These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

12 files changed, 259 insertions, 37 deletions

diff --git a/kernel/include/xen/balloon.h b/kernel/include/xen/balloon.h
index a4c1c6a93..d1767dfb0 100644
--- a/kernel/include/xen/balloon.h
+++ b/kernel/include/xen/balloon.h
@@ -8,30 +8,24 @@ struct balloon_stats {
 	/* We aim for 'current allocation' == 'target allocation'. */
 	unsigned long current_pages;
 	unsigned long target_pages;
+	unsigned long target_unpopulated;
 	/* Number of pages in high- and low-memory balloons. */
 	unsigned long balloon_low;
 	unsigned long balloon_high;
+	unsigned long total_pages;
 	unsigned long schedule_delay;
 	unsigned long max_schedule_delay;
 	unsigned long retry_count;
 	unsigned long max_retry_count;
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
-	unsigned long hotplug_pages;
-	unsigned long balloon_hotplug;
-#endif
 };
 
 extern struct balloon_stats balloon_stats;
 
 void balloon_set_new_target(unsigned long target);
 
-int alloc_xenballooned_pages(int nr_pages, struct page **pages,
-		bool highmem);
+int alloc_xenballooned_pages(int nr_pages, struct page **pages);
 void free_xenballooned_pages(int nr_pages, struct page **pages);
 
-struct page *get_balloon_scratch_page(void);
-void put_balloon_scratch_page(void);
-
 struct device;
 #ifdef CONFIG_XEN_SELFBALLOONING
 extern int register_xen_selfballooning(struct device *dev);
diff --git a/kernel/include/xen/events.h b/kernel/include/xen/events.h
index 7d95fdf9c..88da2abaf 100644
--- a/kernel/include/xen/events.h
+++ b/kernel/include/xen/events.h
@@ -92,7 +92,6 @@ void xen_hvm_callback_vector(void);
 #ifdef CONFIG_TRACING
 #define trace_xen_hvm_callback_vector xen_hvm_callback_vector
 #endif
-extern int xen_have_vector_callback;
 int xen_set_callback_via(uint64_t via);
 void xen_evtchn_do_upcall(struct pt_regs *regs);
 void xen_hvm_evtchn_do_upcall(void);
diff --git a/kernel/include/xen/grant_table.h b/kernel/include/xen/grant_table.h
index 4478f4b4a..34b1379f9 100644
--- a/kernel/include/xen/grant_table.h
+++ b/kernel/include/xen/grant_table.h
@@ -45,8 +45,10 @@
 #include <asm/xen/hypervisor.h>
 
 #include <xen/features.h>
+#include <xen/page.h>
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
+#include <linux/kernel.h>
 
 #define GNTTAB_RESERVED_XENSTORE 1
 
@@ -129,6 +131,15 @@ 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);
 
+/* Give access to the first 4K of the page */
+static inline void gnttab_page_grant_foreign_access_ref_one(
+	grant_ref_t ref, domid_t domid,
+	struct page *page, int readonly)
+{
+	gnttab_grant_foreign_access_ref(ref, domid, xen_page_to_gfn(page),
+					readonly);
+}
+
 void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid,
 				       unsigned long pfn);
 
@@ -224,4 +235,50 @@ static inline struct xen_page_foreign *xen_page_foreign(struct page *page)
 #endif
 }
 
