* [PATCH 4/8] crypto: AF_ALG: crypto API calls to inline functions
From: Stephan Mueller @ 2014-11-12 7:03 UTC (permalink / raw)
To: Herbert Xu; +Cc: ABI/API, linux-crypto, LKML
In-Reply-To: <4738444.A2vZX1nNCo@tachyon.chronox.de>
To avoid excessive branches and cluttering the code, all kernel crypto
API calls are extracted into separate inline functions. These functions
invoke either the ablkcipher or the aead crypto API function calls, as
necessary.
Signed-off-by: Stephan Mueller <smueller@chronox.de>
---
crypto/algif_skcipher.c | 141 ++++++++++++++++++++++++++++++++++++++++++------
1 file changed, 124 insertions(+), 17 deletions(-)
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 9286cfc..fb8efc8 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -247,14 +247,121 @@ static void skcipher_data_wakeup(struct sock *sk)
rcu_read_unlock();
}
+static inline bool skcipher_is_aead(struct crypto_tfm *tfm)
+{
+ return ((crypto_tfm_alg_type(tfm) & CRYPTO_ALG_TYPE_MASK) ==
+ CRYPTO_ALG_TYPE_AEAD);
+}
+
+static inline unsigned int skcipher_crypto_ivsize(void *private)
+{
+ if (skcipher_is_aead(private))
+ return crypto_aead_ivsize(private);
+ else
+ return crypto_ablkcipher_ivsize(private);
+}
+
+static inline unsigned int skcipher_crypto_ivsize_ctx(struct skcipher_ctx *ctx)
+{
+ if (ctx->aead)
+ return crypto_aead_ivsize(crypto_aead_reqtfm(&ctx->u.aead_req));
+ else
+ return crypto_ablkcipher_ivsize(
+ crypto_ablkcipher_reqtfm(&ctx->u.ablkcipher_req));
+}
+
+static inline unsigned int skcipher_crypto_blocksize(struct skcipher_ctx *ctx)
+{
+ if (ctx->aead)
+ return crypto_aead_blocksize(
+ crypto_aead_reqtfm(&ctx->u.aead_req));
+ else
+ return crypto_ablkcipher_blocksize(
+ crypto_ablkcipher_reqtfm(&ctx->u.ablkcipher_req));
+}
+
+static inline unsigned int skcipher_crypto_reqsize(void *private)
+{
+ if (skcipher_is_aead(private))
+ return crypto_aead_reqsize(private);
+ else
+ return crypto_ablkcipher_reqsize(private);
+}
+
+static inline unsigned int skcipher_crypto_setkey(void *private, const u8 *key,
+ unsigned int keylen)
+{
+ if (skcipher_is_aead(private))
+ return crypto_aead_setkey(private, key, keylen);
+ else
+ return crypto_ablkcipher_setkey(private, key, keylen);
+}
+
+static inline void skcipher_crypto_free(void *private)
+{
+ if (skcipher_is_aead(private))
+ crypto_free_aead(private);
+ else
+ crypto_free_ablkcipher(private);
+}
+
+static inline void skcipher_request_set_tfm(struct skcipher_ctx *ctx, void *tfm)
+{
+ if (ctx->aead)
+ aead_request_set_tfm(&ctx->u.aead_req, tfm);
+ else
+ ablkcipher_request_set_tfm(&ctx->u.ablkcipher_req, tfm);
+}
+
+static inline int skcipher_crypto_encrypt(struct skcipher_ctx *ctx)
+{
+ if (ctx->aead)
+ return crypto_aead_encrypt(&ctx->u.aead_req);
+ else
+ return crypto_ablkcipher_encrypt(&ctx->u.ablkcipher_req);
+}
+
+static inline int skcipher_crypto_decrypt(struct skcipher_ctx *ctx)
+{
+ if (ctx->aead)
+ return crypto_aead_decrypt(&ctx->u.aead_req);
+ else
+ return crypto_ablkcipher_decrypt(&ctx->u.ablkcipher_req);
+}
+
+static inline void skcipher_crypto_set_crypt(struct skcipher_ctx *ctx,
+ struct scatterlist *src,
+ struct scatterlist *dst,
+ unsigned int cryptlen, u8 *iv)
+{
+ if (ctx->aead)
+ return aead_request_set_crypt(&ctx->u.aead_req, src, dst,
+ cryptlen, iv);
+ else
+ return ablkcipher_request_set_crypt(&ctx->u.ablkcipher_req, src,
+ dst, cryptlen, iv);
+}
+
+static inline void skcipher_request_set_callback(struct skcipher_ctx *ctx,
+ u32 flags,
+ crypto_completion_t complete,
+ void *data)
+{
+ if (ctx->aead)
+ aead_request_set_callback(&ctx->u.aead_req, flags, complete,
+ data);
+ else
+ ablkcipher_request_set_callback(&ctx->u.ablkcipher_req, flags,
+ complete, data);
+}
+
static int skcipher_sendmsg(struct kiocb *unused, struct socket *sock,
struct msghdr *msg, size_t size)
{
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
struct skcipher_ctx *ctx = ask->private;
- struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req);
- unsigned ivsize = crypto_ablkcipher_ivsize(tfm);
+ unsigned ivsize = skcipher_crypto_ivsize_ctx(ctx);
struct skcipher_sg_list *sgl;
struct af_alg_control con = {};
long copied = 0;
@@ -432,8 +539,7 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
struct skcipher_ctx *ctx = ask->private;
- unsigned bs = crypto_ablkcipher_blocksize(crypto_ablkcipher_reqtfm(
- &ctx->req));
+ unsigned bs = skcipher_crypto_blocksize(ctx);
struct skcipher_sg_list *sgl;
struct scatterlist *sg;
unsigned long iovlen;
@@ -483,8 +589,8 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
err = af_alg_wait_for_completion(
ctx->enc ?
- crypto_ablkcipher_encrypt(&ctx->req) :
- crypto_ablkcipher_decrypt(&ctx->req),
+ skcipher_crypto_encrypt(ctx) :
+ skcipher_crypto_decrypt(ctx),
&ctx->completion);
free:
@@ -603,22 +709,22 @@ static void *skcipher_bind(const char *name, u32 type, u32 mask)
static void skcipher_release(void *private)
{
- crypto_free_ablkcipher(private);
+ skcipher_crypto_free(private);
}
static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen)
{
- return crypto_ablkcipher_setkey(private, key, keylen);
+ return skcipher_crypto_setkey(private, key, keylen);
}
static void skcipher_sock_destruct(struct sock *sk)
{
struct alg_sock *ask = alg_sk(sk);
struct skcipher_ctx *ctx = ask->private;
- struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req);
+ unsigned int ivlen = skcipher_crypto_ivsize_ctx(ctx);
skcipher_free_sgl(sk);
- sock_kfree_s(sk, ctx->iv, crypto_ablkcipher_ivsize(tfm));
+ sock_kfree_s(sk, ctx->iv, ivlen);
sock_kfree_s(sk, ctx, ctx->len);
af_alg_release_parent(sk);
}
@@ -627,20 +733,20 @@ static int skcipher_accept_parent(void *private, struct sock *sk)
{
struct skcipher_ctx *ctx;
struct alg_sock *ask = alg_sk(sk);
- unsigned int len = sizeof(*ctx) + crypto_ablkcipher_reqsize(private);
+ unsigned int len = sizeof(*ctx) + skcipher_crypto_reqsize(private);
+ unsigned int ivlen = skcipher_crypto_ivsize(private);
ctx = sock_kmalloc(sk, len, GFP_KERNEL);
if (!ctx)
return -ENOMEM;
- ctx->iv = sock_kmalloc(sk, crypto_ablkcipher_ivsize(private),
- GFP_KERNEL);
+ ctx->iv = sock_kmalloc(sk, ivlen, GFP_KERNEL);
if (!ctx->iv) {
sock_kfree_s(sk, ctx, len);
return -ENOMEM;
}
- memset(ctx->iv, 0, crypto_ablkcipher_ivsize(private));
+ memset(ctx->iv, 0, ivlen);
INIT_LIST_HEAD(&ctx->tsgl);
ctx->len = len;
@@ -648,13 +754,14 @@ static int skcipher_accept_parent(void *private, struct sock *sk)
ctx->more = 0;
ctx->merge = 0;
ctx->enc = 0;
+ ctx->aead = skcipher_is_aead(private);
af_alg_init_completion(&ctx->completion);
ask->private = ctx;
- ablkcipher_request_set_tfm(&ctx->req, private);
- ablkcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
- af_alg_complete, &ctx->completion);
+ skcipher_request_set_tfm(ctx, private);
+ skcipher_request_set_callback(ctx, CRYPTO_TFM_REQ_MAY_BACKLOG,
+ af_alg_complete, &ctx->completion);
sk->sk_destruct = skcipher_sock_destruct;
--
2.1.0
^ permalink raw reply related
* [PATCH 3/8] crypto: AF_ALG: extend data structuers for AEAD
From: Stephan Mueller @ 2014-11-12 7:01 UTC (permalink / raw)
To: Herbert Xu; +Cc: ABI/API, linux-crypto, LKML
In-Reply-To: <4738444.A2vZX1nNCo@tachyon.chronox.de>
The data structure holding the state of an ongoing symmetric cipher
operation is extended by the data variables needed for AEAD.
The request data structures are encapsulated by a union as the symmetric
cipher implementation is either exclusively used for "normal" symmetric
ciphers or for AEAD ciphers.
The define MAX_AEAD_ASSOCLEN restricts the size of the associated
authentication data. The kernel must allocate memory for this data to be
stored for the cipher operation. To prevent an excessive use of memory,
it is limited to 128 bytes, which is considered to be a sensible size.
Signed-off-by: Stephan Mueller <smueller@chronox.de>
---
crypto/algif_skcipher.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 7a1656b..9286cfc 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -46,7 +46,15 @@ struct skcipher_ctx {
bool merge;
bool enc;
- struct ablkcipher_request req;
+ bool aead;
+ void *aead_assoc;
+ /* define arbitrary maximum length of associated data */
+ #define MAX_AEAD_ASSOCLEN 128
+ struct scatterlist sg_aead_assoc;
+ union {
+ struct ablkcipher_request ablkcipher_req;
+ struct aead_request aead_req;
+ } u;
};
#define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \
--
2.1.0
^ permalink raw reply related
* [PATCH 2/8] crypto: AF_ALG: user space interface for cipher info
From: Stephan Mueller @ 2014-11-12 7:01 UTC (permalink / raw)
To: Herbert Xu; +Cc: ABI/API, linux-crypto, LKML
In-Reply-To: <4738444.A2vZX1nNCo@tachyon.chronox.de>
The AF_ALG interface allows normal cipher (hash, encrypt, decrypt).
However, it does not allow user space to obtain the following generic
information about the currently active cipher:
* block size of the cipher
* IV size of the cipher
* for AEAD, the maximum authentication tag size
The patch adds a getsockopt interface for the symmetric ciphers to
answer such information requests from user space.
The kernel crypto API function calls are used to obtain the real data.
As all data are simple integer values, the getsockopt handler function
uses put_user() to return the integer value to user space in the
*optval parameter of getsockopt.
Signed-off-by: Stephan Mueller <smueller@chronox.de>
---
crypto/algif_skcipher.c | 46 ++++++++++++++++++++++++++++++++++++++++++++-
include/uapi/linux/if_alg.h | 3 +++
2 files changed, 48 insertions(+), 1 deletion(-)
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 83187f4..7a1656b 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -522,6 +522,50 @@ static unsigned int skcipher_poll(struct file *file, struct socket *sock,
return mask;
}
+static int skcipher_getsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ struct sock *sk = sock->sk;
+ struct alg_sock *ask = alg_sk(sk);
+ struct skcipher_ctx *ctx = ask->private;
+ const struct af_alg_type *type;
+ int len = 0;
+ int err = -EOPNOTSUPP;
+
+ lock_sock(sk);
+ type = ask->type;
+
+ if (level != SOL_ALG || !type)
+ goto unlock;
+
+ switch (optname) {
+ case ALG_GET_BLOCKSIZE:
+ len = skcipher_crypto_blocksize(ctx);
+ err = 0;
+ break;
+ case ALG_GET_IVSIZE:
+ len = skcipher_crypto_ivsize_ctx(ctx);
+ err = 0;
+ break;
+ case ALG_GET_AEAD_AUTHSIZE:
+ if (ctx->aead) {
+ len = crypto_aead_authsize(crypto_aead_reqtfm(
+ &ctx->u.aead_req));
+ err = 0;
+ }
+ break;
+ default:
+ break;
+ }
+
+unlock:
+ release_sock(sk);
+ if (err >= 0)
+ err = put_user(len, optlen);
+
+ return err;
+}
+
static struct proto_ops algif_skcipher_ops = {
.family = PF_ALG,
@@ -531,7 +575,6 @@ static struct proto_ops algif_skcipher_ops = {
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
- .getsockopt = sock_no_getsockopt,
.mmap = sock_no_mmap,
.bind = sock_no_bind,
.accept = sock_no_accept,
@@ -542,6 +585,7 @@ static struct proto_ops algif_skcipher_ops = {
.sendpage = skcipher_sendpage,
.recvmsg = skcipher_recvmsg,
.poll = skcipher_poll,
+ .getsockopt = skcipher_getsockopt,
};
static void *skcipher_bind(const char *name, u32 type, u32 mask)
diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h
index 64e7008..267fd73 100644
--- a/include/uapi/linux/if_alg.h
+++ b/include/uapi/linux/if_alg.h
@@ -39,6 +39,9 @@ struct af_alg_aead_assoc {
#define ALG_SET_OP 3
#define ALG_SET_AEAD_ASSOC 4
#define ALG_SET_AEAD_AUTHSIZE 5
+#define ALG_GET_BLOCKSIZE 6
+#define ALG_GET_IVSIZE 7
+#define ALG_GET_AEAD_AUTHSIZE 8
/* Operations */
#define ALG_OP_DECRYPT 0
--
2.1.0
^ permalink raw reply related
* [PATCH 1/8] crypto: AF_ALG: add user space interface for AEAD
From: Stephan Mueller @ 2014-11-12 7:00 UTC (permalink / raw)
To: Herbert Xu; +Cc: ABI/API, linux-crypto, LKML
In-Reply-To: <4738444.A2vZX1nNCo@tachyon.chronox.de>
AEAD requires the following data in addition to normal symmetric
ciphers:
* Associated authentication data of arbitrary length
* Authentication tag for decryption
* Length of authentication tag for encryption
The authentication tag data is communicated as part of the actual
ciphertext as mandated by the kernel crypto API. Therefore we only need
to provide a user space interface for the associated authentication data
as well as for the authentication tag length.
