From 598ddb8cf3329d299746d6704d8df97f397906b6 Mon Sep 17 00:00:00 2001 From: Rashika Kheria Date: Sun, 9 Feb 2014 16:29:30 +0530 Subject: [PATCH 01/11] drivers: xen: Mark function as static in platform-pci.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mark function as static in xen/platform-pci.c because it is not used outside this file. This eliminates the following warning in xen/platform-pci.c: drivers/xen/platform-pci.c:48:15: warning: no previous prototype for ‘alloc_xen_mmio’ [-Wmissing-prototypes] Signed-off-by: Rashika Kheria Reviewed-by: Josh Triplett Signed-off-by: Konrad Rzeszutek Wilk Reviewed-by: David Vrabel --- drivers/xen/platform-pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index a1361c312c06..3454973dc3bb 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -45,7 +45,7 @@ static unsigned long platform_mmio_alloc; static unsigned long platform_mmiolen; static uint64_t callback_via; -unsigned long alloc_xen_mmio(unsigned long len) +static unsigned long alloc_xen_mmio(unsigned long len) { unsigned long addr; From 6cb606f102e45ea7c42cf3d812883489ba99ce5a Mon Sep 17 00:00:00 2001 From: Rashika Kheria Date: Sun, 9 Feb 2014 16:31:46 +0530 Subject: [PATCH 02/11] drivers: xen: Include appropriate header file in pcpu.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Include appropriate header file in xen/pcpu.c because include/xen/acpi.h contains prototype declaration of functions defined in the file. This eliminates the following warning in xen/pcpu.c: drivers/xen/pcpu.c:336:6: warning: no previous prototype for ‘xen_pcpu_hotplug_sync’ [-Wmissing-prototypes] drivers/xen/pcpu.c:346:5: warning: no previous prototype for ‘xen_pcpu_id’ [-Wmissing-prototypes] Signed-off-by: Rashika Kheria Reviewed-by: Josh Triplett Signed-off-by: Konrad Rzeszutek Wilk Reviewed-by: David Vrabel --- drivers/xen/pcpu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index 79e1dff7ed4f..0aac403d53fd 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -40,6 +40,7 @@ #include #include +#include #include #include #include From d4c7abdff73090a98e64d11dada4911ec29bcaea Mon Sep 17 00:00:00 2001 From: Bob Liu Date: Mon, 17 Feb 2014 19:11:39 +0800 Subject: [PATCH 03/11] drivers:xen-selfballoon:reset 'frontswap_inertia_counter' after frontswap_shrink When I looked at this issue https://lkml.org/lkml/2013/11/21/158, I found that frontswap_selfshrink() doesn't work as expected sometimes. Pages are continuously added to frontswap and gotten back soon. It's a waste of cpu time and increases the memory pressue of Guest OS. Take an example. First time in frontswap_selfshrink(): 1. last_frontswap_pages = cur_frontswap_pages = 0 2. cur_frontswap_pages = frontswap_curr_pages() = 100 When 'frontswap_inertia_counter' decreased to 0: 1. last_frontswap_pages = cur_frontswap_pages = 100 2. cur_frontswap_pages = frontswap_curr_pages() = 100 3. call frontswap_shrink() and let's assumption that 10 pages are gotten back from frontswap. 4. now frontswap_curr_pages() is 90. If then memory is not enough in Guest OS and 9 more pages(smaller than gotten back) added to frontswap. Now frontswap_curr_pages() is 99 and we don't expect to get back more pages from frontswap because geust os is under memory pressure. But next time in frontswap_selfshrink(): 1. last_frontswap_pages is set to the old value of cur_frontswap_pages(still 100) 2. cur_frontswap_pages(99) is still smaller than last_frontswap_pages. 3. call frontswap_shrink() and continue to get back pages from frontswap!! Signed-off-by: Bob Liu Signed-off-by: Konrad Rzeszutek Wilk --- drivers/xen/xen-selfballoon.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c index 745ad79c1d8e..3b2bffde534f 100644 --- a/drivers/xen/xen-selfballoon.c +++ b/drivers/xen/xen-selfballoon.c @@ -170,6 +170,7 @@ static void frontswap_selfshrink(void) tgt_frontswap_pages = cur_frontswap_pages - (cur_frontswap_pages / frontswap_hysteresis); frontswap_shrink(tgt_frontswap_pages); + frontswap_inertia_counter = frontswap_inertia; } #endif /* CONFIG_FRONTSWAP */ From 4640ddf5efe71c1338cbb76e73278cfdbcd6426f Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Mon, 17 Feb 2014 17:45:16 +0000 Subject: [PATCH 04/11] xen/events: remove the unused resend_irq_on_evtchn() resend_irq_on_evtchn() was