+/* Split Linux page in chunk of the size of the grant and call fn
+ *
+ * Parameters of fn:
+ *	gfn: guest frame number
+ *	offset: offset in the grant
+ *	len: length of the data in the grant.
+ *	data: internal information
+ */
+typedef void (*xen_grant_fn_t)(unsigned long gfn, unsigned int offset,
+			       unsigned int len, void *data);
+
+void gnttab_foreach_grant_in_range(struct page *page,
+				   unsigned int offset,
+				   unsigned int len,
+				   xen_grant_fn_t fn,
+				   void *data);
+
+/* Helper to get to call fn only on the first "grant chunk" */
+static inline void gnttab_for_one_grant(struct page *page, unsigned int offset,
+					unsigned len, xen_grant_fn_t fn,
+					void *data)
+{
+	/* The first request is limited to the size of one grant */
+	len = min_t(unsigned int, XEN_PAGE_SIZE - (offset & ~XEN_PAGE_MASK),
+		    len);
+
+	gnttab_foreach_grant_in_range(page, offset, len, fn, data);
+}
+
+/* Get @nr_grefs grants from an array of page and call fn for each grant */
+void gnttab_foreach_grant(struct page **pages,
+			  unsigned int nr_grefs,
+			  xen_grant_fn_t fn,
+			  void *data);
+
+/* Get the number of grant in a specified region
+ *
+ * start: Offset from the beginning of the first page
+ * len: total length of data (can cross multiple page)
+ */
+static inline unsigned int gnttab_count_grant(unsigned int start,
+					      unsigned int len)
+{
+	return XEN_PFN_UP(xen_offset_in_page(start) + len);
+}
+
 #endif /* __ASM_GNTTAB_H__ */
diff --git a/kernel/include/xen/interface/io/netif.h b/kernel/include/xen/interface/io/netif.h
index 70054cc07..252ffd480 100644
--- a/kernel/include/xen/interface/io/netif.h
+++ b/kernel/include/xen/interface/io/netif.h
@@ -156,7 +156,9 @@ struct xen_netif_tx_request {
 /* Types of xen_netif_extra_info descriptors. */
 #define XEN_NETIF_EXTRA_TYPE_NONE	(0)  /* Never used - invalid */
 #define XEN_NETIF_EXTRA_TYPE_GSO	(1)  /* u.gso */
-#define XEN_NETIF_EXTRA_TYPE_MAX	(2)
+#define XEN_NETIF_EXTRA_TYPE_MCAST_ADD	(2)  /* u.mcast */
+#define XEN_NETIF_EXTRA_TYPE_MCAST_DEL	(3)  /* u.mcast */
+#define XEN_NETIF_EXTRA_TYPE_MAX	(4)
 
 /* xen_netif_extra_info flags. */
 #define _XEN_NETIF_EXTRA_FLAG_MORE	(0)
@@ -201,6 +203,10 @@ struct xen_netif_extra_info {
 			uint16_t features; /* XEN_NETIF_GSO_FEAT_* */
 		} gso;
 
+		struct {
+			uint8_t addr[6]; /* Address to add/remove. */
+		} mcast;
+
 		uint16_t pad[3];
 	} u;
 };
diff --git a/kernel/include/xen/interface/io/ring.h b/kernel/include/xen/interface/io/ring.h
index 7d28aff60..7dc685b40 100644
--- a/kernel/include/xen/interface/io/ring.h
+++ b/kernel/include/xen/interface/io/ring.h
@@ -181,6 +181,20 @@ struct __name##_back_ring {						\
 #define RING_GET_REQUEST(_r, _idx)					\
     (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))
 
+/*
+ * Get a local copy of a request.
+ *
+ * Use this in preference to RING_GET_REQUEST() so all processing is
+ * done on a local copy that cannot be modified by the other end.
+ *
+ * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this
+ * to be ineffective where _req is a struct which consists of only bitfields.
+ */
+#define RING_COPY_REQUEST(_r, _idx, _req) do {				\
+	/* Use volatile to force the copy into _req. */			\
+	*(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx);	\
+} while (0)
+
 #define RING_GET_RESPONSE(_r, _idx)					\
     (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
 
diff --git a/kernel/include/xen/interface/platform.h b/kernel/include/xen/interface/platform.h
index 5cc49ea8d..8e0358713 100644
--- a/kernel/include/xen/interface/platform.h
+++ b/kernel/include/xen/interface/platform.h
@@ -474,6 +474,23 @@ struct xenpf_core_parking {
 };
 DEFINE_GUEST_HANDLE_STRUCT(xenpf_core_parking);
 
