* [PATCH 1/2]
2013-03-06 4:46 ` [FYI] vringh fixes Rusty Russell
@ 2013-03-06 4:53 ` Rusty Russell
2013-03-06 4:54 ` [PATCH 2/2] tools/virtio: make barriers stronger Rusty Russell
2013-03-06 4:57 ` [PATCH 1/3] vringh: host-side implementation of virtio rings (v2) Rusty Russell
1 sibling, 1 reply; 16+ messages in thread
From: Rusty Russell @ 2013-03-06 4:53 UTC (permalink / raw)
To: mst; +Cc: sjur, Linus Walleij, Erwan Yvin, virtualization, sjur.brandeland
tools/virtio: separate headers more.
This makes them a bit more like the kernel headers, so we can include more
real kernel headers in our tests.
In addition this means that we don't break tools/virtio with the next
patch.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
(Changes since last version: use ACCESS_ONCE() for "userspace" reads.
This semantic is assumed in kernel userspace access, since otherwise
the compiler might decide to re-grab a value after verification,
introducing a security hole).
diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h
new file mode 100644
index 0000000..aff61e1
--- /dev/null
+++ b/tools/virtio/asm/barrier.h
@@ -0,0 +1,14 @@
+#if defined(__i386__) || defined(__x86_64__)
+#define barrier() asm volatile("" ::: "memory")
+#define mb() __sync_synchronize()
+
+#define smp_mb() mb()
+# define smp_rmb() barrier()
+# define smp_wmb() barrier()
+/* Weak barriers should be used. If not - it's a bug */
+# define rmb() abort()
+# define wmb() abort()
+#else
+#error Please fill in barrier macros
+#endif
+
diff --git a/tools/virtio/linux/bug.h b/tools/virtio/linux/bug.h
new file mode 100644
index 0000000..fb94f07
--- /dev/null
+++ b/tools/virtio/linux/bug.h
@@ -0,0 +1,10 @@
+#ifndef BUG_H
+#define BUG_H
+
+#define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond))
+
+#define BUILD_BUG_ON(x)
+
+#define BUG() abort()
+
+#endif /* BUG_H */
diff --git a/tools/virtio/linux/err.h b/tools/virtio/linux/err.h
new file mode 100644
index 0000000..e32eff8
--- /dev/null
+++ b/tools/virtio/linux/err.h
@@ -0,0 +1,26 @@
+#ifndef ERR_H
+#define ERR_H
+#define MAX_ERRNO 4095
+
+#define IS_ERR_VALUE(x) unlikely((x) >= (unsigned long)-MAX_ERRNO)
+
+static inline void * __must_check ERR_PTR(long error)
+{
+ return (void *) error;
+}
+
+static inline long __must_check PTR_ERR(const void *ptr)
+{
+ return (long) ptr;
+}
+
+static inline long __must_check IS_ERR(const void *ptr)
+{
+ return IS_ERR_VALUE((unsigned long)ptr);
+}
+
+static inline long __must_check IS_ERR_OR_NULL(const void *ptr)
+{
+ return !ptr || IS_ERR_VALUE((unsigned long)ptr);
+}
+#endif /* ERR_H */
diff --git a/tools/virtio/linux/export.h b/tools/virtio/linux/export.h
new file mode 100644
index 0000000..7311d32
--- /dev/null
+++ b/tools/virtio/linux/export.h
@@ -0,0 +1,5 @@
+#define EXPORT_SYMBOL(sym)
+#define EXPORT_SYMBOL_GPL(sym)
+#define EXPORT_SYMBOL_GPL_FUTURE(sym)
+#define EXPORT_UNUSED_SYMBOL(sym)
+#define EXPORT_UNUSED_SYMBOL_GPL(sym)
diff --git a/tools/virtio/linux/irqreturn.h b/tools/virtio/linux/irqreturn.h
new file mode 100644
index 0000000..a3c4e7b
--- /dev/null
+++ b/tools/virtio/linux/irqreturn.h
@@ -0,0 +1 @@
+#include "../../../include/linux/irqreturn.h"
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
new file mode 100644
index 0000000..fba7059
--- /dev/null
+++ b/tools/virtio/linux/kernel.h
@@ -0,0 +1,112 @@
+#ifndef KERNEL_H
+#define KERNEL_H
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include <stdarg.h>
+
+#include <linux/types.h>
+#include <linux/printk.h>
+#include <linux/bug.h>
+#include <errno.h>
+#include <unistd.h>
+#include <asm/barrier.h>
+
+#define CONFIG_SMP
+
+#define PAGE_SIZE getpagesize()
+#define PAGE_MASK (~(PAGE_SIZE-1))
+
+typedef unsigned long long dma_addr_t;
+typedef size_t __kernel_size_t;
+
+struct page {
+ unsigned long long dummy;
+};
+
+/* Physical == Virtual */
+#define virt_to_phys(p) ((unsigned long)p)
+#define phys_to_virt(a) ((void *)(unsigned long)(a))
+/* Page address: Virtual / 4K */
+#define page_to_phys(p) ((dma_addr_t)(unsigned long)(p))
+#define virt_to_page(p) ((struct page *)((unsigned long)p & PAGE_MASK))
+
+#define offset_in_page(p) (((unsigned long)p) % PAGE_SIZE)
+
+#define __printf(a,b) __attribute__((format(printf,a,b)))
+
+typedef enum {
+ GFP_KERNEL,
+ GFP_ATOMIC,
+ __GFP_HIGHMEM,
+ __GFP_HIGH
+} gfp_t;
+
+#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
+
+extern void *__kmalloc_fake, *__kfree_ignore_start, *__kfree_ignore_end;
+static inline void *kmalloc(size_t s, gfp_t gfp)
+{
+ if (__kmalloc_fake)
+ return __kmalloc_fake;
+ return malloc(s);
+}
+
+static inline void kfree(void *p)
+{
+ if (p >= __kfree_ignore_start && p < __kfree_ignore_end)
+ return;
+ free(p);
+}
+
+static inline void *krealloc(void *p, size_t s, gfp_t gfp)
+{
+ return realloc(p, s);
+}
+
+
+static inline unsigned long __get_free_page(gfp_t gfp)
+{
+ void *p;
+
+ posix_memalign(&p, PAGE_SIZE, PAGE_SIZE);
+ return (unsigned long)p;
+}
+
+static inline void free_page(unsigned long addr)
+{
+ free((void *)addr);
+}
+
+#define container_of(ptr, type, member) ({ \
+ const typeof( ((type *)0)->member ) *__mptr = (ptr); \
+ (type *)( (char *)__mptr - offsetof(type,member) );})
+
+#define uninitialized_var(x) x = x
+
+# ifndef likely
+# define likely(x) (__builtin_expect(!!(x), 1))
+# endif
+# ifndef unlikely
+# define unlikely(x) (__builtin_expect(!!(x), 0))
+# endif
+
+#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#ifdef DEBUG
+#define pr_debug(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#else
+#define pr_debug(format, ...) do {} while (0)
+#endif
+#define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+
+#define min(x, y) ({ \
+ typeof(x) _min1 = (x); \
+ typeof(y) _min2 = (y); \
+ (void) (&_min1 == &_min2); \
+ _min1 < _min2 ? _min1 : _min2; })
+
+#endif /* KERNEL_H */
diff --git a/tools/virtio/linux/module.h b/tools/virtio/linux/module.h
index e69de29..3039a7e 100644
--- a/tools/virtio/linux/module.h
+++ b/tools/virtio/linux/module.h
@@ -0,0 +1 @@
+#include <linux/export.h>
diff --git a/tools/virtio/linux/printk.h b/tools/virtio/linux/printk.h
new file mode 100644
index 0000000..9f2423b
--- /dev/null
+++ b/tools/virtio/linux/printk.h
@@ -0,0 +1,4 @@
+#include "../../../include/linux/kern_levels.h"
+
+#define printk printf
+#define vprintk vprintf
diff --git a/tools/virtio/linux/ratelimit.h b/tools/virtio/linux/ratelimit.h
new file mode 100644
index 0000000..dcce172
--- /dev/null
+++ b/tools/virtio/linux/ratelimit.h
@@ -0,0 +1,4 @@
+#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init) int name = 0
+
+#define __ratelimit(x) (*(x))
+
diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h
new file mode 100644
index 0000000..b2cf7d0
--- /dev/null
+++ b/tools/virtio/linux/scatterlist.h
@@ -0,0 +1,173 @@
+#ifndef SCATTERLIST_H
+#define SCATTERLIST_H
+#include <linux/kernel.h>
+
+struct scatterlist {
+ unsigned long page_link;
+ unsigned int offset;
+ unsigned int length;
+ dma_addr_t dma_address;
+};
+
+/* Scatterlist helpers, stolen from linux/scatterlist.h */
+#define sg_is_chain(sg) ((sg)->page_link & 0x01)
+#define sg_is_last(sg) ((sg)->page_link & 0x02)
+#define sg_chain_ptr(sg) \
+ ((struct scatterlist *) ((sg)->page_link & ~0x03))
+
+/**
+ * sg_assign_page - Assign a given page to an SG entry
+ * @sg: SG entry
+ * @page: The page
+ *
+ * Description:
+ * Assign page to sg entry. Also see sg_set_page(), the most commonly used
+ * variant.