only used by ia64 (which no longer has Xen support). Signed-off-by: David Vrabel Signed-off-by: Konrad Rzeszutek Wilk Reviewed-by: Boris Ostrovsky --- drivers/xen/events/events_base.c | 33 ++++++++++++-------------------- include/xen/events.h | 1 - 2 files changed, 12 insertions(+), 22 deletions(-) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index f4a9e3311297..dca101ab1747 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -1344,26 +1344,6 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest, return rebind_irq_to_cpu(data->irq, tcpu); } -static int retrigger_evtchn(int evtchn) -{ - int masked; - - if (!VALID_EVTCHN(evtchn)) - return 0; - - masked = test_and_set_mask(evtchn); - set_evtchn(evtchn); - if (!masked) - unmask_evtchn(evtchn); - - return 1; -} - -int resend_irq_on_evtchn(unsigned int irq) -{ - return retrigger_evtchn(evtchn_from_irq(irq)); -} - static void enable_dynirq(struct irq_data *data) { int evtchn = evtchn_from_irq(data->irq); @@ -1398,7 +1378,18 @@ static void mask_ack_dynirq(struct irq_data *data) static int retrigger_dynirq(struct irq_data *data) { - return retrigger_evtchn(evtchn_from_irq(data->irq)); + unsigned int evtchn = evtchn_from_irq(data->irq); + int masked; + + if (!VALID_EVTCHN(evtchn)) + return 0; + + masked = test_and_set_mask(evtchn); + set_evtchn(evtchn); + if (!masked) + unmask_evtchn(evtchn); + + return 1; } static void restore_pirqs(void) diff --git a/include/xen/events.h b/include/xen/events.h index c9c85cf84895..a6d92378354c 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -52,7 +52,6 @@ int evtchn_get(unsigned int evtchn); void evtchn_put(unsigned int evtchn); void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector); -int resend_irq_on_evtchn(unsigned int irq); void rebind_evtchn_irq(int evtchn, int irq); static inline void notify_remote_via_evtchn(int port) From 4201cdbd6cde19a69b862984ef674ce667d526e1 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Mon, 17 Feb 2014 17:45:17 +0000 Subject: [PATCH 05/11] xen/events: remove unnecessary call to bind_evtchn_to_cpu() Since bind_evtchn_to_cpu() is always called after an event channel is bound, there is no need to call it after closing an event channel. Signed-off-by: David Vrabel Signed-off-by: Konrad Rzeszutek Wilk Reviewed-by: Boris Ostrovsky --- drivers/xen/events/events_base.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index dca101ab1747..9875d6ec1063 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -469,9 +469,6 @@ static void xen_evtchn_close(unsigned int port) close.port = port; if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0) BUG(); - - /* Closed ports are implicitly re-bound to VCPU0. */ - bind_evtchn_to_cpu(port, 0); } static void pirq_query_unmask(int irq) From c06f8111792bd35f831c1dc7dbec536d6ba204ac Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Mon, 17 Feb 2014 17:45:18 +0000 Subject: [PATCH 06/11] xen/xenbus: remove unused xenbus_bind_evtchn() xenbus_bind_evtchn() has no callers so remove it. Signed-off-by: David Vrabel Signed-off-by: Konrad Rzeszutek Wilk Reviewed-by: Boris Ostrovsky --- drivers/xen/xenbus/xenbus_client.c | 27 --------------------------- include/xen/xenbus.h | 1 - 2 files changed, 28 deletions(-) diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 01d59e66565d..439c9dca9eee 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -400,33 +400,6 @@ int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port) EXPORT_SYMBOL_GPL(xenbus_alloc_evtchn); -/** - * Bind to an existing interdomain event channel in another domain. Returns 0 - * on success and stores the local port in *port. On error, returns -errno, - * switches the device to XenbusStateClosing, and saves the error in XenStore. - */ -int xenbus_bind_evtchn(struct xenbus_device *dev, int remote_port, int *port) -{ - struct evtchn_bind_interdomain bind_interdomain; - int err; - - bind_interdomain.remote_dom = dev->otherend_id; - bind_interdomain.remote_port = remote_port; - - err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain, - &bind_interdomain); - if (err) - xenbus_dev_fatal(dev, err, - "binding to event channel %d from domain %d", - remote_port, dev->otherend_id); - else - *port = bind_interdomain.local_port; - - return