This patch adds both as a setsockopt interface that is identical to the
AF_ALG interface for setting an IV and for selecting the cipher
operation type (encrypt or decrypt).
Signed-off-by: Stephan Mueller <smueller@chronox.de>
---
crypto/af_alg.c | 17 +++++++++++++++++
include/crypto/if_alg.h | 2 ++
include/uapi/linux/if_alg.h | 7 +++++++
3 files changed, 26 insertions(+)
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 6a3ad80..635140b 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -421,6 +421,23 @@ int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con)
con->op = *(u32 *)CMSG_DATA(cmsg);
break;
+
+ case ALG_SET_AEAD_AUTHSIZE:
+ if (cmsg->cmsg_len < CMSG_LEN(sizeof(u32)))
+ return -EINVAL;
+ con->aead_authsize = *(u32 *)CMSG_DATA(cmsg);
+ break;
+
+ case ALG_SET_AEAD_ASSOC:
+ if (cmsg->cmsg_len < CMSG_LEN(sizeof(*con->aead_assoc)))
+ return -EINVAL;
+ con->aead_assoc = (void *)CMSG_DATA(cmsg);
+ if (cmsg->cmsg_len <
+ CMSG_LEN(con->aead_assoc->aead_assoclen +
+ sizeof(*con->aead_assoc)))
+ return -EINVAL;
+ break;
+
default:
return -EINVAL;
}
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index d61c111..c741483 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -41,7 +41,9 @@ struct af_alg_completion {
struct af_alg_control {
struct af_alg_iv *iv;
+ struct af_alg_aead_assoc *aead_assoc;
int op;
+ unsigned int aead_authsize;
};
struct af_alg_type {
diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h
index 0f9acce..64e7008 100644
--- a/include/uapi/linux/if_alg.h
+++ b/include/uapi/linux/if_alg.h
@@ -28,10 +28,17 @@ struct af_alg_iv {
__u8 iv[0];
};
+struct af_alg_aead_assoc {
+ __u32 aead_assoclen;
+ __u8 aead_assoc[0];
+};
+
/* Socket options */
#define ALG_SET_KEY 1
#define ALG_SET_IV 2
#define ALG_SET_OP 3
+#define ALG_SET_AEAD_ASSOC 4
+#define ALG_SET_AEAD_AUTHSIZE 5
/* Operations */
#define ALG_OP_DECRYPT 0
--
2.1.0
^ permalink raw reply related
* [PATCH 0/8] crypto: AF_ALG: add AEAD and RNG support
From: Stephan Mueller @ 2014-11-12 6:59 UTC (permalink / raw)
To: Herbert Xu; +Cc: ABI/API, linux-crypto, LKML
Hi,
This patch set adds AEAD and RNG support to the AF_ALG interface
exported by the kernel crypto API. By extending AF_ALG with AEAD and RNG
support, all cipher types the kernel crypto API allows access to are
now accessible from userspace.
The RNG support is stand-alone.
The AEAD implementation is added to algif_skcipher.c to prevent
re-implementation of the memory moving logic.
The extension for the AEAD support can be summarized with the following
types of changes:
* select the correct crypto API functions (either the ablkcipher
or the aead functions)
* apply the additional data needed for AEAD at the right time
(associated data, authentication tag) -- this includes the addition
of user space interfaces to allow setting this data.
* add the calculation for the memory size needed for encryption and
decryption.
In addition, the patch set adds a getsockopt implementation to skcipher to
allow user space to inquire about properties of the ciphers (IV size,
block size, authentication data size). This extension would be needed for a
generic user space usage of these ciphers.
The new AEAD and RNG interfaces are fully tested with the test application
provided at [1]. That test application exercises all newly added user space
interfaces.
The patch set was tested on x86_64 and i386.
[1] http://www.chronox.de/libkcapi.html
Stephan Mueller (8):
crypto: AF_ALG: add user space interface for AEAD
crypto: AF_ALG: user space interface for cipher info
crypto: AF_ALG: extend data structuers for AEAD
crypto: AF_ALG: crypto API calls to inline functions
crypto: AF_ALG: add AEAD support
crypto: AF_ALG: make setkey optional
crypto: AF_ALG: add random number generator support
crypto: AF_ALG: enable RNG interface compilation
crypto/Kconfig | 9 ++
crypto/Makefile | 1 +
crypto/af_alg.c | 20 +++
crypto/algif_rng.c | 186 +++++++++++++++++++++++
crypto/algif_skcipher.c | 350 ++++++++++++++++++++++++++++++++++++++++----
include/crypto/if_alg.h | 2 +
include/uapi/linux/if_alg.h | 10 ++
7 files changed, 550 insertions(+), 28 deletions(-)
create mode 100644 crypto/algif_rng.c
--
2.1.0
^ permalink raw reply
* Re: [PATCH] selftests/net: psock_fanout seg faults in sock_fanout_read_ring()
From: David Miller @ 2014-11-12 2:44 UTC (permalink / raw)
To: shuahkh; +Cc: netdev, linux-api, linux-kernel
In-Reply-To: <1415725453-6549-1-git-send-email-shuahkh@osg.samsung.com>
From: Shuah Khan <shuahkh@osg.samsung.com>
Date: Tue, 11 Nov 2014 10:04:13 -0700
> The while loop in sock_fanout_read_ring() checks mmap region
> bounds after access, causing it to segfault. Fix it to check
> count before accessing header->tp_status. This problem can be
> reproduced consistently when the test in run as follows:
>
> make -C tools/testing/selftests TARGETS=net run_tests
> or
> make run_tests from tools/testing/selftests
> or
> make run_test from tools/testing/selftests/net
>
> Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
Definitely looks correct to me, applied, thanks.
^ permalink raw reply
* Re: [PATCH v9] kernel, add panic_on_warn
From: Yasuaki Ishimatsu @ 2014-11-12 1:59 UTC (permalink / raw)
To: Prarit Bhargava, linux-kernel
Cc: Jonathan Corbet, Andrew Morton, Rusty Russell, H. Peter Anvin,
Andi Kleen, Masami Hiramatsu, Fabian Frederick, vgoyal, jbaron,
linux-doc, kexec, linux-api
In-Reply-To: <1415709301-24783-1-git-send-email-prarit@redhat.com>
(2014/11/11 21:35), Prarit Bhargava wrote:
> There have been several times where I have had to rebuild a kernel to
> cause a panic when hitting a WARN() in the code in order to get a crash
> dump from a system. Sometimes this is easy to do, other times (such as
> in the case of a remote admin) it is not trivial to send new images to the
> user.
>
> A much easier method would be a switch to change the WARN() over to a
> panic. This makes debugging easier in that I can now test the actual
> image the WARN() was seen on and I do not have to engage in remote
> debugging.
>
> This patch adds a panic_on_warn kernel parameter and
> /proc/sys/kernel/panic_on_warn calls panic() in the warn_slowpath_common()
> path. The function will still print out the location of the warning.
>
> An example of the panic_on_warn output:
>
> The first line below is from the WARN_ON() to output the WARN_ON()'s location.
> After that the panic() output is displayed.
>
> WARNING: CPU: 30 PID: 11698 at /home/prarit/dummy_module/dummy-module.c:25 init_dummy+0x1f/0x30 [dummy_module]()
> Kernel panic - not syncing: panic_on_warn set ...
>
> CPU: 30 PID: 11698 Comm: insmod Tainted: G W OE 3.17.0+ #57
> Hardware name: Intel Corporation S2600CP/S2600CP, BIOS RMLSDP.86I.00.29.D696.1311111329 11/11/2013
> 0000000000000000 000000008e3f87df ffff88080f093c38 ffffffff81665190
> 0000000000000000 ffffffff818aea3d ffff88080f093cb8 ffffffff8165e2ec
> ffffffff00000008 ffff88080f093cc8 ffff88080f093c68 000000008e3f87df
> Call Trace:
> [<ffffffff81665190>] dump_stack+0x46/0x58
> [<ffffffff8165e2ec>] panic+0xd0/0x204
> [<ffffffffa038e05f>] ? init_dummy+0x1f/0x30 [dummy_module]
> [<ffffffff81076b90>] warn_slowpath_common+0xd0/0xd0
> [<ffffffffa038e040>] ? dummy_greetings+0x40/0x40 [dummy_module]
> [<ffffffff81076c8a>] warn_slowpath_null+0x1a/0x20
> [<ffffffffa038e05f>] init_dummy+0x1f/0x30 [dummy_module]
> [<ffffffff81002144>] do_one_initcall+0xd4/0x210
> [<ffffffff811b52c2>] ? __vunmap+0xc2/0x110
> [<ffffffff810f8889>] load_module+0x16a9/0x1b30
> [<ffffffff810f3d30>] ? store_uevent+0x70/0x70
> [<ffffffff810f49b9>] ? copy_module_from_fd.isra.44+0x129/0x180
> [<ffffffff810f8ec6>] SyS_finit_module+0xa6/0xd0
> [<ffffffff8166cf29>] system_call_fastpath+0x12/0x17
>
> Successfully tested by me.
>
> Cc: Jonathan Corbet <corbet@lwn.net>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Rusty Russell <rusty@rustcorp.com.au>
> Cc: "H. Peter Anvin" <hpa@zytor.com>
> Cc: Andi Kleen <ak@linux.intel.com>
> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
> Cc: Fabian Frederick <fabf@skynet.be>
> Cc: vgoyal@redhat.com
> Cc: isimatu.yasuaki@jp.fujitsu.com
> Cc: jbaron@akamai.com
> Cc: linux-doc@vger.kernel.org
> Cc: kexec@lists.infradead.org
> Cc: linux-api@vger.kernel.org
> Signed-off-by: Prarit Bhargava <prarit@redhat.com>
>
> [v2]: add /proc/sys/kernel/panic_on_warn, additional documentation, modify
> !slowpath cases
> [v3]: use proc_dointvec_minmax() in sysctl handler
> [v4]: remove !slowpath cases, and add __read_mostly
> [v5]: change to panic_on_warn, re-alphabetize Documentation/sysctl/kernel.txt
> [v6]: disable on kdump kernel to avoid bogus panicks.
> [v7]: swithch to core param, and remove change from v6
> [v8]: remove include file
> [v9]: restore cut line, and fix panic_on_warn comment
> ---
Looks goot to me.
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Thanks,
Yasuaki Ishimatsu
> Documentation/kdump/kdump.txt | 7 ++++++
> Documentation/kernel-parameters.txt | 3 +++
> Documentation/sysctl/kernel.txt | 40 +++++++++++++++++++++++------------
> include/linux/kernel.h | 1 +
> include/uapi/linux/sysctl.h | 1 +
> kernel/panic.c | 13 ++++++++++++
> kernel/sysctl.c | 9 ++++++++
> kernel/sysctl_binary.c | 1 +
> 8 files changed, 61 insertions(+), 14 deletions(-)
>
> diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
> index 6c0b9f2..bc4bd5a 100644
> --- a/Documentation/kdump/kdump.txt
> +++ b/Documentation/kdump/kdump.txt
> @@ -471,6 +471,13 @@ format. Crash is available on Dave Anderson's site at the following URL:
>
> http://people.redhat.com/~anderson/
>
> +Trigger Kdump on WARN()
> +=======================
> +
> +The kernel parameter, panic_on_warn, calls panic() in all WARN() paths. This
> +will cause a kdump to occur at the panic() call. In cases where a user wants
> +to specify this during runtime, /proc/sys/kernel/panic_on_warn can be set to 1
> +to achieve the same behaviour.
>
> Contact
> =======
> diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
> index 4c81a86..ea5d57c 100644
> --- a/Documentation/kernel-parameters.txt
> +++ b/Documentation/kernel-parameters.txt
> @@ -2509,6 +2509,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
> timeout < 0: reboot immediately
> Format: <timeout>
>
> + panic_on_warn panic() instead of WARN(). Useful to cause kdump
> + on a WARN().
