* [PATCH 1/9] AF_RXRPC: Add blkcipher accessors for using kernel data directly
2007-04-02 22:44 [PATCH 0/9] AF_RXRPC socket family and AFS rewrite David Howells
@ 2007-04-02 22:44 ` David Howells
2007-04-02 22:45 ` [PATCH 2/9] AF_RXRPC: Move generic skbuff stuff from XFRM code to generic code David Howells
` (3 subsequent siblings)
4 siblings, 0 replies; 7+ messages in thread
From: David Howells @ 2007-04-02 22:44 UTC (permalink / raw)
To: torvalds, akpm; +Cc: linux-kernel, linux-fsdevel, netdev, dhowells
Add blkcipher accessors for using kernel data directly without the use of
scatter lists.
Also add a CRYPTO_ALG_DMA algorithm capability flag to permit or deny the use
of DMA and hardware accelerators. A hardware accelerator may not be used to
access any arbitrary piece of kernel memory lest it not be in a DMA'able
region. Only software algorithms may do that.
If kernel data is going to be accessed directly, then CRYPTO_ALG_DMA must, for
instance, be passed in the mask of crypto_alloc_blkcipher(), but not the type.
This is used by AF_RXRPC to do quick encryptions, where the size of the data
being encrypted or decrypted is 8 bytes or, occasionally, 16 bytes (ie: one or
two chunks only), and since these data are generally on the stack they may be
split over two pages. Because they're so small, and because they may be
misaligned, setting up a scatter-gather list is overly expensive. It is very
unlikely that a hardware FCrypt PCBC engine will be encountered (there is not,
as far as I know, any such thing), and even if one is encountered, the
setup/teardown costs for such small transactions will almost certainly be
prohibitive.
Encrypting and decrypting whole packets, on the other hand, is done through the
scatter-gather list interface as the amount of data is sufficient that the
expense of doing virtual address to page calculations is sufficiently small by
comparison.
Signed-Off-By: David Howells <dhowells@redhat.com>
---
crypto/blkcipher.c | 2 +
crypto/pcbc.c | 62 +++++++++++++++++++++++++
include/linux/crypto.h | 118 ++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 181 insertions(+), 1 deletions(-)
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index b5befe8..4498b2d 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -376,6 +376,8 @@ static int crypto_init_blkcipher_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
crt->setkey = setkey;
crt->encrypt = alg->encrypt;
crt->decrypt = alg->decrypt;
+ crt->encrypt_kernel = alg->encrypt_kernel;
+ crt->decrypt_kernel = alg->decrypt_kernel;
addr = (unsigned long)crypto_tfm_ctx(tfm);
addr = ALIGN(addr, align);
diff --git a/crypto/pcbc.c b/crypto/pcbc.c
index 5174d7f..fa76111 100644
--- a/crypto/pcbc.c
+++ b/crypto/pcbc.c
@@ -126,6 +126,36 @@ static int crypto_pcbc_encrypt(struct blkcipher_desc *desc,
return err;
}
+static int crypto_pcbc_encrypt_kernel(struct blkcipher_desc *desc,
+ u8 *dst, const u8 *src,
+ unsigned int nbytes)
+{
+ struct blkcipher_walk walk;
+ struct crypto_blkcipher *tfm = desc->tfm;
+ struct crypto_pcbc_ctx *ctx = crypto_blkcipher_ctx(tfm);
+ struct crypto_cipher *child = ctx->child;
+ void (*xor)(u8 *, const u8 *, unsigned int bs) = ctx->xor;
+
+ BUG_ON(crypto_tfm_alg_capabilities(crypto_cipher_tfm(child)) &
+ CRYPTO_ALG_DMA);
+
+ if (nbytes == 0)
+ return 0;
+
+ memset(&walk, 0, sizeof(walk));
+ walk.src.virt.addr = (u8 *) src;
+ walk.dst.virt.addr = (u8 *) dst;
+ walk.nbytes = nbytes;
+ walk.total = nbytes;
+ walk.iv = desc->info;
+
+ if (walk.src.virt.addr == walk.dst.virt.addr)
+ nbytes = crypto_pcbc_encrypt_inplace(desc, &walk, child, xor);
+ else
+ nbytes = crypto_pcbc_encrypt_segment(desc, &walk, child, xor);
+ return 0;
+}
+
static int crypto_pcbc_decrypt_segment(struct blkcipher_desc *desc,
struct blkcipher_walk *walk,
struct crypto_cipher *tfm,
@@ -211,6 +241,36 @@ static int crypto_pcbc_decrypt(struct blkcipher_desc *desc,
return err;
}
+static int crypto_pcbc_decrypt_kernel(struct blkcipher_desc *desc,
+ u8 *dst, const u8 *src,
+ unsigned int nbytes)
+{
+ struct blkcipher_walk walk;
+ struct crypto_blkcipher *tfm = desc->tfm;
+ struct crypto_pcbc_ctx *ctx = crypto_blkcipher_ctx(tfm);
+ struct crypto_cipher *child = ctx->child;
+ void (*xor)(u8 *, const u8 *, unsigned int bs) = ctx->xor;
+
+ BUG_ON(crypto_tfm_alg_capabilities(crypto_cipher_tfm(child)) &
+ CRYPTO_ALG_DMA);
+
+ if (nbytes == 0)
+ return 0;
+
+ memset(&walk, 0, sizeof(walk));
+ walk.src.virt.addr = (u8 *) src;
+ walk.dst.virt.addr = (u8 *) dst;
+ walk.nbytes = nbytes;
+ walk.total = nbytes;
+ walk.iv = desc->info;
+
+ if (walk.src.virt.addr == walk.dst.virt.addr)
+ nbytes = crypto_pcbc_decrypt_inplace(desc, &walk, child, xor);
+ else
+ nbytes = crypto_pcbc_decrypt_segment(desc, &walk, child, xor);
+ return 0;
+}
+
static void xor_byte(u8 *a, const u8 *b, unsigned int bs)
{
do {
@@ -313,6 +373,8 @@ static struct crypto_instance *crypto_pcbc_alloc(void *param, unsigned int len)
inst->alg.cra_blkcipher.setkey = crypto_pcbc_setkey;
inst->alg.cra_blkcipher.encrypt = crypto_pcbc_encrypt;
inst->alg.cra_blkcipher.decrypt = crypto_pcbc_decrypt;
+ inst->alg.cra_blkcipher.encrypt_kernel = crypto_pcbc_encrypt_kernel;
+ inst->alg.cra_blkcipher.decrypt_kernel = crypto_pcbc_decrypt_kernel;
out_put_alg:
crypto_mod_put(alg);
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 779aa78..17e786a 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -40,7 +40,10 @@
#define CRYPTO_ALG_LARVAL 0x00000010
#define CRYPTO_ALG_DEAD 0x00000020
#define CRYPTO_ALG_DYING 0x00000040
-#define CRYPTO_ALG_ASYNC 0x00000080
+
+#define CRYPTO_ALG_CAP_MASK 0x00000180 /* capabilities mask */
+#define CRYPTO_ALG_ASYNC 0x00000080 /* capable of async operation */
+#define CRYPTO_ALG_DMA 0x00000100 /* capable of using of DMA */
/*
* Set this bit if and only if the algorithm requires another algorithm of
@@ -125,6 +128,10 @@ struct blkcipher_alg {
int (*decrypt)(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes);
+ int (*encrypt_kernel)(struct blkcipher_desc *desc, u8 *dst,
+ const u8 *src, unsigned int nbytes);
+ int (*decrypt_kernel)(struct blkcipher_desc *desc, u8 *dst,
+ const u8 *src, unsigned int nbytes);
unsigned int min_keysize;
unsigned int max_keysize;
@@ -240,6 +247,10 @@ struct blkcipher_tfm {
struct scatterlist *src, unsigned int nbytes);
int (*decrypt)(struct blkcipher_desc *desc, struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes);
+ int (*encrypt_kernel)(struct blkcipher_desc *desc, u8 *dst,
+ const u8 *src, unsigned int nbytes);
+ int (*decrypt_kernel)(struct blkcipher_desc *desc, u8 *dst,
+ const u8 *src, unsigned int nbytes);
};
struct cipher_tfm {
@@ -372,6 +383,11 @@ static inline u32 crypto_tfm_alg_type(struct crypto_tfm *tfm)
return tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK;
}
+static inline u32 crypto_tfm_alg_capabilities(struct crypto_tfm *tfm)
+{
+ return tfm->__crt_alg->cra_flags & CRYPTO_ALG_CAP_MASK;
+}
+
static inline unsigned int crypto_tfm_alg_blocksize(struct crypto_tfm *tfm)
{
return tfm->__crt_alg->cra_blocksize;
@@ -529,6 +545,56 @@ static inline int crypto_blkcipher_encrypt_iv(struct blkcipher_desc *desc,
return crypto_blkcipher_crt(desc->tfm)->encrypt(desc, dst, src, nbytes);
}
+/**
+ * crypto_blkcipher_encrypt_kernel - Encrypt flat kernel buffer
+ * - @desc - block cipher descriptor indicating the encryption to apply
+ * - @dst - output buffer
+ * - @src - input data
+ * - @nbytes - amount of data
+ *
+ * Encrypt data contained in a flat kernel buffer into another flat kernel
+ * buffer. This avoids the need to spend resources to set up a scatterlist for
+ * a very small amount of data. The encryption begins by selecting the
+ * initialisation vector of the actual block cipher as the initialisation
+ * vector to use and update. This leaves the IV in the cipher altered.
