From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 12 Aug 2010 16:09:41 +0000 (-0700)
Subject: Merge branch 'stable/xen-swiotlb-0.8.6' of git://git.kernel.org/pub/scm/linux/kernel... 
X-Git-Tag: firefly_0821_release~9833^2~808
X-Git-Url: http://plrg.eecs.uci.edu/git/?a=commitdiff_plain;h=26f0cf91813bdc8e61595f8ad6660251e2ee9cf6;p=firefly-linux-kernel-4.4.55.git

Merge branch 'stable/xen-swiotlb-0.8.6' of git://git./linux/kernel/git/konrad/xen

* 'stable/xen-swiotlb-0.8.6' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  x86: Detect whether we should use Xen SWIOTLB.
  pci-swiotlb-xen: Add glue code to setup dma_ops utilizing xen_swiotlb_* functions.
  swiotlb-xen: SWIOTLB library for Xen PV guest with PCI passthrough.
  xen/mmu: inhibit vmap aliases rather than trying to clear them out
  vmap: add flag to allow lazy unmap to be disabled at runtime
  xen: Add xen_create_contiguous_region
  xen: Rename the balloon lock
  xen: Allow unprivileged Xen domains to create iomap pages
  xen: use _PAGE_IOMAP in ioremap to do machine mappings

Fix up trivial conflicts (adding both xen swiotlb and xen pci platform
driver setup close to each other) in drivers/xen/{Kconfig,Makefile} and
include/xen/xen-ops.h
---

26f0cf91813bdc8e61595f8ad6660251e2ee9cf6
diff --cc arch/x86/xen/mmu.c
index 413b19b3d0fe,ef5728dde8f3..42086ac406af
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@@ -56,10 -59,11 +59,12 @@@
  #include <asm/xen/hypercall.h>
  #include <asm/xen/hypervisor.h>
  
+ #include <xen/xen.h>
  #include <xen/page.h>
  #include <xen/interface/xen.h>
 +#include <xen/interface/hvm/hvm_op.h>
  #include <xen/interface/version.h>
+ #include <xen/interface/memory.h>
  #include <xen/hvc-console.h>
  
