Message ID | 1452205147-6320-1-git-send-email-boris.ostrovsky@oracle.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
On 07/01/16 23:19, Boris Ostrovsky wrote: > With commit 8c45adec18e0 ("libxc: create unmapped initrd in domain > builder if supported") location of ramdisk may not be available to > HVMlite guests by the time alloc_magic_pages_hvm() is invoked if the > guest supports unmapped initrd. > > So let's move ramdisk info initialization (along with a few other > operations that are not directly related to allocating magic/special > pages) from alloc_magic_pages_hvm() to bootlate_hvm(). > > Since we now split allocation and mapping of the start_info segment > let's stash it, along with cmdline length, in xc_dom_image so that we > can check whether we are mapping correctly-sized range. > > We can also stop using xc_dom_image.start_info_pfn and leave it for > PV(H) guests only. > > Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> > --- > v4: > * See the last two paragraphs from commit message above > > v4.1: > * Inverted testing of start_info_size in bootlate_hvm(). > > v4.2 > * <facepalm> Actually do what I said I'd do in 4.1 > > tools/libxc/include/xc_dom.h | 2 + > tools/libxc/xc_dom_x86.c | 140 +++++++++++++++++++++++------------------ > 2 files changed, 80 insertions(+), 62 deletions(-) > > diff --git a/tools/libxc/include/xc_dom.h b/tools/libxc/include/xc_dom.h > index 2460818..cac4698 100644 > --- a/tools/libxc/include/xc_dom.h > +++ b/tools/libxc/include/xc_dom.h > @@ -71,6 +71,7 @@ struct xc_dom_image { > > /* arguments and parameters */ > char *cmdline; > + size_t cmdline_size; > uint32_t f_requested[XENFEAT_NR_SUBMAPS]; > > /* info from (elf) kernel image */ > @@ -91,6 +92,7 @@ struct xc_dom_image { > struct xc_dom_seg p2m_seg; > struct xc_dom_seg pgtables_seg; > struct xc_dom_seg devicetree_seg; > + struct xc_dom_seg start_info_seg; /* HVMlite only */ Instead of adding HVM specific members here, you could make use of dom.arch_private and use just a local structure defined in xc_dom_x86.c. Juergen > xen_pfn_t start_info_pfn; > xen_pfn_t console_pfn; > xen_pfn_t xenstore_pfn; > diff --git a/tools/libxc/xc_dom_x86.c b/tools/libxc/xc_dom_x86.c > index b8d2904..edf2db1 100644 > --- a/tools/libxc/xc_dom_x86.c > +++ b/tools/libxc/xc_dom_x86.c > @@ -586,23 +586,12 @@ static void build_hvm_info(void *hvm_info_page, struct xc_dom_image *dom) > static int alloc_magic_pages_hvm(struct xc_dom_image *dom) > { > unsigned long i; > - void *hvm_info_page; > uint32_t *ident_pt, domid = dom->guest_domid; > int rc; > xen_pfn_t special_array[X86_HVM_NR_SPECIAL_PAGES]; > xen_pfn_t ioreq_server_array[NR_IOREQ_SERVER_PAGES]; > xc_interface *xch = dom->xch; > > - if ( dom->device_model ) > - { > - if ( (hvm_info_page = xc_map_foreign_range( > - xch, domid, PAGE_SIZE, PROT_READ | PROT_WRITE, > - HVM_INFO_PFN)) == NULL ) > - goto error_out; > - build_hvm_info(hvm_info_page, dom); > - munmap(hvm_info_page, PAGE_SIZE); > - } > - > /* Allocate and clear special pages. */ > for ( i = 0; i < X86_HVM_NR_SPECIAL_PAGES; i++ ) > special_array[i] = special_pfn(i); > @@ -636,65 +625,25 @@ static int alloc_magic_pages_hvm(struct xc_dom_image *dom) > > if ( !dom->device_model ) > { > - struct xc_dom_seg seg; > - struct hvm_start_info *start_info; > - char *cmdline; > - struct hvm_modlist_entry *modlist; > - void *start_page; > - size_t cmdline_size = 0; > - size_t start_info_size = sizeof(*start_info); > + size_t start_info_size = sizeof(struct hvm_start_info); > > if ( dom->cmdline ) > { > - cmdline_size = ROUNDUP(strlen(dom->cmdline) + 1, 8); > - start_info_size += cmdline_size; > - > + dom->cmdline_size = ROUNDUP(strlen(dom->cmdline) + 1, 8); > + start_info_size += dom->cmdline_size; > } > + > + /* Limited to one module. */ > if ( dom->ramdisk_blob ) > - start_info_size += sizeof(*modlist); /* Limited to one module. */ > + start_info_size += sizeof(struct hvm_modlist_entry); > > - rc = xc_dom_alloc_segment(dom, &seg, "HVMlite start info", 0, > - start_info_size); > + rc = xc_dom_alloc_segment(dom, &dom->start_info_seg, > + "HVMlite