Linux-ARM-Kernel Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v5 03/12] mmc: sdhci: Export sdhci_start_signal_voltage_switch() in sdhci.c
From: Gregory CLEMENT @ 2017-01-11 17:19 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <cover.8527229dae6c124f24c5e637430c2cdc86f80392.1484154449.git-series.gregory.clement@free-electrons.com>

From: Hu Ziji <huziji@marvell.com>

Export sdhci_start_signal_voltage_switch() from sdhci.c.
Thus vendor sdhci driver can implement its own signal voltage
switch routine.

Signed-off-by: Hu Ziji <huziji@marvell.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
---
 drivers/mmc/host/sdhci.c | 5 +++--
 drivers/mmc/host/sdhci.h | 2 ++
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 0e9ed0fadff9..d2338dc362f4 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1839,8 +1839,8 @@ static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
-static int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
-					     struct mmc_ios *ios)
+int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
+				      struct mmc_ios *ios)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
 	u16 ctrl;
@@ -1932,6 +1932,7 @@ static int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
 		return 0;
 	}
 }
+EXPORT_SYMBOL_GPL(sdhci_start_signal_voltage_switch);
 
 static int sdhci_card_busy(struct mmc_host *mmc)
 {
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 3563c0c384ca..e4a07543a12b 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -692,6 +692,8 @@ void sdhci_reset(struct sdhci_host *host, u8 mask);
 void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing);
 int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
 void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios);
+int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
+				      struct mmc_ios *ios);
 
 #ifdef CONFIG_PM
 extern int sdhci_suspend_host(struct sdhci_host *host);
-- 
git-series 0.9.1

^ permalink raw reply related

* [PATCH v5 02/12] mmc: sdhci: Export sdhci_set_ios() from sdhci.c
From: Gregory CLEMENT @ 2017-01-11 17:19 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <cover.8527229dae6c124f24c5e637430c2cdc86f80392.1484154449.git-series.gregory.clement@free-electrons.com>

From: Hu Ziji <huziji@marvell.com>

Export sdhci_set_ios() in sdhci.c.
Thus vendor sdhci driver can implement its own set_ios() routine.

Signed-off-by: Hu Ziji <huziji@marvell.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
---
 drivers/mmc/host/sdhci.c | 3 ++-
 drivers/mmc/host/sdhci.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 23909804ffb8..0e9ed0fadff9 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1570,7 +1570,7 @@ void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing)
 }
 EXPORT_SYMBOL_GPL(sdhci_set_uhs_signaling);
 
-static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
 	unsigned long flags;
@@ -1730,6 +1730,7 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
+EXPORT_SYMBOL_GPL(sdhci_set_ios);
 
 static int sdhci_get_cd(struct mmc_host *mmc)
 {
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 0b66f210ae82..3563c0c384ca 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -691,6 +691,7 @@ void sdhci_set_bus_width(struct sdhci_host *host, int width);
 void sdhci_reset(struct sdhci_host *host, u8 mask);
 void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing);
 int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
+void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios);
 
 #ifdef CONFIG_PM
 extern int sdhci_suspend_host(struct sdhci_host *host);
-- 
git-series 0.9.1

^ permalink raw reply related

* [PATCH v5 01/12] clk: apn806: Add eMMC clock to system controller driver
From: Gregory CLEMENT @ 2017-01-11 17:19 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <cover.8527229dae6c124f24c5e637430c2cdc86f80392.1484154449.git-series.gregory.clement@free-electrons.com>

From: Konstantin Porotchkin <kostap@marvell.com>

Add fixed clock of 400MHz to system controller driver.  This clock is
used as SD/eMMC clock source.

Signed-off-by: Konstantin Porotchkin <kostap@marvell.com>
Reviewed-by: Omri Itach <omrii@marvell.com>
Reviewed-by: Hanna Hawa <hannah@marvell.com>
[fixed up conflicts, added error handling --rmk]
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
---
 arch/arm64/boot/dts/marvell/armada-ap806.dtsi |  3 ++-
 drivers/clk/mvebu/ap806-system-controller.c   | 15 ++++++++++++++-
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index a749ba2edec4..5019c8f4acd0 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -235,7 +235,8 @@
 				#clock-cells = <1>;
 				clock-output-names = "ap-cpu-cluster-0",
 						     "ap-cpu-cluster-1",
-						     "ap-fixed", "ap-mss";
+						     "ap-fixed", "ap-mss",
+						     "ap-emmc";
 				reg = <0x6f4000 0x1000>;
 			};
 		};
diff --git a/drivers/clk/mvebu/ap806-system-controller.c b/drivers/clk/mvebu/ap806-system-controller.c
index 8181b919f062..0a785076b0c6 100644
--- a/drivers/clk/mvebu/ap806-system-controller.c
+++ b/drivers/clk/mvebu/ap806-system-controller.c
@@ -23,7 +23,7 @@
 #define AP806_SAR_REG			0x400
 #define AP806_SAR_CLKFREQ_MODE_MASK	0x1f
 
-#define AP806_CLK_NUM			4
+#define AP806_CLK_NUM			5
 
 static struct clk *ap806_clks[AP806_CLK_NUM];
 
@@ -117,6 +117,17 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev)
 		goto fail3;
 	}
 
+	/* eMMC Clock is fixed clock divided by 3 */
+	of_property_read_string_index(np, "clock-output-names",
+				      4, &name);
+	ap806_clks[4] = clk_register_fixed_factor(NULL, name, fixedclk_name,
+						  0, 1, 3);
+	if (IS_ERR(ap806_clks[4])) {
+		ret = PTR_ERR(ap806_clks[4]);
+		goto fail4;
+	}
+
+	of_clk_add_provider(np, of_clk_src_onecell_get, &ap806_clk_data);
 	ret = of_clk_add_provider(np, of_clk_src_onecell_get, &ap806_clk_data);
 	if (ret)
 		goto fail_clk_add;
@@ -124,6 +135,8 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev)
 	return 0;
 
 fail_clk_add:
+	clk_unregister_fixed_factor(ap806_clks[4]);
+fail4:
 	clk_unregister_fixed_factor(ap806_clks[3]);
 fail3:
 	clk_unregister_fixed_rate(ap806_clks[2]);
-- 
git-series 0.9.1

^ permalink raw reply related

* [PATCH v5 00/12] mmc: Add support to Marvell Xenon SD Host Controller
From: Gregory CLEMENT @ 2017-01-11 17:19 UTC (permalink / raw)
  To: linux-arm-kernel

Hello,

This the fifth version of the series adding support for the SDHCI
Xenon controller. It can be currently found on the Armada 37xx and the
Armada 7K/8K but will be also used in more Marvell SoC (and not only
the mvebu ones actually).

v4->v5:

- Remove the patch to export sdhci_execute_tuning(). It is already
  exported in v4.10.

