* [PATCH 04/12] crypto: atmel-ecc - simplify probe error handling
From: Lothar Rubusch @ 2026-05-17 18:06 UTC (permalink / raw)
To: thorsten.blum, herbert, davem, nicolas.ferre, alexandre.belloni,
claudiu.beznea
Cc: linux-crypto, linux-arm-kernel, linux-kernel, l.rubusch
In-Reply-To: <20260517180639.9657-1-l.rubusch@gmail.com>
Replace early return in atmel_ecc_probe() with explicit error handling
using a goto-based cleanup path.
Add comments to clarify client list insertion and algorithm registration
steps.
No functional change intended.
Signed-off-by: Lothar Rubusch <l.rubusch@gmail.com>
---
drivers/crypto/atmel-ecc.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index 76fb1d0cf075..696ab1d51fc6 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -328,17 +328,20 @@ static int atmel_ecc_probe(struct i2c_client *client)
ret = crypto_register_kpp(&atmel_ecdh_nist_p256);
if (ret) {
- spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
- list_del(&i2c_priv->i2c_client_list_node);
- spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
-
dev_err(&client->dev, "%s alg registration failed\n",
atmel_ecdh_nist_p256.base.cra_driver_name);
+ goto err_list_del;
} else {
dev_info(&client->dev, "atmel ecc algorithms registered in /proc/crypto\n");
}
return ret;
+
+err_list_del:
+ spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
+ list_del(&i2c_priv->i2c_client_list_node);
+ spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
+ return ret;
}
static void atmel_ecc_remove(struct i2c_client *client)
--
2.53.0
^ permalink raw reply related
* [PATCH 05/12] crypto: atmel - factor out i2c client unregistration helper
From: Lothar Rubusch @ 2026-05-17 18:06 UTC (permalink / raw)
To: thorsten.blum, herbert, davem, nicolas.ferre, alexandre.belloni,
claudiu.beznea
Cc: linux-crypto, linux-arm-kernel, linux-kernel, l.rubusch
In-Reply-To: <20260517180639.9657-1-l.rubusch@gmail.com>
Move the i2c client removal logic into a dedicated helper
atmel_i2c_unregister_client() in the atmel-i2c core.
Convert ECC driver remove path to use the new helper and
ensure queue flushing is performed after removing the device
from the shared client list.
Signed-off-by: Lothar Rubusch <l.rubusch@gmail.com>
---
drivers/crypto/atmel-ecc.c | 5 ++---
drivers/crypto/atmel-i2c.c | 9 +++++++++
drivers/crypto/atmel-i2c.h | 2 ++
3 files changed, 13 insertions(+), 3 deletions(-)
diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index 696ab1d51fc6..e5dd77008b97 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -364,9 +364,8 @@ static void atmel_ecc_remove(struct i2c_client *client)
crypto_unregister_kpp(&atmel_ecdh_nist_p256);
- spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
- list_del(&i2c_priv->i2c_client_list_node);
- spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
+ atmel_i2c_flush_queue();
+ atmel_i2c_unregister_client(i2c_priv);
}
static const struct of_device_id atmel_ecc_dt_ids[] = {
diff --git a/drivers/crypto/atmel-i2c.c b/drivers/crypto/atmel-i2c.c
index db24f65ae90e..861af52d7a88 100644
--- a/drivers/crypto/atmel-i2c.c
+++ b/drivers/crypto/atmel-i2c.c
@@ -354,6 +354,15 @@ static int device_sanity_check(struct i2c_client *client)
return ret;
}
+void atmel_i2c_unregister_client(struct atmel_i2c_client_priv *i2c_priv)
+{
+ spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
+ if (!list_empty(&i2c_priv->i2c_client_list_node))
+ list_del_init(&i2c_priv->i2c_client_list_node);
+ spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
+}
+EXPORT_SYMBOL(atmel_i2c_unregister_client);
+
int atmel_i2c_probe(struct i2c_client *client)
{
struct atmel_i2c_client_priv *i2c_priv;
diff --git a/drivers/crypto/atmel-i2c.h b/drivers/crypto/atmel-i2c.h
index a3385e8f0dc9..43a0c1cfcd94 100644
--- a/drivers/crypto/atmel-i2c.h
+++ b/drivers/crypto/atmel-i2c.h
@@ -190,4 +190,6 @@ void atmel_i2c_init_genkey_cmd(struct atmel_i2c_cmd *cmd, u16 keyid);
int atmel_i2c_init_ecdh_cmd(struct atmel_i2c_cmd *cmd,
struct scatterlist *pubkey);
+void atmel_i2c_unregister_client(struct atmel_i2c_client_priv *i2c_priv);
+
#endif /* __ATMEL_I2C_H__ */
--
2.53.0
^ permalink raw reply related
* [PATCH 08/12] crypto: atmel-ecc - switch to module_i2c_driver
From: Lothar Rubusch @ 2026-05-17 18:06 UTC (permalink / raw)
To: thorsten.blum, herbert, davem, nicolas.ferre, alexandre.belloni,
claudiu.beznea
Cc: linux-crypto, linux-arm-kernel, linux-kernel, l.rubusch
In-Reply-To: <20260517180639.9657-1-l.rubusch@gmail.com>
Replace custom module init/exit functions with module_i2c_driver() for
simplified driver registration.
Initialization of the shared I2C client management structure is handled by
the core driver and no longer performed in the ECC module init path.
Signed-off-by: Lothar Rubusch <l.rubusch@gmail.com>
---
drivers/crypto/atmel-ecc.c | 16 +---------------
1 file changed, 1 insertion(+), 15 deletions(-)
diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index e5dd77008b97..dcfc09d24497 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -392,21 +392,7 @@ static struct i2c_driver atmel_ecc_driver = {
.id_table = atmel_ecc_id,
};
-static int __init atmel_ecc_init(void)
-{
- spin_lock_init(&atmel_i2c_mgmt.i2c_list_lock);
- INIT_LIST_HEAD(&atmel_i2c_mgmt.i2c_client_list);
- return i2c_add_driver(&atmel_ecc_driver);
-}
-
-static void __exit atmel_ecc_exit(void)
-{
- atmel_i2c_flush_queue();
- i2c_del_driver(&atmel_ecc_driver);
-}
-
-module_init(atmel_ecc_init);
-module_exit(atmel_ecc_exit);
+module_i2c_driver(atmel_ecc_driver);
MODULE_AUTHOR("Tudor Ambarus");
MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver");
--
2.53.0
^ permalink raw reply related
* [PATCH 06/12] crypto: atmel-sha204a - add i2c hw client list and improve probe error handling
From: Lothar Rubusch @ 2026-05-17 18:06 UTC (permalink / raw)
To: thorsten.blum, herbert, davem, nicolas.ferre, alexandre.belloni,
claudiu.beznea
Cc: linux-crypto, linux-arm-kernel, linux-kernel, l.rubusch
In-Reply-To: <20260517180639.9657-1-l.rubusch@gmail.com>
Add registration of the SHA204A I2C client into the shared atmel_i2c client
management list during probe.
This allows the driver to participate in the common hardware selection
infrastructure used by Atmel crypto devices.
Improve error handling in atmel_sha204a_probe() by ensuring that partial
initialization (hwrng registration or sysfs creation) results in proper
cleanup of the client list entry.
No functional change intended beyond improved lifecycle handling.
Signed-off-by: Lothar Rubusch <l.rubusch@gmail.com>
---
drivers/crypto/atmel-sha204a.c | 20 ++++++++++++++++++--
1 file changed, 18 insertions(+), 2 deletions(-)
diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index 6e6ac4770416..cdfdcf2e43a7 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -173,6 +173,13 @@ static int atmel_sha204a_probe(struct i2c_client *client)
i2c_priv = i2c_get_clientdata(client);
+ /* add to client list */
+ spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
+ list_add_tail(&i2c_priv->i2c_client_list_node,
+ &atmel_i2c_mgmt.i2c_client_list);
+ spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
+
+ /* register rng */
memset(&i2c_priv->hwrng, 0, sizeof(i2c_priv->hwrng));
i2c_priv->hwrng.name = dev_name(&client->dev);
@@ -183,15 +190,24 @@ static int atmel_sha204a_probe(struct i2c_client *client)
i2c_priv->hwrng.quality = *quality;
ret = devm_hwrng_register(&client->dev, &i2c_priv->hwrng);
- if (ret)
+ if (ret) {
dev_warn(&client->dev, "failed to register RNG (%d)\n", ret);
+ goto err_list_del;
+ }
ret = sysfs_create_group(&client->dev.kobj, &atmel_sha204a_groups);
if (ret) {
dev_err(&client->dev, "failed to register sysfs entry\n");
- return ret;
+ goto err_list_del;
}
+ return ret;
+
+err_list_del:
+ spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
+ list_del(&i2c_priv->i2c_client_list_node);
+ spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
+
return ret;
}
--
2.53.0
^ permalink raw reply related
* [PATCH 07/12] crypto: atmel-sha204a - switch to module_i2c_driver
From: Lothar Rubusch @ 2026-05-17 18:06 UTC (permalink / raw)
To: thorsten.blum, herbert, davem, nicolas.ferre, alexandre.belloni,
claudiu.beznea
Cc: linux-crypto, linux-arm-kernel, linux-kernel, l.rubusch
In-Reply-To: <20260517180639.9657-1-l.rubusch@gmail.com>
Replace custom module init/exit functions with module_i2c_driver() for
driver registration.
Update remove path to unregister the client from the shared I2C management
list before flushing pending work and cleaning up sysfs and hwrng
resources.
No functional change intended.
Signed-off-by: Lothar Rubusch <l.rubusch@gmail.com>
---
drivers/crypto/atmel-sha204a.c | 16 +++-------------
1 file changed, 3 insertions(+), 13 deletions(-)
diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index cdfdcf2e43a7..613ed5e7b3f6 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -216,6 +216,8 @@ static void atmel_sha204a_remove(struct i2c_client *client)
struct atmel_i2c_client_priv *i2c_priv = i2c_get_clientdata(client);
devm_hwrng_unregister(&client->dev, &i2c_priv->hwrng);
+
+ atmel_i2c_unregister_client(i2c_priv);
atmel_i2c_flush_queue();
sysfs_remove_group(&client->dev.kobj, &atmel_sha204a_groups);
@@ -246,19 +248,7 @@ static struct i2c_driver atmel_sha204a_driver = {
.driver.of_match_table = atmel_sha204a_dt_ids,
};
-static int __init atmel_sha204a_init(void)
-{
- return i2c_add_driver(&atmel_sha204a_driver);
-}
-
-static void __exit atmel_sha204a_exit(void)
-{
- atmel_i2c_flush_queue();
- i2c_del_driver(&atmel_sha204a_driver);
-}
-
-module_init(atmel_sha204a_init);
-module_exit(atmel_sha204a_exit);
+module_i2c_driver(atmel_sha204a_driver);
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_DESCRIPTION("Microchip / Atmel SHA204A (I2C) driver");
--
2.53.0
^ permalink raw reply related
* [PATCH 09/12] crypto: atmel-ecc - simplify remove path and relax busy handling
From: Lothar Rubusch @ 2026-05-17 18:06 UTC (permalink / raw)
To: thorsten.blum, herbert, davem, nicolas.ferre, alexandre.belloni,
claudiu.beznea
Cc: linux-crypto, linux-arm-kernel, linux-kernel, l.rubusch
In-Reply-To: <20260517180639.9657-1-l.rubusch@gmail.com>
Simplify atmel_ecc_remove() by removing early exit logic and
centralizing client retrieval and validation.
Previously the driver returned early when active transform users
were detected, which could leave partially initialized state
without proper cleanup.
Replace this with a warning when active transforms are present,
but continue with full teardown of crypto registration and
device cleanup.
This ensures consistent removal behaviour even when the device
is still in use.
Signed-off-by: Lothar Rubusch <l.rubusch@gmail.com>
---
drivers/crypto/atmel-ecc.c | 19 ++++++-------------
1 file changed, 6 insertions(+), 13 deletions(-)
diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index dcfc09d24497..ce7a2e750ba8 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -346,21 +346,14 @@ static int atmel_ecc_probe(struct i2c_client *client)
static void atmel_ecc_remove(struct i2c_client *client)
{
- struct atmel_i2c_client_priv *i2c_priv = i2c_get_clientdata(client);
+ struct atmel_i2c_client_priv *i2c_priv;
- /* Return EBUSY if i2c client already allocated. */
- if (atomic_read(&i2c_priv->tfm_count)) {
- /*
- * After we return here, the memory backing the device is freed.
- * That happens no matter what the return value of this function
- * is because in the Linux device model there is no error
- * handling for unbinding a driver.
- * If there is still some action pending, it probably involves
- * accessing the freed memory.
- */
- dev_emerg(&client->dev, "Device is busy, expect memory corruption.\n");
+ i2c_priv = i2c_get_clientdata(client);
+ if (WARN_ON(!i2c_priv))
return;
- }
+
+ if (atomic_read(&i2c_priv->tfm_count))
+ dev_warn(&client->dev, "Device is busy, remove it anyhow\n");
crypto_unregister_kpp(&atmel_ecdh_nist_p256);
--
2.53.0
^ permalink raw reply related
* [PATCH 10/12] crypto: atmel-sha204a - guard remove path against missing client data
From: Lothar Rubusch @ 2026-05-17 18:06 UTC (permalink / raw)
To: thorsten.blum, herbert, davem, nicolas.ferre, alexandre.belloni,
claudiu.beznea
Cc: linux-crypto, linux-arm-kernel, linux-kernel, l.rubusch
In-Reply-To: <20260517180639.9657-1-l.rubusch@gmail.com>
Retrieve the I2C client private data in atmel_sha204a_remove() only
after sysfs cleanup and add a NULL check before continuing device
teardown.
This prevents dereferencing invalid or partially initialized client
state during driver removal and makes the teardown path more robust
against inconsistent probe/remove sequences.
No functional change intended.
Signed-off-by: Lothar Rubusch <l.rubusch@gmail.com>
---
drivers/crypto/atmel-sha204a.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index 613ed5e7b3f6..923e462ff6b0 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -213,7 +213,11 @@ static int atmel_sha204a_probe(struct i2c_client *client)
static void atmel_sha204a_remove(struct i2c_client *client)
{
- struct atmel_i2c_client_priv *i2c_priv = i2c_get_clientdata(client);
+ struct atmel_i2c_client_priv *i2c_priv;
+
+ i2c_priv = i2c_get_clientdata(client);
+ if (WARN_ON(!i2c_priv))
+ return;
devm_hwrng_unregister(&client->dev, &i2c_priv->hwrng);
--
2.53.0
^ permalink raw reply related
* [PATCH 11/12] crypto: atmel - move i2c client selection to core driver
From: Lothar Rubusch @ 2026-05-17 18:06 UTC (permalink / raw)
To: thorsten.blum, herbert, davem, nicolas.ferre, alexandre.belloni,
claudiu.beznea
Cc: linux-crypto, linux-arm-kernel, linux-kernel, l.rubusch
In-Reply-To: <20260517180639.9657-1-l.rubusch@gmail.com>
Move the I2C client selection/allocation logic from the ECC-specific driver
into the shared Atmel I2C core.
This consolidates hardware client selection in a single place, allowing all
Atmel crypto drivers to reuse the same balancing logic for selecting the
least-loaded I2C client based on the current transformation count.
No functional change is intended.
Signed-off-by: Lothar Rubusch <l.rubusch@gmail.com>
---
drivers/crypto/atmel-ecc.c | 37 +------------------------------------
drivers/crypto/atmel-i2c.c | 36 ++++++++++++++++++++++++++++++++++++
drivers/crypto/atmel-i2c.h | 1 +
3 files changed, 38 insertions(+), 36 deletions(-)
diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index ce7a2e750ba8..f877f236552f 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -200,41 +200,6 @@ static int atmel_ecdh_compute_shared_secret(struct kpp_request *req)
return ret;
}
-static struct i2c_client *atmel_ecc_i2c_client_alloc(void)
-{
- struct atmel_i2c_client_priv *i2c_priv, *min_i2c_priv = NULL;
- struct i2c_client *client = ERR_PTR(-ENODEV);
- int min_tfm_cnt = INT_MAX;
- int tfm_cnt;
-
- spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
-
- if (list_empty(&atmel_i2c_mgmt.i2c_client_list)) {
- spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
- return ERR_PTR(-ENODEV);
- }
-
- list_for_each_entry(i2c_priv, &atmel_i2c_mgmt.i2c_client_list,
- i2c_client_list_node) {
- tfm_cnt = atomic_read(&i2c_priv->tfm_count);
- if (tfm_cnt < min_tfm_cnt) {
- min_tfm_cnt = tfm_cnt;
- min_i2c_priv = i2c_priv;
- }
- if (!min_tfm_cnt)
- break;
- }
-
- if (min_i2c_priv) {
- atomic_inc(&min_i2c_priv->tfm_count);
- client = min_i2c_priv->client;
- }
-
- spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
-
- return client;
-}
-
static void atmel_ecc_i2c_client_free(struct i2c_client *client)
{
struct atmel_i2c_client_priv *i2c_priv = i2c_get_clientdata(client);
@@ -249,7 +214,7 @@ static int atmel_ecdh_init_tfm(struct crypto_kpp *tfm)
struct atmel_ecdh_ctx *ctx = kpp_tfm_ctx(tfm);
ctx->curve_id = ECC_CURVE_NIST_P256;
- ctx->client = atmel_ecc_i2c_client_alloc();
+ ctx->client = atmel_i2c_client_alloc();
if (IS_ERR(ctx->client)) {
pr_err("tfm - i2c_client binding failed\n");
return PTR_ERR(ctx->client);
diff --git a/drivers/crypto/atmel-i2c.c b/drivers/crypto/atmel-i2c.c
index 861af52d7a88..4beab68997c4 100644
--- a/drivers/crypto/atmel-i2c.c
+++ b/drivers/crypto/atmel-i2c.c
@@ -57,6 +57,42 @@ static void atmel_i2c_checksum(struct atmel_i2c_cmd *cmd)
*__crc16 = cpu_to_le16(bitrev16(crc16(0, data, len)));
}
+struct i2c_client *atmel_i2c_client_alloc(void)
+{
+ struct atmel_i2c_client_priv *i2c_priv, *min_i2c_priv = NULL;
+ struct i2c_client *client = ERR_PTR(-ENODEV);
+ int min_tfm_cnt = INT_MAX;
+ int tfm_cnt;
+
+ spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
+
+ if (list_empty(&atmel_i2c_mgmt.i2c_client_list)) {
+ spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
+ return ERR_PTR(-ENODEV);
+ }
+
+ list_for_each_entry(i2c_priv, &atmel_i2c_mgmt.i2c_client_list,
+ i2c_client_list_node) {
+ tfm_cnt = atomic_read(&i2c_priv->tfm_count);
+ if (tfm_cnt < min_tfm_cnt) {
+ min_tfm_cnt = tfm_cnt;
+ min_i2c_priv = i2c_priv;
+ }
+ if (!min_tfm_cnt)
+ break;
+ }
+
+ if (min_i2c_priv) {
+ atomic_inc(&min_i2c_priv->tfm_count);
+ client = min_i2c_priv->client;
+ }
+
+ spin_unlock(&atmel_i2c_mgmt.i2c_list_lock);
+
+ return client;
+}
+EXPORT_SYMBOL(atmel_i2c_client_alloc);
+
void atmel_i2c_init_read_config_cmd(struct atmel_i2c_cmd *cmd)
{
cmd->word_addr = COMMAND;
diff --git a/drivers/crypto/atmel-i2c.h b/drivers/crypto/atmel-i2c.h
index 43a0c1cfcd94..ba5a860011c8 100644
--- a/drivers/crypto/atmel-i2c.h
+++ b/drivers/crypto/atmel-i2c.h
@@ -190,6 +190,7 @@ void atmel_i2c_init_genkey_cmd(struct atmel_i2c_cmd *cmd, u16 keyid);
int atmel_i2c_init_ecdh_cmd(struct atmel_i2c_cmd *cmd,
struct scatterlist *pubkey);
+struct i2c_client *atmel_i2c_client_alloc(void);
void atmel_i2c_unregister_client(struct atmel_i2c_client_priv *i2c_priv);
#endif /* __ATMEL_I2C_H__ */
--
2.53.0
^ permalink raw reply related
* [PATCH 12/12] crypto: atmel - add capability-based I2C client selection
From: Lothar Rubusch @ 2026-05-17 18:06 UTC (permalink / raw)
To: thorsten.blum, herbert, davem, nicolas.ferre, alexandre.belloni,
claudiu.beznea
Cc: linux-crypto, linux-arm-kernel, linux-kernel, l.rubusch
In-Reply-To: <20260517180639.9657-1-l.rubusch@gmail.com>
Add capability filtering to the I2C client allocator to support
feature-aware selection of hardware clients.
Each client now exposes supported features via a capability mask. The
allocator selects only clients matching the requested capability and still
prefers the least-loaded device.
ECC marks ECDH support during probe and requests matching clients during
tfm setup. SHA204A exposes no capabilities for now.
This is preparatory work for upcoming features that will extend hardware
usage beyond a single algorithm type.
