[PATCH] mspec driver

Implement the special memory driver (mspec) based on the do_no_pfn
approach.  The driver is currently used only on SN2 hardware with special
fetchop support but could be beneficial on other architectures using the
uncached mode.
Signed-off-by: Jes Sorensen <jes@sgi.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

drivers/char/Kconfig

@@ -439,6 +439,14 @@ config SGI_MBCS
          If you have an SGI Altix with an attached SABrick
          say Y or M here, otherwise say N.
 
+config MSPEC
+	tristate "Memory special operations driver"
+	depends on IA64
+	help
+	  If you have an ia64 and you want to enable memory special
+	  operations support (formerly known as fetchop), say Y here,
+	  otherwise say N.
+
 source "drivers/serial/Kconfig"
 
 config UNIX98_PTYS

drivers/char/Makefile

@@ -47,6 +47,7 @@ obj-$(CONFIG_HVC_RTAS)		+= hvc_rtas.o
 obj-$(CONFIG_HVC_DRIVER)	+= hvc_console.o
 obj-$(CONFIG_RAW_DRIVER)	+= raw.o
 obj-$(CONFIG_SGI_SNSC)		+= snsc.o snsc_event.o
+obj-$(CONFIG_MSPEC)		+= mspec.o
 obj-$(CONFIG_MMTIMER)		+= mmtimer.o
 obj-$(CONFIG_VIOCONS)		+= viocons.o
 obj-$(CONFIG_VIOTAPE)		+= viotape.o