- Introduce a patch adding a missing clock for the sdhci controller
  present on the CP master for A7K/A8K. There is no build dependency
  but obviously this patch is need to use the sdhci controller present
  on the CP part.

- Adjust Xenon return setup, to avoid being overwritten by
   sdhci_add_host().

- Change Xenon register definition prefix to "XENON_".

-  Fix typos in Xenon driver and dt-binding docs.

- Change compatible string "marvell,armada-7000-sdhci" to
  "marvell,armada-8k-sdhci". Actually the Armada 7K SoCs are a subset
  of the Armada 8K SoCs. Moreover, the use of the '000' is not
  consistent with all the other compatible string already used for the
  Armada 7K/8K family.

- Added the Tested-by from Russell King on an Armada 8K based board.

v3 -> v4:
For this version a few change have been done:
- fixes 2 bug  reported by kbuild-bot
  - remove extra of_node_put()
  - convert 0 in false for function returning boolean

- add a device tree node for the sdhci controller present on the CP
  master for A7K/A8K. It also led to rename the sdhci0 node on AP to
  ap_sdhci0 to make a distinction with the one present on CP master.

v2 -> v3
I think that now most (if not all) the remarks had been taking into
account since the second version. According to Ziji Hu, here are the
following changes:
" Changes in V3:
  Adjust and improve Xenon DT bindings. Move some caps setting from driver into
  DT. Use mmc-card sub-node to represent eMMC type.
  Remove PHY Sampling Fixed Delay Line scan in lower speed mode.
  Improve Xenon probe and ->init_card() functions.
  Export sdhci_enable_sdio_irq() and implement own SDIO IRQ control.
  Split PHY patch into two smaller patches.
  Temporarily remove AXI clock before its implementation is improved."

Besides this changes I also
- Removed the sdhci-xenon-phy.h and moved its content in the
shc-xenon-phy.c file.
- Fixed the tuning-count usage
- Managed the error case for clk_prepare_enable

For the record the change from v1 was:
" Changes in V2:
  rebase on v4.9-rc2.
  Re-write Xenon bindings. Ajust Xenon DT property naming.
  Add a new DT property to indicate eMMC card type, instead of using
  variable card_candidate.
  Clear quirks SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12 in Xenon platform data
  Add support to HS400 retuning."

Thanks,

Gregory

Gregory CLEMENT (3):
  arm64: dts: marvell: add eMMC support for Armada 37xx
  arm64: dts: marvell: add sdhci support for Armada 7K/8K
  arm64: configs: enable SDHCI driver for Xenon

Hu Ziji (8):
  mmc: sdhci: Export sdhci_set_ios() from sdhci.c
  mmc: sdhci: Export sdhci_start_signal_voltage_switch() in sdhci.c
  mmc: sdhci: Export sdhci_enable_sdio_irq() from sdhci.c
  dt: bindings: Add bindings for Marvell Xenon SD Host Controller
  mmc: sdhci-xenon: Add Marvell Xenon SDHC core functionality
  mmc: sdhci-xenon: Add support to PHYs of Marvell Xenon SDHC.
  mmc: sdhci-xenon: Add SoC PHY PAD voltage control
  MAINTAINERS: add entry for Marvell Xenon MMC Host Controller drivers

Konstantin Porotchkin (1):
  clk: apn806: Add eMMC clock to system controller driver

 Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt | 197 ++-
 MAINTAINERS                                                   |   7 +-
 arch/arm64/boot/dts/marvell/armada-3720-db.dts                |  16 +-
 arch/arm64/boot/dts/marvell/armada-37xx.dtsi                  |  11 +-
 arch/arm64/boot/dts/marvell/armada-7040-db.dts                |  14 +-
 arch/arm64/boot/dts/marvell/armada-ap806.dtsi                 |  13 +-
 arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi          |  11 +-
 arch/arm64/configs/defconfig                                  |   1 +-
 drivers/clk/mvebu/ap806-system-controller.c                   |  15 +-
 drivers/mmc/host/Kconfig                                      |   9 +-
 drivers/mmc/host/Makefile                                     |   3 +-
 drivers/mmc/host/sdhci-xenon-phy.c                            | 904 +++++++-
 drivers/mmc/host/sdhci-xenon.c                                | 634 +++++-
 drivers/mmc/host/sdhci-xenon.h                                | 109 +-
 drivers/mmc/host/sdhci.c                                      |  11 +-
 drivers/mmc/host/sdhci.h                                      |   4 +-
 16 files changed, 1953 insertions(+), 6 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
 create mode 100644 drivers/mmc/host/sdhci-xenon-phy.c
 create mode 100644 drivers/mmc/host/sdhci-xenon.c
 create mode 100644 drivers/mmc/host/sdhci-xenon.h

base-commit: 0c744ea4f77d72b3dcebb7a8f2684633ec79be88
-- 
git-series 0.9.1

^ permalink raw reply

* [PATCH] usb: dwc3 dwc3_exynos_probe() change goto labels to meaningful names
From: Javier Martinez Canillas @ 2017-01-11 17:06 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20170111164537.2981-1-shuahkh@osg.samsung.com>