Signed-off-by: Lothar Rubusch <l.rubusch@gmail.com>
---
drivers/crypto/atmel-ecc.c | 4 +++-
drivers/crypto/atmel-i2c.c | 5 ++++-
drivers/crypto/atmel-i2c.h | 8 +++++++-
drivers/crypto/atmel-sha204a.c | 2 ++
4 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index f877f236552f..0eeee9ae6c48 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -214,7 +214,7 @@ static int atmel_ecdh_init_tfm(struct crypto_kpp *tfm)
struct atmel_ecdh_ctx *ctx = kpp_tfm_ctx(tfm);
ctx->curve_id = ECC_CURVE_NIST_P256;
- ctx->client = atmel_i2c_client_alloc();
+ ctx->client = atmel_i2c_client_alloc(ATMEL_CAP_ECDH);
if (IS_ERR(ctx->client)) {
pr_err("tfm - i2c_client binding failed\n");
return PTR_ERR(ctx->client);
@@ -286,6 +286,8 @@ static int atmel_ecc_probe(struct i2c_client *client)
i2c_priv = i2c_get_clientdata(client);
+ i2c_priv->caps = BIT(ATMEL_CAP_ECDH);
+
spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
list_add_tail(&i2c_priv->i2c_client_list_node,
&atmel_i2c_mgmt.i2c_client_list);
diff --git a/drivers/crypto/atmel-i2c.c b/drivers/crypto/atmel-i2c.c
index 4beab68997c4..b7ee2ec37531 100644
--- a/drivers/crypto/atmel-i2c.c
+++ b/drivers/crypto/atmel-i2c.c
@@ -57,7 +57,7 @@ static void atmel_i2c_checksum(struct atmel_i2c_cmd *cmd)
*__crc16 = cpu_to_le16(bitrev16(crc16(0, data, len)));
}
-struct i2c_client *atmel_i2c_client_alloc(void)
+struct i2c_client *atmel_i2c_client_alloc(enum atmel_i2c_capability cap)
{
struct atmel_i2c_client_priv *i2c_priv, *min_i2c_priv = NULL;
struct i2c_client *client = ERR_PTR(-ENODEV);
@@ -73,6 +73,9 @@ struct i2c_client *atmel_i2c_client_alloc(void)
list_for_each_entry(i2c_priv, &atmel_i2c_mgmt.i2c_client_list,
i2c_client_list_node) {
+ if (!(i2c_priv->caps & BIT(cap)))
+ continue;
+
tfm_cnt = atomic_read(&i2c_priv->tfm_count);
if (tfm_cnt < min_tfm_cnt) {
min_tfm_cnt = tfm_cnt;
diff --git a/drivers/crypto/atmel-i2c.h b/drivers/crypto/atmel-i2c.h
index ba5a860011c8..70579b438256 100644
--- a/drivers/crypto/atmel-i2c.h
+++ b/drivers/crypto/atmel-i2c.h
@@ -115,6 +115,10 @@ struct atmel_i2c_cmd {
#define ECDH_PREFIX_MODE 0x00
/* Used for binding tfm objects to i2c clients. */
+enum atmel_i2c_capability {
+ ATMEL_CAP_ECDH = 0,
+};
+
struct atmel_i2c_client_mgmt {
struct list_head i2c_client_list;
spinlock_t i2c_list_lock;
@@ -130,6 +134,7 @@ extern struct atmel_i2c_client_mgmt atmel_i2c_mgmt;
* @wake_token_sz : size in bytes of the wake_token
* @tfm_count : number of active crypto transformations on i2c client
* @hwrng : hold the hardware generated rng
+ * @caps : feature capability of the particular driver
*
* Reads and writes from/to the i2c client are sequential. The first byte
* transmitted to the device is treated as the byte size. Any attempt to send
@@ -146,6 +151,7 @@ struct atmel_i2c_client_priv {
size_t wake_token_sz;
atomic_t tfm_count ____cacheline_aligned;
struct hwrng hwrng;
+ u32 caps;
};
/**
@@ -190,7 +196,7 @@ void atmel_i2c_init_genkey_cmd(struct atmel_i2c_cmd *cmd, u16 keyid);
int atmel_i2c_init_ecdh_cmd(struct atmel_i2c_cmd *cmd,
struct scatterlist *pubkey);
-struct i2c_client *atmel_i2c_client_alloc(void);
+struct i2c_client *atmel_i2c_client_alloc(enum atmel_i2c_capability cap);
void atmel_i2c_unregister_client(struct atmel_i2c_client_priv *i2c_priv);
#endif /* __ATMEL_I2C_H__ */
diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index 923e462ff6b0..1a28c6434669 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -173,6 +173,8 @@ static int atmel_sha204a_probe(struct i2c_client *client)
i2c_priv = i2c_get_clientdata(client);
+ i2c_priv->caps = 0;
+
/* add to client list */
spin_lock(&atmel_i2c_mgmt.i2c_list_lock);
list_add_tail(&i2c_priv->i2c_client_list_node,
--
2.53.0
^ permalink raw reply related
* Re: [PATCH] treewide: replace /usr/bin/python3 shebangs with env python3
From: Dmitry Baryshkov @ 2026-05-17 18:13 UTC (permalink / raw)
To: Oli R
Cc: Rob Clark, Dmitry Baryshkov, Abhinav Kumar, Jessica Zhang,
Sean Paul, Marijn Suijten, David Airlie, Simona Vetter,
Mario Limonciello, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Mark Rutland,
Alexander Shishkin, Jiri Olsa, Ian Rogers, Adrian Hunter,
James Clark, Shuah Khan, Mathieu Desnoyers, Paul E. McKenney,
Boqun Feng, open list:DRM DRIVER for Qualcomm display hardware,
open list:DRM DRIVER for Qualcomm display hardware,
open list:DRM DRIVER for Qualcomm display hardware, open list,
open list:AMD CRYPTOGRAPHIC COPROCESSOR (CCP) DRIVER - DB...,
open list:PERFORMANCE EVENTS SUBSYSTEM,
open list:KERNEL SELFTEST FRAMEWORK
In-Reply-To: <20260515180806.246914-1-sigmatwojastara@gmail.com>
On Fri, May 15, 2026 at 08:07:59PM +0200, Oli R wrote:
> Use /usr/bin/env python3 instead of hardcoded interpreter paths
> to improve portability across environments where python3 is not
> installed in /usr/bin.
>
> No functional changes intended.
>
> Signed-off-by: Oli R <sigmatwojastara@gmail.com>
> ---
> drivers/gpu/drm/msm/registers/gen_header.py | 2 +-
Acked-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com> # drm/msm
> scripts/macro_checker.py | 2 +-
> tools/crypto/ccp/dbc.py | 2 +-
> tools/crypto/ccp/dbc_cli.py | 2 +-
> tools/crypto/ccp/test_dbc.py | 2 +-
> tools/perf/tests/shell/lib/perf_json_output_lint.py | 2 +-
> .../selftests/devices/probe/test_discoverable_devices.py | 2 +-
> tools/testing/selftests/rseq/rseq-slice-hist.py | 2 +-
> 8 files changed, 8 insertions(+), 8 deletions(-)
--
With best wishes
Dmitry
^ permalink raw reply
* Re: [PATCH 1/2] gpu: host1x: Allow entries in BO caches to be freed
From: Aaron Kling @ 2026-05-17 20:02 UTC (permalink / raw)
To: Mikko Perttunen
Cc: Thierry Reding, David Airlie, Simona Vetter, Jonathan Hunter,
Akhil R, Herbert Xu, David S. Miller, dri-devel, linux-tegra,
linux-kernel, linux-crypto
In-Reply-To: <20260515-host1x-bocache-leak-v1-1-a0375f68aeab@nvidia.com>
On Thu, May 14, 2026 at 9:35 PM Mikko Perttunen <mperttunen@nvidia.com> wrote:
>
> When a buffer object is pinned via host1x_bo_pin() with a cache, the
> resulting mapping is kept in the cache so it can be reused on subsequent
> pins. Each mapping held a reference to the underlying host1x_bo (taken
> in tegra_bo_pin / gather_bo_pin), so as long as a mapping was cached,
> the bo itself could not be freed.
>
> However, the only way to remove the cached mapping was through the free
> path of the buffer object. This meant that if a bo got cached, it could
> never get freed again.
>
> Resolve the circularity by holding a weak reference to the bo from the
> cache side. This is done by having the .pin callbacks not bump the bo's
> refcount -- instead the common Host1x bo code does so, except for the
> cache reference.
>
> Also move the remove-cache-mapping-on-free code into a common function
> inside Host1x code. This is only called from the TegraDRM GEM buffers
> since those are the only ones that can be cached at the moment.
>
> Reported-by: Aaron Kling <webgeek1234@gmail.com>
> Fixes: 1f39b1dfa53c ("drm/tegra: Implement buffer object cache")
> Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
> ---
> drivers/gpu/drm/tegra/gem.c | 13 ++-------
> drivers/gpu/drm/tegra/submit.c | 3 +--
> drivers/gpu/host1x/bus.c | 60 +++++++++++++++++++++++++++++++++++++++++-
> include/linux/host1x.h | 7 +++++
> 4 files changed, 69 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
> index d2bae88ad545..2377e2b76397 100644
> --- a/drivers/gpu/drm/tegra/gem.c
> +++ b/drivers/gpu/drm/tegra/gem.c
> @@ -69,7 +69,7 @@ static struct host1x_bo_mapping *tegra_bo_pin(struct device *dev, struct host1x_
> return ERR_PTR(-ENOMEM);
>
> kref_init(&map->ref);
> - map->bo = host1x_bo_get(bo);
> + map->bo = bo;
> map->direction = direction;
> map->dev = dev;
>
> @@ -170,7 +170,6 @@ static void tegra_bo_unpin(struct host1x_bo_mapping *map)
> kfree(map->sgt);
> }
>
> - host1x_bo_put(map->bo);
> kfree(map);
> }
>
> @@ -509,17 +508,9 @@ static struct tegra_bo *tegra_bo_import(struct drm_device *drm,
> void tegra_bo_free_object(struct drm_gem_object *gem)
> {
> struct tegra_drm *tegra = gem->dev->dev_private;
> - struct host1x_bo_mapping *mapping, *tmp;
> struct tegra_bo *bo = to_tegra_bo(gem);
>
> - /* remove all mappings of this buffer object from any caches */
> - list_for_each_entry_safe(mapping, tmp, &bo->base.mappings, list) {
> - if (mapping->cache)
> - host1x_bo_unpin(mapping);
> - else
> - dev_err(gem->dev->dev, "mapping %p stale for device %s\n", mapping,
> - dev_name(mapping->dev));
> - }
> + host1x_bo_clear_cached_mappings(&bo->base);
>
> if (tegra->domain) {
> tegra_bo_iommu_unmap(tegra, bo);
> diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c
> index 3009b8b9e619..e5841857c937 100644
> --- a/drivers/gpu/drm/tegra/submit.c
> +++ b/drivers/gpu/drm/tegra/submit.c
> @@ -76,7 +76,7 @@ gather_bo_pin(struct device *dev, struct host1x_bo *bo, enum dma_data_direction
> return ERR_PTR(-ENOMEM);
>
> kref_init(&map->ref);
> - map->bo = host1x_bo_get(bo);
> + map->bo = bo;
> map->direction = direction;
> map->dev = dev;
>
> @@ -117,7 +117,6 @@ static void gather_bo_unpin(struct host1x_bo_mapping *map)
> dma_unmap_sgtable(map->dev, map->sgt, map->direction, 0);
> sg_free_table(map->sgt);
> kfree(map->sgt);
> - host1x_bo_put(map->bo);
>
> kfree(map);
> }
> diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
> index f814eb4941c0..772e05a7b45b 100644
> --- a/drivers/gpu/host1x/bus.c
> +++ b/drivers/gpu/host1x/bus.c
> @@ -887,6 +887,20 @@ int host1x_client_resume(struct host1x_client *client)
> }
> EXPORT_SYMBOL(host1x_client_resume);
>
> +/**
> + * host1x_bo_pin() - Create a DMA mapping for the buffer object
> + * @dev: Device onto which DMA map to
> + * @bo: Buffer object to map
> + * @dir: DMA direction
> + * @cache: Cache in which to store mapping, or NULL
> + *
> + * Creates a DMA mapping pointing to @bo for @dev. The refcount of @bo is incremented
> + * until host1x_bo_unpin is called.
> + *
> + * If @cache is specified, the mapping is also stored in the cache and not released
> + * until @bo is freed (refcount drops to zero). This improves performance when a buffer
> + * is pinned and unpinned frequently as in the case of display use.
> + */
> struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo,
> enum dma_data_direction dir,
> struct host1x_bo_cache *cache)
> @@ -899,6 +913,7 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
> list_for_each_entry(mapping, &cache->mappings, entry) {
> if (mapping->bo == bo && mapping->direction == dir) {
> kref_get(&mapping->ref);
> + host1x_bo_get(bo);
> goto unlock;
> }
> }
> @@ -908,6 +923,8 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
> if (IS_ERR(mapping))
> goto unlock;
>
> + host1x_bo_get(bo);
> +
> spin_lock(&mapping->bo->lock);
> list_add_tail(&mapping->list, &bo->mappings);
> spin_unlock(&mapping->bo->lock);
> @@ -918,7 +935,12 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
>
> list_add_tail(&mapping->entry, &cache->mappings);
>
> - /* bump reference count to track the copy in the cache */
> + /*
> + * Bump the mapping reference count to track the mapping in the cache,
> + * but do not bump the BO's refcount. This allows the BO to still get freed,
> + * triggering the release of the cache mapping through
> + * host1x_bo_clear_cached_mappings.
> + */
> kref_get(&mapping->ref);
> }
>
> @@ -948,9 +970,17 @@ static void __host1x_bo_unpin(struct kref *ref)
> mapping->bo->ops->unpin(mapping);
> }
>
> +/**
> + * host1x_bo_unpin() - Release an established DMA mapping of a buffer object
> + * @mapping: Mapping to release
> + *
> + * Unmaps the given @mapping, unless it is cached. Decreases the refcount on
> + * the underlying buffer object.
> + */
> void host1x_bo_unpin(struct host1x_bo_mapping *mapping)
> {
> struct host1x_bo_cache *cache = mapping->cache;
> + struct host1x_bo *bo = mapping->bo;
>
> if (cache)
> mutex_lock(&cache->lock);
> @@ -959,5 +989,33 @@ void host1x_bo_unpin(struct host1x_bo_mapping *mapping)
>
> if (cache)
> mutex_unlock(&cache->lock);
> +
> + host1x_bo_put(bo);
> }
> EXPORT_SYMBOL(host1x_bo_unpin);
> +
> +/**
> + * host1x_bo_clear_cached_mappings() - Remove all cached mappings pointing at a bo
> + * @bo: Buffer object to release mappings of
> + *
> + * Drops references to any mappings pointing to @bo left in any caches. This must
> + * be called by any host1x_bo implementers that may be pinned with caching enabled
> + * before freeing the bo.
> + */
> +void host1x_bo_clear_cached_mappings(struct host1x_bo *bo)
> +{
> + struct host1x_bo_mapping *mapping, *tmp;
> + struct host1x_bo_cache *cache;
> +
> + list_for_each_entry_safe(mapping, tmp, &bo->mappings, list) {
> + cache = mapping->cache;
> + if (WARN_ON(!cache))
> + continue;
> +
> + mutex_lock(&mapping->cache->lock);
> + WARN_ON(kref_read(&mapping->ref) != 1);
> + __host1x_bo_unpin(&mapping->ref);
> + mutex_unlock(&mapping->cache->lock);
> + }
> +}
> +EXPORT_SYMBOL(host1x_bo_clear_cached_mappings);
> diff --git a/include/linux/host1x.h b/include/linux/host1x.h
> index 5e7a63143a4a..d8f052a85b75 100644
> --- a/include/linux/host1x.h
> +++ b/include/linux/host1x.h
> @@ -143,6 +143,12 @@ static inline struct host1x_bo_mapping *to_host1x_bo_mapping(struct kref *ref)
> return container_of(ref, struct host1x_bo_mapping, ref);
> }
>
> +/**
> + * struct host1x_bo_ops - operations implemented by a host1x_bo provider
> + *
> + * @pin: create a DMA mapping. Implementation must not touch the bo's refcount.
> + * @unpin: destroy a DMA mapping. Implementation must not touch the bo's refcount.
> + */
> struct host1x_bo_ops {
> struct host1x_bo *(*get)(struct host1x_bo *bo);
> void (*put)(struct host1x_bo *bo);
> @@ -181,6 +187,7 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
> enum dma_data_direction dir,
> struct host1x_bo_cache *cache);
> void host1x_bo_unpin(struct host1x_bo_mapping *map);
> +void host1x_bo_clear_cached_mappings(struct host1x_bo *bo);
>
> static inline void *host1x_bo_mmap(struct host1x_bo *bo)
> {
>
> --
> 2.53.0
>
I have verified this on a Jetson AGX Xavier devkit, a Jetson Xavier NX
devkit, a Jetson TX2 devkit, and a Jetson TX2 NX in a p3509 carrier.
No longer seeing allocation failures nor am I seeing any obvious
regressions. I am currently unable to boot any t210 device to Android
userspace to verify those for various preexisting reasons, and Android
recovery does not reallocate buffers to stress this issue.
Tested-by: Aaron Kling <webgeek1234@gmail.com>
Aaron
^ permalink raw reply
* Re: [PATCH 0/2] authencesn: Refactor in-place decryption
From: Herbert Xu @ 2026-05-18 2:33 UTC (permalink / raw)
To: Scott Guo; +Cc: davem, linux-crypto, Scott GUO
In-Reply-To: <8aaa00f3-d8e0-4de0-918b-1f025b632eb9@163.com>
On Fri, May 15, 2026 at 07:01:43PM +0800, Scott Guo wrote:
> Another thought: even with this fix, Fragnesia should still funciton. It
> just block current PoCs which pass in the page cache in the position for
> auth data.
>
> Avoid changing the auth part would not be enough because attacker would
> still be able to link a page cache page within the cryptlen part and
> override it with the 4 bytes from sequence number.
Exactly. The real fix is to not put read-only pages into the
destination scatterlist.
The whole point of a destination is that it will be written to.
Cheers,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH 0/2] authencesn: Refactor in-place decryption
From: Scott Guo @ 2026-05-18 2:55 UTC (permalink / raw)
To: Herbert Xu; +Cc: davem, linux-crypto, Scott GUO
In-Reply-To: <agp6lDddmDZaoH6L@gondor.apana.org.au>
BTW, I am wondering whether we should disable inplace decryption for
now? I think that to mitigate vulnerabilities like Fragnesia, maybe
something has to be done on the memory side. Maybe something like
forcing a pagefault when trying to write to these pages?
在 2026/5/18 10:33, Herbert Xu 写道:
> On Fri, May 15, 2026 at 07:01:43PM +0800, Scott Guo wrote:
>> Another thought: even with this fix, Fragnesia should still funciton. It
>> just block current PoCs which pass in the page cache in the position for
>> auth data.
>>
>> Avoid changing the auth part would not be enough because attacker would
>> still be able to link a page cache page within the cryptlen part and
>> override it with the 4 bytes from sequence number.
>
> Exactly. The real fix is to not put read-only pages into the
> destination scatterlist.
>
> The whole point of a destination is that it will be written to.
>
> Cheers,
^ permalink raw reply
* Re: [PATCH 0/2] authencesn: Refactor in-place decryption
From: Herbert Xu @ 2026-05-18 3:17 UTC (permalink / raw)
To: Scott Guo; +Cc: davem, linux-crypto, Scott GUO, netdev
In-Reply-To: <9f625d9d-6820-442e-9527-1b2802309993@163.com>
On Mon, May 18, 2026 at 10:55:38AM +0800, Scott Guo wrote:
> BTW, I am wondering whether we should disable inplace decryption for now? I
> think that to mitigate vulnerabilities like Fragnesia, maybe something has
> to be done on the memory side. Maybe something like forcing a pagefault when
> trying to write to these pages?
I think stopping ESP from putting frags into the dst SG list would
be prudent until the whole stack has been audited.
Alternatively switch from the black-list to a white-list approach
and only allow ESP to do in-place processing of packets from a
source that's known to be writable.
Cheers,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH v2] mfd: loongson-se: Add multi-node support
From: Qunqin Zhao @ 2026-05-18 3:17 UTC (permalink / raw)
To: Huacai Chen; +Cc: lee, linux-kernel, loongarch, linux-crypto, Xi Ruoyao
In-Reply-To: <CAAhV-H7SYoN49ZoFi+4V=qyctdzJG0hD=WUBBozewkQzKYia5w@mail.gmail.com>
在 2026/4/27 下午6:02, Huacai Chen 写道:
> On Mon, Apr 27, 2026 at 5:52 PM Qunqin Zhao <zhaoqunqin@loongson.cn> wrote:
>>
>> 在 2026/4/27 下午5:37, Huacai Chen 写道:
>>> On Mon, Apr 27, 2026 at 5:24 PM Qunqin Zhao <zhaoqunqin@loongson.cn> wrote:
>>>> 在 2026/4/27 下午5:02, Huacai Chen 写道:
>>>>> Hi, Qunqin,
>>>>>
>>>>> On Mon, Apr 27, 2026 at 4:55 PM Qunqin Zhao <zhaoqunqin@loongson.cn> wrote:
>>>>>> On the Loongson platform, each node is equipped with a security engine
>>>>>> device. However, due to a hardware flaw, only the device on node 0 can
>>>>>> trigger interrupts. Therefore, interrupts from other nodes are forwarded
>>>>>> by node 0. We need to check in the interrupt handler of node 0 whether
>>>>>> this interrupt is intended for other nodes.
>>>>> Multi-node or multi-package? In my opinion SE has no relationship with
>>>>> NUMA node, so maybe package?
>>>> Here is the output of lscpu from my machine:
>>>>
>>>> [loongson@localhost ~]$ lscpu
>>>> Architecture: loongarch64
>>>> CPU op-mode(s): 32-bit, 64-bit
>>>> Address sizes: 48 bits physical, 48 bits virtual
>>>> Byte Order: Little Endian
>>>> CPU(s): 128
>>>> On-line CPU(s) list: 0-127
>>>> Model name: Loongson-3C6000/D
>>>> CPU family: Loongson-64bit
>>>> Model: 0x11
>>>> Thread(s) per core: 2
>>>> Core(s) per socket: 32
>>>> Socket(s): 2
>>>> BogoMIPS: 4200.00
>>>> Flags: cpucfg lam ual fpu lsx lasx crc32 complex crypto
>>>> lvz lbt_x86 lbt_arm lbt_mips
>>>> Caches (sum of all):
>>>> L1d: 4 MiB (64 instances)
>>>> L1i: 4 MiB (64 instances)
>>>> L2: 16 MiB (64 instances)
>>>> L3: 128 MiB (4 instances)
>>>> NUMA:
>>>> NUMA node(s): 4
>>>> NUMA node0 CPU(s): 0-31
>>>> NUMA node1 CPU(s): 32-63
>>>> NUMA node2 CPU(s): 64-95
>>>> NUMA node3 CPU(s): 96-127
>>>>
>>>> There are four SE devices in my system, one for each NUMA node.
>>> For Loongson-3C6000 node is the same as package. You should consider
>>> Loongson-3C5000L, one package contains four nodes.
>> I am not familiar with the SE-related components on the 3C5000L, and
>> this driver is not compatible with the 5000 series.