+#define XENPF_get_symbol      63
+struct xenpf_symdata {
+	/* IN/OUT variables */
+	uint32_t	namelen; /* size of 'name' buffer */
+
+	/* IN/OUT variables */
+	uint32_t	symnum; /* IN:  Symbol to read                       */
+				/* OUT: Next available symbol. If same as IN */
+				/* then  we reached the end                  */
+
+	/* OUT variables */
+	GUEST_HANDLE(char) name;
+	uint64_t	address;
+	char            type;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_symdata);
+
 struct xen_platform_op {
 	uint32_t cmd;
 	uint32_t interface_version; /* XENPF_INTERFACE_VERSION */
@@ -495,6 +512,7 @@ struct xen_platform_op {
 		struct xenpf_cpu_hotadd        cpu_add;
 		struct xenpf_mem_hotadd        mem_add;
 		struct xenpf_core_parking      core_parking;
+		struct xenpf_symdata           symdata;
 		uint8_t                        pad[128];
 	} u;
 };
diff --git a/kernel/include/xen/interface/sched.h b/kernel/include/xen/interface/sched.h
index 9ce083960..f18490985 100644
--- a/kernel/include/xen/interface/sched.h
+++ b/kernel/include/xen/interface/sched.h
@@ -107,5 +107,13 @@ struct sched_watchdog {
 #define SHUTDOWN_suspend    2  /* Clean up, save suspend info, kill.         */
 #define SHUTDOWN_crash      3  /* Tell controller we've crashed.             */
 #define SHUTDOWN_watchdog   4  /* Restart because watchdog time expired.     */
+/*
+ * Domain asked to perform 'soft reset' for it. The expected behavior is to
+ * reset internal Xen state for the domain returning it to the point where it
+ * was created but leaving the domain's memory contents and vCPU contexts
+ * intact. This will allow the domain to start over and set up all Xen specific
+ * interfaces again.
+ */
+#define SHUTDOWN_soft_reset 5
 
 #endif /* __XEN_PUBLIC_SCHED_H__ */
diff --git a/kernel/include/xen/interface/xen.h b/kernel/include/xen/interface/xen.h
index a48378958..167071c29 100644
--- a/kernel/include/xen/interface/xen.h
+++ b/kernel/include/xen/interface/xen.h
@@ -80,6 +80,7 @@
 #define __HYPERVISOR_kexec_op             37
 #define __HYPERVISOR_tmem_op              38
 #define __HYPERVISOR_xc_reserved_op       39 /* reserved for XenClient */
+#define __HYPERVISOR_xenpmu_op            40
 
 /* Architecture-specific hypercall definitions. */
 #define __HYPERVISOR_arch_0               48
@@ -112,6 +113,7 @@
 #define VIRQ_MEM_EVENT  10 /* G. (DOM0) A memory event has occured           */
 #define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient                     */
 #define VIRQ_ENOMEM     12 /* G. (DOM0) Low on heap memory       */
+#define VIRQ_XENPMU     13  /* PMC interrupt                                 */
 
 /* Architecture-specific VIRQ definitions. */
 #define VIRQ_ARCH_0    16
@@ -585,26 +587,29 @@ struct shared_info {
 };
 