> +
> crash_kexec_post_notifiers
> Run kdump after running panic-notifiers and dumping
> kmsg. This only for the users who doubt kdump always
> diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
> index 57baff5..b5d0c85 100644
> --- a/Documentation/sysctl/kernel.txt
> +++ b/Documentation/sysctl/kernel.txt
> @@ -54,8 +54,9 @@ show up in /proc/sys/kernel:
> - overflowuid
> - panic
> - panic_on_oops
> -- panic_on_unrecovered_nmi
> - panic_on_stackoverflow
> +- panic_on_unrecovered_nmi
> +- panic_on_warn
> - pid_max
> - powersave-nap [ PPC only ]
> - printk
> @@ -527,19 +528,6 @@ the recommended setting is 60.
>
> ==============================================================
>
> -panic_on_unrecovered_nmi:
> -
> -The default Linux behaviour on an NMI of either memory or unknown is
> -to continue operation. For many environments such as scientific
> -computing it is preferable that the box is taken out and the error
> -dealt with than an uncorrected parity/ECC error get propagated.
> -
> -A small number of systems do generate NMI's for bizarre random reasons
> -such as power management so the default is off. That sysctl works like
> -the existing panic controls already in that directory.
> -
> -==============================================================
> -
> panic_on_oops:
>
> Controls the kernel's behaviour when an oops or BUG is encountered.
> @@ -563,6 +551,30 @@ This file shows up if CONFIG_DEBUG_STACKOVERFLOW is enabled.
>
> ==============================================================
>
> +panic_on_unrecovered_nmi:
> +
> +The default Linux behaviour on an NMI of either memory or unknown is
> +to continue operation. For many environments such as scientific
> +computing it is preferable that the box is taken out and the error
> +dealt with than an uncorrected parity/ECC error get propagated.
> +
> +A small number of systems do generate NMI's for bizarre random reasons
> +such as power management so the default is off. That sysctl works like
> +the existing panic controls already in that directory.
> +
> +==============================================================
> +
> +panic_on_warn:
> +
> +Calls panic() in the WARN() path when set to 1. This is useful to avoid
> +a kernel rebuild when attempting to kdump at the location of a WARN().
> +
> +0: only WARN(), default behaviour.
> +
> +1: call panic() after printing out WARN() location.
> +
> +==============================================================
> +
> perf_cpu_time_max_percent:
>
> Hints to the kernel how much CPU time it should be allowed to
> diff --git a/include/linux/kernel.h b/include/linux/kernel.h
> index 3d770f55..d60d31d 100644
> --- a/include/linux/kernel.h
> +++ b/include/linux/kernel.h
> @@ -422,6 +422,7 @@ extern int panic_timeout;
> extern int panic_on_oops;
> extern int panic_on_unrecovered_nmi;
> extern int panic_on_io_nmi;
> +extern int panic_on_warn;
> extern int sysctl_panic_on_stackoverflow;
> /*
> * Only to be used by arch init code. If the user over-wrote the default
> diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
> index 43aaba1..0956373 100644
> --- a/include/uapi/linux/sysctl.h
> +++ b/include/uapi/linux/sysctl.h
> @@ -153,6 +153,7 @@ enum
> KERN_MAX_LOCK_DEPTH=74, /* int: rtmutex's maximum lock depth */
> KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */
> KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */
> + KERN_PANIC_ON_WARN=77, /* int: call panic() in WARN() functions */
> };
>
>
> diff --git a/kernel/panic.c b/kernel/panic.c
> index d09dc5c..f9412c0 100644
> --- a/kernel/panic.c
> +++ b/kernel/panic.c
> @@ -33,6 +33,7 @@ static int pause_on_oops;
> static int pause_on_oops_flag;
> static DEFINE_SPINLOCK(pause_on_oops_lock);
> static bool crash_kexec_post_notifiers;
> +int panic_on_warn __read_mostly;
>
> int panic_timeout = CONFIG_PANIC_TIMEOUT;
> EXPORT_SYMBOL_GPL(panic_timeout);
> @@ -427,6 +428,17 @@ static void warn_slowpath_common(const char *file, int line, void *caller,
> if (args)
> vprintk(args->fmt, args->args);
>
> + if (panic_on_warn) {
> + /*
> + * This thread may hit another WARN() in the panic path.
> + * Resetting this prevents additional WARN() from panicking the
> + * system on this thread. Other threads are blocked by the
> + * panic_mutex in panic().
> + */
> + panic_on_warn = 0;
> + panic("panic_on_warn set ...\n");
> + }
> +
> print_modules();
> dump_stack();
> print_oops_end_marker();
> @@ -484,6 +496,7 @@ EXPORT_SYMBOL(__stack_chk_fail);
>
> core_param(panic, panic_timeout, int, 0644);
> core_param(pause_on_oops, pause_on_oops, int, 0644);
> +core_param(panic_on_warn, panic_on_warn, int, 0644);
>
> static int __init setup_crash_kexec_post_notifiers(char *s)
> {
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index 15f2511..7c54ff7 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -1104,6 +1104,15 @@ static struct ctl_table kern_table[] = {
> .proc_handler = proc_dointvec,
> },
> #endif
> + {
> + .procname = "panic_on_warn",
> + .data = &panic_on_warn,
> + .maxlen = sizeof(int),
> + .mode = 0644,
> + .proc_handler = proc_dointvec_minmax,
> + .extra1 = &zero,
> + .extra2 = &one,
> + },
> { }
> };
>
> diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
> index 9a4f750..7e7746a 100644
> --- a/kernel/sysctl_binary.c
> +++ b/kernel/sysctl_binary.c
> @@ -137,6 +137,7 @@ static const struct bin_table bin_kern_table[] = {
> { CTL_INT, KERN_COMPAT_LOG, "compat-log" },
> { CTL_INT, KERN_MAX_LOCK_DEPTH, "max_lock_depth" },
> { CTL_INT, KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" },
> + { CTL_INT, KERN_PANIC_ON_WARN, "panic_on_warn" },
> {}
> };
>
>
^ permalink raw reply
* Re: [PATCH v2 07/19] selftests/firmware: add install target to enable installing test
From: Shuah Khan @ 2014-11-12 1:06 UTC (permalink / raw)
To: Kees Cook
Cc: Greg KH, Andrew Morton, Michal Marek, David S. Miller, Phong Tran,
David Herrmann, Hugh Dickins, pranith kumar, Eric W. Biederman,
Serge E. Hallyn, linux-kbuild, LKML, Linux API,
Network Development
In-Reply-To: <CAGXu5j+yLqH0xj=5N90LRmK9F1xPLVWBy+cyUCzjvKJH7gE7AA@mail.gmail.com>
On 11/11/2014 02:29 PM, Kees Cook wrote:
> Hi,
>
> Sorry, I still really don't like this approach. While it is all in one
> place (thank you for that), I think it isn't a form that is very
> workable for the people maintaining the self tests. How about this,
> instead of per-Makefile customization, why not define an execution
> framework for these tests instead.
If I understand correctly, sounds like you don't like the way
install target is implemented in the individual test Makefiles
and the changes I made to run_tests targets to address the code
duplication concern.
At the moment there is no duplicate code in this patch series
between install and run_tests targets. This is a first step
towards standardizing the framework and a definite improvement
over what we have currently. As I mentioned earlier, my goal
is to make it easier for developers to install and run the
existing tests and evolve the framework as we go.
Assuming my understanding is correct that:
-- install and run_tests targets in individual tests can be
refined and automated with a common Makefile approach you
proposed.
-- the rest of the user-interface kselftest_install and kselftest
are good.
I would like to propose that we get started with the current
implementation and refine it based on the following ideas you
suggested. The refinements you are recommending are confined
to selftests and can be made after the kselftest_install
gets added. Adding kselftest_install makes it easier to make
the refinements as it defines overall UI.
>
> For example, how about every test directory must have a Makefile with
> the needed binary targets. A common makefile could be included that
> defines the "run_tests" target that calls the script "run_tests.sh"
> that is a shell script in the current directory. (For inspiration, see
> how kernel modules can be built out of tree.)
>
> The "run_tests.sh" scripts could all include a common shell script,
> say "../common.sh" that provides any common variables, functions, etc
> (e.g. things like "Start $name test ..." should be in common.sh
> instead of repeated in every script, the installation logic can be in
> once place instead of repeated).
>
> Then along side common.sh could be "run_installed_tests.sh" or
> something, used on the installed target, that would traverse each
> directory, etc. From this, we can have a much more data-driven
> framework, and a common approach to running tests.
>
> As such, we should declare up front how tests should behave on
> failure. And the top-level test runner can do things like count the
> number of tests, failures, etc.
>
> Then, instead of splitting up the patches by test directory, you can
> split them up by logical changes (e.g. defining the common "run_tests"
> target, and then removing the target from all the tests by including
> the common makefile stub that defines it).
>
These are good ideas and I am with on evolving the framework to make
it easier to maintain individual tests. Patches are welcome.
thanks,
-- Shuah
--
Shuah Khan
Sr. Linux Kernel Developer
Samsung Research America (Silicon Valley)
shuahkh@osg.samsung.com | (970) 217-8978
^ permalink raw reply
* Re: [PATCH v6 0/7] vfs: Non-blockling buffered fs read (page cache only)
From: Thomas Gleixner @ 2014-11-11 23:27 UTC (permalink / raw)
To: Theodore Ts'o
Cc: Jeff Moyer, Milosz Tanski, Dave Chinner, LKML, Christoph Hellwig,
linux-fsdevel@vger.kernel.org, linux-aio@kvack.org, Mel Gorman,
Volker Lendecke, Tejun Heo, Al Viro, Linux API, Michael Kerrisk,
linux-arch
In-Reply-To: <20141111224938.GA4112@thunk.org>
On Tue, 11 Nov 2014, Theodore Ts'o wrote:
> On Tue, Nov 11, 2014 at 12:03:14PM -0500, Jeff Moyer wrote:
> >
> > I think he's referring to xfstests. Still, I think that's the wrong
> > place for functional testing. ltp would be better, imo.
>
> I disagree; xfstests is the right place for adding these tests, because
> these patches seem to require fs-specific support, and file system
> developers are already using xfstests when checking for regressions.
> Using xfstests is already part of most of the file system developers'
> workflow; ltp is not.
>
> So if you want to make sure we notice regressions, it really needs to
> go into xfstests. If you insist on putting it in ltp, then one of us
> will then have to make a copy of the tests and put it in xfstests.
No. LTP needs to pull in the latest changes from xfstests simply
because LTP is a conglomerate of domain specific tests. And it never
can become more than a conglomerate for obvious reasons.
xfstests is what the FS developers use and update. If LTP has some
extra magic tests developed then is should send patches against
xfstests and reintegrate the result.
Thanks,
tglx
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [PATCH v6 0/7] vfs: Non-blockling buffered fs read (page cache only)
From: Jeff Moyer @ 2014-11-11 23:21 UTC (permalink / raw)
To: Dave Chinner
Cc: Milosz Tanski, LKML, Christoph Hellwig,
linux-fsdevel@vger.kernel.org, linux-aio@kvack.org, Mel Gorman,
Volker Lendecke, Tejun Heo, Theodore Ts'o, Al Viro, Linux API,
Michael Kerrisk, linux-arch
In-Reply-To: <20141111214240.GV23575@dastard>
Dave Chinner <david@fromorbit.com> writes:
> On Tue, Nov 11, 2014 at 12:03:14PM -0500, Jeff Moyer wrote:
>> Milosz Tanski <milosz@adfin.com> writes:
>>
>> >> Can you write a test (or set of) for fstests that exercises this new
>> >> functionality? I'm not worried about performance, just
>> >> correctness....
>> >
>> > Sure thing. Can you point me at the fstests repo? A quick google
>> > search reveals lots of projects named fstests, most of them abandoned.
>>
>> I think he's referring to xfstests. Still, I think that's the wrong
>> place for functional testing. ltp would be better, imo.
>
> I don't follow. Can you explain why is xfstests be the wrong place
> to exercise this functionality and what makes ltp a better choice?
Right, I should have made a case for that. ltp already has test cases
for system calls such as readv/writev (though they are woefully
inadequate). It simply looked like a better fit to me. For some reason
I view xfstests as a regression test suite, but I know that isn't
strictly true.
If you feel xfstests is a better place, and Ted makes a good case for
that choice, then that's fine with me. I'm not, as Ted worried,
insisting on putting test cases into ltp. :) I was expressing my
opinion, and am happy for the dialog.
Cheers,
Jeff
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [PATCH v6 0/7] vfs: Non-blockling buffered fs read (page cache only)
From: Theodore Ts'o @ 2014-11-11 22:49 UTC (permalink / raw)
To: Jeff Moyer
Cc: Milosz Tanski, Dave Chinner, LKML, Christoph Hellwig,
linux-fsdevel@vger.kernel.org, linux-aio@kvack.org, Mel Gorman,
Volker Lendecke, Tejun Heo, Al Viro, Linux API, Michael Kerrisk,
linux-arch
In-Reply-To: <x49ioilbrfx.fsf@segfault.boston.devel.redhat.com>
On Tue, Nov 11, 2014 at 12:03:14PM -0500, Jeff Moyer wrote:
>
> I think he's referring to xfstests. Still, I think that's the wrong
> place for functional testing. ltp would be better, imo.
I disagree; xfstests is the right place for adding these tests, because
these patches seem to require fs-specific support, and file system
developers are already using xfstests when checking for regressions.
Using xfstests is already part of most of the file system developers'
workflow; ltp is not.
So if you want to make sure we notice regressions, it really needs to
go into xfstests. If you insist on putting it in ltp, then one of us
will then have to make a copy of the tests and put it in xfstests.