> Whether it is compatible to Loongson-3C5000L is not important. The
> importance is package is not always equal to node, and we should
> consider whether SE is per-node or per-package.
Hi, huacai
After consulting with hardware team, I learned that while the 3C5000L
has four SE devices, only one is utilized due to interrupt constraints.
Thanks,
Qunqin
>
> Huacai
>
^ permalink raw reply
* Re: [PATCH 1/2] gpu: host1x: Allow entries in BO caches to be freed
From: Mikko Perttunen @ 2026-05-18 2:12 UTC (permalink / raw)
To: Aaron Kling
Cc: Thierry Reding, David Airlie, Simona Vetter, Jonathan Hunter,
Akhil R, Herbert Xu, David S. Miller, dri-devel, linux-tegra,
linux-kernel, linux-crypto
In-Reply-To: <CALHNRZ8-UKV1aVf6z_8uKOQ5eP1aP_7SEVJAtQ0fvCuAybb37Q@mail.gmail.com>
On Monday, May 18, 2026 5:02 AM Aaron Kling wrote:
> On Thu, May 14, 2026 at 9:35 PM Mikko Perttunen <mperttunen@nvidia.com> wrote:
> >
> > When a buffer object is pinned via host1x_bo_pin() with a cache, the
> > resulting mapping is kept in the cache so it can be reused on subsequent
> > pins. Each mapping held a reference to the underlying host1x_bo (taken
> > in tegra_bo_pin / gather_bo_pin), so as long as a mapping was cached,
> > the bo itself could not be freed.
> >
> > However, the only way to remove the cached mapping was through the free
> > path of the buffer object. This meant that if a bo got cached, it could
> > never get freed again.
> >
> > Resolve the circularity by holding a weak reference to the bo from the
> > cache side. This is done by having the .pin callbacks not bump the bo's
> > refcount -- instead the common Host1x bo code does so, except for the
> > cache reference.
> >
> > Also move the remove-cache-mapping-on-free code into a common function
> > inside Host1x code. This is only called from the TegraDRM GEM buffers
> > since those are the only ones that can be cached at the moment.
> >
> > Reported-by: Aaron Kling <webgeek1234@gmail.com>
> > Fixes: 1f39b1dfa53c ("drm/tegra: Implement buffer object cache")
> > Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
> > ---
> > drivers/gpu/drm/tegra/gem.c | 13 ++-------
> > drivers/gpu/drm/tegra/submit.c | 3 +--
> > drivers/gpu/host1x/bus.c | 60 +++++++++++++++++++++++++++++++++++++++++-
> > include/linux/host1x.h | 7 +++++
> > 4 files changed, 69 insertions(+), 14 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
> > index d2bae88ad545..2377e2b76397 100644
> > --- a/drivers/gpu/drm/tegra/gem.c
> > +++ b/drivers/gpu/drm/tegra/gem.c
> > @@ -69,7 +69,7 @@ static struct host1x_bo_mapping *tegra_bo_pin(struct device *dev, struct host1x_
> > return ERR_PTR(-ENOMEM);
> >
> > kref_init(&map->ref);
> > - map->bo = host1x_bo_get(bo);
> > + map->bo = bo;
> > map->direction = direction;
> > map->dev = dev;
> >
> > @@ -170,7 +170,6 @@ static void tegra_bo_unpin(struct host1x_bo_mapping *map)
> > kfree(map->sgt);
> > }
> >
> > - host1x_bo_put(map->bo);
> > kfree(map);
> > }
> >
> > @@ -509,17 +508,9 @@ static struct tegra_bo *tegra_bo_import(struct drm_device *drm,
> > void tegra_bo_free_object(struct drm_gem_object *gem)
> > {
> > struct tegra_drm *tegra = gem->dev->dev_private;
> > - struct host1x_bo_mapping *mapping, *tmp;
> > struct tegra_bo *bo = to_tegra_bo(gem);
> >
> > - /* remove all mappings of this buffer object from any caches */
> > - list_for_each_entry_safe(mapping, tmp, &bo->base.mappings, list) {
> > - if (mapping->cache)
> > - host1x_bo_unpin(mapping);
> > - else
> > - dev_err(gem->dev->dev, "mapping %p stale for device %s\n", mapping,
> > - dev_name(mapping->dev));
> > - }
> > + host1x_bo_clear_cached_mappings(&bo->base);
> >
> > if (tegra->domain) {
> > tegra_bo_iommu_unmap(tegra, bo);
> > diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c
> > index 3009b8b9e619..e5841857c937 100644
> > --- a/drivers/gpu/drm/tegra/submit.c
> > +++ b/drivers/gpu/drm/tegra/submit.c
> > @@ -76,7 +76,7 @@ gather_bo_pin(struct device *dev, struct host1x_bo *bo, enum dma_data_direction
> > return ERR_PTR(-ENOMEM);
> >
> > kref_init(&map->ref);
> > - map->bo = host1x_bo_get(bo);
> > + map->bo = bo;
> > map->direction = direction;
> > map->dev = dev;
> >
> > @@ -117,7 +117,6 @@ static void gather_bo_unpin(struct host1x_bo_mapping *map)
> > dma_unmap_sgtable(map->dev, map->sgt, map->direction, 0);
> > sg_free_table(map->sgt);
> > kfree(map->sgt);
> > - host1x_bo_put(map->bo);
> >
> > kfree(map);
> > }
> > diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
> > index f814eb4941c0..772e05a7b45b 100644
> > --- a/drivers/gpu/host1x/bus.c
> > +++ b/drivers/gpu/host1x/bus.c
> > @@ -887,6 +887,20 @@ int host1x_client_resume(struct host1x_client *client)
> > }
> > EXPORT_SYMBOL(host1x_client_resume);
> >
> > +/**
> > + * host1x_bo_pin() - Create a DMA mapping for the buffer object
> > + * @dev: Device onto which DMA map to
> > + * @bo: Buffer object to map
> > + * @dir: DMA direction
> > + * @cache: Cache in which to store mapping, or NULL
> > + *
> > + * Creates a DMA mapping pointing to @bo for @dev. The refcount of @bo is incremented
> > + * until host1x_bo_unpin is called.
> > + *
> > + * If @cache is specified, the mapping is also stored in the cache and not released
> > + * until @bo is freed (refcount drops to zero). This improves performance when a buffer
> > + * is pinned and unpinned frequently as in the case of display use.
> > + */
> > struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo,
> > enum dma_data_direction dir,
> > struct host1x_bo_cache *cache)
> > @@ -899,6 +913,7 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
> > list_for_each_entry(mapping, &cache->mappings, entry) {
> > if (mapping->bo == bo && mapping->direction == dir) {
> > kref_get(&mapping->ref);
> > + host1x_bo_get(bo);
> > goto unlock;
> > }
> > }
> > @@ -908,6 +923,8 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
> > if (IS_ERR(mapping))
> > goto unlock;
> >
> > + host1x_bo_get(bo);
> > +
> > spin_lock(&mapping->bo->lock);
> > list_add_tail(&mapping->list, &bo->mappings);
> > spin_unlock(&mapping->bo->lock);
> > @@ -918,7 +935,12 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
> >
> > list_add_tail(&mapping->entry, &cache->mappings);
> >
> > - /* bump reference count to track the copy in the cache */
> > + /*
> > + * Bump the mapping reference count to track the mapping in the cache,
> > + * but do not bump the BO's refcount. This allows the BO to still get freed,
> > + * triggering the release of the cache mapping through
> > + * host1x_bo_clear_cached_mappings.
> > + */
> > kref_get(&mapping->ref);
> > }
> >
> > @@ -948,9 +970,17 @@ static void __host1x_bo_unpin(struct kref *ref)
> > mapping->bo->ops->unpin(mapping);
> > }
> >
> > +/**
> > + * host1x_bo_unpin() - Release an established DMA mapping of a buffer object
> > + * @mapping: Mapping to release
> > + *
> > + * Unmaps the given @mapping, unless it is cached. Decreases the refcount on
> > + * the underlying buffer object.
> > + */
> > void host1x_bo_unpin(struct host1x_bo_mapping *mapping)
> > {
> > struct host1x_bo_cache *cache = mapping->cache;
> > + struct host1x_bo *bo = mapping->bo;
> >
> > if (cache)
> > mutex_lock(&cache->lock);
> > @@ -959,5 +989,33 @@ void host1x_bo_unpin(struct host1x_bo_mapping *mapping)
> >
> > if (cache)
> > mutex_unlock(&cache->lock);
> > +
> > + host1x_bo_put(bo);
> > }
> > EXPORT_SYMBOL(host1x_bo_unpin);
> > +
> > +/**
> > + * host1x_bo_clear_cached_mappings() - Remove all cached mappings pointing at a bo
> > + * @bo: Buffer object to release mappings of
> > + *
> > + * Drops references to any mappings pointing to @bo left in any caches. This must
> > + * be called by any host1x_bo implementers that may be pinned with caching enabled
> > + * before freeing the bo.
> > + */
> > +void host1x_bo_clear_cached_mappings(struct host1x_bo *bo)
> > +{
> > + struct host1x_bo_mapping *mapping, *tmp;
> > + struct host1x_bo_cache *cache;
> > +
> > + list_for_each_entry_safe(mapping, tmp, &bo->mappings, list) {
> > + cache = mapping->cache;
> > + if (WARN_ON(!cache))
> > + continue;
> > +
> > + mutex_lock(&mapping->cache->lock);
> > + WARN_ON(kref_read(&mapping->ref) != 1);
> > + __host1x_bo_unpin(&mapping->ref);
> > + mutex_unlock(&mapping->cache->lock);
> > + }
> > +}
> > +EXPORT_SYMBOL(host1x_bo_clear_cached_mappings);
> > diff --git a/include/linux/host1x.h b/include/linux/host1x.h
> > index 5e7a63143a4a..d8f052a85b75 100644
> > --- a/include/linux/host1x.h
> > +++ b/include/linux/host1x.h
> > @@ -143,6 +143,12 @@ static inline struct host1x_bo_mapping *to_host1x_bo_mapping(struct kref *ref)
> > return container_of(ref, struct host1x_bo_mapping, ref);
> > }
> >
> > +/**
> > + * struct host1x_bo_ops - operations implemented by a host1x_bo provider
> > + *
> > + * @pin: create a DMA mapping. Implementation must not touch the bo's refcount.
> > + * @unpin: destroy a DMA mapping. Implementation must not touch the bo's refcount.
> > + */
> > struct host1x_bo_ops {
> > struct host1x_bo *(*get)(struct host1x_bo *bo);
> > void (*put)(struct host1x_bo *bo);
> > @@ -181,6 +187,7 @@ struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo
> > enum dma_data_direction dir,
> > struct host1x_bo_cache *cache);
> > void host1x_bo_unpin(struct host1x_bo_mapping *map);
> > +void host1x_bo_clear_cached_mappings(struct host1x_bo *bo);
> >
> > static inline void *host1x_bo_mmap(struct host1x_bo *bo)
> > {
> >
> > --
> > 2.53.0
> >
>
> I have verified this on a Jetson AGX Xavier devkit, a Jetson Xavier NX
> devkit, a Jetson TX2 devkit, and a Jetson TX2 NX in a p3509 carrier.
> No longer seeing allocation failures nor am I seeing any obvious
> regressions. I am currently unable to boot any t210 device to Android
> userspace to verify those for various preexisting reasons, and Android
> recovery does not reallocate buffers to stress this issue.
>
> Tested-by: Aaron Kling <webgeek1234@gmail.com>
>
> Aaron
Thank you!
^ permalink raw reply
* Re: [PATCH 01/19] btrfs: require at least 4 devices for RAID 6
From: Christoph Hellwig @ 2026-05-18 5:12 UTC (permalink / raw)
To: H. Peter Anvin
Cc: Christoph Hellwig, kreijack, David Sterba, Andrew Morton,
Catalin Marinas, Will Deacon, Ard Biesheuvel, Huacai Chen,
WANG Xuerui, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Paul Walmsley,
Palmer Dabbelt, Albert Ou, Alexandre Ghiti, Heiko Carstens,
Vasily Gorbik, Alexander Gordeev, Christian Borntraeger,
Sven Schnelle, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, Herbert Xu, Dan Williams, Chris Mason,
David Sterba, Arnd Bergmann, Song Liu, Yu Kuai, Li Nan,
linux-kernel, linux-arm-kernel, loongarch, linuxppc-dev,
linux-riscv, linux-s390, linux-crypto, linux-btrfs, linux-arch,
linux-raid
In-Reply-To: <34C16854-1065-4542-8836-DDED58EC1844@zytor.com>
On Fri, May 15, 2026 at 12:59:34PM -0700, H. Peter Anvin wrote:
> I don't think this is a good idea. Error out; it is the btrfs maintainers' job to ensure user data isn't lost.
>
> The RAID-6 code has *never* supported only 3 units, and if it ever worked for *any* of the implementations it was purely by accident. Speaking as the original author I should know; this was deliberate as in some cases the degenerate case (3) would have required extra trays in the code to no user benefit.
>
> I would not be surprised if the kernel crashed or corrupted the page cache in that case.
It does, that's why I wanted to exclude it. Anyway, for the about to be
resent version I'll drop this btrfs patch over the stated objection and
will otherwise not change anything. This means the (IMHO hypothetical)
users of this configuration will get a WARN_ON_ONCE triggered, but
otherwise keep working (or rather not working) as before.
^ permalink raw reply
* [PATCH 01/18] raid6: turn the userspace test harness into a kunit test
From: Christoph Hellwig @ 2026-05-18 5:12 UTC (permalink / raw)
To: Andrew Morton
Cc: Catalin Marinas, Will Deacon, Ard Biesheuvel, Huacai Chen,
WANG Xuerui, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Paul Walmsley,
Palmer Dabbelt, Albert Ou, Alexandre Ghiti, Heiko Carstens,
Vasily Gorbik, Alexander Gordeev, Christian Borntraeger,
Sven Schnelle, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, H. Peter Anvin, Herbert Xu, Dan Williams,
Chris Mason, David Sterba, Arnd Bergmann, Song Liu, Yu Kuai,
Li Nan, linux-kernel, linux-arm-kernel, loongarch, linuxppc-dev,
linux-riscv, linux-s390, linux-crypto, linux-btrfs, linux-arch,
linux-raid
In-Reply-To: <20260518051245.451860-1-hch@lst.de>
Currently the raid6 code can be compiled as userspace code to run the
test suite. Convert that to be a kunit case with minimal changes to
avoid mutating global state so that we can drop this requirement.
Note that this is not a good kunit test case yet and will need a lot more
work, but that is deferred until the raid6 code is moved to it's new
place, which is easier if the userspace makefile doesn't need adjustments
for the new location first.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Ard Biesheuvel <ardb@kernel.org> # kunit only on arm64
---
include/linux/raid/pq.h | 3 -
lib/Kconfig | 11 +++
lib/raid6/Makefile | 2 +-
lib/raid6/algos.c | 5 +-
lib/raid6/recov.c | 34 ---------
lib/raid6/test/Makefile | 155 +--------------------------------------
lib/raid6/test/test.c | 158 +++++++++++++++++++++-------------------
7 files changed, 101 insertions(+), 267 deletions(-)
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 2467b3be15c9..08c5995ea980 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -144,7 +144,6 @@ extern const struct raid6_calls raid6_neonx8;
/* Algorithm list */
extern const struct raid6_calls * const raid6_algos[];
extern const struct raid6_recov_calls *const raid6_recov_algos[];
-int raid6_select_algo(void);
/* Return values from chk_syndrome */
#define RAID6_OK 0
@@ -165,8 +164,6 @@ extern void (*raid6_2data_recov)(int disks, size_t bytes, int faila, int failb,
void **ptrs);
extern void (*raid6_datap_recov)(int disks, size_t bytes, int faila,
void **ptrs);
-void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
- void **ptrs);
/* Some definitions to allow code to be compiled for testing in userspace */
#ifndef __KERNEL__
diff --git a/lib/Kconfig b/lib/Kconfig
index 00a9509636c1..bffe015a6c10 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -11,6 +11,17 @@ menu "Library routines"
config RAID6_PQ
tristate
+config RAID6_PQ_KUNIT_TEST
+ tristate "KUnit tests for RAID6 PQ functions" if !KUNIT_ALL_TESTS
+ depends on KUNIT
+ depends on RAID6_PQ
+ default KUNIT_ALL_TESTS
+ help
+ Unit tests for the RAID6 PQ library functions.
+
+ This is intended to help people writing architecture-specific
+ optimized versions. If unsure, say N.
+
config RAID6_PQ_BENCHMARK
bool "Automatically choose fastest RAID6 PQ functions"
depends on RAID6_PQ
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 5be0a4e60ab1..6fd048c127b6 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_RAID6_PQ) += raid6_pq.o
+obj-$(CONFIG_RAID6_PQ) += raid6_pq.o test/
raid6_pq-y += algos.o recov.o tables.o int1.o int2.o int4.o \
int8.o
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 799e0e5eac26..5a9f4882e18d 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -19,6 +19,7 @@
#include <linux/module.h>
#include <linux/gfp.h>
#endif
+#include <kunit/visibility.h>
struct raid6_calls raid6_call;
EXPORT_SYMBOL_GPL(raid6_call);
@@ -86,6 +87,7 @@ const struct raid6_calls * const raid6_algos[] = {
&raid6_intx1,
NULL
};
+EXPORT_SYMBOL_IF_KUNIT(raid6_algos);
void (*raid6_2data_recov)(int, size_t, int, int, void **);
EXPORT_SYMBOL_GPL(raid6_2data_recov);
@@ -119,6 +121,7 @@ const struct raid6_recov_calls *const raid6_recov_algos[] = {
&raid6_recov_intx1,
NULL
};
+EXPORT_SYMBOL_IF_KUNIT(raid6_recov_algos);
#ifdef __KERNEL__
#define RAID6_TIME_JIFFIES_LG2 4
@@ -239,7 +242,7 @@ static inline const struct raid6_calls *raid6_choose_gen(
/* Try to pick the best algorithm */
/* This code uses the gfmul table as convenient data set to abuse */
-int __init raid6_select_algo(void)
+static int __init raid6_select_algo(void)
{
const int disks = RAID6_TEST_DISKS;
diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c
index b5e47c008b41..8d113196632e 100644
--- a/lib/raid6/recov.c
+++ b/lib/raid6/recov.c
@@ -99,37 +99,3 @@ const struct raid6_recov_calls raid6_recov_intx1 = {
.name = "intx1",
.priority = 0,
};
-
-#ifndef __KERNEL__
-/* Testing only */
-
-/* Recover two failed blocks. */
-void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, void **ptrs)
-{
- if ( faila > failb ) {
- int tmp = faila;
- faila = failb;
- failb = tmp;
- }
-
- if ( failb == disks-1 ) {
- if ( faila == disks-2 ) {
- /* P+Q failure. Just rebuild the syndrome. */
- raid6_call.gen_syndrome(disks, bytes, ptrs);
- } else {
- /* data+Q failure. Reconstruct data from P,
- then rebuild syndrome. */
- /* NOT IMPLEMENTED - equivalent to RAID-5 */
- }
- } else {
- if ( failb == disks-2 ) {
- /* data+P failure. */
- raid6_datap_recov(disks, bytes, faila, ptrs);
- } else {
- /* data+data failure. */
- raid6_2data_recov(disks, bytes, faila, failb, ptrs);
- }
- }
-}
-
-#endif
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index 09bbe2b14cce..520381ea71d7 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -1,156 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-#
-# This is a simple Makefile to test some of the RAID-6 code
-# from userspace.
-#
-pound := \#
+obj-$(CONFIG_RAID6_PQ_KUNIT_TEST) += raid6_kunit.o
-# Adjust as desired
-CC = gcc
-OPTFLAGS = -O2
-CFLAGS = -I.. -I ../../../include -g $(OPTFLAGS)
-LD = ld
-AWK = awk -f
-AR = ar
-RANLIB = ranlib
-OBJS = int1.o int2.o int4.o int8.o int16.o int32.o recov.o algos.o tables.o
-
-ARCH := $(shell uname -m 2>/dev/null | sed -e /s/i.86/i386/)
-ifeq ($(ARCH),i386)
- CFLAGS += -DCONFIG_X86_32
- IS_X86 = yes
-endif
-ifeq ($(ARCH),x86_64)
- CFLAGS += -DCONFIG_X86_64
- IS_X86 = yes
-endif
-
-ifeq ($(ARCH),arm)
- CFLAGS += -I../../../arch/arm/include -mfpu=neon
- HAS_NEON = yes
-endif
-ifeq ($(ARCH),aarch64)
- CFLAGS += -I../../../arch/arm64/include
- HAS_NEON = yes
-endif
-
-ifeq ($(findstring riscv,$(ARCH)),riscv)
- CFLAGS += -I../../../arch/riscv/include -DCONFIG_RISCV=1
- HAS_RVV = yes
-endif
-
-ifeq ($(findstring ppc,$(ARCH)),ppc)
- CFLAGS += -I../../../arch/powerpc/include
- HAS_ALTIVEC := $(shell printf '$(pound)include <altivec.h>\nvector int a;\n' |\
- gcc -c -x c - >/dev/null && rm ./-.o && echo yes)
-endif
-
-ifeq ($(ARCH),loongarch64)
- CFLAGS += -I../../../arch/loongarch/include -DCONFIG_LOONGARCH=1
- CFLAGS += $(shell echo 'vld $$vr0, $$zero, 0' | \
- gcc -c -x assembler - >/dev/null 2>&1 && \
- rm ./-.o && echo -DCONFIG_CPU_HAS_LSX=1)
- CFLAGS += $(shell echo 'xvld $$xr0, $$zero, 0' | \
- gcc -c -x assembler - >/dev/null 2>&1 && \
- rm ./-.o && echo -DCONFIG_CPU_HAS_LASX=1)
-endif
-
-ifeq ($(IS_X86),yes)
- OBJS += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o avx512.o recov_avx512.o
- CFLAGS += -DCONFIG_X86
-else ifeq ($(HAS_NEON),yes)
- OBJS += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
- CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1
-else ifeq ($(HAS_ALTIVEC),yes)
- CFLAGS += -DCONFIG_ALTIVEC
- OBJS += altivec1.o altivec2.o altivec4.o altivec8.o \
- vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
-else ifeq ($(ARCH),loongarch64)
- OBJS += loongarch_simd.o recov_loongarch_simd.o
-else ifeq ($(HAS_RVV),yes)
- OBJS += rvv.o recov_rvv.o
- CFLAGS += -DCONFIG_RISCV_ISA_V=1
-endif
-
-.c.o:
- $(CC) $(CFLAGS) -c -o $@ $<
-
-%.c: ../%.c
- cp -f $< $@
-
-%.uc: ../%.uc
- cp -f $< $@
-
-all: raid6.a raid6test
-
-raid6.a: $(OBJS)
- rm -f $@
- $(AR) cq $@ $^
- $(RANLIB) $@
-
-raid6test: test.c raid6.a
- $(CC) $(CFLAGS) -o raid6test $^
-
-neon1.c: neon.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=1 < neon.uc > $@
-
-neon2.c: neon.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=2 < neon.uc > $@
-
-neon4.c: neon.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=4 < neon.uc > $@
-
-neon8.c: neon.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=8 < neon.uc > $@
-
-altivec1.c: altivec.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=1 < altivec.uc > $@
-
-altivec2.c: altivec.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=2 < altivec.uc > $@
-
-altivec4.c: altivec.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=4 < altivec.uc > $@
-
-altivec8.c: altivec.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=8 < altivec.uc > $@
-
-vpermxor1.c: vpermxor.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=1 < vpermxor.uc > $@
-
-vpermxor2.c: vpermxor.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=2 < vpermxor.uc > $@
-
-vpermxor4.c: vpermxor.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=4 < vpermxor.uc > $@
-
-vpermxor8.c: vpermxor.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=8 < vpermxor.uc > $@
-
-int1.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=1 < int.uc > $@
-
-int2.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=2 < int.uc > $@
-
-int4.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=4 < int.uc > $@
-
-int8.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=8 < int.uc > $@
-
-int16.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=16 < int.uc > $@
-
-int32.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=32 < int.uc > $@
-
-tables.c: mktables
- ./mktables > tables.c
-
-clean:
- rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c vpermxor*.c neon*.c tables.c raid6test
-
-spotless: clean
- rm -f *~
+raid6_kunit-y += test.o
diff --git a/lib/raid6/test/test.c b/lib/raid6/test/test.c
index 841a55242aba..9db287b4a48f 100644
--- a/lib/raid6/test/test.c
+++ b/lib/raid6/test/test.c
@@ -1,43 +1,37 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- * Copyright 2002-2007 H. Peter Anvin - All Rights Reserved
- *
- * ----------------------------------------------------------------------- */
-
/*
- * raid6test.c
+ * Copyright 2002-2007 H. Peter Anvin - All Rights Reserved
*
- * Test RAID-6 recovery with various algorithms
+ * Test RAID-6 recovery algorithms.