 /*
- * Start-of-day memory layout for the initial domain (DOM0):
+ * Start-of-day memory layout
+ *
  *  1. The domain is started within contiguous virtual-memory region.
  *  2. The contiguous region begins and ends on an aligned 4MB boundary.
- *  3. The region start corresponds to the load address of the OS image.
- *     If the load address is not 4MB aligned then the address is rounded down.
- *  4. This the order of bootstrap elements in the initial virtual region:
+ *  3. This the order of bootstrap elements in the initial virtual region:
  *      a. relocated kernel image
  *      b. initial ram disk              [mod_start, mod_len]
+ *         (may be omitted)
  *      c. list of allocated page frames [mfn_list, nr_pages]
+ *         (unless relocated due to XEN_ELFNOTE_INIT_P2M)
  *      d. start_info_t structure        [register ESI (x86)]
- *      e. bootstrap page tables         [pt_base, CR3 (x86)]
- *      f. bootstrap stack               [register ESP (x86)]
- *  5. Bootstrap elements are packed together, but each is 4kB-aligned.
- *  6. The initial ram disk may be omitted.
- *  7. The list of page frames forms a contiguous 'pseudo-physical' memory
+ *         in case of dom0 this page contains the console info, too
+ *      e. unless dom0: xenstore ring page
+ *      f. unless dom0: console ring page
+ *      g. bootstrap page tables         [pt_base, CR3 (x86)]
+ *      h. bootstrap stack               [register ESP (x86)]
+ *  4. Bootstrap elements are packed together, but each is 4kB-aligned.
+ *  5. The list of page frames forms a contiguous 'pseudo-physical' memory
  *     layout for the domain. In particular, the bootstrap virtual-memory
  *     region is a 1:1 mapping to the first section of the pseudo-physical map.
- *  8. All bootstrap elements are mapped read-writable for the guest OS. The
+ *  6. All bootstrap elements are mapped read-writable for the guest OS. The
  *     only exception is the bootstrap page table, which is mapped read-only.
- *  9. There is guaranteed to be at least 512kB padding after the final
+ *  7. There is guaranteed to be at least 512kB padding after the final
  *     bootstrap element. If necessary, the bootstrap virtual region is
  *     extended by an extra 4MB to ensure this.
  */
@@ -641,10 +646,12 @@ struct start_info {
 };
 
 /* These flags are passed in the 'flags' field of start_info_t. */
-#define SIF_PRIVILEGED    (1<<0)  /* Is the domain privileged? */
-#define SIF_INITDOMAIN    (1<<1)  /* Is this the initial control domain? */
-#define SIF_MULTIBOOT_MOD (1<<2)  /* Is mod_start a multiboot module? */
-#define SIF_MOD_START_PFN (1<<3)  /* Is mod_start a PFN? */
+#define SIF_PRIVILEGED      (1<<0)  /* Is the domain privileged? */
+#define SIF_INITDOMAIN      (1<<1)  /* Is this the initial control domain? */
+#define SIF_MULTIBOOT_MOD   (1<<2)  /* Is mod_start a multiboot module? */
+#define SIF_MOD_START_PFN   (1<<3)  /* Is mod_start a PFN? */
+#define SIF_VIRT_P2M_4TOOLS (1<<4)  /* Do Xen tools understand a virt. mapped */
+				    /* P->M making the 3 level tree obsolete? */
 #define SIF_PM_MASK       (0xFF<<8) /* reserve 1 byte for xen-pm options */
 