Hello Shuah,

On 01/11/2017 01:45 PM, Shuah Khan wrote:
> Change goto labels to meaningful names from a series of errNs.
> 
> Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
> ---
>  drivers/usb/dwc3/dwc3-exynos.c | 22 +++++++++++-----------
>  1 file changed, 11 insertions(+), 11 deletions(-)
> 
> diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
> index f7421c2..ea50f74 100644
> --- a/drivers/usb/dwc3/dwc3-exynos.c
> +++ b/drivers/usb/dwc3/dwc3-exynos.c
> @@ -147,53 +147,53 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
>  	exynos->vdd33 = devm_regulator_get(dev, "vdd33");
>  	if (IS_ERR(exynos->vdd33)) {
>  		ret = PTR_ERR(exynos->vdd33);
> -		goto err2;
> +		goto vdd33_err;
>  	}

I think it's better to use as labels what will be done in the error path
rather than what failed. IOW, "disable_axius_clk" or "disable_clks" are
more clear than vdd33_err for me, since can give you an idea of what will
happen in the error path.

But I don't have a strong opinion and your naming is an improvement over
the current one, so:

Reviewed-by: Javier Martinez Canillas <javier@osg.samsung.com>

Best regards,
-- 
Javier Martinez Canillas
Open Source Group
Samsung Research America

^ permalink raw reply

* [PATCH v2 5/5] crypto: arm/sha2-ce - enable module autoloading based on CPU feature bits
From: Ard Biesheuvel @ 2017-01-11 17:01 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484154118-22139-1-git-send-email-ard.biesheuvel@linaro.org>

Make the module autoloadable by tying it to the CPU feature bit that
describes whether the optional instructions it relies on are implemented
by the current CPU.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/crypto/sha2-ce-glue.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c
index 0755b2d657f3..df4dcef054ae 100644
--- a/arch/arm/crypto/sha2-ce-glue.c
+++ b/arch/arm/crypto/sha2-ce-glue.c
@@ -11,6 +11,7 @@
 #include <crypto/internal/hash.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
+#include <linux/cpufeature.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 
@@ -100,8 +101,6 @@ static struct shash_alg algs[] = { {
 
 static int __init sha2_ce_mod_init(void)
 {
-	if (!(elf_hwcap2 & HWCAP2_SHA2))
-		return -ENODEV;
 	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
 }
 
@@ -110,5 +109,5 @@ static void __exit sha2_ce_mod_fini(void)
 	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
 }
 
-module_init(sha2_ce_mod_init);
+module_cpu_feature_match(SHA2, sha2_ce_mod_init);
 module_exit(sha2_ce_mod_fini);
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 4/5] crypto: arm/sha1-ce - enable module autoloading based on CPU feature bits
From: Ard Biesheuvel @ 2017-01-11 17:01 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484154118-22139-1-git-send-email-ard.biesheuvel@linaro.org>

Make the module autoloadable by tying it to the CPU feature bit that
describes whether the optional instructions it relies on are implemented
by the current CPU.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/crypto/sha1-ce-glue.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/arm/crypto/sha1-ce-glue.c b/arch/arm/crypto/sha1-ce-glue.c
index 80bc2fcd241a..555f72b5e659 100644
--- a/arch/arm/crypto/sha1-ce-glue.c
+++ b/arch/arm/crypto/sha1-ce-glue.c
@@ -11,6 +11,7 @@
 #include <crypto/internal/hash.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
+#include <linux/cpufeature.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 
@@ -82,8 +83,6 @@ static struct shash_alg alg = {
 
 static int __init sha1_ce_mod_init(void)
 {
-	if (!(elf_hwcap2 & HWCAP2_SHA1))
-		return -ENODEV;
 	return crypto_register_shash(&alg);
 }
 
@@ -92,5 +91,5 @@ static void __exit sha1_ce_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(sha1_ce_mod_init);
+module_cpu_feature_match(SHA1, sha1_ce_mod_init);
 module_exit(sha1_ce_mod_fini);
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 3/5] crypto: arm/ghash-ce - enable module autoloading based on CPU feature bits
From: Ard Biesheuvel @ 2017-01-11 17:01 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484154118-22139-1-git-send-email-ard.biesheuvel@linaro.org>

Make the module autoloadable by tying it to the CPU feature bit that
describes whether the optional instructions it relies on are implemented
by the current CPU.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/crypto/ghash-ce-glue.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index 7546b3c02466..6bac8bea9f1e 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -15,6 +15,7 @@
 #include <crypto/cryptd.h>
 #include <crypto/internal/hash.h>
 #include <crypto/gf128mul.h>
+#include <linux/cpufeature.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 
@@ -311,9 +312,6 @@ static int __init ghash_ce_mod_init(void)
 {
 	int err;
 
-	if (!(elf_hwcap2 & HWCAP2_PMULL))
-		return -ENODEV;
-
 	err = crypto_register_shash(&ghash_alg);
 	if (err)
 		return err;
@@ -334,5 +332,5 @@ static void __exit ghash_ce_mod_exit(void)
 	crypto_unregister_shash(&ghash_alg);
 }
 
-module_init(ghash_ce_mod_init);
+module_cpu_feature_match(PMULL, ghash_ce_mod_init);
 module_exit(ghash_ce_mod_exit);
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 2/5] crypto: arm/aes-ce - enable module autoloading based on CPU feature bits
From: Ard Biesheuvel @ 2017-01-11 17:01 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484154118-22139-1-git-send-email-ard.biesheuvel@linaro.org>

Make the module autoloadable by tying it to the CPU feature bit that
describes whether the optional instructions it relies on are implemented
by the current CPU.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/crypto/aes-ce-glue.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
index 8857531915bf..98c68ad101e5 100644
--- a/arch/arm/crypto/aes-ce-glue.c
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -14,6 +14,7 @@
 #include <crypto/aes.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
+#include <linux/cpufeature.h>
 #include <linux/module.h>
 #include <crypto/xts.h>
 