+ *
+ * This should not be used with a cipher that's marked CRYPTO_ALG_DMA as the
+ * DMA process requires a scatterlist to locate the physical pages on which the
+ * data resides.
+ */
+static inline void crypto_blkcipher_encrypt_kernel(struct blkcipher_desc *desc,
+ u8 *dst, const u8 *src,
+ unsigned int nbytes)
+{
+ desc->info = crypto_blkcipher_crt(desc->tfm)->iv;
+ crypto_blkcipher_crt(desc->tfm)->encrypt_kernel(desc, dst, src,
+ nbytes);
+}
+
+/**
+ * crypto_blkcipher_encrypt_kernel_iv - Encrypt flat kernel buffer
+ * - @desc - block cipher descriptor indicating the encryption to apply
+ * - @dst - output buffer
+ * - @src - input data
+ * - @nbytes - amount of data
+ *
+ * Encrypt data contained in a flat kernel buffer into another flat kernel
+ * buffer. This avoids the need to spend resources to set up a scatterlist for
+ * a very small amount of data. The encryption proceeds from the
+ * initialisation vector held within the block cipher descriptor.
+ *
+ * This should not be used with a cipher that's marked CRYPTO_ALG_DMA as the
+ * DMA process requires a scatterlist to locate the physical pages on which the
+ * data resides.
+ */
+static inline void crypto_blkcipher_encrypt_kernel_iv(
+ struct blkcipher_desc *desc, u8 *dst, const u8 *src,
+ unsigned int nbytes)
+{
+ crypto_blkcipher_crt(desc->tfm)->encrypt_kernel(desc, dst, src,
+ nbytes);
+}
+
static inline int crypto_blkcipher_decrypt(struct blkcipher_desc *desc,
struct scatterlist *dst,
struct scatterlist *src,
@@ -546,6 +612,56 @@ static inline int crypto_blkcipher_decrypt_iv(struct blkcipher_desc *desc,
return crypto_blkcipher_crt(desc->tfm)->decrypt(desc, dst, src, nbytes);
}
+/**
+ * crypto_blkcipher_decrypt_kernel - Decrypt flat kernel buffer
+ * - @desc - block cipher descriptor indicating the decryption to apply
+ * - @dst - output buffer
+ * - @src - input data
+ * - @nbytes - amount of data
+ *
+ * Decrypt data contained in a flat kernel buffer into another flat kernel
+ * buffer. This avoids the need to spend resources to set up a scatterlist for
+ * a very small amount of data. The decryption begins by selecting the
+ * initialisation vector of the actual block cipher as the initialisation
+ * vector to use and update. This leaves the IV in the cipher altered.
+ *
+ * This should not be used with a cipher that's marked CRYPTO_ALG_DMA as the
+ * DMA process requires a scatterlist to locate the physical pages on which the
+ * data resides.
+ */
+static inline void crypto_blkcipher_decrypt_kernel(struct blkcipher_desc *desc,
+ u8 *dst, const u8 *src,
+ unsigned int nbytes)
+{
+ desc->info = crypto_blkcipher_crt(desc->tfm)->iv;
+ crypto_blkcipher_crt(desc->tfm)->decrypt_kernel(desc, dst, src,
+ nbytes);
+}
+
+/**
+ * crypto_blkcipher_decrypt_kernel_iv - Decrypt flat kernel buffer
+ * - @desc - block cipher descriptor indicating the decryption to apply
+ * - @dst - output buffer
+ * - @src - input data
+ * - @nbytes - amount of data
+ *
+ * Encrypt data contained in a flat kernel buffer into another flat kernel
+ * buffer. This avoids the need to spend resources to set up a scatterlist for
+ * a very small amount of data. The decryption proceeds from the
+ * initialisation vector held within the block cipher descriptor.
+ *
+ * This should not be used with a cipher that's marked CRYPTO_ALG_DMA as the
+ * DMA process requires a scatterlist to locate the physical pages on which the
+ * data resides.
+ */
+static inline void crypto_blkcipher_decrypt_kernel_iv(
+ struct blkcipher_desc *desc, u8 *dst, const u8 *src,
+ unsigned int nbytes)
+{
+ crypto_blkcipher_crt(desc->tfm)->decrypt_kernel(desc, dst, src,
+ nbytes);
+}
+
static inline void crypto_blkcipher_set_iv(struct crypto_blkcipher *tfm,
const u8 *src, unsigned int len)
{
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH 2/9] AF_RXRPC: Move generic skbuff stuff from XFRM code to generic code
2007-04-02 22:44 [PATCH 0/9] AF_RXRPC socket family and AFS rewrite David Howells
2007-04-02 22:44 ` [PATCH 1/9] AF_RXRPC: Add blkcipher accessors for using kernel data directly David Howells
@ 2007-04-02 22:45 ` David Howells
2007-04-03 3:20 ` David Miller
2007-04-02 22:45 ` [PATCH 3/9] AF_RXRPC: Make it possible to merely try to cancel timers and delayed work David Howells
` (2 subsequent siblings)
4 siblings, 1 reply; 7+ messages in thread
From: David Howells @ 2007-04-02 22:45 UTC (permalink / raw)
To: torvalds, akpm; +Cc: linux-kernel, linux-fsdevel, netdev, dhowells
Move generic skbuff stuff from XFRM code to generic code so that AF_RXRPC can
use it too.
The kdoc comments I've attached to the functions needs to be checked by whoever
wrote them as I had to make some guesses about the workings of these functions.
Signed-Off-By: David Howells <dhowells@redhat.com>
---
include/linux/skbuff.h | 6 ++
include/net/esp.h | 2 -
net/core/skbuff.c | 188 ++++++++++++++++++++++++++++++++++++++++++++++++
net/xfrm/xfrm_algo.c | 169 -------------------------------------------
4 files changed, 194 insertions(+), 171 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 82f43ad..d53ff7c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -83,6 +83,7 @@
*/
struct net_device;
+struct scatterlist;
#ifdef CONFIG_NETFILTER
struct nf_conntrack {
@@ -364,6 +365,11 @@ extern struct sk_buff *skb_realloc_headroom(struct sk_buff *skb,
extern struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
int newheadroom, int newtailroom,
gfp_t priority);
+extern int skb_to_sgvec(struct sk_buff *skb,
+ struct scatterlist *sg, int offset,
+ int len);
+extern int skb_cow_data(struct sk_buff *skb, int tailbits,
+ struct sk_buff **trailer);
extern int skb_pad(struct sk_buff *skb, int pad);
#define dev_kfree_skb(a) kfree_skb(a)
extern void skb_over_panic(struct sk_buff *skb, int len,
diff --git a/include/net/esp.h b/include/net/esp.h
index 713d039..d05d8d2 100644
--- a/include/net/esp.h
+++ b/include/net/esp.h
@@ -40,8 +40,6 @@ struct esp_data
} auth;
};
-extern int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len);
-extern int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer);
extern void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len);
static inline int esp_mac_digest(struct esp_data *esp, struct sk_buff *skb,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 87573ae..156b9c0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -55,6 +55,7 @@
#include <linux/cache.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
+#include <linux/scatterlist.h>
#include <net/protocol.h>
#include <net/dst.h>
@@ -2060,6 +2061,190 @@ void __init skb_init(void)
NULL, NULL);
}
+/**
+ * skb_to_sgvec - Fill a scatter-gather list from a socket buffer
+ * @skb: Socket buffer containing the buffers to be mapped
+ * @sg: The scatter-gather list to map into
+ * @offset: The offset into the buffer's contents to start mapping
+ * @len: Length of buffer space to be mapped
+ *
+ * Fill the specified scatter-gather list with mappings/pointers into a
+ * region of the buffer space attached to a socket buffer.