  #include "multicalls.h"
@@@ -1940,42 -2024,206 +2025,240 @@@ void __init xen_init_mmu_ops(void
  	x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
  	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
  	pv_mmu_ops = xen_mmu_ops;
+ 
+ 	vmap_lazy_unmap = false;
+ }
+ 
+ /* Protected by xen_reservation_lock. */
+ #define MAX_CONTIG_ORDER 9 /* 2MB */
+ static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER];
+ 
+ #define VOID_PTE (mfn_pte(0, __pgprot(0)))
+ static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
+ 				unsigned long *in_frames,
+ 				unsigned long *out_frames)
+ {
+ 	int i;
+ 	struct multicall_space mcs;
+ 
+ 	xen_mc_batch();
+ 	for (i = 0; i < (1UL<<order); i++, vaddr += PAGE_SIZE) {
+ 		mcs = __xen_mc_entry(0);
+ 
+ 		if (in_frames)
+ 			in_frames[i] = virt_to_mfn(vaddr);
+ 
+ 		MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
+ 		set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
+ 
+ 		if (out_frames)
+ 			out_frames[i] = virt_to_pfn(vaddr);
+ 	}
+ 	xen_mc_issue(0);
+ }
+ 
+ /*
+  * Update the pfn-to-mfn mappings for a virtual address range, either to
+  * point to an array of mfns, or contiguously from a single starting
+  * mfn.
+  */
+ static void xen_remap_exchanged_ptes(unsigned long vaddr, int order,
+ 				     unsigned long *mfns,
+ 				     unsigned long first_mfn)
+ {
+ 	unsigned i, limit;
+ 	unsigned long mfn;
+ 
+ 	xen_mc_batch();
+ 
+ 	limit = 1u << order;
+ 	for (i = 0; i < limit; i++, vaddr += PAGE_SIZE) {
+ 		struct multicall_space mcs;
+ 		unsigned flags;
+ 
+ 		mcs = __xen_mc_entry(0);
+ 		if (mfns)
+ 			mfn = mfns[i];
+ 		else
+ 			mfn = first_mfn + i;
+ 
+ 		if (i < (limit - 1))
+ 			flags = 0;
+ 		else {
+ 			if (order == 0)
+ 				flags = UVMF_INVLPG | UVMF_ALL;
+ 			else
+ 				flags = UVMF_TLB_FLUSH | UVMF_ALL;
+ 		}
+ 
+ 		MULTI_update_va_mapping(mcs.mc, vaddr,
+ 				mfn_pte(mfn, PAGE_KERNEL), flags);
+ 
+ 		set_phys_to_machine(virt_to_pfn(vaddr), mfn);
+ 	}
+ 
+ 	xen_mc_issue(0);
+ }
+ 
+ /*
+  * Perform the hypercall to exchange a region of our pfns to point to
+  * memory with the required contiguous alignment.  Takes the pfns as
+  * input, and populates mfns as output.
+  *
+  * Returns a success code indicating whether the hypervisor was able to
+  * satisfy the request or not.
+  */
+ static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
+ 			       unsigned long *pfns_in,
+ 			       unsigned long extents_out,
+ 			       unsigned int order_out,
+ 			       unsigned long *mfns_out,
+ 			       unsigned int address_bits)
+ {
+ 	long rc;
+ 	int success;
+ 
+ 	struct xen_memory_exchange exchange = {
+ 		.in = {
+ 			.nr_extents   = extents_in,
+ 			.extent_order = order_in,
+ 			.extent_start = pfns_in,
+ 			.domid        = DOMID_SELF
+ 		},
+ 		.out = {
+ 			.nr_extents   = extents_out,
+ 			.extent_order = order_out,
+ 			.extent_start = mfns_out,
+ 			.address_bits = address_bits,
+ 			.domid        = DOMID_SELF
+ 		}
+ 	};
+ 
+ 	BUG_ON(extents_in << order_in != extents_out << order_out);
+ 
+ 	rc = HYPERVISOR_memory_op(XENMEM_exchange, &exchange);
+ 	success = (exchange.nr_exchanged == extents_in);
+ 
+ 	BUG_ON(!success && ((exchange.nr_exchanged != 0) || (rc == 0)));
+ 	BUG_ON(success && (rc != 0));
+ 
+ 	return success;
+ }
+ 
+ int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
+ 				 unsigned int address_bits)
+ {
+ 	unsigned long *in_frames = discontig_frames, out_frame;
+ 	unsigned long  flags;
+ 	int            success;
+ 
+ 	/*
+ 	 * Currently an auto-translated guest will not perform I/O, nor will
+ 	 * it require PAE page directories below 4GB. Therefore any calls to
+ 	 * this function are redundant and can be ignored.
+ 	 */
+ 
+ 	if (xen_feature(XENFEAT_auto_translated_physmap))
+ 		return 0;
+ 
+ 	if (unlikely(order > MAX_CONTIG_ORDER))
+ 		return -ENOMEM;
+ 
+ 	memset((void *) vstart, 0, PAGE_SIZE << order);
+ 
+ 	spin_lock_irqsave(&xen_reservation_lock, flags);
+ 
+ 	/* 1. Zap current PTEs, remembering MFNs. */
+ 	xen_zap_pfn_range(vstart, order, in_frames, NULL);
+ 
+ 	/* 2. Get a new contiguous memory extent. */
+ 	out_frame = virt_to_pfn(vstart);
+ 	success = xen_exchange_memory(1UL << order, 0, in_frames,
+ 				      1, order, &out_frame,
+ 				      address_bits);
+ 
+ 	/* 3. Map the new extent in place of old pages. */
+ 	if (success)
+ 		xen_remap_exchanged_ptes(vstart, order, NULL, out_frame);
+ 	else
+ 		xen_remap_exchanged_ptes(vstart, order, in_frames, 0);
+ 
+ 	spin_unlock_irqrestore(&xen_reservation_lock, flags);
+ 
+ 	return success ? 0 : -ENOMEM;
+ }
+ EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
+ 
+ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
+ {
+ 	unsigned long *out_frames = discontig_frames, in_frame;
+ 	unsigned long  flags;
+ 	int success;
+ 
+ 	if (xen_feature(XENFEAT_auto_translated_physmap))
+ 		return;
+ 
+ 	if (unlikely(order > MAX_CONTIG_ORDER))
+ 		return;
+ 
+ 	memset((void *) vstart, 0, PAGE_SIZE << order);
+ 
+ 	spin_lock_irqsave(&xen_reservation_lock, flags);
+ 
+ 	/* 1. Find start MFN of contiguous extent. */
+ 	in_frame = virt_to_mfn(vstart);
+ 
+ 	/* 2. Zap current PTEs. */
+ 	xen_zap_pfn_range(vstart, order, NULL, out_frames);
+ 
+ 	/* 3. Do the exchange for non-contiguous MFNs. */
+ 	success = xen_exchange_memory(1, order, &in_frame, 1UL << order,
+ 					0, out_frames, 0);
+ 
+ 	/* 4. Map new pages in place of old pages. */
+ 	if (success)
+ 		xen_remap_exchanged_ptes(vstart, order, out_frames, 0);
+ 	else
+ 		xen_remap_exchanged_ptes(vstart, order, NULL, in_frame);
+ 
+ 	spin_unlock_irqrestore(&xen_reservation_lock, flags);
  }
+ EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
  
