xen: fixes and features for 4.14

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQEcBAABAgAGBQJZsBbYAAoJELDendYovxMv4hoH/39psrSeHw2hPX78KJ6orq4v
 mTVEP2gLA/qxaM03EnFljXfd88J8NcJsxv7vVjh/U4xRwntvAMovCkygkkO1aw93
 nZEhUq6IGupr8KzmqQi5U7WtiWAXFwDbGSasnOKEj/lLa7E0/9MsYYQ01FS6oFkc
 c9CHONaCWepdz0Xpt7s6BKyzo74ZbJeCc5rUZU81oH40XphaZEoy8E9NOgDdfz3l
 VvPSaxZvebynT8JKDe4KxrMPpBjhr7mwgLcXk/Zy2EzOzxFSxXLsDAnwjtCW1gTh
 lPLD4TkgtziDfPfZXxFH3J34IUe1tZ2M+7Cz157FBu6BKX/g9ETQT24DXWDzFuI=
 =cgfV
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-4.14b-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - the new pvcalls backend for routing socket calls from a guest to dom0

 - some cleanups of Xen code

 - a fix for wrong usage of {get,put}_cpu()

* tag 'for-linus-4.14b-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (27 commits)
  xen/mmu: set MMU_NORMAL_PT_UPDATE in remap_area_mfn_pte_fn
  xen: Don't try to call xen_alloc_p2m_entry() on autotranslating guests
  xen/events: events_fifo: Don't use {get,put}_cpu() in xen_evtchn_fifo_init()
  xen/pvcalls: use WARN_ON(1) instead of __WARN()
  xen: remove not used trace functions
  xen: remove unused function xen_set_domain_pte()
  xen: remove tests for pvh mode in pure pv paths
  xen-platform: constify pci_device_id.
  xen: cleanup xen.h
  xen: introduce a Kconfig option to enable the pvcalls backend
  xen/pvcalls: implement write
  xen/pvcalls: implement read
  xen/pvcalls: implement the ioworker functions
  xen/pvcalls: disconnect and module_exit
  xen/pvcalls: implement release command
  xen/pvcalls: implement poll command
  xen/pvcalls: implement accept command
  xen/pvcalls: implement listen command
  xen/pvcalls: implement bind command
  xen/pvcalls: implement connect command
  ...

arch/x86/include/asm/xen/page.h

@@ -158,9 +158,6 @@ static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
 	unsigned long pfn;
 	int ret;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return mfn;
-
 	if (unlikely(mfn >= machine_to_phys_nr))
 		return ~0;
 
@@ -317,8 +314,6 @@ static inline pte_t __pte_ma(pteval_t x)
 #define p4d_val_ma(x)	((x).p4d)
 #endif
 
-void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid);
-
 xmaddr_t arbitrary_virt_to_machine(void *address);
 unsigned long arbitrary_virt_to_mfn(void *vaddr);
 void make_lowmem_page_readonly(void *vaddr);

arch/x86/xen/mmu.c

@@ -84,7 +84,7 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token,
 	else
 		rmd->mfn++;
 
-	rmd->mmu_update->ptr = virt_to_machine(ptep).maddr;
+	rmd->mmu_update->ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
 	rmd->mmu_update->val = pte_val_ma(pte);
 	rmd->mmu_update++;
 

arch/x86/xen/mmu_pv.c

@@ -162,26 +162,6 @@ static bool xen_page_pinned(void *ptr)
 	return PagePinned(page);
 }
 
-void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid)
-{
-	struct multicall_space mcs;
-	struct mmu_update *u;
-
-	trace_xen_mmu_set_domain_pte(ptep, pteval, domid);
-
-	mcs = xen_mc_entry(sizeof(*u));
-	u = mcs.args;
-
-	/* ptep might be kmapped when using 32-bit HIGHPTE */
-	u->ptr = virt_to_machine(ptep).maddr;
-	u->val = pte_val_ma(pteval);
-
-	MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, domid);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-}
-EXPORT_SYMBOL_GPL(xen_set_domain_pte);
-
 static void xen_extend_mmu_update(const struct mmu_update *update)
 {
 	struct multicall_space mcs;

arch/x86/xen/p2m.c

@@ -212,8 +212,7 @@ void __ref xen_build_mfn_list_list(void)
 	unsigned int level, topidx, mididx;
 	unsigned long *mid_mfn_p;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap) ||
+	if (xen_start_info->flags & SIF_VIRT_P2M_4TOOLS)
-	    xen_start_info->flags & SIF_VIRT_P2M_4TOOLS)
 		return;
 
