Merge branch 'stable/autoballoon.v5.2' into stable/for-linus-3.5

* stable/autoballoon.v5.2:
  xen/setup: update VA mapping when releasing memory during setup
  xen/setup: Combine the two hypercall functions - since they are quite similar.
  xen/setup: Populate freed MFNs from non-RAM E820 entries and gaps to E820 RAM
  xen/setup: Only print "Freeing XXX-YYY pfn range: Z pages freed" if Z > 0
  xen/p2m: An early bootup variant of set_phys_to_machine
  xen/p2m: Collapse early_alloc_p2m_middle redundant checks.
  xen/p2m: Allow alloc_p2m_middle to call reserve_brk depending on argument
  xen/p2m: Move code around to allow for better re-usage.

5 files changed, 206 insertions, 94 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index eca90e5..d1f9a04 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1316,7 +1316,6 @@ asmlinkage void __init xen_start_kernel(void)
 
 	xen_raw_console_write("mapping kernel into physical memory\n");
 	pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
-	xen_ident_map_ISA();
 
 	/* Allocate and initialize top and mid mfn levels for p2m structure */
 	xen_build_mfn_list_list();
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index b8e2794..b756d8c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1929,29 +1929,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 }
 
-void __init xen_ident_map_ISA(void)
-{
-	unsigned long pa;
-
-	/*
-	 * If we're dom0, then linear map the ISA machine addresses into
-	 * the kernel's address space.
-	 */
-	if (!xen_initial_domain())
-		return;
-
-	xen_raw_printk("Xen: setup ISA identity maps\n");
-
-	for (pa = ISA_START_ADDRESS; pa < ISA_END_ADDRESS; pa += PAGE_SIZE) {
-		pte_t pte = mfn_pte(PFN_DOWN(pa), PAGE_KERNEL_IO);
-
-		if (HYPERVISOR_update_va_mapping(PAGE_OFFSET + pa, pte, 0))
-			BUG();
-	}
-
-	xen_flush_tlb();
-}
-
 static void __init xen_post_allocator_init(void)
 {
 	pv_mmu_ops.set_pte = xen_set_pte;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 1b267e7..ffd08c4 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -499,16 +499,18 @@ static bool alloc_p2m(unsigned long pfn)
 	return true;
 }
 
-static bool __init __early_alloc_p2m(unsigned long pfn)
+static bool __init early_alloc_p2m_middle(unsigned long pfn, bool check_boundary)
 {
 	unsigned topidx, mididx, idx;
+	unsigned long *p2m;
+	unsigned long *mid_mfn_p;
 
 	topidx = p2m_top_index(pfn);
 	mididx = p2m_mid_index(pfn);
 	idx = p2m_index(pfn);
 
 	/* Pfff.. No boundary cross-over, lets get out. */
-	if (!idx)
+	if (!idx && check_boundary)
 		return false;
 
 	WARN(p2m_top[topidx][mididx] == p2m_identity,
@@ -522,24 +524,66 @@ static bool __init __early_alloc_p2m(unsigned long pfn)
 		return false;
 
 	/* Boundary cross-over for the edges: */
-	if (idx) {
-		unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
-		unsigned long *mid_mfn_p;
+	p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
 
-		p2m_init(p2m);
+	p2m_init(p2m);
 
-		p2m_top[topidx][mididx] = p2m;
+	p2m_top[topidx][mididx] = p2m;
 
-		/* For save/restore we need to MFN of the P2M saved */
-		
-		mid_mfn_p = p2m_top_mfn_p[topidx];
-		WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
-			"P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
-			topidx, mididx);
-		mid_mfn_p[mididx] = virt_to_mfn(p2m);
+	/* For save/restore we need to MFN of the P2M saved */
+
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
+		"P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
+		topidx, mididx);
+	mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
+	return true;
+}
+
+static bool __init early_alloc_p2m(unsigned long pfn)
+{
+	unsigned topidx = p2m_top_index(pfn);
+	unsigned long *mid_mfn_p;
+	unsigned long **mid;
+
+	mid = p2m_top[topidx];
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	if (mid == p2m_mid_missing) {
+		mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+
+		p2m_mid_init(mid);
+
+		p2m_top[topidx] = mid;
 