+ */
+int
+skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
+{
+ int start = skb_headlen(skb);
+ int i, copy = start - offset;
+ int elt = 0;
+
+ if (copy > 0) {
+ if (copy > len)
+ copy = len;
+ sg[elt].page = virt_to_page(skb->data + offset);
+ sg[elt].offset = (unsigned long)(skb->data + offset) % PAGE_SIZE;
+ sg[elt].length = copy;
+ elt++;
+ if ((len -= copy) == 0)
+ return elt;
+ offset += copy;
+ }
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ int end;
+
+ BUG_TRAP(start <= offset + len);
+
+ end = start + skb_shinfo(skb)->frags[i].size;
+ if ((copy = end - offset) > 0) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ if (copy > len)
+ copy = len;
+ sg[elt].page = frag->page;
+ sg[elt].offset = frag->page_offset+offset-start;
+ sg[elt].length = copy;
+ elt++;
+ if (!(len -= copy))
+ return elt;
+ offset += copy;
+ }
+ start = end;
+ }
+
+ if (skb_shinfo(skb)->frag_list) {
+ struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+ for (; list; list = list->next) {
+ int end;
+
+ BUG_TRAP(start <= offset + len);
+
+ end = start + list->len;
+ if ((copy = end - offset) > 0) {
+ if (copy > len)
+ copy = len;
+ elt += skb_to_sgvec(list, sg+elt, offset - start, copy);
+ if ((len -= copy) == 0)
+ return elt;
+ offset += copy;
+ }
+ start = end;
+ }
+ }
+ BUG_ON(len);
+ return elt;
+}
+
+/**
+ * skb_cow_data - Check that a socket buffer's data buffers are writable
+ * @skb: The socket buffer to check.
+ * @tailbits: Amount of trailing space to be added
+ * @trailer: Returned pointer to the skb where the @tailbits space begins
+ *
+ * Make sure that the data buffers attached to a socket buffer are
+ * writable. If they are not, private copies are made of the data buffers
+ * and the socket buffer is set to use these instead.
+ *
+ * If @tailbits is given, make sure that there is space to write @tailbits
+ * bytes of data beyond current end of socket buffer. @trailer will be
+ * set to point to the skb in which this space begins.
+ *
+ * The number of scatterlist elements required to completely map the
+ * COW'd and extended socket buffer will be returned.
+ */
+int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
+{
+ int copyflag;
+ int elt;
+ struct sk_buff *skb1, **skb_p;
+
+ /* If skb is cloned or its head is paged, reallocate
+ * head pulling out all the pages (pages are considered not writable
+ * at the moment even if they are anonymous).
+ */
+ if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) &&
+ __pskb_pull_tail(skb, skb_pagelen(skb)-skb_headlen(skb)) == NULL)
+ return -ENOMEM;
+
+ /* Easy case. Most of packets will go this way. */
+ if (!skb_shinfo(skb)->frag_list) {
+ /* A little of trouble, not enough of space for trailer.
+ * This should not happen, when stack is tuned to generate
+ * good frames. OK, on miss we reallocate and reserve even more
+ * space, 128 bytes is fair. */
+
+ if (skb_tailroom(skb) < tailbits &&
+ pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC))
+ return -ENOMEM;
+
+ /* Voila! */
+ *trailer = skb;
+ return 1;
+ }
+
+ /* Misery. We are in troubles, going to mincer fragments... */
+
+ elt = 1;
+ skb_p = &skb_shinfo(skb)->frag_list;
+ copyflag = 0;
+
+ while ((skb1 = *skb_p) != NULL) {
+ int ntail = 0;
+
+ /* The fragment is partially pulled by someone,
+ * this can happen on input. Copy it and everything
+ * after it. */
+
+ if (skb_shared(skb1))
+ copyflag = 1;
+
+ /* If the skb is the last, worry about trailer. */
+
+ if (skb1->next == NULL && tailbits) {
+ if (skb_shinfo(skb1)->nr_frags ||
+ skb_shinfo(skb1)->frag_list ||
+ skb_tailroom(skb1) < tailbits)
+ ntail = tailbits + 128;
+ }
+
+ if (copyflag ||
+ skb_cloned(skb1) ||
+ ntail ||
+ skb_shinfo(skb1)->nr_frags ||
+ skb_shinfo(skb1)->frag_list) {
+ struct sk_buff *skb2;
+
+ /* Fuck, we are miserable poor guys... */
+ if (ntail == 0)
+ skb2 = skb_copy(skb1, GFP_ATOMIC);
+ else
+ skb2 = skb_copy_expand(skb1,
+ skb_headroom(skb1),
+ ntail,
+ GFP_ATOMIC);
+ if (unlikely(skb2 == NULL))
+ return -ENOMEM;
+
+ if (skb1->sk)
+ skb_set_owner_w(skb2, skb1->sk);
+
+ /* Looking around. Are we still alive?
+ * OK, link new skb, drop old one */
+
+ skb2->next = skb1->next;
+ *skb_p = skb2;
+ kfree_skb(skb1);
+ skb1 = skb2;
+ }
+ elt++;
+ *trailer = skb1;
+ skb_p = &skb1->next;
+ }
+
+ return elt;
+}
+
EXPORT_SYMBOL(___pskb_trim);
EXPORT_SYMBOL(__kfree_skb);
EXPORT_SYMBOL(kfree_skb);
@@ -2094,3 +2279,6 @@ EXPORT_SYMBOL(skb_seq_read);
EXPORT_SYMBOL(skb_abort_seq_read);
EXPORT_SYMBOL(skb_find_text);
EXPORT_SYMBOL(skb_append_datato_frags);
+
+EXPORT_SYMBOL_GPL(skb_to_sgvec);
+EXPORT_SYMBOL_GPL(skb_cow_data);
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index f373a8a..6249a94 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -612,175 +612,6 @@ EXPORT_SYMBOL_GPL(skb_icv_walk);
#if defined(CONFIG_INET_ESP) || defined(CONFIG_INET_ESP_MODULE) || defined(CONFIG_INET6_ESP) || defined(CONFIG_INET6_ESP_MODULE)
-/* Looking generic it is not used in another places. */
-
-int
-skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
-{
- int start = skb_headlen(skb);
- int i, copy = start - offset;
- int elt = 0;
-
- if (copy > 0) {
- if (copy > len)
- copy = len;
- sg[elt].page = virt_to_page(skb->data + offset);
- sg[elt].offset = (unsigned long)(skb->data + offset) % PAGE_SIZE;
- sg[elt].length = copy;
- elt++;
- if ((len -= copy) == 0)
- return elt;
- offset += copy;
- }
-
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- int end;
-
- BUG_TRAP(start <= offset + len);
-
- end = start + skb_shinfo(skb)->frags[i].size;
- if ((copy = end - offset) > 0) {
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
- if (copy > len)
- copy = len;
- sg[elt].page = frag->page;
- sg[elt].offset = frag->page_offset+offset-start;
- sg[elt].length = copy;
- elt++;
- if (!(len -= copy))
- return elt;
- offset += copy;
- }
- start = end;
- }
-
- if (skb_shinfo(skb)->frag_list) {
- struct sk_buff *list = skb_shinfo(skb)->frag_list;
-
- for (; list; list = list->next) {
- int end;
-
- BUG_TRAP(start <= offset + len);
-
- end = start + list->len;
- if ((copy = end - offset) > 0) {
- if (copy > len)
- copy = len;
- elt += skb_to_sgvec(list, sg+elt, offset - start, copy);
- if ((len -= copy) == 0)
- return elt;
- offset += copy;
- }
- start = end;
- }
- }
- BUG_ON(len);
- return elt;
-}
-EXPORT_SYMBOL_GPL(skb_to_sgvec);
-
-/* Check that skb data bits are writable. If they are not, copy data
- * to newly created private area. If "tailbits" is given, make sure that
- * tailbits bytes beyond current end of skb are writable.
- *
- * Returns amount of elements of scatterlist to load for subsequent
- * transformations and pointer to writable trailer skb.
- */
-
-int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
-{
- int copyflag;
- int elt;
- struct sk_buff *skb1, **skb_p;
-
- /* If skb is cloned or its head is paged, reallocate
- * head pulling out all the pages (pages are considered not writable
- * at the moment even if they are anonymous).
- */
- if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) &&
- __pskb_pull_tail(skb, skb_pagelen(skb)-skb_headlen(skb)) == NULL)
- return -ENOMEM;
-
- /* Easy case. Most of packets will go this way. */
- if (!skb_shinfo(skb)->frag_list) {
- /* A little of trouble, not enough of space for trailer.
- * This should not happen, when stack is tuned to generate
- * good frames. OK, on miss we reallocate and reserve even more
- * space, 128 bytes is fair. */
-
- if (skb_tailroom(skb) < tailbits &&
- pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC))
- return -ENOMEM;
-
- /* Voila! */
- *trailer = skb;
- return 1;
- }
-
- /* Misery. We are in troubles, going to mincer fragments... */
-
- elt = 1;
- skb_p = &skb_shinfo(skb)->frag_list;
- copyflag = 0;
-
- while ((skb1 = *skb_p) != NULL) {
- int ntail = 0;
-
- /* The fragment is partially pulled by someone,
- * this can happen on input. Copy it and everything
- * after it. */
-
- if (skb_shared(skb1))
- copyflag = 1;
-
- /* If the skb is the last, worry about trailer. */
-
- if (skb1->next == NULL && tailbits) {
- if (skb_shinfo(skb1)->nr_frags ||
- skb_shinfo(skb1)->frag_list ||
- skb_tailroom(skb1) < tailbits)
- ntail = tailbits + 128;
- }
-
- if (copyflag ||
- skb_cloned(skb1) ||
- ntail ||
- skb_shinfo(skb1)->nr_frags ||
- skb_shinfo(skb1)->frag_list) {
- struct sk_buff *skb2;
-
- /* Fuck, we are miserable poor guys... */
- if (ntail == 0)
- skb2 = skb_copy(skb1, GFP_ATOMIC);
- else
- skb2 = skb_copy_expand(skb1,
- skb_headroom(skb1),
- ntail,
- GFP_ATOMIC);
- if (unlikely(skb2 == NULL))
- return -ENOMEM;
-
- if (skb1->sk)
- skb_set_owner_w(skb2, skb1->sk);
-
- /* Looking around. Are we still alive?
- * OK, link new skb, drop old one */
-
- skb2->next = skb1->next;
- *skb_p = skb2;
- kfree_skb(skb1);
- skb1 = skb2;
- }
- elt++;
- *trailer = skb1;
- skb_p = &skb1->next;
- }
-
- return elt;
-}
-EXPORT_SYMBOL_GPL(skb_cow_data);
-
void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len)
{
if (tail != skb) {
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH 7/9] AF_RXRPC: Add an interface to the AF_RXRPC module for the AFS filesystem to use
2007-04-02 22:44 [PATCH 0/9] AF_RXRPC socket family and AFS rewrite David Howells
` (3 preceding siblings ...)
2007-04-02 22:45 ` [PATCH 4/9] AF_RXRPC: Key facility changes for AF_RXRPC David Howells
@ 2007-04-02 22:45 ` David Howells
4 siblings, 0 replies; 7+ messages in thread
From: David Howells @ 2007-04-02 22:45 UTC (permalink / raw)
To: torvalds, akpm; +Cc: linux-kernel, linux-fsdevel, netdev, dhowells
Add an interface to the AF_RXRPC module so that the AFS filesystem module can
more easily make use of the services available. AFS still opens a socket but
then uses the action functions in lieu of sendmsg() and registers an intercept
functions to grab messages before they're queued on the socket Rx queue.
This permits AFS (or whatever) to:
(1) Avoid the overhead of using the recvmsg() call.
(2) Use different keys directly on individual client calls on one socket
rather than having to open a whole slew of sockets, one for each key it
might want to use.
(3) Avoid calling request_key() at the point of issue of a call or opening of
a socket. This is done instead by AFS at the point of open(), unlink() or
other VFS operation and the key handed through.
(4) Request the use of something other than GFP_KERNEL to allocate memory.
Furthermore:
(*) The socket buffer markings used by RxRPC are made available for AFS so
that it can interpret the cooked RxRPC messages itself.
(*) rxgen (un)marshalling abort codes are made available.
The following documentation for the kernel interface is added to
Documentation/networking/rxrpc.txt:
=========================
AF_RXRPC KERNEL INTERFACE
=========================
The AF_RXRPC module also provides an interface for use by in-kernel utilities
such as the AFS filesystem. This permits such a utility to:
(1) Use different keys directly on individual client calls on one socket
rather than having to open a whole slew of sockets, one for each key it
might want to use.
(2) Avoid having RxRPC call request_key() at the point of issue of a call or
opening of a socket. Instead the utility is responsible for requesting a
key at the appropriate point. AFS, for instance, would do this during VFS
operations such as open() or unlink(). The key is then handed through
when the call is initiated.
(3) Request the use of something other than GFP_KERNEL to allocate memory.
(4) Avoid the overhead of using the recvmsg() call. RxRPC messages can be
intercepted before they get put into the socket Rx queue and the socket
buffers manipulated directly.
To use the RxRPC facility, a kernel utility must still open an AF_RXRPC socket,
bind an addess as appropriate and listen if it's to be a server socket, but
then it passes this to the kernel interface functions.
The kernel interface functions are as follows:
(*) Begin a new client call.
struct rxrpc_call *
rxrpc_kernel_begin_call(struct socket *sock,
struct sockaddr_rxrpc *srx,
struct key *key,
unsigned long user_call_ID,
gfp_t gfp);
This allocates the infrastructure to make a new RxRPC call and assigns
call and connection numbers. The call will be made on the UDP port that
the socket is bound to. The call will go to the destination address of a
connected client socket unless an alternative is supplied (srx is
non-NULL).
If a key is supplied then this will be used to secure the call instead of
the key bound to the socket with the RXRPC_SECURITY_KEY sockopt. Calls
secured in this way will still share connections if at all possible.
The user_call_ID is equivalent to that supplied to sendmsg() in the
control data buffer. It is entirely feasible to use this to point to a
kernel data structure.
If this function is successful, an opaque reference to the RxRPC call is
returned. The caller now holds a reference on this and it must be
properly ended.
(*) End a client call.
void rxrpc_kernel_end_call(struct rxrpc_call *call);
This is used to end a previously begun call. The user_call_ID is expunged
from AF_RXRPC's knowledge and will not be seen again in association with
the specified call.
(*) Send data through a call.
int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg,
size_t len);
This is used to supply either the request part of a client call or the
reply part of a server call. msg.msg_iovlen and msg.msg_iov specify the
data buffers to be used. msg_iov may not be NULL and must point
exclusively to in-kernel virtual addresses. msg.msg_flags may be given
MSG_MORE if there will be subsequent data sends for this call.
The msg must not specify a destination address, control data or any flags
other than MSG_MORE. len is the total amount of data to transmit.
(*) Abort a call.
void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code);
This is used to abort a call if it's still in an abortable state. The
abort code specified will be placed in the ABORT message sent.
(*) Intercept received RxRPC messages.
typedef void (*rxrpc_interceptor_t)(struct sock *sk,
unsigned long user_call_ID,
struct sk_buff *skb);
void
rxrpc_kernel_intercept_rx_messages(struct socket *sock,
rxrpc_interceptor_t interceptor);
This installs an interceptor function on the specified AF_RXRPC socket.
All messages that would otherwise wind up in the socket's Rx queue are
then diverted to this function. Note that care must be taken to process
the messages in the right order to maintain DATA message sequentiality.
The interceptor function itself is provided with the address of the socket
and handling the incoming message, the ID assigned by the kernel utility
to the call and the socket buffer containing the message.
The skb->mark field indicates the type of message:
MARK MEANING
=============================== =======================================
RXRPC_SKB_MARK_DATA Data message
RXRPC_SKB_MARK_FINAL_ACK Final ACK received for an incoming call
RXRPC_SKB_MARK_BUSY Client call rejected as server busy
RXRPC_SKB_MARK_REMOTE_ABORT Call aborted by peer
RXRPC_SKB_MARK_NET_ERROR Network error detected
RXRPC_SKB_MARK_LOCAL_ERROR Local error encountered
RXRPC_SKB_MARK_NEW_CALL New incoming call awaiting acceptance
The remote abort message can be probed with rxrpc_kernel_get_abort_code().
The two error messages can be probed with rxrpc_kernel_get_error_number().
A new call can be accepted with rxrpc_kernel_accept_call().
Data messages can have their contents extracted with the usual bunch of
socket buffer manipulation functions. A data message can be determined to
be the last one in a sequence with rxrpc_kernel_is_data_last(). When a
data message has been used up, rxrpc_kernel_data_delivered() should be
called on it..
Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose
of. It is possible to get extra refs on all types of message for later
freeing, but this may pin the state of a call until the message is finally
freed.
(*) Accept an incoming call.
struct rxrpc_call *
rxrpc_kernel_accept_call(struct socket *sock,
unsigned long user_call_ID);
This is used to accept an incoming call and to assign it a call ID. This
function is similar to rxrpc_kernel_begin_call() and calls accepted must
be ended in the same way.
If this function is successful, an opaque reference to the RxRPC call is
returned. The caller now holds a reference on this and it must be
properly ended.
(*) Reject an incoming call.
int rxrpc_kernel_reject_call(struct socket *sock);
This is used to reject the first incoming call on the socket's queue with
a BUSY message. -ENODATA is returned if there were no incoming calls.
Other errors may be returned if the call had been aborted (-ECONNABORTED)
or had timed out (-ETIME).
(*) Record the delivery of a data message and free it.
void rxrpc_kernel_data_delivered(struct sk_buff *skb);
This is used to record a data message as having been delivered and to
update the ACK state for the call. The socket buffer will be freed.
(*) Free a message.
void rxrpc_kernel_free_skb(struct sk_buff *skb);
This is used to free a non-DATA socket buffer intercepted from an AF_RXRPC
socket.
(*) Determine if a data message is the last one on a call.
bool rxrpc_kernel_is_data_last(struct sk_buff *skb);
This is used to determine if a socket buffer holds the last data message
to be received for a call (true will be returned if it does, false
if not).
The data message will be part of the reply on a client call and the
request on an incoming call. In the latter case there will be more
messages, but in the former case there will not.
(*) Get the abort code from an abort message.
u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb);
This is used to extract the abort code from a remote abort message.
(*) Get the error number from a local or network error message.
int rxrpc_kernel_get_error_number(struct sk_buff *skb);
This is used to extract the error number from a message indicating either
a local error occurred or a network error occurred.
Signed-Off-By: David Howells <dhowells@redhat.com>
---
Documentation/networking/rxrpc.txt | 196 ++++++++++++++++++++++++++++++++++++
include/net/af_rxrpc.h | 44 ++++++++
include/rxrpc/packet.h | 12 ++
net/rxrpc/af_rxrpc.c | 122 +++++++++++++++++++++-
net/rxrpc/ar-accept.c | 111 ++++++++++++++++++++
net/rxrpc/ar-connection.c | 24 +++-
net/rxrpc/ar-input.c | 36 ++++---
net/rxrpc/ar-internal.h | 17 +--
net/rxrpc/ar-output.c | 83 +++++++++++++++
net/rxrpc/ar-recvmsg.c | 73 +++++++++++++
net/rxrpc/ar-skbuff.c | 14 +++
11 files changed, 682 insertions(+), 50 deletions(-)
diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt
index 146a73e..21ea5fa 100644
--- a/Documentation/networking/rxrpc.txt
+++ b/Documentation/networking/rxrpc.txt
@@ -25,6 +25,8 @@ Contents of this document:
(*) Example server usage.
+ (*) AF_RXRPC kernel interface.
+
========
OVERVIEW
@@ -661,3 +663,197 @@ A server would be set up to accept operations in the following manner:
Note that all the communications for a particular service take place through
the one server socket, using control messages on sendmsg() and recvmsg() to
determine the call affected.
+
+
+=========================
+AF_RXRPC KERNEL INTERFACE
+=========================
+
+The AF_RXRPC module also provides an interface for use by in-kernel utilities
+such as the AFS filesystem. This permits such a utility to:
+
+ (1) Use different keys directly on individual client calls on one socket
+ rather than having to open a whole slew of sockets, one for each key it
+ might want to use.
+
+ (2) Avoid having RxRPC call request_key() at the point of issue of a call or
+ opening of a socket. Instead the utility is responsible for requesting a
+ key at the appropriate point. AFS, for instance, would do this during VFS
+ operations such as open() or unlink(). The key is then handed through
+ when the call is initiated.
+
+ (3) Request the use of something other than GFP_KERNEL to allocate memory.
+
+ (4) Avoid the overhead of using the recvmsg() call. RxRPC messages can be
+ intercepted before they get put into the socket Rx queue and the socket
+ buffers manipulated directly.
+
+To use the RxRPC facility, a kernel utility must still open an AF_RXRPC socket,
+bind an addess as appropriate and listen if it's to be a server socket, but
+then it passes this to the kernel interface functions.
+
+The kernel interface functions are as follows:
+
+ (*) Begin a new client call.
+
+ struct rxrpc_call *
+ rxrpc_kernel_begin_call(struct socket *sock,
+ struct sockaddr_rxrpc *srx,
+ struct key *key,
+ unsigned long user_call_ID,
+ gfp_t gfp);
+
+ This allocates the infrastructure to make a new RxRPC call and assigns
+ call and connection numbers. The call will be made on the UDP port that
+ the socket is bound to. The call will go to the destination address of a
+ connected client socket unless an alternative is supplied (srx is
+ non-NULL).
+
+ If a key is supplied then this will be used to secure the call instead of
+ the key bound to the socket with the RXRPC_SECURITY_KEY sockopt. Calls
+ secured in this way will still share connections if at all possible.
+
+ The user_call_ID is equivalent to that supplied to sendmsg() in the
+ control data buffer. It is entirely feasible to use this to point to a
+ kernel data structure.
+
+ If this function is successful, an opaque reference to the RxRPC call is
+ returned. The caller now holds a reference on this and it must be
+ properly ended.
+
+ (*) End a client call.
+
+ void rxrpc_kernel_end_call(struct rxrpc_call *call);
+
+ This is used to end a previously begun call. The user_call_ID is expunged
+ from AF_RXRPC's knowledge and will not be seen again in association with
+ the specified call.
+
+ (*) Send data through a call.
+
+ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg,
+ size_t len);
+
+ This is used to supply either the request part of a client call or the
+ reply part of a server call. msg.msg_iovlen and msg.msg_iov specify the
+ data buffers to be used. msg_iov may not be NULL and must point
+ exclusively to in-kernel virtual addresses. msg.msg_flags may be given
+ MSG_MORE if there will be subsequent data sends for this call.
+
+ The msg must not specify a destination address, control data or any flags
+ other than MSG_MORE. len is the total amount of data to transmit.
+
+ (*) Abort a call.
+
+ void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code);
+
+ This is used to abort a call if it's still in an abortable state. The
+ abort code specified will be placed in the ABORT message sent.
+
+ (*) Intercept received RxRPC messages.
+
+ typedef void (*rxrpc_interceptor_t)(struct sock *sk,
+ unsigned long user_call_ID,
+ struct sk_buff *skb);
+
+ void
+ rxrpc_kernel_intercept_rx_messages(struct socket *sock,
+ rxrpc_interceptor_t interceptor);
+
+ This installs an interceptor function on the specified AF_RXRPC socket.
+ All messages that would otherwise wind up in the socket's Rx queue are
+ then diverted to this function. Note that care must be taken to process
+ the messages in the right order to maintain DATA message sequentiality.
+
+ The interceptor function itself is provided with the address of the socket
+ and handling the incoming message, the ID assigned by the kernel utility
+ to the call and the socket buffer containing the message.
+
+ The skb->mark field indicates the type of message:
+
+ MARK MEANING
+ =============================== =======================================
+ RXRPC_SKB_MARK_DATA Data message
+ RXRPC_SKB_MARK_FINAL_ACK Final ACK received for an incoming call
+ RXRPC_SKB_MARK_BUSY Client call rejected as server busy
+ RXRPC_SKB_MARK_REMOTE_ABORT Call aborted by peer
+ RXRPC_SKB_MARK_NET_ERROR Network error detected
+ RXRPC_SKB_MARK_LOCAL_ERROR Local error encountered
+ RXRPC_SKB_MARK_NEW_CALL New incoming call awaiting acceptance
+
+ The remote abort message can be probed with rxrpc_kernel_get_abort_code().
+ The two error messages can be probed with rxrpc_kernel_get_error_number().
+ A new call can be accepted with rxrpc_kernel_accept_call().
+
+ Data messages can have their contents extracted with the usual bunch of
+ socket buffer manipulation functions. A data message can be determined to
+ be the last one in a sequence with rxrpc_kernel_is_data_last(). When a
+ data message has been used up, rxrpc_kernel_data_delivered() should be
+ called on it..
+
+ Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose
+ of. It is possible to get extra refs on all types of message for later
+ freeing, but this may pin the state of a call until the message is finally
+ freed.
+
+ (*) Accept an incoming call.
+
+ struct rxrpc_call *
+ rxrpc_kernel_accept_call(struct socket *sock,
+ unsigned long user_call_ID);
+
+ This is used to accept an incoming call and to assign it a call ID. This
+ function is similar to rxrpc_kernel_begin_call() and calls accepted must
+ be ended in the same way.
+
+ If this function is successful, an opaque reference to the RxRPC call is
+ returned. The caller now holds a reference on this and it must be
+ properly ended.
+
+ (*) Reject an incoming call.
+
+ int rxrpc_kernel_reject_call(struct socket *sock);
+
+ This is used to reject the first incoming call on the socket's queue with
+ a BUSY message. -ENODATA is returned if there were no incoming calls.
+ Other errors may be returned if the call had been aborted (-ECONNABORTED)
+ or had timed out (-ETIME).
+
+ (*) Record the delivery of a data message and free it.
+
+ void rxrpc_kernel_data_delivered(struct sk_buff *skb);
+
+ This is used to record a data message as having been delivered and to
+ update the ACK state for the call. The socket buffer will be freed.
+
+ (*) Free a message.
+
+ void rxrpc_kernel_free_skb(struct sk_buff *skb);
+
+ This is used to free a non-DATA socket buffer intercepted from an AF_RXRPC
+ socket.
+
+ (*) Determine if a data message is the last one on a call.
+
+ bool rxrpc_kernel_is_data_last(struct sk_buff *skb);
+
+ This is used to determine if a socket buffer holds the last data message
+ to be received for a call (true will be returned if it does, false
+ if not).
+
+ The data message will be part of the reply on a client call and the
+ request on an incoming call. In the latter case there will be more
+ messages, but in the former case there will not.
+
+ (*) Get the abort code from an abort message.
+
+ u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb);
+
+ This is used to extract the abort code from a remote abort message.
+
+ (*) Get the error number from a local or network error message.
+
+ int rxrpc_kernel_get_error_number(struct sk_buff *skb);
+
+ This is used to extract the error number from a message indicating either
+ a local error occurred or a network error occurred.
