Re: Load increase after memory upgrade (part2)

[Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>]

[-- Attachment #1: Type: text/plain, Size: 467 bytes --]

On Wed, Jan 25, 2012 at 08:06:12PM +0100, Carsten Schiers wrote:
> Some news: in order to prepare a clean setting, I upgraded to 3.2.1 kernel. I noticed that the load increase is
> reduced a bit, but noticably. It's only a simple test, running the DomU for 2 minutes, but the idle load is aprox.
> 
>   - 2.6.32 pvops		12-13%
>   - 3.2.1 pvops		10-11%
>   - 2.6.34 XenoLinux	7-8%

I took a stab at Jan's idea - it compiles but I hadn't been able to properly test it.

[-- Attachment #2: vmalloc_using_xen_limit_pages.patch --]
[-- Type: text/plain, Size: 6845 bytes --]

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 87f6673..6bb6f68 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -47,6 +47,7 @@
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 
 #include <trace/events/xen.h>
 
@@ -2073,6 +2074,7 @@ void __init xen_init_mmu_ops(void)
 /* Protected by xen_reservation_lock. */
 #define MAX_CONTIG_ORDER 9 /* 2MB */
 static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER];
+static unsigned long limited_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,
@@ -2097,6 +2099,36 @@ static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
 	}
 	xen_mc_issue(0);
 }
+static int xen_zap_page_range(struct page *pages, unsigned int order,
+				unsigned long *in_frames,
+				unsigned long *out_frames,
+				void *limit_bitmap)
+{
+	int i, n = 0;
+	struct multicall_space mcs;
+	struct page *page;
+	xen_mc_batch();
+	for (i = 0; i < (1UL<<order); i++) {
+		if (!test_bit(i, limit_bitmap))
+			continue;
+		page = &pages[i];
+		mcs = __xen_mc_entry(0);
+
+		if (in_frames)
+			in_frames[i] = pfn_to_mfn(page_to_pfn(page));
+
+		MULTI_update_va_mapping(mcs.mc, (unsigned long)page_address(page), VOID_PTE, 0);
+		__set_phys_to_machine(page_to_pfn(page), INVALID_P2M_ENTRY);
+
+		if (out_frames)
+			out_frames[i] = page_to_pfn(page);
+		++n;
+
+	}
+	xen_mc_issue(0);
+
+	return n;
+}
 
 /*
  * Update the pfn-to-mfn mappings for a virtual address range, either to
@@ -2140,6 +2172,49 @@ static void xen_remap_exchanged_ptes(unsigned long vaddr, int order,
 
 	xen_mc_issue(0);
 }
+static void xen_remap_exchanged_pages(struct page *pages, int order,
+				     unsigned long *mfns,
+				     unsigned long first_mfn,
+				     void *limit_map)
+{
+	unsigned i, limit;
+	unsigned long mfn;
+	struct page *page;
+
+	xen_mc_batch();
+
+	limit = 1u << order;
+	for (i = 0; i < limit; i++) {
+		struct multicall_space mcs;
+		unsigned flags;
+
+		if (!test_bit(i, limit_map))
+			continue;
+		page = &pages[i];
+		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, (unsigned long)page_address(page),
+				mfn_pte(mfn, PAGE_KERNEL), flags);
+
+		set_phys_to_machine(page_to_pfn(page), mfn);
+	}
+
+	xen_mc_issue(0);
+}
+
 
 /*
  * Perform the hypercall to exchange a region of our pfns to point to
@@ -2266,6 +2341,90 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
 }
 EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
 
