From 8d693b911bb9c57009c24cb1772d205b84c7985c Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 11 Jul 2014 11:51:35 -0400 Subject: xen: Introduce 'xen_nopv' to disable PV extensions for HVM guests. By default when CONFIG_XEN and CONFIG_XEN_PVHVM kernels are run, they will enable the PV extensions (drivers, interrupts, timers, etc) - which is the best option for the majority of use cases. However, in some cases (kexec not fully working, benchmarking) we want to disable Xen PV extensions. As such introduce the 'xen_nopv' parameter that will do it. This parameter is intended only for HVM guests as the Xen PV guests MUST boot with PV extensions. However, even if you use 'xen_nopv' on Xen PV guests it will be ignored. Signed-off-by: Konrad Rzeszutek Wilk Reviewed-by: David Vrabel --- [v2: s/off/xen_nopv/ per Boris Ostrovsky recommendation.] [v3: Add Reviewed-by] [v4: Clarify that this is only for HVM guests] --- Documentation/kernel-parameters.txt | 4 ++++ arch/x86/xen/enlighten.c | 13 +++++++++++++ 2 files changed, 17 insertions(+) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c1b9aa8..403f927 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3691,6 +3691,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Disables the ticketlock slowpath using Xen PV optimizations. + xen_nopv [X86] + Disables the PV optimizations forcing the HVM guest to + run as generic HVM guest with no PV drivers. + xirc2ps_cs= [NET,PCMCIA] Format: ,,,,,[,[,[,]]] diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ffb101e..eb82239 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1826,8 +1826,19 @@ static void __init xen_hvm_guest_init(void) xen_hvm_init_mmu_ops(); } +static bool xen_nopv = false; +static __init int xen_parse_nopv(char *arg) +{ + xen_nopv = true; + return 0; +} +early_param("xen_nopv", xen_parse_nopv); + static uint32_t __init xen_hvm_platform(void) { + if (xen_nopv) + return 0; + if (xen_pv_domain()) return 0; @@ -1836,6 +1847,8 @@ static uint32_t __init xen_hvm_platform(void) bool xen_hvm_need_lapic(void) { + if (xen_nopv) + return false; if (xen_pv_domain()) return false; if (!xen_hvm_domain()) -- cgit v1.1 From a2c5ae65addb122270cf4115c92039c5b8bf15b9 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 27 Jun 2014 10:10:45 -0400 Subject: MAINTAINERS: Make me the Xen block subsystem (front and back) maintainer The other MAINTAINER entries don't cover for this so the xen-blkback driver looks like it is unmaintained. That is not the case - but to make it obvious to tools - here is the proper entry. CC: Jens Axboe Signed-off-by: Konrad Rzeszutek Wilk --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index e31c874..7aac7e1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10032,6 +10032,13 @@ S: Supported F: arch/x86/pci/*xen* F: drivers/pci/*xen* +XEN BLOCK SUBSYSTEM +M: Konrad Rzeszutek Wilk +L: xen-devel@lists.xenproject.org (moderated for non-subscribers) +S: Supported +F: drivers/block/xen-blkback/* +F: drivers/block/xen* + XEN SWIOTLB SUBSYSTEM M: Konrad Rzeszutek Wilk L: xen-devel@lists.xenproject.org (moderated for non-subscribers) -- cgit v1.1 From 162e371712768248a38646eefa71af38b6e0f8ce Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Fri, 11 Jul 2014 16:42:34 +0100 Subject: x86/xen: safely map and unmap grant frames when in atomic context arch_gnttab_map_frames() and arch_gnttab_unmap_frames() are called in atomic context but were calling alloc_vm_area() which might sleep. Also, if a driver attempts to allocate a grant ref from an interrupt and the table needs expanding, then the CPU may already by in lazy MMU mode and apply_to_page_range() will BUG when it tries to re-enable lazy MMU mode. These two functions are only used in PV guests. Introduce arch_gnttab_init() to allocates the virtual address space in advance. Avoid the use of apply_to_page_range() by using saving and using the array of PTE addresses from the alloc_vm_area() call. N.B. 'alloc_vm_area' pre-allocates the pagetable so there is no need to worry about having to do a PGD/PUD/PMD walk (like apply_to_page_range does) and we can instead do set_pte. Signed-off-by: David Vrabel Signed-off-by: Konrad Rzeszutek Wilk ---- [v2: Add comment about alloc_vm_area] [v3: Fix compile error found by 0-day bot] --- arch/arm/xen/grant-table.c | 5 ++ arch/x86/xen/grant-table.c | 148 ++++++++++++++++++++++++++++----------------- drivers/xen/grant-table.c | 9 ++- include/xen/grant_table.h | 1 + 4 files changed, 105 insertions(+), 58 deletions(-) diff --git a/arch/arm/xen/grant-table.c b/arch/arm/xen/grant-table.c index 859a9bb..91cf08b 100644 --- a/arch/arm/xen/grant-table.c +++ b/arch/arm/xen/grant-table.c @@ -51,3 +51,8 @@ int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, { return -ENOSYS; } + +int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status) +{ + return 