@@ -428,9 +429,6 @@ static int __init aes_init(void)
 	int err;
 	int i;
 
-	if (!(elf_hwcap2 & HWCAP2_AES))
-		return -ENODEV;
-
 	err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 	if (err)
 		return err;
@@ -454,5 +452,5 @@ static int __init aes_init(void)
 	return err;
 }
 
-module_init(aes_init);
+module_cpu_feature_match(AES, aes_init);
 module_exit(aes_exit);
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 1/5] ARM: wire up HWCAP2 feature bits to the CPU modalias
From: Ard Biesheuvel @ 2017-01-11 17:01 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484154118-22139-1-git-send-email-ard.biesheuvel@linaro.org>

Wire up the generic support for exposing CPU feature bits via the
modalias in /sys/device/system/cpu. This allows udev to automatically
load modules for things like crypto algorithms that are implemented
using optional instructions.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/Kconfig                  |  1 +
 arch/arm/include/asm/cpufeature.h | 32 ++++++++++++++++++++
 2 files changed, 33 insertions(+)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5fab553fd03a..3758466365ee 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -21,6 +21,7 @@ config ARM
 	select GENERIC_ALLOCATOR
 	select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_PROBE
diff --git a/arch/arm/include/asm/cpufeature.h b/arch/arm/include/asm/cpufeature.h
new file mode 100644
index 000000000000..134bd4c63d53
--- /dev/null
+++ b/arch/arm/include/asm/cpufeature.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_CPUFEATURE_H
+#define __ASM_CPUFEATURE_H
+
+#include <asm/hwcap.h>
+
+/*
+ * Due to the fact that ELF_HWCAP is a 32-bit type on ARM, and given the number
+ * of optional CPU features it defines, ARM's CPU capability bits have been
+ * distributed over separate elf_hwcap and elf_hwcap2 variables, each of which
+ * covers a subset of the available CPU features.
+ *
+ * Currently, only a few of those are suitable for automatic module loading
+ * (which is the primary use case of this facility) and those happen to be all
+ * covered by HWCAP2. So let's only expose those via the CPU modalias for now.
+ */
+#define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap2))
+#define cpu_feature(x)		ilog2(HWCAP2_ ## x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+	return elf_hwcap2 & (1UL << num);
+}
+
+#endif
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 0/5] ARM: add module autoloading support for crypto modules
From: Ard Biesheuvel @ 2017-01-11 17:01 UTC (permalink / raw)
  To: linux-arm-kernel

This series wires up the crypto modules that use the ARM 32-bit versions of
the ARMv8 Crypto Extensions to udev autoloading, by exposing the HWCAP2
feature bits via the CPU modalias. This is very similar to the arm64
implementation, with the notable exception that ARM has its CPU feature
definitions split across HWCAP and HWCAP2.

Given that the crypto feature bits are all exposed via HWCAP2, and considering
that there are currently no features exposed via HWCAP that are relevant to
udev module autoloading, exposing HWCAP2 only should be sufficient, at least
for now.

Changes since v1:
- rebase onto v4.10-rc2

Ard Biesheuvel (5):
  ARM: wire up HWCAP2 feature bits to the CPU modalias
  crypto: arm/aes-ce - enable module autoloading based on CPU feature
    bits
  crypto: arm/ghash-ce - enable module autoloading based on CPU feature
    bits
  crypto: arm/sha1-ce - enable module autoloading based on CPU feature
    bits
  crypto: arm/sha2-ce - enable module autoloading based on CPU feature
    bits

 arch/arm/Kconfig                  |  1 +
 arch/arm/crypto/aes-ce-glue.c     |  6 ++--
 arch/arm/crypto/ghash-ce-glue.c   |  6 ++--
 arch/arm/crypto/sha1-ce-glue.c    |  5 ++-
 arch/arm/crypto/sha2-ce-glue.c    |  5 ++-
 arch/arm/include/asm/cpufeature.h | 32 ++++++++++++++++++++
 6 files changed, 41 insertions(+), 14 deletions(-)
 create mode 100644 arch/arm/include/asm/cpufeature.h

-- 
2.7.4

^ permalink raw reply

* [PATCH] KVM: arm64: Increase number of memslots to 512
From: linucherian at gmail.com @ 2017-01-11 16:52 UTC (permalink / raw)
  To: linux-arm-kernel

From: Linu Cherian <linu.cherian@cavium.com>

Having only 32 memslots is a real constraint for the maximum number of
PCI devices that can be assigned to a single guest. Assuming each PCI
device/virtual function having two memory BAR regions, we could assign
only 15 devices/virtual functions to a guest.

So increase KVM_MEM_SLOTS_NUM to 512 as done in other archs like x86 and
powerpc. For this, KVM_USER_MEM_SLOTS has been changed to 508.

Signed-off-by: Linu Cherian <linu.cherian@cavium.com>
---
 arch/arm/kvm/arm.c                | 3 +++
 arch/arm64/include/asm/kvm_host.h | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 8f92efa..a19389b 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -221,6 +221,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+	case KVM_CAP_NR_MEMSLOTS:
+		r = KVM_USER_MEM_SLOTS;
+		break;
 	case KVM_CAP_MSI_DEVID:
 		if (!kvm)
 			r = -EINVAL;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e505038..88f017d 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,7 +30,7 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
-#define KVM_USER_MEM_SLOTS 32
+#define KVM_USER_MEM_SLOTS 508
 #define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HALT_POLL_NS_DEFAULT 500000
-- 
1.9.1

^ permalink raw reply related

* [PATCH] arm64: avoid increasing DMA masks above what hardware supports
From: Robin Murphy @ 2017-01-11 16:50 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <105b0b38-8c48-3355-4951-435c5dca18a4@cogentembedded.com>