+		BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
 	}
-	return idx != 0;
+	/* And the save/restore P2M tables.. */
+	if (mid_mfn_p == p2m_mid_missing_mfn) {
+		mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+		p2m_mid_mfn_init(mid_mfn_p);
+
+		p2m_top_mfn_p[topidx] = mid_mfn_p;
+		p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
+		/* Note: we don't set mid_mfn_p[midix] here,
+		 * look in early_alloc_p2m_middle */
+	}
+	return true;
+}
+bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
+		if (!early_alloc_p2m(pfn))
+			return false;
+
+		if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/))
+			return false;
+
+		if (!__set_phys_to_machine(pfn, mfn))
+			return false;
+	}
+
+	return true;
 }
 unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 				      unsigned long pfn_e)
@@ -559,35 +603,11 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 		pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
 		pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
 	{
-		unsigned topidx = p2m_top_index(pfn);
-		unsigned long *mid_mfn_p;
-		unsigned long **mid;
-
-		mid = p2m_top[topidx];
-		mid_mfn_p = p2m_top_mfn_p[topidx];
-		if (mid == p2m_mid_missing) {
-			mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
-
-			p2m_mid_init(mid);
-
-			p2m_top[topidx] = mid;
-
-			BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
-		}
-		/* And the save/restore P2M tables.. */
-		if (mid_mfn_p == p2m_mid_missing_mfn) {
-			mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
-			p2m_mid_mfn_init(mid_mfn_p);
-
-			p2m_top_mfn_p[topidx] = mid_mfn_p;
-			p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
-			/* Note: we don't set mid_mfn_p[midix] here,
-		 	 * look in __early_alloc_p2m */
-		}
+		WARN_ON(!early_alloc_p2m(pfn));
 	}
 
-	__early_alloc_p2m(pfn_s);
-	__early_alloc_p2m(pfn_e);
+	early_alloc_p2m_middle(pfn_s, true);
+	early_alloc_p2m_middle(pfn_e, true);
 
 	for (pfn = pfn_s; pfn < pfn_e; pfn++)
 		if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1ba8dff..3ebba07 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -26,7 +26,6 @@
 #include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
 #include <xen/features.h>
-
 #include "xen-ops.h"
 #include "vdso.h"
 
@@ -84,8 +83,8 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 }
 
-static unsigned long __init xen_release_chunk(unsigned long start,
-					      unsigned long end)
+static unsigned long __init xen_do_chunk(unsigned long start,
+					 unsigned long end, bool release)
 {
 	struct xen_memory_reservation reservation = {
 		.address_bits = 0,
@@ -96,30 +95,138 @@ static unsigned long __init xen_release_chunk(unsigned long start,
 	unsigned long pfn;
 	int ret;
 
-	for(pfn = start; pfn < end; pfn++) {
+	for (pfn = start; pfn < end; pfn++) {
+		unsigned long frame;
 		unsigned long mfn = pfn_to_mfn(pfn);
 
-		/* Make sure pfn exists to start with */
-		if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
-			continue;
-
-		set_xen_guest_handle(reservation.extent_start, &mfn);
+		if (release) {
+			/* Make sure pfn exists to start with */
+			if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
+				continue;
+			frame = mfn;
+		} else {
+			if (mfn != INVALID_P2M_ENTRY)
+				continue;
+			frame = pfn;
+		}
+		set_xen_guest_handle(reservation.extent_start, &frame);
 		reservation.nr_extents = 1;
 
-		ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
+		ret = HYPERVISOR_memory_op(release ? XENMEM_decrease_reservation : XENMEM_populate_physmap,
 					   &reservation);
-		WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
+		WARN(ret != 1, "Failed to %s pfn %lx err=%d\n",
+		     release ? "release" : "populate", pfn, ret);
+
 		if (ret == 1) {
-			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+			if (!early_set_phys_to_machine(pfn, release ? INVALID_P2M_ENTRY : frame)) {
+				if (release)
+					break;
+				set_xen_guest_handle(reservation.extent_start, &frame);
+				reservation.nr_extents = 1;
+				ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
+							   &reservation);
+				break;
+			}
 			len++;
-		}
+		} else
+			break;
 	}
-	printk(KERN_INFO "Freeing  %lx-%lx pfn range: %lu pages freed\n",
-	       start, end, len);
+	if (len)
+		printk(KERN_INFO "%s %lx-%lx pfn range: %lu pages %s\n",
+		       release ? "Freeing" : "Populating",
+		       start, end, len,
+		       release ? "freed" : "added");
 