0; +} diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index c985835..ebfa9b2 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -36,99 +36,133 @@ #include #include +#include #include #include #include #include +#include #include -static int map_pte_fn(pte_t *pte, struct page *pmd_page, - unsigned long addr, void *data) +static struct gnttab_vm_area { + struct vm_struct *area; + pte_t **ptes; +} gnttab_shared_vm_area, gnttab_status_vm_area; + +int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, + unsigned long max_nr_gframes, + void **__shared) { - unsigned long **frames = (unsigned long **)data; + void *shared = *__shared; + unsigned long addr; + unsigned long i; - set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL)); - (*frames)++; - return 0; -} + if (shared == NULL) + *__shared = shared = gnttab_shared_vm_area.area->addr; -/* - * This function is used to map shared frames to store grant status. It is - * different from map_pte_fn above, the frames type here is uint64_t. - */ -static int map_pte_fn_status(pte_t *pte, struct page *pmd_page, - unsigned long addr, void *data) -{ - uint64_t **frames = (uint64_t **)data; + addr = (unsigned long)shared; + + for (i = 0; i < nr_gframes; i++) { + set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i], + mfn_pte(frames[i], PAGE_KERNEL)); + addr += PAGE_SIZE; + } - set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL)); - (*frames)++; return 0; } -static int unmap_pte_fn(pte_t *pte, struct page *pmd_page, - unsigned long addr, void *data) +int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, + unsigned long max_nr_gframes, + grant_status_t **__shared) { + grant_status_t *shared = *__shared; + unsigned long addr; + unsigned long i; + + if (shared == NULL) + *__shared = shared = gnttab_status_vm_area.area->addr; + + addr = (unsigned long)shared; + + for (i = 0; i < nr_gframes; i++) { + set_pte_at(&init_mm, addr, gnttab_status_vm_area.ptes[i], + mfn_pte(frames[i], PAGE_KERNEL)); + addr += PAGE_SIZE; + } - set_pte_at(&init_mm, addr, pte, __pte(0)); return 0; } -int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, - unsigned long max_nr_gframes, - void **__shared) +void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) { - int rc; - void *shared = *__shared; + pte_t **ptes; + unsigned long addr; + unsigned long i; - if (shared == NULL) { - struct vm_struct *area = - alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL); - BUG_ON(area == NULL); - shared = area->addr; - *__shared = shared; - } + if (shared == gnttab_status_vm_area.area->addr) + ptes = gnttab_status_vm_area.ptes; + else + ptes = gnttab_shared_vm_area.ptes; - rc = apply_to_page_range(&init_mm, (unsigned long)shared, - PAGE_SIZE * nr_gframes, - map_pte_fn, &frames); - return rc; + addr = (unsigned long)shared; + + for (i = 0; i < nr_gframes; i++) { + set_pte_at(&init_mm, addr, ptes[i], __pte(0)); + addr += PAGE_SIZE; + } } -int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, - unsigned long max_nr_gframes, - grant_status_t **__shared) +static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames) { - int rc; - grant_status_t *shared = *__shared; + area->ptes = kmalloc(sizeof(pte_t *) * nr_frames, GFP_KERNEL); + if (area->ptes == NULL) + return -ENOMEM; - if (shared == NULL) { - /* No need to pass in PTE as we are going to do it - * in apply_to_page_range anyhow. */ - struct vm_struct *area = - alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL); - BUG_ON(area == NULL); - shared = area->addr; - *__shared = shared; + area->area = alloc_vm_area(PAGE_SIZE * nr_frames, area->ptes); + if (area->area == NULL) { + kfree(area->ptes); + return -ENOMEM; } - rc = apply_to_page_range(&init_mm, (unsigned long)shared, - PAGE_SIZE * nr_gframes, - map_pte_fn_status, &frames); - return rc; + return 0; } -void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) +static void arch_gnttab_vfree(struct gnttab_vm_area *area) +{ + free_vm_area(area->area); + kfree(area->ptes); +} + +int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status) { - apply_to_page_range(&init_mm, (unsigned long)shared, - PAGE_SIZE * nr_gframes, unmap_pte_fn, NULL); + int ret; + + if (!xen_pv_domain()) + return 0; + + ret = arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared); + if (ret < 0) + return ret; + + /* + * Always allocate the space for the status frames in case + * we're migrated to a host with V2 support. + */ + ret = arch_gnttab_valloc(&gnttab_status_vm_area, nr_status); + if (ret < 0) + goto err; + + return 0; + err: + arch_gnttab_vfree(&gnttab_shared_vm_area); + return -ENOMEM; } + #ifdef CONFIG_XEN_PVH #include #include -#include #include static int __init xlated_setup_gnttab_pages(void) { diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 5d4de88..eeba754 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -1195,18 +1195,20 @@ static int