On 11/01/17 16:03, Nikita Yushchenko wrote:
> 
> 
> 11.01.2017 17:50, Robin Murphy ?????:
>> On 11/01/17 13:41, Nikita Yushchenko wrote:
>>>> Yes, I think that ought to work, although the __iommu_setup_dma_ops()
>>>> call will still want a real size reflecting the default mask
>>>
>>> I see iommu_dma_ops do not define set_dma_mask.
>>>
>>> So what if setup was done for size reflecting one mask and then driver
>>> changes mask?  Will things still operate correctly?
>>
>> We've overridden dma_set_mask() at the function level, so it should
>> always apply regardless. Besides, none of the arm64 ops implement
>> .set_dma_mask anyway, so we could possibly drop the references to it
>> altogether.
>>
>> Conversely, I suppose we could just implement said callback for
>> swiotlb_dma_ops and iommu_dma_ops with the parent_dma_mask-checking
>> function and drop the HAVE_ARCH_DMA_SET_MASK override instead. I'm not
>> sure which approach is preferable - the latter seems arguably cleaner in
>> isolation, but would also be less consistent with how the coherent mask
>> has to be handled. Ho hum.
> 
> I mean, before patch is applied.
> 
> In the current mainline codebase, arm64 iommu does setup dependent on
> [default] dma_mask, but does not anyhow react on dma mask change.
> 
> I don't know much details about arm64 iommu, but from distant view this
> combination looks incorrect:
> - if behavior of this hardware should depend on dma_mask of device, then
> it should handle mask change,
> - if behavior of this hardware should not depend on dma_mask of device,
> then what for to pass size to it's setup?

Ah, right, I did indeed misunderstand. The IOMMU code is happy with the
DMA masks changing, since it always checks the appropriate one at the
point of IOVA allocation. The initial size given to
__iommu_setup_dma_ops() really just sets up a caching threshold in the
IOVA domain - if there is an explicitly-configured mask, then it's
generally good to set the limit based on that, but otherwise the default
32-bit limit is fine even if the driver subsequently alters the device's
mask(s) before making DMA API calls. Your patch won't actually change
any behaviour in this regard, as long as it still passes a 4GB size by
default.

Robin.

^ permalink raw reply

* [PATCH] usb: dwc3 dwc3_exynos_probe() change goto labels to meaningful names
From: Shuah Khan @ 2017-01-11 16:45 UTC (permalink / raw)
  To: linux-arm-kernel

Change goto labels to meaningful names from a series of errNs.

Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 drivers/usb/dwc3/dwc3-exynos.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
index f7421c2..ea50f74 100644
--- a/drivers/usb/dwc3/dwc3-exynos.c
+++ b/drivers/usb/dwc3/dwc3-exynos.c
@@ -147,53 +147,53 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 	exynos->vdd33 = devm_regulator_get(dev, "vdd33");
 	if (IS_ERR(exynos->vdd33)) {
 		ret = PTR_ERR(exynos->vdd33);
-		goto err2;
+		goto vdd33_err;
 	}
 	ret = regulator_enable(exynos->vdd33);
 	if (ret) {
 		dev_err(dev, "Failed to enable VDD33 supply\n");
-		goto err2;
+		goto vdd33_err;
 	}
 
 	exynos->vdd10 = devm_regulator_get(dev, "vdd10");
 	if (IS_ERR(exynos->vdd10)) {
 		ret = PTR_ERR(exynos->vdd10);
-		goto err3;
+		goto vdd10_err;
 	}
 	ret = regulator_enable(exynos->vdd10);
 	if (ret) {
 		dev_err(dev, "Failed to enable VDD10 supply\n");
-		goto err3;
+		goto vdd10_err;
 	}
 
 	ret = dwc3_exynos_register_phys(exynos);
 	if (ret) {
 		dev_err(dev, "couldn't register PHYs\n");
-		goto err4;
+		goto phys_err;
 	}
 
 	if (node) {
 		ret = of_platform_populate(node, NULL, NULL, dev);
 		if (ret) {
 			dev_err(dev, "failed to add dwc3 core\n");
-			goto err5;
+			goto populate_err;
 		}
 	} else {
 		dev_err(dev, "no device node, failed to add dwc3 core\n");
 		ret = -ENODEV;
-		goto err5;
+		goto populate_err;
 	}
 
 	return 0;
 
-err5:
+populate_err:
 	platform_device_unregister(exynos->usb2_phy);
 	platform_device_unregister(exynos->usb3_phy);
-err4:
+phys_err:
 	regulator_disable(exynos->vdd10);
-err3:
+vdd10_err:
 	regulator_disable(exynos->vdd33);
-err2:
+vdd33_err:
 	clk_disable_unprepare(exynos->axius_clk);
 axius_clk_err:
 	clk_disable_unprepare(exynos->susp_clk);
-- 
2.7.4

^ permalink raw reply related

* [PATCH] arm64: assembler: make adr_l work in modules under KASLR
From: Mark Rutland @ 2017-01-11 16:44 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <CAKv+Gu-FMCdkxpFCheCoRrCYFUdZPpViH4-G613sXyQVEH3chA@mail.gmail.com>

On Wed, Jan 11, 2017 at 04:08:30PM +0000, Ard Biesheuvel wrote:
> On 11 January 2017 at 15:34, Mark Rutland <mark.rutland@arm.com> wrote:
> > On Wed, Jan 11, 2017 at 03:25:09PM +0000, Ard Biesheuvel wrote:
> >> On 11 January 2017 at 15:18, Mark Rutland <mark.rutland@arm.com> wrote:
> >> > On Wed, Jan 11, 2017 at 02:54:53PM +0000, Ard Biesheuvel wrote:

> >> But in general, if the macro is available to modules, I would like to
> >> make sure that it does not result in code that builds fine but may
> >> fail in some cases only at runtime, especially given the fact that
> >> there is also a Cortex-A53 erratum regarding adrp instructions, for
> >> which reason we build modules with -mcmodel=large (which amounts to
> >> the same thing as the patch above)
> >>
> >> > It seems somewhat surprising to me to have adr_l expand to something
> >> > that doesn't use adr/adrp, but that's not necessarily a problem.
> >>
> >> I did realise that, but I don't think it is a problem tbh.
> >
> > In this case it should be fine, certainly.
> >
> > There are cases like the early boot code and hyp code where it's
> > critical that we use adr. It's also possible that we might build
> > (modular) drivers which want some idmapped code, where we want adr, so
> > it seems unfortunate that this depends on howthe code is built.
> 
> How would /that/ work? Modules are vmalloc'ed, and not covered by the
> ID map to begin with, so it is impossible to execute those adr
> instructions in a way that would make them return anything other than
> the virtual address of the symbol they refer to.