 	/* Pre-initialize p2m_top_mfn to be completely missing */
@@ -269,9 +268,6 @@ void __ref xen_build_mfn_list_list(void)
 
 void xen_setup_mfn_list_list(void)
 {
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
 
 	if (xen_start_info->flags & SIF_VIRT_P2M_4TOOLS)
@@ -291,9 +287,6 @@ void __init xen_build_dynamic_phys_to_machine(void)
 {
 	unsigned long pfn;
 
-	 if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	xen_p2m_addr = (unsigned long *)xen_start_info->mfn_list;
 	xen_p2m_size = ALIGN(xen_start_info->nr_pages, P2M_PER_PAGE);
 
@@ -540,9 +533,6 @@ int xen_alloc_p2m_entry(unsigned long pfn)
 	unsigned long addr = (unsigned long)(xen_p2m_addr + pfn);
 	unsigned long p2m_pfn;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 0;
-
 	ptep = lookup_address(addr, &level);
 	BUG_ON(!ptep || level != PG_LEVEL_4K);
 	pte_pg = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1));
@@ -640,9 +630,6 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 	if (unlikely(pfn_s >= xen_p2m_size))
 		return 0;
 
-	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
-		return pfn_e - pfn_s;
-
 	if (pfn_s > pfn_e)
 		return 0;
 
@@ -660,10 +647,6 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 	pte_t *ptep;
 	unsigned int level;
 
-	/* don't track P2M changes in autotranslate guests */
-	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
-		return true;
-
 	if (unlikely(pfn >= xen_p2m_size)) {
 		BUG_ON(mfn != INVALID_P2M_ENTRY);
 		return true;
@@ -711,9 +694,6 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 	int i, ret = 0;
 	pte_t *pte;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 0;
-
 	if (kmap_ops) {
 		ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref,
 						kmap_ops, count);
@@ -756,9 +736,6 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 {
 	int i, ret = 0;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 0;
-
 	for (i = 0; i < count; i++) {
 		unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i]));
 		unsigned long pfn = page_to_pfn(pages[i]);

arch/x86/xen/setup.c

@@ -340,8 +340,6 @@ static void __init xen_do_set_identity_and_remap_chunk(
 
 	WARN_ON(size == 0);
 
-	BUG_ON(xen_feature(XENFEAT_auto_translated_physmap));
-
 	mfn_save = virt_to_mfn(buf);
 
 	for (ident_pfn_iter = start_pfn, remap_pfn_iter = remap_pfn;
@@ -1024,8 +1022,7 @@ void __init xen_pvmmu_arch_setup(void)
 void __init xen_arch_setup(void)
 {
 	xen_panic_handler_init();
-	if (!xen_feature(XENFEAT_auto_translated_physmap))
+	xen_pvmmu_arch_setup();
-		xen_pvmmu_arch_setup();
 
 #ifdef CONFIG_ACPI
 	if (!(xen_start_info->flags & SIF_INITDOMAIN)) {

drivers/xen/Kconfig

@@ -196,6 +196,18 @@ config XEN_PCIDEV_BACKEND
 
 	  If in doubt, say m.
 
+config XEN_PVCALLS_BACKEND
+	bool "XEN PV Calls backend driver"
+	depends on INET && XEN && XEN_BACKEND
+	default n
+	help
+	  Experimental backend for the Xen PV Calls protocol
+	  (https://xenbits.xen.org/docs/unstable/misc/pvcalls.html). It
+	  allows PV Calls frontends to send POSIX calls to the backend,
+	  which implements them.
+
+	  If in doubt, say n.
+
 config XEN_SCSI_BACKEND
 	tristate "XEN SCSI backend driver"
 	depends on XEN && XEN_BACKEND && TARGET_CORE

drivers/xen/Makefile

@@ -35,6 +35,7 @@ obj-$(CONFIG_XEN_ACPI_PROCESSOR)	+= xen-acpi-processor.o
 obj-$(CONFIG_XEN_EFI)			+= efi.o
 obj-$(CONFIG_XEN_SCSI_BACKEND)		+= xen-scsiback.o
 obj-$(CONFIG_XEN_AUTO_XLATE)		+= xlate_mmu.o
+obj-$(CONFIG_XEN_PVCALLS_BACKEND)	+= pvcalls-back.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
 xen-gntalloc-y				:= gntalloc.o

drivers/xen/balloon.c

@@ -664,9 +664,11 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages)
 			 */
 			BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
 
-			ret = xen_alloc_p2m_entry(page_to_pfn(page));
+			if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			if (ret < 0)
+				ret = xen_alloc_p2m_entry(page_to_pfn(page));
-				goto out_undo;
+				if (ret < 0)
+					goto out_undo;
+			}
 #endif
 		} else {
 			ret = add_ballooned_pages(nr_pages - pgno);

drivers/xen/events/events_fifo.c

@@ -432,12 +432,12 @@ static int xen_evtchn_cpu_dead(unsigned int cpu)
 
 int __init xen_evtchn_fifo_init(void)
 {
-	int cpu = get_cpu();
+	int cpu = smp_processor_id();
 	int ret;
 
 	ret = evtchn_fifo_alloc_control_block(cpu);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	pr_info("Using FIFO-based ABI\n");
 
@@ -446,7 +446,6 @@ int __init xen_evtchn_fifo_init(void)
 	cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE,
 				  "xen/evtchn:prepare",
 				  xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead);
-out:
+
-	put_cpu();
 	return ret;
 }

drivers/xen/platform-pci.c

@@ -175,7 +175,7 @@ pci_out:
 	return ret;
 }
 
-static struct pci_device_id platform_pci_tbl[] = {
+static const struct pci_device_id platform_pci_tbl[] = {
 	{PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{0,}

include/trace/events/xen.h

@@ -149,24 +149,6 @@ DECLARE_EVENT_CLASS(xen_mmu__set_pte,
 DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte);
 DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte_atomic);
 
-TRACE_EVENT(xen_mmu_set_domain_pte,
-	    TP_PROTO(pte_t *ptep, pte_t pteval, unsigned domid),
-	    TP_ARGS(ptep, pteval, domid),
-	    TP_STRUCT__entry(
-		    __field(pte_t *, ptep)
-		    __field(pteval_t, pteval)
-		    __field(unsigned, domid)
-		    ),
-	    TP_fast_assign(__entry->ptep = ptep;
-			   __entry->pteval = pteval.pte;
-			   __entry->domid = domid),
-	    TP_printk("ptep %p pteval %0*llx (raw %0*llx) domid %u",
-		      __entry->ptep,
-		      (int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
-		      (int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval,
-		      __entry->domid)
-	);
-
 TRACE_EVENT(xen_mmu_set_pte_at,
 	    TP_PROTO(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pteval),
@@ -266,16 +248,6 @@ TRACE_EVENT(xen_mmu_set_p4d,
 		      (int)sizeof(p4dval_t) * 2, (unsigned long long)pgd_val(native_make_pgd(__entry->p4dval)),
 		      (int)sizeof(p4dval_t) * 2, (unsigned long long)__entry->p4dval)
 	);
-
-TRACE_EVENT(xen_mmu_pud_clear,
-	    TP_PROTO(pud_t *pudp),
-	    TP_ARGS(pudp),
-	    TP_STRUCT__entry(
-		    __field(pud_t *, pudp)
-		    ),
-	    TP_fast_assign(__entry->pudp = pudp),
-	    TP_printk("pudp %p", __entry->pudp)
-	);
 #else
 
 TRACE_EVENT(xen_mmu_set_pud,
@@ -295,16 +267,6 @@ TRACE_EVENT(xen_mmu_set_pud,
 
 #endif
 
-TRACE_EVENT(xen_mmu_pgd_clear,
-	    TP_PROTO(pgd_t *pgdp),
-	    TP_ARGS(pgdp),
-	    TP_STRUCT__entry(
-		    __field(pgd_t *, pgdp)
-		    ),
-	    TP_fast_assign(__entry->pgdp = pgdp),
-	    TP_printk("pgdp %p", __entry->pgdp)
-	);
-
 DECLARE_EVENT_CLASS(xen_mmu_ptep_modify_prot,
 	    TP_PROTO(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pteval),