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index b01ca25..00c2eaa 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -1,6 +1,6 @@
-/* RxRPC definitions
+/* RxRPC kernel service interface definitions
*
- * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
@@ -12,6 +12,46 @@
#ifndef _NET_RXRPC_H
#define _NET_RXRPC_H
+#ifdef __KERNEL__
+
#include <linux/rxrpc.h>
+struct rxrpc_call;
+
+/*
+ * the mark applied to socket buffers that may be intercepted
+ */
+enum {
+ RXRPC_SKB_MARK_DATA, /* data message */
+ RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */
+ RXRPC_SKB_MARK_BUSY, /* server busy message */
+ RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */
+ RXRPC_SKB_MARK_NET_ERROR, /* network error message */
+ RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */
+ RXRPC_SKB_MARK_NEW_CALL, /* local error message */
+};
+
+typedef void (*rxrpc_interceptor_t)(struct sock *, unsigned long,
+ struct sk_buff *);
+extern void rxrpc_kernel_intercept_rx_messages(struct socket *,
+ rxrpc_interceptor_t);
+extern struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *,
+ struct sockaddr_rxrpc *,
+ struct key *,
+ unsigned long,
+ gfp_t);
+extern int rxrpc_kernel_send_data(struct rxrpc_call *, struct msghdr *,
+ size_t);
+extern void rxrpc_kernel_abort_call(struct rxrpc_call *, u32);
+extern void rxrpc_kernel_end_call(struct rxrpc_call *);
+extern bool rxrpc_kernel_is_data_last(struct sk_buff *);
+extern u32 rxrpc_kernel_get_abort_code(struct sk_buff *);
+extern int rxrpc_kernel_get_error_number(struct sk_buff *);
+extern void rxrpc_kernel_data_delivered(struct sk_buff *);
+extern void rxrpc_kernel_free_skb(struct sk_buff *);
+extern struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *,
+ unsigned long);
+extern int rxrpc_kernel_reject_call(struct socket *);
+
+#endif /* __KERNEL__ */
#endif /* _NET_RXRPC_H */
diff --git a/include/rxrpc/packet.h b/include/rxrpc/packet.h
index 452a9bb..09b11a1 100644
--- a/include/rxrpc/packet.h
+++ b/include/rxrpc/packet.h
@@ -186,6 +186,18 @@ struct rxkad_response {
#define RX_DEBUGI_BADTYPE -8 /* bad debugging packet type */
/*
+ * (un)marshalling abort codes (rxgen)
+ */
+#define RXGEN_CC_MARSHAL -450
+#define RXGEN_CC_UNMARSHAL -451
+#define RXGEN_SS_MARSHAL -452
+#define RXGEN_SS_UNMARSHAL -453
+#define RXGEN_DECODE -454
+#define RXGEN_OPCODE -455
+#define RXGEN_SS_XDRFREE -456
+#define RXGEN_CC_XDRFREE -457
+
+/*
* Rx kerberos security abort codes
* - unfortunately we have no generalised security abort codes to say things
* like "unsupported security", so we have to use these instead and hope the
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 54b93d7..fb35998 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -214,7 +214,8 @@ static int rxrpc_listen(struct socket *sock, int backlog)
*/
static struct rxrpc_transport *rxrpc_name_to_transport(struct socket *sock,
struct sockaddr *addr,
- int addr_len, int flags)
+ int addr_len, int flags,
+ gfp_t gfp)
{
struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr;
struct rxrpc_transport *trans;
@@ -232,17 +233,127 @@ static struct rxrpc_transport *rxrpc_name_to_transport(struct socket *sock,
return ERR_PTR(-EAFNOSUPPORT);
/* find a remote transport endpoint from the local one */
- peer = rxrpc_get_peer(srx, GFP_KERNEL);
+ peer = rxrpc_get_peer(srx, gfp);
if (IS_ERR(peer))
return ERR_PTR(PTR_ERR(peer));
/* find a transport */
- trans = rxrpc_get_transport(rx->local, peer, GFP_KERNEL);
+ trans = rxrpc_get_transport(rx->local, peer, gfp);
rxrpc_put_peer(peer);
_leave(" = %p", trans);
return trans;
}
+/**
+ * rxrpc_kernel_begin_call - Allow a kernel service to begin a call
+ * @sock: The socket on which to make the call
+ * @srx: The address of the peer to contact (defaults to socket setting)
+ * @key: The security context to use (defaults to socket setting)
+ * @user_call_ID: The ID to use
+ *
+ * Allow a kernel service to begin a call on the nominated socket. This just
+ * sets up all the internal tracking structures and allocates connection and
+ * call IDs as appropriate. The call to be used is returned.
+ *
+ * The default socket destination address and security may be overridden by
+ * supplying @srx and @key.
+ */
+struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
+ struct sockaddr_rxrpc *srx,
+ struct key *key,
+ unsigned long user_call_ID,
+ gfp_t gfp)
+{
+ struct rxrpc_conn_bundle *bundle;
+ struct rxrpc_transport *trans;
+ struct rxrpc_call *call;
+ struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+ __be16 service_id;
+
+ _enter(",,%x,%lx", key_serial(key), user_call_ID);
+
+ lock_sock(&rx->sk);
+
+ if (srx) {
+ trans = rxrpc_name_to_transport(sock, (struct sockaddr *) srx,
+ sizeof(*srx), 0, gfp);
+ if (IS_ERR(trans)) {
+ call = ERR_PTR(PTR_ERR(trans));
+ trans = NULL;
+ goto out;
+ }
+ } else {
+ trans = rx->trans;
+ if (!trans) {
+ call = ERR_PTR(-ENOTCONN);
+ goto out;
+ }
+ atomic_inc(&trans->usage);
+ }
+
+ service_id = rx->service_id;
+ if (srx)
+ service_id = htons(srx->srx_service);
+
+ if (!key)
+ key = rx->key;
+
+ bundle = rxrpc_get_bundle(rx, trans, key, service_id, gfp);
+ if (IS_ERR(bundle)) {
+ call = ERR_PTR(PTR_ERR(bundle));
+ goto out;
+ }
+
+ call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID, true,
+ gfp);
+ rxrpc_put_bundle(trans, bundle);
+out:
+ rxrpc_put_transport(trans);
+ release_sock(&rx->sk);
+ _leave(" = %p", call);
+ return call;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_begin_call);
+
+/**
+ * rxrpc_kernel_end_call - Allow a kernel service to end a call it was using
+ * @call: The call to end
+ *
+ * Allow a kernel service to end a call it was using. The call must be
+ * complete before this is called (the call should be aborted if necessary).
+ */
+void rxrpc_kernel_end_call(struct rxrpc_call *call)
+{
+ _enter("%d{%d}", call->debug_id, atomic_read(&call->usage));
+ rxrpc_remove_user_ID(call->socket, call);
+ rxrpc_put_call(call);
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_end_call);
+
+/**
+ * rxrpc_kernel_intercept_rx_messages - Intercept received RxRPC messages
+ * @sock: The socket to intercept received messages on
+ * @interceptor: The function to pass the messages to
+ *
+ * Allow a kernel service to intercept messages heading for the Rx queue on an
+ * RxRPC socket. They get passed to the specified function instead.
+ * @interceptor should free the socket buffers it is given. @interceptor is
+ * called with the socket receive queue spinlock held and softirqs disabled -
+ * this ensures that the messages will be delivered in the right order.