+int xen_limit_pages_to_max_mfn(struct page *pages, unsigned int order,
+			       unsigned int address_bits)
+{
+	unsigned long *in_frames = discontig_frames, *out_frames = limited_frames;
+	unsigned long  flags;
+	struct page *page;
+	int success;
+	int i, n = 0;
+	unsigned long _limit_map;
+	unsigned long *limit_map;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return 0;
+
+	if (unlikely(order > MAX_CONTIG_ORDER))
+		return -ENOMEM;
+
+	if (BITS_PER_LONG >> order) {
+		limit_map = kzalloc(BITS_TO_LONGS(1U << order) *
+				    sizeof(*limit_map), GFP_KERNEL);
+		if (unlikely(!limit_map))
+			return -ENOMEM;
+	} else
+		limit_map = &_limit_map;
+
+	/* 0. Construct our per page bitmap lookup. */
+
+	if (address_bits && (address_bits < PAGE_SHIFT))
+			return -EINVAL;
+
+	if (order)
+		bitmap_zero(limit_map, 1U << order);
+	else
+		__set_bit(0, limit_map);
+
+	/* 1. Clear the pages */
+	for (i = 0; i < 1ULL << order; i++) {
+		void *vaddr;
+		page = &pages[i];
+		vaddr = page_address(page);
+		if (address_bits) {
+			if (!pfn_to_mfn(virt_to_mfn(vaddr)) >> (address_bits - PAGE_SHIFT))
+				continue;
+			__set_bit(i, limit_map);
+		}
+		if (!PageHighMem(page))
+			memset(vaddr, 0, PAGE_SIZE);
+		else {
+			memset(kmap(page), 0, PAGE_SIZE);
+			kunmap(page);
+			++n;
+		}
+	}
+	/* Check to see if we actually have to do any work. */
+	if (bitmap_empty(limit_map, 1U << order)) {
+		if (limit_map != &_limit_map)
+			kfree(limit_map);
+		return 0;
+	}
+	if (n)
+		kmap_flush_unused();
+
+	spin_lock_irqsave(&xen_reservation_lock, flags);
+
+	/* 2. Zap current PTEs. */
+	n = xen_zap_page_range(pages, order, in_frames, NULL /*out_frames */, limit_map);
+
+	/* 3. Do the exchange for non-contiguous MFNs. */
+	success = xen_exchange_memory(n, 0, in_frames,
+				      n, 0, out_frames, address_bits);
+
+	/* 4. Map new pages in place of old pages. */
+	if (success)
+		xen_remap_exchanged_pages(pages, order, out_frames, 0, limit_map);
+	else
+		xen_remap_exchanged_pages(pages, order, NULL, *in_frames, limit_map);
+
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
+	if (limit_map != &_limit_map)
+		kfree(limit_map);
+
+	return success ? 0 : -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(xen_limit_pages_to_max_mfn);
 #ifdef CONFIG_XEN_PVHVM
 static void xen_hvm_exit_mmap(struct mm_struct *mm)
 {
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 03c85d7..ae5b1ef 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -28,4 +28,6 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 			       unsigned long mfn, int nr,
 			       pgprot_t prot, unsigned domid);
 
+int xen_limit_pages_to_max_mfn(struct page *pages, unsigned int order,
+			       unsigned int address_bits);
 #endif /* INCLUDE_XEN_OPS_H */
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 27be2f0..4fa2066 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -31,6 +31,8 @@
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
 
+#include <xen/xen.h>
+#include <xen/xen-ops.h>
 /*** Page table manipulation functions ***/
 
 static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
@@ -1550,7 +1552,11 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	struct page **pages;
 	unsigned int nr_pages, array_size, i;
 	gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
-
+	gfp_t dma_mask = gfp_mask & (__GFP_DMA | __GFP_DMA32);
+	if (xen_pv_domain()) {
+		if (dma_mask == (__GFP_DMA | __GFP_DMA32))
+			gfp_mask &= (__GFP_DMA | __GFP_DMA32);
+	}
 	nr_pages = (area->size - PAGE_SIZE) >> PAGE_SHIFT;
 	array_size = (nr_pages * sizeof(struct page *));
 
@@ -1586,6 +1592,16 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 			goto fail;
 		}
 		area->pages[i] = page;
+		if (xen_pv_domain()) {
+			if (dma_mask) {
+				if (xen_limit_pages_to_max_mfn(page, 0, 32)) {
+					area->nr_pages = i + 1;
+					goto fail;
+				}
+			if (gfp_mask & __GFP_ZERO)
+				clear_highpage(page);
+			}
+		}
 	}
 
 	if (map_vm_area(area, prot, &pages))

[-- Attachment #3: Type: text/plain, Size: 138 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel