xen/x86: Remove PVH support

We are replacing existing PVH guests with new implementation.

We are keeping xen_pvh_domain() macro (for now set to zero) because
when we introduce new PVH implementation later in this series we will
reuse current PVH-specific code (xen_pvh_gnttab_setup()), and that
code is conditioned by 'if (xen_pvh_domain())'. (We will also need
a noop xen_pvh_domain() for !CONFIG_XEN_PVH).
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

arch/x86/xen/enlighten.c

@@ -1138,10 +1138,11 @@ void xen_setup_vcpu_info_placement(void)
 		xen_vcpu_setup(cpu);
 	}
 
-	/* xen_vcpu_setup managed to place the vcpu_info within the
-	 * percpu area for all cpus, so make use of it. Note that for
-	 * PVH we want to use native IRQ mechanism. */
-	if (have_vcpu_info_placement && !xen_pvh_domain()) {
+	/*
+	 * xen_vcpu_setup managed to place the vcpu_info within the
+	 * percpu area for all cpus, so make use of it.
+	 */
+	if (have_vcpu_info_placement) {
 		pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
 		pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
 		pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
@@ -1413,49 +1414,9 @@ static void __init xen_boot_params_init_edd(void)
  * Set up the GDT and segment registers for -fstack-protector.  Until
  * we do this, we have to be careful not to call any stack-protected
  * function, which is most of the kernel.
- *
- * Note, that it is __ref because the only caller of this after init
- * is PVH which is not going to use xen_load_gdt_boot or other
- * __init functions.
  */
-static void __ref xen_setup_gdt(int cpu)
+static void xen_setup_gdt(int cpu)
 {
-	if (xen_feature(XENFEAT_auto_translated_physmap)) {
-#ifdef CONFIG_X86_64
-		unsigned long dummy;
-
-		load_percpu_segment(cpu); /* We need to access per-cpu area */
-		switch_to_new_gdt(cpu); /* GDT and GS set */
-
-		/* We are switching of the Xen provided GDT to our HVM mode
-		 * GDT. The new GDT has  __KERNEL_CS with CS.L = 1
-		 * and we are jumping to reload it.
-		 */
-		asm volatile ("pushq %0\n"
-			      "leaq 1f(%%rip),%0\n"
-			      "pushq %0\n"
-			      "lretq\n"
-			      "1:\n"
-			      : "=&r" (dummy) : "0" (__KERNEL_CS));
-
-		/*
-		 * While not needed, we also set the %es, %ds, and %fs
-		 * to zero. We don't care about %ss as it is NULL.
-		 * Strictly speaking this is not needed as Xen zeros those
-		 * out (and also MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE)
-		 *
-		 * Linux zeros them in cpu_init() and in secondary_startup_64
-		 * (for BSP).
-		 */
-		loadsegment(es, 0);
-		loadsegment(ds, 0);
-		loadsegment(fs, 0);
-#else
-		/* PVH: TODO Implement. */
-		BUG();
-#endif
-		return; /* PVH does not need any PV GDT ops. */
-	}
 	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
 	pv_cpu_ops.load_gdt = xen_load_gdt_boot;
 
@@ -1466,59 +1427,6 @@ static void __ref xen_setup_gdt(int cpu)
 	pv_cpu_ops.load_gdt = xen_load_gdt;
 }
 