include/xen/interface/io/pvcalls.h

@@ -0,0 +1,121 @@
+#ifndef __XEN_PUBLIC_IO_XEN_PVCALLS_H__
+#define __XEN_PUBLIC_IO_XEN_PVCALLS_H__
+
+#include <linux/net.h>
+#include <xen/interface/io/ring.h>
+#include <xen/interface/grant_table.h>
+
+/* "1" means socket, connect, release, bind, listen, accept and poll */
+#define XENBUS_FUNCTIONS_CALLS "1"
+
+/*
+ * See docs/misc/pvcalls.markdown in xen.git for the full specification:
+ * https://xenbits.xen.org/docs/unstable/misc/pvcalls.html
+ */
+struct pvcalls_data_intf {
+    RING_IDX in_cons, in_prod, in_error;
+
+    uint8_t pad1[52];
+
+    RING_IDX out_cons, out_prod, out_error;
+
+    uint8_t pad2[52];
+
+    RING_IDX ring_order;
+    grant_ref_t ref[];
+};
+DEFINE_XEN_FLEX_RING(pvcalls);
+
+#define PVCALLS_SOCKET         0
+#define PVCALLS_CONNECT        1
+#define PVCALLS_RELEASE        2
+#define PVCALLS_BIND           3
+#define PVCALLS_LISTEN         4
+#define PVCALLS_ACCEPT         5
+#define PVCALLS_POLL           6
+
+struct xen_pvcalls_request {
+    uint32_t req_id; /* private to guest, echoed in response */
+    uint32_t cmd;    /* command to execute */
+    union {
+        struct xen_pvcalls_socket {
+            uint64_t id;
+            uint32_t domain;
+            uint32_t type;
+            uint32_t protocol;
+        } socket;
+        struct xen_pvcalls_connect {
+            uint64_t id;
+            uint8_t addr[28];
+            uint32_t len;
+            uint32_t flags;
+            grant_ref_t ref;
+            uint32_t evtchn;
+        } connect;
+        struct xen_pvcalls_release {
+            uint64_t id;
+            uint8_t reuse;
+        } release;
+        struct xen_pvcalls_bind {
+            uint64_t id;
+            uint8_t addr[28];
+            uint32_t len;
+        } bind;
+        struct xen_pvcalls_listen {
+            uint64_t id;
+            uint32_t backlog;
+        } listen;
+        struct xen_pvcalls_accept {
+            uint64_t id;
+            uint64_t id_new;
+            grant_ref_t ref;
+            uint32_t evtchn;
+        } accept;
+        struct xen_pvcalls_poll {
+            uint64_t id;
+        } poll;
+        /* dummy member to force sizeof(struct xen_pvcalls_request)
+         * to match across archs */
+        struct xen_pvcalls_dummy {
+            uint8_t dummy[56];
+        } dummy;
+    } u;
+};
+
+struct xen_pvcalls_response {
+    uint32_t req_id;
+    uint32_t cmd;
+    int32_t ret;
+    uint32_t pad;
+    union {
+        struct _xen_pvcalls_socket {
+            uint64_t id;
+        } socket;
+        struct _xen_pvcalls_connect {
+            uint64_t id;
+        } connect;
+        struct _xen_pvcalls_release {
+            uint64_t id;
+        } release;
+        struct _xen_pvcalls_bind {
+            uint64_t id;
+        } bind;
+        struct _xen_pvcalls_listen {
+            uint64_t id;
+        } listen;
+        struct _xen_pvcalls_accept {
+            uint64_t id;
+        } accept;
+        struct _xen_pvcalls_poll {
+            uint64_t id;
+        } poll;
+        struct _xen_pvcalls_dummy {
+            uint8_t dummy[8];
+        } dummy;
+    } u;
+};
+
+DEFINE_RING_TYPES(xen_pvcalls, struct xen_pvcalls_request,
+                  struct xen_pvcalls_response);
+
+#endif

include/xen/interface/io/ring.h

@@ -9,6 +9,8 @@
 #ifndef __XEN_PUBLIC_IO_RING_H__
 #define __XEN_PUBLIC_IO_RING_H__
 
+#include <xen/interface/grant_table.h>
+
 typedef unsigned int RING_IDX;
 
 /* Round a 32-bit unsigned constant down to the nearest power of two. */

include/xen/xen.h

@@ -13,11 +13,16 @@ extern enum xen_domain_type xen_domain_type;
 #define xen_domain_type		XEN_NATIVE
 #endif
 
+#ifdef CONFIG_XEN_PVH
+extern bool xen_pvh;
+#else
+#define xen_pvh			0
+#endif
+
 #define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain() &&			\
+#define xen_pv_domain()		(xen_domain_type == XEN_PV_DOMAIN)
-				 xen_domain_type == XEN_PV_DOMAIN)
+#define xen_hvm_domain()	(xen_domain_type == XEN_HVM_DOMAIN)
-#define xen_hvm_domain()	(xen_domain() &&			\
+#define xen_pvh_domain()	(xen_pvh)
-				 xen_domain_type == XEN_HVM_DOMAIN)
 
 #ifdef CONFIG_XEN_DOM0
 #include <xen/interface/xen.h>
@@ -29,11 +34,4 @@ extern enum xen_domain_type xen_domain_type;
 #define xen_initial_domain()	(0)
 #endif	/* CONFIG_XEN_DOM0 */
 
-#ifdef CONFIG_XEN_PVH
-extern bool xen_pvh;
-#define xen_pvh_domain()	(xen_hvm_domain() && xen_pvh)
-#else
-#define xen_pvh_domain()	(0)
-#endif
-
 #endif	/* _XEN_XEN_H */