*/
-#include <stdlib.h>
-#include <stdio.h>
-#include <string.h>
+#include <kunit/test.h>
+#include <linux/prandom.h>
#include <linux/raid/pq.h>
-#define NDISKS 16 /* Including P and Q */
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
+
+#define RAID6_KUNIT_SEED 42
-const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+#define NDISKS 16 /* Including P and Q */
-char *dataptrs[NDISKS];
-char data[NDISKS][PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
-char recovi[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
-char recovj[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static struct rnd_state rng;
+static void *dataptrs[NDISKS];
+static char data[NDISKS][PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static char recovi[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static char recovj[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
static void makedata(int start, int stop)
{
- int i, j;
+ int i;
for (i = start; i <= stop; i++) {
- for (j = 0; j < PAGE_SIZE; j++)
- data[i][j] = rand();
-
+ prandom_bytes_state(&rng, data[i], PAGE_SIZE);
dataptrs[i] = data[i];
}
}
-static char disk_type(int d)
+static char member_type(int d)
{
switch (d) {
case NDISKS-2:
@@ -49,104 +43,118 @@ static char disk_type(int d)
}
}
-static int test_disks(int i, int j)
+static void test_disks(struct kunit *test, const struct raid6_calls *calls,
+ const struct raid6_recov_calls *ra, int faila, int failb)
{
- int erra, errb;
-
memset(recovi, 0xf0, PAGE_SIZE);
memset(recovj, 0xba, PAGE_SIZE);
- dataptrs[i] = recovi;
- dataptrs[j] = recovj;
-
- raid6_dual_recov(NDISKS, PAGE_SIZE, i, j, (void **)&dataptrs);
-
- erra = memcmp(data[i], recovi, PAGE_SIZE);
- errb = memcmp(data[j], recovj, PAGE_SIZE);
-
- if (i < NDISKS-2 && j == NDISKS-1) {
- /* We don't implement the DQ failure scenario, since it's
- equivalent to a RAID-5 failure (XOR, then recompute Q) */
- erra = errb = 0;
+ dataptrs[faila] = recovi;
+ dataptrs[failb] = recovj;
+
+ if (failb == NDISKS - 1) {
+ /*
+ * We don't implement the data+Q failure scenario, since it
+ * is equivalent to a RAID-5 failure (XOR, then recompute Q).
+ */
+ if (faila != NDISKS - 2)
+ goto skip;
+
+ /* P+Q failure. Just rebuild the syndrome. */
+ calls->gen_syndrome(NDISKS, PAGE_SIZE, dataptrs);
+ } else if (failb == NDISKS - 2) {
+ /* data+P failure. */
+ ra->datap(NDISKS, PAGE_SIZE, faila, dataptrs);
} else {
- printf("algo=%-8s faila=%3d(%c) failb=%3d(%c) %s\n",
- raid6_call.name,
- i, disk_type(i),
- j, disk_type(j),
- (!erra && !errb) ? "OK" :
- !erra ? "ERRB" :
- !errb ? "ERRA" : "ERRAB");
+ /* data+data failure. */
+ ra->data2(NDISKS, PAGE_SIZE, faila, failb, dataptrs);
}
- dataptrs[i] = data[i];
- dataptrs[j] = data[j];
-
- return erra || errb;
+ KUNIT_EXPECT_MEMEQ_MSG(test, data[faila], recovi, PAGE_SIZE,
+ "algo=%-8s/%-8s faila miscompared: %3d[%c] (failb=%3d[%c])\n",
+ calls->name, ra->name,
+ faila, member_type(faila),
+ failb, member_type(failb));
+ KUNIT_EXPECT_MEMEQ_MSG(test, data[failb], recovj, PAGE_SIZE,
+ "algo=%-8s/%-8s failb miscompared: %3d[%c] (faila=%3d[%c])\n",
+ calls->name, ra->name,
+ failb, member_type(failb),
+ faila, member_type(faila));
+
+skip:
+ dataptrs[faila] = data[faila];
+ dataptrs[failb] = data[failb];
}
-int main(int argc, char *argv[])
+static void raid6_test(struct kunit *test)
{
const struct raid6_calls *const *algo;
const struct raid6_recov_calls *const *ra;
int i, j, p1, p2;
- int err = 0;
-
- makedata(0, NDISKS-1);
for (ra = raid6_recov_algos; *ra; ra++) {
if ((*ra)->valid && !(*ra)->valid())
continue;
- raid6_2data_recov = (*ra)->data2;
- raid6_datap_recov = (*ra)->datap;
-
- printf("using recovery %s\n", (*ra)->name);
-
for (algo = raid6_algos; *algo; algo++) {
- if ((*algo)->valid && !(*algo)->valid())
- continue;
+ const struct raid6_calls *calls = *algo;
- raid6_call = **algo;
+ if (calls->valid && !calls->valid())
+ continue;
/* Nuke syndromes */
- memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE);
+ memset(data[NDISKS - 2], 0xee, PAGE_SIZE);
+ memset(data[NDISKS - 1], 0xee, PAGE_SIZE);
/* Generate assumed good syndrome */
- raid6_call.gen_syndrome(NDISKS, PAGE_SIZE,
+ calls->gen_syndrome(NDISKS, PAGE_SIZE,
(void **)&dataptrs);
for (i = 0; i < NDISKS-1; i++)
for (j = i+1; j < NDISKS; j++)
- err += test_disks(i, j);
+ test_disks(test, calls, *ra, i, j);
- if (!raid6_call.xor_syndrome)
+ if (!calls->xor_syndrome)
continue;
for (p1 = 0; p1 < NDISKS-2; p1++)
for (p2 = p1; p2 < NDISKS-2; p2++) {
/* Simulate rmw run */
- raid6_call.xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
+ calls->xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
(void **)&dataptrs);
makedata(p1, p2);
- raid6_call.xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
+ calls->xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
(void **)&dataptrs);
for (i = 0; i < NDISKS-1; i++)
for (j = i+1; j < NDISKS; j++)
- err += test_disks(i, j);
+ test_disks(test, calls,
+ *ra, i, j);
}
}
- printf("\n");
}
+}
- printf("\n");
- /* Pick the best algorithm test */
- raid6_select_algo();
-
- if (err)
- printf("\n*** ERRORS FOUND ***\n");
+static struct kunit_case raid6_test_cases[] = {
+ KUNIT_CASE(raid6_test),
+ {},
+};
- return err;
+static int raid6_suite_init(struct kunit_suite *suite)
+{
+ prandom_seed_state(&rng, RAID6_KUNIT_SEED);
+ makedata(0, NDISKS - 1);
+ return 0;
}
+
+static struct kunit_suite raid6_test_suite = {
+ .name = "raid6",
+ .test_cases = raid6_test_cases,
+ .suite_init = raid6_suite_init,
+};
+kunit_test_suite(raid6_test_suite);
+
+MODULE_DESCRIPTION("Unit test for the RAID P/Q library functions");
+MODULE_LICENSE("GPL");
--
2.53.0
^ permalink raw reply related
* cleanup the RAID6 P/Q library v3
From: Christoph Hellwig @ 2026-05-18 5:12 UTC (permalink / raw)
To: Andrew Morton
Cc: Catalin Marinas, Will Deacon, Ard Biesheuvel, Huacai Chen,
WANG Xuerui, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Paul Walmsley,
Palmer Dabbelt, Albert Ou, Alexandre Ghiti, Heiko Carstens,
Vasily Gorbik, Alexander Gordeev, Christian Borntraeger,
Sven Schnelle, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, H. Peter Anvin, Herbert Xu, Dan Williams,
Chris Mason, David Sterba, Arnd Bergmann, Song Liu, Yu Kuai,
Li Nan, linux-kernel, linux-arm-kernel, loongarch, linuxppc-dev,
linux-riscv, linux-s390, linux-crypto, linux-btrfs, linux-arch,
linux-raid
Hi all,
this series cleans up the RAID6 P/Q library to match the recent updates
to the RAID 5 XOR library and other CRC/crypto libraries. This includes
providing properly documented external interfaces, hiding the internals,
using static_call instead of indirect calls and turning the user space
test suite into an in-kernel kunit test which is also extended to
improve coverage.
Note that this changes registration so that non-priority algorithms are
not registered, which greatly helps with the benchmark time at boot time.
I'd like to encourage all architecture maintainers to see if they can
further optimized this by registering as few as possible algorithms when
there is a clear benefit in optimized or more unrolled implementations.
This series sits on top of the "cleanup the RAID5 XOR library v3" series.
A git tree is also available here:
git://git.infradead.org/users/hch/misc.git lib-raid6
Gitweb:
https://git.infradead.org/?p=users/hch/misc.git;a=shortlog;h=refs/heads/lib-raid6
Changes since v2:
- merge two patches that should have been one
- split out enforcing the 4-device minimum into a well-documented patch
explaining the rationale
- drop the btrfs patch to restrict the number of devices again
- fix them module description for the kunit test
- add -I $(src) to fix out of srctree builds for architectures with
headers in the architecture-specific directories
- always add the least optimized/unrolled algorithms first to keep the
existing no-benchmark behavior
- drop the delayed benchmarking for now to avoid corner cases
- improve a few commit messages
Changes since v1:
- fix arm64 objdir != srcdir builds
- call the kunit module raid6_kunit.ko from the beginning
- update MAINTAINERS
- don't require preemptible context and apply the same restrictions as
the merged version of the XOR API
- fix the arm64 default in Kconfig
- pick the last registered (and presumably most optimized) algorithm when
benchmarking is disabled
- port over the randomization fixes from the XOR series
- misc other kunit cleanups
- require at least 4 devices for RAID6 to skip broken special cases
Diffstat:
b/Documentation/crypto/async-tx-api.rst | 4
b/MAINTAINERS | 2
b/crypto/async_tx/async_pq.c | 9
b/crypto/async_tx/async_raid6_recov.c | 9
b/drivers/dma/bcm-sba-raid.c | 1
b/drivers/md/raid5.c | 4
b/fs/btrfs/raid56.c | 8
b/include/linux/raid/pq.h | 216 ------------
b/include/linux/raid/pq_tables.h | 19 +
b/lib/Kconfig | 11
b/lib/Makefile | 1
b/lib/raid/Kconfig | 33 +
b/lib/raid/Makefile | 2
b/lib/raid/raid6/Makefile | 128 +++++++
b/lib/raid/raid6/algos.c | 377 ++++++++++++++++++++++
b/lib/raid/raid6/algos.h | 41 ++
b/lib/raid/raid6/arm/neon.c | 23 -
b/lib/raid/raid6/arm/neon.uc | 2
b/lib/raid/raid6/arm/pq_arch.h | 21 +
b/lib/raid/raid6/arm/recov_neon.c | 27 -
b/lib/raid/raid6/arm/recov_neon_inner.c | 2
b/lib/raid/raid6/arm64/pq_arch.h | 1
b/lib/raid/raid6/int.uc | 10
b/lib/raid/raid6/loongarch/loongarch_simd.c | 31 -
b/lib/raid/raid6/loongarch/pq_arch.h | 23 +
b/lib/raid/raid6/loongarch/recov_loongarch_simd.c | 39 --
b/lib/raid/raid6/mktables.c | 28 -
b/lib/raid/raid6/powerpc/altivec.uc | 32 -
b/lib/raid/raid6/powerpc/pq_arch.h | 32 +
b/lib/raid/raid6/powerpc/vpermxor.uc | 29 -
b/lib/raid/raid6/recov.c | 62 ---
b/lib/raid/raid6/riscv/pq_arch.h | 21 +
b/lib/raid/raid6/riscv/recov_rvv.c | 14
b/lib/raid/raid6/riscv/rvv.h | 26 -
b/lib/raid/raid6/s390/pq_arch.h | 15
b/lib/raid/raid6/s390/recov_s390xc.c | 14
b/lib/raid/raid6/s390/s390vx.uc | 15
b/lib/raid/raid6/tests/Makefile | 3
b/lib/raid/raid6/tests/raid6_kunit.c | 321 ++++++++++++++++++
b/lib/raid/raid6/x86/avx2.c | 47 --
b/lib/raid/raid6/x86/avx512.c | 57 +--
b/lib/raid/raid6/x86/mmx.c | 39 --
b/lib/raid/raid6/x86/pq_arch.h | 96 +++++
b/lib/raid/raid6/x86/recov_avx2.c | 22 -
b/lib/raid/raid6/x86/recov_avx512.c | 26 -
b/lib/raid/raid6/x86/recov_ssse3.c | 23 -
b/lib/raid/raid6/x86/sse1.c | 49 --
b/lib/raid/raid6/x86/sse2.c | 47 --
lib/raid6/Makefile | 83 ----
lib/raid6/algos.c | 291 ----------------
lib/raid6/loongarch.h | 38 --
lib/raid6/test/.gitignore | 3
lib/raid6/test/Makefile | 156 ---------
lib/raid6/test/test.c | 152 --------
lib/raid6/x86.h | 75 ----
55 files changed, 1349 insertions(+), 1511 deletions(-)
^ permalink raw reply
* [PATCH 02/18] raid6: remove __KERNEL__ ifdefs
From: Christoph Hellwig @ 2026-05-18 5:12 UTC (permalink / raw)
To: Andrew Morton
Cc: Catalin Marinas, Will Deacon, Ard Biesheuvel, Huacai Chen,
WANG Xuerui, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Paul Walmsley,
Palmer Dabbelt, Albert Ou, Alexandre Ghiti, Heiko Carstens,
Vasily Gorbik, Alexander Gordeev, Christian Borntraeger,
Sven Schnelle, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, H. Peter Anvin, Herbert Xu, Dan Williams,
Chris Mason, David Sterba, Arnd Bergmann, Song Liu, Yu Kuai,
Li Nan, linux-kernel, linux-arm-kernel, loongarch, linuxppc-dev,
linux-riscv, linux-s390, linux-crypto, linux-btrfs, linux-arch,
linux-raid
In-Reply-To: <20260518051245.451860-1-hch@lst.de>
With the test code ported to kernel space, none of this is required.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Ard Biesheuvel <ardb@kernel.org> # kunit only on arm64
---
include/linux/raid/pq.h | 90 --------------------------------
lib/raid6/algos.c | 12 -----
lib/raid6/altivec.uc | 10 +---
lib/raid6/avx2.c | 2 +-
lib/raid6/avx512.c | 2 +-
lib/raid6/loongarch.h | 38 --------------
lib/raid6/loongarch_simd.c | 3 +-
lib/raid6/mktables.c | 14 -----
lib/raid6/mmx.c | 2 +-
lib/raid6/neon.c | 6 ---
lib/raid6/recov_avx2.c | 2 +-
lib/raid6/recov_avx512.c | 2 +-
lib/raid6/recov_loongarch_simd.c | 3 +-
lib/raid6/recov_neon.c | 6 ---
lib/raid6/recov_ssse3.c | 2 +-
lib/raid6/rvv.h | 11 +---
lib/raid6/sse1.c | 2 +-
lib/raid6/sse2.c | 2 +-
lib/raid6/vpermxor.uc | 7 ---
lib/raid6/x86.h | 75 --------------------------
20 files changed, 15 insertions(+), 276 deletions(-)
delete mode 100644 lib/raid6/loongarch.h
delete mode 100644 lib/raid6/x86.h
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 08c5995ea980..d26788fada58 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -8,8 +8,6 @@
#ifndef LINUX_RAID_RAID6_H
#define LINUX_RAID_RAID6_H
-#ifdef __KERNEL__
-
#include <linux/blkdev.h>
#include <linux/mm.h>
@@ -19,59 +17,6 @@ static inline void *raid6_get_zero_page(void)
return page_address(ZERO_PAGE(0));
}
-#else /* ! __KERNEL__ */
-/* Used for testing in user space */
-
-#include <errno.h>
-#include <inttypes.h>
-#include <stddef.h>
-#include <string.h>
-#include <sys/mman.h>
-#include <sys/time.h>
-#include <sys/types.h>
-
-/* Not standard, but glibc defines it */
-#define BITS_PER_LONG __WORDSIZE
-
-typedef uint8_t u8;
-typedef uint16_t u16;
-typedef uint32_t u32;
-typedef uint64_t u64;
-
-#ifndef PAGE_SIZE
-# define PAGE_SIZE 4096
-#endif
-#ifndef PAGE_SHIFT
-# define PAGE_SHIFT 12
-#endif
-extern const char raid6_empty_zero_page[PAGE_SIZE];
-
-#define __init
-#define __exit
-#ifndef __attribute_const__
-# define __attribute_const__ __attribute__((const))
-#endif
-#define noinline __attribute__((noinline))
-
-#define preempt_enable()
-#define preempt_disable()
-#define cpu_has_feature(x) 1
-#define enable_kernel_altivec()
-#define disable_kernel_altivec()
-
-#undef EXPORT_SYMBOL
-#define EXPORT_SYMBOL(sym)
-#undef EXPORT_SYMBOL_GPL
-#define EXPORT_SYMBOL_GPL(sym)
-#define MODULE_LICENSE(licence)
-#define MODULE_DESCRIPTION(desc)
-#define subsys_initcall(x)
-#define module_exit(x)
-
-#define IS_ENABLED(x) (x)
-#define CONFIG_RAID6_PQ_BENCHMARK 1
-#endif /* __KERNEL__ */
-
/* Routine choices */
struct raid6_calls {
void (*gen_syndrome)(int, size_t, void **);
@@ -165,39 +110,4 @@ extern void (*raid6_2data_recov)(int disks, size_t bytes, int faila, int failb,
extern void (*raid6_datap_recov)(int disks, size_t bytes, int faila,
void **ptrs);
-/* Some definitions to allow code to be compiled for testing in userspace */
-#ifndef __KERNEL__
-
-# define jiffies raid6_jiffies()
-# define printk printf
-# define pr_err(format, ...) fprintf(stderr, format, ## __VA_ARGS__)
-# define pr_info(format, ...) fprintf(stdout, format, ## __VA_ARGS__)
-# define GFP_KERNEL 0
-# define __get_free_pages(x, y) ((unsigned long)mmap(NULL, PAGE_SIZE << (y), \
- PROT_READ|PROT_WRITE, \
- MAP_PRIVATE|MAP_ANONYMOUS,\
- 0, 0))
-# define free_pages(x, y) munmap((void *)(x), PAGE_SIZE << (y))
-
-static inline void cpu_relax(void)
-{
- /* Nothing */
-}
-
-#undef HZ
-#define HZ 1000
-static inline uint32_t raid6_jiffies(void)
-{
- struct timeval tv;
- gettimeofday(&tv, NULL);
- return tv.tv_sec*1000 + tv.tv_usec/1000;
-}
-
-static inline void *raid6_get_zero_page(void)
-{
- return raid6_empty_zero_page;
-}
-
-#endif /* ! __KERNEL__ */
-
#endif /* LINUX_RAID_RAID6_H */
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 5a9f4882e18d..985c60bb00a4 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -12,13 +12,8 @@
*/
#include <linux/raid/pq.h>
-#ifndef __KERNEL__
-#include <sys/mman.h>
-#include <stdio.h>
-#else
#include <linux/module.h>
#include <linux/gfp.h>
-#endif
#include <kunit/visibility.h>
struct raid6_calls raid6_call;
@@ -123,14 +118,7 @@ const struct raid6_recov_calls *const raid6_recov_algos[] = {
};
EXPORT_SYMBOL_IF_KUNIT(raid6_recov_algos);
-#ifdef __KERNEL__
#define RAID6_TIME_JIFFIES_LG2 4
-#else
-/* Need more time to be stable in userspace */
-#define RAID6_TIME_JIFFIES_LG2 9
-#define time_before(x, y) ((x) < (y))
-#endif
-
#define RAID6_TEST_DISKS 8
#define RAID6_TEST_DISKS_ORDER 3
diff --git a/lib/raid6/altivec.uc b/lib/raid6/altivec.uc
index d20ed0d11411..2c59963e58f9 100644
--- a/lib/raid6/altivec.uc
+++ b/lib/raid6/altivec.uc
@@ -27,10 +27,8 @@
#ifdef CONFIG_ALTIVEC
#include <altivec.h>
-#ifdef __KERNEL__
-# include <asm/cputable.h>
-# include <asm/switch_to.h>
-#endif /* __KERNEL__ */
+#include <asm/cputable.h>
+#include <asm/switch_to.h>
/*
* This is the C data type to use. We use a vector of
@@ -113,11 +111,7 @@ int raid6_have_altivec(void);
int raid6_have_altivec(void)
{
/* This assumes either all CPUs have Altivec or none does */
-# ifdef __KERNEL__
return cpu_has_feature(CPU_FTR_ALTIVEC);
-# else
- return 1;
-# endif
}
#endif
diff --git a/lib/raid6/avx2.c b/lib/raid6/avx2.c
index 059024234dce..a1a5213918af 100644
--- a/lib/raid6/avx2.c
+++ b/lib/raid6/avx2.c
@@ -14,7 +14,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static const struct raid6_avx2_constants {
u64 x1d[4];
diff --git a/lib/raid6/avx512.c b/lib/raid6/avx512.c
index 009bd0adeebf..874998bcd7d7 100644
--- a/lib/raid6/avx512.c
+++ b/lib/raid6/avx512.c
@@ -18,7 +18,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static const struct raid6_avx512_constants {
u64 x1d[8];
diff --git a/lib/raid6/loongarch.h b/lib/raid6/loongarch.h
deleted file mode 100644