-#ifdef CONFIG_XEN_PVH
-/*
- * A PV guest starts with default flags that are not set for PVH, set them
- * here asap.
- */
-static void xen_pvh_set_cr_flags(int cpu)
-{
-
-	/* Some of these are setup in 'secondary_startup_64'. The others:
-	 * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests
-	 * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */
-	write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM);
-
-	if (!cpu)
-		return;
-	/*
-	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
-	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
-	*/
-	if (boot_cpu_has(X86_FEATURE_PSE))
-		cr4_set_bits_and_update_boot(X86_CR4_PSE);
-
-	if (boot_cpu_has(X86_FEATURE_PGE))
-		cr4_set_bits_and_update_boot(X86_CR4_PGE);
-}
-
-/*
- * Note, that it is ref - because the only caller of this after init
- * is PVH which is not going to use xen_load_gdt_boot or other
- * __init functions.
- */
-void __ref xen_pvh_secondary_vcpu_init(int cpu)
-{
-	xen_setup_gdt(cpu);
-	xen_pvh_set_cr_flags(cpu);
-}
-
-static void __init xen_pvh_early_guest_init(void)
-{
-	if (!xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
-	BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector));
-
-	xen_pvh_early_cpu_init(0, false);
-	xen_pvh_set_cr_flags(0);
-
-#ifdef CONFIG_X86_32
-	BUG(); /* PVH: Implement proper support. */
-#endif
-}
-#endif    /* CONFIG_XEN_PVH */
-
 static void __init xen_dom0_set_legacy_features(void)
 {
 	x86_platform.legacy.rtc = 1;
@@ -1555,24 +1463,17 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	xen_domain_type = XEN_PV_DOMAIN;
 
 	xen_setup_features();
-#ifdef CONFIG_XEN_PVH
-	xen_pvh_early_guest_init();
-#endif
+
 	xen_setup_machphys_mapping();
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
-	if (!xen_pvh_domain()) {
-		pv_cpu_ops = xen_cpu_ops;
+	pv_cpu_ops = xen_cpu_ops;
 
-		x86_platform.get_nmi_reason = xen_get_nmi_reason;
-	}
+	x86_platform.get_nmi_reason = xen_get_nmi_reason;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
-	else
-		x86_init.resources.memory_setup = xen_memory_setup;
+	x86_init.resources.memory_setup = xen_memory_setup;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
 
@@ -1665,18 +1566,15 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	/* set the limit of our address space */
 	xen_reserve_top();
 
-	/* PVH: runs at default kernel iopl of 0 */
-	if (!xen_pvh_domain()) {
-		/*
-		 * We used to do this in xen_arch_setup, but that is too late
-		 * on AMD were early_cpu_init (run before ->arch_setup()) calls
-		 * early_amd_init which pokes 0xcf8 port.
-		 */
-		set_iopl.iopl = 1;
-		rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
-		if (rc != 0)
-			xen_raw_printk("physdev_op failed %d\n", rc);
-	}
+	/*
+	 * We used to do this in xen_arch_setup, but that is too late
+	 * on AMD were early_cpu_init (run before ->arch_setup()) calls
+	 * early_amd_init which pokes 0xcf8 port.
+	 */
+	set_iopl.iopl = 1;
+	rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
+	if (rc != 0)
+		xen_raw_printk("physdev_op failed %d\n", rc);
 
 #ifdef CONFIG_X86_32
 	/* set up basic CPUID stuff */

arch/x86/xen/mmu.c

@@ -1792,10 +1792,6 @@ static void __init set_page_prot_flags(void *addr, pgprot_t prot,
 	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
 	pte_t pte = pfn_pte(pfn, prot);
 
-	/* For PVH no need to set R/O or R/W to pin them or unpin them. */
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags))
 		BUG();
 }
@@ -1902,8 +1898,7 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
  * level2_ident_pgt, and level2_kernel_pgt.  This means that only the
  * kernel has a physical mapping to start with - but that's enough to
  * get __va working.  We need to fill in the rest of the physical
- * mapping once some sort of allocator has been set up.  NOTE: for
- * PVH, the page tables are native.
+ * mapping once some sort of allocator has been set up.
  */
 void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
@@ -2812,16 +2807,6 @@ static int do_remap_gfn(struct vm_area_struct *vma,
 
 	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
 
-	if (xen_feature(XENFEAT_auto_translated_physmap)) {
-#ifdef CONFIG_XEN_PVH
-		/* We need to update the local page tables and the xen HAP */
-		return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr,
-						 prot, domid, pages);
-#else
-		return -EINVAL;
-#endif
-        }
-
 	rmd.mfn = gfn;
 	rmd.prot = prot;
 	/* We use the err_ptr to indicate if there we are doing a contiguous
@@ -2915,10 +2900,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
 	if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
 		return 0;
 