Cheers,
- Ted
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [v6 4/4] ext4: adds FS_IOC_FSSETXATTR/FS_IOC_FSGETXATTR interface support
From: Dave Chinner @ 2014-11-11 21:58 UTC (permalink / raw)
To: Li Xi
Cc: linux-fsdevel, linux-ext4, linux-api, tytso, adilger, jack, viro,
hch, dmonakhov
In-Reply-To: <1415468619-31851-5-git-send-email-lixi@ddn.com>
On Sun, Nov 09, 2014 at 01:43:39AM +0800, Li Xi wrote:
> This patch adds FS_IOC_FSSETXATTR/FS_IOC_FSGETXATTR ioctl interface
> support for ext4. The interface is kept consistent with
> XFS_IOC_FSGETXATTR/XFS_IOC_FSGETXATTR.
I missed somethignthe first time around, and it's to do with
fsx_flags field and what ext4 is putting in it....
> @@ -617,7 +713,45 @@ resizefs_out:
> }
> case EXT4_IOC_PRECACHE_EXTENTS:
> return ext4_ext_precache(inode);
> + case EXT4_IOC_FSGETXATTR:
> + {
> + struct fsxattr fa;
> +
> + memset(&fa, 0, sizeof(struct fsxattr));
> +
> + ext4_get_inode_flags(ei);
> + fa.fsx_xflags = ei->i_flags & EXT4_FL_USER_VISIBLE;
You're putting ext4 inode flags in this field. That's not right -
the flags that are defined for this field are the XFS_XFLAGS_*
fields, and you need to translate between the ext4 flags and the
existing falg definitions. Any falg definitions that don't already
exist that ext4 needs to support need to be added to the XFS_XFLAGS
definitions.
i.e. this is not a field that has flags defined by ext4 - the
flags must be the same across all filesystems that implement it, and
that means ext4 must use the existing definitions where they already
exist.
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
^ permalink raw reply
* Re: [PATCH v6 0/7] vfs: Non-blockling buffered fs read (page cache only)
From: Dave Chinner @ 2014-11-11 21:42 UTC (permalink / raw)
To: Jeff Moyer
Cc: Milosz Tanski, LKML, Christoph Hellwig,
linux-fsdevel@vger.kernel.org, linux-aio@kvack.org, Mel Gorman,
Volker Lendecke, Tejun Heo, Theodore Ts'o, Al Viro, Linux API,
Michael Kerrisk, linux-arch
In-Reply-To: <x49ioilbrfx.fsf@segfault.boston.devel.redhat.com>
On Tue, Nov 11, 2014 at 12:03:14PM -0500, Jeff Moyer wrote:
> Milosz Tanski <milosz@adfin.com> writes:
>
> >> Can you write a test (or set of) for fstests that exercises this new
> >> functionality? I'm not worried about performance, just
> >> correctness....
> >
> > Sure thing. Can you point me at the fstests repo? A quick google
> > search reveals lots of projects named fstests, most of them abandoned.
>
> I think he's referring to xfstests. Still, I think that's the wrong
> place for functional testing. ltp would be better, imo.
I don't follow. Can you explain why is xfstests be the wrong place
to exercise this functionality and what makes ltp a better choice?
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [PATCH v6 0/7] vfs: Non-blockling buffered fs read (page cache only)
From: Dave Chinner @ 2014-11-11 21:40 UTC (permalink / raw)
To: Milosz Tanski
Cc: LKML, Christoph Hellwig, linux-fsdevel@vger.kernel.org,
linux-aio@kvack.org, Mel Gorman, Volker Lendecke, Tejun Heo,
Jeff Moyer, Theodore Ts'o, Al Viro, Linux API,
Michael Kerrisk, linux-arch
In-Reply-To: <CANP1eJHfWT0Foe+weB1SJkJ10JnOge_g=E8CXBsQNPW7i2+4NA@mail.gmail.com>
On Tue, Nov 11, 2014 at 11:02:00AM -0500, Milosz Tanski wrote:
> On Tue, Nov 11, 2014 at 1:44 AM, Dave Chinner <david@fromorbit.com> wrote:
> > On Mon, Nov 10, 2014 at 11:40:23AM -0500, Milosz Tanski wrote:
> >> This patcheset introduces an ability to perform a non-blocking read from
> >> regular files in buffered IO mode. This works by only for those filesystems
> >> that have data in the page cache.
> >>
> >> It does this by introducing new syscalls new syscalls preadv2/pwritev2. These
> >> new syscalls behave like the network sendmsg, recvmsg syscalls that accept an
> >> extra flag argument (RWF_NONBLOCK).
> >>
> >> It's a very common patern today (samba, libuv, etc..) use a large threadpool to
> >> perform buffered IO operations. They submit the work form another thread
> >> that performs network IO and epoll or other threads that perform CPU work. This
> >> leads to increased latency for processing, esp. in the case of data that's
> >> already cached in the page cache.
> >>
> >> With the new interface the applications will now be able to fetch the data in
> >> their network / cpu bound thread(s) and only defer to a threadpool if it's not
> >> there. In our own application (VLDB) we've observed a decrease in latency for
> >> "fast" request by avoiding unnecessary queuing and having to swap out current
> >> tasks in IO bound work threads.
> >
> > Can you write a test (or set of) for fstests that exercises this new
> > functionality? I'm not worried about performance, just
> > correctness....
>
> Sure thing. Can you point me at the fstests repo? A quick google
> search reveals lots of projects named fstests, most of them abandoned.
git://git.kernel.org/pub/scm/fs/xfs/xfstests-dev.git
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [PATCH v2 07/19] selftests/firmware: add install target to enable installing test
From: Kees Cook @ 2014-11-11 21:29 UTC (permalink / raw)
To: Shuah Khan
Cc: Greg KH, Andrew Morton, Michal Marek, David S. Miller, Phong Tran,
David Herrmann, Hugh Dickins, pranith kumar, Eric W. Biederman,
Serge E. Hallyn, linux-kbuild, LKML, Linux API,
Network Development
In-Reply-To: <1d2d13556ddbbbbb13989cdcb08447909bc4afaf.1415735831.git.shuahkh-JPH+aEBZ4P+UEJcrhfAQsw@public.gmane.org>
Hi,
Sorry, I still really don't like this approach. While it is all in one
place (thank you for that), I think it isn't a form that is very
workable for the people maintaining the self tests. How about this,
instead of per-Makefile customization, why not define an execution
framework for these tests instead.
For example, how about every test directory must have a Makefile with
the needed binary targets. A common makefile could be included that
defines the "run_tests" target that calls the script "run_tests.sh"
that is a shell script in the current directory. (For inspiration, see
how kernel modules can be built out of tree.)
The "run_tests.sh" scripts could all include a common shell script,
say "../common.sh" that provides any common variables, functions, etc
(e.g. things like "Start $name test ..." should be in common.sh
instead of repeated in every script, the installation logic can be in
once place instead of repeated).
Then along side common.sh could be "run_installed_tests.sh" or
something, used on the installed target, that would traverse each
directory, etc. From this, we can have a much more data-driven
framework, and a common approach to running tests.
As such, we should declare up front how tests should behave on
failure. And the top-level test runner can do things like count the
number of tests, failures, etc.
Then, instead of splitting up the patches by test directory, you can
split them up by logical changes (e.g. defining the common "run_tests"
target, and then removing the target from all the tests by including
the common makefile stub that defines it).
-Kees
On Tue, Nov 11, 2014 at 12:27 PM, Shuah Khan <shuahkh-JPH+aEBZ4P+UEJcrhfAQsw@public.gmane.org> wrote:
> Add a new make target to enable installing test. This target
> installs test in the kselftest install location and add to the
> kselftest script to run the test. Install target can be run
> only from top level source dir.
>
> Signed-off-by: Shuah Khan <shuahkh-JPH+aEBZ4P+UEJcrhfAQsw@public.gmane.org>
> ---
> tools/testing/selftests/firmware/Makefile | 49 ++++++++++++++++++++-----------
> 1 file changed, 32 insertions(+), 17 deletions(-)
>
> diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile
> index e23cce0..2286dbb 100644
> --- a/tools/testing/selftests/firmware/Makefile
> +++ b/tools/testing/selftests/firmware/Makefile
> @@ -1,25 +1,40 @@
> # Makefile for firmware loading selftests
>
> # No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
> +
> +__fw_filesystem:
> +fw_filesystem = if /bin/sh ./fw_filesystem.sh ; then
> +fw_filesystem += echo fw_filesystem: ok;
> +fw_filesystem += else echo fw_filesystem: [FAIL];
> +fw_filesystem += fi
> +
> +__fw_userhelper:
> +fw_userhelper = if /bin/sh ./fw_userhelper.sh ; then
> +fw_userhelper += echo fw_userhelper: ok;
> +fw_userhelper += else
> +fw_userhelper += echo fw_userhelper: [FAIL];
> +fw_userhelper += fi
> +
> all:
>
> -fw_filesystem:
> - @if /bin/sh ./fw_filesystem.sh ; then \
> - echo "fw_filesystem: ok"; \
> - else \
> - echo "fw_filesystem: [FAIL]"; \
> - exit 1; \
> - fi
> -
> -fw_userhelper:
> - @if /bin/sh ./fw_userhelper.sh ; then \
> - echo "fw_userhelper: ok"; \
> - else \
> - echo "fw_userhelper: [FAIL]"; \
> - exit 1; \
> - fi
> -
> -run_tests: all fw_filesystem fw_userhelper
> +install:
> +ifdef INSTALL_KSFT_PATH
> + install ./fw_filesystem.sh ./fw_userhelper.sh $(INSTALL_KSFT_PATH)
> + @echo echo Start firmware filesystem test .... >> $(KSELFTEST)
> + @echo "$(fw_filesystem)" >> $(KSELFTEST)
> + @echo echo End firmware filesystem test .... >> $(KSELFTEST)
> + @echo echo -------------------- >> $(KSELFTEST)
> + @echo echo Start firmware userhelper test .... >> $(KSELFTEST)
> + @echo "$(fw_userhelper)" >> $(KSELFTEST)
> + @echo echo End firmware userhelper test .... >> $(KSELFTEST)
> + @echo echo ============================== >> $(KSELFTEST)
> +else
> + @echo Run make kselftest_install in top level source directory
> +endif
> +
> +run_tests:
> + @$(fw_filesystem)
> + @$(fw_userhelper)
>
> # Nothing to clean up.
> clean:
> --
> 1.9.1
>
--
Kees Cook
Chrome OS Security
^ permalink raw reply
* Re: [PATCH v6 2/7] vfs: Define new syscalls preadv2,pwritev2
From: Jeff Moyer @ 2014-11-11 21:09 UTC (permalink / raw)
To: Milosz Tanski
Cc: linux-kernel, Christoph Hellwig, linux-fsdevel, linux-aio,
Mel Gorman, Volker Lendecke, Tejun Heo, Theodore Ts'o,
Al Viro, linux-api, Michael Kerrisk, linux-arch, linux-mm
In-Reply-To: <0a8539257086c2a3f7615d35ef621c7f81df52cf.1415636409.git.milosz@adfin.com>
Milosz Tanski <milosz@adfin.com> writes:
> New syscalls that take an flag argument. This change does not add any specific
> flags.
Looks good.