+ */
+void rxrpc_kernel_intercept_rx_messages(struct socket *sock,
+ rxrpc_interceptor_t interceptor)
+{
+ struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+
+ _enter("");
+ rx->interceptor = interceptor;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_intercept_rx_messages);
+
/*
* connect an RxRPC socket
* - this just targets it at a specific destination; no actual connection
@@ -294,7 +405,8 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr,
return -EBUSY; /* server sockets can't connect as well */
}
- trans = rxrpc_name_to_transport(sock, addr, addr_len, flags);
+ trans = rxrpc_name_to_transport(sock, addr, addr_len, flags,
+ GFP_KERNEL);
if (IS_ERR(trans)) {
release_sock(&rx->sk);
_leave(" = %ld", PTR_ERR(trans));
@@ -344,7 +456,7 @@ static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock,
if (m->msg_name) {
ret = -EISCONN;
trans = rxrpc_name_to_transport(sock, m->msg_name,
- m->msg_namelen, 0);
+ m->msg_namelen, 0, GFP_KERNEL);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
diff --git a/net/rxrpc/ar-accept.c b/net/rxrpc/ar-accept.c
index b988e0f..405092d 100644
--- a/net/rxrpc/ar-accept.c
+++ b/net/rxrpc/ar-accept.c
@@ -310,7 +310,8 @@ security_mismatch:
* handle acceptance of a call by userspace
* - assign the user call ID to the call at the front of the queue
*/
-int rxrpc_accept_call(struct rxrpc_sock *rx, unsigned long user_call_ID)
+struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
+ unsigned long user_call_ID)
{
struct rxrpc_call *call;
struct rb_node *parent, **pp;
@@ -376,10 +377,11 @@ int rxrpc_accept_call(struct rxrpc_sock *rx, unsigned long user_call_ID)
BUG();
schedule_work(&call->processor);
+ rxrpc_get_call(call);
write_unlock_bh(&call->state_lock);
write_unlock(&rx->call_lock);
- _leave(" = 0");
- return 0;
+ _leave(" = %p{%d}", call, call->debug_id);
+ return call;
/* if the call is already dying or dead, then we leave the socket's ref
* on it to be released by rxrpc_dead_call_expired() as induced by
@@ -395,5 +397,108 @@ out_discard:
out:
write_unlock(&rx->call_lock);
_leave(" = %d", ret);
+ return ERR_PTR(ret);
+}
+
+/*
+ * handle rejectance of a call by userspace
+ * - reject the call at the front of the queue
+ */
+int rxrpc_reject_call(struct rxrpc_sock *rx)
+{
+ struct rxrpc_call *call;
+ int ret;
+
+ _enter("");
+
+ ASSERT(!irqs_disabled());
+
+ write_lock(&rx->call_lock);
+
+ ret = -ENODATA;
+ if (list_empty(&rx->acceptq))
+ goto out;
+
+ /* dequeue the first call and check it's still valid */
+ call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link);
+ list_del_init(&call->accept_link);
+ sk_acceptq_removed(&rx->sk);
+
+ write_lock_bh(&call->state_lock);
+ switch (call->state) {
+ case RXRPC_CALL_SERVER_ACCEPTING:
+ call->state = RXRPC_CALL_SERVER_BUSY;
+ if (test_and_set_bit(RXRPC_CALL_REJECT_BUSY, &call->events))
+ schedule_work(&call->processor);
+ ret = 0;
+ goto out_release;
+ case RXRPC_CALL_REMOTELY_ABORTED:
+ case RXRPC_CALL_LOCALLY_ABORTED:
+ ret = -ECONNABORTED;
+ goto out_release;
+ case RXRPC_CALL_NETWORK_ERROR:
+ ret = call->conn->error;
+ goto out_release;
+ case RXRPC_CALL_DEAD:
+ ret = -ETIME;
+ goto out_discard;
+ default:
+ BUG();
+ }
+
+ /* if the call is already dying or dead, then we leave the socket's ref
+ * on it to be released by rxrpc_dead_call_expired() as induced by
+ * rxrpc_release_call() */
+out_release:
+ _debug("release %p", call);
+ if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) &&
+ !test_and_set_bit(RXRPC_CALL_RELEASE, &call->events))
+ schedule_work(&call->processor);
+out_discard:
+ write_unlock_bh(&call->state_lock);
+ _debug("discard %p", call);
+out:
+ write_unlock(&rx->call_lock);
+ _leave(" = %d", ret);
+ return ret;
+}
+
+/**
+ * rxrpc_kernel_accept_call - Allow a kernel service to accept an incoming call
+ * @sock: The socket on which the impending call is waiting
+ * @user_call_ID: The tag to attach to the call
+ *
+ * Allow a kernel service to accept an incoming call, assuming the incoming
+ * call is still valid.
+ */
+struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *sock,
+ unsigned long user_call_ID)
+{
+ struct rxrpc_call *call;
+
+ _enter(",%lx", user_call_ID);
+ call = rxrpc_accept_call(rxrpc_sk(sock->sk), user_call_ID);
+ _leave(" = %p", call);
+ return call;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_accept_call);
+
+/**
+ * rxrpc_kernel_reject_call - Allow a kernel service to reject an incoming call
+ * @sock: The socket on which the impending call is waiting
+ *
+ * Allow a kernel service to reject an incoming call with a BUSY message,
+ * assuming the incoming call is still valid.
+ */
+int rxrpc_kernel_reject_call(struct socket *sock)
+{
+ int ret;
+
+ _enter("");
+ ret = rxrpc_reject_call(rxrpc_sk(sock->sk));
+ _leave(" = %d", ret);
return ret;
}
+
+EXPORT_SYMBOL(rxrpc_kernel_reject_call);
diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c
index a24d0fc..093af56 100644
--- a/net/rxrpc/ar-connection.c
+++ b/net/rxrpc/ar-connection.c
@@ -21,7 +21,7 @@ static void rxrpc_connection_reaper(struct work_struct *work);
LIST_HEAD(rxrpc_connections);
DEFINE_RWLOCK(rxrpc_connection_lock);
-static unsigned long rxrpc_connection_timeout = 5;
+static unsigned long rxrpc_connection_timeout = 10 * 60;
static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper);
/*
@@ -52,10 +52,10 @@ static struct rxrpc_conn_bundle *rxrpc_alloc_bundle(gfp_t gfp)
*/
static inline
int rxrpc_cmp_bundle(const struct rxrpc_conn_bundle *bundle,
- const struct rxrpc_sock *rx)
+ struct key *key, __be16 service_id)
{
- return (bundle->service_id - rx->service_id) ?:
- ((unsigned long) bundle->key - (unsigned long) rx->key);
+ return (bundle->service_id - service_id) ?:
+ ((unsigned long) bundle->key - (unsigned long) key);
}
/*
@@ -63,6 +63,7 @@ int rxrpc_cmp_bundle(const struct rxrpc_conn_bundle *bundle,
*/
struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
struct rxrpc_transport *trans,
+ struct key *key,
__be16 service_id,
gfp_t gfp)
{
@@ -70,7 +71,7 @@ struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
struct rb_node *p, *parent, **pp;
_enter("%p{%x},%x,%hx,",
- rx, key_serial(rx->key), trans->debug_id, ntohl(service_id));
+ rx, key_serial(key), trans->debug_id, ntohl(service_id));
if (rx->trans == trans && rx->bundle) {
atomic_inc(&rx->bundle->usage);
@@ -85,9 +86,9 @@ struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
while (p) {
bundle = rb_entry(p, struct rxrpc_conn_bundle, node);
- if (rxrpc_cmp_bundle(bundle, rx) < 0)
+ if (rxrpc_cmp_bundle(bundle, key, service_id) < 0)
p = p->rb_left;
- else if (rxrpc_cmp_bundle(bundle, rx) > 0)
+ else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0)
p = p->rb_right;
else
goto found_extant_bundle;
@@ -103,7 +104,7 @@ struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
return ERR_PTR(-ENOMEM);
}
- candidate->key = key_get(rx->key);
+ candidate->key = key_get(key);
candidate->service_id = service_id;
spin_lock(&trans->client_lock);
@@ -114,9 +115,9 @@ struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
parent = *pp;
bundle = rb_entry(parent, struct rxrpc_conn_bundle, node);
- if (rxrpc_cmp_bundle(bundle, rx) < 0)
+ if (rxrpc_cmp_bundle(bundle, key, service_id) < 0)
pp = &(*pp)->rb_left;
- else if (rxrpc_cmp_bundle(bundle, rx) > 0)
+ else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0)
pp = &(*pp)->rb_right;
else
goto found_extant_second;
@@ -129,6 +130,7 @@ struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
rb_link_node(&bundle->node, parent, pp);
rb_insert_color(&bundle->node, &trans->bundles);
spin_unlock(&trans->client_lock);
+ _net("BUNDLE new on trans %d", trans->debug_id);
if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
atomic_inc(&bundle->usage);
rx->bundle = bundle;
@@ -140,6 +142,7 @@ struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
found_extant_bundle:
atomic_inc(&bundle->usage);
spin_unlock(&trans->client_lock);
+ _net("BUNDLE old on trans %d", trans->debug_id);
if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
atomic_inc(&bundle->usage);
rx->bundle = bundle;
@@ -152,6 +155,7 @@ found_extant_second:
atomic_inc(&bundle->usage);
spin_unlock(&trans->client_lock);
kfree(candidate);
+ _net("BUNDLE old2 on trans %d", trans->debug_id);
if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
atomic_inc(&bundle->usage);
rx->bundle = bundle;
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c
index 64ae9fa..9269786 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/ar-input.c
@@ -42,6 +42,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
bool force, bool terminal)
{
struct rxrpc_skb_priv *sp;
+ struct rxrpc_sock *rx = call->socket;
struct sock *sk;
int skb_len, ret;
@@ -64,7 +65,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
return 0;
}
- sk = &call->socket->sk;
+ sk = &rx->sk;
if (!force) {
/* cast skb->rcvbuf to unsigned... It's pointless, but
@@ -89,25 +90,30 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
skb->sk = sk;
atomic_add(skb->truesize, &sk->sk_rmem_alloc);
- /* Cache the SKB length before we tack it onto the receive
- * queue. Once it is added it no longer belongs to us and
- * may be freed by other threads of control pulling packets
- * from the queue.