That's a fair point.

> > So, maybe it's better to have a mov_sym helper for this case, to be
> > explicit about what we want? That can use either adr* or mov*, or the
> > latter consistently.
> 
> Well, the point is that adr_l should not be used for modules so adding
> something that may be used is fine, but that still leaves the risk
> that someone may end up using it in a module.

Sure.

Given you have a concrete use case, and all I have are some vague
concerns for code that doesn't exist at present, I have no real
objection to the patch as it stands. FWIW:

Acked-by: Mark Rutland <mark.rutland@arm.com>

Thanks,
Mark.

^ permalink raw reply

* [PATCH v2 7/7] crypto: arm64/aes - reimplement bit-sliced ARM/NEON implementation for arm64
From: Ard Biesheuvel @ 2017-01-11 16:41 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484152915-26517-1-git-send-email-ard.biesheuvel@linaro.org>

This is a reimplementation of the NEON version of the bit-sliced AES
algorithm. This code is heavily based on Andy Polyakov's OpenSSL version
for ARM, which is also available in the kernel. This is an alternative for
the existing NEON implementation for arm64 authored by me, which suffers
from poor performance due to its reliance on the pathologically slow four
register variant of the tbl/tbx NEON instruction.

This version is about ~30% (*) faster than the generic C code, but only in
cases where the input can be 8x interleaved (this is a fundamental property
of bit slicing). For this reason, only the chaining modes ECB, XTS and CTR
are implemented. (The significance of ECB is that it could potentially be
used by other chaining modes)

* Measured on Cortex-A57. Note that this is still an order of magnitude
  slower than the implementations that use the dedicated AES instructions
  introduced in ARMv8, but those are part of an optional extension, and so
  it is good to have a fallback.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/Kconfig           |   7 +
 arch/arm64/crypto/Makefile          |   3 +
 arch/arm64/crypto/aes-neonbs-core.S | 963 ++++++++++++++++++++
 arch/arm64/crypto/aes-neonbs-glue.c | 420 +++++++++
 4 files changed, 1393 insertions(+)

diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 0826f8e599a6..5de75c3dcbd4 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -82,4 +82,11 @@ config CRYPTO_CHACHA20_NEON
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_CHACHA20
 
+config CRYPTO_AES_ARM64_BS
+	tristate "AES in ECB/CBC/CTR/XTS modes using bit-sliced NEON algorithm"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_AES_ARM64
+	select CRYPTO_SIMD
+
 endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index a893507629eb..d1ae1b9cbe70 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -47,6 +47,9 @@ chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o
 obj-$(CONFIG_CRYPTO_AES_ARM64) += aes-arm64.o
 aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o
 
+obj-$(CONFIG_CRYPTO_AES_ARM64_BS) += aes-neon-bs.o
+aes-neon-bs-y := aes-neonbs-core.o aes-neonbs-glue.o
+
 AFLAGS_aes-ce.o		:= -DINTERLEAVE=4
 AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
 