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
>
> Signed-off-by: Milosz Tanski <milosz@adfin.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
> fs/read_write.c | 172 ++++++++++++++++++++++++++++++--------
> include/linux/compat.h | 6 ++
> include/linux/syscalls.h | 6 ++
> include/uapi/asm-generic/unistd.h | 6 +-
> mm/filemap.c | 5 +-
> 5 files changed, 156 insertions(+), 39 deletions(-)
>
> diff --git a/fs/read_write.c b/fs/read_write.c
> index 94b2d34..b1b4bc8 100644
> --- a/fs/read_write.c
> +++ b/fs/read_write.c
> @@ -866,6 +866,8 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
> return -EBADF;
> if (!(file->f_mode & FMODE_CAN_READ))
> return -EINVAL;
> + if (flags & ~0)
> + return -EINVAL;
>
> return do_readv_writev(READ, file, vec, vlen, pos, flags);
> }
> @@ -879,21 +881,23 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
> return -EBADF;
> if (!(file->f_mode & FMODE_CAN_WRITE))
> return -EINVAL;
> + if (flags & ~0)
> + return -EINVAL;
>
> return do_readv_writev(WRITE, file, vec, vlen, pos, flags);
> }
>
> EXPORT_SYMBOL(vfs_writev);
>
> -SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
> - unsigned long, vlen)
> +static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
> + unsigned long vlen, int flags)
> {
> struct fd f = fdget_pos(fd);
> ssize_t ret = -EBADF;
>
> if (f.file) {
> loff_t pos = file_pos_read(f.file);
> - ret = vfs_readv(f.file, vec, vlen, &pos, 0);
> + ret = vfs_readv(f.file, vec, vlen, &pos, flags);
> if (ret >= 0)
> file_pos_write(f.file, pos);
> fdput_pos(f);
> @@ -905,15 +909,15 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
> return ret;
> }
>
> -SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
> - unsigned long, vlen)
> +static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec,
> + unsigned long vlen, int flags)
> {
> struct fd f = fdget_pos(fd);
> ssize_t ret = -EBADF;
>
> if (f.file) {
> loff_t pos = file_pos_read(f.file);
> - ret = vfs_writev(f.file, vec, vlen, &pos, 0);
> + ret = vfs_writev(f.file, vec, vlen, &pos, flags);
> if (ret >= 0)
> file_pos_write(f.file, pos);
> fdput_pos(f);
> @@ -931,10 +935,9 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
> return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
> }
>
> -SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
> - unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
> +static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec,
> + unsigned long vlen, loff_t pos, int flags)
> {
> - loff_t pos = pos_from_hilo(pos_h, pos_l);
> struct fd f;
> ssize_t ret = -EBADF;
>
> @@ -945,7 +948,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
> if (f.file) {
> ret = -ESPIPE;
> if (f.file->f_mode & FMODE_PREAD)
> - ret = vfs_readv(f.file, vec, vlen, &pos, 0);
> + ret = vfs_readv(f.file, vec, vlen, &pos, flags);
> fdput(f);
> }
>
> @@ -955,10 +958,9 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
> return ret;
> }
>
> -SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
> - unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
> +static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec,
> + unsigned long vlen, loff_t pos, int flags)
> {
> - loff_t pos = pos_from_hilo(pos_h, pos_l);
> struct fd f;
> ssize_t ret = -EBADF;
>
> @@ -969,7 +971,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
> if (f.file) {
> ret = -ESPIPE;
> if (f.file->f_mode & FMODE_PWRITE)
> - ret = vfs_writev(f.file, vec, vlen, &pos, 0);
> + ret = vfs_writev(f.file, vec, vlen, &pos, flags);
> fdput(f);
> }
>
> @@ -979,11 +981,63 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
> return ret;
> }
>
> +SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
> + unsigned long, vlen)
> +{
> + return do_readv(fd, vec, vlen, 0);
> +}
> +
> +SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
> + unsigned long, vlen)
> +{
> + return do_writev(fd, vec, vlen, 0);
> +}
> +
> +SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
> + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
> +{
> + loff_t pos = pos_from_hilo(pos_h, pos_l);
> +
> + return do_preadv(fd, vec, vlen, pos, 0);
> +}
> +
> +SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec,
> + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
> + int, flags)
> +{
> + loff_t pos = pos_from_hilo(pos_h, pos_l);
> +
> + if (pos == -1)
> + return do_readv(fd, vec, vlen, flags);
> +
> + return do_preadv(fd, vec, vlen, pos, flags);
> +}
> +
> +SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
> + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
> +{
> + loff_t pos = pos_from_hilo(pos_h, pos_l);
> +
> + return do_pwritev(fd, vec, vlen, pos, 0);
> +}
> +
> +SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
> + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
> + int, flags)
> +{
> + loff_t pos = pos_from_hilo(pos_h, pos_l);
> +
> + if (pos == -1)
> + return do_writev(fd, vec, vlen, flags);
> +
> + return do_pwritev(fd, vec, vlen, pos, flags);
> +}
> +
> #ifdef CONFIG_COMPAT
>
> static ssize_t compat_do_readv_writev(int type, struct file *file,
> const struct compat_iovec __user *uvector,
> - unsigned long nr_segs, loff_t *pos)
> + unsigned long nr_segs, loff_t *pos, int flags)
> {
> compat_ssize_t tot_len;
> struct iovec iovstack[UIO_FASTIOV];
> @@ -1017,7 +1071,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
>
> if (iter_fn)
> ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len,
> - pos, iter_fn, 0);
> + pos, iter_fn, flags);
> else if (fnv)
> ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
> pos, fnv);
> @@ -1041,7 +1095,7 @@ out:
>
> static size_t compat_readv(struct file *file,
> const struct compat_iovec __user *vec,
> - unsigned long vlen, loff_t *pos)
> + unsigned long vlen, loff_t *pos, int flags)
> {
> ssize_t ret = -EBADF;
>
> @@ -1051,8 +1105,10 @@ static size_t compat_readv(struct file *file,
> ret = -EINVAL;
> if (!(file->f_mode & FMODE_CAN_READ))
> goto out;
> + if (flags & ~0)
> + goto out;
>
> - ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
> + ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags);
>
> out:
> if (ret > 0)
> @@ -1061,9 +1117,9 @@ out:
> return ret;
> }
>
> -COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
> - const struct compat_iovec __user *,vec,
> - compat_ulong_t, vlen)
> +static size_t __compat_sys_readv(compat_ulong_t fd,
> + const struct compat_iovec __user *vec,
> + compat_ulong_t vlen, int flags)
> {
> struct fd f = fdget_pos(fd);
> ssize_t ret;
> @@ -1072,16 +1128,24 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
> if (!f.file)
> return -EBADF;
> pos = f.file->f_pos;
> - ret = compat_readv(f.file, vec, vlen, &pos);
> + ret = compat_readv(f.file, vec, vlen, &pos, flags);
> if (ret >= 0)
> f.file->f_pos = pos;
> fdput_pos(f);
> return ret;
> +
> +}
> +
> +COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
> + const struct compat_iovec __user *,vec,
> + compat_ulong_t, vlen)
> +{
> + return __compat_sys_readv(fd, vec, vlen, 0);
> }
>
> static long __compat_sys_preadv64(unsigned long fd,
> const struct compat_iovec __user *vec,
> - unsigned long vlen, loff_t pos)
> + unsigned long vlen, loff_t pos, int flags)
> {
> struct fd f;
> ssize_t ret;
> @@ -1093,7 +1157,7 @@ static long __compat_sys_preadv64(unsigned long fd,
> return -EBADF;
> ret = -ESPIPE;
> if (f.file->f_mode & FMODE_PREAD)
> - ret = compat_readv(f.file, vec, vlen, &pos);
> + ret = compat_readv(f.file, vec, vlen, &pos, flags);
> fdput(f);
> return ret;
> }
> @@ -1103,7 +1167,7 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
> const struct compat_iovec __user *,vec,
> unsigned long, vlen, loff_t, pos)
> {
> - return __compat_sys_preadv64(fd, vec, vlen, pos);
> + return __compat_sys_preadv64(fd, vec, vlen, pos, 0);
> }
> #endif
>
> @@ -1113,12 +1177,25 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
> {
> loff_t pos = ((loff_t)pos_high << 32) | pos_low;
>
> - return __compat_sys_preadv64(fd, vec, vlen, pos);
> + return __compat_sys_preadv64(fd, vec, vlen, pos, 0);
> +}
> +
> +COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
> + const struct compat_iovec __user *,vec,
> + compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
> + int, flags)
> +{
> + loff_t pos = ((loff_t)pos_high << 32) | pos_low;
> +
> + if (pos == -1)
> + return __compat_sys_readv(fd, vec, vlen, flags);
> +
> + return __compat_sys_preadv64(fd, vec, vlen, pos, flags);
> }
>
> static size_t compat_writev(struct file *file,
> const struct compat_iovec __user *vec,
> - unsigned long vlen, loff_t *pos)
> + unsigned long vlen, loff_t *pos, int flags)
> {
> ssize_t ret = -EBADF;
>
> @@ -1128,8 +1205,10 @@ static size_t compat_writev(struct file *file,
> ret = -EINVAL;
> if (!(file->f_mode & FMODE_CAN_WRITE))
> goto out;
> + if (flags & ~0)
> + goto out;
>
> - ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
> + ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, flags);
>
> out:
> if (ret > 0)
> @@ -1138,9 +1217,9 @@ out:
> return ret;
> }
>
> -COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
> - const struct compat_iovec __user *, vec,
> - compat_ulong_t, vlen)
> +static size_t __compat_sys_writev(compat_ulong_t fd,
> + const struct compat_iovec __user* vec,
> + compat_ulong_t vlen, int flags)
> {
> struct fd f = fdget_pos(fd);
> ssize_t ret;
> @@ -1149,28 +1228,36 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
> if (!f.file)
> return -EBADF;
> pos = f.file->f_pos;
> - ret = compat_writev(f.file, vec, vlen, &pos);
> + ret = compat_writev(f.file, vec, vlen, &pos, flags);
> if (ret >= 0)
> f.file->f_pos = pos;
> fdput_pos(f);
> return ret;
> }
>
> +COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
> + const struct compat_iovec __user *, vec,
> + compat_ulong_t, vlen)
> +{
> + return __compat_sys_writev(fd, vec, vlen, 0);
> +}
> +
> static long __compat_sys_pwritev64(unsigned long fd,
> const struct compat_iovec __user *vec,
> - unsigned long vlen, loff_t pos)
> + unsigned long vlen, loff_t pos, int flags)
> {
> struct fd f;
> ssize_t ret;
>
> if (pos < 0)
> return -EINVAL;
> +
> f = fdget(fd);
> if (!f.file)
> return -EBADF;
> ret = -ESPIPE;
> if (f.file->f_mode & FMODE_PWRITE)
> - ret = compat_writev(f.file, vec, vlen, &pos);
> + ret = compat_writev(f.file, vec, vlen, &pos, flags);
> fdput(f);
> return ret;
> }
> @@ -1180,7 +1267,7 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
> const struct compat_iovec __user *,vec,
> unsigned long, vlen, loff_t, pos)
> {
> - return __compat_sys_pwritev64(fd, vec, vlen, pos);
> + return __compat_sys_pwritev64(fd, vec, vlen, pos, 0);
> }
> #endif
>
> @@ -1190,8 +1277,21 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
> {
> loff_t pos = ((loff_t)pos_high << 32) | pos_low;
>
> - return __compat_sys_pwritev64(fd, vec, vlen, pos);
> + return __compat_sys_pwritev64(fd, vec, vlen, pos, 0);
> +}
> +
> +COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
> + const struct compat_iovec __user *,vec,
> + compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags)
> +{
> + loff_t pos = ((loff_t)pos_high << 32) | pos_low;
> +
> + if (pos == -1)
> + return __compat_sys_writev(fd, vec, vlen, flags);
> +
> + return __compat_sys_pwritev64(fd, vec, vlen, pos, flags);
> }
> +
> #endif
>
> static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
> diff --git a/include/linux/compat.h b/include/linux/compat.h
> index e649426..63a94e2 100644
> --- a/include/linux/compat.h
> +++ b/include/linux/compat.h
> @@ -340,6 +340,12 @@ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
> asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd,
> const struct compat_iovec __user *vec,
> compat_ulong_t vlen, u32 pos_low, u32 pos_high);
> +asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd,
> + const struct compat_iovec __user *vec,
> + compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags);
> +asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd,
> + const struct compat_iovec __user *vec,
> + compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags);
>
> #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
> asmlinkage long compat_sys_preadv64(unsigned long fd,
> diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
> index bda9b81..cedc22e 100644
> --- a/include/linux/syscalls.h
> +++ b/include/linux/syscalls.h
> @@ -571,8 +571,14 @@ asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf,
> size_t count, loff_t pos);
> asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec,
> unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
> +asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec,
> + unsigned long vlen, unsigned long pos_l, unsigned long pos_h,
> + int flags);
> asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec,
> unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
> +asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec,
> + unsigned long vlen, unsigned long pos_l, unsigned long pos_h,
> + int flags);
> asmlinkage long sys_getcwd(char __user *buf, unsigned long size);
> asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode);
> asmlinkage long sys_chdir(const char __user *filename);
> diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
> index 22749c1..9406018 100644
> --- a/include/uapi/asm-generic/unistd.h
> +++ b/include/uapi/asm-generic/unistd.h
> @@ -213,6 +213,10 @@ __SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
> __SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
> #define __NR_pwritev 70
> __SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
> +#define __NR_preadv2 281
> +__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
> +#define __NR_pwritev2 282
> +__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
>
> /* fs/sendfile.c */
> #define __NR3264_sendfile 71
> @@ -709,7 +713,7 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create)
> __SYSCALL(__NR_bpf, sys_bpf)
>
> #undef __NR_syscalls
> -#define __NR_syscalls 281
> +#define __NR_syscalls 283
>
> /*
> * All syscalls below here should go away really,
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 14b4642..530c263 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -1457,6 +1457,7 @@ static void shrink_readahead_size_eio(struct file *filp,
> * @ppos: current file position
> * @iter: data destination
> * @written: already copied
> + * @flags: optional flags
> *
> * This is a generic file read routine, and uses the
> * mapping->a_ops->readpage() function for the actual low-level stuff.
> @@ -1465,7 +1466,7 @@ static void shrink_readahead_size_eio(struct file *filp,
> * of the logic when it comes to error handling etc.
> */
> static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
> - struct iov_iter *iter, ssize_t written)
> + struct iov_iter *iter, ssize_t written, int flags)
> {
> struct address_space *mapping = filp->f_mapping;
> struct inode *inode = mapping->host;
> @@ -1735,7 +1736,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
> }
> }
>
> - retval = do_generic_file_read(file, ppos, iter, retval);
> + retval = do_generic_file_read(file, ppos, iter, retval, iocb->ki_rwflags);
> out:
> return retval;
> }
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [v6 3/4] ext4: adds project quota support
From: Jan Kara @ 2014-11-11 20:34 UTC (permalink / raw)
To: Li Xi
Cc: linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-ext4-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, tytso-3s7WtUTddSA,
adilger-m1MBpc4rdrD3fQ9qLvQP4Q, jack-AlSwsSmVLrQ,
viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn, hch-wEGCiKHe2LqWVfeAwA7xHQ,
dmonakhov-GEFAQzZX7r8dnm+yROfE0A
In-Reply-To: <1415468619-31851-4-git-send-email-lixi-LfVdkaOWEx8@public.gmane.org>
On Sun 09-11-14 01:43:38, Li Xi wrote:
> This patch adds mount options for enabling/disabling project quota
> accounting and enforcement. A new specific inode is also used for
> project quota accounting.
>
> Signed-off-by: Li Xi <lixi-LfVdkaOWEx8@public.gmane.org>
> Signed-off-by: Dmitry Monakhov <dmonakhov-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
The patch looks good. You can add:
Reviewed-by: Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>
Honza
> ---
> fs/ext4/ext4.h | 8 +++-
> fs/ext4/super.c | 95 ++++++++++++++++++++++++++++++++++++++++++++++++------
> 2 files changed, 90 insertions(+), 13 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index d30dfa6..4c797da 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -217,6 +217,7 @@ struct ext4_io_submit {
> #define EXT4_UNDEL_DIR_INO 6 /* Undelete directory inode */
> #define EXT4_RESIZE_INO 7 /* Reserved group descriptors inode */
> #define EXT4_JOURNAL_INO 8 /* Journal inode */
> +#define EXT4_PRJ_QUOTA_INO 9 /* Project quota inode */
>
> /* First non-reserved inode for old ext4 filesystems */
> #define EXT4_GOOD_OLD_FIRST_INO 11
> @@ -991,6 +992,7 @@ struct ext4_inode_info {
> #define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
> #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
> #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
> +#define EXT4_MOUNT_PRJQUOTA 0x2000000 /* Project quota support */
> #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
> #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
> #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
> @@ -1166,7 +1168,8 @@ struct ext4_super_block {
> __le32 s_grp_quota_inum; /* inode for tracking group quota */
> __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
> __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */
> - __le32 s_reserved[106]; /* Padding to the end of the block */
> + __le32 s_prj_quota_inum; /* inode for tracking project quota */
> + __le32 s_reserved[105]; /* Padding to the end of the block */
> __le32 s_checksum; /* crc32c(superblock) */
> };
>
> @@ -1181,7 +1184,7 @@ struct ext4_super_block {
> #define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */
>
> /* Number of quota types we support */
> -#define EXT4_MAXQUOTAS 2
> +#define EXT4_MAXQUOTAS 3
>
> /*
> * fourth extended-fs super-block data in memory
> @@ -1372,6 +1375,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
> ino == EXT4_BOOT_LOADER_INO ||
> ino == EXT4_JOURNAL_INO ||
> ino == EXT4_RESIZE_INO ||
> + ino == EXT4_PRJ_QUOTA_INO ||
> (ino >= EXT4_FIRST_INO(sb) &&
> ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
> }
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index d8a348d..564fbd7 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -1045,8 +1045,8 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
> }
>
> #ifdef CONFIG_QUOTA
> -#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group")
> -#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
> +static char *quotatypes[] = INITQFNAMES;
> +#define QTYPE2NAME(t) (quotatypes[t])
>
> static int ext4_write_dquot(struct dquot *dquot);
> static int ext4_acquire_dquot(struct dquot *dquot);
> @@ -1138,10 +1138,11 @@ enum {
> Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
> Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
> Opt_data_err_abort, Opt_data_err_ignore,
> - Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
> + Opt_usrjquota, Opt_grpjquota, Opt_prjjquota,
> + Opt_offusrjquota, Opt_offgrpjquota, Opt_offprjjquota,
> Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
> Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
> - Opt_usrquota, Opt_grpquota, Opt_i_version,
> + Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version,
> Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
> Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
> Opt_inode_readahead_blks, Opt_journal_ioprio,
> @@ -1192,6 +1193,8 @@ static const match_table_t tokens = {
> {Opt_usrjquota, "usrjquota=%s"},
> {Opt_offgrpjquota, "grpjquota="},
> {Opt_grpjquota, "grpjquota=%s"},
> + {Opt_offprjjquota, "prjjquota="},
> + {Opt_prjjquota, "prjjquota=%s"},
> {Opt_jqfmt_vfsold, "jqfmt=vfsold"},
> {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
> {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
> @@ -1199,6 +1202,7 @@ static const match_table_t tokens = {
> {Opt_noquota, "noquota"},
> {Opt_quota, "quota"},
> {Opt_usrquota, "usrquota"},
> + {Opt_prjquota, "prjquota"},
> {Opt_barrier, "barrier=%u"},
> {Opt_barrier, "barrier"},
> {Opt_nobarrier, "nobarrier"},
> @@ -1411,12 +1415,17 @@ static const struct mount_opts {
> MOPT_SET | MOPT_Q},
> {Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA,
> MOPT_SET | MOPT_Q},
> + {Opt_prjquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_PRJQUOTA,
> + MOPT_SET | MOPT_Q},
> {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
> - EXT4_MOUNT_GRPQUOTA), MOPT_CLEAR | MOPT_Q},
> + EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA),
> + MOPT_CLEAR | MOPT_Q},
> {Opt_usrjquota, 0, MOPT_Q},
> {Opt_grpjquota, 0, MOPT_Q},
> + {Opt_prjjquota, 0, MOPT_Q},
> {Opt_offusrjquota, 0, MOPT_Q},
> {Opt_offgrpjquota, 0, MOPT_Q},
> + {Opt_offprjjquota, 0, MOPT_Q},
> {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
> {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
> {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
> @@ -1439,10 +1448,14 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
> return set_qf_name(sb, USRQUOTA, &args[0]);
> else if (token == Opt_grpjquota)
> return set_qf_name(sb, GRPQUOTA, &args[0]);
> + else if (token == Opt_prjjquota)
> + return set_qf_name(sb, PRJQUOTA, &args[0]);
> else if (token == Opt_offusrjquota)
> return clear_qf_name(sb, USRQUOTA);
> else if (token == Opt_offgrpjquota)
> return clear_qf_name(sb, GRPQUOTA);
> + else if (token == Opt_offprjjquota)
> + return clear_qf_name(sb, PRJQUOTA);
> #endif
> switch (token) {
> case Opt_noacl:
> @@ -1668,19 +1681,28 @@ static int parse_options(char *options, struct super_block *sb,
> }
> #ifdef CONFIG_QUOTA
> if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
> - (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) {
> + (test_opt(sb, USRQUOTA) ||
> + test_opt(sb, GRPQUOTA) ||
> + test_opt(sb, PRJQUOTA))) {
> ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA "
> "feature is enabled");
> return 0;
> }
> - if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
> + if (sbi->s_qf_names[USRQUOTA] ||
> + sbi->s_qf_names[GRPQUOTA] ||
> + sbi->s_qf_names[PRJQUOTA]) {
> if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
> clear_opt(sb, USRQUOTA);
>
> if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
> clear_opt(sb, GRPQUOTA);
>
> - if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) {
> + if (test_opt(sb, PRJQUOTA) && sbi->s_qf_names[PRJQUOTA])
> + clear_opt(sb, PRJQUOTA);
> +
> + if (test_opt(sb, GRPQUOTA) ||
> + test_opt(sb, USRQUOTA) ||
> + test_opt(sb, PRJQUOTA)) {
> ext4_msg(sb, KERN_ERR, "old and new quota "
> "format mixing");
> return 0;
> @@ -1734,6 +1756,9 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
>
> if (sbi->s_qf_names[GRPQUOTA])
> seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
> +
> + if (sbi->s_qf_names[PRJQUOTA])
> + seq_printf(seq, ",prjjquota=%s", sbi->s_qf_names[PRJQUOTA]);
> #endif
> }
>
> @@ -5030,6 +5055,46 @@ restore_opts:
> return err;
> }
>
> +static int ext4_statfs_project(struct super_block *sb,
> + kprojid_t projid, struct kstatfs *buf)
> +{
> + struct kqid qid;
> + struct dquot *dquot;
> + u64 limit;
> + u64 curblock;
> +
> + qid = make_kqid_projid(projid);
> + dquot = dqget(sb, qid);
> + if (!dquot)
> + return -ESRCH;
> + spin_lock(&dq_data_lock);
> +
> + limit = dquot->dq_dqb.dqb_bsoftlimit ?
> + dquot->dq_dqb.dqb_bsoftlimit :
> + dquot->dq_dqb.dqb_bhardlimit;
> + if (limit && buf->f_blocks * buf->f_bsize > limit) {
> + curblock = dquot->dq_dqb.dqb_curspace / buf->f_bsize;
> + buf->f_blocks = limit / buf->f_bsize;
> + buf->f_bfree = buf->f_bavail =
> + (buf->f_blocks > curblock) ?
> + (buf->f_blocks - curblock) : 0;
> + }
> +
> + limit = dquot->dq_dqb.dqb_isoftlimit ?
> + dquot->dq_dqb.dqb_isoftlimit :
> + dquot->dq_dqb.dqb_ihardlimit;
> + if (limit && buf->f_files > limit) {
> + buf->f_files = limit;
> + buf->f_ffree =
> + (buf->f_files > dquot->dq_dqb.dqb_curinodes) ?
> + (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
> + }
> +
> + spin_unlock(&dq_data_lock);
> + dqput(dquot);
> + return 0;
> +}
> +
> static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
> {
> struct super_block *sb = dentry->d_sb;
> @@ -5038,6 +5103,7 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
> ext4_fsblk_t overhead = 0, resv_blocks;
> u64 fsid;
> s64 bfree;
> + struct inode *inode = dentry->d_inode;
> resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters));
>
> if (!test_opt(sb, MINIX_DF))
> @@ -5062,6 +5128,9 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
> buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
> buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
>
> + if (ext4_test_inode_flag(inode, EXT4_INODE_PROJINHERIT) &&
> + sb_has_quota_limits_enabled(sb, PRJQUOTA))
> + ext4_statfs_project(sb, EXT4_I(inode)->i_projid, buf);
> return 0;
> }
>
> @@ -5142,7 +5211,9 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot)
>
> /* Are we journaling quotas? */
> if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) ||
> - sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
> + sbi->s_qf_names[USRQUOTA] ||
> + sbi->s_qf_names[GRPQUOTA] ||
> + sbi->s_qf_names[PRJQUOTA]) {
> dquot_mark_dquot_dirty(dquot);
> return ext4_write_dquot(dquot);
> } else {
> @@ -5226,7 +5297,8 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
> struct inode *qf_inode;
> unsigned long qf_inums[EXT4_MAXQUOTAS] = {
> le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
> - le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
> + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum),
> + le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum)
> };
>
> BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA));
> @@ -5254,7 +5326,8 @@ static int ext4_enable_quotas(struct super_block *sb)
> int type, err = 0;
> unsigned long qf_inums[EXT4_MAXQUOTAS] = {
> le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
> - le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
> + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum),
> + le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum)
> };
>
> sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
> --
> 1.7.1
>
--
Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>
SUSE Labs, CR
^ permalink raw reply
* Re: [v6 2/4] ext4: adds project ID support
From: Jan Kara @ 2014-11-11 20:31 UTC (permalink / raw)
To: Li Xi
Cc: linux-fsdevel, linux-ext4, linux-api, tytso, adilger, jack, viro,
hch, dmonakhov
In-Reply-To: <1415468619-31851-3-git-send-email-lixi@ddn.com>
On Sun 09-11-14 01:43:37, Li Xi wrote:
> This patch adds a new internal field of ext4 inode to save project
> identifier. Also a new flag EXT4_INODE_PROJINHERIT is added for
> inheriting project ID from parent directory.
>
> Signed-off-by: Li Xi <lixi@ddn.com>
You didn't add my Reviewed-by tag from the last round. Why is that? I was
wondering whether you significantly changed the patch since the last
submission but it doesn't seem so.
Honza
> ---
> fs/ext4/ext4.h | 21 +++++++++++++++++----
> fs/ext4/ialloc.c | 6 ++++++
> fs/ext4/inode.c | 29 +++++++++++++++++++++++++++++
> fs/ext4/namei.c | 17 +++++++++++++++++
> fs/ext4/super.c | 1 +
> 5 files changed, 70 insertions(+), 4 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index c55a1fa..d30dfa6 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -386,16 +386,18 @@ struct flex_groups {
> #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */
> #define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */
> #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */
> +#define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
> #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
>
> -#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */
> -#define EXT4_FL_USER_MODIFIABLE 0x004380FF /* User modifiable flags */
> +#define EXT4_FL_USER_VISIBLE 0x204BDFFF /* User visible flags */
> +#define EXT4_FL_USER_MODIFIABLE 0x204380FF /* User modifiable flags */
>
> /* Flags that should be inherited by new inodes from their parent. */
> #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
> EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
> EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
> - EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
> + EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
> + EXT4_PROJINHERIT_FL)
>
> /* Flags that are appropriate for regular files (all but dir-specific ones). */
> #define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL))
> @@ -443,6 +445,7 @@ enum {
> EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */
> EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */
> EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */
> + EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */
> EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */
> };
>
> @@ -694,6 +697,7 @@ struct ext4_inode {
> __le32 i_crtime; /* File Creation time */
> __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */
> __le32 i_version_hi; /* high 32 bits for 64-bit version */
> + __le32 i_projid; /* Project ID */
> };
>
> struct move_extent {
> @@ -943,6 +947,7 @@ struct ext4_inode_info {
>
> /* Precomputed uuid+inum+igen checksum for seeding inode checksums */
> __u32 i_csum_seed;
> + kprojid_t i_projid;
> };
>
> /*
> @@ -1526,6 +1531,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
> * GDT_CSUM bits are mutually exclusive.