- */
- skb_len = skb->len;
-
- _net("post skb %p", skb);
- __skb_queue_tail(&sk->sk_receive_queue, skb);
- spin_unlock_bh(&sk->sk_receive_queue.lock);
-
- if (!sock_flag(sk, SOCK_DEAD))
- sk->sk_data_ready(sk, skb_len);
-
if (terminal) {
_debug("<<<< TERMINAL MESSAGE >>>>");
set_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags);
}
+ /* allow interception by a kernel service */
+ if (rx->interceptor) {
+ rx->interceptor(sk, call->user_call_ID, skb);
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
+ } else {
+
+ /* Cache the SKB length before we tack it onto the
+ * receive queue. Once it is added it no longer
+ * belongs to us and may be freed by other threads of
+ * control pulling packets from the queue */
+ skb_len = skb->len;
+
+ _net("post skb %p", skb);
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk->sk_data_ready(sk, skb_len);
+ }
skb = NULL;
} else {
spin_unlock_bh(&sk->sk_receive_queue.lock);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index d6a667e..7c1887a 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -50,6 +50,7 @@ enum {
struct rxrpc_sock {
/* WARNING: sk has to be the first member */
struct sock sk;
+ rxrpc_interceptor_t interceptor; /* kernel service Rx interceptor function */
struct rxrpc_local *local; /* local endpoint */
struct rxrpc_transport *trans; /* transport handler */
struct rxrpc_conn_bundle *bundle; /* virtual connection bundle */
@@ -91,16 +92,6 @@ struct rxrpc_skb_priv {
#define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb)
-enum {
- RXRPC_SKB_MARK_DATA, /* data message */
- RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */
- RXRPC_SKB_MARK_BUSY, /* server busy message */
- RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */
- RXRPC_SKB_MARK_NET_ERROR, /* network error message */
- RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */
- RXRPC_SKB_MARK_NEW_CALL, /* local error message */
-};
-
enum rxrpc_command {
RXRPC_CMD_SEND_DATA, /* send data message */
RXRPC_CMD_SEND_ABORT, /* request abort generation */
@@ -457,7 +448,9 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb)
* ar-accept.c
*/
extern void rxrpc_accept_incoming_calls(struct work_struct *);
-extern int rxrpc_accept_call(struct rxrpc_sock *, unsigned long);
+extern struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *,
+ unsigned long);
+extern int rxrpc_reject_call(struct rxrpc_sock *);
/*
* ar-ack.c
@@ -495,6 +488,7 @@ extern rwlock_t rxrpc_connection_lock;
extern struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *,
struct rxrpc_transport *,
+ struct key *,
__be16, gfp_t);
extern void rxrpc_put_bundle(struct rxrpc_transport *,
struct rxrpc_conn_bundle *);
@@ -582,6 +576,7 @@ extern struct file_operations rxrpc_connection_seq_fops;
/*
* ar-recvmsg.c
*/
+extern void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *);
extern int rxrpc_recvmsg(struct kiocb *, struct socket *, struct msghdr *,
size_t, int);
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index c5ee56e..a79576f 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -153,7 +153,8 @@ int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
(struct sockaddr_rxrpc *) msg->msg_name;
service_id = htons(srx->srx_service);
}
- bundle = rxrpc_get_bundle(rx, trans, service_id, GFP_KERNEL);
+ bundle = rxrpc_get_bundle(rx, trans, rx->key, service_id,
+ GFP_KERNEL);
if (IS_ERR(bundle))
return PTR_ERR(bundle);
}
@@ -189,6 +190,77 @@ int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
return ret;
}
+/**
+ * rxrpc_kernel_send_data - Allow a kernel service to send data on a call
+ * @call: The call to send data through
+ * @msg: The data to send
+ * @len: The amount of data to send
+ *
+ * Allow a kernel service to send data on a call. The call must be in an state
+ * appropriate to sending data. No control data should be supplied in @msg,
+ * nor should an address be supplied. MSG_MORE should be flagged if there's
+ * more data to come, otherwise this data will end the transmission phase.
+ */
+int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg,
+ size_t len)
+{
+ int ret;
+
+ _enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
+
+ ASSERTCMP(msg->msg_name, ==, NULL);
+ ASSERTCMP(msg->msg_control, ==, NULL);
+
+ lock_sock(&call->socket->sk);
+
+ _debug("CALL %d USR %lx ST %d on CONN %p",
+ call->debug_id, call->user_call_ID, call->state, call->conn);
+
+ if (call->state >= RXRPC_CALL_COMPLETE) {
+ ret = -ESHUTDOWN; /* it's too late for this call */
+ } else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
+ call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+ call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
+ ret = -EPROTO; /* request phase complete for this client call */
+ } else {
+ mm_segment_t oldfs = get_fs();
+ set_fs(KERNEL_DS);
+ ret = rxrpc_send_data(NULL, call->socket, call, msg, len);
+ set_fs(oldfs);
+ }
+
+ release_sock(&call->socket->sk);
+ _leave(" = %d", ret);
+ return ret;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_send_data);
+
+/*
+ * rxrpc_kernel_abort_call - Allow a kernel service to abort a call
+ * @call: The call to be aborted
+ * @abort_code: The abort code to stick into the ABORT packet
+ *
+ * Allow a kernel service to abort a call, if it's still in an abortable state.
+ */
+void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code)
+{
+ _enter("{%d},%d", call->debug_id, abort_code);
+
+ lock_sock(&call->socket->sk);
+
+ _debug("CALL %d USR %lx ST %d on CONN %p",
+ call->debug_id, call->user_call_ID, call->state, call->conn);
+
+ if (call->state < RXRPC_CALL_COMPLETE)
+ rxrpc_send_abort(call, abort_code);
+
+ release_sock(&call->socket->sk);
+ _leave("");
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_abort_call);
+
/*
* send a message through a server socket
* - caller holds the socket locked
@@ -209,8 +281,13 @@ int rxrpc_server_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
if (ret < 0)
return ret;
- if (cmd == RXRPC_CMD_ACCEPT)
- return rxrpc_accept_call(rx, user_call_ID);
+ if (cmd == RXRPC_CMD_ACCEPT) {
+ call = rxrpc_accept_call(rx, user_call_ID);
+ if (IS_ERR(call))
+ return PTR_ERR(call);
+ rxrpc_put_call(call);
+ return 0;
+ }
call = rxrpc_find_server_call(rx, user_call_ID);
if (!call)
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index e947d5c..6fab099 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -19,7 +19,7 @@
* removal a call's user ID from the socket tree to make the user ID available
* again and so that it won't be seen again in association with that call
*/
-static void rxrpc_remove_user_ID(struct rxrpc_sock *rx, struct rxrpc_call *call)
+void rxrpc_remove_user_ID(struct rxrpc_sock *rx, struct rxrpc_call *call)
{
_debug("RELEASE CALL %d", call->debug_id);
@@ -364,3 +364,74 @@ wait_error:
return copied;
}
+
+/**
+ * rxrpc_kernel_data_delivered - Record delivery of data message
+ * @skb: Message holding data
+ *
+ * Record the delivery of a data message. This permits RxRPC to keep its
+ * tracking correct. The socket buffer will be deleted.
+ */
+void rxrpc_kernel_data_delivered(struct sk_buff *skb)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ struct rxrpc_call *call = sp->call;
+
+ ASSERTCMP(ntohl(sp->hdr.seq), >=, call->rx_data_recv);
+ ASSERTCMP(ntohl(sp->hdr.seq), <=, call->rx_data_recv + 1);
+ call->rx_data_recv = ntohl(sp->hdr.seq);
+
+ ASSERTCMP(ntohl(sp->hdr.seq), >, call->rx_data_eaten);
+ rxrpc_free_skb(skb);
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_data_delivered);
+
+/**
+ * rxrpc_kernel_is_data_last - Determine if data message is last one
+ * @skb: Message holding data
+ *
+ * Determine if data message is last one for the parent call.
+ */
+bool rxrpc_kernel_is_data_last(struct sk_buff *skb)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ ASSERTCMP(skb->mark, ==, RXRPC_SKB_MARK_DATA);
+
+ return sp->hdr.flags & RXRPC_LAST_PACKET;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_is_data_last);
+
+/**
+ * rxrpc_kernel_get_abort_code - Get the abort code from an RxRPC abort message
+ * @skb: Message indicating an abort
+ *
+ * Get the abort code from an RxRPC abort message.
+ */
+u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ ASSERTCMP(skb->mark, ==, RXRPC_SKB_MARK_REMOTE_ABORT);
+
+ return sp->call->abort_code;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_get_abort_code);
+
+/**
+ * rxrpc_kernel_get_error - Get the error number from an RxRPC error message
+ * @skb: Message indicating an error
+ *
+ * Get the error number from an RxRPC error message.
+ */
+int rxrpc_kernel_get_error_number(struct sk_buff *skb)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ return sp->error;
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_get_error_number);
diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/ar-skbuff.c
index d73f6fc..487e689 100644
--- a/net/rxrpc/ar-skbuff.c
+++ b/net/rxrpc/ar-skbuff.c
@@ -116,3 +116,17 @@ void rxrpc_packet_destructor(struct sk_buff *skb)
sock_rfree(skb);
_leave("");
}
+
+/**
+ * rxrpc_kernel_free_skb - Free an RxRPC socket buffer
+ * @skb: The socket buffer to be freed
+ *
+ * Let RxRPC free its own socket buffer, permitting it to maintain debug
+ * accounting.
+ */
+void rxrpc_kernel_free_skb(struct sk_buff *skb)
+{
+ rxrpc_free_skb(skb);
+}
+
+EXPORT_SYMBOL(rxrpc_kernel_free_skb);
^ permalink raw reply related [flat|nested] 7+ messages in thread