index acfc33ce7056..000000000000
--- a/lib/raid6/loongarch.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
- *
- * raid6/loongarch.h
- *
- * Definitions common to LoongArch RAID-6 code only
- */
-
-#ifndef _LIB_RAID6_LOONGARCH_H
-#define _LIB_RAID6_LOONGARCH_H
-
-#ifdef __KERNEL__
-
-#include <asm/cpu-features.h>
-#include <asm/fpu.h>
-
-#else /* for user-space testing */
-
-#include <sys/auxv.h>
-
-/* have to supply these defines for glibc 2.37- and musl */
-#ifndef HWCAP_LOONGARCH_LSX
-#define HWCAP_LOONGARCH_LSX (1 << 4)
-#endif
-#ifndef HWCAP_LOONGARCH_LASX
-#define HWCAP_LOONGARCH_LASX (1 << 5)
-#endif
-
-#define kernel_fpu_begin()
-#define kernel_fpu_end()
-
-#define cpu_has_lsx (getauxval(AT_HWCAP) & HWCAP_LOONGARCH_LSX)
-#define cpu_has_lasx (getauxval(AT_HWCAP) & HWCAP_LOONGARCH_LASX)
-
-#endif /* __KERNEL__ */
-
-#endif /* _LIB_RAID6_LOONGARCH_H */
diff --git a/lib/raid6/loongarch_simd.c b/lib/raid6/loongarch_simd.c
index aa5d9f924ca3..72f4d92d4876 100644
--- a/lib/raid6/loongarch_simd.c
+++ b/lib/raid6/loongarch_simd.c
@@ -10,7 +10,8 @@
*/
#include <linux/raid/pq.h>
-#include "loongarch.h"
+#include <asm/cpu-features.h>
+#include <asm/fpu.h>
/*
* The vector algorithms are currently priority 0, which means the generic
diff --git a/lib/raid6/mktables.c b/lib/raid6/mktables.c
index 3be03793237c..3de1dbf6846c 100644
--- a/lib/raid6/mktables.c
+++ b/lib/raid6/mktables.c
@@ -56,9 +56,7 @@ int main(int argc, char *argv[])
uint8_t v;
uint8_t exptbl[256], invtbl[256];
- printf("#ifdef __KERNEL__\n");
printf("#include <linux/export.h>\n");
- printf("#endif\n");
printf("#include <linux/raid/pq.h>\n");
/* Compute multiplication table */
@@ -76,9 +74,7 @@ int main(int argc, char *argv[])
printf("\t},\n");
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gfmul);\n");
- printf("#endif\n");
/* Compute vector multiplication table */
printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -101,9 +97,7 @@ int main(int argc, char *argv[])
printf("\t},\n");
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_vgfmul);\n");
- printf("#endif\n");
/* Compute power-of-2 table (exponent) */
v = 1;
@@ -120,9 +114,7 @@ int main(int argc, char *argv[])
}
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gfexp);\n");
- printf("#endif\n");
/* Compute log-of-2 table */
printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -140,9 +132,7 @@ int main(int argc, char *argv[])
}
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gflog);\n");
- printf("#endif\n");
/* Compute inverse table x^-1 == x^254 */
printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -155,9 +145,7 @@ int main(int argc, char *argv[])
}
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gfinv);\n");
- printf("#endif\n");
/* Compute inv(2^x + 1) (exponent-xor-inverse) table */
printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -169,9 +157,7 @@ int main(int argc, char *argv[])
(j == 7) ? '\n' : ' ');
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gfexi);\n");
- printf("#endif\n");
return 0;
}
diff --git a/lib/raid6/mmx.c b/lib/raid6/mmx.c
index 3a5bf53a297b..e411f0cfbd95 100644
--- a/lib/raid6/mmx.c
+++ b/lib/raid6/mmx.c
@@ -14,7 +14,7 @@
#ifdef CONFIG_X86_32
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
/* Shared with raid6/sse1.c */
const struct raid6_mmx_constants {
diff --git a/lib/raid6/neon.c b/lib/raid6/neon.c
index 6d9474ce6da9..47b8bb0afc65 100644
--- a/lib/raid6/neon.c
+++ b/lib/raid6/neon.c
@@ -6,13 +6,7 @@
*/
#include <linux/raid/pq.h>
-
-#ifdef __KERNEL__
#include <asm/simd.h>
-#else
-#define scoped_ksimd()
-#define cpu_has_neon() (1)
-#endif
/*
* There are 2 reasons these wrappers are kept in a separate compilation unit
diff --git a/lib/raid6/recov_avx2.c b/lib/raid6/recov_avx2.c
index 97d598d2535c..19fbd9c4dce6 100644
--- a/lib/raid6/recov_avx2.c
+++ b/lib/raid6/recov_avx2.c
@@ -5,7 +5,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static int raid6_has_avx2(void)
{
diff --git a/lib/raid6/recov_avx512.c b/lib/raid6/recov_avx512.c
index 7986120ca444..143f4976b2ad 100644
--- a/lib/raid6/recov_avx512.c
+++ b/lib/raid6/recov_avx512.c
@@ -7,7 +7,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static int raid6_has_avx512(void)
{
diff --git a/lib/raid6/recov_loongarch_simd.c b/lib/raid6/recov_loongarch_simd.c
index 93dc515997a1..eb3a1e79f01f 100644
--- a/lib/raid6/recov_loongarch_simd.c
+++ b/lib/raid6/recov_loongarch_simd.c
@@ -11,7 +11,8 @@
*/
#include <linux/raid/pq.h>
-#include "loongarch.h"
+#include <asm/cpu-features.h>
+#include <asm/fpu.h>
/*
* Unlike with the syndrome calculation algorithms, there's no boot-time
diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c
index 9d99aeabd31a..13d5df718c15 100644
--- a/lib/raid6/recov_neon.c
+++ b/lib/raid6/recov_neon.c
@@ -5,14 +5,8 @@
*/
#include <linux/raid/pq.h>
-
-#ifdef __KERNEL__
#include <asm/simd.h>
#include "neon.h"
-#else
-#define scoped_ksimd()
-#define cpu_has_neon() (1)
-#endif
static int raid6_has_neon(void)
{
diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c
index 2e849185c32b..146cdbf465bd 100644
--- a/lib/raid6/recov_ssse3.c
+++ b/lib/raid6/recov_ssse3.c
@@ -4,7 +4,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static int raid6_has_ssse3(void)
{
diff --git a/lib/raid6/rvv.h b/lib/raid6/rvv.h
index 6d0708a2c8a4..b0a71b375962 100644
--- a/lib/raid6/rvv.h
+++ b/lib/raid6/rvv.h
@@ -7,17 +7,8 @@
* Definitions for RISC-V RAID-6 code
*/
-#ifdef __KERNEL__
-#include <asm/vector.h>
-#else
-#define kernel_vector_begin()
-#define kernel_vector_end()
-#include <sys/auxv.h>
-#include <asm/hwcap.h>
-#define has_vector() (getauxval(AT_HWCAP) & COMPAT_HWCAP_ISA_V)
-#endif
-
#include <linux/raid/pq.h>
+#include <asm/vector.h>
static int rvv_has_vector(void)
{
diff --git a/lib/raid6/sse1.c b/lib/raid6/sse1.c
index 692fa3a93bf0..794d5cfa0306 100644
--- a/lib/raid6/sse1.c
+++ b/lib/raid6/sse1.c
@@ -19,7 +19,7 @@
#ifdef CONFIG_X86_32
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
/* Defined in raid6/mmx.c */
extern const struct raid6_mmx_constants {
diff --git a/lib/raid6/sse2.c b/lib/raid6/sse2.c
index 2930220249c9..f9edf8a8d1c4 100644
--- a/lib/raid6/sse2.c
+++ b/lib/raid6/sse2.c
@@ -13,7 +13,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static const struct raid6_sse_constants {
u64 x1d[2];
diff --git a/lib/raid6/vpermxor.uc b/lib/raid6/vpermxor.uc
index 1bfb127fbfe8..a8e76b1c956e 100644
--- a/lib/raid6/vpermxor.uc
+++ b/lib/raid6/vpermxor.uc
@@ -25,10 +25,8 @@
#include <altivec.h>
#include <asm/ppc-opcode.h>
-#ifdef __KERNEL__
#include <asm/cputable.h>
#include <asm/switch_to.h>
-#endif
typedef vector unsigned char unative_t;
#define NSIZE sizeof(unative_t)
@@ -85,13 +83,8 @@ int raid6_have_altivec_vpermxor(void);
int raid6_have_altivec_vpermxor(void)
{
/* Check if arch has both altivec and the vpermxor instructions */
-# ifdef __KERNEL__
return (cpu_has_feature(CPU_FTR_ALTIVEC_COMP) &&
cpu_has_feature(CPU_FTR_ARCH_207S));
-# else
- return 1;
-#endif
-
}
#endif
diff --git a/lib/raid6/x86.h b/lib/raid6/x86.h
deleted file mode 100644
index 9a6ff37115e7..000000000000
--- a/lib/raid6/x86.h
+++ /dev/null
@@ -1,75 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* ----------------------------------------------------------------------- *
- *
- * Copyright 2002-2004 H. Peter Anvin - All Rights Reserved
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * raid6/x86.h
- *
- * Definitions common to x86 and x86-64 RAID-6 code only
- */
-
-#ifndef LINUX_RAID_RAID6X86_H
-#define LINUX_RAID_RAID6X86_H
-
-#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
-
-#ifdef __KERNEL__ /* Real code */
-
-#include <asm/fpu/api.h>
-
-#else /* Dummy code for user space testing */
-
-static inline void kernel_fpu_begin(void)
-{
-}
-
-static inline void kernel_fpu_end(void)
-{
-}
-
-#define __aligned(x) __attribute__((aligned(x)))
-
-#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR (0*32+24) /* FXSAVE and FXRSTOR instructions
- * (fast save and restore) */
-#define X86_FEATURE_XMM (0*32+25) /* Streaming SIMD Extensions */
-#define X86_FEATURE_XMM2 (0*32+26) /* Streaming SIMD Extensions-2 */
-#define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_SSSE3 (4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_AVX2 (9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_AVX512F (9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_AVX512DQ (9*32+17) /* AVX-512 DQ (Double/Quad granular)
- * Instructions
- */
-#define X86_FEATURE_AVX512BW (9*32+30) /* AVX-512 BW (Byte/Word granular)
- * Instructions
- */
-#define X86_FEATURE_AVX512VL (9*32+31) /* AVX-512 VL (128/256 Vector Length)
- * Extensions
- */
-#define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */
-
-/* Should work well enough on modern CPUs for testing */
-static inline int boot_cpu_has(int flag)
-{
- u32 eax, ebx, ecx, edx;
-
- eax = (flag & 0x100) ? 7 :
- (flag & 0x20) ? 0x80000001 : 1;
- ecx = 0;
-
- asm volatile("cpuid"
- : "+a" (eax), "=b" (ebx), "=d" (edx), "+c" (ecx));
-
- return ((flag & 0x100 ? ebx :
- (flag & 0x80) ? ecx : edx) >> (flag & 31)) & 1;
-}
-
-#endif /* ndef __KERNEL__ */
-
-#endif
-#endif
--
2.53.0
^ permalink raw reply related
* cleanup the RAID6 P/Q library v3
From: Christoph Hellwig @ 2026-05-18 5:17 UTC (permalink / raw)
To: Andrew Morton
Cc: Catalin Marinas, Will Deacon, Ard Biesheuvel, Huacai Chen,
WANG Xuerui, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Paul Walmsley,
Palmer Dabbelt, Albert Ou, Alexandre Ghiti, Heiko Carstens,
Vasily Gorbik, Alexander Gordeev, Christian Borntraeger,
Sven Schnelle, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, H. Peter Anvin, Herbert Xu, Dan Williams,
Chris Mason, David Sterba, Arnd Bergmann, Song Liu, Yu Kuai,
Li Nan, linux-kernel, linux-arm-kernel, loongarch, linuxppc-dev,
linux-riscv, linux-s390, linux-crypto, linux-btrfs, linux-arch,
linux-raid
Hi all,
this series cleans up the RAID6 P/Q library to match the recent updates
to the RAID 5 XOR library and other CRC/crypto libraries. This includes
providing properly documented external interfaces, hiding the internals,
using static_call instead of indirect calls and turning the user space
test suite into an in-kernel kunit test which is also extended to
improve coverage.
Note that this changes registration so that non-priority algorithms are
not registered, which greatly helps with the benchmark time at boot time.
I'd like to encourage all architecture maintainers to see if they can
further optimized this by registering as few as possible algorithms when
there is a clear benefit in optimized or more unrolled implementations.
This series sits on top of the "cleanup the RAID5 XOR library v3" series.
A git tree is also available here:
git://git.infradead.org/users/hch/misc.git lib-raid6
Gitweb:
https://git.infradead.org/?p=users/hch/misc.git;a=shortlog;h=refs/heads/lib-raid6
Changes since v2:
- merge two patches that should have been one
- split out enforcing the 4-device minimum into a well-documented patch
explaining the rationale
- drop the btrfs patch to restrict the number of devices again
- fix them module description for the kunit test
- add -I $(src) to fix out of srctree builds for architectures with
headers in the architecture-specific directories
- always add the least optimized/unrolled algorithms first to keep the
existing no-benchmark behavior
- drop the delayed benchmarking for now to avoid corner cases
- improve a few commit messages
Changes since v1:
- fix arm64 objdir != srcdir builds
- call the kunit module raid6_kunit.ko from the beginning
- update MAINTAINERS
- don't require preemptible context and apply the same restrictions as
the merged version of the XOR API
- fix the arm64 default in Kconfig
- pick the last registered (and presumably most optimized) algorithm when
benchmarking is disabled
- port over the randomization fixes from the XOR series
- misc other kunit cleanups
- require at least 4 devices for RAID6 to skip broken special cases
Diffstat:
b/Documentation/crypto/async-tx-api.rst | 4
b/MAINTAINERS | 2
b/crypto/async_tx/async_pq.c | 9
b/crypto/async_tx/async_raid6_recov.c | 9
b/drivers/dma/bcm-sba-raid.c | 1
b/drivers/md/raid5.c | 4
b/fs/btrfs/raid56.c | 8
b/include/linux/raid/pq.h | 216 ------------
b/include/linux/raid/pq_tables.h | 19 +
b/lib/Kconfig | 11
b/lib/Makefile | 1
b/lib/raid/Kconfig | 33 +
b/lib/raid/Makefile | 2
b/lib/raid/raid6/Makefile | 128 +++++++
b/lib/raid/raid6/algos.c | 377 ++++++++++++++++++++++
b/lib/raid/raid6/algos.h | 41 ++
b/lib/raid/raid6/arm/neon.c | 23 -
b/lib/raid/raid6/arm/neon.uc | 2
b/lib/raid/raid6/arm/pq_arch.h | 21 +
b/lib/raid/raid6/arm/recov_neon.c | 27 -
b/lib/raid/raid6/arm/recov_neon_inner.c | 2
b/lib/raid/raid6/arm64/pq_arch.h | 1
b/lib/raid/raid6/int.uc | 10
b/lib/raid/raid6/loongarch/loongarch_simd.c | 31 -
b/lib/raid/raid6/loongarch/pq_arch.h | 23 +
b/lib/raid/raid6/loongarch/recov_loongarch_simd.c | 39 --
b/lib/raid/raid6/mktables.c | 28 -
b/lib/raid/raid6/powerpc/altivec.uc | 32 -
b/lib/raid/raid6/powerpc/pq_arch.h | 32 +
b/lib/raid/raid6/powerpc/vpermxor.uc | 29 -
b/lib/raid/raid6/recov.c | 62 ---
b/lib/raid/raid6/riscv/pq_arch.h | 21 +
b/lib/raid/raid6/riscv/recov_rvv.c | 14
b/lib/raid/raid6/riscv/rvv.h | 26 -
b/lib/raid/raid6/s390/pq_arch.h | 15
b/lib/raid/raid6/s390/recov_s390xc.c | 14
b/lib/raid/raid6/s390/s390vx.uc | 15
b/lib/raid/raid6/tests/Makefile | 3
b/lib/raid/raid6/tests/raid6_kunit.c | 321 ++++++++++++++++++
b/lib/raid/raid6/x86/avx2.c | 47 --
b/lib/raid/raid6/x86/avx512.c | 57 +--
b/lib/raid/raid6/x86/mmx.c | 39 --
b/lib/raid/raid6/x86/pq_arch.h | 96 +++++
b/lib/raid/raid6/x86/recov_avx2.c | 22 -
b/lib/raid/raid6/x86/recov_avx512.c | 26 -
b/lib/raid/raid6/x86/recov_ssse3.c | 23 -
b/lib/raid/raid6/x86/sse1.c | 49 --
b/lib/raid/raid6/x86/sse2.c | 47 --
lib/raid6/Makefile | 83 ----
lib/raid6/algos.c | 291 ----------------
lib/raid6/loongarch.h | 38 --
lib/raid6/test/.gitignore | 3
lib/raid6/test/Makefile | 156 ---------
lib/raid6/test/test.c | 152 --------
lib/raid6/x86.h | 75 ----
55 files changed, 1349 insertions(+), 1511 deletions(-)
^ permalink raw reply
* [PATCH 01/18] raid6: turn the userspace test harness into a kunit test
From: Christoph Hellwig @ 2026-05-18 5:17 UTC (permalink / raw)
To: Andrew Morton
Cc: Catalin Marinas, Will Deacon, Ard Biesheuvel, Huacai Chen,
WANG Xuerui, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Paul Walmsley,
Palmer Dabbelt, Albert Ou, Alexandre Ghiti, Heiko Carstens,
Vasily Gorbik, Alexander Gordeev, Christian Borntraeger,
Sven Schnelle, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, H. Peter Anvin, Herbert Xu, Dan Williams,
Chris Mason, David Sterba, Arnd Bergmann, Song Liu, Yu Kuai,
Li Nan, linux-kernel, linux-arm-kernel, loongarch, linuxppc-dev,
linux-riscv, linux-s390, linux-crypto, linux-btrfs, linux-arch,
linux-raid
In-Reply-To: <20260518051804.462141-1-hch@lst.de>
Currently the raid6 code can be compiled as userspace code to run the
test suite. Convert that to be a kunit case with minimal changes to
avoid mutating global state so that we can drop this requirement.
Note that this is not a good kunit test case yet and will need a lot more
work, but that is deferred until the raid6 code is moved to it's new
place, which is easier if the userspace makefile doesn't need adjustments
for the new location first.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Ard Biesheuvel <ardb@kernel.org> # kunit only on arm64
---
include/linux/raid/pq.h | 3 -
lib/Kconfig | 11 +++
lib/raid6/Makefile | 2 +-
lib/raid6/algos.c | 5 +-
lib/raid6/recov.c | 34 ---------
lib/raid6/test/Makefile | 155 +--------------------------------------
lib/raid6/test/test.c | 158 +++++++++++++++++++++-------------------
7 files changed, 101 insertions(+), 267 deletions(-)
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 2467b3be15c9..08c5995ea980 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -144,7 +144,6 @@ extern const struct raid6_calls raid6_neonx8;
/* Algorithm list */
extern const struct raid6_calls * const raid6_algos[];
extern const struct raid6_recov_calls *const raid6_recov_algos[];
-int raid6_select_algo(void);
/* Return values from chk_syndrome */
#define RAID6_OK 0
@@ -165,8 +164,6 @@ extern void (*raid6_2data_recov)(int disks, size_t bytes, int faila, int failb,
void **ptrs);
extern void (*raid6_datap_recov)(int disks, size_t bytes, int faila,
void **ptrs);
-void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
- void **ptrs);
/* Some definitions to allow code to be compiled for testing in userspace */
#ifndef __KERNEL__
diff --git a/lib/Kconfig b/lib/Kconfig
index 00a9509636c1..bffe015a6c10 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -11,6 +11,17 @@ menu "Library routines"
config RAID6_PQ
tristate
+config RAID6_PQ_KUNIT_TEST
+ tristate "KUnit tests for RAID6 PQ functions" if !KUNIT_ALL_TESTS
+ depends on KUNIT
+ depends on RAID6_PQ
+ default KUNIT_ALL_TESTS
+ help
+ Unit tests for the RAID6 PQ library functions.
+
+ This is intended to help people writing architecture-specific
+ optimized versions. If unsure, say N.