err; -} -EXPORT_SYMBOL_GPL(xenbus_bind_evtchn); - - /** * Free an existing event channel. Returns 0 on success or -errno on error. */ diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index 569c07f2e344..0324c6d340c1 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -207,7 +207,6 @@ int xenbus_unmap_ring(struct xenbus_device *dev, grant_handle_t handle, void *vaddr); int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port); -int xenbus_bind_evtchn(struct xenbus_device *dev, int remote_port, int *port); int xenbus_free_evtchn(struct xenbus_device *dev, int port); enum xenbus_state xenbus_read_driver_state(const char *path); From efdfa3eda5d7b33c6e3c4f6e66144fcd10ed41a3 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Fri, 21 Feb 2014 17:53:40 +0100 Subject: [PATCH 07/11] xen-pciback: Use pci_enable_msix_exact() instead of pci_enable_msix() As result of deprecation of MSI-X/MSI enablement functions pci_enable_msix() and pci_enable_msi_block() all drivers using these two interfaces need to be updated to use the new pci_enable_msi_range() or pci_enable_msi_exact() and pci_enable_msix_range() or pci_enable_msix_exact() interfaces. Signed-off-by: Alexander Gordeev Cc: Konrad Rzeszutek Wilk Cc: Boris Ostrovsky Cc: David Vrabel Cc: linux-pci@vger.kernel.org Signed-off-by: Konrad Rzeszutek Wilk Reviewed-by: Boris Ostrovsky --- drivers/xen/xen-pciback/pciback_ops.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 64eb0cd8b8af..929dd46bb40c 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -213,8 +213,7 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev, entries[i].vector = op->msix_entries[i].vector; } - result = pci_enable_msix(dev, entries, op->value); - + result = pci_enable_msix_exact(dev, entries, op->value); if (result == 0) { for (i = 0; i < op->value; i++) { op->msix_entries[i].entry = entries[i].entry; From 4892c9b4ada9f9a71a0da7a268f95e988d88064b Mon Sep 17 00:00:00 2001 From: Roger Pau Monne Date: Thu, 27 Feb 2014 19:15:35 +0100 Subject: [PATCH 08/11] xen: add support for MSI message groups MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for MSI message groups for Xen Dom0 using the MAP_PIRQ_TYPE_MULTI_MSI pirq map type. In order to keep track of which pirq is the first one in the group all pirqs in the MSI group except for the first one have the newly introduced PIRQ_MSI_GROUP flag set. This prevents calling PHYSDEVOP_unmap_pirq on them, since the unmap must be done with the first pirq in the group. Signed-off-by: Roger Pau Monné Signed-off-by: David Vrabel Cc: Boris Ostrovsky --- arch/x86/pci/xen.c | 29 +++++++++++------ drivers/xen/events/events_base.c | 47 +++++++++++++++++++--------- drivers/xen/events/events_internal.h | 1 + include/xen/events.h | 5 ++- include/xen/interface/physdev.h | 10 ++++-- 5 files changed, 65 insertions(+), 27 deletions(-) diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 103e702ec5a7..905956f16465 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -178,6 +178,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) i = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], + (type == PCI_CAP_ID_MSI) ? nvec : 1, (type == PCI_CAP_ID_MSIX) ? "pcifront-msi-x" : "pcifront-msi", @@ -245,6 +246,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) "xen: msi already bound to pirq=%d\n", pirq); } irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, + (type == PCI_CAP_ID_MSI) ? nvec : 1, (type == PCI_CAP_ID_MSIX) ? "msi-x" : "msi", DOMID_SELF); @@ -269,9 +271,6 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) int ret = 0; struct msi_desc *msidesc; - if (type == PCI_CAP_ID_MSI && nvec > 1) - return 1; - list_for_each_entry(msidesc, &dev->msi_list, list) { struct physdev_map_pirq map_irq; domid_t domid; @@ -291,7 +290,10 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) (pci_domain_nr(dev->bus) << 16); map_irq.devfn = dev->devfn; - if (type == PCI_CAP_ID_MSIX) { + if (type == PCI_CAP_ID_MSI && nvec > 1) { + map_irq.type = MAP_PIRQ_TYPE_MULTI_MSI; + map_irq.entry_nr = nvec; + } else if (type == PCI_CAP_ID_MSIX) { int pos; u32 table_offset, bir; @@ -308,6 +310,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (pci_seg_supported) ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); + if (type == PCI_CAP_ID_MSI && nvec > 1 && ret) { + /* + * If MAP_PIRQ_TYPE_MULTI_MSI is not available + * there's nothing else we can do in this case. + * Just set ret > 0 so driver can retry with + * single MSI. + */ + ret = 1; + goto out; + } if (ret == -EINVAL && !pci_domain_nr(dev->bus)) { map_irq.type = MAP_PIRQ_TYPE_MSI; map_irq.index = -1; @@ -324,11 +336,10 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) goto out; } - ret = xen_bind_pirq_msi_to_irq(dev, msidesc, - map_irq.pirq, - (type == PCI_CAP_ID_MSIX) ? - "msi-x" : "msi", - domid); + ret = xen_bind_pirq_msi_to_irq(dev, msidesc, map_irq.pirq, + (type == PCI_CAP_ID_MSI) ? nvec : 1, + (type == PCI_CAP_ID_MSIX) ? "msi-x" : "msi", + domid); if (ret < 0) goto out; } diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 9875d6ec1063..793053065629 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -391,10 +391,10 @@ static void xen_irq_init(unsigned irq) list_add_tail(&info->list, &xen_irq_list_head); } -static int __must_check xen_allocate_irq_dynamic(void) +static int __must_check xen_allocate_irqs_dynamic(int nvec) { int first = 0; - int irq; + int i, irq; #ifdef CONFIG_X86_IO_APIC /* @@ -408,14 +408,22 @@ static int __must_check xen_allocate_irq_dynamic(void) first = get_nr_irqs_gsi(); #endif - irq = irq_alloc_desc_from(first, -1); + irq = irq_alloc_descs_from(first, nvec, -1); - if (irq >= 0) - xen_irq_init(irq); + if (irq >= 0) { + for (i = 0; i < nvec; i++) + xen_irq_init(irq + i); + } return irq; } +static inline int __must_check xen_allocate_irq_dynamic(void) +{ + + return xen_allocate_irqs_dynamic(1); +} + static int __must_check xen_allocate_irq_gsi(unsigned gsi) { int irq; @@ -738,22 +746,25 @@ int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc) } int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, - int pirq, const char *name, domid_t domid) + int pirq, int nvec, const char *name, domid_t domid) { - int irq, ret; + int i, irq, ret; mutex_lock(&irq_mapping_update_lock); - irq = xen_allocate_irq_dynamic(); + irq = xen_allocate_irqs_dynamic(nvec); if (irq < 0) goto out; - irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq, - name); + for (i = 0; i < nvec; i++) { + irq_set_chip_and_handler_name(irq + i, &xen_pirq_chip, handle_edge_irq, name); + + ret = xen_irq_info_pirq_setup(irq + i, 0, pirq + i, 0, domid, + i == 0 ? 0 : PIRQ_MSI_GROUP); + if (ret < 0) + goto error_irq; + } - ret = xen_irq_info_pirq_setup(irq, 0, pirq, 0, domid, 0); - if (ret < 0) - goto error_irq; ret = irq_set_msi_desc(irq, msidesc); if (ret < 0) goto error_irq; @@ -761,7 +772,8 @@ out: mutex_unlock(&irq_mapping_update_lock); return irq; error_irq: - __unbind_from_irq(irq); + for (; i >= 0; i--) + __unbind_from_irq(irq + i); mutex_unlock(&irq_mapping_update_lock); return ret; } @@ -780,7 +792,12 @@ int xen_destroy_irq(int irq) if (!desc) goto out; - if (xen_initial_domain()) { + /* + * If trying to remove a vector in a MSI group different + * than the first one skip the PIRQ unmap unless this vector + * is the first one in the group. + */ + if (xen_initial_domain() && !(info->u.pirq.flags & PIRQ_MSI_GROUP)) { unmap_irq.pirq = info->u.pirq.pirq; unmap_irq.domid = info->u.pirq.domid; rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq); diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h index 677f41a0fff9..50c2050a1e32 100644 --- a/drivers/xen/events/events_internal.h +++ b/drivers/xen/events/events_internal.h @@ -53,6 +53,7 @@ struct irq_info { #define PIRQ_NEEDS_EOI (1 << 0) #define PIRQ_SHAREABLE (1 << 1) +#define PIRQ_MSI_GROUP (1 << 2) struct evtchn_ops { unsigned (*max_channels)(void); diff --git a/include/xen/events.h b/include/xen/events.h index a6d92378354c..8bee7a75e850 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -2,6 +2,9 @@ #define _XEN_EVENTS_H #include +#ifdef CONFIG_PCI_MSI +#include +#endif #include #include @@ -101,7 +104,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi, int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc); /* Bind an PSI pirq to an irq. */ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, - int pirq, const char *name, domid_t domid); + int pirq, int nvec, const char *name, domid_t domid); #endif /* De-allocates the above mentioned physical interrupt. */ diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h index 42721d13a106..610dba9b620a 100644 --- a/include/xen/interface/physdev.h +++ b/include/xen/interface/physdev.h @@ -131,6 +131,7 @@ struct physdev_irq { #define MAP_PIRQ_TYPE_GSI 0x1 #define MAP_PIRQ_TYPE_UNKNOWN 0x2 #define MAP_PIRQ_TYPE_MSI_SEG 0x3 +#define MAP_PIRQ_TYPE_MULTI_MSI 0x4 #define PHYSDEVOP_map_pirq 13 struct physdev_map_pirq { @@ -141,11 +142,16 @@ struct physdev_map_pirq { int index; /* IN or OUT */ int pirq; - /* IN - high 16 bits hold segment for MAP_PIRQ_TYPE_MSI_SEG */ + /* IN - high 16 bits hold segment for ..._MSI_SEG and ..._MULTI_MSI */ int bus; /* IN */ int devfn; - /* IN */ + /* IN + * - For MSI-X contains entry number. + * - For MSI with ..._MULTI_MSI contains number of vectors. + * OUT (..._MULTI_MSI only) + * - Number of vectors allocated. + */ int entry_nr; /* IN */ uint64_t table_base; From 395edbb80b049884df075be54ef46cc742c3e266 Mon Sep 17 00:00:00 2001 From: Michael Opdenacker Date: Tue, 18 Feb 2014 14:07:41 +0100 Subject: [PATCH 09/11] xen: remove XEN_PRIVILEGED_GUEST This patch removes the Kconfig symbol XEN_PRIVILEGED_GUEST which is used nowhere in the tree. We do know grub2 has a script that greps kernel configuration files for its macro. It shouldn't do that. As Linus summarized: This is a grub bug. It really is that simple. Treat it as one. Besides, grub2's grepping for that macro is actually superfluous. See, that script currently contains this test (simplified): grep -x CONFIG_XEN_DOM0=y $config || grep -x CONFIG_XEN_PRIVILEGED_GUEST=y $config But since XEN_DOM0 and XEN_PRIVILEGED_GUEST are by definition equal, removing XEN_PRIVILEGED_GUEST cannot influence this test. So there's no reason to not remove this symbol, like we do with all unused Kconfig symbols. [pebolle@tiscali.nl: rewrote commit explanation.] Signed-off-by: Michael Opdenacker Signed-off-by: Paul Bolle Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/Kconfig | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 01b90261fa38..512219d89560 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -19,11 +19,6 @@ config XEN_DOM0 depends on XEN && PCI_XEN && SWIOTLB_XEN depends on X86_LOCAL_APIC && X86_IO_APIC && ACPI && PCI -# Dummy symbol since people have come to rely on the PRIVILEGED_GUEST -# name in tools. -config XEN_PRIVILEGED_GUEST - def_bool XEN_DOM0 - config XEN_PVHVM def_bool y depends on XEN && PCI && X86_LOCAL_APIC From 1429d46df4c538d28460d0b493997006a62a1093 Mon Sep 17 00:00:00 2001 From: Zoltan Kiss Date: Thu, 27 Feb 2014 15:55:30 +0000 Subject: [PATCH 10/11] xen/grant-table: Refactor gnttab_[un]map_refs to avoid m2p_override The grant mapping API does m2p_override unnecessarily: only gntdev needs it, for blkback and future netback patches it just cause a lock contention, as those pages never go to userspace. Therefore this series does the following: - the bulk of the original function (everything after the mapping hypercall) is moved to arch-dependent set/clear_foreign_p2m_mapping - the "if (xen_feature(XENFEAT_auto_translated_physmap))" branch goes to ARM - therefore the ARM function could be much smaller, the m2p_override stubs could be also removed - on x86 the set_phys_to_machine calls were moved up to this new funcion from m2p_override functions - and m2p_override functions are only called when there is a kmap_ops param It also removes a stray space from arch/x86/include/asm/xen/page.h. Signed-off-by: Zoltan Kiss Suggested-by: Anthony Liguori Suggested-by: David Vrabel Suggested-by: Stefano Stabellini Signed-off-by: David Vrabel Signed-off-by: Stefano Stabellini --- arch/arm/include/asm/xen/page.h | 15 ++-- arch/arm/xen/p2m.c | 32 +++++++++ arch/x86/include/asm/xen/page.h | 11 ++- arch/x86/xen/p2m.c | 121 ++++++++++++++++++++++++++++---- drivers/xen/grant-table.c | 73 +------------------ 5 files changed, 156 insertions(+), 96 deletions(-) diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index e0965abacb7d..cf4f3e867395 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -97,16 +97,13 @@ static inline pte_t *lookup_address(unsigned long address, unsigned int *level) return NULL; } -static inline int m2p_add_override(unsigned long mfn, struct page *page, - struct gnttab_map_grant_ref *kmap_op) -{ - return 