 	return len;
 }
 
+static unsigned long __init xen_release_chunk(unsigned long start,
+					      unsigned long end)
+{
+	return xen_do_chunk(start, end, true);
+}
+
+static unsigned long __init xen_populate_chunk(
+	const struct e820entry *list, size_t map_size,
+	unsigned long max_pfn, unsigned long *last_pfn,
+	unsigned long credits_left)
+{
+	const struct e820entry *entry;
+	unsigned int i;
+	unsigned long done = 0;
+	unsigned long dest_pfn;
+
+	for (i = 0, entry = list; i < map_size; i++, entry++) {
+		unsigned long credits = credits_left;
+		unsigned long s_pfn;
+		unsigned long e_pfn;
+		unsigned long pfns;
+		long capacity;
+
+		if (credits <= 0)
+			break;
+
+		if (entry->type != E820_RAM)
+			continue;
+
+		e_pfn = PFN_UP(entry->addr + entry->size);
+
+		/* We only care about E820 after the xen_start_info->nr_pages */
+		if (e_pfn <= max_pfn)
+			continue;
+
+		s_pfn = PFN_DOWN(entry->addr);
+		/* If the E820 falls within the nr_pages, we want to start
+		 * at the nr_pages PFN.
+		 * If that would mean going past the E820 entry, skip it
+		 */
+		if (s_pfn <= max_pfn) {
+			capacity = e_pfn - max_pfn;
+			dest_pfn = max_pfn;
+		} else {
+			/* last_pfn MUST be within E820_RAM regions */
+			if (*last_pfn && e_pfn >= *last_pfn)
+				s_pfn = *last_pfn;
+			capacity = e_pfn - s_pfn;
+			dest_pfn = s_pfn;
+		}
+		/* If we had filled this E820_RAM entry, go to the next one. */
+		if (capacity <= 0)
+			continue;
+
+		if (credits > capacity)
+			credits = capacity;
+
+		pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false);
+		done += pfns;
+		credits_left -= pfns;
+		*last_pfn = (dest_pfn + pfns);
+	}
+	return done;
+}
+
+static void __init xen_set_identity_and_release_chunk(
+	unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
+	unsigned long *released, unsigned long *identity)
+{
+	unsigned long pfn;
+
+	/*
+	 * If the PFNs are currently mapped, the VA mapping also needs
+	 * to be updated to be 1:1.
+	 */
+	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
+		(void)HYPERVISOR_update_va_mapping(
+			(unsigned long)__va(pfn << PAGE_SHIFT),
+			mfn_pte(pfn, PAGE_KERNEL_IO), 0);
+
+	if (start_pfn < nr_pages)
+		*released += xen_release_chunk(
+			start_pfn, min(end_pfn, nr_pages));
+
+	*identity += set_phys_range_identity(start_pfn, end_pfn);
+}
+
 static unsigned long __init xen_set_identity_and_release(
 	const struct e820entry *list, size_t map_size, unsigned long nr_pages)
 {
@@ -142,7 +249,6 @@ static unsigned long __init xen_set_identity_and_release(
 	 */
 	for (i = 0, entry = list; i < map_size; i++, entry++) {
 		phys_addr_t end = entry->addr + entry->size;
-
 		if (entry->type == E820_RAM || i == map_size - 1) {
 			unsigned long start_pfn = PFN_DOWN(start);
 			unsigned long end_pfn = PFN_UP(end);
@@ -150,20 +256,19 @@ static unsigned long __init xen_set_identity_and_release(
 			if (entry->type == E820_RAM)
 				end_pfn = PFN_UP(entry->addr);
 
-			if (start_pfn < end_pfn) {
-				if (start_pfn < nr_pages)
-					released += xen_release_chunk(
-						start_pfn, min(end_pfn, nr_pages));
+			if (start_pfn < end_pfn)
+				xen_set_identity_and_release_chunk(
+					start_pfn, end_pfn, nr_pages,
+					&released, &identity);
 
-				identity += set_phys_range_identity(
-					start_pfn, end_pfn);
-			}
 			start = end;
 		}
 	}
 
-	printk(KERN_INFO "Released %lu pages of unused memory\n", released);
-	printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
+	if (released)
+		printk(KERN_INFO "Released %lu pages of unused memory\n", released);
+	if (identity)
+		printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
 
 	return released;
 }
@@ -217,7 +322,9 @@ char * __init xen_memory_setup(void)
 	int rc;
 	struct xen_memory_map memmap;
 	unsigned long max_pages;
+	unsigned long last_pfn = 0;
 	unsigned long extra_pages = 0;
+	unsigned long populated;
 	int i;
 	int op;
 
@@ -257,9 +364,20 @@ char * __init xen_memory_setup(void)
 	 */
 	xen_released_pages = xen_set_identity_and_release(
 		map, memmap.nr_entries, max_pfn);
-	extra_pages += xen_released_pages;
 
 	/*
+	 * Populate back the non-RAM pages and E820 gaps that had been
+	 * released. */
+	populated = xen_populate_chunk(map, memmap.nr_entries,
+			max_pfn, &last_pfn, xen_released_pages);
+
+	extra_pages += (xen_released_pages - populated);
+
+	if (last_pfn > max_pfn) {
+		max_pfn = min(MAX_DOMAIN_PAGES, last_pfn);
+		mem_end = PFN_PHYS(max_pfn);
+	}
+	/*
 	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
 	 * factor the base size.  On non-highmem systems, the base
 	 * size is the full initial memory allocation; on highmem it
@@ -272,7 +390,6 @@ char * __init xen_memory_setup(void)
 	 */
 	extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
 			  extra_pages);
-
 	i = 0;
 	while (i < memmap.nr_entries) {
 		u64 addr = map[i].addr;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index b095739..506fa08 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -28,7 +28,6 @@ void xen_setup_shared_info(void);
 void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
-void xen_ident_map_ISA(void);
 void xen_reserve_top(void);
 extern unsigned long xen_max_p2m_pfn;