-#ifdef CONFIG_XEN_PVH
-	return xen_xlate_unmap_gfn_range(vma, numpgs, pages);
-#else
 	return -EINVAL;
-#endif
 }
 EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);

arch/x86/xen/setup.c

@@ -914,39 +914,6 @@ char * __init xen_memory_setup(void)
 	return "Xen";
 }
 
-/*
- * Machine specific memory setup for auto-translated guests.
- */
-char * __init xen_auto_xlated_memory_setup(void)
-{
-	struct xen_memory_map memmap;
-	int i;
-	int rc;
-
-	memmap.nr_entries = ARRAY_SIZE(xen_e820_map);
-	set_xen_guest_handle(memmap.buffer, xen_e820_map);
-
-	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
-	if (rc < 0)
-		panic("No memory map (%d)\n", rc);
-
-	xen_e820_map_entries = memmap.nr_entries;
-
-	sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
-			  &xen_e820_map_entries);
-
-	for (i = 0; i < xen_e820_map_entries; i++)
-		e820_add_region(xen_e820_map[i].addr, xen_e820_map[i].size,
-				xen_e820_map[i].type);
-
-	/* Remove p2m info, it is not needed. */
-	xen_start_info->mfn_list = 0;
-	xen_start_info->first_p2m_pfn = 0;
-	xen_start_info->nr_p2m_frames = 0;
-
-	return "Xen";
-}
-
 /*
  * Set the bit indicating "nosegneg" library variants should be used.
  * We only need to bother in pure 32-bit mode; compat 32-bit processes
@@ -1032,8 +999,8 @@ 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)) {

arch/x86/xen/smp.c

@@ -99,18 +99,8 @@ static void cpu_bringup(void)
 	local_irq_enable();
 }
 
-/*
- * Note: cpu parameter is only relevant for PVH. The reason for passing it
- * is we can't do smp_processor_id until the percpu segments are loaded, for
- * which we need the cpu number! So we pass it in rdi as first parameter.
- */
-asmlinkage __visible void cpu_bringup_and_idle(int cpu)
+asmlinkage __visible void cpu_bringup_and_idle(void)
 {
-#ifdef CONFIG_XEN_PVH
-	if (xen_feature(XENFEAT_auto_translated_physmap) &&
-	    xen_feature(XENFEAT_supervisor_mode_kernel))
-		xen_pvh_secondary_vcpu_init(cpu);
-#endif
 	cpu_bringup();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
@@ -404,61 +394,47 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	gdt = get_cpu_gdt_table(cpu);
 
 #ifdef CONFIG_X86_32
-	/* Note: PVH is not yet supported on x86_32. */
 	ctxt->user_regs.fs = __KERNEL_PERCPU;
 	ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
 #endif
 	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
 
-	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
-		ctxt->flags = VGCF_IN_KERNEL;
-		ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
-		ctxt->user_regs.ds = __USER_DS;
-		ctxt->user_regs.es = __USER_DS;
-		ctxt->user_regs.ss = __KERNEL_DS;
+	ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
+	ctxt->flags = VGCF_IN_KERNEL;
+	ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
+	ctxt->user_regs.ds = __USER_DS;
+	ctxt->user_regs.es = __USER_DS;
+	ctxt->user_regs.ss = __KERNEL_DS;
 
-		xen_copy_trap_info(ctxt->trap_ctxt);
+	xen_copy_trap_info(ctxt->trap_ctxt);
 
-		ctxt->ldt_ents = 0;
+	ctxt->ldt_ents = 0;
 
-		BUG_ON((unsigned long)gdt & ~PAGE_MASK);
+	BUG_ON((unsigned long)gdt & ~PAGE_MASK);
 