+ *
+ **/
+static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
+{
+ unsigned long page_link = sg->page_link & 0x3;
+
+ /*
+ * In order for the low bit stealing approach to work, pages
+ * must be aligned at a 32-bit boundary as a minimum.
+ */
+ BUG_ON((unsigned long) page & 0x03);
+#ifdef CONFIG_DEBUG_SG
+ BUG_ON(sg->sg_magic != SG_MAGIC);
+ BUG_ON(sg_is_chain(sg));
+#endif
+ sg->page_link = page_link | (unsigned long) page;
+}
+
+/**
+ * sg_set_page - Set sg entry to point at given page
+ * @sg: SG entry
+ * @page: The page
+ * @len: Length of data
+ * @offset: Offset into page
+ *
+ * Description:
+ * Use this function to set an sg entry pointing at a page, never assign
+ * the page directly. We encode sg table information in the lower bits
+ * of the page pointer. See sg_page() for looking up the page belonging
+ * to an sg entry.
+ *
+ **/
+static inline void sg_set_page(struct scatterlist *sg, struct page *page,
+ unsigned int len, unsigned int offset)
+{
+ sg_assign_page(sg, page);
+ sg->offset = offset;
+ sg->length = len;
+}
+
+static inline struct page *sg_page(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+ BUG_ON(sg->sg_magic != SG_MAGIC);
+ BUG_ON(sg_is_chain(sg));
+#endif
+ return (struct page *)((sg)->page_link & ~0x3);
+}
+
+/*
+ * Loop over each sg element, following the pointer to a new list if necessary
+ */
+#define for_each_sg(sglist, sg, nr, __i) \
+ for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg))
+
+/**
+ * sg_chain - Chain two sglists together
+ * @prv: First scatterlist
+ * @prv_nents: Number of entries in prv
+ * @sgl: Second scatterlist
+ *
+ * Description:
+ * Links @prv@ and @sgl@ together, to form a longer scatterlist.
+ *
+ **/
+static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
+ struct scatterlist *sgl)
+{
+ /*
+ * offset and length are unused for chain entry. Clear them.
+ */
+ prv[prv_nents - 1].offset = 0;
+ prv[prv_nents - 1].length = 0;
+
+ /*
+ * Set lowest bit to indicate a link pointer, and make sure to clear
+ * the termination bit if it happens to be set.
+ */
+ prv[prv_nents - 1].page_link = ((unsigned long) sgl | 0x01) & ~0x02;
+}
+
+/**
+ * sg_mark_end - Mark the end of the scatterlist
+ * @sg: SG entryScatterlist
+ *
+ * Description:
+ * Marks the passed in sg entry as the termination point for the sg
+ * table. A call to sg_next() on this entry will return NULL.
+ *
+ **/
+static inline void sg_mark_end(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+ BUG_ON(sg->sg_magic != SG_MAGIC);
+#endif
+ /*
+ * Set termination bit, clear potential chain bit
+ */
+ sg->page_link |= 0x02;
+ sg->page_link &= ~0x01;
+}
+
+static inline struct scatterlist *sg_next(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+ BUG_ON(sg->sg_magic != SG_MAGIC);
+#endif
+ if (sg_is_last(sg))
+ return NULL;
+
+ sg++;
+ if (unlikely(sg_is_chain(sg)))
+ sg = sg_chain_ptr(sg);
+
+ return sg;
+}
+
+static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents)
+{
+ memset(sgl, 0, sizeof(*sgl) * nents);
+#ifdef CONFIG_DEBUG_SG
+ {
+ unsigned int i;
+ for (i = 0; i < nents; i++)
+ sgl[i].sg_magic = SG_MAGIC;
+ }
+#endif
+ sg_mark_end(&sgl[nents - 1]);
+}
+
+static inline dma_addr_t sg_phys(struct scatterlist *sg)
+{
+ return page_to_phys(sg_page(sg)) + sg->offset;
+}
+
+static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
+ unsigned int buflen)
+{
+ sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
+}
+
+static inline void sg_init_one(struct scatterlist *sg,
+ const void *buf, unsigned int buflen)
+{
+ sg_init_table(sg, 1);
+ sg_set_buf(sg, buf, buflen);
+}
+#endif /* SCATTERLIST_H */
diff --git a/tools/virtio/linux/types.h b/tools/virtio/linux/types.h
new file mode 100644
index 0000000..f8ebb9a
--- /dev/null
+++ b/tools/virtio/linux/types.h
@@ -0,0 +1,28 @@
+#ifndef TYPES_H
+#define TYPES_H
+#include <stdint.h>
+
+#define __force
+#define __user
+#define __must_check
+#define __cold
+
+typedef uint64_t u64;
+typedef int64_t s64;
+typedef uint32_t u32;
+typedef int32_t s32;
+typedef uint16_t u16;
+typedef int16_t s16;
+typedef uint8_t u8;
+typedef int8_t s8;
+
+typedef uint64_t __u64;
+typedef int64_t __s64;
+typedef uint32_t __u32;
+typedef int32_t __s32;
+typedef uint16_t __u16;
+typedef int16_t __s16;
+typedef uint8_t __u8;
+typedef int8_t __s8;
+
+#endif /* TYPES_H */
diff --git a/tools/virtio/linux/uaccess.h b/tools/virtio/linux/uaccess.h
new file mode 100644
index 0000000..0a578fe
--- /dev/null
+++ b/tools/virtio/linux/uaccess.h
@@ -0,0 +1,50 @@
+#ifndef UACCESS_H
+#define UACCESS_H
+extern void *__user_addr_min, *__user_addr_max;
+
+#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
+
+static inline void __chk_user_ptr(const volatile void *p, size_t size)
+{
+ assert(p >= __user_addr_min && p + size <= __user_addr_max);
+}
+
+#define put_user(x, ptr) \
+({ \
+ typeof(ptr) __pu_ptr = (ptr); \
+ __chk_user_ptr(__pu_ptr, sizeof(*__pu_ptr)); \
+ ACCESS_ONCE(*(__pu_ptr)) = x; \
+ 0; \
+})
+
+#define get_user(x, ptr) \
+({ \
+ typeof(ptr) __pu_ptr = (ptr); \
+ __chk_user_ptr(__pu_ptr, sizeof(*__pu_ptr)); \
+ x = ACCESS_ONCE(*(__pu_ptr)); \
+ 0; \
+})
+
+static void volatile_memcpy(volatile char *to, const volatile char *from,
+ unsigned long n)
+{
+ while (n--)
+ *(to++) = *(from++);
+}
+
+static inline int copy_from_user(void *to, const void __user volatile *from,
+ unsigned long n)
+{
+ __chk_user_ptr(from, n);
+ volatile_memcpy(to, from, n);
+ return 0;
+}
+
+static inline int copy_to_user(void __user volatile *to, const void *from,
+ unsigned long n)
+{
+ __chk_user_ptr(to, n);
+ volatile_memcpy(to, from, n);
+ return 0;
+}
+#endif /* UACCESS_H */
diff --git a/tools/virtio/linux/uio.h b/tools/virtio/linux/uio.h
new file mode 100644
index 0000000..ecbdf92
--- /dev/null
+++ b/tools/virtio/linux/uio.h
@@ -0,0 +1 @@
+#include "../../../include/linux/uio.h"
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index 390c4cb..e4af659 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -1,129 +1,7 @@
#ifndef LINUX_VIRTIO_H
#define LINUX_VIRTIO_H
-
-#include <stdbool.h>
-#include <stdlib.h>
-#include <stddef.h>
-#include <stdio.h>
-#include <string.h>
-#include <assert.h>
-
-#include <linux/types.h>
-#include <errno.h>
-
-typedef unsigned long long dma_addr_t;
-
-struct scatterlist {
- unsigned long page_link;
- unsigned int offset;
- unsigned int length;
- dma_addr_t dma_address;
-};
-
-struct page {
- unsigned long long dummy;
-};
-
-#define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond))
-
-/* Physical == Virtual */
-#define virt_to_phys(p) ((unsigned long)p)
-#define phys_to_virt(a) ((void *)(unsigned long)(a))
-/* Page address: Virtual / 4K */
-#define virt_to_page(p) ((struct page*)((virt_to_phys(p) / 4096) * \
- sizeof(struct page)))
-#define offset_in_page(p) (((unsigned long)p) % 4096)
-#define sg_phys(sg) ((sg->page_link & ~0x3) / sizeof(struct page) * 4096 + \
- sg->offset)
-static inline void sg_mark_end(struct scatterlist *sg)
-{
- /*
- * Set termination bit, clear potential chain bit
- */
- sg->page_link |= 0x02;
- sg->page_link &= ~0x01;
-}
-static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents)
-{
- memset(sgl, 0, sizeof(*sgl) * nents);
- sg_mark_end(&sgl[nents - 1]);
-}
-static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
-{
- unsigned long page_link = sg->page_link & 0x3;
-
- /*
- * In order for the low bit stealing approach to work, pages
- * must be aligned at a 32-bit boundary as a minimum.
- */
- BUG_ON((unsigned long) page & 0x03);
- sg->page_link = page_link | (unsigned long) page;
-}
-
-static inline void sg_set_page(struct scatterlist *sg, struct page *page,
- unsigned int len, unsigned int offset)
-{
- sg_assign_page(sg, page);
- sg->offset = offset;
- sg->length = len;
-}
-
-static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
- unsigned int buflen)
-{
- sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
-}
-
-static inline void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen)
-{
- sg_init_table(sg, 1);
- sg_set_buf(sg, buf, buflen);
-}
-
-typedef __u16 u16;
-
-typedef enum {
- GFP_KERNEL,
- GFP_ATOMIC,
- __GFP_HIGHMEM,
- __GFP_HIGH
-} gfp_t;
-typedef enum {
- IRQ_NONE,
- IRQ_HANDLED
-} irqreturn_t;
-
-static inline void *kmalloc(size_t s, gfp_t gfp)
-{
- return malloc(s);
-}
-
-static inline void kfree(void *p)
-{
- free(p);
-}
-
-#define container_of(ptr, type, member) ({ \
- const typeof( ((type *)0)->member ) *__mptr = (ptr); \
- (type *)( (char *)__mptr - offsetof(type,member) );})
-
-#define uninitialized_var(x) x = x
-
-# ifndef likely
-# define likely(x) (__builtin_expect(!!(x), 1))
-# endif
-# ifndef unlikely
-# define unlikely(x) (__builtin_expect(!!(x), 0))
-# endif
-
-#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
-#ifdef DEBUG
-#define pr_debug(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
-#else
-#define pr_debug(format, ...) do {} while (0)
-#endif
-#define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
-#define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#include <linux/scatterlist.h>
+#include <linux/kernel.h>
/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
#define list_add_tail(a, b) do {} while (0)
@@ -133,6 +11,7 @@ static inline void kfree(void *p)
#define BITS_PER_BYTE 8
#define BITS_PER_LONG (sizeof(long) * BITS_PER_BYTE)
#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
+
/* TODO: Not atomic as it should be:
* we don't use this for anything important. */
static inline void clear_bit(int nr, volatile unsigned long *addr)
@@ -147,10 +26,6 @@ static inline int test_bit(int nr, const volatile unsigned long *addr)
{
return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
}
-
-/* The only feature we care to support */
-#define virtio_has_feature(dev, feature) \
- test_bit((feature), (dev)->features)
/* end of stubs */
struct virtio_device {
@@ -170,28 +45,9 @@ struct virtqueue {
void *priv;
};
-#define EXPORT_SYMBOL_GPL(__EXPORT_SYMBOL_GPL_name) \
- void __EXPORT_SYMBOL_GPL##__EXPORT_SYMBOL_GPL_name() { \
-}
#define MODULE_LICENSE(__MODULE_LICENSE_value) \
const char *__MODULE_LICENSE_name = __MODULE_LICENSE_value
-#define CONFIG_SMP
-
-#if defined(__i386__) || defined(__x86_64__)
-#define barrier() asm volatile("" ::: "memory")
-#define mb() __sync_synchronize()
-
-#define smp_mb() mb()
-# define smp_rmb() barrier()
-# define smp_wmb() barrier()
-/* Weak barriers should be used. If not - it's a bug */
-# define rmb() abort()
-# define wmb() abort()
-#else
-#error Please fill in barrier macros
-#endif
-
/* Interfaces exported by virtio_ring. */
int virtqueue_add_buf(struct virtqueue *vq,
struct scatterlist sg[],
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
new file mode 100644
index 0000000..5049967
--- /dev/null
+++ b/tools/virtio/linux/virtio_config.h
@@ -0,0 +1,6 @@
+#define VIRTIO_TRANSPORT_F_START 28
+#define VIRTIO_TRANSPORT_F_END 32
+
+#define virtio_has_feature(dev, feature) \
+ test_bit((feature), (dev)->features)
+
diff --git a/tools/virtio/linux/virtio_ring.h b/tools/virtio/linux/virtio_ring.h
new file mode 100644
index 0000000..8949c4e
--- /dev/null
+++ b/tools/virtio/linux/virtio_ring.h
@@ -0,0 +1 @@
+#include "../../../include/linux/virtio_ring.h"
diff --git a/tools/virtio/linux/vringh.h b/tools/virtio/linux/vringh.h
new file mode 100644
index 0000000..9348957
--- /dev/null
+++ b/tools/virtio/linux/vringh.h
@@ -0,0 +1 @@
+#include "../../../include/linux/vringh.h"
diff --git a/tools/virtio/uapi/linux/uio.h b/tools/virtio/uapi/linux/uio.h
new file mode 100644
index 0000000..7230e90
--- /dev/null
+++ b/tools/virtio/uapi/linux/uio.h
@@ -0,0 +1 @@
+#include <sys/uio.h>
diff --git a/tools/virtio/uapi/linux/virtio_config.h b/tools/virtio/uapi/linux/virtio_config.h
new file mode 100644
index 0000000..4c86675
--- /dev/null
+++ b/tools/virtio/uapi/linux/virtio_config.h
@@ -0,0 +1 @@
+#include "../../../../include/uapi/linux/virtio_config.h"
diff --git a/tools/virtio/uapi/linux/virtio_ring.h b/tools/virtio/uapi/linux/virtio_ring.h
new file mode 100644
index 0000000..4d99c78
--- /dev/null
+++ b/tools/virtio/uapi/linux/virtio_ring.h
@@ -0,0 +1,4 @@
+#ifndef VIRTIO_RING_H
+#define VIRTIO_RING_H
+#include "../../../../include/uapi/linux/virtio_ring.h"
+#endif /* VIRTIO_RING_H */
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index faf3f0c..814ae80 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -10,11 +10,15 @@
#include <sys/stat.h>
#include <sys/types.h>
#include <fcntl.h>
+#include <stdbool.h>
#include <linux/vhost.h>
#include <linux/virtio.h>
#include <linux/virtio_ring.h>
#include "../../drivers/vhost/test.h"
+/* Unused */
+void *__kmalloc_fake, *__kfree_ignore_start, *__kfree_ignore_end;
+
struct vq_info {
int kick;
int call;
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH 1/3] vringh: host-side implementation of virtio rings (v2)
2013-03-06 4:46 ` [FYI] vringh fixes Rusty Russell
2013-03-06 4:53 ` [PATCH 1/2] Rusty Russell
@ 2013-03-06 4:57 ` Rusty Russell
2013-03-06 4:59 ` [PATCH 2/3] vringh: don't flag already listening Rusty Russell
2013-03-06 5:02 ` [PATCH 3/3] tools/virtio: add vring_test (v2) Rusty Russell
1 sibling, 2 replies; 16+ messages in thread
From: Rusty Russell @ 2013-03-06 4:57 UTC (permalink / raw)
To: sjur.brandeland, Ohad Ben-Cohen, mst
Cc: sjur, Linus Walleij, Erwan Yvin, virtualization
Getting use of virtio rings correct is tricky, and a recent patch saw
an implementation of in-kernel rings (as separate from userspace).
This abstracts the business of dealing with the virtio ring layout
from the access (userspace or direct); to do this, we use function
pointers, which gcc inlines correctly.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Changed:
Use ACCESS_ONCE in kernel ring accessors, to match user accessor
semantics.
diff --git a/drivers/Makefile b/drivers/Makefile
index dce39a9..72d28d3 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -123,7 +123,7 @@ obj-$(CONFIG_PPC_PS3) += ps3/
obj-$(CONFIG_OF) += of/
obj-$(CONFIG_SSB) += ssb/
obj-$(CONFIG_BCMA) += bcma/
-obj-$(CONFIG_VHOST_NET) += vhost/
+obj-$(CONFIG_VHOST_RING) += vhost/
obj-$(CONFIG_VLYNQ) += vlynq/
obj-$(CONFIG_STAGING) += staging/
obj-y += platform/
diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
index bf24317..85b773a 100644
--- a/drivers/vhost/Kconfig
+++ b/drivers/vhost/Kconfig
@@ -1,6 +1,7 @@
config VHOST_NET
tristate "Host kernel accelerator for virtio net"
depends on NET && EVENTFD && (TUN || !TUN) && (MACVTAP || !MACVTAP)
+ select VHOST_RING
---help---
This kernel module can be loaded in host kernel to accelerate
guest networking with virtio_net. Not to be confused with virtio_net
@@ -12,3 +13,10 @@ config VHOST_NET
if STAGING
source "drivers/vhost/Kconfig.tcm"
endif
+
+config VHOST_RING
+ tristate
+ ---help---
+ This option is selected by any driver which needs to access
+ the host side of a virtio ring.
+
diff --git a/drivers/vhost/Kconfig.tcm b/drivers/vhost/Kconfig.tcm
index 7e3aa28..c3a8cfa 100644
--- a/drivers/vhost/Kconfig.tcm
+++ b/drivers/vhost/Kconfig.tcm
@@ -1,6 +1,7 @@
config TCM_VHOST
tristate "TCM_VHOST fabric module"
depends on TARGET_CORE && EVENTFD && m
+ select VHOST_RING
default n
---help---
Say M here to enable the TCM_VHOST fabric module for use with virtio-scsi guests
diff --git a/drivers/vhost/Makefile b/drivers/vhost/Makefile
index a27b053..1d37f5e 100644
--- a/drivers/vhost/Makefile
+++ b/drivers/vhost/Makefile
@@ -2,3 +2,5 @@ obj-$(CONFIG_VHOST_NET) += vhost_net.o
vhost_net-y := vhost.o net.o
obj-$(CONFIG_TCM_VHOST) += tcm_vhost.o
+
+obj-$(CONFIG_VHOST_RING) += vringh.o
diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
new file mode 100644
index 0000000..8234f2b
--- /dev/null
+++ b/drivers/vhost/vringh.c
@@ -0,0 +1,1012 @@
+/*
+ * Helpers for the host side of a virtio ring.
+ *
+ * Since these may be in userspace, we use (inline) accessors.
+ */
+#include <linux/vringh.h>
+#include <linux/virtio_ring.h>
+#include <linux/kernel.h>
+#include <linux/ratelimit.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+
+static __printf(1,2) __cold void vringh_bad(const char *fmt, ...)
+{
+ static DEFINE_RATELIMIT_STATE(vringh_rs,
+ DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+ if (__ratelimit(&vringh_rs)) {
+ va_list ap;
+ va_start(ap, fmt);
+ printk(KERN_NOTICE "vringh:");
+ vprintk(fmt, ap);
+ va_end(ap);
+ }
+}
+
+/* Returns vring->num if empty, -ve on error. */
+static inline int __vringh_get_head(const struct vringh *vrh,
+ int (*getu16)(u16 *val, const u16 *p),
+ u16 *last_avail_idx)
+{
+ u16 avail_idx, i, head;
+ int err;
+
+ err = getu16(&avail_idx, &vrh->vring.avail->idx);
+ if (err) {
+ vringh_bad("Failed to access avail idx at %p",
+ &vrh->vring.avail->idx);
+ return err;
+ }
+
+ if (*last_avail_idx == avail_idx)
+ return vrh->vring.num;
+
+ /* Only get avail ring entries after they have been exposed by guest. */
+ virtio_rmb(vrh->weak_barriers);
+
+ i = *last_avail_idx & (vrh->vring.num - 1);
+
+ err = getu16(&head, &vrh->vring.avail->ring[i]);
+ if (err) {
+ vringh_bad("Failed to read head: idx %d address %p",
+ *last_avail_idx, &vrh->vring.avail->ring[i]);
+ return err;
+ }
+
+ if (head >= vrh->vring.num) {
+ vringh_bad("Guest says index %u > %u is available",
+ head, vrh->vring.num);
+ return -EINVAL;
+ }
+
+ (*last_avail_idx)++;
+ return head;
+}
+
+/* Copy some bytes to/from the iovec. Returns num copied. */
+static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov,
+ void *ptr, size_t len,
+ int (*xfer)(void *addr, void *ptr,
+ size_t len))
+{
+ int err, done = 0;
+
+ while (len && iov->i < iov->used) {
+ size_t partlen;
+
+ partlen = min(iov->iov[iov->i].iov_len - iov->off, len);
+ err = xfer(iov->iov[iov->i].iov_base + iov->off, ptr, partlen);
+ if (err)
+ return err;
+ done += partlen;
+ len -= partlen;
+ ptr += partlen;
+ iov->off += partlen;
+
+ if (iov->off == iov->iov[iov->i].iov_len) {
+ iov->off = 0;
+ iov->i++;
+ }
+ }
+ return done;
+}
+
+/* May reduce *len if range is shorter. */
+static inline bool range_check(struct vringh *vrh, u64 addr, size_t *len,
+ struct vringh_range *range,
+ bool (*getrange)(struct vringh *,
+ u64, struct vringh_range *))
+{
+ if (addr < range->start || addr > range->end_incl) {
+ if (!getrange(vrh, addr, range))
+ return false;
+ }
+ BUG_ON(addr < range->start || addr > range->end_incl);
+
+ /* To end of memory? */
+ if (unlikely(addr + *len == 0)) {
+ if (range->end_incl == -1ULL)
+ return true;
+ goto truncate;
+ }
+
+ /* Otherwise, don't wrap. */
+ if (addr + *len < addr) {
+ vringh_bad("Wrapping descriptor %zu@0x%llx",
+ *len, (unsigned long long)addr);
+ return false;
+ }
+
+ if (unlikely(addr + *len - 1 > range->end_incl))
+ goto truncate;
+ return true;
+
+truncate:
+ *len = range->end_incl + 1 - addr;
+ return true;
+}
+
+static inline bool no_range_check(struct vringh *vrh, u64 addr, size_t *len,
+ struct vringh_range *range,
+ bool (*getrange)(struct vringh *,
+ u64, struct vringh_range *))
+{
+ return true;
+}
+
+/* No reason for this code to be inline. */
+static int move_to_indirect(int *up_next, u16 *i, void *addr,
+ const struct vring_desc *desc,
+ struct vring_desc **descs, int *desc_max)
+{
+ /* Indirect tables can't have indirect. */
+ if (*up_next != -1) {
+ vringh_bad("Multilevel indirect %u->%u", *up_next, *i);
+ return -EINVAL;
+ }
+
+ if (unlikely(desc->len % sizeof(struct vring_desc))) {
+ vringh_bad("Strange indirect len %u", desc->len);
+ return -EINVAL;
+ }
+
+ /* We will check this when we follow it! */
+ if (desc->flags & VRING_DESC_F_NEXT)
+ *up_next = desc->next;
+ else
+ *up_next = -2;
+ *descs = addr;
+ *desc_max = desc->len / sizeof(struct vring_desc);
+
+ /* Now, start at the first indirect. */
+ *i = 0;
+ return 0;
+}
+
+static int resize_iovec(struct vringh_kiov *iov, gfp_t gfp)
+{
+ struct kvec *new;
+ unsigned int flag, new_num = (iov->max_num & ~VRINGH_IOV_ALLOCATED) * 2;
+
+ if (new_num < 8)
+ new_num = 8;
+
+ flag = (iov->max_num & VRINGH_IOV_ALLOCATED);
+ if (flag)
+ new = krealloc(iov->iov, new_num * sizeof(struct iovec), gfp);
+ else {
+ new = kmalloc(new_num * sizeof(struct iovec), gfp);
+ if (new) {
+ memcpy(new, iov->iov,
+ iov->max_num * sizeof(struct iovec));
+ flag = VRINGH_IOV_ALLOCATED;
+ }
+ }
+ if (!new)
+ return -ENOMEM;
+ iov->iov = new;
+ iov->max_num = (new_num | flag);
+ return 0;
+}
+
+static u16 __cold return_from_indirect(const struct vringh *vrh, int *up_next,
+ struct vring_desc **descs, int *desc_max)
+{
+ u16 i = *up_next;
+
+ *up_next = -1;
+ *descs = vrh->vring.desc;
+ *desc_max = vrh->vring.num;
+ return i;
+}
+
+static int slow_copy(struct vringh *vrh, void *dst, const void *src,
+ bool (*rcheck)(struct vringh *vrh, u64 addr, size_t *len,
+ struct vringh_range *range,
+ bool (*getrange)(struct vringh *vrh,
+ u64,
+ struct vringh_range *)),
+ bool (*getrange)(struct vringh *vrh,
+ u64 addr,
+ struct vringh_range *r),
+ struct vringh_range *range,
+ int (*copy)(void *dst, const void *src, size_t len))
+{
+ size_t part, len = sizeof(struct vring_desc);
+
+ do {
+ u64 addr;
+ int err;
+
+ part = len;
+ addr = (u64)(unsigned long)src - range->offset;
+
+ if (!rcheck(vrh, addr, &part, range, getrange))
+ return -EINVAL;
+
+ err = copy(dst, src, part);
+ if (err)
+ return err;
+
+ dst += part;
+ src += part;
+ len -= part;
+ } while (len);
+ return 0;
+}
+
+static inline int
+__vringh_iov(struct vringh *vrh, u16 i,
+ struct vringh_kiov *riov,
+ struct vringh_kiov *wiov,
+ bool (*rcheck)(struct vringh *vrh, u64 addr, size_t *len,
+ struct vringh_range *range,
+ bool (*getrange)(struct vringh *, u64,
+ struct vringh_range *)),
+ bool (*getrange)(struct vringh *, u64, struct vringh_range *),
+ gfp_t gfp,
+ int (*copy)(void *dst, const void *src, size_t len))
+{
+ int err, count = 0, up_next, desc_max;
+ struct vring_desc desc, *descs;
+ struct vringh_range range = { -1ULL, 0 }, slowrange;
+ bool slow = false;
+
+ /* We start traversing vring's descriptor table. */
+ descs = vrh->vring.desc;
+ desc_max = vrh->vring.num;
+ up_next = -1;
+
+ if (riov)
+ riov->i = riov->used = 0;
+ else if (wiov)
+ wiov->i = wiov->used = 0;
+ else
+ /* You must want something! */
+ BUG();
+
+ for (;;) {
+ void *addr;
+ struct vringh_kiov *iov;
+ size_t len;
+
+ if (unlikely(slow))
+ err = slow_copy(vrh, &desc, &descs[i], rcheck, getrange,
+ &slowrange, copy);
+ else
+ err = copy(&desc, &descs[i], sizeof(desc));
+ if (unlikely(err))
+ goto fail;
+
+ if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) {
+ /* Make sure it's OK, and get offset. */
+ len = desc.len;
+ if (!rcheck(vrh, desc.addr, &len, &range, getrange)) {
+ err = -EINVAL;
+ goto fail;
+ }
+
+ if (unlikely(len != desc.len)) {
+ slow = true;
+ /* We need to save this range to use offset */
+ slowrange = range;
+ }
+
+ addr = (void *)(long)(desc.addr + range.offset);
+ err = move_to_indirect(&up_next, &i, addr, &desc,
+ &descs, &desc_max);
+ if (err)
+ goto fail;
+ continue;
+ }
+
+ if (count++ == vrh->vring.num) {
+ vringh_bad("Descriptor loop in %p", descs);
+ err = -ELOOP;
+ goto fail;
+ }
+
+ if (desc.flags & VRING_DESC_F_WRITE)
+ iov = wiov;
+ else {
+ iov = riov;
+ if (unlikely(wiov && wiov->i)) {
+ vringh_bad("Readable desc %p after writable",
+ &descs[i]);
+ err = -EINVAL;
+ goto fail;
+ }
+ }
+
+ if (!iov) {
+ vringh_bad("Unexpected %s desc",
+ !wiov ? "writable" : "readable");
+ err = -EPROTO;
+ goto fail;
+ }
+
+ again:
+ /* Make sure it's OK, and get offset. */
+ len = desc.len;
+ if (!rcheck(vrh, desc.addr, &len, &range, getrange)) {
+ err = -EINVAL;
+ goto fail;
+ }
+ addr = (void *)(unsigned long)(desc.addr + range.offset);
+
+ if (unlikely(iov->used == (iov->max_num & ~VRINGH_IOV_ALLOCATED))) {
+ err = resize_iovec(iov, gfp);
+ if (err)
+ goto fail;
+ }
+
+ iov->iov[iov->used].iov_base = addr;
+ iov->iov[iov->used].iov_len = len;
+ iov->used++;
+
+ if (unlikely(len != desc.len)) {
+ desc.len -= len;
+ desc.addr += len;
+ goto again;
+ }
+
+ if (desc.flags & VRING_DESC_F_NEXT) {
+ i = desc.next;
+ } else {
+ /* Just in case we need to finish traversing above. */
+ if (unlikely(up_next > 0)) {
+ i = return_from_indirect(vrh, &up_next,
+ &descs, &desc_max);
+ slow = false;
+ } else
+ break;
+ }
+
+ if (i >= desc_max) {
+ vringh_bad("Chained index %u > %u", i, desc_max);
+ err = -EINVAL;
+ goto fail;
+ }
+ }
+
+ return 0;
+
+fail:
+ return err;
+}
+
+static inline int __vringh_complete(struct vringh *vrh,
+ const struct vring_used_elem *used,
+ unsigned int num_used,
+ int (*putu16)(u16 *p, u16 val),
+ int (*putused)(struct vring_used_elem *dst,
+ const struct vring_used_elem
+ *src, unsigned num))
+{
+ struct vring_used *used_ring;
+ int err;
+ u16 used_idx, off;
+
+ used_ring = vrh->vring.used;
+ used_idx = vrh->last_used_idx + vrh->completed;
+
+ off = used_idx % vrh->vring.num;
+
+ /* Compiler knows num_used == 1 sometimes, hence extra check */
+ if (num_used > 1 && unlikely(off + num_used >= vrh->vring.num)) {
+ u16 part = vrh->vring.num - off;
+ err = putused(&used_ring->ring[off], used, part);
+ if (!err)
+ err = putused(&used_ring->ring[0], used + part,
+ num_used - part);
+ } else
+ err = putused(&used_ring->ring[off], used, num_used);
+
+ if (err) {
+ vringh_bad("Failed to write %u used entries %u at %p",
+ num_used, off, &used_ring->ring[off]);
+ return err;
+ }
+
+ /* Make sure buffer is written before we update index. */
+ virtio_wmb(vrh->weak_barriers);
+
+ err = putu16(&vrh->vring.used->idx, used_idx + num_used);
+ if (err) {
+ vringh_bad("Failed to update used index at %p",
+ &vrh->vring.used->idx);
+ return err;
+ }
+
+ vrh->completed += num_used;
+ return 0;
+}
+
+
+static inline int __vringh_need_notify(struct vringh *vrh,
+ int (*getu16)(u16 *val, const u16 *p))
+{
+ bool notify;
+ u16 used_event;
+ int err;
+
+ /* Flush out used index update. This is paired with the
+ * barrier that the Guest executes when enabling
+ * interrupts. */
+ virtio_mb(vrh->weak_barriers);
+
+ /* Old-style, without event indices. */
+ if (!vrh->event_indices) {
+ u16 flags;
+ err = getu16(&flags, &vrh->vring.avail->flags);
+ if (err) {
+ vringh_bad("Failed to get flags at %p",
+ &vrh->vring.avail->flags);
+ return err;
+ }
+ return (!(flags & VRING_AVAIL_F_NO_INTERRUPT));
+ }
+
+ /* Modern: we know when other side wants to know. */
+ err = getu16(&used_event, &vring_used_event(&vrh->vring));
+ if (err) {
+ vringh_bad("Failed to get used event idx at %p",
+ &vring_used_event(&vrh->vring));
+ return err;
+ }
+
+ /* Just in case we added so many that we wrap. */
+ if (unlikely(vrh->completed > 0xffff))
+ notify = true;
+ else
+ notify = vring_need_event(used_event,
+ vrh->last_used_idx + vrh->completed,
+ vrh->last_used_idx);
+
+ vrh->last_used_idx += vrh->completed;
+ vrh->completed = 0;
+ return notify;
+}
+
+static inline bool __vringh_notify_enable(struct vringh *vrh,
+ int (*getu16)(u16 *val, const u16 *p),
+ int (*putu16)(u16 *p, u16 val))
+{
+ u16 avail;
+
+ /* Already enabled? */
+ if (vrh->listening)
+ return false;
+
+ vrh->listening = true;
+
+ if (!vrh->event_indices) {
+ /* Old-school; update flags. */
+ if (putu16(&vrh->vring.used->flags, 0) != 0) {
+ vringh_bad("Clearing used flags %p",
+ &vrh->vring.used->flags);
+ return false;
+ }
+ } else {
+ if (putu16(&vring_avail_event(&vrh->vring),
+ vrh->last_avail_idx) != 0) {
+ vringh_bad("Updating avail event index %p",
+ &vring_avail_event(&vrh->vring));
+ return false;
+ }
+ }
+
+ /* They could have slipped one in as we were doing that: make
+ * sure it's written, then check again. */
+ virtio_mb(vrh->weak_barriers);
+
+ if (getu16(&avail, &vrh->vring.avail->idx) != 0) {
+ vringh_bad("Failed to check avail idx at %p",
+ &vrh->vring.avail->idx);
+ return false;
+ }
+
+ /* This is so unlikely, we just leave notifications enabled. */
+ return avail != vrh->last_avail_idx;
+}
+
+static inline void __vringh_notify_disable(struct vringh *vrh,
+ int (*putu16)(u16 *p, u16 val))
+{
+ /* Already disabled? */
+ if (!vrh->listening)
+ return;
+
+ vrh->listening = false;
+ if (!vrh->event_indices) {
+ /* Old-school; update flags. */
+ if (putu16(&vrh->vring.used->flags, VRING_USED_F_NO_NOTIFY)) {
+ vringh_bad("Setting used flags %p",
+ &vrh->vring.used->flags);
+ }
+ }
+}
+
+/* Userspace access helpers: in this case, addresses are really userspace. */
+static inline int getu16_user(u16 *val, const u16 *p)
+{
+ return get_user(*val, (__force u16 __user *)p);
+}
+
+static inline int putu16_user(u16 *p, u16 val)
+{
+ return put_user(val, (__force u16 __user *)p);
+}
+
+static inline int copydesc_user(void *dst, const void *src, size_t len)
+{
+ return copy_from_user(dst, (__force void __user *)src, len) ?
+ -EFAULT : 0;
+}
+
+static inline int putused_user(struct vring_used_elem *dst,
+ const struct vring_used_elem *src,
+ unsigned int num)
+{
+ return copy_to_user((__force void __user *)dst, src,
+ sizeof(*dst) * num) ? -EFAULT : 0;
+}
+
+static inline int xfer_from_user(void *src, void *dst, size_t len)
+{
+ return copy_from_user(dst, (__force void __user *)src, len) ?
+ -EFAULT : 0;
+}
+
+static inline int xfer_to_user(void *dst, void *src, size_t len)
+{
+ return copy_to_user((__force void __user *)dst, src, len) ?
+ -EFAULT : 0;
+}
+
+/**
+ * vringh_init_user - initialize a vringh for a userspace vring.
+ * @vrh: the vringh to initialize.
+ * @features: the feature bits for this ring.
+ * @num: the number of elements.
+ * @weak_barriers: true if we only need memory barriers, not I/O.
+ * @desc: the userpace descriptor pointer.
+ * @avail: the userpace avail pointer.
+ * @used: the userpace used pointer.
+ *
+ * Returns an error if num is invalid: you should check pointers
+ * yourself!
+ */
+int vringh_init_user(struct vringh *vrh, u32 features,
+ unsigned int num, bool weak_barriers,
+ struct vring_desc __user *desc,
+ struct vring_avail __user *avail,
+ struct vring_used __user *used)
+{
+ /* Sane power of 2 please! */
+ if (!num || num > 0xffff || (num & (num - 1))) {
+ vringh_bad("Bad ring size %u", num);
+ return -EINVAL;
+ }
+
+ vrh->event_indices = (features & (1 << VIRTIO_RING_F_EVENT_IDX));
+ vrh->weak_barriers = weak_barriers;
+ vrh->listening = false;
+ vrh->completed = 0;
+ vrh->last_avail_idx = 0;
+ vrh->last_used_idx = 0;
+ vrh->vring.num = num;
+ /* vring expects kernel addresses, but only used via accessors. */
+ vrh->vring.desc = (__force struct vring_desc *)desc;
+ vrh->vring.avail = (__force struct vring_avail *)avail;
+ vrh->vring.used = (__force struct vring_used *)used;
+ return 0;
+}
+EXPORT_SYMBOL(vringh_init_user);
+
+/**
+ * vringh_getdesc_user - get next available descriptor from userspace ring.
+ * @vrh: the userspace vring.
+ * @riov: where to put the readable descriptors (or NULL)
+ * @wiov: where to put the writable descriptors (or NULL)
+ * @getrange: function to call to check ranges.
+ * @head: head index we received, for passing to vringh_complete_user().
+ *
+ * Returns 0 if there was no descriptor, 1 if there was, or -errno.
+ *
+ * Note that on error return, you can tell the difference between an
+ * invalid ring and a single invalid descriptor: in the former case,
+ * *head will be vrh->vring.num. You may be able to ignore an invalid
+ * descriptor, but there's not much you can do with an invalid ring.
+ *
+ * Note that you may need to clean up riov and wiov, even on error!
+ */
+int vringh_getdesc_user(struct vringh *vrh,
+ struct vringh_iov *riov,
+ struct vringh_iov *wiov,
+ bool (*getrange)(struct vringh *vrh,
+ u64 addr, struct vringh_range *r),
+ u16 *head)
+{
+ int err;
+
+ *head = vrh->vring.num;
+ err = __vringh_get_head(vrh, getu16_user, &vrh->last_avail_idx);
+ if (err < 0)
+ return err;
+
+ /* Empty... */
+ if (err == vrh->vring.num)
+ return 0;
+
+ /* We need the layouts to be the indentical for this to work */
+ BUILD_BUG_ON(sizeof(struct vringh_kiov) != sizeof(struct vringh_iov));
+ BUILD_BUG_ON(offsetof(struct vringh_kiov, iov) !=
+ offsetof(struct vringh_iov, iov));
+ BUILD_BUG_ON(offsetof(struct vringh_kiov, i) !=
+ offsetof(struct vringh_iov, i));
+ BUILD_BUG_ON(offsetof(struct vringh_kiov, used) !=
+ offsetof(struct vringh_iov, used));
+ BUILD_BUG_ON(offsetof(struct vringh_kiov, max_num) !=
+ offsetof(struct vringh_iov, max_num));
+ BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec));
+ BUILD_BUG_ON(offsetof(struct iovec, iov_base) !=
+ offsetof(struct kvec, iov_base));
+ BUILD_BUG_ON(offsetof(struct iovec, iov_len) !=
+ offsetof(struct kvec, iov_len));
+ BUILD_BUG_ON(sizeof(((struct iovec *)NULL)->iov_base)
+ != sizeof(((struct kvec *)NULL)->iov_base));
+ BUILD_BUG_ON(sizeof(((struct iovec *)NULL)->iov_len)
+ != sizeof(((struct kvec *)NULL)->iov_len));
+
+ *head = err;
+ err = __vringh_iov(vrh, *head, (struct vringh_kiov *)riov,
+ (struct vringh_kiov *)wiov,
+ range_check, getrange, GFP_KERNEL, copydesc_user);
+ if (err)
+ return err;
+
+ return 1;
+}
+EXPORT_SYMBOL(vringh_getdesc_user);
+
+/**
+ * vringh_iov_pull_user - copy bytes from vring_iov.
+ * @riov: the riov as passed to vringh_getdesc_user() (updated as we consume)
+ * @dst: the place to copy.
+ * @len: the maximum length to copy.
+ *
+ * Returns the bytes copied <= len or a negative errno.
+ */
+ssize_t vringh_iov_pull_user(struct vringh_iov *riov, void *dst, size_t len)
+{
+ return vringh_iov_xfer((struct vringh_kiov *)riov,
+ dst, len, xfer_from_user);
+}
+EXPORT_SYMBOL(vringh_iov_pull_user);
+
+/**
+ * vringh_iov_push_user - copy bytes into vring_iov.
+ * @wiov: the wiov as passed to vringh_getdesc_user() (updated as we consume)
+ * @dst: the place to copy.