+
config RAID6_PQ_BENCHMARK
bool "Automatically choose fastest RAID6 PQ functions"
depends on RAID6_PQ
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 5be0a4e60ab1..6fd048c127b6 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_RAID6_PQ) += raid6_pq.o
+obj-$(CONFIG_RAID6_PQ) += raid6_pq.o test/
raid6_pq-y += algos.o recov.o tables.o int1.o int2.o int4.o \
int8.o
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 799e0e5eac26..5a9f4882e18d 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -19,6 +19,7 @@
#include <linux/module.h>
#include <linux/gfp.h>
#endif
+#include <kunit/visibility.h>
struct raid6_calls raid6_call;
EXPORT_SYMBOL_GPL(raid6_call);
@@ -86,6 +87,7 @@ const struct raid6_calls * const raid6_algos[] = {
&raid6_intx1,
NULL
};
+EXPORT_SYMBOL_IF_KUNIT(raid6_algos);
void (*raid6_2data_recov)(int, size_t, int, int, void **);
EXPORT_SYMBOL_GPL(raid6_2data_recov);
@@ -119,6 +121,7 @@ const struct raid6_recov_calls *const raid6_recov_algos[] = {
&raid6_recov_intx1,
NULL
};
+EXPORT_SYMBOL_IF_KUNIT(raid6_recov_algos);
#ifdef __KERNEL__
#define RAID6_TIME_JIFFIES_LG2 4
@@ -239,7 +242,7 @@ static inline const struct raid6_calls *raid6_choose_gen(
/* Try to pick the best algorithm */
/* This code uses the gfmul table as convenient data set to abuse */
-int __init raid6_select_algo(void)
+static int __init raid6_select_algo(void)
{
const int disks = RAID6_TEST_DISKS;
diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c
index b5e47c008b41..8d113196632e 100644
--- a/lib/raid6/recov.c
+++ b/lib/raid6/recov.c
@@ -99,37 +99,3 @@ const struct raid6_recov_calls raid6_recov_intx1 = {
.name = "intx1",
.priority = 0,
};
-
-#ifndef __KERNEL__
-/* Testing only */
-
-/* Recover two failed blocks. */
-void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, void **ptrs)
-{
- if ( faila > failb ) {
- int tmp = faila;
- faila = failb;
- failb = tmp;
- }
-
- if ( failb == disks-1 ) {
- if ( faila == disks-2 ) {
- /* P+Q failure. Just rebuild the syndrome. */
- raid6_call.gen_syndrome(disks, bytes, ptrs);
- } else {
- /* data+Q failure. Reconstruct data from P,
- then rebuild syndrome. */
- /* NOT IMPLEMENTED - equivalent to RAID-5 */
- }
- } else {
- if ( failb == disks-2 ) {
- /* data+P failure. */
- raid6_datap_recov(disks, bytes, faila, ptrs);
- } else {
- /* data+data failure. */
- raid6_2data_recov(disks, bytes, faila, failb, ptrs);
- }
- }
-}
-
-#endif
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index 09bbe2b14cce..520381ea71d7 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -1,156 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-#
-# This is a simple Makefile to test some of the RAID-6 code
-# from userspace.
-#
-pound := \#
+obj-$(CONFIG_RAID6_PQ_KUNIT_TEST) += raid6_kunit.o
-# Adjust as desired
-CC = gcc
-OPTFLAGS = -O2
-CFLAGS = -I.. -I ../../../include -g $(OPTFLAGS)
-LD = ld
-AWK = awk -f
-AR = ar
-RANLIB = ranlib
-OBJS = int1.o int2.o int4.o int8.o int16.o int32.o recov.o algos.o tables.o
-
-ARCH := $(shell uname -m 2>/dev/null | sed -e /s/i.86/i386/)
-ifeq ($(ARCH),i386)
- CFLAGS += -DCONFIG_X86_32
- IS_X86 = yes
-endif
-ifeq ($(ARCH),x86_64)
- CFLAGS += -DCONFIG_X86_64
- IS_X86 = yes
-endif
-
-ifeq ($(ARCH),arm)
- CFLAGS += -I../../../arch/arm/include -mfpu=neon
- HAS_NEON = yes
-endif
-ifeq ($(ARCH),aarch64)
- CFLAGS += -I../../../arch/arm64/include
- HAS_NEON = yes
-endif
-
-ifeq ($(findstring riscv,$(ARCH)),riscv)
- CFLAGS += -I../../../arch/riscv/include -DCONFIG_RISCV=1
- HAS_RVV = yes
-endif
-
-ifeq ($(findstring ppc,$(ARCH)),ppc)
- CFLAGS += -I../../../arch/powerpc/include
- HAS_ALTIVEC := $(shell printf '$(pound)include <altivec.h>\nvector int a;\n' |\
- gcc -c -x c - >/dev/null && rm ./-.o && echo yes)
-endif
-
-ifeq ($(ARCH),loongarch64)
- CFLAGS += -I../../../arch/loongarch/include -DCONFIG_LOONGARCH=1
- CFLAGS += $(shell echo 'vld $$vr0, $$zero, 0' | \
- gcc -c -x assembler - >/dev/null 2>&1 && \
- rm ./-.o && echo -DCONFIG_CPU_HAS_LSX=1)
- CFLAGS += $(shell echo 'xvld $$xr0, $$zero, 0' | \
- gcc -c -x assembler - >/dev/null 2>&1 && \
- rm ./-.o && echo -DCONFIG_CPU_HAS_LASX=1)
-endif
-
-ifeq ($(IS_X86),yes)
- OBJS += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o avx512.o recov_avx512.o
- CFLAGS += -DCONFIG_X86
-else ifeq ($(HAS_NEON),yes)
- OBJS += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
- CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1
-else ifeq ($(HAS_ALTIVEC),yes)
- CFLAGS += -DCONFIG_ALTIVEC
- OBJS += altivec1.o altivec2.o altivec4.o altivec8.o \
- vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
-else ifeq ($(ARCH),loongarch64)
- OBJS += loongarch_simd.o recov_loongarch_simd.o
-else ifeq ($(HAS_RVV),yes)
- OBJS += rvv.o recov_rvv.o
- CFLAGS += -DCONFIG_RISCV_ISA_V=1
-endif
-
-.c.o:
- $(CC) $(CFLAGS) -c -o $@ $<
-
-%.c: ../%.c
- cp -f $< $@
-
-%.uc: ../%.uc
- cp -f $< $@
-
-all: raid6.a raid6test
-
-raid6.a: $(OBJS)
- rm -f $@
- $(AR) cq $@ $^
- $(RANLIB) $@
-
-raid6test: test.c raid6.a
- $(CC) $(CFLAGS) -o raid6test $^
-
-neon1.c: neon.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=1 < neon.uc > $@
-
-neon2.c: neon.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=2 < neon.uc > $@
-
-neon4.c: neon.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=4 < neon.uc > $@
-
-neon8.c: neon.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=8 < neon.uc > $@
-
-altivec1.c: altivec.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=1 < altivec.uc > $@
-
-altivec2.c: altivec.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=2 < altivec.uc > $@
-
-altivec4.c: altivec.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=4 < altivec.uc > $@
-
-altivec8.c: altivec.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=8 < altivec.uc > $@
-
-vpermxor1.c: vpermxor.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=1 < vpermxor.uc > $@
-
-vpermxor2.c: vpermxor.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=2 < vpermxor.uc > $@
-
-vpermxor4.c: vpermxor.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=4 < vpermxor.uc > $@
-
-vpermxor8.c: vpermxor.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=8 < vpermxor.uc > $@
-
-int1.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=1 < int.uc > $@
-
-int2.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=2 < int.uc > $@
-
-int4.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=4 < int.uc > $@
-
-int8.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=8 < int.uc > $@
-
-int16.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=16 < int.uc > $@
-
-int32.c: int.uc ../unroll.awk
- $(AWK) ../unroll.awk -vN=32 < int.uc > $@
-
-tables.c: mktables
- ./mktables > tables.c
-
-clean:
- rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c vpermxor*.c neon*.c tables.c raid6test
-
-spotless: clean
- rm -f *~
+raid6_kunit-y += test.o
diff --git a/lib/raid6/test/test.c b/lib/raid6/test/test.c
index 841a55242aba..9db287b4a48f 100644
--- a/lib/raid6/test/test.c
+++ b/lib/raid6/test/test.c
@@ -1,43 +1,37 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- * Copyright 2002-2007 H. Peter Anvin - All Rights Reserved
- *
- * ----------------------------------------------------------------------- */
-
/*
- * raid6test.c
+ * Copyright 2002-2007 H. Peter Anvin - All Rights Reserved
*
- * Test RAID-6 recovery with various algorithms
+ * Test RAID-6 recovery algorithms.
*/
-#include <stdlib.h>
-#include <stdio.h>
-#include <string.h>
+#include <kunit/test.h>
+#include <linux/prandom.h>
#include <linux/raid/pq.h>
-#define NDISKS 16 /* Including P and Q */
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
+
+#define RAID6_KUNIT_SEED 42
-const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+#define NDISKS 16 /* Including P and Q */
-char *dataptrs[NDISKS];
-char data[NDISKS][PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
-char recovi[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
-char recovj[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static struct rnd_state rng;
+static void *dataptrs[NDISKS];
+static char data[NDISKS][PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static char recovi[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static char recovj[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
static void makedata(int start, int stop)
{
- int i, j;
+ int i;
for (i = start; i <= stop; i++) {
- for (j = 0; j < PAGE_SIZE; j++)
- data[i][j] = rand();
-
+ prandom_bytes_state(&rng, data[i], PAGE_SIZE);
dataptrs[i] = data[i];
}
}
-static char disk_type(int d)
+static char member_type(int d)
{
switch (d) {
case NDISKS-2:
@@ -49,104 +43,118 @@ static char disk_type(int d)
}
}
-static int test_disks(int i, int j)
+static void test_disks(struct kunit *test, const struct raid6_calls *calls,
+ const struct raid6_recov_calls *ra, int faila, int failb)
{
- int erra, errb;
-
memset(recovi, 0xf0, PAGE_SIZE);
memset(recovj, 0xba, PAGE_SIZE);
- dataptrs[i] = recovi;
- dataptrs[j] = recovj;
-
- raid6_dual_recov(NDISKS, PAGE_SIZE, i, j, (void **)&dataptrs);
-
- erra = memcmp(data[i], recovi, PAGE_SIZE);
- errb = memcmp(data[j], recovj, PAGE_SIZE);
-
- if (i < NDISKS-2 && j == NDISKS-1) {
- /* We don't implement the DQ failure scenario, since it's
- equivalent to a RAID-5 failure (XOR, then recompute Q) */
- erra = errb = 0;
+ dataptrs[faila] = recovi;
+ dataptrs[failb] = recovj;
+
+ if (failb == NDISKS - 1) {
+ /*
+ * We don't implement the data+Q failure scenario, since it
+ * is equivalent to a RAID-5 failure (XOR, then recompute Q).
+ */
+ if (faila != NDISKS - 2)
+ goto skip;
+
+ /* P+Q failure. Just rebuild the syndrome. */
+ calls->gen_syndrome(NDISKS, PAGE_SIZE, dataptrs);
+ } else if (failb == NDISKS - 2) {
+ /* data+P failure. */
+ ra->datap(NDISKS, PAGE_SIZE, faila, dataptrs);
} else {
- printf("algo=%-8s faila=%3d(%c) failb=%3d(%c) %s\n",
- raid6_call.name,
- i, disk_type(i),
- j, disk_type(j),
- (!erra && !errb) ? "OK" :
- !erra ? "ERRB" :
- !errb ? "ERRA" : "ERRAB");
+ /* data+data failure. */
+ ra->data2(NDISKS, PAGE_SIZE, faila, failb, dataptrs);
}
- dataptrs[i] = data[i];
- dataptrs[j] = data[j];
-
- return erra || errb;
+ KUNIT_EXPECT_MEMEQ_MSG(test, data[faila], recovi, PAGE_SIZE,
+ "algo=%-8s/%-8s faila miscompared: %3d[%c] (failb=%3d[%c])\n",
+ calls->name, ra->name,
+ faila, member_type(faila),
+ failb, member_type(failb));
+ KUNIT_EXPECT_MEMEQ_MSG(test, data[failb], recovj, PAGE_SIZE,
+ "algo=%-8s/%-8s failb miscompared: %3d[%c] (faila=%3d[%c])\n",
+ calls->name, ra->name,
+ failb, member_type(failb),
+ faila, member_type(faila));
+
+skip:
+ dataptrs[faila] = data[faila];
+ dataptrs[failb] = data[failb];
}
-int main(int argc, char *argv[])
+static void raid6_test(struct kunit *test)
{
const struct raid6_calls *const *algo;
const struct raid6_recov_calls *const *ra;
int i, j, p1, p2;
- int err = 0;
-
- makedata(0, NDISKS-1);
for (ra = raid6_recov_algos; *ra; ra++) {
if ((*ra)->valid && !(*ra)->valid())
continue;
- raid6_2data_recov = (*ra)->data2;
- raid6_datap_recov = (*ra)->datap;
-
- printf("using recovery %s\n", (*ra)->name);
-
for (algo = raid6_algos; *algo; algo++) {
- if ((*algo)->valid && !(*algo)->valid())
- continue;
+ const struct raid6_calls *calls = *algo;
- raid6_call = **algo;
+ if (calls->valid && !calls->valid())
+ continue;
/* Nuke syndromes */
- memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE);
+ memset(data[NDISKS - 2], 0xee, PAGE_SIZE);
+ memset(data[NDISKS - 1], 0xee, PAGE_SIZE);
/* Generate assumed good syndrome */
- raid6_call.gen_syndrome(NDISKS, PAGE_SIZE,
+ calls->gen_syndrome(NDISKS, PAGE_SIZE,
(void **)&dataptrs);
for (i = 0; i < NDISKS-1; i++)
for (j = i+1; j < NDISKS; j++)
- err += test_disks(i, j);
+ test_disks(test, calls, *ra, i, j);
- if (!raid6_call.xor_syndrome)
+ if (!calls->xor_syndrome)
continue;
for (p1 = 0; p1 < NDISKS-2; p1++)
for (p2 = p1; p2 < NDISKS-2; p2++) {
/* Simulate rmw run */
- raid6_call.xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
+ calls->xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
(void **)&dataptrs);
makedata(p1, p2);
- raid6_call.xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
+ calls->xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
(void **)&dataptrs);
for (i = 0; i < NDISKS-1; i++)
for (j = i+1; j < NDISKS; j++)
- err += test_disks(i, j);
+ test_disks(test, calls,
+ *ra, i, j);
}
}
- printf("\n");
}
+}
- printf("\n");
- /* Pick the best algorithm test */
- raid6_select_algo();
-
- if (err)
- printf("\n*** ERRORS FOUND ***\n");
+static struct kunit_case raid6_test_cases[] = {
+ KUNIT_CASE(raid6_test),
+ {},
+};
- return err;
+static int raid6_suite_init(struct kunit_suite *suite)
+{
+ prandom_seed_state(&rng, RAID6_KUNIT_SEED);
+ makedata(0, NDISKS - 1);
+ return 0;
}
+
+static struct kunit_suite raid6_test_suite = {
+ .name = "raid6",
+ .test_cases = raid6_test_cases,
+ .suite_init = raid6_suite_init,
+};
+kunit_test_suite(raid6_test_suite);
+
+MODULE_DESCRIPTION("Unit test for the RAID P/Q library functions");
+MODULE_LICENSE("GPL");
--
2.53.0
^ permalink raw reply related
* [PATCH 02/18] raid6: remove __KERNEL__ ifdefs
From: Christoph Hellwig @ 2026-05-18 5:17 UTC (permalink / raw)
To: Andrew Morton
Cc: Catalin Marinas, Will Deacon, Ard Biesheuvel, Huacai Chen,
WANG Xuerui, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Paul Walmsley,
Palmer Dabbelt, Albert Ou, Alexandre Ghiti, Heiko Carstens,
Vasily Gorbik, Alexander Gordeev, Christian Borntraeger,
Sven Schnelle, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, H. Peter Anvin, Herbert Xu, Dan Williams,
Chris Mason, David Sterba, Arnd Bergmann, Song Liu, Yu Kuai,
Li Nan, linux-kernel, linux-arm-kernel, loongarch, linuxppc-dev,
linux-riscv, linux-s390, linux-crypto, linux-btrfs, linux-arch,
linux-raid
In-Reply-To: <20260518051804.462141-1-hch@lst.de>
With the test code ported to kernel space, none of this is required.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Ard Biesheuvel <ardb@kernel.org> # kunit only on arm64
---
include/linux/raid/pq.h | 90 --------------------------------
lib/raid6/algos.c | 12 -----
lib/raid6/altivec.uc | 10 +---
lib/raid6/avx2.c | 2 +-
lib/raid6/avx512.c | 2 +-
lib/raid6/loongarch.h | 38 --------------
lib/raid6/loongarch_simd.c | 3 +-
lib/raid6/mktables.c | 14 -----
lib/raid6/mmx.c | 2 +-
lib/raid6/neon.c | 6 ---
lib/raid6/recov_avx2.c | 2 +-
lib/raid6/recov_avx512.c | 2 +-
lib/raid6/recov_loongarch_simd.c | 3 +-
lib/raid6/recov_neon.c | 6 ---
lib/raid6/recov_ssse3.c | 2 +-
lib/raid6/rvv.h | 11 +---
lib/raid6/sse1.c | 2 +-
lib/raid6/sse2.c | 2 +-
lib/raid6/vpermxor.uc | 7 ---
lib/raid6/x86.h | 75 --------------------------
20 files changed, 15 insertions(+), 276 deletions(-)
delete mode 100644 lib/raid6/loongarch.h
delete mode 100644 lib/raid6/x86.h
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 08c5995ea980..d26788fada58 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -8,8 +8,6 @@
#ifndef LINUX_RAID_RAID6_H
#define LINUX_RAID_RAID6_H
-#ifdef __KERNEL__
-
#include <linux/blkdev.h>
#include <linux/mm.h>
@@ -19,59 +17,6 @@ static inline void *raid6_get_zero_page(void)
return page_address(ZERO_PAGE(0));
}
-#else /* ! __KERNEL__ */
-/* Used for testing in user space */
-
-#include <errno.h>
-#include <inttypes.h>
-#include <stddef.h>
-#include <string.h>
-#include <sys/mman.h>
-#include <sys/time.h>
-#include <sys/types.h>
-
-/* Not standard, but glibc defines it */
-#define BITS_PER_LONG __WORDSIZE
-
-typedef uint8_t u8;
-typedef uint16_t u16;
-typedef uint32_t u32;
-typedef uint64_t u64;
-
-#ifndef PAGE_SIZE
-# define PAGE_SIZE 4096
-#endif
-#ifndef PAGE_SHIFT
-# define PAGE_SHIFT 12
-#endif
-extern const char raid6_empty_zero_page[PAGE_SIZE];
-
-#define __init
-#define __exit
-#ifndef __attribute_const__
-# define __attribute_const__ __attribute__((const))
-#endif
-#define noinline __attribute__((noinline))
-
-#define preempt_enable()
-#define preempt_disable()
-#define cpu_has_feature(x) 1
-#define enable_kernel_altivec()
-#define disable_kernel_altivec()
-
-#undef EXPORT_SYMBOL
-#define EXPORT_SYMBOL(sym)
-#undef EXPORT_SYMBOL_GPL
-#define EXPORT_SYMBOL_GPL(sym)
-#define MODULE_LICENSE(licence)
-#define MODULE_DESCRIPTION(desc)
-#define subsys_initcall(x)
-#define module_exit(x)
-
-#define IS_ENABLED(x) (x)
-#define CONFIG_RAID6_PQ_BENCHMARK 1
-#endif /* __KERNEL__ */
-
/* Routine choices */
struct raid6_calls {
void (*gen_syndrome)(int, size_t, void **);
@@ -165,39 +110,4 @@ extern void (*raid6_2data_recov)(int disks, size_t bytes, int faila, int failb,
extern void (*raid6_datap_recov)(int disks, size_t bytes, int faila,
void **ptrs);
-/* Some definitions to allow code to be compiled for testing in userspace */
-#ifndef __KERNEL__
-
-# define jiffies raid6_jiffies()
-# define printk printf
-# define pr_err(format, ...) fprintf(stderr, format, ## __VA_ARGS__)
-# define pr_info(format, ...) fprintf(stdout, format, ## __VA_ARGS__)
-# define GFP_KERNEL 0
-# define __get_free_pages(x, y) ((unsigned long)mmap(NULL, PAGE_SIZE << (y), \
- PROT_READ|PROT_WRITE, \
- MAP_PRIVATE|MAP_ANONYMOUS,\
- 0, 0))
-# define free_pages(x, y) munmap((void *)(x), PAGE_SIZE << (y))
-
-static inline void cpu_relax(void)
-{
- /* Nothing */
-}
-
-#undef HZ
-#define HZ 1000
-static inline uint32_t raid6_jiffies(void)
-{
- struct timeval tv;
- gettimeofday(&tv, NULL);
- return tv.tv_sec*1000 + tv.tv_usec/1000;
-}
-
-static inline void *raid6_get_zero_page(void)
-{
- return raid6_empty_zero_page;
-}
-
-#endif /* ! __KERNEL__ */
-
#endif /* LINUX_RAID_RAID6_H */
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 5a9f4882e18d..985c60bb00a4 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -12,13 +12,8 @@
*/
#include <linux/raid/pq.h>
-#ifndef __KERNEL__
-#include <sys/mman.h>
-#include <stdio.h>
-#else