0; -} +extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count); -static inline int m2p_remove_override(struct page *page, bool clear_pte) -{ - return 0; -} +extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count); bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn, diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c index b31ee1b275b0..97baf4427817 100644 --- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -146,6 +146,38 @@ unsigned long __mfn_to_pfn(unsigned long mfn) } EXPORT_SYMBOL_GPL(__mfn_to_pfn); +int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count) +{ + int i; + + for (i = 0; i < count; i++) { + if (map_ops[i].status) + continue; + set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT, + map_ops[i].dev_bus_addr >> PAGE_SHIFT); + } + + return 0; +} +EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping); + +int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count) +{ + int i; + + for (i = 0; i < count; i++) { + set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT, + INVALID_P2M_ENTRY); + } + + return 0; +} +EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping); + bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn, unsigned long nr_pages) { diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 3e276eb23d1b..c949923a5668 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -49,10 +49,17 @@ extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); extern unsigned long set_phys_range_identity(unsigned long pfn_s, unsigned long pfn_e); +extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count); extern int m2p_add_override(unsigned long mfn, struct page *page, struct gnttab_map_grant_ref *kmap_op); +extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count); extern int m2p_remove_override(struct page *page, - struct gnttab_map_grant_ref *kmap_op); + struct gnttab_map_grant_ref *kmap_op, + unsigned long mfn); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); @@ -121,7 +128,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) pfn = m2p_find_override_pfn(mfn, ~0); } - /* + /* * pfn is ~0 if there are no entries in the m2p for mfn or if the * entry doesn't map back to the mfn and m2p_override doesn't have a * valid entry for it. diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 696c694986d0..85e5d78c9874 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -881,6 +881,65 @@ static unsigned long mfn_hash(unsigned long mfn) return hash_long(mfn, M2P_OVERRIDE_HASH_SHIFT); } +int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count) +{ + int i, ret = 0; + bool lazy = false; + pte_t *pte; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + + if (kmap_ops && + !in_interrupt() && + paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { + arch_enter_lazy_mmu_mode(); + lazy = true; + } + + for (i = 0; i < count; i++) { + unsigned long mfn, pfn; + + /* Do not add to override if the map failed. */ + if (map_ops[i].status) + continue; + + if (map_ops[i].flags & GNTMAP_contains_pte) { + pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) + + (map_ops[i].host_addr & ~PAGE_MASK)); + mfn = pte_mfn(*pte); + } else { + mfn = PFN_DOWN(map_ops[i].dev_bus_addr); + } + pfn = page_to_pfn(pages[i]); + + WARN_ON(PagePrivate(pages[i])); + SetPagePrivate(pages[i]); + set_page_private(pages[i], mfn); + pages[i]->index = pfn_to_mfn(pfn); + + if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { + ret = -ENOMEM; + goto out; + } + + if (kmap_ops) { + ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]); + if (ret) + goto out; + } + } + +out: + if (lazy) + arch_leave_lazy_mmu_mode(); + + return ret; +} +EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping); + /* Add an MFN override for a particular page */ int m2p_add_override(unsigned long mfn, struct page *page, struct gnttab_map_grant_ref *kmap_op) @@ -899,13 +958,6 @@ int m2p_add_override(unsigned long mfn, struct page *page, "m2p_add_override: pfn %lx not mapped", pfn)) return -EINVAL; } - WARN_ON(PagePrivate(page)); - SetPagePrivate(page); - set_page_private(page, mfn); - page->index = pfn_to_mfn(pfn); - - if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) - return -ENOMEM; if (kmap_op != NULL) { if (!PageHighMem(page)) { @@ -943,20 +995,62 @@ int m2p_add_override(unsigned long mfn, struct page *page, return 0; } EXPORT_SYMBOL_GPL(m2p_add_override); + +int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count) +{ + int i, ret = 0; + bool lazy = false; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + + if (kmap_ops && + !in_interrupt() && + paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { + arch_enter_lazy_mmu_mode(); + lazy = true; + } + + for (i = 0; i < count; i++) { + unsigned long mfn = get_phys_to_machine(page_to_pfn(pages[i])); + unsigned long pfn = page_to_pfn(pages[i]); + + if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) { + ret = -EINVAL; + goto out; + } + + set_page_private(pages[i], INVALID_P2M_ENTRY); + WARN_ON(!PagePrivate(pages[i])); + ClearPagePrivate(pages[i]); + set_phys_to_machine(pfn, pages[i]->index); + + if (kmap_ops) + ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn); + if (ret) + goto out; + } + +out: + if (lazy) + arch_leave_lazy_mmu_mode(); + return ret; +} +EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping); + int m2p_remove_override(struct page *page, - struct gnttab_map_grant_ref *kmap_op) + struct gnttab_map_grant_ref *kmap_op, + unsigned long mfn) { unsigned long flags; - unsigned long mfn; unsigned long pfn; unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; pfn = page_to_pfn(page); - mfn = get_phys_to_machine(pfn); - if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) - return -EINVAL; if (!PageHighMem(page)) { address = (unsigned long)__va(pfn << PAGE_SHIFT); @@ -970,10 +1064,7 @@ int m2p_remove_override(struct page *page, spin_lock_irqsave(&m2p_override_lock, flags); list_del(&page->lru); spin_unlock_irqrestore(&m2p_override_lock, flags); - WARN_ON(!PagePrivate(page)); - ClearPagePrivate(page); - set_phys_to_machine(pfn, page->index); if (kmap_op != NULL) { if (!PageHighMem(page)) { struct multicall_space mcs; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index b84e3ab839aa..6d325bda76da 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -933,9 +933,6 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, struct page **pages, unsigned int count) { int i, ret; - bool lazy = false; - pte_t *pte; - unsigned long mfn; ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count); if (ret) @@ -947,45 +944,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i, &map_ops[i].status, __func__); - /* this is basically a nop on x86 */ - if (xen_feature(XENFEAT_auto_translated_physmap)) { - for (i = 0; i < count; i++) { - if (map_ops[i].status) - continue; - set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT, - map_ops[i].dev_bus_addr >> PAGE_SHIFT); - } - return ret; - } - - if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { - arch_enter_lazy_mmu_mode(); - lazy = true; - } - - for (i = 0; i < count; i++) { - /* Do not add to override if the map failed. */ - if (map_ops[i].status) - continue; - - if (map_ops[i].flags & GNTMAP_contains_pte) { - pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) + - (map_ops[i].host_addr & ~PAGE_MASK)); - mfn = pte_mfn(*pte); - } else { - mfn = PFN_DOWN(map_ops[i].dev_bus_addr); - } - ret = m2p_add_override(mfn, pages[i], kmap_ops ? - &kmap_ops[i] : NULL); - if (ret) - goto out; - } - - out: - if (lazy) - arch_leave_lazy_mmu_mode(); - - return ret; + return set_foreign_p2m_mapping(map_ops, kmap_ops, pages, count); } EXPORT_SYMBOL_GPL(gnttab_map_refs); @@ -993,39 +952,13 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count) { - int i, ret; - bool lazy = false; + int ret; ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count); if (ret) return ret; - /* this is basically a nop on x86 */ - if (xen_feature(XENFEAT_auto_translated_physmap)) { - for (i = 0; i < count; i++) { - set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT, - INVALID_P2M_ENTRY); - } - return ret; - } - - if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { - arch_enter_lazy_mmu_mode(); - lazy = true; - } - - for (i = 0; i < count; i++) { - ret = m2p_remove_override(pages[i], kmap_ops ? - &kmap_ops[i] : NULL); - if (ret) - goto out; - } - - out: - if (lazy) - arch_leave_lazy_mmu_mode(); - - return ret; + return clear_foreign_p2m_mapping(unmap_ops, kmap_ops, pages, count); } EXPORT_SYMBOL_GPL(gnttab_unmap_refs); From