-		gdt_mfn = arbitrary_virt_to_mfn(gdt);
-		make_lowmem_page_readonly(gdt);
-		make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
+	gdt_mfn = arbitrary_virt_to_mfn(gdt);
+	make_lowmem_page_readonly(gdt);
+	make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
 
-		ctxt->gdt_frames[0] = gdt_mfn;
-		ctxt->gdt_ents      = GDT_ENTRIES;
+	ctxt->gdt_frames[0] = gdt_mfn;
+	ctxt->gdt_ents      = GDT_ENTRIES;
 
-		ctxt->kernel_ss = __KERNEL_DS;
-		ctxt->kernel_sp = idle->thread.sp0;
+	ctxt->kernel_ss = __KERNEL_DS;
+	ctxt->kernel_sp = idle->thread.sp0;
 
 #ifdef CONFIG_X86_32
-		ctxt->event_callback_cs     = __KERNEL_CS;
-		ctxt->failsafe_callback_cs  = __KERNEL_CS;
+	ctxt->event_callback_cs     = __KERNEL_CS;
+	ctxt->failsafe_callback_cs  = __KERNEL_CS;
 #else
-		ctxt->gs_base_kernel = per_cpu_offset(cpu);
-#endif
-		ctxt->event_callback_eip    =
-					(unsigned long)xen_hypervisor_callback;
-		ctxt->failsafe_callback_eip =
-					(unsigned long)xen_failsafe_callback;
-		ctxt->user_regs.cs = __KERNEL_CS;
-		per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
-	}
-#ifdef CONFIG_XEN_PVH
-	else {
-		/*
-		 * The vcpu comes on kernel page tables which have the NX pte
-		 * bit set. This means before DS/SS is touched, NX in
-		 * EFER must be set. Hence the following assembly glue code.
-		 */
-		ctxt->user_regs.eip = (unsigned long)xen_pvh_early_cpu_init;
-		ctxt->user_regs.rdi = cpu;
-		ctxt->user_regs.rsi = true;  /* entry == true */
-	}
+	ctxt->gs_base_kernel = per_cpu_offset(cpu);
 #endif
+	ctxt->event_callback_eip    =
+		(unsigned long)xen_hypervisor_callback;
+	ctxt->failsafe_callback_eip =
+		(unsigned long)xen_failsafe_callback;
+	ctxt->user_regs.cs = __KERNEL_CS;
+	per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
+
 	ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
 	ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
 	if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))

arch/x86/xen/smp.h

@@ -21,12 +21,4 @@ static inline int xen_smp_intr_init(unsigned int cpu)
 static inline void xen_smp_intr_free(unsigned int cpu) {}
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_XEN_PVH
-extern void xen_pvh_early_cpu_init(int cpu, bool entry);
-#else
-static inline void xen_pvh_early_cpu_init(int cpu, bool entry)
-{
-}
-#endif
-
 #endif

arch/x86/xen/xen-head.S

@@ -16,25 +16,6 @@
 #include <xen/interface/xen-mca.h>
 #include <asm/xen/interface.h>
 
-#ifdef CONFIG_XEN_PVH
-#define PVH_FEATURES_STR  "|writable_descriptor_tables|auto_translated_physmap|supervisor_mode_kernel"
-/* Note the lack of 'hvm_callback_vector'. Older hypervisor will
- * balk at this being part of XEN_ELFNOTE_FEATURES, so we put it in
- * XEN_ELFNOTE_SUPPORTED_FEATURES which older hypervisors will ignore.
- */
-#define PVH_FEATURES ((1 << XENFEAT_writable_page_tables) | \
-		      (1 << XENFEAT_auto_translated_physmap) | \
-		      (1 << XENFEAT_supervisor_mode_kernel) | \
-		      (1 << XENFEAT_hvm_callback_vector))
-/* The XENFEAT_writable_page_tables is not stricly necessary as we set that
- * up regardless whether this CONFIG option is enabled or not, but it
- * clarifies what the right flags need to be.
- */
-#else
-#define PVH_FEATURES_STR  ""
-#define PVH_FEATURES (0)
-#endif
-
 	__INIT
 ENTRY(startup_xen)
 	cld
@@ -54,41 +35,6 @@ ENTRY(startup_xen)
 