start info", 0, start_info_size); > if ( rc != 0 ) > { > DOMPRINTF("Unable to reserve memory for the start info"); > goto out; > } > - > - start_page = xc_map_foreign_range(xch, domid, start_info_size, > - PROT_READ | PROT_WRITE, > - seg.pfn); > - if ( start_page == NULL ) > - { > - DOMPRINTF("Unable to map HVM start info page"); > - goto error_out; > - } > - > - start_info = start_page; > - cmdline = start_page + sizeof(*start_info); > - modlist = start_page + sizeof(*start_info) + cmdline_size; > - > - if ( dom->cmdline ) > - { > - strncpy(cmdline, dom->cmdline, cmdline_size); > - start_info->cmdline_paddr = (seg.pfn << PAGE_SHIFT) + > - ((uintptr_t)cmdline - (uintptr_t)start_info); > - } > - > - if ( dom->ramdisk_blob ) > - { > - modlist[0].paddr = dom->ramdisk_seg.vstart - dom->parms.virt_base; > - modlist[0].size = dom->ramdisk_seg.vend - dom->ramdisk_seg.vstart; > - start_info->modlist_paddr = (seg.pfn << PAGE_SHIFT) + > - ((uintptr_t)modlist - (uintptr_t)start_info); > - start_info->nr_modules = 1; > - } > - > - start_info->magic = HVM_START_MAGIC_VALUE; > - > - munmap(start_page, start_info_size); > - > - dom->start_info_pfn = seg.pfn; > } > else > { > @@ -1095,8 +1044,8 @@ static int vcpu_hvm(struct xc_dom_image *dom) > /* Set the IP. */ > bsp_ctx.cpu.rip = dom->parms.phys_entry; > > - if ( dom->start_info_pfn ) > - bsp_ctx.cpu.rbx = dom->start_info_pfn << PAGE_SHIFT; > + if ( dom->start_info_seg.pfn ) > + bsp_ctx.cpu.rbx = dom->start_info_seg.pfn << PAGE_SHIFT; > > /* Set the end descriptor. */ > bsp_ctx.end_d.typecode = HVM_SAVE_CODE(END); > @@ -1783,7 +1732,74 @@ static int alloc_pgtables_hvm(struct xc_dom_image *dom) > > static int bootlate_hvm(struct xc_dom_image *dom) > { > - DOMPRINTF("%s: doing nothing", __func__); > + uint32_t domid = dom->guest_domid; > + xc_interface *xch = dom->xch; > + > + if ( !dom->device_model ) > + { > + struct hvm_start_info *start_info; > + size_t start_info_size; > + void *start_page; > + > + start_info_size = sizeof(*start_info) + dom->cmdline_size; > + if ( dom->ramdisk_blob ) > + start_info_size += sizeof(struct hvm_modlist_entry); > + > + if ( start_info_size > > + dom->start_info_seg.pages << XC_DOM_PAGE_SHIFT(dom) ) > + { > + DOMPRINTF("Trying to map beyond start_info_seg"); > + return -1; > + } > + > + start_page = xc_map_foreign_range(xch, domid, start_info_size, > + PROT_READ | PROT_WRITE, > + dom->start_info_seg.pfn); > + if ( start_page == NULL ) > + { > + DOMPRINTF("Unable to map HVM start info page"); > + return -1; > + } > + > + start_info = start_page; > + > + if ( dom->cmdline ) > + { > + char *cmdline = start_page + sizeof(*start_info); > + > + strncpy(cmdline, dom->cmdline, dom->cmdline_size); > + start_info->cmdline_paddr = (dom->start_info_seg.pfn << PAGE_SHIFT) + > + ((uintptr_t)cmdline - (uintptr_t)start_info); > + } > + > + if ( dom->ramdisk_blob ) > + { > + struct hvm_modlist_entry *modlist = > + start_page + sizeof(*start_info) + dom->cmdline_size; > + > + modlist[0].paddr = dom->ramdisk_seg.vstart - dom->parms.virt_base; > + modlist[0].size = dom->ramdisk_seg.vend - dom->ramdisk_seg.vstart; > + start_info->modlist_paddr = (dom->start_info_seg.pfn << PAGE_SHIFT) + > + ((uintptr_t)modlist - (uintptr_t)start_info); > + start_info->nr_modules = 1; > + } > + > + start_info->magic = HVM_START_MAGIC_VALUE; > + > + munmap(start_page, start_info_size); > + } > + else > + { > + void *hvm_info_page; > + > + if ( (hvm_info_page = xc_map_foreign_range( > + xch, domid, PAGE_SIZE, PROT_READ | PROT_WRITE, > + HVM_INFO_PFN)) == NULL ) > + return -1; > + build_hvm_info(hvm_info_page, dom); > + munmap(hvm_info_page, PAGE_SIZE); > + } > + > return 0; > } > >
On Thu, 2016-01-07 at 17:19 -0500, Boris Ostrovsky wrote: > v4: > * See the last two paragraphs from commit message above > > v4.1: > * Inverted testing of start_info_size in bootlate_hvm(). > > v4.2 > * <facepalm> Actually do what I said I'd do in 4.1 I was so proud of myself for spotting 4.1 just before I reviewed 4, I didn't think to look for a 4.2 ;-) Ian.
On 01/07/2016 11:57 PM, Juergen Gross wrote: > On 07/01/16 23:19, Boris Ostrovsky wrote: >> With commit 8c45adec18e0 ("libxc: create unmapped initrd in domain >> builder if supported") location of ramdisk may not be available to >> HVMlite guests by the time alloc_magic_pages_hvm() is invoked if the >> guest supports unmapped initrd. >> >> So let's move ramdisk info initialization (along with a few other >> operations that are not directly related to allocating magic/special >> pages) from alloc_magic_pages_hvm() to bootlate_hvm(). >> >> Since we now split allocation and mapping of the start_info segment >> let's stash it, along with cmdline length, in xc_dom_image so that we >> can check whether we are mapping correctly-sized range. >> >> We can also stop using xc_dom_image.start_info_pfn and leave it for >> PV(H) guests only. >> >> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> >> --- >> v4: >> * See the last two paragraphs from commit message above >> >> v4.1: >> * Inverted testing of start_info_size in bootlate_hvm(). >> >> v4.2 >> * <facepalm> Actually do what I said I'd do in 4.1 >> >> tools/libxc/include/xc_dom.h | 2 + >> tools/libxc/xc_dom_x86.c | 140 +++++++++++++++++++++++------------------ >> 2 files changed, 80 insertions(+), 62 deletions(-) >> >> diff --git a/tools/libxc/include/xc_dom.h b/tools/libxc/include/xc_dom.h >> index 2460818..cac4698 100644 >> --- a/tools/libxc/include/xc_dom.h >> +++ b/tools/libxc/include/xc_dom.h >> @@ -71,6 +71,7 @@ struct xc_dom_image { >> >> /* arguments and parameters */ >> char *cmdline; >> + size_t cmdline_size; >> uint32_t f_requested[XENFEAT_NR_SUBMAPS]; >> >> /* info from (elf) kernel image */ >> @@ -91,6 +92,7 @@ struct xc_dom_image { >> struct xc_dom_seg p2m_seg; >> struct xc_dom_seg pgtables_seg; >> struct xc_dom_seg devicetree_seg; >> + struct xc_dom_seg start_info_seg; /* HVMlite only */ > Instead of adding HVM specific members here, you could make use of > dom.arch_private and use just a local structure defined in xc_dom_x86.c. I did consider this but since we already keep type-specific segments in this structure (e.g. p2m_seg) decided to add an explicit segment for HVMlite. Besides, I think to properly use it we'd need to add an arch hook and IMHO it's not worth the trouble in this case. -boris
On 08/01/16 15:19, Boris Ostrovsky wrote: > On 01/07/2016 11:57 PM, Juergen Gross wrote: >> On 07/01/16 23:19, Boris Ostrovsky wrote: >>> With commit 8c45adec18e0 ("libxc: create unmapped initrd in domain >>> builder if supported") location of ramdisk may not be available to >>> HVMlite guests by the time alloc_magic_pages_hvm() is invoked if the >>> guest supports unmapped initrd. >>> >>> So let's move ramdisk info initialization (along with a few other >>> operations that are not directly related to allocating magic/special >>> pages) from alloc_magic_pages_hvm() to bootlate_hvm(). >>> >>> Since we now split allocation and mapping of the start_info segment >>> let's stash it, along with cmdline length, in xc_dom_image so that we >>> can check whether we are mapping correctly-sized range. >>> >>> We can also stop using xc_dom_image.start_info_pfn and leave it for >>> PV(H) guests only. >>> >>> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> >>> --- >>> v4: >>> * See the last two paragraphs from commit message above >>> >>> v4.1: >>> * Inverted testing of start_info_size in bootlate_hvm(). >>> >>> v4.2 >>> * <facepalm> Actually do what I said I'd do in 4.1 >>> >>> tools/libxc/include/xc_dom.h | 2 + >>> tools/libxc/xc_dom_x86.c | 140 >>> +++++++++++++++++++++++------------------ >>> 2 files changed, 80 insertions(+), 62 deletions(-) >>> >>> diff --git a/tools/libxc/include/xc_dom.h b/tools/libxc/include/xc_dom.h >>> index 2460818..cac4698 100644 >>> --- a/tools/libxc/include/xc_dom.h >>> +++ b/tools/libxc/include/xc_dom.h >>> @@ -71,6 +71,7 @@ struct xc_dom_image { >>> /* arguments and parameters */ >>> char *cmdline; >>> + size_t cmdline_size; >>> uint32_t f_requested[XENFEAT_NR_SUBMAPS]; >>> /* info from (elf) kernel image */ >>> @@ -91,6 +92,7 @@ struct xc_dom_image { >>> struct xc_dom_seg p2m_seg; >>> struct xc_dom_seg pgtables_seg; >>> struct xc_dom_seg devicetree_seg; >>> + struct xc_dom_seg start_info_seg; /* HVMlite only */ >> Instead of adding HVM specific members here, you could make use of >> dom.arch_private and use just a local structure defined in xc_dom_x86.c. > > I did consider this but since we already keep type-specific segments in > this structure (e.g. p2m_seg) decided to add an explicit segment for > HVMlite. But p2m_seg is accessed from multiple sources, while cmdline_size and start_info_seg would be local to xc_dom_x86.c BTW: thanks for the hint - I'll have a look whether p2m_seg can't be moved to arch_private... > Besides, I think to properly use it we'd need to add an arch hook and > IMHO it's not worth the trouble in this case. Why would you need another arch hook? Just add the arch_private_size member to struct xc_dom_arch and everything is set up for you. Look how it is handled for the pv case in xc_dom_x86.c Juergen
On Fri, 2016-01-08 at 09:19 -0500, Boris Ostrovsky wrote: > index 2460818..cac4698 100644 > > > --- a/tools/libxc/include/xc_dom.h > > > +++ b/tools/libxc/include/xc_dom.h > > > @@ -71,6 +71,7 @@ struct xc_dom_image { > > > > > > /* arguments and parameters */ > > > char *cmdline; > > > + size_t cmdline_size; > > > uint32_t f_requested[XENFEAT_NR_SUBMAPS]; > > > > > > /* info from (elf) kernel image */ > > > @@ -91,6 +92,7 @@ struct xc_dom_image { > > > struct xc_dom_seg p2m_seg; > > > struct xc_dom_seg pgtables_seg; > > > struct xc_dom_seg devicetree_seg; > > > + struct xc_dom_seg start_info_seg; /* HVMlite only */ > > Instead of adding HVM specific members here, you could make use of > > dom.arch_private and use just a local structure defined in > > xc_dom_x86.c. > > I did consider this but since we already keep type-specific segments in > this structure (e.g. p2m_seg) decided to add an explicit segment for > HVMlite. > > Besides, I think to properly use it we'd need to add an arch hook and > IMHO it's not worth the trouble in this case. Agreed, it is at best a potential future cleanup. Ian.
On 01/08/2016 09:30 AM, Juergen Gross wrote: > On 08/01/16 15:19, Boris Ostrovsky wrote: >> On 01/07/2016 11:57 PM, Juergen Gross wrote: >>> On 07/01/16 23:19, Boris Ostrovsky wrote: >>>> With commit 8c45adec18e0 ("libxc: create unmapped initrd in domain >>>> builder if supported") location of ramdisk may not be available to >>>> HVMlite guests by the time alloc_magic_pages_hvm() is invoked if the >>>> guest supports unmapped initrd. >>>> >>>> So let's move ramdisk info initialization (along with a few other >>>> operations that are not directly related to allocating magic/special >>>> pages) from alloc_magic_pages_hvm() to bootlate_hvm(). >>>> >>>> Since we now split allocation and mapping of the start_info segment >>>> let's stash it, along with cmdline length, in xc_dom_image so that we >>>> can check whether we are mapping correctly-sized range. >>>> >>>> We can also stop using xc_dom_image.start_info_pfn and leave it for >>>> PV(H) guests only. >>>> >>>> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> >>>> --- >>>> v4: >>>> * See the last two paragraphs from commit message above >>>> >>>> v4.1: >>>> * Inverted testing of start_info_size in bootlate_hvm(). >>>> >>>> v4.2 >>>> * <facepalm> Actually do what I said I'd do in 4.1 >>>> >>>> tools/libxc/include/xc_dom.h | 2 + >>>> tools/libxc/xc_dom_x86.c | 140 >>>> +++++++++++++++++++++++------------------ >>>> 2 files changed, 80 insertions(+), 62 deletions(-) >>>> >>>> diff --git a/tools/libxc/include/xc_dom.h b/tools/libxc/include/xc_dom.h >>>> index 2460818..cac4698 100644 >>>> --- a/tools/libxc/include/xc_dom.h >>>> +++ b/tools/libxc/include/xc_dom.h >>>> @@ -71,6 +71,7 @@ struct xc_dom_image { >>>> /* arguments and parameters */ >>>> char *cmdline; >>>> + size_t cmdline_size; >>>> uint32_t f_requested[XENFEAT_NR_SUBMAPS]; >>>> /* info from (elf) kernel image */ >>>> @@ -91,6 +92,7 @@ struct xc_dom_image { >>>> struct xc_dom_seg p2m_seg; >>>> struct xc_dom_seg pgtables_seg; >>>> struct xc_dom_seg devicetree_seg; >>>> + struct xc_dom_seg start_info_seg; /* HVMlite only */ >>> Instead of adding HVM specific members here, you could make use of >>> dom.arch_private and use just a local structure defined in xc_dom_x86.c. >> I did consider this but since we already keep type-specific segments in >> this structure (e.g. p2m_seg) decided to add an explicit segment for >> HVMlite. > But p2m_seg is accessed from multiple sources, while cmdline_size and > start_info_seg would be local to xc_dom_x86.c > > BTW: thanks for the hint - I'll have a look whether p2m_seg can't be > moved to arch_private... > >> Besides, I think to properly use it we'd need to add an arch hook and >> IMHO it's not worth the trouble in this case. > Why would you need another arch hook? Just add the arch_private_size > member to struct xc_dom_arch and everything is set up for you. Look > how it is handled for the pv case in xc_dom_x86.c So it is already hooked up, I didn't notice that we do register xc_hvm_32, even though arch_private_size is 0. This would be a type-specific area though, not arch-specific as the name implies. So perhaps xc_dom_image_x86 should be modified to include type-specific structures (via a union). -boris
On Fri, 2016-01-08 at 09:53 -0500, Boris Ostrovsky wrote: > On 01/08/2016 09:30 AM, Juergen Gross wrote: > > On 08/01/16 15:19, Boris Ostrovsky wrote: > > > On 01/07/2016 11:57 PM, Juergen Gross wrote: > > > > On 07/01/16 23:19, Boris Ostrovsky wrote: > > > > > With commit 8c45adec18e0 ("libxc: create unmapped initrd in > > > > > domain > > > > > builder if supported") location of ramdisk may not be available > > > > > to > > > > > HVMlite guests by the time alloc_magic_pages_hvm() is invoked if > > > > > the > > > > > guest supports unmapped initrd. > > > > > > > > > > So let's move ramdisk info initialization (along with a few other > > > > > operations that are not directly related to allocating > > > > > magic/special > > > > > pages) from alloc_magic_pages_hvm() to bootlate_hvm(). > > > > > > > > > > Since we now split allocation and mapping of the start_info > > > > > segment > > > > > let's stash it, along with cmdline length, in xc_dom_image so > > > > > that we > > > > > can check whether we are mapping correctly-sized range. > > > > > > > > > > We can also stop using xc_dom_image.start_info_pfn and leave it > > > > > for > > > > > PV(H) guests only. > > > > > > > > > > Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> > > > > > --- > > > > > v4: > > > > > * See the last two paragraphs from commit message above > > > > > > > > > > v4.1: > > > > > * Inverted testing of start_info_size in bootlate_hvm(). > > > > > > > > > > v4.2 > > > > > * <facepalm> Actually do what I said I'd do in 4.1 > > > > > > > > > > tools/libxc/include/xc_dom.h | 2 + > > > > > tools/libxc/xc_dom_x86.c | 140 > > > > > +++++++++++++++++++++++------------------ > > > > > 2 files changed, 80 insertions(+), 62 deletions(-) > > > > > > > > > > diff --git a/tools/libxc/include/xc_dom.h > > > > > b/tools/libxc/include/xc_dom.h > > > > > index 2460818..cac4698 100644 > > > > > --- a/tools/libxc/include/xc_dom.h > > > > > +++ b/tools/libxc/include/xc_dom.h > > > > > @@ -71,6 +71,7 @@ struct xc_dom_image { > > > > > /* arguments and parameters */ > > > > > char *cmdline; > > > > > + size_t cmdline_size; > > > > > uint32_t