#include <linux/module.h>
#include <linux/gfp.h>
-#endif
#include <kunit/visibility.h>
struct raid6_calls raid6_call;
@@ -123,14 +118,7 @@ const struct raid6_recov_calls *const raid6_recov_algos[] = {
};
EXPORT_SYMBOL_IF_KUNIT(raid6_recov_algos);
-#ifdef __KERNEL__
#define RAID6_TIME_JIFFIES_LG2 4
-#else
-/* Need more time to be stable in userspace */
-#define RAID6_TIME_JIFFIES_LG2 9
-#define time_before(x, y) ((x) < (y))
-#endif
-
#define RAID6_TEST_DISKS 8
#define RAID6_TEST_DISKS_ORDER 3
diff --git a/lib/raid6/altivec.uc b/lib/raid6/altivec.uc
index d20ed0d11411..2c59963e58f9 100644
--- a/lib/raid6/altivec.uc
+++ b/lib/raid6/altivec.uc
@@ -27,10 +27,8 @@
#ifdef CONFIG_ALTIVEC
#include <altivec.h>
-#ifdef __KERNEL__
-# include <asm/cputable.h>
-# include <asm/switch_to.h>
-#endif /* __KERNEL__ */
+#include <asm/cputable.h>
+#include <asm/switch_to.h>
/*
* This is the C data type to use. We use a vector of
@@ -113,11 +111,7 @@ int raid6_have_altivec(void);
int raid6_have_altivec(void)
{
/* This assumes either all CPUs have Altivec or none does */
-# ifdef __KERNEL__
return cpu_has_feature(CPU_FTR_ALTIVEC);
-# else
- return 1;
-# endif
}
#endif
diff --git a/lib/raid6/avx2.c b/lib/raid6/avx2.c
index 059024234dce..a1a5213918af 100644
--- a/lib/raid6/avx2.c
+++ b/lib/raid6/avx2.c
@@ -14,7 +14,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static const struct raid6_avx2_constants {
u64 x1d[4];
diff --git a/lib/raid6/avx512.c b/lib/raid6/avx512.c
index 009bd0adeebf..874998bcd7d7 100644
--- a/lib/raid6/avx512.c
+++ b/lib/raid6/avx512.c
@@ -18,7 +18,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static const struct raid6_avx512_constants {
u64 x1d[8];
diff --git a/lib/raid6/loongarch.h b/lib/raid6/loongarch.h
deleted file mode 100644
index acfc33ce7056..000000000000
--- a/lib/raid6/loongarch.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
- *
- * raid6/loongarch.h
- *
- * Definitions common to LoongArch RAID-6 code only
- */
-
-#ifndef _LIB_RAID6_LOONGARCH_H
-#define _LIB_RAID6_LOONGARCH_H
-
-#ifdef __KERNEL__
-
-#include <asm/cpu-features.h>
-#include <asm/fpu.h>
-
-#else /* for user-space testing */
-
-#include <sys/auxv.h>
-
-/* have to supply these defines for glibc 2.37- and musl */
-#ifndef HWCAP_LOONGARCH_LSX
-#define HWCAP_LOONGARCH_LSX (1 << 4)
-#endif
-#ifndef HWCAP_LOONGARCH_LASX
-#define HWCAP_LOONGARCH_LASX (1 << 5)
-#endif
-
-#define kernel_fpu_begin()
-#define kernel_fpu_end()
-
-#define cpu_has_lsx (getauxval(AT_HWCAP) & HWCAP_LOONGARCH_LSX)
-#define cpu_has_lasx (getauxval(AT_HWCAP) & HWCAP_LOONGARCH_LASX)
-
-#endif /* __KERNEL__ */
-
-#endif /* _LIB_RAID6_LOONGARCH_H */
diff --git a/lib/raid6/loongarch_simd.c b/lib/raid6/loongarch_simd.c
index aa5d9f924ca3..72f4d92d4876 100644
--- a/lib/raid6/loongarch_simd.c
+++ b/lib/raid6/loongarch_simd.c
@@ -10,7 +10,8 @@
*/
#include <linux/raid/pq.h>
-#include "loongarch.h"
+#include <asm/cpu-features.h>
+#include <asm/fpu.h>
/*
* The vector algorithms are currently priority 0, which means the generic
diff --git a/lib/raid6/mktables.c b/lib/raid6/mktables.c
index 3be03793237c..3de1dbf6846c 100644
--- a/lib/raid6/mktables.c
+++ b/lib/raid6/mktables.c
@@ -56,9 +56,7 @@ int main(int argc, char *argv[])
uint8_t v;
uint8_t exptbl[256], invtbl[256];
- printf("#ifdef __KERNEL__\n");
printf("#include <linux/export.h>\n");
- printf("#endif\n");
printf("#include <linux/raid/pq.h>\n");
/* Compute multiplication table */
@@ -76,9 +74,7 @@ int main(int argc, char *argv[])
printf("\t},\n");
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gfmul);\n");
- printf("#endif\n");
/* Compute vector multiplication table */
printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -101,9 +97,7 @@ int main(int argc, char *argv[])
printf("\t},\n");
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_vgfmul);\n");
- printf("#endif\n");
/* Compute power-of-2 table (exponent) */
v = 1;
@@ -120,9 +114,7 @@ int main(int argc, char *argv[])
}
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gfexp);\n");
- printf("#endif\n");
/* Compute log-of-2 table */
printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -140,9 +132,7 @@ int main(int argc, char *argv[])
}
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gflog);\n");
- printf("#endif\n");
/* Compute inverse table x^-1 == x^254 */
printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -155,9 +145,7 @@ int main(int argc, char *argv[])
}
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gfinv);\n");
- printf("#endif\n");
/* Compute inv(2^x + 1) (exponent-xor-inverse) table */
printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -169,9 +157,7 @@ int main(int argc, char *argv[])
(j == 7) ? '\n' : ' ');
}
printf("};\n");
- printf("#ifdef __KERNEL__\n");
printf("EXPORT_SYMBOL(raid6_gfexi);\n");
- printf("#endif\n");
return 0;
}
diff --git a/lib/raid6/mmx.c b/lib/raid6/mmx.c
index 3a5bf53a297b..e411f0cfbd95 100644
--- a/lib/raid6/mmx.c
+++ b/lib/raid6/mmx.c
@@ -14,7 +14,7 @@
#ifdef CONFIG_X86_32
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
/* Shared with raid6/sse1.c */
const struct raid6_mmx_constants {
diff --git a/lib/raid6/neon.c b/lib/raid6/neon.c
index 6d9474ce6da9..47b8bb0afc65 100644
--- a/lib/raid6/neon.c
+++ b/lib/raid6/neon.c
@@ -6,13 +6,7 @@
*/
#include <linux/raid/pq.h>
-
-#ifdef __KERNEL__
#include <asm/simd.h>
-#else
-#define scoped_ksimd()
-#define cpu_has_neon() (1)
-#endif
/*
* There are 2 reasons these wrappers are kept in a separate compilation unit
diff --git a/lib/raid6/recov_avx2.c b/lib/raid6/recov_avx2.c
index 97d598d2535c..19fbd9c4dce6 100644
--- a/lib/raid6/recov_avx2.c
+++ b/lib/raid6/recov_avx2.c
@@ -5,7 +5,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static int raid6_has_avx2(void)
{
diff --git a/lib/raid6/recov_avx512.c b/lib/raid6/recov_avx512.c
index 7986120ca444..143f4976b2ad 100644
--- a/lib/raid6/recov_avx512.c
+++ b/lib/raid6/recov_avx512.c
@@ -7,7 +7,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static int raid6_has_avx512(void)
{
diff --git a/lib/raid6/recov_loongarch_simd.c b/lib/raid6/recov_loongarch_simd.c
index 93dc515997a1..eb3a1e79f01f 100644
--- a/lib/raid6/recov_loongarch_simd.c
+++ b/lib/raid6/recov_loongarch_simd.c
@@ -11,7 +11,8 @@
*/
#include <linux/raid/pq.h>
-#include "loongarch.h"
+#include <asm/cpu-features.h>
+#include <asm/fpu.h>
/*
* Unlike with the syndrome calculation algorithms, there's no boot-time
diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c
index 9d99aeabd31a..13d5df718c15 100644
--- a/lib/raid6/recov_neon.c
+++ b/lib/raid6/recov_neon.c
@@ -5,14 +5,8 @@
*/
#include <linux/raid/pq.h>
-
-#ifdef __KERNEL__
#include <asm/simd.h>
#include "neon.h"
-#else
-#define scoped_ksimd()
-#define cpu_has_neon() (1)
-#endif
static int raid6_has_neon(void)
{
diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c
index 2e849185c32b..146cdbf465bd 100644
--- a/lib/raid6/recov_ssse3.c
+++ b/lib/raid6/recov_ssse3.c
@@ -4,7 +4,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static int raid6_has_ssse3(void)
{
diff --git a/lib/raid6/rvv.h b/lib/raid6/rvv.h
index 6d0708a2c8a4..b0a71b375962 100644
--- a/lib/raid6/rvv.h
+++ b/lib/raid6/rvv.h
@@ -7,17 +7,8 @@
* Definitions for RISC-V RAID-6 code
*/
-#ifdef __KERNEL__
-#include <asm/vector.h>
-#else
-#define kernel_vector_begin()
-#define kernel_vector_end()
-#include <sys/auxv.h>
-#include <asm/hwcap.h>
-#define has_vector() (getauxval(AT_HWCAP) & COMPAT_HWCAP_ISA_V)
-#endif
-
#include <linux/raid/pq.h>
+#include <asm/vector.h>
static int rvv_has_vector(void)
{
diff --git a/lib/raid6/sse1.c b/lib/raid6/sse1.c
index 692fa3a93bf0..794d5cfa0306 100644
--- a/lib/raid6/sse1.c
+++ b/lib/raid6/sse1.c
@@ -19,7 +19,7 @@
#ifdef CONFIG_X86_32
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
/* Defined in raid6/mmx.c */
extern const struct raid6_mmx_constants {
diff --git a/lib/raid6/sse2.c b/lib/raid6/sse2.c
index 2930220249c9..f9edf8a8d1c4 100644
--- a/lib/raid6/sse2.c
+++ b/lib/raid6/sse2.c
@@ -13,7 +13,7 @@
*/
#include <linux/raid/pq.h>
-#include "x86.h"
+#include <asm/fpu/api.h>
static const struct raid6_sse_constants {
u64 x1d[2];
diff --git a/lib/raid6/vpermxor.uc b/lib/raid6/vpermxor.uc
index 1bfb127fbfe8..a8e76b1c956e 100644
--- a/lib/raid6/vpermxor.uc
+++ b/lib/raid6/vpermxor.uc
@@ -25,10 +25,8 @@
#include <altivec.h>
#include <asm/ppc-opcode.h>
-#ifdef __KERNEL__
#include <asm/cputable.h>
#include <asm/switch_to.h>
-#endif
typedef vector unsigned char unative_t;
#define NSIZE sizeof(unative_t)
@@ -85,13 +83,8 @@ int raid6_have_altivec_vpermxor(void);
int raid6_have_altivec_vpermxor(void)
{
/* Check if arch has both altivec and the vpermxor instructions */
-# ifdef __KERNEL__
return (cpu_has_feature(CPU_FTR_ALTIVEC_COMP) &&
cpu_has_feature(CPU_FTR_ARCH_207S));
-# else
- return 1;
-#endif
-
}
#endif
diff --git a/lib/raid6/x86.h b/lib/raid6/x86.h
deleted file mode 100644
index 9a6ff37115e7..000000000000
--- a/lib/raid6/x86.h
+++ /dev/null
@@ -1,75 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* ----------------------------------------------------------------------- *
- *
- * Copyright 2002-2004 H. Peter Anvin - All Rights Reserved
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * raid6/x86.h
- *
- * Definitions common to x86 and x86-64 RAID-6 code only
- */
-
-#ifndef LINUX_RAID_RAID6X86_H
-#define LINUX_RAID_RAID6X86_H
-
-#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
-
-#ifdef __KERNEL__ /* Real code */
-
-#include <asm/fpu/api.h>
-
-#else /* Dummy code for user space testing */
-
-static inline void kernel_fpu_begin(void)
-{
-}
-
-static inline void kernel_fpu_end(void)
-{
-}
-
-#define __aligned(x) __attribute__((aligned(x)))
-
-#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR (0*32+24) /* FXSAVE and FXRSTOR instructions
- * (fast save and restore) */
-#define X86_FEATURE_XMM (0*32+25) /* Streaming SIMD Extensions */
-#define X86_FEATURE_XMM2 (0*32+26) /* Streaming SIMD Extensions-2 */
-#define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_SSSE3 (4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_AVX2 (9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_AVX512F (9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_AVX512DQ (9*32+17) /* AVX-512 DQ (Double/Quad granular)
- * Instructions
- */
-#define X86_FEATURE_AVX512BW (9*32+30) /* AVX-512 BW (Byte/Word granular)
- * Instructions
- */
-#define X86_FEATURE_AVX512VL (9*32+31) /* AVX-512 VL (128/256 Vector Length)
- * Extensions
- */
-#define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */
-
-/* Should work well enough on modern CPUs for testing */
-static inline int boot_cpu_has(int flag)
-{
- u32 eax, ebx, ecx, edx;
-
- eax = (flag & 0x100) ? 7 :
- (flag & 0x20) ? 0x80000001 : 1;
- ecx = 0;
-
- asm volatile("cpuid"
- : "+a" (eax), "=b" (ebx), "=d" (edx), "+c" (ecx));
-
- return ((flag & 0x100 ? ebx :
- (flag & 0x80) ? ecx : edx) >> (flag & 31)) & 1;
-}
-
-#endif /* ndef __KERNEL__ */
-
-#endif
-#endif
--
2.53.0
^ permalink raw reply related
* [PATCH 03/18] raid6: move to lib/raid/
From: Christoph Hellwig @ 2026-05-18 5:17 UTC (permalink / raw)
To: Andrew Morton
Cc: Catalin Marinas, Will Deacon, Ard Biesheuvel, Huacai Chen,
WANG Xuerui, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Paul Walmsley,
Palmer Dabbelt, Albert Ou, Alexandre Ghiti, Heiko Carstens,
Vasily Gorbik, Alexander Gordeev, Christian Borntraeger,
Sven Schnelle, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, H. Peter Anvin, Herbert Xu, Dan Williams,
Chris Mason, David Sterba, Arnd Bergmann, Song Liu, Yu Kuai,
Li Nan, linux-kernel, linux-arm-kernel, loongarch, linuxppc-dev,
linux-riscv, linux-s390, linux-crypto, linux-btrfs, linux-arch,
linux-raid
In-Reply-To: <20260518051804.462141-1-hch@lst.de>
Move the raid6 code to live in lib/raid/ with the XOR code, and change
the internal organization so that each architecture has a subdirectory
similar to the CRC, crypto and XOR libraries, and fix up the Makefile to
only build files actually needed.
Also move the kunit test case from the history test/ subdirectory to
tests/ and use the normal naming scheme for it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Ard Biesheuvel <ardb@kernel.org> # kunit only on arm64
---
MAINTAINERS | 2 +-
lib/Kconfig | 22 ----
lib/Makefile | 1 -
lib/raid/Kconfig | 22 ++++
lib/raid/Makefile | 2 +-
lib/{ => raid}/raid6/.gitignore | 0
lib/raid/raid6/Makefile | 122 ++++++++++++++++++
lib/{ => raid}/raid6/algos.c | 0
lib/{raid6 => raid/raid6/arm}/neon.c | 0
lib/{raid6 => raid/raid6/arm}/neon.h | 0
lib/{raid6 => raid/raid6/arm}/neon.uc | 2 +-
lib/{raid6 => raid/raid6/arm}/recov_neon.c | 2 +-
.../raid6/arm}/recov_neon_inner.c | 2 +-
lib/{ => raid}/raid6/int.uc | 0
.../raid6/loongarch}/loongarch_simd.c | 0
.../raid6/loongarch}/recov_loongarch_simd.c | 0
lib/{ => raid}/raid6/mktables.c | 0
lib/{raid6 => raid/raid6/powerpc}/altivec.uc | 4 -
lib/{raid6 => raid/raid6/powerpc}/vpermxor.uc | 3 -
lib/{ => raid}/raid6/recov.c | 0
lib/{raid6 => raid/raid6/riscv}/recov_rvv.c | 0
lib/{raid6 => raid/raid6/riscv}/rvv.c | 0
lib/{raid6 => raid/raid6/riscv}/rvv.h | 0
lib/{raid6 => raid/raid6/s390}/recov_s390xc.c | 0
lib/{raid6 => raid/raid6/s390}/s390vx.uc | 0
lib/{raid6/test => raid/raid6/tests}/Makefile | 2 -
.../test.c => raid/raid6/tests/raid6_kunit.c} | 0
lib/{ => raid}/raid6/unroll.awk | 0
lib/{raid6 => raid/raid6/x86}/avx2.c | 0
lib/{raid6 => raid/raid6/x86}/avx512.c | 0
lib/{raid6 => raid/raid6/x86}/mmx.c | 4 -
lib/{raid6 => raid/raid6/x86}/recov_avx2.c | 0
lib/{raid6 => raid/raid6/x86}/recov_avx512.c | 0
lib/{raid6 => raid/raid6/x86}/recov_ssse3.c | 0
lib/{raid6 => raid/raid6/x86}/sse1.c | 4 -
lib/{raid6 => raid/raid6/x86}/sse2.c | 0
lib/raid6/Makefile | 83 ------------
lib/raid6/test/.gitignore | 3 -
38 files changed, 149 insertions(+), 131 deletions(-)
rename lib/{ => raid}/raid6/.gitignore (100%)
create mode 100644 lib/raid/raid6/Makefile
rename lib/{ => raid}/raid6/algos.c (100%)
rename lib/{raid6 => raid/raid6/arm}/neon.c (100%)
rename lib/{raid6 => raid/raid6/arm}/neon.h (100%)
rename lib/{raid6 => raid/raid6/arm}/neon.uc (99%)
rename lib/{raid6 => raid/raid6/arm}/recov_neon.c (99%)
rename lib/{raid6 => raid/raid6/arm}/recov_neon_inner.c (99%)
rename lib/{ => raid}/raid6/int.uc (100%)
rename lib/{raid6 => raid/raid6/loongarch}/loongarch_simd.c (100%)
rename lib/{raid6 => raid/raid6/loongarch}/recov_loongarch_simd.c (100%)
rename lib/{ => raid}/raid6/mktables.c (100%)
rename lib/{raid6 => raid/raid6/powerpc}/altivec.uc (98%)
rename lib/{raid6 => raid/raid6/powerpc}/vpermxor.uc (98%)
rename lib/{ => raid}/raid6/recov.c (100%)
rename lib/{raid6 => raid/raid6/riscv}/recov_rvv.c (100%)
rename lib/{raid6 => raid/raid6/riscv}/rvv.c (100%)
rename lib/{raid6 => raid/raid6/riscv}/rvv.h (100%)
rename lib/{raid6 => raid/raid6/s390}/recov_s390xc.c (100%)
rename lib/{raid6 => raid/raid6/s390}/s390vx.uc (100%)
rename lib/{raid6/test => raid/raid6/tests}/Makefile (77%)
rename lib/{raid6/test/test.c => raid/raid6/tests/raid6_kunit.c} (100%)
rename lib/{ => raid}/raid6/unroll.awk (100%)
rename lib/{raid6 => raid/raid6/x86}/avx2.c (100%)
rename lib/{raid6 => raid/raid6/x86}/avx512.c (100%)
rename lib/{raid6 => raid/raid6/x86}/mmx.c (99%)
rename lib/{raid6 => raid/raid6/x86}/recov_avx2.c (100%)
rename lib/{raid6 => raid/raid6/x86}/recov_avx512.c (100%)
rename lib/{raid6 => raid/raid6/x86}/recov_ssse3.c (100%)
rename lib/{raid6 => raid/raid6/x86}/sse1.c (99%)
rename lib/{raid6 => raid/raid6/x86}/sse2.c (100%)
delete mode 100644 lib/raid6/Makefile
delete mode 100644 lib/raid6/test/.gitignore
diff --git a/MAINTAINERS b/MAINTAINERS
index c2c6d79275c6..e6f778339a3f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24821,7 +24821,7 @@ F: drivers/md/md*
F: drivers/md/raid*
F: include/linux/raid/
F: include/uapi/linux/raid/
-F: lib/raid6/
+F: lib/raid/raid6/
SOLIDRUN CLEARFOG SUPPORT
M: Russell King <linux@armlinux.org.uk>
diff --git a/lib/Kconfig b/lib/Kconfig
index bffe015a6c10..b87f954a14bc 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -8,28 +8,6 @@ config BINARY_PRINTF
menu "Library routines"
-config RAID6_PQ
- tristate
-
-config RAID6_PQ_KUNIT_TEST
- tristate "KUnit tests for RAID6 PQ functions" if !KUNIT_ALL_TESTS
- depends on KUNIT
- depends on RAID6_PQ
- default KUNIT_ALL_TESTS
- help
- Unit tests for the RAID6 PQ library functions.
-
- This is intended to help people writing architecture-specific
- optimized versions. If unsure, say N.
-
-config RAID6_PQ_BENCHMARK
- bool "Automatically choose fastest RAID6 PQ functions"
- depends on RAID6_PQ
- default y
- help
- Benchmark all available RAID6 PQ functions on init and choose the
- fastest one.
-
config LINEAR_RANGES
tristate
diff --git a/lib/Makefile b/lib/Makefile
index f33a24bf1c19..6e72d2c1cce7 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -167,7 +167,6 @@ obj-$(CONFIG_LZ4_DECOMPRESS) += lz4/
obj-$(CONFIG_ZSTD_COMPRESS) += zstd/
obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd/
obj-$(CONFIG_XZ_DEC) += xz/
-obj-$(CONFIG_RAID6_PQ) += raid6/
lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o
lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o
diff --git a/lib/raid/Kconfig b/lib/raid/Kconfig
index 5ab2b0a7be4c..e39f6d667792 100644
--- a/lib/raid/Kconfig
+++ b/lib/raid/Kconfig
@@ -28,3 +28,25 @@ config XOR_KUNIT_TEST
This is intended to help people writing architecture-specific
optimized versions. If unsure, say N.
+
+config RAID6_PQ
+ tristate
+
+config RAID6_PQ_KUNIT_TEST
+ tristate "KUnit tests for RAID6 PQ functions" if !KUNIT_ALL_TESTS
+ depends on KUNIT
+ depends on RAID6_PQ
+ default KUNIT_ALL_TESTS
+ help
+ Unit tests for the RAID6 PQ library functions.
+
+ This is intended to help people writing architecture-specific
+ optimized versions. If unsure, say N.