 	__FINIT
 
-#ifdef CONFIG_XEN_PVH
-/*
- * xen_pvh_early_cpu_init() - early PVH VCPU initialization
- * @cpu:   this cpu number (%rdi)
- * @entry: true if this is a secondary vcpu coming up on this entry
- *         point, false if this is the boot CPU being initialized for
- *         the first time (%rsi)
- *
- * Note: This is called as a function on the boot CPU, and is the entry point
- *       on the secondary CPU.
- */
-ENTRY(xen_pvh_early_cpu_init)
-	mov     %rsi, %r11
-
-	/* Gather features to see if NX implemented. */
-	mov     $0x80000001, %eax
-	cpuid
-	mov     %edx, %esi
-
-	mov     $MSR_EFER, %ecx
-	rdmsr
-	bts     $_EFER_SCE, %eax
-
-	bt      $20, %esi
-	jnc     1f      	/* No NX, skip setting it */
-	bts     $_EFER_NX, %eax
-1:	wrmsr
-#ifdef CONFIG_SMP
-	cmp     $0, %r11b
-	jne     cpu_bringup_and_idle
-#endif
-	ret
-
-#endif /* CONFIG_XEN_PVH */
-
 .pushsection .text
 	.balign PAGE_SIZE
 ENTRY(hypercall_page)
@@ -114,10 +60,10 @@ ENTRY(hypercall_page)
 #endif
 	ELFNOTE(Xen, XEN_ELFNOTE_ENTRY,          _ASM_PTR startup_xen)
 	ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page)
-	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,       .ascii "!writable_page_tables|pae_pgdir_above_4gb"; .asciz PVH_FEATURES_STR)
-	ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long (PVH_FEATURES) |
-						(1 << XENFEAT_writable_page_tables) |
-						(1 << XENFEAT_dom0))
+	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,
+		.ascii "!writable_page_tables|pae_pgdir_above_4gb")
+	ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES,
+		.long (1 << XENFEAT_writable_page_tables) | (1 << XENFEAT_dom0))
 	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "yes")
 	ELFNOTE(Xen, XEN_ELFNOTE_LOADER,         .asciz "generic")
 	ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID,

arch/x86/xen/xen-ops.h

@@ -146,5 +146,4 @@ __visible void xen_adjust_exception_frame(void);
 
 extern int xen_panic_handler_init(void);
 
-void xen_pvh_secondary_vcpu_init(int cpu);
 #endif /* XEN_OPS_H */

drivers/xen/events/events_base.c

@@ -1704,7 +1704,6 @@ void __init xen_init_IRQ(void)
 		pirq_eoi_map = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 		eoi_gmfn.gmfn = virt_to_gfn(pirq_eoi_map);
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_pirq_eoi_gmfn_v2, &eoi_gmfn);
-		/* TODO: No PVH support for PIRQ EOI */
 		if (rc != 0) {
 			free_page((unsigned long) pirq_eoi_map);
 			pirq_eoi_map = NULL;

include/xen/xen.h

@@ -29,17 +29,6 @@ extern enum xen_domain_type xen_domain_type;
 #define xen_initial_domain()	(0)
 #endif	/* CONFIG_XEN_DOM0 */
 
-#ifdef CONFIG_XEN_PVH
-/* This functionality exists only for x86. The XEN_PVHVM support exists
- * only in x86 world - hence on ARM it will be always disabled.
- * N.B. ARM guests are neither PV nor HVM nor PVHVM.
- * It's a bit like PVH but is different also (it's further towards the H
- * end of the spectrum than even PVH).
- */
-#include <xen/features.h>
-#define xen_pvh_domain() (xen_pv_domain() && \
-			  xen_feature(XENFEAT_auto_translated_physmap))
-#else
 #define xen_pvh_domain()	(0)
-#endif
+
 #endif	/* _XEN_XEN_H */