 /*
diff --git a/kernel/include/xen/interface/xenpmu.h b/kernel/include/xen/interface/xenpmu.h
new file mode 100644
index 000000000..139efc91b
--- /dev/null
+++ b/kernel/include/xen/interface/xenpmu.h
@@ -0,0 +1,94 @@
+#ifndef __XEN_PUBLIC_XENPMU_H__
+#define __XEN_PUBLIC_XENPMU_H__
+
+#include "xen.h"
+
+#define XENPMU_VER_MAJ    0
+#define XENPMU_VER_MIN    1
+
+/*
+ * ` enum neg_errnoval
+ * ` HYPERVISOR_xenpmu_op(enum xenpmu_op cmd, struct xenpmu_params *args);
+ *
+ * @cmd  == XENPMU_* (PMU operation)
+ * @args == struct xenpmu_params
+ */
+/* ` enum xenpmu_op { */
+#define XENPMU_mode_get        0 /* Also used for getting PMU version */
+#define XENPMU_mode_set        1
+#define XENPMU_feature_get     2
+#define XENPMU_feature_set     3
+#define XENPMU_init            4
+#define XENPMU_finish          5
+#define XENPMU_lvtpc_set       6
+#define XENPMU_flush           7
+
+/* ` } */
+
+/* Parameters structure for HYPERVISOR_xenpmu_op call */
+struct xen_pmu_params {
+	/* IN/OUT parameters */
+	struct {
+		uint32_t maj;
+		uint32_t min;
+	} version;
+	uint64_t val;
+
+	/* IN parameters */
+	uint32_t vcpu;
+	uint32_t pad;
+};
+
+/* PMU modes:
+ * - XENPMU_MODE_OFF:   No PMU virtualization
+ * - XENPMU_MODE_SELF:  Guests can profile themselves
+ * - XENPMU_MODE_HV:    Guests can profile themselves, dom0 profiles
+ *                      itself and Xen
+ * - XENPMU_MODE_ALL:   Only dom0 has access to VPMU and it profiles
+ *                      everyone: itself, the hypervisor and the guests.
+ */
+#define XENPMU_MODE_OFF           0
+#define XENPMU_MODE_SELF          (1<<0)
+#define XENPMU_MODE_HV            (1<<1)
+#define XENPMU_MODE_ALL           (1<<2)
+
+/*
+ * PMU features:
+ * - XENPMU_FEATURE_INTEL_BTS: Intel BTS support (ignored on AMD)
+ */
+#define XENPMU_FEATURE_INTEL_BTS  1
+
+/*
+ * Shared PMU data between hypervisor and PV(H) domains.
+ *
+ * The hypervisor fills out this structure during PMU interrupt and sends an
+ * interrupt to appropriate VCPU.
+ * Architecture-independent fields of xen_pmu_data are WO for the hypervisor
+ * and RO for the guest but some fields in xen_pmu_arch can be writable
+ * by both the hypervisor and the guest (see arch-$arch/pmu.h).
+ */
+struct xen_pmu_data {
+	/* Interrupted VCPU */
+	uint32_t vcpu_id;
+
+	/*
+	 * Physical processor on which the interrupt occurred. On non-privileged
+	 * guests set to vcpu_id;
+	 */
+	uint32_t pcpu_id;
+
+	/*
+	 * Domain that was interrupted. On non-privileged guests set to
+	 * DOMID_SELF.
+	 * On privileged guests can be DOMID_SELF, DOMID_XEN, or, when in
+	 * XENPMU_MODE_ALL mode, domain ID of another domain.
+	 */
+	domid_t  domain_id;
+
+	uint8_t pad[6];
+
+	/* Architecture-specific information */
+	struct xen_pmu_arch pmu;
+};
+
+#endif /* __XEN_PUBLIC_XENPMU_H__ */
diff --git a/kernel/include/xen/page.h b/kernel/include/xen/page.h
index c5ed20bb3..96294ac93 100644
--- a/kernel/include/xen/page.h
+++ b/kernel/include/xen/page.h
@@ -1,16 +1,41 @@
 #ifndef _XEN_PAGE_H
 #define _XEN_PAGE_H
 
+#include <asm/page.h>
+
+/* The hypercall interface supports only 4KB page */
+#define XEN_PAGE_SHIFT	12
+#define XEN_PAGE_SIZE	(_AC(1, UL) << XEN_PAGE_SHIFT)
+#define XEN_PAGE_MASK	(~(XEN_PAGE_SIZE-1))
+#define xen_offset_in_page(p)	((unsigned long)(p) & ~XEN_PAGE_MASK)
+
+/*
+ * We assume that PAGE_SIZE is a multiple of XEN_PAGE_SIZE
+ * XXX: Add a BUILD_BUG_ON?
+ */
+
+#define xen_pfn_to_page(xen_pfn)	\
+	((pfn_to_page(((unsigned long)(xen_pfn) << XEN_PAGE_SHIFT) >> PAGE_SHIFT)))
+#define page_to_xen_pfn(page)		\
+	(((page_to_pfn(page)) << PAGE_SHIFT) >> XEN_PAGE_SHIFT)
+
+#define XEN_PFN_PER_PAGE	(PAGE_SIZE / XEN_PAGE_SIZE)
+
+#define XEN_PFN_DOWN(x)	((x) >> XEN_PAGE_SHIFT)
+#define XEN_PFN_UP(x)	(((x) + XEN_PAGE_SIZE-1) >> XEN_PAGE_SHIFT)
+#define XEN_PFN_PHYS(x)	((phys_addr_t)(x) << XEN_PAGE_SHIFT)
+
 #include <asm/xen/page.h>
 
