Enable a guest to access a device's memory mapped I/O regions directly. When the guest changes the I/O memory mappings for a passthrough device, send the updated mmio region to the kernel.
Signed-off-by: Ben-Ami Yassour <[EMAIL PROTECTED]> Signed-off-by: Muli Ben-Yehuda <[EMAIL PROTECTED]> --- libkvm/libkvm.c | 24 ++++++++---- qemu/hw/pci-passthrough.c | 88 +++++++++++--------------------------------- qemu/hw/pci-passthrough.h | 2 + 3 files changed, 40 insertions(+), 74 deletions(-) diff --git a/libkvm/libkvm.c b/libkvm/libkvm.c index a49cbdc..35bc411 100644 --- a/libkvm/libkvm.c +++ b/libkvm/libkvm.c @@ -400,7 +400,7 @@ void *kvm_create_userspace_phys_mem(kvm_context_t kvm, unsigned long phys_start, { int r; int prot = PROT_READ; - void *ptr; + void *ptr = NULL; struct kvm_userspace_memory_region memory = { .memory_size = len, .guest_phys_addr = phys_start, @@ -410,16 +410,24 @@ void *kvm_create_userspace_phys_mem(kvm_context_t kvm, unsigned long phys_start, if (writable) prot |= PROT_WRITE; - ptr = mmap(NULL, len, prot, MAP_ANONYMOUS | MAP_SHARED, -1, 0); - if (ptr == MAP_FAILED) { - fprintf(stderr, "create_userspace_phys_mem: %s", strerror(errno)); - return 0; - } + if (len > 0) { + ptr = mmap(NULL, len, prot, MAP_ANONYMOUS | MAP_SHARED, -1, 0); + if (ptr == MAP_FAILED) { + fprintf(stderr, "create_userspace_phys_mem: %s", + strerror(errno)); + return 0; + } - memset(ptr, 0, len); + memset(ptr, 0, len); + } memory.userspace_addr = (unsigned long)ptr; - memory.slot = get_free_slot(kvm); + + if (len > 0) + memory.slot = get_free_slot(kvm); + else + memory.slot = get_slot(phys_start); + r = ioctl(kvm->vm_fd, KVM_SET_USER_MEMORY_REGION, &memory); if (r == -1) { fprintf(stderr, "create_userspace_phys_mem: %s", strerror(errno)); diff --git a/qemu/hw/pci-passthrough.c b/qemu/hw/pci-passthrough.c index 250d7ef..08e339d 100644 --- a/qemu/hw/pci-passthrough.c +++ b/qemu/hw/pci-passthrough.c @@ -51,59 +51,6 @@ extern FILE *logfile; #define DEBUG(fmt, args...) #endif -#define pt_mmio_write(suffix, type) \ -static void pt_mmio_write##suffix(void *opaque, target_phys_addr_t e_phys, \ - uint32_t value) \ -{ \ - pt_region_t *r_access = (pt_region_t *)opaque; \ - void *r_virt = (uint8_t *)r_access->r_virtbase + \ - (e_phys - r_access->e_physbase); \ - if (r_access->debug & PT_DEBUG_MMIO) { \ - fprintf(logfile, "pt_mmio_write" #suffix \ - ": e_physbase=%p e_phys=%p r_virt=%p value=%08x\n", \ - (void *)r_access->e_physbase, (void *)e_phys, \ - r_virt, value); \ - } \ - *(type *)r_virt = (type)value; \ -} - -pt_mmio_write(b, uint8_t) -pt_mmio_write(w, uint16_t) -pt_mmio_write(l, uint32_t) - -#define pt_mmio_read(suffix, type) \ -static uint32_t pt_mmio_read##suffix(void *opaque, target_phys_addr_t e_phys) \ -{ \ - pt_region_t *r_access = (pt_region_t *)opaque; \ - void *r_virt = (uint8_t *)r_access->r_virtbase + \ - (e_phys - r_access->e_physbase); \ - uint32_t value = (uint32_t) (*(type *) r_virt); \ - if (r_access->debug & PT_DEBUG_MMIO) { \ - fprintf(logfile, \ - "pt_mmio_read" #suffix ": e_physbase=%p " \ - "e_phys=%p r_virt=%p value=%08x\n", \ - (void *)r_access->e_physbase, \ - (void *)e_phys, r_virt, value); \ - } \ - return value; \ -} - -pt_mmio_read(b, uint8_t) -pt_mmio_read(w, uint16_t) -pt_mmio_read(l, uint32_t) - -CPUReadMemoryFunc *pt_mmio_read_cb[3] = { - pt_mmio_readb, - pt_mmio_readw, - pt_mmio_readl -}; - -CPUWriteMemoryFunc *pt_mmio_write_cb[3] = { - pt_mmio_writeb, - pt_mmio_writew, - pt_mmio_writel -}; - #define pt_ioport_write(suffix) \ static void pt_ioport_write##suffix(void *opaque, uint32_t addr, uint32_t value) \ { \ @@ -145,20 +92,32 @@ pt_ioport_read(b) pt_ioport_read(w) pt_ioport_read(l) -static void pt_iomem_map(PCIDevice *d, int region_num, - uint32_t e_phys, uint32_t e_size, int type) +void pt_iomem_map(PCIDevice * pci_dev, int region_num, uint32_t e_phys, + uint32_t e_size, int type) { - pt_dev_t *r_dev = (pt_dev_t *) d; - - r_dev->v_addrs[region_num].e_physbase = e_phys; + pt_dev_t *r_dev = (pt_dev_t *) pci_dev; + pt_region_t *region = &r_dev->v_addrs[region_num]; + int first_map = (region->e_size == 0); + int ret = 0; DEBUG("e_phys=%08x r_virt=%p type=%d len=%08x region_num=%d \n", e_phys, r_dev->v_addrs[region_num].r_virtbase, type, e_size, region_num); - cpu_register_physical_memory(e_phys, - r_dev->dev.io_regions[region_num].size, - r_dev->v_addrs[region_num].memory_index); + region->e_physbase = e_phys; + region->e_size = e_size; + + if (!first_map) + kvm_destroy_phys_mem(kvm_context, e_phys, e_size); + + if (e_size > 0) + ret = kvm_register_userspace_phys_mem(kvm_context, + e_phys, + region->r_virtbase, + e_size, + 0); + if (ret != 0) + fprintf(logfile, "Error: create new mapping failed\n"); } static void pt_ioport_map(PCIDevice *pci_dev, int region_num, @@ -295,6 +254,8 @@ static int pt_register_regions(pci_region_t *io_regions, (uint32_t) (cur_region->base_addr)); return -1; } + pci_dev->v_addrs[i].r_size = cur_region->size; + pci_dev->v_addrs[i].e_size = 0; /* add offset */ pci_dev->v_addrs[i].r_virtbase += @@ -304,11 +265,6 @@ static int pt_register_regions(pci_region_t *io_regions, cur_region->size, t, pt_iomem_map); - pci_dev->v_addrs[i].memory_index = - cpu_register_io_memory(0, pt_mmio_read_cb, - pt_mmio_write_cb, - (void *) &(pci_dev->v_addrs[i])); - continue; } /* handle port io regions */ diff --git a/qemu/hw/pci-passthrough.h b/qemu/hw/pci-passthrough.h index 60df017..7a98b0e 100644 --- a/qemu/hw/pci-passthrough.h +++ b/qemu/hw/pci-passthrough.h @@ -65,6 +65,8 @@ typedef struct pt_region_s { uint32_t memory_index; void *r_virtbase; /* mmapped access address */ int num; /* our index within v_addrs[] */ + uint32_t e_size; /* emulated size of region in bytes */ + uint32_t r_size; /* real size of region in bytes */ uint32_t debug; } pt_region_t; -- 1.5.6 -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html