f_requested[XENFEAT_NR_SUBMAPS]; > > > > > /* info from (elf) kernel image */ > > > > > @@ -91,6 +92,7 @@ struct xc_dom_image { > > > > > struct xc_dom_seg p2m_seg; > > > > > struct xc_dom_seg pgtables_seg; > > > > > struct xc_dom_seg devicetree_seg; > > > > > + struct xc_dom_seg start_info_seg; /* HVMlite only */ > > > > Instead of adding HVM specific members here, you could make use of > > > > dom.arch_private and use just a local structure defined in > > > > xc_dom_x86.c. > > > I did consider this but since we already keep type-specific segments > > > in > > > this structure (e.g. p2m_seg) decided to add an explicit segment for > > > HVMlite. > > But p2m_seg is accessed from multiple sources, while cmdline_size and > > start_info_seg would be local to xc_dom_x86.c > > > > BTW: thanks for the hint - I'll have a look whether p2m_seg can't be > > moved to arch_private... > > > > > Besides, I think to properly use it we'd need to add an arch hook and > > > IMHO it's not worth the trouble in this case. > > Why would you need another arch hook? Just add the arch_private_size > > member to struct xc_dom_arch and everything is set up for you. Look > > how it is handled for the pv case in xc_dom_x86.c > > So it is already hooked up, I didn't notice that we do register > xc_hvm_32, even though arch_private_size is 0. > > This would be a type-specific area though, not arch-specific as the name > implies. So perhaps xc_dom_image_x86 should be modified to include > type-specific structures (via a union). You are talking future work here, right? There's no reason not to proceed with the current patch AFAICT, I'm really just giving Roger a chance to have a look at this point. BTW, it might be possible to use xc_dom_seg_to_ptr instead of an open coded xc_map_foreign? Although it wasn't used before and maybe there is a reason for that which still applies. Ian.
On 01/08/2016 10:11 AM, Ian Campbell wrote: > On Fri, 2016-01-08 at 09:53 -0500, Boris Ostrovsky wrote: >> On 01/08/2016 09:30 AM, Juergen Gross wrote: >>> On 08/01/16 15:19, Boris Ostrovsky wrote: >>>> On 01/07/2016 11:57 PM, Juergen Gross wrote: >>>>> On 07/01/16 23:19, Boris Ostrovsky wrote: >>>>>> With commit 8c45adec18e0 ("libxc: create unmapped initrd in >>>>>> domain >>>>>> builder if supported") location of ramdisk may not be available >>>>>> to >>>>>> HVMlite guests by the time alloc_magic_pages_hvm() is invoked if >>>>>> the >>>>>> guest supports unmapped initrd. >>>>>> >>>>>> So let's move ramdisk info initialization (along with a few other >>>>>> operations that are not directly related to allocating >>>>>> magic/special >>>>>> pages) from alloc_magic_pages_hvm() to bootlate_hvm(). >>>>>> >>>>>> Since we now split allocation and mapping of the start_info >>>>>> segment >>>>>> let's stash it, along with cmdline length, in xc_dom_image so >>>>>> that we >>>>>> can check whether we are mapping correctly-sized range. >>>>>> >>>>>> We can also stop using xc_dom_image.start_info_pfn and leave it >>>>>> for >>>>>> PV(H) guests only. >>>>>> >>>>>> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> >>>>>> --- >>>>>> v4: >>>>>> * See the last two paragraphs from commit message above >>>>>> >>>>>> v4.1: >>>>>> * Inverted testing of start_info_size in bootlate_hvm(). >>>>>> >>>>>> v4.2 >>>>>> * <facepalm> Actually do what I said I'd do in 4.1 >>>>>> >>>>>> tools/libxc/include/xc_dom.h | 2 + >>>>>> tools/libxc/xc_dom_x86.c | 140 >>>>>> +++++++++++++++++++++++------------------ >>>>>> 2 files changed, 80 insertions(+), 62 deletions(-) >>>>>> >>>>>> diff --git a/tools/libxc/include/xc_dom.h >>>>>> b/tools/libxc/include/xc_dom.h >>>>>> index 2460818..cac4698 100644 >>>>>> --- a/tools/libxc/include/xc_dom.h >>>>>> +++ b/tools/libxc/include/xc_dom.h >>>>>> @@ -71,6 +71,7 @@ struct xc_dom_image { >>>>>> /* arguments and parameters */ >>>>>> char *cmdline; >>>>>> + size_t cmdline_size; >>>>>> uint32_t f_requested[XENFEAT_NR_SUBMAPS]; >>>>>> /* info from (elf) kernel image */ >>>>>> @@ -91,6 +92,7 @@ struct xc_dom_image { >>>>>> struct xc_dom_seg p2m_seg; >>>>>> struct xc_dom_seg pgtables_seg; >>>>>> struct xc_dom_seg devicetree_seg; >>>>>> + struct xc_dom_seg start_info_seg; /* HVMlite only */ >>>>> Instead of adding HVM specific members here, you could make use of >>>>> dom.arch_private and use just a local structure defined in >>>>> xc_dom_x86.c. >>>> I did consider this but since we already keep type-specific segments >>>> in >>>> this structure (e.g. p2m_seg) decided to add an explicit segment for >>>> HVMlite. >>> But p2m_seg is accessed from multiple sources, while cmdline_size and >>> start_info_seg would be local to xc_dom_x86.c >>> >>> BTW: thanks for the hint - I'll have a look whether p2m_seg can't be >>> moved to arch_private... >>> >>>> Besides, I think to properly use it we'd need to add an arch hook and >>>> IMHO it's not worth the trouble in this case. >>> Why would you need another arch hook? Just add the arch_private_size >>> member to struct xc_dom_arch and everything is set up for you. Look >>> how it is handled for the pv case in xc_dom_x86.c >> So it is already hooked up, I didn't notice that we do register >> xc_hvm_32, even though arch_private_size is 0. >> >> This would be a type-specific area though, not arch-specific as the name >> implies. So perhaps xc_dom_image_x86 should be modified to include >> type-specific structures (via a union). > You are talking future work here, right? There's no reason not to proceed > with the current patch AFAICT, I'm really just giving Roger a chance to > have a look at this point. Yes, I wasn't thinking of doing this in this patch. > > BTW, it might be possible to use xc_dom_seg_to_ptr instead of an open coded > xc_map_foreign? Although it wasn't used before and maybe there is a reason > for that which still applies. No explicit reason, this was just moving things around. -boris
El 08/01/16 a les 16.11, Ian Campbell ha escrit: > On Fri, 2016-01-08 at 09:53 -0500, Boris Ostrovsky wrote: >> On 01/08/2016 09:30 AM, Juergen Gross wrote: >>> On 08/01/16 15:19, Boris Ostrovsky wrote: >>>> On 01/07/2016 11:57 PM, Juergen Gross wrote: >>>>> On 07/01/16 23:19, Boris Ostrovsky wrote: >>>>>> With commit 8c45adec18e0 ("libxc: create unmapped initrd in >>>>>> domain >>>>>> builder if supported") location of ramdisk may not be available >>>>>> to >>>>>> HVMlite guests by the time alloc_magic_pages_hvm() is invoked if >>>>>> the >>>>>> guest supports unmapped initrd. >>>>>> >>>>>> So let's move ramdisk info initialization (along with a few other >>>>>> operations that are not directly related to allocating >>>>>> magic/special >>>>>> pages) from alloc_magic_pages_hvm() to bootlate_hvm(). >>>>>> >>>>>> Since we now split allocation and mapping of the start_info >>>>>> segment >>>>>> let's stash it, along with cmdline length, in xc_dom_image so >>>>>> that we >>>>>> can check whether we are mapping correctly-sized range. >>>>>> >>>>>> We can also stop using xc_dom_image.start_info_pfn and leave it >>>>>> for >>>>>> PV(H) guests only. >>>>>> >>>>>> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> >>>>>> --- >>>>>> v4: >>>>>> * See the last two paragraphs from commit message above >>>>>> >>>>>> v4.1: >>>>>> * Inverted testing of start_info_size in bootlate_hvm(). >>>>>> >>>>>> v4.2 >>>>>> * <facepalm> Actually do what I said I'd do in 4.1 >>>>>> >>>>>> tools/libxc/include/xc_dom.h | 2 + >>>>>> tools/libxc/xc_dom_x86.c | 140 >>>>>> +++++++++++++++++++++++------------------ >>>>>> 2 files changed, 80 insertions(+), 62 deletions(-) >>>>>> >>>>>> diff --git a/tools/libxc/include/xc_dom.h >>>>>> b/tools/libxc/include/xc_dom.h >>>>>> index 2460818..cac4698 100644 >>>>>> --- a/tools/libxc/include/xc_dom.h >>>>>> +++ b/tools/libxc/include/xc_dom.h >>>>>> @@ -71,6 +71,7 @@ struct xc_dom_image { >>>>>> /* arguments and parameters */ >>>>>> char *cmdline; >>>>>> + size_t cmdline_size; >>>>>> uint32_t f_requested[XENFEAT_NR_SUBMAPS]; >>>>>> /* info from (elf) kernel image */ >>>>>> @@ -91,6 +92,7 @@ struct xc_dom_image { >>>>>> struct xc_dom_seg p2m_seg; >>>>>> struct xc_dom_seg pgtables_seg; >>>>>> struct xc_dom_seg devicetree_seg; >>>>>> + struct xc_dom_seg start_info_seg; /* HVMlite only */ >>>>> Instead of adding HVM specific members here, you could make use of >>>>> dom.arch_private and use just a local structure defined in >>>>> xc_dom_x86.c. >>>> I did consider this but since we already keep type-specific segments >>>> in >>>> this structure (e.g. p2m_seg) decided to add an explicit segment for >>>> HVMlite. >>> But p2m_seg is accessed from multiple sources, while cmdline_size and >>> start_info_seg would be local to xc_dom_x86.c >>> >>> BTW: thanks for the hint - I'll have a look whether p2m_seg can't be >>> moved to arch_private... >>> >>>> Besides, I think to properly use it we'd need to add an arch hook and >>>> IMHO it's not worth the trouble in this case. >>> Why would you need another arch hook? Just add the arch_private_size >>> member to struct xc_dom_arch and everything is set up for you. Look >>> how it is handled for the pv case in xc_dom_x86.c >> >> So it is already hooked up, I didn't notice that we do register >> xc_hvm_32, even though arch_private_size is 0. >> >> This would be a type-specific area though, not arch-specific as the name >> implies. So perhaps xc_dom_image_x86 should be modified to include >> type-specific structures (via a union). > > You are talking future work here, right? There's no reason not to proceed > with the current patch AFAICT, I'm really just giving Roger a chance to > have a look at this point. LGTM: Acked-by: Roger Pau Monné <roger.pau@citrix.com>
On 01/08/2016 10:11 AM, Ian Campbell wrote: > > BTW, it might be possible to use xc_dom_seg_to_ptr instead of an open coded > xc_map_foreign? Although it wasn't used before and maybe there is a reason > for that which still applies. Is this waiting for me to replace xc_map_foreign() with xc_dom_seg_to_ptr? It wasn't clear to me from this last message. -boris
On Tue, 2016-01-19 at 10:02 -0500, Boris Ostrovsky wrote: > On 01/08/2016 10:11 AM, Ian Campbell wrote: > > > > BTW, it might be possible to use xc_dom_seg_to_ptr instead of an open > > coded > > xc_map_foreign? Although it wasn't used before and maybe there is a > > reason > > for that which still applies. > > > Is this waiting for me to replace xc_map_foreign() with > xc_dom_seg_to_ptr? It wasn't clear to me from this last message. I was just wondering that myself. Looking back over the thread it seems like I was waiting for Roger's feedback, which came in ages ago (and I didn't notice). Acked-by: Ian Campbell <ian.campbell@citrix.com> I'll pick this up in my next sweep.
On Tue, 2016-01-19 at 15:13 +0000, Ian Campbell wrote: > On Tue, 2016-01-19 at 10:02 -0500, Boris Ostrovsky wrote: > > On 01/08/2016 10:11 AM, Ian Campbell wrote: > > > > > > BTW, it might be possible to use xc_dom_seg_to_ptr instead of an open > > > coded > > > xc_map_foreign? Although it wasn't used before and maybe there is a > > > reason > > > for that which still applies. > > > > > > Is this waiting for me to replace xc_map_foreign() with > > xc_dom_seg_to_ptr? It wasn't clear to me from this last message. > > I was just wondering that myself. Looking back over the thread it seems > like I was waiting for Roger's feedback, which came in ages ago (and I > didn't notice). > > Acked-by: Ian Campbell <ian.campbell@citrix.com> > > I'll pick this up in my next sweep. Done. > > > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xen.org > http://lists.xen.org/xen-devel
diff --git a/tools/libxc/include/xc_dom.h b/tools/libxc/include/xc_dom.h index 2460818..cac4698 100644 --- a/tools/libxc/include/xc_dom.h +++ b/tools/libxc/include/xc_dom.h @@ -71,6 +71,7 @@ struct xc_dom_image { /* arguments and parameters */ char *cmdline; + size_t cmdline_size; uint32_t f_requested[XENFEAT_NR_SUBMAPS]; /* info from (elf) kernel image */ @@ -91,6 +92,7 @@ struct xc_dom_image { struct xc_dom_seg p2m_seg; struct xc_dom_seg pgtables_seg; struct xc_dom_seg devicetree_seg; + struct xc_dom_seg start_info_seg; /* HVMlite only */ xen_pfn_t start_info_pfn; xen_pfn_t console_pfn; xen_pfn_t xenstore_pfn; diff --git a/tools/libxc/xc_dom_x86.c b/tools/libxc/xc_dom_x86.c index b8d2904..edf2db1 100644 --- a/tools/libxc/xc_dom_x86.c +++ b/tools/libxc/xc_dom_x86.c @@ -586,23 +586,12 @@ static void build_hvm_info(void *hvm_info_page, struct xc_dom_image *dom) static int alloc_magic_pages_hvm(struct xc_dom_image *dom) { unsigned long i; - void *hvm_info_page; uint32_t *ident_pt, domid = dom->guest_domid; int rc; xen_pfn_t special_array[X86_HVM_NR_SPECIAL_PAGES]; xen_pfn_t ioreq_server_array[NR_IOREQ_SERVER_PAGES]; xc_interface *xch = dom->xch; - if ( dom->device_model ) - { - if ( (hvm_info_page = xc_map_foreign_range( - xch, domid, PAGE_SIZE, PROT_READ | PROT_WRITE, - HVM_INFO_PFN)) == NULL ) - goto error_out; - build_hvm_info(hvm_info_page, dom); - munmap(hvm_info_page, PAGE_SIZE); - } - /* Allocate and clear special pages. */ for ( i = 0; i < X86_HVM_NR_SPECIAL_PAGES; i++ ) special_array[i] = special_pfn(i); @@ -636,65 +625,25 @@ static int alloc_magic_pages_hvm(struct xc_dom_image *dom) if ( !dom->device_model ) { - struct xc_dom_seg seg; - struct hvm_start_info *start_info; - char *cmdline; - struct hvm_modlist_entry *modlist; - void *start_page; - size_t cmdline_size = 0; - size_t start_info_size = sizeof(*start_info); + size_t start_info_size = sizeof(struct hvm_start_info); if ( dom->cmdline ) { - cmdline_size = ROUNDUP(strlen(dom->cmdline) + 1, 8); - start_info_size += cmdline_size; - + dom->cmdline_size = ROUNDUP(strlen(dom->cmdline) + 1, 8); + start_info_size += dom->cmdline_size; } + + /* Limited to one module. */ if ( dom->ramdisk_blob ) - start_info_size += sizeof(*modlist); /* Limited to one module. */ + start_info_size += sizeof(struct hvm_modlist_entry); - rc = xc_dom_alloc_segment(dom, &seg, "HVMlite start info", 0, - start_info_size); + rc = xc_dom_alloc_segment(dom, &dom->start_info_seg, + "HVMlite start info", 0, start_info_size); if ( rc != 0 ) { DOMPRINTF("Unable to reserve memory for the start info"); goto out; } - - start_page = xc_map_foreign_range(xch, domid, start_info_size, - PROT_READ | PROT_WRITE, - seg.pfn); - if ( start_page == NULL ) - { - DOMPRINTF("Unable to map HVM start info page"); - goto error_out; - } - - start_info = start_page; - cmdline = start_page + sizeof(*start_info); - modlist = start_page + sizeof(*start_info) + cmdline_size; - - if ( dom->cmdline ) - { - strncpy(cmdline, dom->cmdline, cmdline_size); - start_info->cmdline_paddr = (seg.pfn << PAGE_SHIFT) + - ((uintptr_t)cmdline - (uintptr_t)start_info); - } - - if ( dom->ramdisk_blob ) - { - modlist[0].paddr = dom->ramdisk_seg.vstart - dom->parms.virt_base; - modlist[0].size = dom->ramdisk_seg.vend - dom->ramdisk_seg.vstart; - start_info->modlist_paddr = (seg.pfn << PAGE_SHIFT) + - ((uintptr_t)modlist - (uintptr_t)start_info); - start_info->nr_modules = 1; - } - - start_info->magic = HVM_START_MAGIC_VALUE; - - munmap(start_page, start_info_size); - - dom->start_info_pfn = seg.pfn; } else { @@ -1095,8 +1044,8 @@ static int vcpu_hvm(struct xc_dom_image *dom) /* Set the IP. */ bsp_ctx.cpu.rip = dom->parms.phys_entry; - if ( dom->start_info_pfn ) - bsp_ctx.cpu.rbx = dom->start_info_pfn << PAGE_SHIFT; + if ( dom->start_info_seg.pfn ) + bsp_ctx.cpu.rbx = dom->start_info_seg.pfn << PAGE_SHIFT; /* Set the end descriptor. */ bsp_ctx.end_d.typecode = HVM_SAVE_CODE(END); @@ -1783,7 +1732,74 @@ static int alloc_pgtables_hvm(struct xc_dom_image *dom) static int bootlate_hvm(struct xc_dom_image *dom) { - DOMPRINTF("%s: doing nothing", __func__); + uint32_t domid = dom->guest_domid; + xc_interface *xch = dom->xch; + + if ( !dom->device_model ) + { + struct hvm_start_info *start_info; + size_t start_info_size; + void *start_page; + + start_info_size = sizeof(*start_info) + dom->cmdline_size; + if ( dom->ramdisk_blob ) + start_info_size += sizeof(struct hvm_modlist_entry); + + if ( start_info_size > + dom->start_info_seg.pages << XC_DOM_PAGE_SHIFT(dom) ) + { + DOMPRINTF("Trying to map beyond start_info_seg"); + return -1; + } + + start_page = xc_map_foreign_range(xch, domid, start_info_size, + PROT_READ | PROT_WRITE, + dom->start_info_seg.pfn); + if ( start_page == NULL ) + { + DOMPRINTF("Unable to map HVM start info page"); + return -1; + } + + start_info = start_page; + + if ( dom->cmdline ) + { + char *cmdline = start_page + sizeof(*start_info); + + strncpy(cmdline, dom->cmdline, dom->cmdline_size); + start_info->cmdline_paddr = (dom->start_info_seg.pfn << PAGE_SHIFT) + + ((uintptr_t)cmdline - (uintptr_t)start_info); + } + + if ( dom->ramdisk_blob ) + { + struct hvm_modlist_entry *modlist = + start_page + sizeof(*start_info) + dom->cmdline_size; + + modlist[0].paddr = dom->ramdisk_seg.vstart - dom->parms.virt_base; + modlist[0].size = dom->ramdisk_seg.vend - dom->ramdisk_seg.vstart; + start_info->modlist_paddr = (dom->start_info_seg.pfn << PAGE_SHIFT) + + ((uintptr_t)modlist - (uintptr_t)start_info); + start_info->nr_modules = 1; + } + + start_info->magic = HVM_START_MAGIC_VALUE; + + munmap(start_page, start_info_size); + } + else + { + void *hvm_info_page; + + if ( (hvm_info_page = xc_map_foreign_range( + xch, domid, PAGE_SIZE, PROT_READ | PROT_WRITE, + HVM_INFO_PFN)) == NULL ) + return -1; + build_hvm_info(hvm_info_page, dom); + munmap(hvm_info_page, PAGE_SIZE); + } + return 0; }
With commit 8c45adec18e0 ("libxc: create unmapped initrd in domain builder if supported") location of ramdisk may not be available to HVMlite guests by the time alloc_magic_pages_hvm() is invoked if the guest supports unmapped initrd. So let's move ramdisk info initialization (along with a few other operations that are not directly related to allocating magic/special pages) from alloc_magic_pages_hvm() to bootlate_hvm(). Since we now split allocation and mapping of the start_info segment let's stash it, along with cmdline length, in xc_dom_image so that we can check whether we are mapping correctly-sized range. We can also stop using xc_dom_image.start_info_pfn and leave it for PV(H) guests only. Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> --- v4: * See the last two paragraphs from commit message above v4.1: * Inverted testing of start_info_size in bootlate_hvm(). v4.2 * <facepalm> Actually do what I said I'd do in 4.1 tools/libxc/include/xc_dom.h | 2 + tools/libxc/xc_dom_x86.c | 140 +++++++++++++++++++++++------------------ 2 files changed, 80 insertions(+), 62 deletions(-)