 +#ifdef CONFIG_XEN_PVHVM
 +static void xen_hvm_exit_mmap(struct mm_struct *mm)
 +{
 +	struct xen_hvm_pagetable_dying a;
 +	int rc;
 +
 +	a.domid = DOMID_SELF;
 +	a.gpa = __pa(mm->pgd);
 +	rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a);
 +	WARN_ON_ONCE(rc < 0);
 +}
 +
 +static int is_pagetable_dying_supported(void)
 +{
 +	struct xen_hvm_pagetable_dying a;
 +	int rc = 0;
 +
 +	a.domid = DOMID_SELF;
 +	a.gpa = 0x00;
 +	rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a);
 +	if (rc < 0) {
 +		printk(KERN_DEBUG "HVMOP_pagetable_dying not supported\n");
 +		return 0;
 +	}
 +	return 1;
 +}
 +
 +void __init xen_hvm_init_mmu_ops(void)
 +{
 +	if (is_pagetable_dying_supported())
 +		pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
 +}
 +#endif
 +
  #ifdef CONFIG_XEN_DEBUG_FS
  
  static struct dentry *d_mmu_debug;
diff --cc drivers/xen/Kconfig
index 0a8826936639,97199c2a64a0..60d71e9abe9f
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@@ -62,13 -62,8 +62,18 @@@ config XEN_SYS_HYPERVISO
  	 virtual environment, /sys/hypervisor will still be present,
  	 but will have no xen contents.
  
 +config XEN_PLATFORM_PCI
 +	tristate "xen platform pci device driver"
 +	depends on XEN_PVHVM
 +	default m
 +	help
 +	  Driver for the Xen PCI Platform device: it is responsible for
 +	  initializing xenbus and grant_table when running in a Xen HVM
 +	  domain. As a consequence this driver is required to run any Xen PV
 +	  frontend on Xen HVM.
++
+ config SWIOTLB_XEN
+ 	def_bool y
+ 	depends on SWIOTLB
+ 
  endmenu
diff --cc drivers/xen/Makefile
index e392fb776af3,85f84cff8104..fcaf838f54be
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@@ -10,4 -10,4 +10,5 @@@ obj-$(CONFIG_XEN_BALLOON)	+= balloon.
  obj-$(CONFIG_XEN_DEV_EVTCHN)	+= evtchn.o
  obj-$(CONFIG_XENFS)		+= xenfs/
  obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
 +obj-$(CONFIG_XEN_PLATFORM_PCI)	+= platform-pci.o
+ obj-$(CONFIG_SWIOTLB_XEN)	+= swiotlb-xen.o
diff --cc include/xen/xen-ops.h
index 46bc81ef74c6,d789c937c48a..351f4051f6d8
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@@ -15,6 -14,10 +15,12 @@@ void xen_mm_unpin_all(void)
  void xen_timer_resume(void);
  void xen_arch_resume(void);
  
 +int xen_setup_shutdown_event(void);
 +
+ extern unsigned long *xen_contiguous_bitmap;
+ int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
+ 				unsigned int address_bits);
+ 
+ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order);
+ 
  #endif /* INCLUDE_XEN_OPS_H */