+
+config RAID6_PQ_BENCHMARK
+ bool "Automatically choose fastest RAID6 PQ functions"
+ depends on RAID6_PQ
+ default y
+ help
+ Benchmark all available RAID6 PQ functions on init and choose the
+ fastest one.
diff --git a/lib/raid/Makefile b/lib/raid/Makefile
index 3540fe846dc4..6fc5eeb53df0 100644
--- a/lib/raid/Makefile
+++ b/lib/raid/Makefile
@@ -1,3 +1,3 @@
# SPDX-License-Identifier: GPL-2.0
-obj-y += xor/
+obj-y += xor/ raid6/
diff --git a/lib/raid6/.gitignore b/lib/raid/raid6/.gitignore
similarity index 100%
rename from lib/raid6/.gitignore
rename to lib/raid/raid6/.gitignore
diff --git a/lib/raid/raid6/Makefile b/lib/raid/raid6/Makefile
new file mode 100644
index 000000000000..7cb31b8a5c17
--- /dev/null
+++ b/lib/raid/raid6/Makefile
@@ -0,0 +1,122 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ccflags-y += -I $(src)
+
+obj-$(CONFIG_RAID6_PQ) += raid6_pq.o tests/
+
+raid6_pq-y += algos.o tables.o
+
+# generic integer generation and recovery implementation
+raid6_pq-y += int1.o int2.o int4.o int8.o
+raid6_pq-y += recov.o
+
+# architecture-specific generation and recovery implementations:
+raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += arm/neon.o \
+ arm/neon1.o \
+ arm/neon2.o \
+ arm/neon4.o \
+ arm/neon8.o \
+ arm/recov_neon.o \
+ arm/recov_neon_inner.o
+raid6_pq-$(CONFIG_LOONGARCH) += loongarch/loongarch_simd.o \
+ loongarch/recov_loongarch_simd.o
+raid6_pq-$(CONFIG_ALTIVEC) += powerpc/altivec1.o \
+ powerpc/altivec2.o \
+ powerpc/altivec4.o \
+ powerpc/altivec8.o \
+ powerpc/vpermxor1.o \
+ powerpc/vpermxor2.o \
+ powerpc/vpermxor4.o \
+ powerpc/vpermxor8.o
+raid6_pq-$(CONFIG_RISCV_ISA_V) += riscv/rvv.o \
+ riscv/recov_rvv.o
+raid6_pq-$(CONFIG_S390) += s390/s390vx8.o \
+ s390/recov_s390xc.o
+ifeq ($(CONFIG_X86),y)
+raid6_pq-$(CONFIG_X86_32) += x86/mmx.o \
+ x86/sse1.o
+endif
+raid6_pq-$(CONFIG_X86) += x86/sse2.o \
+ x86/avx2.o \
+ x86/avx512.o \
+ x86/recov_ssse3.o \
+ x86/recov_avx2.o \
+ x86/recov_avx512.o
+
+hostprogs += mktables
+
+CFLAGS_arm/neon1.o += $(CC_FLAGS_FPU)
+CFLAGS_arm/neon2.o += $(CC_FLAGS_FPU)
+CFLAGS_arm/neon4.o += $(CC_FLAGS_FPU)
+CFLAGS_arm/neon8.o += $(CC_FLAGS_FPU)
+CFLAGS_arm/recov_neon_inner.o += $(CC_FLAGS_FPU)
+CFLAGS_REMOVE_arm/neon1.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_arm/neon2.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_arm/neon4.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_arm/neon8.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_arm/recov_neon_inner.o += $(CC_FLAGS_NO_FPU)
+
+ifeq ($(CONFIG_ALTIVEC),y)
+altivec_flags := -maltivec $(call cc-option,-mabi=altivec)
+# Enable <altivec.h>
+altivec_flags += -isystem $(shell $(CC) -print-file-name=include)
+
+CFLAGS_powerpc/altivec1.o += $(altivec_flags)
+CFLAGS_powerpc/altivec2.o += $(altivec_flags)
+CFLAGS_powerpc/altivec4.o += $(altivec_flags)
+CFLAGS_powerpc/altivec8.o += $(altivec_flags)
+CFLAGS_powerpc/vpermxor1.o += $(altivec_flags)
+CFLAGS_powerpc/vpermxor2.o += $(altivec_flags)
+CFLAGS_powerpc/vpermxor4.o += $(altivec_flags)
+CFLAGS_powerpc/vpermxor8.o += $(altivec_flags)
+
+ifdef CONFIG_CC_IS_CLANG
+# clang ppc port does not yet support -maltivec when -msoft-float is
+# enabled. A future release of clang will resolve this
+# https://llvm.org/pr31177
+CFLAGS_REMOVE_powerpc/altivec1.o += -msoft-float
+CFLAGS_REMOVE_powerpc/altivec2.o += -msoft-float
+CFLAGS_REMOVE_powerpc/altivec4.o += -msoft-float
+CFLAGS_REMOVE_powerpc/altivec8.o += -msoft-float
+CFLAGS_REMOVE_powerpc/vpermxor1.o += -msoft-float
+CFLAGS_REMOVE_powerpc/vpermxor2.o += -msoft-float
+CFLAGS_REMOVE_powerpc/vpermxor4.o += -msoft-float
+CFLAGS_REMOVE_powerpc/vpermxor8.o += -msoft-float
+endif # CONFIG_CC_IS_CLANG
+endif # CONFIG_ALTIVEC
+
+quiet_cmd_mktable = TABLE $@
+ cmd_mktable = $(obj)/mktables > $@
+
+targets += tables.c
+$(obj)/tables.c: $(obj)/mktables FORCE
+ $(call if_changed,mktable)
+
+quiet_cmd_unroll = UNROLL $@
+ cmd_unroll = $(AWK) -v N=$* -f $(src)/unroll.awk < $< > $@
+
+targets += int1.c int2.c int4.c int8.c
+$(obj)/int%.c: $(src)/int.uc $(src)/unroll.awk FORCE
+ $(call if_changed,unroll)
+
+targets += arm/neon1.c arm/neon2.c arm/neon4.c arm/neon8.c
+$(obj)/arm/neon%.c: $(src)/arm/neon.uc $(src)/unroll.awk FORCE
+ $(call if_changed,unroll)
+
+targets += powerpc/altivec1.c \
+ powerpc/altivec2.c \
+ powerpc/altivec4.c \
+ powerpc/altivec8.c
+$(obj)/powerpc/altivec%.c: $(src)/powerpc/altivec.uc $(src)/unroll.awk FORCE
+ $(call if_changed,unroll)
+
+targets += powerpc/vpermxor1.c \
+ powerpc/vpermxor2.c \
+ powerpc/vpermxor4.c \
+ powerpc/vpermxor8.c
+$(obj)/powerpc/vpermxor%.c: $(src)/powerpc/vpermxor.uc $(src)/unroll.awk FORCE
+ $(call if_changed,unroll)
+
+targets += s390/s390vx8.c
+$(obj)/s390/s390vx%.c: $(src)/s390/s390vx.uc $(src)/unroll.awk FORCE
+ $(call if_changed,unroll)
diff --git a/lib/raid6/algos.c b/lib/raid/raid6/algos.c
similarity index 100%
rename from lib/raid6/algos.c
rename to lib/raid/raid6/algos.c
diff --git a/lib/raid6/neon.c b/lib/raid/raid6/arm/neon.c
similarity index 100%
rename from lib/raid6/neon.c
rename to lib/raid/raid6/arm/neon.c
diff --git a/lib/raid6/neon.h b/lib/raid/raid6/arm/neon.h
similarity index 100%
rename from lib/raid6/neon.h
rename to lib/raid/raid6/arm/neon.h
diff --git a/lib/raid6/neon.uc b/lib/raid/raid6/arm/neon.uc
similarity index 99%
rename from lib/raid6/neon.uc
rename to lib/raid/raid6/arm/neon.uc
index 355270af0cd6..14a9fc2c60fa 100644
--- a/lib/raid6/neon.uc
+++ b/lib/raid/raid6/arm/neon.uc
@@ -25,7 +25,7 @@
*/
#include <arm_neon.h>
-#include "neon.h"
+#include "arm/neon.h"
typedef uint8x16_t unative_t;
diff --git a/lib/raid6/recov_neon.c b/lib/raid/raid6/arm/recov_neon.c
similarity index 99%
rename from lib/raid6/recov_neon.c
rename to lib/raid/raid6/arm/recov_neon.c
index 13d5df718c15..5a48fcc762e8 100644
--- a/lib/raid6/recov_neon.c
+++ b/lib/raid/raid6/arm/recov_neon.c
@@ -6,7 +6,7 @@
#include <linux/raid/pq.h>
#include <asm/simd.h>
-#include "neon.h"
+#include "arm/neon.h"
static int raid6_has_neon(void)
{
diff --git a/lib/raid6/recov_neon_inner.c b/lib/raid/raid6/arm/recov_neon_inner.c
similarity index 99%
rename from lib/raid6/recov_neon_inner.c
rename to lib/raid/raid6/arm/recov_neon_inner.c
index f9e7e8f5a151..53c355efa7ff 100644
--- a/lib/raid6/recov_neon_inner.c
+++ b/lib/raid/raid6/arm/recov_neon_inner.c
@@ -5,7 +5,7 @@
*/
#include <arm_neon.h>
-#include "neon.h"
+#include "arm/neon.h"
#ifdef CONFIG_ARM
/*
diff --git a/lib/raid6/int.uc b/lib/raid/raid6/int.uc
similarity index 100%
rename from lib/raid6/int.uc
rename to lib/raid/raid6/int.uc
diff --git a/lib/raid6/loongarch_simd.c b/lib/raid/raid6/loongarch/loongarch_simd.c
similarity index 100%
rename from lib/raid6/loongarch_simd.c
rename to lib/raid/raid6/loongarch/loongarch_simd.c
diff --git a/lib/raid6/recov_loongarch_simd.c b/lib/raid/raid6/loongarch/recov_loongarch_simd.c
similarity index 100%
rename from lib/raid6/recov_loongarch_simd.c
rename to lib/raid/raid6/loongarch/recov_loongarch_simd.c
diff --git a/lib/raid6/mktables.c b/lib/raid/raid6/mktables.c
similarity index 100%
rename from lib/raid6/mktables.c
rename to lib/raid/raid6/mktables.c
diff --git a/lib/raid6/altivec.uc b/lib/raid/raid6/powerpc/altivec.uc
similarity index 98%
rename from lib/raid6/altivec.uc
rename to lib/raid/raid6/powerpc/altivec.uc
index 2c59963e58f9..130d3d3dd42c 100644
--- a/lib/raid6/altivec.uc
+++ b/lib/raid/raid6/powerpc/altivec.uc
@@ -24,8 +24,6 @@
#include <linux/raid/pq.h>
-#ifdef CONFIG_ALTIVEC
-
#include <altivec.h>
#include <asm/cputable.h>
#include <asm/switch_to.h>
@@ -122,5 +120,3 @@ const struct raid6_calls raid6_altivec$# = {
"altivecx$#",
0
};
-
-#endif /* CONFIG_ALTIVEC */
diff --git a/lib/raid6/vpermxor.uc b/lib/raid/raid6/powerpc/vpermxor.uc
similarity index 98%
rename from lib/raid6/vpermxor.uc
rename to lib/raid/raid6/powerpc/vpermxor.uc
index a8e76b1c956e..595f20aaf4cf 100644
--- a/lib/raid6/vpermxor.uc
+++ b/lib/raid/raid6/powerpc/vpermxor.uc
@@ -21,8 +21,6 @@
*/
#include <linux/raid/pq.h>
-#ifdef CONFIG_ALTIVEC
-
#include <altivec.h>
#include <asm/ppc-opcode.h>
#include <asm/cputable.h>
@@ -95,4 +93,3 @@ const struct raid6_calls raid6_vpermxor$# = {
"vpermxor$#",
0
};
-#endif
diff --git a/lib/raid6/recov.c b/lib/raid/raid6/recov.c
similarity index 100%
rename from lib/raid6/recov.c
rename to lib/raid/raid6/recov.c
diff --git a/lib/raid6/recov_rvv.c b/lib/raid/raid6/riscv/recov_rvv.c
similarity index 100%
rename from lib/raid6/recov_rvv.c
rename to lib/raid/raid6/riscv/recov_rvv.c
diff --git a/lib/raid6/rvv.c b/lib/raid/raid6/riscv/rvv.c
similarity index 100%
rename from lib/raid6/rvv.c
rename to lib/raid/raid6/riscv/rvv.c
diff --git a/lib/raid6/rvv.h b/lib/raid/raid6/riscv/rvv.h
similarity index 100%
rename from lib/raid6/rvv.h
rename to lib/raid/raid6/riscv/rvv.h
diff --git a/lib/raid6/recov_s390xc.c b/lib/raid/raid6/s390/recov_s390xc.c
similarity index 100%
rename from lib/raid6/recov_s390xc.c
rename to lib/raid/raid6/s390/recov_s390xc.c
diff --git a/lib/raid6/s390vx.uc b/lib/raid/raid6/s390/s390vx.uc
similarity index 100%
rename from lib/raid6/s390vx.uc
rename to lib/raid/raid6/s390/s390vx.uc
diff --git a/lib/raid6/test/Makefile b/lib/raid/raid6/tests/Makefile
similarity index 77%
rename from lib/raid6/test/Makefile
rename to lib/raid/raid6/tests/Makefile
index 520381ea71d7..87a001b22847 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid/raid6/tests/Makefile
@@ -1,5 +1,3 @@
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_RAID6_PQ_KUNIT_TEST) += raid6_kunit.o
-
-raid6_kunit-y += test.o
diff --git a/lib/raid6/test/test.c b/lib/raid/raid6/tests/raid6_kunit.c
similarity index 100%
rename from lib/raid6/test/test.c
rename to lib/raid/raid6/tests/raid6_kunit.c
diff --git a/lib/raid6/unroll.awk b/lib/raid/raid6/unroll.awk
similarity index 100%
rename from lib/raid6/unroll.awk
rename to lib/raid/raid6/unroll.awk
diff --git a/lib/raid6/avx2.c b/lib/raid/raid6/x86/avx2.c
similarity index 100%
rename from lib/raid6/avx2.c
rename to lib/raid/raid6/x86/avx2.c
diff --git a/lib/raid6/avx512.c b/lib/raid/raid6/x86/avx512.c
similarity index 100%
rename from lib/raid6/avx512.c
rename to lib/raid/raid6/x86/avx512.c
diff --git a/lib/raid6/mmx.c b/lib/raid/raid6/x86/mmx.c
similarity index 99%
rename from lib/raid6/mmx.c
rename to lib/raid/raid6/x86/mmx.c
index e411f0cfbd95..7e9810669347 100644
--- a/lib/raid6/mmx.c
+++ b/lib/raid/raid6/x86/mmx.c
@@ -11,8 +11,6 @@
* MMX implementation of RAID-6 syndrome functions
*/
-#ifdef CONFIG_X86_32
-
#include <linux/raid/pq.h>
#include <asm/fpu/api.h>
@@ -135,5 +133,3 @@ const struct raid6_calls raid6_mmxx2 = {
"mmxx2",
0
};
-
-#endif
diff --git a/lib/raid6/recov_avx2.c b/lib/raid/raid6/x86/recov_avx2.c
similarity index 100%
rename from lib/raid6/recov_avx2.c
rename to lib/raid/raid6/x86/recov_avx2.c
diff --git a/lib/raid6/recov_avx512.c b/lib/raid/raid6/x86/recov_avx512.c
similarity index 100%
rename from lib/raid6/recov_avx512.c
rename to lib/raid/raid6/x86/recov_avx512.c
diff --git a/lib/raid6/recov_ssse3.c b/lib/raid/raid6/x86/recov_ssse3.c
similarity index 100%
rename from lib/raid6/recov_ssse3.c
rename to lib/raid/raid6/x86/recov_ssse3.c
diff --git a/lib/raid6/sse1.c b/lib/raid/raid6/x86/sse1.c
similarity index 99%
rename from lib/raid6/sse1.c
rename to lib/raid/raid6/x86/sse1.c
index 794d5cfa0306..deecdd72ceec 100644
--- a/lib/raid6/sse1.c
+++ b/lib/raid/raid6/x86/sse1.c
@@ -16,8 +16,6 @@
* worthwhile as a separate implementation.
*/
-#ifdef CONFIG_X86_32
-
#include <linux/raid/pq.h>
#include <asm/fpu/api.h>
@@ -155,5 +153,3 @@ const struct raid6_calls raid6_sse1x2 = {
"sse1x2",
1 /* Has cache hints */
};
-
-#endif
diff --git a/lib/raid6/sse2.c b/lib/raid/raid6/x86/sse2.c
similarity index 100%
rename from lib/raid6/sse2.c
rename to lib/raid/raid6/x86/sse2.c
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
deleted file mode 100644
index 6fd048c127b6..000000000000
--- a/lib/raid6/Makefile
+++ /dev/null
@@ -1,83 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_RAID6_PQ) += raid6_pq.o test/
-
-raid6_pq-y += algos.o recov.o tables.o int1.o int2.o int4.o \
- int8.o
-
-raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o avx512.o recov_avx512.o
-raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o \
- vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
-raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
-raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
-raid6_pq-$(CONFIG_LOONGARCH) += loongarch_simd.o recov_loongarch_simd.o
-raid6_pq-$(CONFIG_RISCV_ISA_V) += rvv.o recov_rvv.o
-
-hostprogs += mktables
-
-ifeq ($(CONFIG_ALTIVEC),y)
-altivec_flags := -maltivec $(call cc-option,-mabi=altivec)
-# Enable <altivec.h>
-altivec_flags += -isystem $(shell $(CC) -print-file-name=include)
-
-ifdef CONFIG_CC_IS_CLANG
-# clang ppc port does not yet support -maltivec when -msoft-float is
-# enabled. A future release of clang will resolve this
-# https://llvm.org/pr31177
-CFLAGS_REMOVE_altivec1.o += -msoft-float
-CFLAGS_REMOVE_altivec2.o += -msoft-float
-CFLAGS_REMOVE_altivec4.o += -msoft-float
-CFLAGS_REMOVE_altivec8.o += -msoft-float
-CFLAGS_REMOVE_vpermxor1.o += -msoft-float
-CFLAGS_REMOVE_vpermxor2.o += -msoft-float
-CFLAGS_REMOVE_vpermxor4.o += -msoft-float
-CFLAGS_REMOVE_vpermxor8.o += -msoft-float
-endif
-endif
-
-quiet_cmd_unroll = UNROLL $@
- cmd_unroll = $(AWK) -v N=$* -f $(src)/unroll.awk < $< > $@
-
-targets += int1.c int2.c int4.c int8.c
-$(obj)/int%.c: $(src)/int.uc $(src)/unroll.awk FORCE
- $(call if_changed,unroll)
-
-CFLAGS_altivec1.o += $(altivec_flags)
-CFLAGS_altivec2.o += $(altivec_flags)
-CFLAGS_altivec4.o += $(altivec_flags)
-CFLAGS_altivec8.o += $(altivec_flags)
-targets += altivec1.c altivec2.c altivec4.c altivec8.c
-$(obj)/altivec%.c: $(src)/altivec.uc $(src)/unroll.awk FORCE
- $(call if_changed,unroll)
-
-CFLAGS_vpermxor1.o += $(altivec_flags)
-CFLAGS_vpermxor2.o += $(altivec_flags)
-CFLAGS_vpermxor4.o += $(altivec_flags)
-CFLAGS_vpermxor8.o += $(altivec_flags)
-targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c
-$(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
- $(call if_changed,unroll)
-
-CFLAGS_neon1.o += $(CC_FLAGS_FPU)
-CFLAGS_neon2.o += $(CC_FLAGS_FPU)
-CFLAGS_neon4.o += $(CC_FLAGS_FPU)
-CFLAGS_neon8.o += $(CC_FLAGS_FPU)
-CFLAGS_recov_neon_inner.o += $(CC_FLAGS_FPU)
-CFLAGS_REMOVE_neon1.o += $(CC_FLAGS_NO_FPU)
-CFLAGS_REMOVE_neon2.o += $(CC_FLAGS_NO_FPU)
-CFLAGS_REMOVE_neon4.o += $(CC_FLAGS_NO_FPU)
-CFLAGS_REMOVE_neon8.o += $(CC_FLAGS_NO_FPU)
-CFLAGS_REMOVE_recov_neon_inner.o += $(CC_FLAGS_NO_FPU)
-targets += neon1.c neon2.c neon4.c neon8.c
-$(obj)/neon%.c: $(src)/neon.uc $(src)/unroll.awk FORCE
- $(call if_changed,unroll)
-
-targets += s390vx8.c
-$(obj)/s390vx%.c: $(src)/s390vx.uc $(src)/unroll.awk FORCE
- $(call if_changed,unroll)
-
-quiet_cmd_mktable = TABLE $@
- cmd_mktable = $(obj)/mktables > $@
-
-targets += tables.c
-$(obj)/tables.c: $(obj)/mktables FORCE
- $(call if_changed,mktable)
diff --git a/lib/raid6/test/.gitignore b/lib/raid6/test/.gitignore
deleted file mode 100644
index 1b68a77f348f..000000000000
--- a/lib/raid6/test/.gitignore
+++ /dev/null
@@ -1,3 +0,0 @@
-/int.uc
-/neon.uc
-/raid6test
--
2.53.0
^ permalink raw reply related
* [PATCH 04/18] raid6: remove unused defines in pq.h
From: Christoph Hellwig @ 2026-05-18 5:17 UTC (permalink / raw)
To: Andrew Morton
Cc: Catalin Marinas, Will Deacon, Ard Biesheuvel, Huacai Chen,
WANG Xuerui, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Paul Walmsley,
Palmer Dabbelt, Albert Ou, Alexandre Ghiti, Heiko Carstens,
Vasily Gorbik, Alexander Gordeev, Christian Borntraeger,
Sven Schnelle, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, H. Peter Anvin, Herbert Xu, Dan Williams,
Chris Mason, David Sterba, Arnd Bergmann, Song Liu, Yu Kuai,
Li Nan, linux-kernel, linux-arm-kernel, loongarch, linuxppc-dev,
linux-riscv, linux-s390, linux-crypto, linux-btrfs, linux-arch,
linux-raid
In-Reply-To: <20260518051804.462141-1-hch@lst.de>
These are not used anywhere in the kernel.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Ard Biesheuvel <ardb@kernel.org> # kunit only on arm64
---
include/linux/raid/pq.h | 6 ------
1 file changed, 6 deletions(-)
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index d26788fada58..5e7e743b83f5 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -90,12 +90,6 @@ extern const struct raid6_calls raid6_neonx8;
extern const struct raid6_calls * const raid6_algos[];
extern const struct raid6_recov_calls *const raid6_recov_algos[];
-/* Return values from chk_syndrome */
-#define RAID6_OK 0
-#define RAID6_P_BAD 1
-#define RAID6_Q_BAD 2
-#define RAID6_PQ_BAD 3
-
/* Galois field tables */
extern const u8 raid6_gfmul[256][256] __attribute__((aligned(256)));
extern const u8 raid6_vgfmul[256][32] __attribute__((aligned(256)));
--
2.53.0
^ permalink raw reply related
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