+ * @len: the maximum length to copy.
+ *
+ * Returns the bytes copied <= len or a negative errno.
+ */
+ssize_t vringh_iov_push_user(struct vringh_iov *wiov,
+ const void *src, size_t len)
+{
+ return vringh_iov_xfer((struct vringh_kiov *)wiov,
+ (void *)src, len, xfer_to_user);
+}
+EXPORT_SYMBOL(vringh_iov_push_user);
+
+/**
+ * vringh_abandon_user - we've decided not to handle the descriptor(s).
+ * @vrh: the vring.
+ * @num: the number of descriptors to put back (ie. num
+ * vringh_get_user() to undo).
+ *
+ * The next vringh_get_user() will return the old descriptor(s) again.
+ */
+void vringh_abandon_user(struct vringh *vrh, unsigned int num)
+{
+ /* We only update vring_avail_event(vr) when we want to be notified,
+ * so we haven't changed that yet. */
+ vrh->last_avail_idx -= num;
+}
+EXPORT_SYMBOL(vringh_abandon_user);
+
+/**
+ * vringh_complete_user - we've finished with descriptor, publish it.
+ * @vrh: the vring.
+ * @head: the head as filled in by vringh_getdesc_user.
+ * @len: the length of data we have written.
+ *
+ * You should check vringh_need_notify_user() after one or more calls
+ * to this function.
+ */
+int vringh_complete_user(struct vringh *vrh, u16 head, u32 len)
+{
+ struct vring_used_elem used;
+
+ used.id = head;
+ used.len = len;
+ return __vringh_complete(vrh, &used, 1, putu16_user, putused_user);
+}
+EXPORT_SYMBOL(vringh_complete_user);
+
+/**
+ * vringh_complete_multi_user - we've finished with many descriptors.
+ * @vrh: the vring.
+ * @used: the head, length pairs.
+ * @num_used: the number of used elements.
+ *
+ * You should check vringh_need_notify_user() after one or more calls
+ * to this function.
+ */
+int vringh_complete_multi_user(struct vringh *vrh,
+ const struct vring_used_elem used[],
+ unsigned num_used)
+{
+ return __vringh_complete(vrh, used, num_used,
+ putu16_user, putused_user);
+}
+EXPORT_SYMBOL(vringh_complete_multi_user);
+
+/**
+ * vringh_notify_enable_user - we want to know if something changes.
+ * @vrh: the vring.
+ *
+ * This always enables notifications, but returns true if there are
+ * now more buffers available in the vring.
+ */
+bool vringh_notify_enable_user(struct vringh *vrh)
+{
+ return __vringh_notify_enable(vrh, getu16_user, putu16_user);
+}
+EXPORT_SYMBOL(vringh_notify_enable_user);
+
+/**
+ * vringh_notify_disable_user - don't tell us if something changes.
+ * @vrh: the vring.
+ *
+ * This is our normal running state: we disable and then only enable when
+ * we're going to sleep.
+ */
+void vringh_notify_disable_user(struct vringh *vrh)
+{
+ __vringh_notify_disable(vrh, putu16_user);
+}
+EXPORT_SYMBOL(vringh_notify_disable_user);
+
+/**
+ * vringh_need_notify_user - must we tell the other side about used buffers?
+ * @vrh: the vring we've called vringh_complete_user() on.
+ *
+ * Returns -errno or 0 if we don't need to tell the other side, 1 if we do.
+ */
+int vringh_need_notify_user(struct vringh *vrh)
+{
+ return __vringh_need_notify(vrh, getu16_user);
+}
+EXPORT_SYMBOL(vringh_need_notify_user);
+
+/* Kernelspace access helpers. */
+static inline int getu16_kern(u16 *val, const u16 *p)
+{
+ *val = ACCESS_ONCE(*p);
+ return 0;
+}
+
+static inline int putu16_kern(u16 *p, u16 val)
+{
+ ACCESS_ONCE(*p) = val;
+ return 0;
+}
+
+static inline int copydesc_kern(void *dst, const void *src, size_t len)
+{
+ memcpy(dst, src, len);
+ return 0;
+}
+
+static inline int putused_kern(struct vring_used_elem *dst,
+ const struct vring_used_elem *src,
+ unsigned int num)
+{
+ memcpy(dst, src, num * sizeof(*dst));
+ return 0;
+}
+
+static inline int xfer_kern(void *src, void *dst, size_t len)
+{
+ memcpy(dst, src, len);
+ return 0;
+}
+
+/**
+ * vringh_init_kern - initialize a vringh for a kernelspace vring.
+ * @vrh: the vringh to initialize.
+ * @features: the feature bits for this ring.
+ * @num: the number of elements.
+ * @weak_barriers: true if we only need memory barriers, not I/O.
+ * @desc: the userpace descriptor pointer.
+ * @avail: the userpace avail pointer.
+ * @used: the userpace used pointer.
+ *
+ * Returns an error if num is invalid.
+ */
+int vringh_init_kern(struct vringh *vrh, u32 features,
+ unsigned int num, bool weak_barriers,
+ struct vring_desc *desc,
+ struct vring_avail *avail,
+ struct vring_used *used)
+{
+ /* Sane power of 2 please! */
+ if (!num || num > 0xffff || (num & (num - 1))) {
+ vringh_bad("Bad ring size %u", num);
+ return -EINVAL;
+ }
+
+ vrh->event_indices = (features & (1 << VIRTIO_RING_F_EVENT_IDX));
+ vrh->weak_barriers = weak_barriers;
+ vrh->listening = false;
+ vrh->completed = 0;
+ vrh->last_avail_idx = 0;
+ vrh->last_used_idx = 0;
+ vrh->vring.num = num;
+ vrh->vring.desc = desc;
+ vrh->vring.avail = avail;
+ vrh->vring.used = used;
+ return 0;
+}
+EXPORT_SYMBOL(vringh_init_kern);
+
+/**
+ * vringh_getdesc_kern - get next available descriptor from kernelspace ring.
+ * @vrh: the kernelspace vring.
+ * @riov: where to put the readable descriptors (or NULL)
+ * @wiov: where to put the writable descriptors (or NULL)
+ * @head: head index we received, for passing to vringh_complete_kern().
+ * @gfp: flags for allocating larger riov/wiov.
+ *
+ * Returns 0 if there was no descriptor, 1 if there was, or -errno.
+ *
+ * Note that on error return, you can tell the difference between an
+ * invalid ring and a single invalid descriptor: in the former case,
+ * *head will be vrh->vring.num. You may be able to ignore an invalid
+ * descriptor, but there's not much you can do with an invalid ring.
+ *
+ * Note that you may need to clean up riov and wiov, even on error!
+ */
+int vringh_getdesc_kern(struct vringh *vrh,
+ struct vringh_kiov *riov,
+ struct vringh_kiov *wiov,
+ u16 *head,
+ gfp_t gfp)
+{
+ int err;
+
+ err = __vringh_get_head(vrh, getu16_kern, &vrh->last_avail_idx);
+ if (err < 0)
+ return err;
+
+ /* Empty... */
+ if (err == vrh->vring.num)
+ return 0;
+
+ *head = err;
+ err = __vringh_iov(vrh, *head, riov, wiov, no_range_check, NULL,
+ gfp, copydesc_kern);
+ if (err)
+ return err;
+
+ return 1;
+}
+EXPORT_SYMBOL(vringh_getdesc_kern);
+
+/**
+ * vringh_iov_pull_kern - copy bytes from vring_iov.
+ * @riov: the riov as passed to vringh_getdesc_kern() (updated as we consume)
+ * @dst: the place to copy.
+ * @len: the maximum length to copy.
+ *
+ * Returns the bytes copied <= len or a negative errno.
+ */
+ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len)
+{
+ return vringh_iov_xfer(riov, dst, len, xfer_kern);
+}
+EXPORT_SYMBOL(vringh_iov_pull_kern);
+
+/**
+ * vringh_iov_push_kern - copy bytes into vring_iov.
+ * @wiov: the wiov as passed to vringh_getdesc_kern() (updated as we consume)
+ * @dst: the place to copy.
+ * @len: the maximum length to copy.
+ *
+ * Returns the bytes copied <= len or a negative errno.
+ */
+ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov,
+ const void *src, size_t len)
+{
+ return vringh_iov_xfer(wiov, (void *)src, len, xfer_kern);
+}
+EXPORT_SYMBOL(vringh_iov_push_kern);
+
+/**
+ * vringh_abandon_kern - we've decided not to handle the descriptor(s).
