf; + V9fsFidState *fidp; + V9fsFlock *flock; +} V9fsLockState; + +typedef struct V9fsGetlock +{ + uint8_t type; + uint64_t start; /* absolute offset */ + uint64_t length; + uint32_t proc_id; + V9fsString client_id; +} V9fsGetlock; + +typedef struct V9fsGetlockState +{ + V9fsPDU *pdu; + size_t offset; + struct stat stbuf; + V9fsFidState *fidp; + V9fsGetlock *glock; +} V9fsGetlockState; + +typedef struct V9fsReadLinkState +{ + V9fsPDU *pdu; + size_t offset; + V9fsString target; +} V9fsReadLinkState; + extern size_t pdu_packunpack(void *addr, struct iovec *sg, int sg_count, size_t offset, size_t size, int pack); diff --git a/hw/virtio-balloon.c b/hw/virtio-balloon.c index 9fe3886b0f..8adddeaa53 100644 --- a/hw/virtio-balloon.c +++ b/hw/virtio-balloon.c @@ -29,6 +29,10 @@ #include <sys/mman.h> #endif +/* Disable guest-provided stats by now (https://bugzilla.redhat.com/show_bug.cgi?id=623903) */ +#define ENABLE_GUEST_STATS 0 + + typedef struct VirtIOBalloon { VirtIODevice vdev; @@ -51,8 +55,8 @@ static void balloon_page(void *addr, int deflate) { #if defined(__linux__) if (!kvm_enabled() || kvm_has_sync_mmu()) - madvise(addr, TARGET_PAGE_SIZE, - deflate ? MADV_WILLNEED : MADV_DONTNEED); + qemu_madvise(addr, TARGET_PAGE_SIZE, + deflate ? QEMU_MADV_WILLNEED : QEMU_MADV_DONTNEED); #endif } @@ -83,12 +87,14 @@ static QObject *get_stats_qobject(VirtIOBalloon *dev) VIRTIO_BALLOON_PFN_SHIFT); stat_put(dict, "actual", actual); +#if ENABLE_GUEST_STATS stat_put(dict, "mem_swapped_in", dev->stats[VIRTIO_BALLOON_S_SWAP_IN]); stat_put(dict, "mem_swapped_out", dev->stats[VIRTIO_BALLOON_S_SWAP_OUT]); stat_put(dict, "major_page_faults", dev->stats[VIRTIO_BALLOON_S_MAJFLT]); stat_put(dict, "minor_page_faults", dev->stats[VIRTIO_BALLOON_S_MINFLT]); stat_put(dict, "free_mem", dev->stats[VIRTIO_BALLOON_S_MEMFREE]); stat_put(dict, "total_mem", dev->stats[VIRTIO_BALLOON_S_MEMTOT]); +#endif return QOBJECT(dict); } @@ -214,7 +220,7 @@ static void virtio_balloon_to_target(void *opaque, ram_addr_t target, } dev->stats_callback = cb; dev->stats_opaque_callback_data = cb_data; - if (dev->vdev.guest_features & (1 << VIRTIO_BALLOON_F_STATS_VQ)) { + if (ENABLE_GUEST_STATS && (dev->vdev.guest_features & (1 << VIRTIO_BALLOON_F_STATS_VQ))) { virtqueue_push(dev->svq, &dev->stats_vq_elem, dev->stats_vq_offset); virtio_notify(&dev->vdev, dev->svq); } else { diff --git a/hw/virtio-blk.c b/hw/virtio-blk.c index 8747634fbe..a1df26dbcf 100644 --- a/hw/virtio-blk.c +++ b/hw/virtio-blk.c @@ -12,6 +12,9 @@ */ #include <qemu-common.h> +#include "qemu-error.h" +#include "trace.h" +#include "blockdev.h" #include "virtio-blk.h" #ifdef __linux__ # include <scsi/sg.h> @@ -27,6 +30,7 @@ typedef struct VirtIOBlock BlockConf *conf; unsigned short sector_mask; char sn[BLOCK_SERIAL_STRLEN]; + DeviceState *qdev; } VirtIOBlock; static VirtIOBlock *to_virtio_blk(VirtIODevice *vdev) @@ -49,6 +53,8 @@ static void virtio_blk_req_complete(VirtIOBlockReq *req, int status) { VirtIOBlock *s = req->dev; + trace_virtio_blk_req_complete(req, status); + req->in->status = status; virtqueue_push(s->vq, &req->elem, req->qiov.size + sizeof(*req->in)); virtio_notify(&s->vdev, s->vq); @@ -85,6 +91,8 @@ static void virtio_blk_rw_complete(void *opaque, int ret) { VirtIOBlockReq *req = opaque; + trace_virtio_blk_rw_complete(req, ret); + if (ret) { int is_read = !(req->out->type & VIRTIO_BLK_T_OUT); if (virtio_blk_handle_rw_error(req, -ret, is_read)) @@ -267,6 +275,8 @@ static void virtio_blk_handle_write(VirtIOBlockReq *req, MultiReqBuffer *mrb) { BlockRequest *blkreq; + trace_virtio_blk_handle_write(req, req->out->sector, req->qiov.size / 512); + if (req->out->sector & req->dev->sector_mask) { virtio_blk_rw_complete(req, -EIO); return; @@ -478,6 +488,11 @@ static int virtio_blk_load(QEMUFile *f, void *opaque, int version_id) qemu_get_buffer(f, (unsigned char*)&req->elem, sizeof(req->elem)); req->next = s->rq; s->rq = req; + + virtqueue_map_sg(req->elem.in_sg, req->elem.in_addr, + req->elem.in_num, 1); + virtqueue_map_sg(req->elem.out_sg, req->elem.out_addr, + req->elem.out_num, 0); } return 0; @@ -490,6 +505,15 @@ VirtIODevice *virtio_blk_init(DeviceState *dev, BlockConf *conf) static int virtio_blk_id; DriveInfo *dinfo; + if (!conf->bs) { + error_report("virtio-blk-pci: drive property not set"); + return NULL; + } + if (!bdrv_is_inserted(conf->bs)) { + error_report("Device needs media, but drive is empty"); + return NULL; + } + s = (VirtIOBlock *)virtio_common_init("virtio-blk", VIRTIO_ID_BLOCK, sizeof(struct virtio_blk_config), sizeof(VirtIOBlock)); @@ -512,9 +536,17 @@ VirtIODevice *virtio_blk_init(DeviceState *dev, BlockConf *conf) s->vq = virtio_add_queue(&s->vdev, 128, virtio_blk_handle_output); qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s); + s->qdev = dev; register_savevm(dev, "virtio-blk", virtio_blk_id++, 2, virtio_blk_save, virtio_blk_load, s); bdrv_set_removable(s->bs, 0); + s->bs->buffer_alignment = conf->logical_block_size; return &s->vdev; } + +void virtio_blk_exit(VirtIODevice *vdev) +{ + VirtIOBlock *s = to_virtio_blk(vdev); + unregister_savevm(s->qdev, "virtio-blk", s); +} diff --git a/hw/virtio-net.c b/hw/virtio-net.c index 075f72df2d..7e1688cf69 100644 --- a/hw/virtio-net.c +++ b/hw/virtio-net.c @@ -36,7 +36,10 @@ typedef struct VirtIONet VirtQueue *ctrl_vq; NICState *nic; QEMUTimer *tx_timer; - int tx_timer_active; + QEMUBH *tx_bh; + uint32_t tx_timeout; + int32_t tx_burst; + int tx_waiting; uint32_t has_vnet_hdr; uint8_t has_ufo; struct { @@ -51,6 +54,7 @@ typedef struct VirtIONet uint8_t nouni; uint8_t nobcast; uint8_t vhost_started; + bool vm_running; VMChangeStateEntry *vmstate; struct { int in_use; @@ -95,6 +99,38 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config) } } +static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) +{ + VirtIONet *n = to_virtio_net(vdev); + if (!n->nic->nc.peer) { + return; + } + if (n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) { + return; + } + + if (!tap_get_vhost_net(n->nic->nc.peer)) { + return; + } + if (!!n->vhost_started == ((status & VIRTIO_CONFIG_S_DRIVER_OK) && + (n->status & VIRTIO_NET_S_LINK_UP) && + n->vm_running)) { + return; + } + if (!n->vhost_started) { + int r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer), &n->vdev); + if (r < 0) { + fprintf(stderr, "unable to start vhost net: %d: " + "falling back on userspace virtio\n", -r); + } else { + n->vhost_started = 1; + } + } else { + vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), &n->vdev); + n->vhost_started = 0; + } +} + static void virtio_net_set_link_status(VLANClientState *nc) { VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque; @@ -107,6 +143,8 @@ static void virtio_net_set_link_status(VLANClientState *nc) if (n->status != old_status) virtio_notify_config(&n->vdev); + + virtio_net_set_status(&n->vdev, n->vdev.status); } static void virtio_net_reset(VirtIODevice *vdev) @@ -120,10 +158,6 @@ static void virtio_net_reset(VirtIODevice *vdev) n->nomulti = 0; n->nouni = 0; n->nobcast = 0; - if (n->vhost_started) { - vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), vdev); - n->vhost_started = 0; - } /* Flush any MAC and VLAN filter table state */ n->mac_table.in_use = 0; @@ -619,7 +653,7 @@ static ssize_t virtio_net_receive(VLANClientState *nc, const uint8_t *buf, size_ return size; } -static void virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq); +static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq); static void virtio_net_tx_complete(VLANClientState *nc, ssize_t len) { @@ -635,16 +669,18 @@ static void virtio_net_tx_complete(VLANClientState *nc, ssize_t len) } /* TX */ -static void virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq) +static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq) { VirtQueueElement elem; + int32_t num_packets = 0; - if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)) - return; + if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)) { + return num_packets; + } if (n->async_tx.elem.out_num) { virtio_queue_set_notification(n->tx_vq, 0); - return; + return num_packets; } while (virtqueue_pop(vq, &elem)) { @@ -681,38 +717,55 @@ static void virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq) virtio_queue_set_notification(n->tx_vq, 0); n->async_tx.elem = elem; n->async_tx.len = len; - return; + return -EBUSY; } len += ret; virtqueue_push(vq, &elem, len); virtio_notify(&n->vdev, vq); + + if (++num_packets >= n->tx_burst) { + break; + } } + return num_packets; } -static void virtio_net_handle_tx(VirtIODevice *vdev, VirtQueue *vq) +static void virtio_net_handle_tx_timer(VirtIODevice *vdev, VirtQueue *vq) { VirtIONet *n = to_virtio_net(vdev); - if (n->tx_timer_active) { + if (n->tx_waiting) { virtio_queue_set_notification(vq, 1); qemu_del_timer(n->tx_timer); - n->tx_timer_active = 0; + n->tx_waiting = 0; virtio_net_flush_tx(n, vq); } else { qemu_mod_timer(n->tx_timer, - qemu_get_clock(vm_clock) + TX_TIMER_INTERVAL); - n->tx_timer_active = 1; + qemu_get_clock(vm_clock) + n->tx_timeout); + n->tx_waiting = 1; virtio_queue_set_notification(vq, 0); } } +static void virtio_net_handle_tx_bh(VirtIODevice *vdev, VirtQueue *vq) +{ + VirtIONet *n = to_virtio_net(vdev); + + if (unlikely(n->tx_waiting)) { + return; + } + virtio_queue_set_notification(vq, 0); + qemu_bh_schedule(n->tx_bh); + n->tx_waiting = 1; +} + static void virtio_net_tx_timer(void *opaque) { VirtIONet *n = opaque; - n->tx_timer_active = 0; + n->tx_waiting = 0; /* Just in case the driver is not ready on more */ if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)) @@ -722,20 +775,52 @@ static void virtio_net_tx_timer(void *opaque) virtio_net_flush_tx(n, n->tx_vq); } -static void virtio_net_save(QEMUFile *f, void *opaque) +static void virtio_net_tx_bh(void *opaque) { VirtIONet *n = opaque; + int32_t ret; - if (n->vhost_started) { - /* TODO: should we really stop the backend? - * If we don't, it might keep writing to memory. */ - vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), &n->vdev); - n->vhost_started = 0; + n->tx_waiting = 0; + + /* Just in case the driver is not ready on more */ + if (unlikely(!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))) + return; + + ret = virtio_net_flush_tx(n, n->tx_vq); + if (ret == -EBUSY) { + return; /* Notification re-enable handled by tx_complete */ } + + /* If we flush a full burst of packets, assume there are + * more coming and immediately reschedule */ + if (ret >= n->tx_burst) { + qemu_bh_schedule(n->tx_bh); + n->tx_waiting = 1; + return; + } + + /* If less than a full burst, re-enable notification and flush + * anything that may have come in while we weren't looking. If + * we find something, assume the guest is still active and reschedule */ + virtio_queue_set_notification(n->tx_vq, 1); + if (virtio_net_flush_tx(n, n->tx_vq) > 0) { + virtio_queue_set_notification(n->tx_vq, 0); + qemu_bh_schedule(n->tx_bh); + n->tx_waiting = 1; + } +} + +static void virtio_net_save(QEMUFile *f, void *opaque) +{ + VirtIONet *n = opaque; + + /* At this point, backend must be stopped, otherwise + * it might keep writing to memory. */ + assert(!n->vhost_started); virtio_save(&n->vdev, f); qemu_put_buffer(f, n->mac, ETH_ALEN); - qemu_put_be32(f, n->tx_timer_active); + qemu_put_be32(f, n->tx_waiting); qemu_put_be32(f, n->mergeable_rx_bufs); qemu_put_be16(f, n->status); qemu_put_byte(f, n->promisc); @@ -764,7 +849,7 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id) virtio_load(&n->vdev, f); qemu_get_buffer(f, n->mac, ETH_ALEN); - n->tx_timer_active = qemu_get_be32(f); + n->tx_waiting = qemu_get_be32(f); n->mergeable_rx_bufs = qemu_get_be32(f); if (version_id >= 3) @@ -840,9 +925,13 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id) } n->mac_table.first_multi = i; - if (n->tx_timer_active) { - qemu_mod_timer(n->tx_timer, - qemu_get_clock(vm_clock) + TX_TIMER_INTERVAL); + if (n->tx_waiting) { + if (n->tx_timer) { + qemu_mod_timer(n->tx_timer, + qemu_get_clock(vm_clock) + n->tx_timeout); + } else { + qemu_bh_schedule(n->tx_bh); + } } return 0; } @@ -863,47 +952,18 @@ static NetClientInfo net_virtio_info = { .link_status_changed = virtio_net_set_link_status, }; -static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) -{ - VirtIONet *n = to_virtio_net(vdev); - if (!n->nic->nc.peer) { - return; - } - if (n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) { - return; - } - - if (!tap_get_vhost_net(n->nic->nc.peer)) { - return; - } - if (!!n->vhost_started == !!(status & VIRTIO_CONFIG_S_DRIVER_OK)) { - return; - } - if (status & VIRTIO_CONFIG_S_DRIVER_OK) { - int r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer), vdev); - if (r < 0) { - fprintf(stderr, "unable to start vhost net: %d: " - "falling back on userspace virtio\n", -r); - } else { - n->vhost_started = 1; - } - } else { - vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), vdev); - n->vhost_started = 0; - } -} - static void virtio_net_vmstate_change(void *opaque, int running, int reason) { VirtIONet *n = opaque; - uint8_t status = running ? VIRTIO_CONFIG_S_DRIVER_OK : 0; + n->vm_running = running; /* This is called when vm is started/stopped, - * it will start/stop vhost backend if * appropriate + * it will start/stop vhost backend if appropriate * e.g. after migration. */ - virtio_net_set_status(&n->vdev, n->vdev.status & status); + virtio_net_set_status(&n->vdev, n->vdev.status); } -VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf) +VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf, + virtio_net_conf *net) { VirtIONet *n; @@ -919,7 +979,22 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf) n->vdev.reset = virtio_net_reset; n->vdev.set_status = virtio_net_set_status; n->rx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_rx); - n->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx); + + if (net->tx && strcmp(net->tx, "timer") && strcmp(net->tx, "bh")) { + fprintf(stderr, "virtio-net: " + "Unknown option tx=%s, valid options: \"timer\" \"bh\"\n", + net->tx); + fprintf(stderr, "Defaulting to \"bh\"\n"); + } + + if (net->tx && !strcmp(net->tx, "timer")) { + n->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx_timer); + n->tx_timer = qemu_new_timer(vm_clock, virtio_net_tx_timer, n); + n->tx_timeout = net->txtimer; + } else { + n->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx_bh); + n->tx_bh = qemu_bh_new(virtio_net_tx_bh, n); + } n->ctrl_vq = virtio_add_queue(&n->vdev, 64, virtio_net_handle_ctrl); qemu_macaddr_default_if_unset(&conf->macaddr); memcpy(&n->mac[0], &conf->macaddr, sizeof(n->mac)); @@ -929,8 +1004,8 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf) qemu_format_nic_info_str(&n->nic->nc, conf->macaddr.a); - n->tx_timer = qemu_new_timer(vm_clock, virtio_net_tx_timer, n); - n->tx_timer_active = 0; + n->tx_waiting = 0; + n->tx_burst = net->txburst; n->mergeable_rx_bufs = 0; n->promisc = 1; /* for compatibility */ @@ -951,9 +1026,8 @@ void virtio_net_exit(VirtIODevice *vdev) VirtIONet *n = DO_UPCAST(VirtIONet, vdev, vdev); qemu_del_vm_change_state_handler(n->vmstate); - if (n->vhost_started) { - vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), vdev); - } + /* This will stop vhost backend if appropriate. */ + virtio_net_set_status(vdev, 0); qemu_purge_queued_packets(&n->nic->nc); @@ -962,8 +1036,12 @@ void virtio_net_exit(VirtIODevice *vdev) qemu_free(n->mac_table.macs); qemu_free(n->vlans); - qemu_del_timer(n->tx_timer); - qemu_free_timer(n->tx_timer); + if (n->tx_timer) { + qemu_del_timer(n->tx_timer); + qemu_free_timer(n->tx_timer); + } else { + qemu_bh_delete(n->tx_bh); + } virtio_cleanup(&n->vdev); qemu_del_vlan_client(&n->nic->nc); diff --git a/hw/virtio-net.h b/hw/virtio-net.h index 235f1a9fa8..8af9a1ce55 100644 --- a/hw/virtio-net.h +++ b/hw/virtio-net.h @@ -49,6 +49,20 @@ #define TX_TIMER_INTERVAL 150000 /* 150 us */ +/* Limit the number of packets that can be sent via a single flush + * of the TX queue. This gives us a guaranteed exit condition and + * ensures fairness in the io path. 256 conveniently matches the + * length of the TX queue and shows a good balance of performance + * and latency. */ +#define TX_BURST 256 + +typedef struct virtio_net_conf +{ + uint32_t txtimer; + int32_t txburst; + char *tx; +} virtio_net_conf; + /* Maximum packet size we can receive from tap device: header + 64k */ #define VIRTIO_NET_MAX_BUFSIZE (sizeof(struct virtio_net_hdr) + (64 << 10)) diff --git a/hw/virtio-pci.c b/hw/virtio-pci.c index c728fffd73..729917d891 100644 --- a/hw/virtio-pci.c +++ b/hw/virtio-pci.c @@ -24,6 +24,7 @@ #include "net.h" #include "loader.h" #include "kvm.h" +#include "blockdev.h" /* from Linux's linux/virtio_pci.h */ @@ -106,6 +107,7 @@ typedef struct { #endif /* Max. number of ports we can have for a the virtio-serial device */ uint32_t max_virtserial_ports; + virtio_net_conf net; } VirtIOPCIProxy; /* virtio device */ @@ -449,6 +451,33 @@ static int virtio_pci_set_guest_notifier(void *opaque, int n, bool assign) return 0; } +static int virtio_pci_set_guest_notifiers(void *opaque, bool assign) +{ + VirtIOPCIProxy *proxy = opaque; + VirtIODevice *vdev = proxy->vdev; + int r, n; + + for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) { + if (!virtio_queue_get_num(vdev, n)) { + break; + } + + r = virtio_pci_set_guest_notifier(opaque, n, assign); + if (r < 0) { + goto assign_error; + } + } + + return 0; + +assign_error: + /* We get here on assignment failure. Recover by undoing for VQs 0 .. n. */ + while (--n >= 0) { + virtio_pci_set_guest_notifier(opaque, n, !assign); + } + return r; +} + static int virtio_pci_set_host_notifier(void *opaque, int n, bool assign) { VirtIOPCIProxy *proxy = opaque; @@ -486,7 +515,7 @@ static const VirtIOBindings virtio_pci_bindings = { .load_queue = virtio_pci_load_queue, .get_features = virtio_pci_get_features, .set_host_notifier = virtio_pci_set_host_notifier, - .set_guest_notifier = virtio_pci_set_guest_notifier, + .set_guest_notifiers = virtio_pci_set_guest_notifiers, }; static void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev, @@ -546,11 +575,10 @@ static int virtio_blk_init_pci(PCIDevice *pci_dev) proxy->class_code != PCI_CLASS_STORAGE_OTHER) proxy->class_code = PCI_CLASS_STORAGE_SCSI; - if (!proxy->block.bs) { - error_report("virtio-blk-pci: drive property not set"); + vdev = virtio_blk_init(&pci_dev->qdev, &proxy->block); + if (!vdev) { return -1; } - vdev = virtio_blk_init(&pci_dev->qdev, &proxy->block); vdev->nvectors = proxy->nvectors; virtio_init_pci(proxy, vdev, PCI_VENDOR_ID_REDHAT_QUMRANET, @@ -570,6 +598,7 @@ static int virtio_blk_exit_pci(PCIDevice *pci_dev) { VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev); + virtio_blk_exit(proxy->vdev); blockdev_mark_auto_del(proxy->block.bs); return virtio_exit_pci(pci_dev); } @@ -599,12 +628,20 @@ static int virtio_serial_init_pci(PCIDevice *pci_dev) return 0; } +static int virtio_serial_exit_pci(PCIDevice *pci_dev) +{ + VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev); + + virtio_serial_exit(proxy->vdev); + return virtio_exit_pci(pci_dev); +} + static int virtio_net_init_pci(PCIDevice *pci_dev) { VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev); VirtIODevice *vdev; - vdev = virtio_net_init(&pci_dev->qdev, &proxy->nic); + vdev = virtio_net_init(&pci_dev->qdev, &proxy->nic, &proxy->net); vdev->nvectors = proxy->nvectors; virtio_init_pci(proxy, vdev, @@ -681,6 +718,11 @@ static PCIDeviceInfo virtio_info[] = { DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3), DEFINE_VIRTIO_NET_FEATURES(VirtIOPCIProxy, host_features), DEFINE_NIC_PROPERTIES(VirtIOPCIProxy, nic), + DEFINE_PROP_UINT32("x-txtimer", VirtIOPCIProxy, + net.txtimer, TX_TIMER_INTERVAL), + DEFINE_PROP_INT32("x-txburst", VirtIOPCIProxy, + net.txburst, TX_BURST), + DEFINE_PROP_STRING("tx", VirtIOPCIProxy, net.tx), DEFINE_PROP_END_OF_LIST(), }, .qdev.reset = virtio_pci_reset, @@ -689,7 +731,7 @@ static PCIDeviceInfo virtio_info[] = { .qdev.alias = "virtio-serial", .qdev.size = sizeof(VirtIOPCIProxy), .init = virtio_serial_init_pci, - .exit = virtio_exit_pci, + .exit = virtio_serial_exit_pci, .qdev.props = (Property[]) { DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, DEV_NVECTORS_UNSPECIFIED), diff --git a/hw/virtio-serial-bus.c b/hw/virtio-serial-bus.c index 26d5841154..74ba5ec3d3 100644 --- a/hw/virtio-serial-bus.c +++ b/hw/virtio-serial-bus.c @@ -41,6 +41,8 @@ struct VirtIOSerial { VirtIOSerialBus *bus; + DeviceState *qdev; + QTAILQ_HEAD(, VirtIOSerialPort) ports; /* bitmap for identifying active ports */ @@ -117,6 +119,7 @@ static void do_flush_queued_data(VirtIOSerialPort *port, VirtQueue *vq, VirtQueueElement elem; assert(port || discard); + assert(virtio_queue_ready(vq)); while ((discard || !port->throttled) && virtqueue_pop(vq, &elem)) { uint8_t *buf; @@ -139,6 +142,9 @@ static void flush_queued_data(VirtIOSerialPort *port, bool discard) { assert(port); + if (!virtio_queue_ready(port->ovq)) { + return; + } do_flush_queued_data(port, port->ovq, &port->vser->vdev, discard); } @@ -730,11 +736,19 @@ VirtIODevice *virtio_serial_init(DeviceState *dev, uint32_t max_nr_ports) { VirtIOSerial *vser; VirtIODevice *vdev; - uint32_t i; + uint32_t i, max_supported_ports; if (!max_nr_ports) return NULL; + /* Each port takes 2 queues, and one pair is for the control queue */ + max_supported_ports = VIRTIO_PCI_QUEUE_MAX / 2 - 1; + + if (max_nr_ports > max_supported_ports) { + error_report("maximum ports supported: %u", max_supported_ports); + return NULL; + } + vdev = virtio_common_init("virtio-serial", VIRTIO_ID_CONSOLE, sizeof(struct virtio_console_config), sizeof(VirtIOSerial)); @@ -780,6 +794,8 @@ VirtIODevice *virtio_serial_init(DeviceState *dev, uint32_t max_nr_ports) vser->vdev.get_config = get_config; vser->vdev.set_config = set_config; + vser->qdev = dev; + /* * Register for the savevm section with the virtio-console name * to preserve backward compat @@ -789,3 +805,16 @@ VirtIODevice *virtio_serial_init(DeviceState *dev, uint32_t max_nr_ports) return vdev; } + +void virtio_serial_exit(VirtIODevice *vdev) +{ + VirtIOSerial *vser = DO_UPCAST(VirtIOSerial, vdev, vdev); + + unregister_savevm(vser->qdev, "virtio-console", vser); + + qemu_free(vser->ivqs); + qemu_free(vser->ovqs); + qemu_free(vser->ports_map); + + virtio_cleanup(vdev); +} diff --git a/hw/virtio.c b/hw/virtio.c index 4475bb3e44..a2a657e132 100644 --- a/hw/virtio.c +++ b/hw/virtio.c @@ -13,6 +13,7 @@ #include <inttypes.h> +#include "trace.h" #include "virtio.h" #include "sysemu.h" @@ -205,6 +206,8 @@ void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem, unsigned int offset; int i; + trace_virtqueue_fill(vq, elem, len, idx); + offset = 0; for (i = 0; i < elem->in_num; i++) { size_t size = MIN(len - offset, elem->in_sg[i].iov_len); @@ -232,6 +235,7 @@ void virtqueue_flush(VirtQueue *vq, unsigned int count) { /* Make sure buffer is written before we update index. */ wmb(); + trace_virtqueue_flush(vq, count); vring_used_idx_increment(vq, count); vq->inuse -= count; } @@ -360,11 +364,26 @@ int virtqueue_avail_bytes(VirtQueue *vq, int in_bytes, int out_bytes) return 0; } +void virtqueue_map_sg(struct iovec *sg, target_phys_addr_t *addr, + size_t num_sg, int is_write) +{ + unsigned int i; + target_phys_addr_t len; + + for (i = 0; i < num_sg; i++) { + len = sg[i].iov_len; + sg[i].iov_base = cpu_physical_memory_map(addr[i], &len, is_write); + if (sg[i].iov_base == NULL || len != sg[i].iov_len) { + fprintf(stderr, "virtio: trying to map MMIO memory\n"); + exit(1); + } + } +} + int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem) { unsigned int i, head, max; target_phys_addr_t desc_pa = vq->vring.desc; - target_phys_addr_t len; if (!virtqueue_num_heads(vq, vq->last_avail_idx)) return 0; @@ -388,28 +407,19 @@ int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem) i = 0; } + /* Collect all the descriptors */ do { struct iovec *sg; - int is_write = 0; if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_WRITE) { elem->in_addr[elem->in_num] = vring_desc_addr(desc_pa, i); sg = &elem->in_sg[elem->in_num++]; - is_write = 1; - } else + } else { + elem->out_addr[elem->out_num] = vring_desc_addr(desc_pa, i); sg = &elem->out_sg[elem->out_num++]; + } - /* Grab the first descriptor, and check it's OK. */ sg->iov_len = vring_desc_len(desc_pa, i); - len = sg->iov_len; - - sg->iov_base = cpu_physical_memory_map(vring_desc_addr(desc_pa, i), - &len, is_write); - - if (sg->iov_base == NULL || len != sg->iov_len) { - fprintf(stderr, "virtio: trying to map MMIO memory\n"); - exit(1); - } /* If we've got too many, that implies a descriptor loop. */ if ((elem->in_num + elem->out_num) > max) { @@ -418,10 +428,15 @@ int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem) } } while ((i = virtqueue_next_desc(desc_pa, i, max)) != max); + /* Now map what we have collected */ + virtqueue_map_sg(elem->in_sg, elem->in_addr, elem->in_num, 1); + virtqueue_map_sg(elem->out_sg, elem->out_addr, elem->out_num, 0); + elem->index = head; vq->inuse++; + trace_virtqueue_pop(vq, elem, elem->in_num, elem->out_num); return elem->in_num + elem->out_num; } @@ -443,6 +458,8 @@ void virtio_reset(void *opaque) VirtIODevice *vdev = opaque; int i; + virtio_set_status(vdev, 0); + if (vdev->reset) vdev->reset(vdev); @@ -560,6 +577,7 @@ int virtio_queue_get_num(VirtIODevice *vdev, int n) void virtio_queue_notify(VirtIODevice *vdev, int n) { if (n < VIRTIO_PCI_QUEUE_MAX && vdev->vq[n].vring.desc) { + trace_virtio_queue_notify(vdev, n, &vdev->vq[n]); vdev->vq[n].handle_output(vdev, &vdev->vq[n]); } } @@ -597,6 +615,7 @@ VirtQueue *virtio_add_queue(VirtIODevice *vdev, int queue_size, void virtio_irq(VirtQueue *vq) { + trace_virtio_irq(vq); vq->vdev->isr |= 0x01; virtio_notify_vector(vq->vdev, vq->vector); } @@ -609,6 +628,7 @@ void virtio_notify(VirtIODevice *vdev, VirtQueue *vq) (vq->inuse || vring_avail_idx(vq) != vq->last_avail_idx))) return; + trace_virtio_notify(vdev, vq); vdev->isr |= 0x01; virtio_notify_vector(vdev, vq->vector); } @@ -661,6 +681,7 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f) uint32_t features; uint32_t supported_features = vdev->binding->get_features(vdev->binding_opaque); + uint16_t num_heads; if (vdev->binding->load_config) { ret = vdev->binding->load_config(vdev->binding_opaque, f); @@ -693,6 +714,16 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f) if (vdev->vq[i].pa) { virtqueue_init(&vdev->vq[i]); } + num_heads = vring_avail_idx(&vdev->vq[i]) - vdev->vq[i].last_avail_idx; + /* Check it isn't doing very strange things with descriptor numbers. */ + if (num_heads > vdev->vq[i].vring.num) { + fprintf(stderr, "VQ %d size 0x%x Guest index 0x%x " + "inconsistent with Host index 0x%x: delta 0x%x\n", + i, vdev->vq[i].vring.num, + vring_avail_idx(&vdev->vq[i]), + vdev->vq[i].last_avail_idx, num_heads); + return -1; + } if (vdev->binding->load_queue) { ret = vdev->binding->load_queue(vdev->binding_opaque, i, f); if (ret) diff --git a/hw/virtio.h b/hw/virtio.h index e4306cd750..02fa312d3e 100644 --- a/hw/virtio.h +++ b/hw/virtio.h @@ -81,6 +81,7 @@ typedef struct VirtQueueElement unsigned int out_num; unsigned int in_num; target_phys_addr_t in_addr[VIRTQUEUE_MAX_SIZE]; + target_phys_addr_t out_addr[VIRTQUEUE_MAX_SIZE]; struct iovec in_sg[VIRTQUEUE_MAX_SIZE]; struct iovec out_sg[VIRTQUEUE_MAX_SIZE]; } VirtQueueElement; @@ -92,7 +93,7 @@ typedef struct { int (*load_config)(void * opaque, QEMUFile *f); int (*load_queue)(void * opaque, int n, QEMUFile *f); unsigned (*get_features)(void * opaque); - int (*set_guest_notifier)(void * opaque, int n, bool assigned); + int (*set_guest_notifiers)(void * opaque, bool assigned); int (*set_host_notifier)(void * opaque, int n, bool assigned); } VirtIOBindings; @@ -142,6 +143,8 @@ void virtqueue_flush(VirtQueue *vq, unsigned int count); void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem, unsigned int len, unsigned int idx); +void virtqueue_map_sg(struct iovec *sg, target_phys_addr_t *addr, + size_t num_sg, int is_write); int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem); int virtqueue_avail_bytes(VirtQueue *vq, int in_bytes, int out_bytes); @@ -185,7 +188,9 @@ void virtio_bind_device(VirtIODevice *vdev, const VirtIOBindings *binding, /* Base devices. */ VirtIODevice *virtio_blk_init(DeviceState *dev, BlockConf *conf); -VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf); +struct virtio_net_conf; +VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf, + struct virtio_net_conf *net); VirtIODevice *virtio_serial_init(DeviceState *dev, uint32_t max_nr_ports); VirtIODevice *virtio_balloon_init(DeviceState *dev); #ifdef CONFIG_LINUX @@ -194,6 +199,8 @@ VirtIODevice *virtio_9p_init(DeviceState *dev, V9fsConf *conf); void virtio_net_exit(VirtIODevice *vdev); +void virtio_blk_exit(VirtIODevice *vdev); +void virtio_serial_exit(VirtIODevice *vdev); #define DEFINE_VIRTIO_COMMON_FEATURES(_state, _field) \ DEFINE_PROP_BIT("indirect_desc", _state, _field, \ diff --git a/hw/vmmouse.c b/hw/vmmouse.c index f3593047e7..209711942f 100644 --- a/hw/vmmouse.c +++ b/hw/vmmouse.c @@ -100,16 +100,29 @@ static void vmmouse_mouse_event(void *opaque, int x, int y, int dz, int buttons_ i8042_isa_mouse_fake_event(s->ps2_mouse); } -static void vmmouse_update_handler(VMMouseState *s) +static void vmmouse_remove_handler(VMMouseState *s) { if (s->entry) { qemu_remove_mouse_event_handler(s->entry); s->entry = NULL; } - if (s->status == 0) +} + +static void vmmouse_update_handler(VMMouseState *s, int absolute) +{ + if (s->status != 0) { + return; + } + if (s->absolute != absolute) { + s->absolute = absolute; + vmmouse_remove_handler(s); + } + if (s->entry == NULL) { s->entry = qemu_add_mouse_event_handler(vmmouse_mouse_event, s, s->absolute, "vmmouse"); + qemu_activate_mouse_event_handler(s->entry); + } } static void vmmouse_read_id(VMMouseState *s) @@ -121,28 +134,25 @@ static void vmmouse_read_id(VMMouseState *s) s->queue[s->nb_queue++] = VMMOUSE_VERSION; s->status = 0; - vmmouse_update_handler(s); } static void vmmouse_request_relative(VMMouseState *s) { DPRINTF("vmmouse_request_relative()\n"); - s->absolute = 0; - vmmouse_update_handler(s); + vmmouse_update_handler(s, 0); } static void vmmouse_request_absolute(VMMouseState *s) { DPRINTF("vmmouse_request_absolute()\n"); - s->absolute = 1; - vmmouse_update_handler(s); + vmmouse_update_handler(s, 1); } static void vmmouse_disable(VMMouseState *s) { DPRINTF("vmmouse_disable()\n"); s->status = 0xffff; - vmmouse_update_handler(s); + vmmouse_remove_handler(s); } static void vmmouse_data(VMMouseState *s, uint32_t *data, uint32_t size) @@ -154,7 +164,7 @@ static void vmmouse_data(VMMouseState *s, uint32_t *data, uint32_t size) if (size == 0 || size > 6 || size > s->nb_queue) { printf("vmmouse: driver requested too much data %d\n", size); s->status = 0xffff; - vmmouse_update_handler(s); + vmmouse_remove_handler(s); return; } @@ -239,7 +249,8 @@ static int vmmouse_post_load(void *opaque, int version_id) { VMMouseState *s = opaque; - vmmouse_update_handler(s); + vmmouse_remove_handler(s); + vmmouse_update_handler(s, s->absolute); return 0; } diff --git a/hw/vmware_vga.c b/hw/vmware_vga.c index 12bff480eb..3d25c14da9 100644 --- a/hw/vmware_vga.c +++ b/hw/vmware_vga.c @@ -519,11 +519,15 @@ static inline void vmsvga_cursor_define(struct vmsvga_state_s *s, #define CMD(f) le32_to_cpu(s->cmd->f) -static inline int vmsvga_fifo_empty(struct vmsvga_state_s *s) +static inline int vmsvga_fifo_length(struct vmsvga_state_s *s) { + int num; if (!s->config || !s->enable) - return 1; - return (s->cmd->next_cmd == s->cmd->stop); + return 0; + num = CMD(next_cmd) - CMD(stop); + if (num < 0) + num += CMD(max) - CMD(min); + return num >> 2; } static inline uint32_t vmsvga_fifo_read_raw(struct vmsvga_state_s *s) @@ -543,13 +547,23 @@ static inline uint32_t vmsvga_fifo_read(struct vmsvga_state_s *s) static void vmsvga_fifo_run(struct vmsvga_state_s *s) { uint32_t cmd, colour; - int args = 0; + int args, len; int x, y, dx, dy, width, height; struct vmsvga_cursor_definition_s cursor; - while (!vmsvga_fifo_empty(s)) + uint32_t cmd_start; + + len = vmsvga_fifo_length(s); + while (len > 0) { + /* May need to go back to the start of the command if incomplete */ + cmd_start = s->cmd->stop; + switch (cmd = vmsvga_fifo_read(s)) { case SVGA_CMD_UPDATE: case SVGA_CMD_UPDATE_VERBOSE: + len -= 5; + if (len < 0) + goto rewind; + x = vmsvga_fifo_read(s); y = vmsvga_fifo_read(s); width = vmsvga_fifo_read(s); @@ -558,6 +572,10 @@ static void vmsvga_fifo_run(struct vmsvga_state_s *s) break; case SVGA_CMD_RECT_FILL: + len -= 6; + if (len < 0) + goto rewind; + colour = vmsvga_fifo_read(s); x = vmsvga_fifo_read(s); y = vmsvga_fifo_read(s); @@ -567,10 +585,15 @@ static void vmsvga_fifo_run(struct vmsvga_state_s *s) vmsvga_fill_rect(s, colour, x, y, width, height); break; #else + args = 0; goto badcmd; #endif case SVGA_CMD_RECT_COPY: + len -= 7; + if (len < 0) + goto rewind; + x = vmsvga_fifo_read(s); y = vmsvga_fifo_read(s); dx = vmsvga_fifo_read(s); @@ -581,10 +604,15 @@ static void vmsvga_fifo_run(struct vmsvga_state_s *s) vmsvga_copy_rect(s, x, y, dx, dy, width, height); break; #else + args = 0; goto badcmd; #endif case SVGA_CMD_DEFINE_CURSOR: + len -= 8; + if (len < 0) + goto rewind; + cursor.id = vmsvga_fifo_read(s); cursor.hot_x = vmsvga_fifo_read(s); cursor.hot_y = vmsvga_fifo_read(s); @@ -593,11 +621,14 @@ static void vmsvga_fifo_run(struct vmsvga_state_s *s) vmsvga_fifo_read(s); cursor.bpp = vmsvga_fifo_read(s); - if (SVGA_BITMAP_SIZE(x, y) > sizeof cursor.mask || - SVGA_PIXMAP_SIZE(x, y, cursor.bpp) > sizeof cursor.image) { - args = SVGA_BITMAP_SIZE(x, y) + SVGA_PIXMAP_SIZE(x, y, cursor.bpp); - goto badcmd; - } + args = SVGA_BITMAP_SIZE(x, y) + SVGA_PIXMAP_SIZE(x, y, cursor.bpp); + if (SVGA_BITMAP_SIZE(x, y) > sizeof cursor.mask || + SVGA_PIXMAP_SIZE(x, y, cursor.bpp) > sizeof cursor.image) + goto badcmd; + + len -= args; + if (len < 0) + goto rewind; for (args = 0; args < SVGA_BITMAP_SIZE(x, y); args ++) cursor.mask[args] = vmsvga_fifo_read_raw(s); @@ -616,6 +647,10 @@ static void vmsvga_fifo_run(struct vmsvga_state_s *s) * for so we can avoid FIFO desync if driver uses them illegally. */ case SVGA_CMD_DEFINE_ALPHA_CURSOR: + len -= 6; + if (len < 0) + goto rewind; + vmsvga_fifo_read(s); vmsvga_fifo_read(s); vmsvga_fifo_read(s); @@ -630,6 +665,10 @@ static void vmsvga_fifo_run(struct vmsvga_state_s *s) args = 7; goto badcmd; case SVGA_CMD_DRAW_GLYPH_CLIPPED: + len -= 4; + if (len < 0) + goto rewind; + vmsvga_fifo_read(s); vmsvga_fifo_read(s); args = 7 + (vmsvga_fifo_read(s) >> 2); @@ -650,13 +689,22 @@ static void vmsvga_fifo_run(struct vmsvga_state_s *s) break; /* Nop */ default: + args = 0; badcmd: + len -= args; + if (len < 0) + goto rewind; while (args --) vmsvga_fifo_read(s); printf("%s: Unknown command 0x%02x in SVGA command FIFO\n", __FUNCTION__, cmd); break; + + rewind: + s->cmd->stop = cmd_start; + break; } + } s->syncing = 0; } @@ -809,11 +857,11 @@ static void vmsvga_value_write(void *opaque, uint32_t address, uint32_t value) s->invalidated = 1; s->vga.invalidate(&s->vga); if (s->enable) { - s->fb_size = ((s->depth + 7) >> 3) * s->new_width * s->new_height; - vga_dirty_log_stop(&s->vga); - } else { - vga_dirty_log_start(&s->vga); - } + s->fb_size = ((s->depth + 7) >> 3) * s->new_width * s->new_height; + vga_dirty_log_stop(&s->vga); + } else { + vga_dirty_log_start(&s->vga); + } break; case SVGA_REG_WIDTH: @@ -1255,7 +1303,7 @@ static int pci_vmsvga_initfn(PCIDevice *dev) PCI_BASE_ADDRESS_MEM_PREFETCH, pci_vmsvga_map_mem); pci_register_bar(&s->card, 2, SVGA_FIFO_SIZE, - PCI_BASE_ADDRESS_MEM_PREFETCH, pci_vmsvga_map_fifo); + PCI_BASE_ADDRESS_MEM_PREFETCH, pci_vmsvga_map_fifo); vmsvga_init(&s->chip, VGA_RAM_SIZE); diff --git a/hw/vt82c686.c b/hw/vt82c686.c index a0c5747b59..cacc21767b 100644 --- a/hw/vt82c686.c +++ b/hw/vt82c686.c @@ -468,7 +468,6 @@ static int vt82c686b_pm_initfn(PCIDevice *dev) pci_config_set_device_id(pci_conf, PCI_DEVICE_ID_VIA_ACPI); pci_config_set_class(pci_conf, PCI_CLASS_BRIDGE_OTHER); pci_config_set_revision(pci_conf, 0x40); - pci_conf[PCI_HEADER_TYPE] = PCI_HEADER_TYPE_NORMAL; // header_type pci_set_word(pci_conf + PCI_COMMAND, 0); pci_set_word(pci_conf + PCI_STATUS, PCI_STATUS_FAST_BACK | @@ -556,8 +555,6 @@ static int vt82c686b_initfn(PCIDevice *d) pci_config_set_class(pci_conf, PCI_CLASS_BRIDGE_ISA); pci_config_set_prog_interface(pci_conf, 0x0); pci_config_set_revision(pci_conf,0x40); /* Revision 4.0 */ - pci_conf[PCI_HEADER_TYPE] = - PCI_HEADER_TYPE_NORMAL | PCI_HEADER_TYPE_MULTI_FUNCTION; wmask = d->wmask; for (i = 0x00; i < 0xff; i++) { @@ -575,7 +572,7 @@ int vt82c686b_init(PCIBus *bus, int devfn) { PCIDevice *d; - d = pci_create_simple(bus, devfn, "VT82C686B"); + d = pci_create_simple_multifunction(bus, devfn, true, "VT82C686B"); return d->devfn; } diff --git a/hw/watchdog.c b/hw/watchdog.c index aebb08a0ee..e9dd56e229 100644 --- a/hw/watchdog.c +++ b/hw/watchdog.c @@ -66,7 +66,7 @@ int select_watchdog(const char *p) QLIST_FOREACH(model, &watchdog_list, entry) { if (strcasecmp(model->wdt_name, p) == 0) { /* add the device */ - opts = qemu_opts_create(&qemu_device_opts, NULL, 0); + opts = qemu_opts_create(qemu_find_opts("device"), NULL, 0); qemu_opt_set(opts, "driver", p); return 0; } diff --git a/hw/wm8750.c b/hw/wm8750.c index ce43c234ac..c9c674451b 100644 --- a/hw/wm8750.c +++ b/hw/wm8750.c @@ -171,7 +171,6 @@ static void wm8750_set_format(WM8750State *s) int i; struct audsettings in_fmt; struct audsettings out_fmt; - struct audsettings monoout_fmt; wm8750_out_flush(s); @@ -212,10 +211,6 @@ static void wm8750_set_format(WM8750State *s) out_fmt.nchannels = 2; out_fmt.freq = s->dac_hz; out_fmt.fmt = AUD_FMT_S16; - monoout_fmt.endianness = 0; - monoout_fmt.nchannels = 1; - monoout_fmt.freq = s->rate->dac_hz; - monoout_fmt.fmt = AUD_FMT_S16; s->dac_voice[0] = AUD_open_out(&s->card, s->dac_voice[0], CODEC ".speaker", s, wm8750_audio_out_cb, &out_fmt); diff --git a/hw/xen_backend.h b/hw/xen_backend.h index cc25f9d7db..1b428e3bf4 100644 --- a/hw/xen_backend.h +++ b/hw/xen_backend.h @@ -4,8 +4,6 @@ #include "xen_common.h" #include "sysemu.h" #include "net.h" -#include "block_int.h" -#include "blockdev.h" /* ------------------------------------------------------------- */ @@ -86,7 +84,7 @@ int xen_be_bind_evtchn(struct XenDevice *xendev); void xen_be_unbind_evtchn(struct XenDevice *xendev); int xen_be_send_notify(struct XenDevice *xendev); void xen_be_printf(struct XenDevice *xendev, int msg_level, const char *fmt, ...) - __attribute__ ((format(printf, 3, 4))); + GCC_FMT_ATTR(3, 4); /* actual backend drivers */ extern struct XenDevOps xen_console_ops; /* xen_console.c */ diff --git a/hw/xen_devconfig.c b/hw/xen_devconfig.c index ea8f8c4c2d..8d50216c04 100644 --- a/hw/xen_devconfig.c +++ b/hw/xen_devconfig.c @@ -1,4 +1,6 @@ #include "xen_backend.h" +#include "blockdev.h" +#include "block_int.h" /* XXX */ /* ------------------------------------------------------------- */ diff --git a/hw/xen_disk.c b/hw/xen_disk.c index 9a466f3cc1..134ac3388e 100644 --- a/hw/xen_disk.c +++ b/hw/xen_disk.c @@ -41,6 +41,7 @@ #include "qemu-char.h" #include "xen_blkif.h" #include "xen_backend.h" +#include "blockdev.h" /* ------------------------------------------------------------- */ diff --git a/hw/xen_machine_pv.c b/hw/xen_machine_pv.c index 586214d8ba..77a34bf111 100644 --- a/hw/xen_machine_pv.c +++ b/hw/xen_machine_pv.c @@ -28,6 +28,7 @@ #include "boards.h" #include "xen_backend.h" #include "xen_domainbuild.h" +#include "blockdev.h" static void xen_init_pv(ram_addr_t ram_size, const char *boot_device, |