-static inline unsigned long page_to_mfn(struct page *page)
+/* Return the GFN associated to the first 4KB of the page */
+static inline unsigned long xen_page_to_gfn(struct page *page)
 {
-	return pfn_to_mfn(page_to_pfn(page));
+	return pfn_to_gfn(page_to_xen_pfn(page));
 }
 
 struct xen_memory_region {
-	phys_addr_t start;
-	phys_addr_t size;
+	unsigned long start_pfn;
+	unsigned long n_pfns;
 };
 
 #define XEN_EXTRA_MEM_MAX_REGIONS 128 /* == E820MAX */
diff --git a/kernel/include/xen/xen-ops.h b/kernel/include/xen/xen-ops.h
index 0ce4f3201..e4e214a5a 100644
--- a/kernel/include/xen/xen-ops.h
+++ b/kernel/include/xen/xen-ops.h
@@ -30,7 +30,7 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order);
 struct vm_area_struct;
 
 /*
- * xen_remap_domain_mfn_array() - map an array of foreign frames
+ * xen_remap_domain_gfn_array() - map an array of foreign frames
  * @vma:     VMA to map the pages into
  * @addr:    Address at which to map the pages
  * @gfn:     Array of GFNs to map
@@ -46,14 +46,14 @@ struct vm_area_struct;
  * Returns the number of successfully mapped frames, or a -ve error
  * code.
  */
-int xen_remap_domain_mfn_array(struct vm_area_struct *vma,
+int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
 			       unsigned long addr,
 			       xen_pfn_t *gfn, int nr,
 			       int *err_ptr, pgprot_t prot,
 			       unsigned domid,
 			       struct page **pages);
 
-/* xen_remap_domain_mfn_range() - map a range of foreign frames
+/* xen_remap_domain_gfn_range() - map a range of foreign frames
  * @vma:     VMA to map the pages into
  * @addr:    Address at which to map the pages
  * @gfn:     First GFN to map.
@@ -65,12 +65,12 @@ int xen_remap_domain_mfn_array(struct vm_area_struct *vma,
  * Returns the number of successfully mapped frames, or a -ve error
  * code.
  */
-int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
+int xen_remap_domain_gfn_range(struct vm_area_struct *vma,
 			       unsigned long addr,
 			       xen_pfn_t gfn, int nr,
 			       pgprot_t prot, unsigned domid,
 			       struct page **pages);
-int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
 			       int numpgs, struct page **pages);
 int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
 			      unsigned long addr,
diff --git a/kernel/include/xen/xenbus.h b/kernel/include/xen/xenbus.h
index 289c0b5f0..32b944b7c 100644
--- a/kernel/include/xen/xenbus.h
+++ b/kernel/include/xen/xenbus.h
@@ -46,8 +46,8 @@
 #include <xen/interface/io/xenbus.h>
 #include <xen/interface/io/xs_wire.h>
 
-#define XENBUS_MAX_RING_PAGE_ORDER 4
-#define XENBUS_MAX_RING_PAGES      (1U << XENBUS_MAX_RING_PAGE_ORDER)
+#define XENBUS_MAX_RING_GRANT_ORDER 4
+#define XENBUS_MAX_RING_GRANTS      (1U << XENBUS_MAX_RING_GRANT_ORDER)
 #define INVALID_GRANT_HANDLE       (~0U)
 
 /* Register callback to watch this node. */