> */
> #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400
> +#define EXT4_FEATURE_RO_COMPAT_PROJECT 0x1000 /* Project quota */
>
> #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001
> #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002
> @@ -1575,7 +1581,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
> EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
> EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
> EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
> - EXT4_FEATURE_RO_COMPAT_QUOTA)
> + EXT4_FEATURE_RO_COMPAT_QUOTA |\
> + EXT4_FEATURE_RO_COMPAT_PROJECT)
>
> /*
> * Default values for user and/or group using reserved blocks
> @@ -1583,6 +1590,11 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
> #define EXT4_DEF_RESUID 0
> #define EXT4_DEF_RESGID 0
>
> +/*
> + * Default project ID
> + */
> +#define EXT4_DEF_PROJID 0
> +
> #define EXT4_DEF_INODE_READAHEAD_BLKS 32
>
> /*
> @@ -2135,6 +2147,7 @@ extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
> loff_t lstart, loff_t lend);
> extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
> extern qsize_t *ext4_get_reserved_space(struct inode *inode);
> +extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
> extern void ext4_da_update_reserve_space(struct inode *inode,
> int used, int quota_claim);
>
> diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
> index ac644c3..fefb948 100644
> --- a/fs/ext4/ialloc.c
> +++ b/fs/ext4/ialloc.c
> @@ -756,6 +756,12 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
> inode->i_gid = dir->i_gid;
> } else
> inode_init_owner(inode, dir, mode);
> + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) &&
> + ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) {
> + ei->i_projid = EXT4_I(dir)->i_projid;
> + } else {
> + ei->i_projid = make_kprojid(&init_user_ns, EXT4_DEF_PROJID);
> + }
> dquot_initialize(inode);
>
> if (!goal)
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 3356ab5..1c440be 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -3886,6 +3886,14 @@ static inline void ext4_iget_extra_inode(struct inode *inode,
> EXT4_I(inode)->i_inline_off = 0;
> }
>
> +int ext4_get_projid(struct inode *inode, kprojid_t *projid)
> +{
> + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_PROJECT))
> + return -EOPNOTSUPP;
> + *projid = EXT4_I(inode)->i_projid;
> + return 0;
> +}
> +
> struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
> {
> struct ext4_iloc iloc;
> @@ -3897,6 +3905,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
> int block;
> uid_t i_uid;
> gid_t i_gid;
> + projid_t i_projid;
>
> inode = iget_locked(sb, ino);
> if (!inode)
> @@ -3946,12 +3955,18 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
> inode->i_mode = le16_to_cpu(raw_inode->i_mode);
> i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
> i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
> + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT))
> + i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid);
> + else
> + i_projid = EXT4_DEF_PROJID;
> +
> if (!(test_opt(inode->i_sb, NO_UID32))) {
> i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
> i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
> }
> i_uid_write(inode, i_uid);
> i_gid_write(inode, i_gid);
> + ei->i_projid = make_kprojid(&init_user_ns, i_projid);;
> set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
>
> ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
> @@ -4181,6 +4196,7 @@ static int ext4_do_update_inode(handle_t *handle,
> int need_datasync = 0, set_large_file = 0;
> uid_t i_uid;
> gid_t i_gid;
> + projid_t i_projid;
>
> spin_lock(&ei->i_raw_lock);
>
> @@ -4193,6 +4209,7 @@ static int ext4_do_update_inode(handle_t *handle,
> raw_inode->i_mode = cpu_to_le16(inode->i_mode);
> i_uid = i_uid_read(inode);
> i_gid = i_gid_read(inode);
> + i_projid = from_kprojid(&init_user_ns, ei->i_projid);
> if (!(test_opt(inode->i_sb, NO_UID32))) {
> raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid));
> raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid));
> @@ -4272,6 +4289,18 @@ static int ext4_do_update_inode(handle_t *handle,
> }
> }
>
> + BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
> + EXT4_FEATURE_RO_COMPAT_PROJECT) &&
> + i_projid != EXT4_DEF_PROJID);
> + if (i_projid != EXT4_DEF_PROJID &&
> + (EXT4_INODE_SIZE(inode->i_sb) <= EXT4_GOOD_OLD_INODE_SIZE ||
> + (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)))) {
> + spin_unlock(&ei->i_raw_lock);
> + err = -EFBIG;
> + goto out_brelse;
> + }
> + raw_inode->i_projid = cpu_to_le32(i_projid);
> +
> ext4_inode_csum_set(inode, raw_inode, ei);
>
> spin_unlock(&ei->i_raw_lock);
> diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
> index 4262118..160a743 100644
> --- a/fs/ext4/namei.c
> +++ b/fs/ext4/namei.c
> @@ -2939,6 +2939,11 @@ static int ext4_link(struct dentry *old_dentry,
> if (inode->i_nlink >= EXT4_LINK_MAX)
> return -EMLINK;
>
> + if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) &&
> + (!projid_eq(EXT4_I(dir)->i_projid,
> + EXT4_I(old_dentry->d_inode)->i_projid)))
> + return -EXDEV;
> +
> dquot_initialize(dir);
>
> retry:
> @@ -3218,6 +3223,11 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
> int credits;
> u8 old_file_type;
>
> + if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT)) &&
> + (!projid_eq(EXT4_I(new_dir)->i_projid,
> + EXT4_I(old_dentry->d_inode)->i_projid)))
> + return -EXDEV;
> +
> dquot_initialize(old.dir);
> dquot_initialize(new.dir);
>
> @@ -3396,6 +3406,13 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
> u8 new_file_type;
> int retval;
>
> + if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT)) &&
> + ((!projid_eq(EXT4_I(new_dir)->i_projid,
> + EXT4_I(old_dentry->d_inode)->i_projid)) ||
> + (!projid_eq(EXT4_I(old_dir)->i_projid,
> + EXT4_I(new_dentry->d_inode)->i_projid))))
> + return -EXDEV;
> +
> dquot_initialize(old.dir);
> dquot_initialize(new.dir);
>
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index 2c9e686..d8a348d 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -1077,6 +1077,7 @@ static const struct dquot_operations ext4_quota_operations = {
> .write_info = ext4_write_info,
> .alloc_dquot = dquot_alloc,
> .destroy_dquot = dquot_destroy,
> + .get_projid = ext4_get_projid,
> };
>
> static const struct quotactl_ops ext4_qctl_operations = {
> --
> 1.7.1
>
--
Jan Kara <jack@suse.cz>
SUSE Labs, CR
^ permalink raw reply
* [PATCH v2 19/19] selftests/user: add install target to enable installing test
From: Shuah Khan @ 2014-11-11 20:27 UTC (permalink / raw)
To: gregkh, akpm, mmarek, davem, keescook, tranmanphong, dh.herrmann,
hughd, bobby.prani, ebiederm, serge.hallyn
Cc: Shuah Khan, linux-kbuild, linux-kernel, linux-api, netdev
In-Reply-To: <cover.1415735831.git.shuahkh@osg.samsung.com>
Add a new make target to enable installing test. This target
installs test in the kselftest install location and add to the
kselftest script to run the test. Install target can be run
only from top level source dir.
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
tools/testing/selftests/user/Makefile | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/user/Makefile b/tools/testing/selftests/user/Makefile
index 12c9d15..b62962a 100644
--- a/tools/testing/selftests/user/Makefile
+++ b/tools/testing/selftests/user/Makefile
@@ -1,7 +1,20 @@
# Makefile for user memory selftests
+TEST_STR = ./test_user_copy.sh
+
# No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
all:
+install:
+ifdef INSTALL_KSFT_PATH
+ install ./test_user_copy.sh $(INSTALL_KSFT_PATH)
+ @echo echo Start user copy test .... >> $(KSELFTEST)
+ @echo "$(TEST_STR)" >> $(KSELFTEST)
+ @echo echo End user copy test .... >> $(KSELFTEST)
+ @echo echo ============================== >> $(KSELFTEST)
+else
+ @echo Run make kselftest_install in top level source directory
+endif
+
run_tests: all
- ./test_user_copy.sh
+ @$(TEST_STR)
--
1.9.1
^ permalink raw reply related
* [PATCH v2 18/19] selftests/vm: add install target to enable installing test
From: Shuah Khan @ 2014-11-11 20:27 UTC (permalink / raw)
To: gregkh, akpm, mmarek, davem, keescook, tranmanphong, dh.herrmann,
hughd, bobby.prani, ebiederm, serge.hallyn
Cc: Shuah Khan, linux-kbuild, linux-kernel, linux-api, netdev
In-Reply-To: <cover.1415735831.git.shuahkh@osg.samsung.com>
Add a new make target to enable installing test. This target
installs test in the kselftest install location and add to the
kselftest script to run the test. Install target can be run
only from top level source dir.
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
tools/testing/selftests/vm/Makefile | 14 +++++++++++++-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 4c4b1f6..7fbe551 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -4,13 +4,25 @@ CC = $(CROSS_COMPILE)gcc
CFLAGS = -Wall
BINARIES = hugepage-mmap hugepage-shm map_hugetlb thuge-gen hugetlbfstest
BINARIES += transhuge-stress
+TEST_STR = /bin/sh ./run_vmtests || echo vmtests: [FAIL]
all: $(BINARIES)
%: %.c
$(CC) $(CFLAGS) -o $@ $^
+install:
+ifdef INSTALL_KSFT_PATH
+ install run_vmtests $(BINARIES) $(INSTALL_KSFT_PATH)
+ @echo echo Start vm test .... >> $(KSELFTEST)
+ @echo "$(TEST_STR)" >> $(KSELFTEST)
+ @echo echo End vm test .... >> $(KSELFTEST)
+ @echo echo ============================== >> $(KSELFTEST)
+else
+ @echo Run make kselftest_install in top level source directory
+endif
+
run_tests: all
- @/bin/sh ./run_vmtests || (echo "vmtests: [FAIL]"; exit 1)
+ @$(TEST_STR)
clean:
$(RM) $(BINARIES)
--
1.9.1
^ permalink raw reply related
* [PATCH v2 17/19] selftests/timers: add install target to enable installing test
From: Shuah Khan @ 2014-11-11 20:27 UTC (permalink / raw)
To: gregkh, akpm, mmarek, davem, keescook, tranmanphong, dh.herrmann,
hughd, bobby.prani, ebiederm, serge.hallyn
Cc: Shuah Khan, linux-kbuild, linux-kernel, linux-api, netdev
In-Reply-To: <cover.1415735831.git.shuahkh@osg.samsung.com>
Add a new make target to enable installing test. This target
installs test in the kselftest install location and add to the
kselftest script to run the test. Install target can be run
only from top level source dir.
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
tools/testing/selftests/timers/Makefile | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index eb2859f..0c3c67b 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -1,8 +1,21 @@
+TEST_STR = ./posix_timers
+
all:
gcc posix_timers.c -o posix_timers -lrt
+install:
+ifdef INSTALL_KSFT_PATH
+ install ./posix_timers $(INSTALL_KSFT_PATH)
+ @echo echo Start timers test .... >> $(KSELFTEST)
+ @echo "$(TEST_STR)" >> $(KSELFTEST)
+ @echo echo End timers test .... >> $(KSELFTEST)
+ @echo echo ============================== >> $(KSELFTEST)
+else
+ @echo Run make kselftest_install in top level source directory
+endif
+
run_tests: all
- ./posix_timers
+ @$(TEST_STR)
clean:
rm -f ./posix_timers
--
1.9.1
^ permalink raw reply related
* [PATCH v2 16/19] selftests/sysctl: add install target to enable installing test
From: Shuah Khan @ 2014-11-11 20:27 UTC (permalink / raw)
To: gregkh, akpm, mmarek, davem, keescook, tranmanphong, dh.herrmann,
hughd, bobby.prani, ebiederm, serge.hallyn
Cc: Shuah Khan, linux-kbuild, linux-kernel, linux-api, netdev
In-Reply-To: <cover.1415735831.git.shuahkh@osg.samsung.com>
Add a new make target to enable installing test. This target
installs test in the kselftest install location and add to the
kselftest script to run the test. Install target can be run
only from top level source dir.
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
tools/testing/selftests/sysctl/Makefile | 23 +++++++++++++++++++++--
1 file changed, 21 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/sysctl/Makefile b/tools/testing/selftests/sysctl/Makefile
index 0a92ada..34cca1b 100644
--- a/tools/testing/selftests/sysctl/Makefile
+++ b/tools/testing/selftests/sysctl/Makefile
@@ -4,12 +4,31 @@
# No binaries, but make sure arg-less "make" doesn't trigger "run_tests".
all:
+INSTALL_PROGS = common_tests run_numerictests run_stringtests
+NUMERIC_TEST_STR = /bin/sh ./run_numerictests
+STRING_TEST_STR = /bin/sh ./run_stringtests
+
# Allow specific tests to be selected.
test_num:
- @/bin/sh ./run_numerictests
+ @$(NUMERIC_TEST_STR)
test_string:
- @/bin/sh ./run_stringtests
+ @$(STRING_TEST_STR)
+
+install: all
+ifdef INSTALL_KSFT_PATH
+ install $(INSTALL_PROGS) $(INSTALL_KSFT_PATH)
+ @echo echo Start sysctl numeric tests .... >> $(KSELFTEST)
+ @echo "$(NUMERIC_TEST_STR)" >> $(KSELFTEST)
+ @echo echo End sysctl numeric tests .... >> $(KSELFTEST)
+ @echo echo -------------------- >> $(KSELFTEST)
+ @echo echo Start sysctl string tests .... >> $(KSELFTEST)
+ @echo "$(STRING_TEST_STR)" >> $(KSELFTEST)
+ @echo echo End sysctl string test .... >> $(KSELFTEST)
+ @echo echo ============================== >> $(KSELFTEST)
+else
+ @echo Run make kselftest_install in top level source directory
+endif
run_tests: all test_num test_string
--
1.9.1
^ permalink raw reply related
* [PATCH v2 15/19] selftests/ptrace: add install target to enable installing test
From: Shuah Khan @ 2014-11-11 20:27 UTC (permalink / raw)
To: gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b, mmarek-AlSwsSmVLrQ,
davem-fT/PcQaiUtIeIZ0/mPfg9Q, keescook-F7+t8E8rja9g9hUCZPvPmw,
tranmanphong-Re5JQEeQqe8AvxtiuMwx3w,
dh.herrmann-Re5JQEeQqe8AvxtiuMwx3w, hughd-hpIqsD4AKlfQT0dZR+AlfA,
bobby.prani-Re5JQEeQqe8AvxtiuMwx3w,
ebiederm-aS9lmoZGLiVWk0Htik3J/w,
serge.hallyn-GeWIH/nMZzLQT0dZR+AlfA
Cc: Shuah Khan, linux-kbuild-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <cover.1415735831.git.shuahkh-JPH+aEBZ4P+UEJcrhfAQsw@public.gmane.org>
Add a new make target to enable installing test. This target
installs test in the kselftest install location and add to the
kselftest script to run the test. Install target can be run
only from top level source dir.