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
new file mode 100644
index 000000000000..8d0cdaa2768d
--- /dev/null
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -0,0 +1,963 @@
+/*
+ * Bit sliced AES using NEON instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * The algorithm implemented here is described in detail by the paper
+ * 'Faster and Timing-Attack Resistant AES-GCM' by Emilia Kaesper and
+ * Peter Schwabe (https://eprint.iacr.org/2009/129.pdf)
+ *
+ * This implementation is based primarily on the OpenSSL implementation
+ * for 32-bit ARM written by Andy Polyakov <appro@openssl.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+
+	rounds		.req	x11
+	bskey		.req	x12
+
+	.macro		in_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
+	eor		\b2, \b2, \b1
+	eor		\b5, \b5, \b6
+	eor		\b3, \b3, \b0
+	eor		\b6, \b6, \b2
+	eor		\b5, \b5, \b0
+	eor		\b6, \b6, \b3
+	eor		\b3, \b3, \b7
+	eor		\b7, \b7, \b5
+	eor		\b3, \b3, \b4
+	eor		\b4, \b4, \b5
+	eor		\b2, \b2, \b7
+	eor		\b3, \b3, \b1
+	eor		\b1, \b1, \b5
+	.endm
+
+	.macro		out_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
+	eor		\b0, \b0, \b6
+	eor		\b1, \b1, \b4
+	eor		\b4, \b4, \b6
+	eor		\b2, \b2, \b0
+	eor		\b6, \b6, \b1
+	eor		\b1, \b1, \b5
+	eor		\b5, \b5, \b3
+	eor		\b3, \b3, \b7
+	eor		\b7, \b7, \b5
+	eor		\b2, \b2, \b5
+	eor		\b4, \b4, \b7
+	.endm
+
+	.macro		inv_in_bs_ch, b6, b1, b2, b4, b7, b0, b3, b5
+	eor		\b1, \b1, \b7
+	eor		\b4, \b4, \b7
+	eor		\b7, \b7, \b5
+	eor		\b1, \b1, \b3
+	eor		\b2, \b2, \b5
+	eor		\b3, \b3, \b7
+	eor		\b6, \b6, \b1
+	eor		\b2, \b2, \b0
+	eor		\b5, \b5, \b3
+	eor		\b4, \b4, \b6
+	eor		\b0, \b0, \b6
+	eor		\b1, \b1, \b4
+	.endm
+
+	.macro		inv_out_bs_ch, b6, b5, b0, b3, b7, b1, b4, b2
+	eor		\b1, \b1, \b5
+	eor		\b2, \b2, \b7
+	eor		\b3, \b3, \b1
+	eor		\b4, \b4, \b5
+	eor		\b7, \b7, \b5
+	eor		\b3, \b3, \b4
+	eor 		\b5, \b5, \b0
+	eor		\b3, \b3, \b7
+	eor		\b6, \b6, \b2
+	eor		\b2, \b2, \b1
+	eor		\b6, \b6, \b3
+	eor		\b3, \b3, \b0
+	eor		\b5, \b5, \b6
+	.endm
+
+	.macro		mul_gf4, x0, x1, y0, y1, t0, t1
+	eor 		\t0, \y0, \y1
+	and		\t0, \t0, \x0
+	eor		\x0, \x0, \x1
+	and		\t1, \x1, \y0
+	and		\x0, \x0, \y1
+	eor		\x1, \t1, \t0
+	eor		\x0, \x0, \t1
+	.endm
+
+	.macro		mul_gf4_n_gf4, x0, x1, y0, y1, t0, x2, x3, y2, y3, t1
+	eor		\t0, \y0, \y1
+	eor 		\t1, \y2, \y3
+	and		\t0, \t0, \x0
+	and		\t1, \t1, \x2
+	eor		\x0, \x0, \x1
+	eor		\x2, \x2, \x3
+	and		\x1, \x1, \y0
+	and		\x3, \x3, \y2
+	and		\x0, \x0, \y1
+	and		\x2, \x2, \y3
+	eor		\x1, \x1, \x0
+	eor		\x2, \x2, \x3
+	eor		\x0, \x0, \t0
+	eor		\x3, \x3, \t1
+	.endm
+
+	.macro		mul_gf16_2, x0, x1, x2, x3, x4, x5, x6, x7, \
+				    y0, y1, y2, y3, t0, t1, t2, t3
+	eor		\t0, \x0, \x2
+	eor		\t1, \x1, \x3
+	mul_gf4  	\x0, \x1, \y0, \y1, \t2, \t3
+	eor		\y0, \y0, \y2
+	eor		\y1, \y1, \y3
+	mul_gf4_n_gf4	\t0, \t1, \y0, \y1, \t3, \x2, \x3, \y2, \y3, \t2
+	eor		\x0, \x0, \t0
+	eor		\x2, \x2, \t0
+	eor		\x1, \x1, \t1
+	eor		\x3, \x3, \t1
+	eor		\t0, \x4, \x6
+	eor		\t1, \x5, \x7
+	mul_gf4_n_gf4	\t0, \t1, \y0, \y1, \t3, \x6, \x7, \y2, \y3, \t2
+	eor		\y0, \y0, \y2
+	eor		\y1, \y1, \y3
+	mul_gf4  	\x4, \x5, \y0, \y1, \t2, \t3
+	eor		\x4, \x4, \t0
+	eor		\x6, \x6, \t0
+	eor		\x5, \x5, \t1
+	eor		\x7, \x7, \t1
+	.endm
+
+	.macro		inv_gf256, x0, x1, x2, x3, x4, x5, x6, x7, \
+				   t0, t1, t2, t3, s0, s1, s2, s3
+	eor		\t3, \x4, \x6
+	eor		\t0, \x5, \x7
+	eor		\t1, \x1, \x3
+	eor		\s1, \x7, \x6
+	eor		\s0, \x0, \x2
+	eor		\s3, \t3, \t0
+	orr		\t2, \t0, \t1
+	and		\s2, \t3, \s0
+	orr		\t3, \t3, \s0
+	eor		\s0, \s0, \t1
+	and		\t0, \t0, \t1
+	eor		\t1, \x3, \x2
+	and		\s3, \s3, \s0
+	and		\s1, \s1, \t1
+	eor		\t1, \x4, \x5
+	eor		\s0, \x1, \x0
+	eor		\t3, \t3, \s1
+	eor		\t2, \t2, \s1
+	and		\s1, \t1, \s0
+	orr		\t1, \t1, \s0
+	eor		\t3, \t3, \s3
+	eor		\t0, \t0, \s1
+	eor		\t2, \t2, \s2
+	eor		\t1, \t1, \s3
+	eor		\t0, \t0, \s2
+	and		\s0, \x7, \x3
+	eor		\t1, \t1, \s2
+	and		\s1, \x6, \x2
+	and		\s2, \x5, \x1
+	orr		\s3, \x4, \x0
+	eor		\t3, \t3, \s0
+	eor		\t1, \t1, \s2
+	eor		\s0, \t0, \s3
+	eor		\t2, \t2, \s1
+	and		\s2, \t3, \t1
+	eor		\s1, \t2, \s2
+	eor		\s3, \s0, \s2
+	bsl		\s1, \t1, \s0
+	not		\t0, \s0
+	bsl		\s0, \s1, \s3
+	bsl		\t0, \s1, \s3
+	bsl		\s3, \t3, \t2