drivers/char/mspec.c

+/*
+ * Copyright (C) 2001-2006 Silicon Graphics, Inc.  All rights
+ * reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+/*
+ * SN Platform Special Memory (mspec) Support
+ *
+ * This driver exports the SN special memory (mspec) facility to user
+ * processes.
+ * There are three types of memory made available thru this driver:
+ * fetchops, uncached and cached.
+ *
+ * Fetchops are atomic memory operations that are implemented in the
+ * memory controller on SGI SN hardware.
+ *
+ * Uncached are used for memory write combining feature of the ia64
+ * cpu.
+ *
+ * Cached are used for areas of memory that are used as cached addresses
+ * on our partition and used as uncached addresses from other partitions.
+ * Due to a design constraint of the SN2 Shub, you can not have processors
+ * on the same FSB perform both a cached and uncached reference to the
+ * same cache line.  These special memory cached regions prevent the
+ * kernel from ever dropping in a TLB entry and therefore prevent the
+ * processor from ever speculating a cache line from this page.
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/miscdevice.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/numa.h>
+#include <asm/page.h>
+#include <asm/system.h>
+#include <asm/pgtable.h>
+#include <asm/atomic.h>
+#include <asm/tlbflush.h>
+#include <asm/uncached.h>
+#include <asm/sn/addrs.h>
+#include <asm/sn/arch.h>
+#include <asm/sn/mspec.h>
+#include <asm/sn/sn_cpuid.h>
+#include <asm/sn/io.h>
+#include <asm/sn/bte.h>
+#include <asm/sn/shubio.h>
+
+
+#define FETCHOP_ID	"SGI Fetchop,"
+#define CACHED_ID	"Cached,"
+#define UNCACHED_ID	"Uncached"
+#define REVISION	"4.0"
+#define MSPEC_BASENAME	"mspec"
+
+/*
+ * Page types allocated by the device.
+ */
+enum {
+	MSPEC_FETCHOP = 1,
+	MSPEC_CACHED,
+	MSPEC_UNCACHED
+};
+
+static int is_sn2;
+
+/*
+ * One of these structures is allocated when an mspec region is mmaped. The
+ * structure is pointed to by the vma->vm_private_data field in the vma struct.
+ * This structure is used to record the addresses of the mspec pages.
+ */
+struct vma_data {
+	atomic_t refcnt;	/* Number of vmas sharing the data. */
+	spinlock_t lock;	/* Serialize access to the vma. */
+	int count;		/* Number of pages allocated. */
+	int type;		/* Type of pages allocated. */
+	unsigned long maddr[0];	/* Array of MSPEC addresses. */
+};
+
+/* used on shub2 to clear FOP cache in the HUB */
+static unsigned long scratch_page[MAX_NUMNODES];
+#define SH2_AMO_CACHE_ENTRIES	4
+
+static inline int
+mspec_zero_block(unsigned long addr, int len)
+{
+	int status;
+
+	if (is_sn2) {
+		if (is_shub2()) {
+			int nid;
+			void *p;
+			int i;
+
+			nid = nasid_to_cnodeid(get_node_number(__pa(addr)));
+			p = (void *)TO_AMO(scratch_page[nid]);
+
+			for (i=0; i < SH2_AMO_CACHE_ENTRIES; i++) {
+				FETCHOP_LOAD_OP(p, FETCHOP_LOAD);
+				p += FETCHOP_VAR_SIZE;
+			}
+		}
+
+		status = bte_copy(0, addr & ~__IA64_UNCACHED_OFFSET, len,
+				  BTE_WACQUIRE | BTE_ZERO_FILL, NULL);
+	} else {
+		memset((char *) addr, 0, len);
+		status = 0;
+	}
+	return status;
+}
+
+/*
+ * mspec_open
+ *
+ * Called when a device mapping is created by a means other than mmap
+ * (via fork, etc.).  Increments the reference count on the underlying
+ * mspec data so it is not freed prematurely.
+ */
+static void
+mspec_open(struct vm_area_struct *vma)
+{
+	struct vma_data *vdata;
+
+	vdata = vma->vm_private_data;
+	atomic_inc(&vdata->refcnt);
+}
+
+/*
+ * mspec_close
+ *
+ * Called when unmapping a device mapping. Frees all mspec pages
+ * belonging to the vma.
+ */
+static void
+mspec_close(struct vm_area_struct *vma)
+{
+	struct vma_data *vdata;
+	int i, pages, result, vdata_size;
+
+	vdata = vma->vm_private_data;
+	if (!atomic_dec_and_test(&vdata->refcnt))
+		return;
+
+	pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	vdata_size = sizeof(struct vma_data) + pages * sizeof(long);
+	for (i = 0; i < pages; i++) {
+		if (vdata->maddr[i] == 0)
+			continue;
+		/*
+		 * Clear the page before sticking it back
+		 * into the pool.
+		 */
+		result = mspec_zero_block(vdata->maddr[i], PAGE_SIZE);
+		if (!result)
+			uncached_free_page(vdata->maddr[i]);
+		else
+			printk(KERN_WARNING "mspec_close(): "
+			       "failed to zero page %i\n",
+			       result);
+	}
+
+	if (vdata_size <= PAGE_SIZE)
+		kfree(vdata);
+	else
+		vfree(vdata);
+}
+
+
+/*
+ * mspec_nopfn
+ *
+ * Creates a mspec page and maps it to user space.
+ */
+static unsigned long
+mspec_nopfn(struct vm_area_struct *vma, unsigned long address)
+{
+	unsigned long paddr, maddr;
+	unsigned long pfn;
+	int index;
+	struct vma_data *vdata = vma->vm_private_data;
+
+	index = (address - vma->vm_start) >> PAGE_SHIFT;
+	maddr = (volatile unsigned long) vdata->maddr[index];
+	if (maddr == 0) {
+		maddr = uncached_alloc_page(numa_node_id());
+		if (maddr == 0)
+			return NOPFN_OOM;
+
+		spin_lock(&vdata->lock);
+		if (vdata->maddr[index] == 0) {
+			vdata->count++;
+			vdata->maddr[index] = maddr;
+		} else {
+			uncached_free_page(maddr);
+			maddr = vdata->maddr[index];
+		}
+		spin_unlock(&vdata->lock);
+	}
+
+	if (vdata->type == MSPEC_FETCHOP)
+		paddr = TO_AMO(maddr);
+	else
+		paddr = __pa(TO_CAC(maddr));
+
+	pfn = paddr >> PAGE_SHIFT;
+
+	return pfn;
+}
+
+static struct vm_operations_struct mspec_vm_ops = {
+	.open = mspec_open,
+	.close = mspec_close,
+	.nopfn = mspec_nopfn
+};
+
+/*
+ * mspec_mmap
+ *
+ * Called when mmaping the device.  Initializes the vma with a fault handler
+ * and private data structure necessary to allocate, track, and free the
+ * underlying pages.
+ */
+static int
+mspec_mmap(struct file *file, struct vm_area_struct *vma, int type)
+{
+	struct vma_data *vdata;
+	int pages, vdata_size;
+
+	if (vma->vm_pgoff != 0)
+		return -EINVAL;
+
+	if ((vma->vm_flags & VM_SHARED) == 0)
+		return -EINVAL;
+
+	if ((vma->vm_flags & VM_WRITE) == 0)
+		return -EPERM;
+
+	pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	vdata_size = sizeof(struct vma_data) + pages * sizeof(long);
+	if (vdata_size <= PAGE_SIZE)
+		vdata = kmalloc(vdata_size, GFP_KERNEL);
+	else
+		vdata = vmalloc(vdata_size);
+	if (!vdata)
+		return -ENOMEM;
+	memset(vdata, 0, vdata_size);
+
+	vdata->type = type;
+	spin_lock_init(&vdata->lock);
+	vdata->refcnt = ATOMIC_INIT(1);
+	vma->vm_private_data = vdata;
+
+	vma->vm_flags |= (VM_IO | VM_LOCKED | VM_RESERVED | VM_PFNMAP);
+	if (vdata->type == MSPEC_FETCHOP || vdata->type == MSPEC_UNCACHED)
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_ops = &mspec_vm_ops;
+
+	return 0;
+}
+
+static int
+fetchop_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	return mspec_mmap(file, vma, MSPEC_FETCHOP);
+}
+
+static int
+cached_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	return mspec_mmap(file, vma, MSPEC_CACHED);
+}
+
+static int
+uncached_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	return mspec_mmap(file, vma, MSPEC_UNCACHED);
+}
+
+static struct file_operations fetchop_fops = {
+	.owner = THIS_MODULE,
+	.mmap = fetchop_mmap
+};
+
+static struct miscdevice fetchop_miscdev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "sgi_fetchop",
+	.fops = &fetchop_fops
+};
+
+static struct file_operations cached_fops = {
+	.owner = THIS_MODULE,
+	.mmap = cached_mmap
+};
+
+static struct miscdevice cached_miscdev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "mspec_cached",
+	.fops = &cached_fops
+};
+
+static struct file_operations uncached_fops = {
+	.owner = THIS_MODULE,
+	.mmap = uncached_mmap
+};
+
+static struct miscdevice uncached_miscdev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "mspec_uncached",
+	.fops = &uncached_fops
+};
+
+/*
+ * mspec_init
+ *
+ * Called at boot time to initialize the mspec facility.
+ */
+static int __init
+mspec_init(void)
+{
+	int ret;
+	int nid;
+
+	/*
+	 * The fetchop device only works on SN2 hardware, uncached and cached
+	 * memory drivers should both be valid on all ia64 hardware
+	 */
+	if (ia64_platform_is("sn2")) {
+		is_sn2 = 1;
+		if (is_shub2()) {
+			ret = -ENOMEM;
+			for_each_online_node(nid) {
+				int actual_nid;
+				int nasid;
+				unsigned long phys;
+
+				scratch_page[nid] = uncached_alloc_page(nid);
+				if (scratch_page[nid] == 0)
+					goto free_scratch_pages;
+				phys = __pa(scratch_page[nid]);
+				nasid = get_node_number(phys);
+				actual_nid = nasid_to_cnodeid(nasid);
+				if (actual_nid != nid)
+					goto free_scratch_pages;
+			}
+		}
+
+		ret = misc_register(&fetchop_miscdev);
+		if (ret) {
+			printk(KERN_ERR
+			       "%s: failed to register device %i\n",
+			       FETCHOP_ID, ret);
+			goto free_scratch_pages;
+		}
+	}
+	ret = misc_register(&cached_miscdev);
+	if (ret) {
+		printk(KERN_ERR "%s: failed to register device %i\n",
+		       CACHED_ID, ret);
+		if (is_sn2)
+			misc_deregister(&fetchop_miscdev);
+		goto free_scratch_pages;
+	}
+	ret = misc_register(&uncached_miscdev);
+	if (ret) {
+		printk(KERN_ERR "%s: failed to register device %i\n",
+		       UNCACHED_ID, ret);
+		misc_deregister(&cached_miscdev);
+		if (is_sn2)
+			misc_deregister(&fetchop_miscdev);
+		goto free_scratch_pages;
+	}
+
+	printk(KERN_INFO "%s %s initialized devices: %s %s %s\n",
+	       MSPEC_BASENAME, REVISION, is_sn2 ? FETCHOP_ID : "",
+	       CACHED_ID, UNCACHED_ID);
+
+	return 0;
+
+ free_scratch_pages:
+	for_each_node(nid) {
+		if (scratch_page[nid] != 0)
+			uncached_free_page(scratch_page[nid]);
+	}
+	return ret;
+}
+
+static void __exit
+mspec_exit(void)
+{
+	int nid;
+
+	misc_deregister(&uncached_miscdev);
+	misc_deregister(&cached_miscdev);
+	if (is_sn2) {
+		misc_deregister(&fetchop_miscdev);
+
+		for_each_node(nid) {
+			if (scratch_page[nid] != 0)
+				uncached_free_page(scratch_page[nid]);
+		}
+	}
+}
+
+module_init(mspec_init);
+module_exit(mspec_exit);
+
+MODULE_AUTHOR("Silicon Graphics, Inc. <linux-altix@sgi.com>");
+MODULE_DESCRIPTION("Driver for SGI SN special memory operations");
+MODULE_LICENSE("GPL");