Signed-off-by: Shuah Khan <shuahkh-JPH+aEBZ4P+UEJcrhfAQsw@public.gmane.org>
---
tools/testing/selftests/ptrace/Makefile | 19 ++++++++++++++++---
1 file changed, 16 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile
index 47ae2d3..9ef3c4b 100644
--- a/tools/testing/selftests/ptrace/Makefile
+++ b/tools/testing/selftests/ptrace/Makefile
@@ -1,10 +1,23 @@
CFLAGS += -iquote../../../../include/uapi -Wall
-peeksiginfo: peeksiginfo.c
-all: peeksiginfo
+TEST_STR = ./peeksiginfo || echo peeksiginfo selftests: [FAIL]
+
+all:
+ gcc peeksiginfo.c -o peeksiginfo
+
+install:
+ifdef INSTALL_KSFT_PATH
+ install ./peeksiginfo $(INSTALL_KSFT_PATH)
+ @echo echo Start ptrace test .... >> $(KSELFTEST)
+ @echo "$(TEST_STR)" >> $(KSELFTEST)
+ @echo echo End ptrace test .... >> $(KSELFTEST)
+ @echo echo ============================== >> $(KSELFTEST)
+else
+ @echo Run make kselftest_install in top level source directory
+endif
clean:
rm -f peeksiginfo
run_tests: all
- @./peeksiginfo || echo "peeksiginfo selftests: [FAIL]"
+ @$(TEST_STR)
--
1.9.1
^ permalink raw reply related
* [PATCH v2 14/19] selftests/net: add install target to enable installing test
From: Shuah Khan @ 2014-11-11 20:27 UTC (permalink / raw)
To: gregkh, akpm, mmarek, davem, keescook, tranmanphong, dh.herrmann,
hughd, bobby.prani, ebiederm, serge.hallyn
Cc: Shuah Khan, linux-kbuild, linux-kernel, linux-api, netdev
In-Reply-To: <cover.1415735831.git.shuahkh@osg.samsung.com>
Add a new make target to enable installing test. This target
installs test in the kselftest install location and add to the
kselftest script to run the test. Install target can be run
only from top level source dir.
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
tools/testing/selftests/net/Makefile | 23 ++++++++++++++++++++---
1 file changed, 20 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 62f22cc..16550eb 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -6,14 +6,31 @@ CFLAGS = -Wall -O2 -g
CFLAGS += -I../../../../usr/include/
NET_PROGS = socket psock_fanout psock_tpacket
+INSTALL_PROGS = run_netsocktests run_afpackettests test_bpf.sh $(NET_PROGS)
+NETSOCK_TEST_STR = /bin/sh ./run_netsocktests || echo sockettests: [FAIL]
+AFPKT_TEST_STR = /bin/sh ./run_afpackettests || echo afpackettests: [FAIL]
+BFP_TEST_STR = ./test_bpf.sh
all: $(NET_PROGS)
%: %.c
$(CC) $(CFLAGS) -o $@ $^
+install:
+ifdef INSTALL_KSFT_PATH
+ install $(INSTALL_PROGS) $(INSTALL_KSFT_PATH)
+ @echo echo Start net test .... >> $(KSELFTEST)
+ @echo "$(NETSOCK_TEST_STR)" >> $(KSELFTEST)
+ @echo "$(AFPKT_TEST_STR)" >> $(KSELFTEST)
+ @echo "$(BFP_TEST_STR)" >> $(KSELFTEST)
+ @echo echo End net test .... >> $(KSELFTEST)
+ @echo echo ============================== >> $(KSELFTEST)
+else
+ @echo Run make kselftest_install in top level source directory
+endif
+
run_tests: all
- @/bin/sh ./run_netsocktests || echo "sockettests: [FAIL]"
- @/bin/sh ./run_afpackettests || echo "afpackettests: [FAIL]"
- ./test_bpf.sh
+ @$(NETSOCK_TEST_STR)
+ @$(AFPKT_TEST_STR)
+ @$(BFP_TEST_STR)
clean:
$(RM) $(NET_PROGS)
--
1.9.1
^ permalink raw reply related
* Re: [v6 1/4] vfs: adds general codes to enforces project quota limits
From: Jan Kara @ 2014-11-11 20:27 UTC (permalink / raw)
To: Li Xi
Cc: linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-ext4-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, tytso-3s7WtUTddSA,
adilger-m1MBpc4rdrD3fQ9qLvQP4Q, jack-AlSwsSmVLrQ,
viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn, hch-wEGCiKHe2LqWVfeAwA7xHQ,
dmonakhov-GEFAQzZX7r8dnm+yROfE0A
In-Reply-To: <1415468619-31851-2-git-send-email-lixi-LfVdkaOWEx8@public.gmane.org>
On Sun 09-11-14 01:43:36, Li Xi wrote:
> This patch adds support for a new quota type PRJQUOTA for project quota
> enforcement. Also a new method get_projid() is added into dquot_operations
> structure.
The patch looks good. You can add:
Reviewed-by: Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>
Honza
> Signed-off-by: Li Xi <lixi-LfVdkaOWEx8@public.gmane.org>
> Signed-off-by: Dmitry Monakhov <dmonakhov-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
> ---
> fs/quota/dquot.c | 35 ++++++++++++++++++++++++++++++-----
> fs/quota/quota.c | 8 ++++++--
> fs/quota/quotaio_v2.h | 6 ++++--
> include/linux/quota.h | 2 ++
> include/uapi/linux/quota.h | 6 ++++--
> 5 files changed, 46 insertions(+), 11 deletions(-)
>
> diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
> index 8b663b2..84f9bb1 100644
> --- a/fs/quota/dquot.c
> +++ b/fs/quota/dquot.c
> @@ -1154,8 +1154,8 @@ static int need_print_warning(struct dquot_warn *warn)
> return uid_eq(current_fsuid(), warn->w_dq_id.uid);
> case GRPQUOTA:
> return in_group_p(warn->w_dq_id.gid);
> - case PRJQUOTA: /* Never taken... Just make gcc happy */
> - return 0;
> + case PRJQUOTA:
> + return 1;
> }
> return 0;
> }
> @@ -1394,6 +1394,9 @@ static void __dquot_initialize(struct inode *inode, int type)
> /* First get references to structures we might need. */
> for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
> struct kqid qid;
> + kprojid_t projid;
> + int rc;
> +
> got[cnt] = NULL;
> if (type != -1 && cnt != type)
> continue;
> @@ -1404,6 +1407,10 @@ static void __dquot_initialize(struct inode *inode, int type)
> */
> if (inode->i_dquot[cnt])
> continue;
> +
> + if (!sb_has_quota_active(sb, cnt))
> + continue;
> +
> init_needed = 1;
>
> switch (cnt) {
> @@ -1413,6 +1420,12 @@ static void __dquot_initialize(struct inode *inode, int type)
> case GRPQUOTA:
> qid = make_kqid_gid(inode->i_gid);
> break;
> + case PRJQUOTA:
> + rc = inode->i_sb->dq_op->get_projid(inode, &projid);
> + if (rc)
> + continue;
> + qid = make_kqid_projid(projid);
> + break;
> }
> got[cnt] = dqget(sb, qid);
> }
> @@ -2156,7 +2169,8 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
> error = -EROFS;
> goto out_fmt;
> }
> - if (!sb->s_op->quota_write || !sb->s_op->quota_read) {
> + if (!sb->s_op->quota_write || !sb->s_op->quota_read ||
> + (type == PRJQUOTA && sb->dq_op->get_projid == NULL)) {
> error = -EINVAL;
> goto out_fmt;
> }
> @@ -2397,8 +2411,19 @@ static void do_get_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
>
> memset(di, 0, sizeof(*di));
> di->d_version = FS_DQUOT_VERSION;
> - di->d_flags = dquot->dq_id.type == USRQUOTA ?
> - FS_USER_QUOTA : FS_GROUP_QUOTA;
> + switch (dquot->dq_id.type) {
> + case USRQUOTA:
> + di->d_flags = FS_USER_QUOTA;
> + break;
> + case GRPQUOTA:
> + di->d_flags = FS_GROUP_QUOTA;
> + break;
> + case PRJQUOTA:
> + di->d_flags = FS_PROJ_QUOTA;
> + break;
> + default:
> + BUG();
> + }
> di->d_id = from_kqid_munged(current_user_ns(), dquot->dq_id);
>
> spin_lock(&dq_data_lock);
> diff --git a/fs/quota/quota.c b/fs/quota/quota.c
> index 7562164..795d694 100644
> --- a/fs/quota/quota.c
> +++ b/fs/quota/quota.c
> @@ -30,11 +30,15 @@ static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
> case Q_XGETQSTATV:
> case Q_XQUOTASYNC:
> break;
> - /* allow to query information for dquots we "own" */
> + /*
> + * allow to query information for dquots we "own"
> + * always allow querying project quota
> + */
> case Q_GETQUOTA:
> case Q_XGETQUOTA:
> if ((type == USRQUOTA && uid_eq(current_euid(), make_kuid(current_user_ns(), id))) ||
> - (type == GRPQUOTA && in_egroup_p(make_kgid(current_user_ns(), id))))
> + (type == GRPQUOTA && in_egroup_p(make_kgid(current_user_ns(), id))) ||
> + (type == PRJQUOTA))
> break;
> /*FALLTHROUGH*/
> default:
> diff --git a/fs/quota/quotaio_v2.h b/fs/quota/quotaio_v2.h
> index f1966b4..4e95430 100644
> --- a/fs/quota/quotaio_v2.h
> +++ b/fs/quota/quotaio_v2.h
> @@ -13,12 +13,14 @@
> */
> #define V2_INITQMAGICS {\
> 0xd9c01f11, /* USRQUOTA */\
> - 0xd9c01927 /* GRPQUOTA */\
> + 0xd9c01927, /* GRPQUOTA */\
> + 0xd9c03f14, /* PRJQUOTA */\
> }
>
> #define V2_INITQVERSIONS {\
> 1, /* USRQUOTA */\
> - 1 /* GRPQUOTA */\
> + 1, /* GRPQUOTA */\
> + 1, /* PRJQUOTA */\
> }
>
> /* First generic header */
> diff --git a/include/linux/quota.h b/include/linux/quota.h
> index 80d345a..f1b25f8 100644
> --- a/include/linux/quota.h
> +++ b/include/linux/quota.h
> @@ -50,6 +50,7 @@
>
> #undef USRQUOTA
> #undef GRPQUOTA
> +#undef PRJQUOTA
> enum quota_type {
> USRQUOTA = 0, /* element used for user quotas */
> GRPQUOTA = 1, /* element used for group quotas */
> @@ -312,6 +313,7 @@ struct dquot_operations {
> /* get reserved quota for delayed alloc, value returned is managed by
> * quota code only */
> qsize_t *(*get_reserved_space) (struct inode *);
> + int (*get_projid) (struct inode *, kprojid_t *);/* Get project ID */
> };
>
> struct path;
> diff --git a/include/uapi/linux/quota.h b/include/uapi/linux/quota.h
> index 3b6cfbe..b2d9486 100644
> --- a/include/uapi/linux/quota.h
> +++ b/include/uapi/linux/quota.h
> @@ -36,11 +36,12 @@
> #include <linux/errno.h>
> #include <linux/types.h>
>
> -#define __DQUOT_VERSION__ "dquot_6.5.2"
> +#define __DQUOT_VERSION__ "dquot_6.6.0"
>
> -#define MAXQUOTAS 2
> +#define MAXQUOTAS 3
> #define USRQUOTA 0 /* element used for user quotas */
> #define GRPQUOTA 1 /* element used for group quotas */
> +#define PRJQUOTA 2 /* element used for project quotas */
>
> /*
> * Definitions for the default names of the quotas files.
> @@ -48,6 +49,7 @@
> #define INITQFNAMES { \
> "user", /* USRQUOTA */ \
> "group", /* GRPQUOTA */ \
> + "project", /* PRJQUOTA */ \
> "undefined", \
> };
>
> --
> 1.7.1
>
--
Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>
SUSE Labs, CR
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox