x86/xen: Move pv specific parts of arch/x86/xen/mmu.c to mmu_pv.c

There are some PV specific functions in arch/x86/xen/mmu.c which can be
moved to mmu_pv.c. This in turn enables to build multicalls.c dependent
on CONFIG_XEN_PV.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: xen-devel@lists.xenproject.org
Cc: virtualization@lists.linux-foundation.org
Cc: akataria@vmware.com
Cc: rusty@rustcorp.com.au
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/20180828074026.820-3-jgross@suse.com

1 files changed, 138 insertions, 0 deletions

diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2fe5c9b1816b..b0691c7a3951 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -99,6 +99,12 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
 #endif /* CONFIG_X86_64 */
 
 /*
+ * Protects atomic reservation decrease/increase against concurrent increases.
+ * Also protects non-atomic updates of current_pages and balloon lists.
+ */
+DEFINE_SPINLOCK(xen_reservation_lock);
+
+/*
  * Note about cr3 (pagetable base) values:
  *
  * xen_cr3 contains the current logical cr3 value; it contains the
@@ -2662,6 +2668,138 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 }
 EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
 
+static noinline void xen_flush_tlb_all(void)
+{
+	struct mmuext_op *op;
+	struct multicall_space mcs;
+
+	preempt_disable();
+
+	mcs = xen_mc_entry(sizeof(*op));
+
+	op = mcs.args;
+	op->cmd = MMUEXT_TLB_FLUSH_ALL;
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
+
+#define REMAP_BATCH_SIZE 16
+
+struct remap_data {
+	xen_pfn_t *pfn;
+	bool contiguous;
+	bool no_translate;
+	pgprot_t prot;
+	struct mmu_update *mmu_update;
+};
+
+static int remap_area_pfn_pte_fn(pte_t *ptep, pgtable_t token,
+				 unsigned long addr, void *data)
+{
+	struct remap_data *rmd = data;
+	pte_t pte = pte_mkspecial(mfn_pte(*rmd->pfn, rmd->prot));
+
+	/*
+	 * If we have a contiguous range, just update the pfn itself,
+	 * else update pointer to be "next pfn".
+	 */
+	if (rmd->contiguous)
+		(*rmd->pfn)++;
+	else
+		rmd->pfn++;
+
+	rmd->mmu_update->ptr = virt_to_machine(ptep).maddr;
+	rmd->mmu_update->ptr |= rmd->no_translate ?
+		MMU_PT_UPDATE_NO_TRANSLATE :
+		MMU_NORMAL_PT_UPDATE;
+	rmd->mmu_update->val = pte_val_ma(pte);
+	rmd->mmu_update++;
+
+	return 0;
+}
+
+int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
+		  xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot,
+		  unsigned int domid, bool no_translate, struct page **pages)
+{
+	int err = 0;
+	struct remap_data rmd;
+	struct mmu_update mmu_update[REMAP_BATCH_SIZE];
+	unsigned long range;
+	int mapped = 0;
+
+	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
+
+	rmd.pfn = pfn;
+	rmd.prot = prot;
+	/*
+	 * We use the err_ptr to indicate if there we are doing a contiguous
+	 * mapping or a discontigious mapping.
+	 */
+	rmd.contiguous = !err_ptr;
+	rmd.no_translate = no_translate;
+
+	while (nr) {
+		int index = 0;
+		int done = 0;
+		int batch = min(REMAP_BATCH_SIZE, nr);
+		int batch_left = batch;
+
+		range = (unsigned long)batch << PAGE_SHIFT;
+
+		rmd.mmu_update = mmu_update;
+		err = apply_to_page_range(vma->vm_mm, addr, range,
+					  remap_area_pfn_pte_fn, &rmd);
+		if (err)
+			goto out;
+
+		/*
+		 * We record the error for each page that gives an error, but
+		 * continue mapping until the whole set is done
+		 */
+		do {
+			int i;
+
+			err = HYPERVISOR_mmu_update(&mmu_update[index],
+						    batch_left, &done, domid);
+
+			/*
+			 * @err_ptr may be the same buffer as @gfn, so
+			 * only clear it after each chunk of @gfn is
+			 * used.
+			 */
+			if (err_ptr) {
+				for (i = index; i < index + done; i++)
+					err_ptr[i] = 0;
+			}
+			if (err < 0) {
+				if (!err_ptr)
+					goto out;
+				err_ptr[i] = err;
+				done++; /* Skip failed frame. */
+			} else
+				mapped += done;
+			batch_left -= done;
+			index += done;
+		} while (batch_left);
+
+		nr -= batch;
+		addr += range;
+		if (err_ptr)
+			err_ptr += batch;
+		cond_resched();
+	}
+out:
+
+	xen_flush_tlb_all();
+
+	return err < 0 ? err : mapped;
+}
+EXPORT_SYMBOL_GPL(xen_remap_pfn);
+
 #ifdef CONFIG_KEXEC_CORE
 phys_addr_t paddr_vmcoreinfo_note(void)
 {