gnttab_expand(unsigned int req_entries) int gnttab_init(void) { int i; + unsigned long max_nr_grant_frames; unsigned int max_nr_glist_frames, nr_glist_frames; unsigned int nr_init_grefs; int ret; gnttab_request_version(); + max_nr_grant_frames = gnttab_max_grant_frames(); nr_grant_frames = 1; /* Determine the maximum number of frames required for the * grant reference free list on the current hypervisor. */ BUG_ON(grefs_per_grant_frame == 0); - max_nr_glist_frames = (gnttab_max_grant_frames() * + max_nr_glist_frames = (max_nr_grant_frames * grefs_per_grant_frame / RPP); gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *), @@ -1223,6 +1225,11 @@ int gnttab_init(void) } } + ret = arch_gnttab_init(max_nr_grant_frames, + nr_status_frames(max_nr_grant_frames)); + if (ret < 0) + goto ini_nomem; + if (gnttab_setup() < 0) { ret = -ENODEV; goto ini_nomem; diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index a5af2a2..5c1aba1 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -170,6 +170,7 @@ gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, phys_addr_t addr, unmap->dev_bus_addr = 0; } +int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status); int arch_gnttab_map_shared(xen_pfn_t *frames, unsigned long nr_gframes, unsigned long max_nr_gframes, void **__shared); -- cgit v1.1 From 438b33c7145ca8a5131a30c36d8f59bce119a19a Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Wed, 2 Jul 2014 11:25:29 +0100 Subject: xen/grant-table: remove support for V2 tables Since 11c7ff17c9b6dbf3a4e4f36be30ad531a6cf0ec9 (xen/grant-table: Force to use v1 of grants.) the code for V2 grant tables is not used. Signed-off-by: David Vrabel Signed-off-by: Konrad Rzeszutek Wilk --- arch/arm/xen/grant-table.c | 9 +- arch/x86/xen/grant-table.c | 60 +-------- drivers/xen/grant-table.c | 309 +-------------------------------------------- include/xen/grant_table.h | 30 +---- 4 files changed, 13 insertions(+), 395 deletions(-) diff --git a/arch/arm/xen/grant-table.c b/arch/arm/xen/grant-table.c index 91cf08b..e437918 100644 --- a/arch/arm/xen/grant-table.c +++ b/arch/arm/xen/grant-table.c @@ -45,14 +45,7 @@ void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) return; } -int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, - unsigned long max_nr_gframes, - grant_status_t **__shared) -{ - return -ENOSYS; -} - -int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status) +int arch_gnttab_init(unsigned long nr_shared) { return 0; } diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index ebfa9b2..c041304 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -49,7 +49,7 @@ static struct gnttab_vm_area { struct vm_struct *area; pte_t **ptes; -} gnttab_shared_vm_area, gnttab_status_vm_area; +} gnttab_shared_vm_area; int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, unsigned long max_nr_gframes, @@ -73,43 +73,16 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, return 0; } -int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, - unsigned long max_nr_gframes, - grant_status_t **__shared) -{ - grant_status_t *shared = *__shared; - unsigned long addr; - unsigned long i; - - if (shared == NULL) - *__shared = shared = gnttab_status_vm_area.area->addr; - - addr = (unsigned long)shared; - - for (i = 0; i < nr_gframes; i++) { - set_pte_at(&init_mm, addr, gnttab_status_vm_area.ptes[i], - mfn_pte(frames[i], PAGE_KERNEL)); - addr += PAGE_SIZE; - } - - return 0; -} - void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) { - pte_t **ptes; unsigned long addr; unsigned long i; - if (shared == gnttab_status_vm_area.area->addr) - ptes = gnttab_status_vm_area.ptes; - else - ptes = gnttab_shared_vm_area.ptes; - addr = (unsigned long)shared; for (i = 0; i < nr_gframes; i++) { - set_pte_at(&init_mm, addr, ptes[i], __pte(0)); + set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i], + __pte(0)); addr += PAGE_SIZE; } } @@ -129,35 +102,12 @@ static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames) return 0; } -static void arch_gnttab_vfree(struct gnttab_vm_area *area) +int arch_gnttab_init(unsigned long nr_shared) { - free_vm_area(area->area); - kfree(area->ptes); -} - -int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status) -{ - int ret; - if (!xen_pv_domain()) return 0; - ret = arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared); - if (ret < 0) - return ret; - - /* - * Always allocate the space for the status frames in case - * we're migrated to a host with V2 support. - */ - ret = arch_gnttab_valloc(&gnttab_status_vm_area, nr_status); - if (ret < 0) - goto err; - - return 0; - err: - arch_gnttab_vfree(&gnttab_shared_vm_area); - return -ENOMEM; + return arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared); } #ifdef CONFIG_XEN_PVH diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index eeba754..c254ae0 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -69,7 +69,6 @@ struct grant_frames xen_auto_xlat_grant_frames; static union { struct grant_entry_v1 *v1; - union grant_entry_v2 *v2; void *addr; } gnttab_shared; @@ -120,36 +119,10 @@ struct gnttab_ops { * by bit operations. */ int (*query_foreign_access)(grant_ref_t ref); - /* - * Grant a domain to access a range of bytes within the page referred by - * an available grant entry. Ref parameter is reference of a grant entry - * which will be sub-page accessed, domid is id of grantee domain, frame - * is frame address of subpage grant, flags is grant type and flag - * information, page_off is offset of the range of bytes, and length is - * length of bytes to be accessed. - */ - void (*update_subpage_entry)(grant_ref_t ref, domid_t domid, - unsigned long frame, int flags, - unsigned page_off, unsigned length); - /* - * Redirect an available grant entry on domain A to another grant - * reference of domain B, then allow domain C to use grant reference - * of domain B transitively. Ref parameter is an available grant entry - * reference on domain A, domid is id of domain C which accesses grant - * entry transitively, flags is grant type and flag information, - * trans_domid is id of domain B whose grant entry is finally accessed - * transitively, trans_gref is grant entry transitive reference of - * domain B. - */ - void (*update_trans_entry)(grant_ref_t ref, domid_t domid, int flags, - domid_t trans_domid, grant_ref_t trans_gref); }; static struct gnttab_ops *gnttab_interface; -/*This reflects status of grant entries, so act as a global value*/ -static grant_status_t *grstatus; - static int grant_table_version; static int grefs_per_grant_frame; @@ -231,7 +204,7 @@ static void put_free_entry(grant_ref_t ref) } /* - * Following applies to gnttab_update_entry_v1 and gnttab_update_entry_v2. + * Following applies to gnttab_update_entry_v1. * Introducing a valid entry into the grant table: * 1. Write ent->domid. * 2. Write ent->frame: @@ -250,15 +223,6 @@ static void gnttab_update_entry_v1(grant_ref_t ref, domid_t domid, gnttab_shared.v1[ref].flags = flags; } -static void gnttab_update_entry_v2(grant_ref_t ref, domid_t domid, - unsigned long frame, unsigned flags) -{ - gnttab_shared.v2[ref].hdr.domid = domid; - gnttab_shared.v2[ref].full_page.frame = frame; - wmb(); - gnttab_shared.v2[ref].hdr.flags = GTF_permit_access | flags; -} - /* * Public grant-issuing interface functions */ @@ -285,132 +249,11 @@ int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, } EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access); -static void gnttab_update_subpage_entry_v2(grant_ref_t ref, domid_t domid, - unsigned long frame, int flags, - unsigned page_off, unsigned length) -{ - gnttab_shared.v2[ref].sub_page.frame = frame; - gnttab_shared.v2[ref].sub_page.page_off = page_off; - gnttab_shared.v2[ref].sub_page.length = length; - gnttab_shared.v2[ref].hdr.domid = domid; - wmb(); - gnttab_shared.v2[ref].hdr.flags = - GTF_permit_access | GTF_sub_page | flags; -} - -int gnttab_grant_foreign_access_subpage_ref(grant_ref_t ref, domid_t domid, - unsigned long frame, int flags, - unsigned page_off, - unsigned length) -{ - if (flags & (GTF_accept_transfer | GTF_reading | - GTF_writing | GTF_transitive)) - return -EPERM; - - if (gnttab_interface->update_subpage_entry == NULL) - return -ENOSYS; - - gnttab_interface->update_subpage_entry(ref, domid, frame, flags, - page_off, length); - - return 0; -} -EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_subpage_ref); - -int gnttab_grant_foreign_access_subpage(domid_t domid, unsigned long frame, - int flags, unsigned page_off, - unsigned length) -{ - int ref, rc; - - ref = get_free_entries(1); - if (unlikely(ref < 0)) - return -ENOSPC; - - rc = gnttab_grant_foreign_access_subpage_ref(ref, domid, frame, flags, - page_off, length); - if (rc < 0) { - put_free_entry(ref); - return rc; - } - - return ref; -} -EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_subpage); - -bool gnttab_subpage_grants_available(void) -{ - return gnttab_interface->update_subpage_entry != NULL; -} -EXPORT_SYMBOL_GPL(gnttab_subpage_grants_available); - -static void gnttab_update_trans_entry_v2(grant_ref_t ref, domid_t domid, - int flags, domid_t trans_domid, - grant_ref_t trans_gref) -{ - gnttab_shared.v2[ref].transitive.trans_domid = trans_domid; - gnttab_shared.v2[ref].transitive.gref = trans_gref; - gnttab_shared.v2[ref].hdr.domid = domid; - wmb(); - gnttab_shared.v2[ref].hdr.flags = - GTF_permit_access | GTF_transitive | flags; -} - -int gnttab_grant_foreign_access_trans_ref(grant_ref_t ref, domid_t domid, - int flags, domid_t trans_domid, - grant_ref_t trans_gref) -{ - if (flags & (GTF_accept_transfer | GTF_reading | - GTF_writing | GTF_sub_page)) - return -EPERM; - - if (gnttab_interface->update_trans_entry == NULL) - return -ENOSYS; - - gnttab_interface->update_trans_entry(ref, domid, flags, trans_domid, - trans_gref); - - return 0; -} -EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_trans_ref); - -int gnttab_grant_foreign_access_trans(domid_t domid, int flags, - domid_t trans_domid, - grant_ref_t trans_gref) -{ - int ref, rc; - - ref = get_free_entries(1); - if (unlikely(ref < 0)) - return -ENOSPC; - - rc = gnttab_grant_foreign_access_trans_ref(ref, domid, flags, - trans_domid, trans_gref); - if (rc < 0) { - put_free_entry(ref); - return rc; - } - - return ref; -} -EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_trans); - -bool gnttab_trans_grants_available(void) -{ - return gnttab_interface->update_trans_entry != NULL; -} -EXPORT_SYMBOL_GPL(gnttab_trans_grants_available); - static int gnttab_query_foreign_access_v1(grant_ref_t ref) { return gnttab_shared.v1[ref].flags & (GTF_reading|GTF_writing); } -static int gnttab_query_foreign_access_v2(grant_ref_t ref) -{ - return grstatus[ref] & (GTF_reading|GTF_writing); -} - int gnttab_query_foreign_access(grant_ref_t ref) { return gnttab_interface->query_foreign_access(ref); @@ -433,29 +276,6 @@ static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly) return 1; } -static int gnttab_end_foreign_access_ref_v2(grant_ref_t ref, int readonly) -{ - gnttab_shared.v2[ref].hdr.flags = 0; - mb(); - if (grstatus[ref] & (GTF_reading|GTF_writing)) { - return 0; - } else { - /* The read of grstatus needs to have acquire - semantics. On x86, reads already have - that, and we just need to protect against - compiler reorderings. On other - architectures we may need a full - barrier. */ -#ifdef CONFIG_X86 - barrier(); -#else - mb(); -#endif - } - - return 1; -} - static inline int _gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly) { return gnttab_interface->end_foreign_access_ref(ref, readonly); @@ -616,37 +436,6 @@ static unsigned long gnttab_end_foreign_transfer_ref_v1(grant_ref_t ref) return frame; } -static unsigned long gnttab_end_foreign_transfer_ref_v2(grant_ref_t ref) -{ - unsigned long frame; - u16 flags; - u16 *pflags; - - pflags = &gnttab_shared.v2[ref].hdr.flags; - - /* - * If a transfer is not even yet started, try to reclaim the grant - * reference and return failure (== 0). - */ - while (!((flags = *pflags) & GTF_transfer_committed)) { - if (sync_cmpxchg(pflags, flags, 0) == flags) - return 0; - cpu_relax(); - } - - /* If a transfer is in progress then wait until it is completed. */ - while (!(flags & GTF_transfer_completed)) { - flags = *pflags; - cpu_relax(); - } - - rmb(); /* Read the frame number /after/ reading completion status. */ - frame = gnttab_shared.v2[ref].full_page.frame; - BUG_ON(frame == 0); - - return frame; -} - unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref) { return gnttab_interface->end_foreign_transfer_ref(ref); @@ -962,12 +751,6 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, } EXPORT_SYMBOL_GPL(gnttab_unmap_refs); -static unsigned nr_status_frames(unsigned nr_grant_frames) -{ - BUG_ON(grefs_per_grant_frame == 0); - return (nr_grant_frames * grefs_per_grant_frame + SPP - 1) / SPP; -} - static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes) { int rc; @@ -985,55 +768,6 @@ static void gnttab_unmap_frames_v1(void) arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames); } -static int gnttab_map_frames_v2(xen_pfn_t *frames, unsigned int nr_gframes) -{ - uint64_t *sframes; - unsigned int nr_sframes; - struct gnttab_get_status_frames getframes; - int rc; - - nr_sframes = nr_status_frames(nr_gframes); - - /* No need for kzalloc as it is initialized in following hypercall - * GNTTABOP_get_status_frames. - */ - sframes = kmalloc(nr_sframes * sizeof(uint64_t), GFP_ATOMIC); - if (!sframes) - return -ENOMEM; - - getframes.dom = DOMID_SELF; - getframes.nr_frames = nr_sframes; - set_xen_guest_handle(getframes.frame_list, sframes); - - rc = HYPERVISOR_grant_table_op(GNTTABOP_get_status_frames, - &getframes, 1); - if (rc == -ENOSYS) { - kfree(sframes); - return -ENOSYS; - } - - BUG_ON(rc || getframes.status); - - rc = arch_gnttab_map_status(sframes, nr_sframes, - nr_status_frames(gnttab_max_grant_frames()), - &grstatus); - BUG_ON(rc); - kfree(sframes); - - rc = arch_gnttab_map_shared(frames, nr_gframes, - gnttab_max_grant_frames(), - &gnttab_shared.addr); - BUG_ON(rc); - - return 0; -} - -static void gnttab_unmap_frames_v2(void) -{ - arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames); - arch_gnttab_unmap(grstatus, nr_status_frames(nr_grant_frames)); -} - static int gnttab_map(unsigned int start_idx, unsigned int end_idx) { struct gnttab_setup_table setup; @@ -1101,43 +835,13 @@ static struct gnttab_ops gnttab_v1_ops = { .query_foreign_access = gnttab_query_foreign_access_v1, }; -static struct gnttab_ops gnttab_v2_ops = { - .map_frames = gnttab_map_frames_v2, - .unmap_frames = gnttab_unmap_frames_v2, - .update_entry = gnttab_update_entry_v2, - .end_foreign_access_ref = gnttab_end_foreign_access_ref_v2, - .end_foreign_transfer_ref = gnttab_end_foreign_transfer_ref_v2, - .query_foreign_access = gnttab_query_foreign_access_v2, - .update_subpage_entry = gnttab_update_subpage_entry_v2, - .update_trans_entry = gnttab_update_trans_entry_v2, -}; - static void gnttab_request_version(void) { - int rc; - struct gnttab_set_version gsv; + /* Only version 1 is used, which will always be available. */ + grant_table_version = 1; + grefs_per_grant_frame = PAGE_SIZE / sizeof(struct grant_entry_v1); + gnttab_interface = &gnttab_v1_ops; - gsv.version = 1; - - rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1); - if (rc == 0 && gsv.version == 2) { - grant_table_version = 2; - grefs_per_grant_frame = PAGE_SIZE / sizeof(union grant_entry_v2); - gnttab_interface = &gnttab_v2_ops; - } else if (grant_table_version == 2) { - /* - * If we've already used version 2 features, - * but then suddenly discover that they're not - * available (e.g. migrating to an older - * version of Xen), almost unbounded badness - * can happen. - */ - panic("we need grant tables version 2, but only version 1 is available"); - } else { - grant_table_version = 1; - grefs_per_grant_frame = PAGE_SIZE / sizeof(struct grant_entry_v1); - gnttab_interface = &gnttab_v1_ops; - } pr_info("Grant tables using version %d layout\n", grant_table_version); } @@ -1225,8 +929,7 @@ int gnttab_init(void) } } - ret = arch_gnttab_init(max_nr_grant_frames, - nr_status_frames(max_nr_grant_frames)); + ret = arch_gnttab_init(max_nr_grant_frames); if (ret < 0) goto ini_nomem; diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 5c1aba1..3387465 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -64,24 +64,6 @@ int gnttab_resume(void); int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, int readonly); -int gnttab_grant_foreign_access_subpage(domid_t domid, unsigned long frame, - int flags, unsigned page_off, - unsigned length); -int gnttab_grant_foreign_access_trans(domid_t domid, int flags, - domid_t trans_domid, - grant_ref_t trans_gref); - -/* - * Are sub-page grants available on this version of Xen? Returns true if they - * are, and false if they're not. - */ -bool gnttab_subpage_grants_available(void); - -/* - * Are transitive grants available on this version of Xen? Returns true if they - * are, and false if they're not. - */ -bool gnttab_trans_grants_available(void); /* * End access through the given grant reference, iff the grant entry is no @@ -128,13 +110,6 @@ void gnttab_cancel_free_callback(struct gnttab_free_callback *callback); void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, unsigned long frame, int readonly); -int gnttab_grant_foreign_access_subpage_ref(grant_ref_t ref, domid_t domid, - unsigned long frame, int flags, - unsigned page_off, - unsigned length); -int gnttab_grant_foreign_access_trans_ref(grant_ref_t ref, domid_t domid, - int flags, domid_t trans_domid, - grant_ref_t trans_gref); void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid, unsigned long pfn); @@ -170,13 +145,10 @@ gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, phys_addr_t addr, unmap->dev_bus_addr = 0; } -int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status); +int arch_gnttab_init(unsigned long nr_shared); int arch_gnttab_map_shared(xen_pfn_t *frames, unsigned long nr_gframes, unsigned long max_nr_gframes, void **__shared); -int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, - unsigned long max_nr_gframes, - grant_status_t **__shared); void arch_gnttab_unmap(void *shared, unsigned long nr_gframes); struct grant_frames { -- cgit v1.1 From a91c7775e3469821711c1eadf15149b3ba2c82c9 Mon Sep 17 00:00:00 2001 From: Himangi Saraogi Date: Fri, 25 Jul 2014 12:05:39 -0400 Subject: xen/arm: use BUG_ON Use BUG_ON(x) rather than if(x) BUG(); The semantic patch that fixes this problem is as follows: // @@ identifier x; @@ -if (x) BUG(); +BUG_ON(x); // Signed-off-by: Himangi Saraogi Signed-off-by: Konrad Rzeszutek Wilk Acked-by: Stefano Stabellini --- arch/arm/xen/enlighten.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 1e63243..98544c5 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -181,8 +181,7 @@ static void xen_restart(enum reboot_mode reboot_mode, const char *cmd) struct sched_shutdown r = { .reason = SHUTDOWN_reboot }; int rc; rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); - if (rc) - BUG(); + BUG_ON(rc); } static void xen_power_off(void) @@ -190,8 +189,7 @@ static void xen_power_off(void) struct sched_shutdown r = { .reason = SHUTDOWN_poweroff }; int rc; rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); - if (rc) - BUG(); + BUG_ON(rc); } static int xen_cpu_notification(struct notifier_block *self, -- cgit v1.1 From c12784c3d14a2110468ec4d1383f60cfd2665576 