cd979883b9ede90643e019f33cb317933eb867b4 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Wed, 26 Feb 2014 11:30:30 +0100 Subject: [PATCH 11/11] xen/acpi-processor: fix enabling interrupts on syscore_resume syscore->resume() callback is expected to do not enable interrupts, it generates warning like below otherwise: [ 9386.365390] WARNING: CPU: 0 PID: 6733 at drivers/base/syscore.c:104 syscore_resume+0x9a/0xe0() [ 9386.365403] Interrupts enabled after xen_acpi_processor_resume+0x0/0x34 [xen_acpi_processor] ... [ 9386.365429] Call Trace: [ 9386.365434] [] dump_stack+0x45/0x56 [ 9386.365437] [] warn_slowpath_common+0x7d/0xa0 [ 9386.365439] [] warn_slowpath_fmt+0x4c/0x50 [ 9386.365442] [] ? xen_upload_processor_pm_data+0x300/0x300 [xen_acpi_processor] [ 9386.365443] [] syscore_resume+0x9a/0xe0 [ 9386.365445] [] suspend_devices_and_enter+0x402/0x470 [ 9386.365447] [] pm_suspend+0x178/0x260 On xen_acpi_processor_resume() we call various procedures, which are non atomic and can enable interrupts. To prevent the issue introduce separate resume notify called after we enable interrupts on resume and before we call other drivers resume callbacks. Signed-off-by: Stanislaw Gruszka Signed-off-by: Konrad Rzeszutek Wilk --- drivers/xen/manage.c | 16 ++++++++++++++++ drivers/xen/xen-acpi-processor.c | 15 ++++++++------- include/xen/xen-ops.h | 4 ++++ 3 files changed, 28 insertions(+), 7 deletions(-) diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 624e8dc24532..fc6c94c0b436 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -46,6 +46,20 @@ struct suspend_info { void (*post)(int cancelled); }; +static RAW_NOTIFIER_HEAD(xen_resume_notifier); + +void xen_resume_notifier_register(struct notifier_block *nb) +{ + raw_notifier_chain_register(&xen_resume_notifier, nb); +} +EXPORT_SYMBOL_GPL(xen_resume_notifier_register); + +void xen_resume_notifier_unregister(struct notifier_block *nb) +{ + raw_notifier_chain_unregister(&xen_resume_notifier, nb); +} +EXPORT_SYMBOL_GPL(xen_resume_notifier_unregister); + #ifdef CONFIG_HIBERNATE_CALLBACKS static void xen_hvm_post_suspend(int cancelled) { @@ -152,6 +166,8 @@ static void do_suspend(void) err = stop_machine(xen_suspend, &si, cpumask_of(0)); + raw_notifier_call_chain(&xen_resume_notifier, 0, NULL); + dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE); if (err) { diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index 7231859119f1..82358d14ecf1 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -27,10 +27,10 @@ #include #include #include -#include #include #include #include +#include #include #include @@ -495,14 +495,15 @@ static int xen_upload_processor_pm_data(void) return rc; } -static void xen_acpi_processor_resume(void) +static int xen_acpi_processor_resume(struct notifier_block *nb, + unsigned long action, void *data) { bitmap_zero(acpi_ids_done, nr_acpi_bits); - xen_upload_processor_pm_data(); + return xen_upload_processor_pm_data(); } -static struct syscore_ops xap_syscore_ops = { - .resume = xen_acpi_processor_resume, +struct notifier_block xen_acpi_processor_resume_nb = { + .notifier_call = xen_acpi_processor_resume, }; static int __init xen_acpi_processor_init(void) @@ -555,7 +556,7 @@ static int __init xen_acpi_processor_init(void) if (rc) goto err_unregister; - register_syscore_ops(&xap_syscore_ops); + xen_resume_notifier_register(&xen_acpi_processor_resume_nb); return 0; err_unregister: @@ -574,7 +575,7 @@ static void __exit xen_acpi_processor_exit(void) { int i; - unregister_syscore_ops(&xap_syscore_ops); + xen_resume_notifier_unregister(&xen_acpi_processor_resume_nb); kfree(acpi_ids_done); kfree(acpi_id_present); kfree(acpi_id_cst_present); diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index fb2ea8f26552..2cf47175b12b 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -2,6 +2,7 @@ #define INCLUDE_XEN_OPS_H #include +#include #include DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); @@ -16,6 +17,9 @@ void xen_mm_unpin_all(void); void xen_timer_resume(void); void xen_arch_resume(void); +void xen_resume_notifier_register(struct notifier_block *nb); +void xen_resume_notifier_unregister(struct notifier_block *nb); + int xen_setup_shutdown_event(void); extern unsigned long *xen_contiguous_bitmap;