+ * @vrh: the vring.
+ * @num: the number of descriptors to put back (ie. num
+ * vringh_get_kern() to undo).
+ *
+ * The next vringh_get_kern() will return the old descriptor(s) again.
+ */
+void vringh_abandon_kern(struct vringh *vrh, unsigned int num)
+{
+ /* We only update vring_avail_event(vr) when we want to be notified,
+ * so we haven't changed that yet. */
+ vrh->last_avail_idx -= num;
+}
+EXPORT_SYMBOL(vringh_abandon_kern);
+
+/**
+ * vringh_complete_kern - we've finished with descriptor, publish it.
+ * @vrh: the vring.
+ * @head: the head as filled in by vringh_getdesc_kern.
+ * @len: the length of data we have written.
+ *
+ * You should check vringh_need_notify_kern() after one or more calls
+ * to this function.
+ */
+int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len)
+{
+ struct vring_used_elem used;
+
+ used.id = head;
+ used.len = len;
+
+ return __vringh_complete(vrh, &used, 1, putu16_kern, putused_kern);
+}
+EXPORT_SYMBOL(vringh_complete_kern);
+
+/**
+ * vringh_notify_enable_kern - we want to know if something changes.
+ * @vrh: the vring.
+ *
+ * This always enables notifications, but returns true if there are
+ * now more buffers available in the vring.
+ */
+bool vringh_notify_enable_kern(struct vringh *vrh)
+{
+ return __vringh_notify_enable(vrh, getu16_kern, putu16_kern);
+}
+EXPORT_SYMBOL(vringh_notify_enable_kern);
+
+/**
+ * vringh_notify_disable_kern - don't tell us if something changes.
+ * @vrh: the vring.
+ *
+ * This is our normal running state: we disable and then only enable when
+ * we're going to sleep.
+ */
+void vringh_notify_disable_kern(struct vringh *vrh)
+{
+ __vringh_notify_disable(vrh, putu16_kern);
+}
+EXPORT_SYMBOL(vringh_notify_disable_kern);
+
+/**
+ * vringh_need_notify_kern - must we tell the other side about used buffers?
+ * @vrh: the vring we've called vringh_complete_kern() on.
+ *
+ * Returns -errno or 0 if we don't need to tell the other side, 1 if we do.
+ */
+int vringh_need_notify_kern(struct vringh *vrh)
+{
+ return __vringh_need_notify(vrh, getu16_kern);
+}
+EXPORT_SYMBOL(vringh_need_notify_kern);
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
new file mode 100644
index 0000000..ab41185
--- /dev/null
+++ b/include/linux/vringh.h
@@ -0,0 +1,185 @@
+/*
+ * Linux host-side vring helpers; for when the kernel needs to access
+ * someone else's vring.
+ *
+ * Copyright IBM Corporation, 2013.
+ * Parts taken from drivers/vhost/vhost.c Copyright 2009 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Written by: Rusty Russell <rusty@rustcorp.com.au>
+ */
+#ifndef _LINUX_VRINGH_H
+#define _LINUX_VRINGH_H
+#include <uapi/linux/virtio_ring.h>
+#include <linux/uio.h>
+#include <linux/slab.h>
+#include <asm/barrier.h>
+
+/* virtio_ring with information needed for host access. */
+struct vringh {
+ /* Guest publishes used event idx (note: we always do). */
+ bool event_indices;
+
+ /* Have we told the other end we want to be notified? */
+ bool listening;
+
+ /* Can we get away with weak barriers? */
+ bool weak_barriers;
+
+ /* Last available index we saw (ie. where we're up to). */
+ u16 last_avail_idx;
+
+ /* Last index we used. */
+ u16 last_used_idx;
+
+ /* How many descriptors we've completed since last need_notify(). */
+ u32 completed;
+
+ /* The vring (note: it may contain user pointers!) */
+ struct vring vring;
+};
+
+/* The memory the vring can access, and what offset to apply. */
+struct vringh_range {
+ u64 start, end_incl;
+ u64 offset;
+};
+
+/* All the information about an iovec. */
+struct vringh_iov {
+ struct iovec *iov;
+ size_t off; /* Within iov[i] */
+ unsigned i, used, max_num;
+};
+
+/* All the information about a kvec. */
+struct vringh_kiov {
+ struct kvec *iov;
+ size_t off; /* Within iov[i] */
+ unsigned i, used, max_num;
+};
+
+/* Flag on max_num to indicate we're kmalloced. */
+#define VRINGH_IOV_ALLOCATED 0x8000000
+
+/* Helpers for userspace vrings. */
+int vringh_init_user(struct vringh *vrh, u32 features,
+ unsigned int num, bool weak_barriers,
+ struct vring_desc __user *desc,
+ struct vring_avail __user *avail,
+ struct vring_used __user *used);
+
+static inline void vringh_iov_init(struct vringh_iov *iov,
+ struct iovec *iovec, unsigned num)
+{
+ iov->used = iov->i = 0;
+ iov->off = 0;
+ iov->max_num = num;
+ iov->iov = iovec;
+}
+
+static inline void vringh_iov_reset(struct vringh_iov *iov)
+{
+ iov->off = 0;
+ iov->i = 0;
+}
+
+static inline void vringh_iov_cleanup(struct vringh_iov *iov)
+{
+ if (iov->max_num & VRINGH_IOV_ALLOCATED)
+ kfree(iov->iov);
+ iov->max_num = iov->used = iov->i = iov->off = 0;
+ iov->iov = NULL;
+}
+
+/* Convert a descriptor into iovecs. */
+int vringh_getdesc_user(struct vringh *vrh,
+ struct vringh_iov *riov,
+ struct vringh_iov *wiov,
+ bool (*getrange)(struct vringh *vrh,
+ u64 addr, struct vringh_range *r),
+ u16 *head);
+
+/* Copy bytes from readable vsg, consuming it (and incrementing wiov->i). */
+ssize_t vringh_iov_pull_user(struct vringh_iov *riov, void *dst, size_t len);
+
+/* Copy bytes into writable vsg, consuming it (and incrementing wiov->i). */
+ssize_t vringh_iov_push_user(struct vringh_iov *wiov,
+ const void *src, size_t len);
+
+/* Mark a descriptor as used. */
+int vringh_complete_user(struct vringh *vrh, u16 head, u32 len);
+int vringh_complete_multi_user(struct vringh *vrh,
+ const struct vring_used_elem used[],
+ unsigned num_used);
+
+/* Pretend we've never seen descriptor (for easy error handling). */
+void vringh_abandon_user(struct vringh *vrh, unsigned int num);
+
+/* Do we need to fire the eventfd to notify the other side? */
+int vringh_need_notify_user(struct vringh *vrh);
+
+bool vringh_notify_enable_user(struct vringh *vrh);
+void vringh_notify_disable_user(struct vringh *vrh);
+
+/* Helpers for kernelspace vrings. */
+int vringh_init_kern(struct vringh *vrh, u32 features,
+ unsigned int num, bool weak_barriers,
+ struct vring_desc *desc,
+ struct vring_avail *avail,
+ struct vring_used *used);
+
+static inline void vringh_kiov_init(struct vringh_kiov *kiov,
+ struct kvec *kvec, unsigned num)
+{
+ kiov->used = kiov->i = 0;
+ kiov->off = 0;
+ kiov->max_num = num;
+ kiov->iov = kvec;
+}
+
+static inline void vringh_kiov_reset(struct vringh_kiov *kiov)
+{
+ kiov->off = 0;
+ kiov->i = 0;
+}
+
+static inline void vringh_kiov_cleanup(struct vringh_kiov *kiov)
+{
+ if (kiov->max_num & VRINGH_IOV_ALLOCATED)
+ kfree(kiov->iov);
+ kiov->max_num = kiov->used = kiov->i = kiov->off = 0;
+ kiov->iov = NULL;
+}
+
+int vringh_getdesc_kern(struct vringh *vrh,
+ struct vringh_kiov *riov,
+ struct vringh_kiov *wiov,
+ u16 *head,
+ gfp_t gfp);
+
+ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len);
+ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov,
+ const void *src, size_t len);
+void vringh_abandon_kern(struct vringh *vrh, unsigned int num);
+int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len);
+
+bool vringh_notify_enable_kern(struct vringh *vrh);
+void vringh_notify_disable_kern(struct vringh *vrh);
+
+int vringh_need_notify_kern(struct vringh *vrh);
+
+#endif /* _LINUX_VRINGH_H */
^ permalink raw reply related [flat|nested] 16+ messages in thread