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Thu, 31 Jul 2014 16:22:24 +0100 Subject: xen/events/fifo: reset control block and local HEADs on resume When using the FIFO-based event channel ABI, if the control block or the local HEADs are not reset after resuming the guest may see stale HEAD values and will fail to traverse the FIFO correctly. This may prevent one or more VCPUs from receiving any events following a resume. Signed-off-by: David Vrabel Reviewed-by: Boris Ostrovsky Cc: stable@vger.kernel.org --- drivers/xen/events/events_fifo.c | 48 +++++++++++++++++++++++----------------- 1 file changed, 28 insertions(+), 20 deletions(-) diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 84b4bfb..c7ff203 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -100,6 +100,25 @@ static unsigned evtchn_fifo_nr_channels(void) return event_array_pages * EVENT_WORDS_PER_PAGE; } +static int init_control_block(int cpu, + struct evtchn_fifo_control_block *control_block) +{ + struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); + struct evtchn_init_control init_control; + unsigned int i; + + /* Reset the control block and the local HEADs. */ + clear_page(control_block); + for (i = 0; i < EVTCHN_FIFO_MAX_QUEUES; i++) + q->head[i] = 0; + + init_control.control_gfn = virt_to_mfn(control_block); + init_control.offset = 0; + init_control.vcpu = cpu; + + return HYPERVISOR_event_channel_op(EVTCHNOP_init_control, &init_control); +} + static void free_unused_array_pages(void) { unsigned i; @@ -324,7 +343,6 @@ static void evtchn_fifo_resume(void) for_each_possible_cpu(cpu) { void *control_block = per_cpu(cpu_control_block, cpu); - struct evtchn_init_control init_control; int ret; if (!control_block) @@ -341,12 +359,7 @@ static void evtchn_fifo_resume(void) continue; } - init_control.control_gfn = virt_to_mfn(control_block); - init_control.offset = 0; - init_control.vcpu = cpu; - - ret = HYPERVISOR_event_channel_op(EVTCHNOP_init_control, - &init_control); + ret = init_control_block(cpu, control_block); if (ret < 0) BUG(); } @@ -374,30 +387,25 @@ static const struct evtchn_ops evtchn_ops_fifo = { .resume = evtchn_fifo_resume, }; -static int evtchn_fifo_init_control_block(unsigned cpu) +static int evtchn_fifo_alloc_control_block(unsigned cpu) { - struct page *control_block = NULL; - struct evtchn_init_control init_control; + void *control_block = NULL; int ret = -ENOMEM; - control_block = alloc_page(GFP_KERNEL|__GFP_ZERO); + control_block = (void *)__get_free_page(GFP_KERNEL); if (control_block == NULL) goto error; - init_control.control_gfn = virt_to_mfn(page_address(control_block)); - init_control.offset = 0; - init_control.vcpu = cpu; - - ret = HYPERVISOR_event_channel_op(EVTCHNOP_init_control, &init_control); + ret = init_control_block(cpu, control_block); if (ret < 0) goto error; - per_cpu(cpu_control_block, cpu) = page_address(control_block); + per_cpu(cpu_control_block, cpu) = control_block; return 0; error: - __free_page(control_block); + free_page((unsigned long)control_block); return ret; } @@ -411,7 +419,7 @@ static int evtchn_fifo_cpu_notification(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: if (!per_cpu(cpu_control_block, cpu)) - ret = evtchn_fifo_init_control_block(cpu); + ret = evtchn_fifo_alloc_control_block(cpu); break; default: break; @@ -428,7 +436,7 @@ int __init xen_evtchn_fifo_init(void) int cpu = get_cpu(); int ret; - ret = evtchn_fifo_init_control_block(cpu); + ret = evtchn_fifo_alloc_control_block(cpu); if (ret < 0) goto out; -- cgit v1.1 From dcecb8fd93a65787130a74e61fdf29932c8d85eb Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Thu, 31 Jul 2014 16:22:25 +0100 Subject: xen/events/fifo: ensure all bitops are properly aligned even on x86 When using the FIFO-based ABI on x86_64, if the last port is at the end of an event array page then sync_test_bit() on this port's event word will read beyond the end of the page and in certain circumstances this may fault. The fault requires the following page in the kernel's direct mapping to be not present, which would mean: a) the array page is the last page of RAM; or b) the following page is ballooned out /and/ it has been used for a foreign mapping by a kernel driver (such as netback or blkback) /and/ the grant has been unmapped. Use the infrastructure added for arm64 to ensure that all bitops operating on event words are unsigned long aligned. Signed-off-by: David Vrabel Reviewed-by: Boris Ostrovsky Cc: stable@vger.kernel.org --- drivers/xen/events/events_fifo.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index c7ff203..48dcb2e 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -67,10 +67,9 @@ static event_word_t *event_array[MAX_EVENT_ARRAY_PAGES] __read_mostly; static unsigned event_array_pages __read_mostly; /* - * sync_set_bit() and friends must be unsigned long aligned on non-x86 - * platforms. + * sync_set_bit() and friends must be unsigned long aligned. */ -#if !defined(CONFIG_X86) && BITS_PER_LONG > 32 +#if BITS_PER_LONG > 32 #define BM(w) (unsigned long *)((unsigned long)w & ~0x7UL) #define EVTCHN_FIFO_BIT(b, w) \ -- cgit v1.1 From e4a7431240e0e4230bb4e2e05ccf413325a60e88 Mon Sep 17 00:00:00 2001 From: Frediano Ziglio Date: Thu, 31 Jul 2014 16:22:26 +0100 Subject: xen/events/fifo: remove a unecessary use of BM() Since 05a812ac474d0d6aef6d54b66bb08b81abde79c6 (xen/events/fifo: correctly align bitops), ready is an unsigned long instead of uint32_t and the BM() macro is no longer required. Signed-off-by: Frediano Ziglio Signed-off-by: David Vrabel Reviewed-by: Boris Ostrovsky --- drivers/xen/events/events_fifo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 48dcb2e..417415d 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -330,7 +330,7 @@ static void evtchn_fifo_handle_events(unsigned cpu) ready = xchg(&control_block->ready, 0); while (ready) { - q = find_first_bit(BM(&ready), EVTCHN_FIFO_MAX_QUEUES); + q = find_first_bit(&ready, EVTCHN_FIFO_MAX_QUEUES); consume_one_event(cpu, control_block, q, &ready); ready |= xchg(&control_block->ready, 0); } -- cgit v1.1 From 3fbdf631b765571b18ee51e073d8f46958e98ceb Mon Sep 17 00:00:00 2001 From: Matt Rushton Date: Sat, 19 Jul 2014 17:01:34 -0700 Subject: xen/setup: Remove Identity Map Debug Message Removing a debug message for setting the identity map since it becomes rather noisy after rework of the identity map code. Signed-off-by: Matthew Rushton Signed-off-by: David Vrabel --- arch/x86/xen/p2m.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 9bb3d82..3172692 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -841,10 +841,9 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s, pfn = ALIGN(pfn, P2M_PER_PAGE); } - if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s), + WARN((pfn - pfn_s) != (pfn_e - pfn_s), "Identity mapping failed. We are %ld short of 1-1 mappings!\n", - (pfn_e - pfn_s) - (pfn - pfn_s))) - printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn); + (pfn_e - pfn_s) - (pfn - pfn_s)); return pfn - pfn_s; } -- cgit v1.1 From 474b8feafb5013130d625898139b56fa54e6c9f2 Mon Sep 17 00:00:00 2001 From: Andrey Utkin Date: Thu, 17 Jul 2014 19:25:50 +0300 Subject: xen/events: drop negativity check of unsigned parameter Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=80531 Reported-by: David Binderman Signed-off-by: Andrey Utkin Signed-off-by: David Vrabel --- drivers/xen/events/events_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index c919d3d..5b5c5ff 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -246,7 +246,7 @@ static void xen_irq_info_cleanup(struct irq_info *info) */ unsigned int evtchn_from_irq(unsigned irq) { - if (unlikely(WARN(irq < 0 || irq >= nr_irqs, "Invalid irq %d!\n", irq))) + if (unlikely(WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq))) return 0; return info_for_irq(irq)->evtchn; -- cgit v1.1 From 2ef760323a8a7ced5e1b2286c8df95226606a64e Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sun, 20 Jul 2014 13:46:01 +0800 Subject: xen/pciback: Fix error return code in xen_pcibk_attach() Fix to return -EFAULT from the error handling case instead of 0 when version mismatch with pcifront. Signed-off-by: Wei Yongjun Reviewed-by Jan Beulich Signed-off-by: David Vrabel --- drivers/xen/xen-pciback/xenbus.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index 4a7e6e0..c214daa 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -174,6 +174,7 @@ static int xen_pcibk_attach(struct xen_pcibk_device *pdev) "version mismatch (%s/%s) with pcifront - " "halting " DRV_NAME, magic, XEN_PCI_MAGIC); + err = -EFAULT; goto out; } -- cgit v1.1 From 8b63c998b31c69fff2c8c8c7e543e3142d9eea71 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Mon, 14 Jul 2014 12:18:51 -0400 Subject: xen-pciback: Document the 'quirks' sysfs file Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: David Vrabel --- Documentation/ABI/testing/sysfs-driver-pciback | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-driver-pciback diff --git a/Documentation/ABI/testing/sysfs-driver-pciback b/Documentation/ABI/testing/sysfs-driver-pciback new file mode 100644 index 0000000..6a733bf --- /dev/null +++ b/Documentation/ABI/testing/sysfs-driver-pciback @@ -0,0 +1,13 @@ +What: /sys/bus/pci/drivers/pciback/quirks +Date: Oct 2011 +KernelVersion: 3.1 +Contact: xen-devel@lists.xenproject.org +Description: + If the permissive attribute is set, then writing a string in + the format of DDDD:BB:DD.F-REG:SIZE:MASK will allow the guest + to write and read from the PCI device. That is Domain:Bus: + Device.Function-Register:Size:Mask (Domain is optional). + For example: + #echo 00:19.0-E0:2:FF > /sys/bus/pci/drivers/pciback/quirks + will allow the guest to read and write to the configuration + register 0x0E. -- cgit v1.1