+	eor		\t3, \t3, \t2
+	and		\s2, \s0, \s3
+	eor		\t1, \t1, \t0
+	eor		\s2, \s2, \t3
+	mul_gf16_2	\x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
+			\s3, \s2, \s1, \t1, \s0, \t0, \t2, \t3
+	.endm
+
+	.macro		sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
+			      t0, t1, t2, t3, s0, s1, s2, s3
+	in_bs_ch	\b0\().16b, \b1\().16b, \b2\().16b, \b3\().16b, \
+			\b4\().16b, \b5\().16b, \b6\().16b, \b7\().16b
+	inv_gf256	\b6\().16b, \b5\().16b, \b0\().16b, \b3\().16b, \
+			\b7\().16b, \b1\().16b, \b4\().16b, \b2\().16b, \
+			\t0\().16b, \t1\().16b, \t2\().16b, \t3\().16b, \
+			\s0\().16b, \s1\().16b, \s2\().16b, \s3\().16b
+	out_bs_ch	\b7\().16b, \b1\().16b, \b4\().16b, \b2\().16b, \
+			\b6\().16b, \b5\().16b, \b0\().16b, \b3\().16b
+	.endm
+
+	.macro		inv_sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
+				  t0, t1, t2, t3, s0, s1, s2, s3
+	inv_in_bs_ch	\b0\().16b, \b1\().16b, \b2\().16b, \b3\().16b, \
+			\b4\().16b, \b5\().16b, \b6\().16b, \b7\().16b
+	inv_gf256	\b5\().16b, \b1\().16b, \b2\().16b, \b6\().16b, \
+			\b3\().16b, \b7\().16b, \b0\().16b, \b4\().16b, \
+			\t0\().16b, \t1\().16b, \t2\().16b, \t3\().16b, \
+			\s0\().16b, \s1\().16b, \s2\().16b, \s3\().16b
+	inv_out_bs_ch	\b3\().16b, \b7\().16b, \b0\().16b, \b4\().16b, \
+			\b5\().16b, \b1\().16b, \b2\().16b, \b6\().16b
+	.endm
+
+	.macro		enc_next_rk
+	ldp		q16, q17, [bskey], #128
+	ldp		q18, q19, [bskey, #-96]
+	ldp		q20, q21, [bskey, #-64]
+	ldp		q22, q23, [bskey, #-32]
+	.endm
+
+	.macro		dec_next_rk
+	ldp		q16, q17, [bskey, #-128]!
+	ldp		q18, q19, [bskey, #32]
+	ldp		q20, q21, [bskey, #64]
+	ldp		q22, q23, [bskey, #96]
+	.endm
+
+	.macro		add_round_key, x0, x1, x2, x3, x4, x5, x6, x7
+	eor		\x0\().16b, \x0\().16b, v16.16b
+	eor		\x1\().16b, \x1\().16b, v17.16b
+	eor		\x2\().16b, \x2\().16b, v18.16b
+	eor		\x3\().16b, \x3\().16b, v19.16b
+	eor		\x4\().16b, \x4\().16b, v20.16b
+	eor		\x5\().16b, \x5\().16b, v21.16b
+	eor		\x6\().16b, \x6\().16b, v22.16b
+	eor		\x7\().16b, \x7\().16b, v23.16b
+	.endm
+
+	.macro		shift_rows, x0, x1, x2, x3, x4, x5, x6, x7, mask
+	tbl		\x0\().16b, {\x0\().16b}, \mask\().16b
+	tbl		\x1\().16b, {\x1\().16b}, \mask\().16b
+	tbl		\x2\().16b, {\x2\().16b}, \mask\().16b
+	tbl		\x3\().16b, {\x3\().16b}, \mask\().16b
+	tbl		\x4\().16b, {\x4\().16b}, \mask\().16b
+	tbl		\x5\().16b, {\x5\().16b}, \mask\().16b
+	tbl		\x6\().16b, {\x6\().16b}, \mask\().16b
+	tbl		\x7\().16b, {\x7\().16b}, \mask\().16b
+	.endm
+
+	.macro		mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
+				  t0, t1, t2, t3, t4, t5, t6, t7, inv
+	ext		\t0\().16b, \x0\().16b, \x0\().16b, #12
+	ext		\t1\().16b, \x1\().16b, \x1\().16b, #12
+	eor		\x0\().16b, \x0\().16b, \t0\().16b
+	ext		\t2\().16b, \x2\().16b, \x2\().16b, #12
+	eor		\x1\().16b, \x1\().16b, \t1\().16b
+	ext		\t3\().16b, \x3\().16b, \x3\().16b, #12
+	eor		\x2\().16b, \x2\().16b, \t2\().16b
+	ext		\t4\().16b, \x4\().16b, \x4\().16b, #12
+	eor		\x3\().16b, \x3\().16b, \t3\().16b
+	ext		\t5\().16b, \x5\().16b, \x5\().16b, #12
+	eor		\x4\().16b, \x4\().16b, \t4\().16b
+	ext		\t6\().16b, \x6\().16b, \x6\().16b, #12
+	eor		\x5\().16b, \x5\().16b, \t5\().16b
+	ext		\t7\().16b, \x7\().16b, \x7\().16b, #12
+	eor		\x6\().16b, \x6\().16b, \t6\().16b
+	eor		\t1\().16b, \t1\().16b, \x0\().16b
+	eor		\x7\().16b, \x7\().16b, \t7\().16b
+	ext		\x0\().16b, \x0\().16b, \x0\().16b, #8
+	eor		\t2\().16b, \t2\().16b, \x1\().16b
+	eor		\t0\().16b, \t0\().16b, \x7\().16b
+	eor		\t1\().16b, \t1\().16b, \x7\().16b
+	ext		\x1\().16b, \x1\().16b, \x1\().16b, #8
+	eor		\t5\().16b, \t5\().16b, \x4\().16b
+	eor		\x0\().16b, \x0\().16b, \t0\().16b
+	eor		\t6\().16b, \t6\().16b, \x5\().16b
+	eor		\x1\().16b, \x1\().16b, \t1\().16b
+	ext		\t0\().16b, \x4\().16b, \x4\().16b, #8
+	eor		\t4\().16b, \t4\().16b, \x3\().16b
+	ext		\t1\().16b, \x5\().16b, \x5\().16b, #8
+	eor		\t7\().16b, \t7\().16b, \x6\().16b
+	ext		\x4\().16b, \x3\().16b, \x3\().16b, #8
+	eor		\t3\().16b, \t3\().16b, \x2\().16b
+	ext		\x5\().16b, \x7\().16b, \x7\().16b, #8
+	eor		\t4\().16b, \t4\().16b, \x7\().16b
+	ext		\x3\().16b, \x6\().16b, \x6\().16b, #8
+	eor		\t3\().16b, \t3\().16b, \x7\().16b
+	ext		\x6\().16b, \x2\().16b, \x2\().16b, #8
+	eor		\x7\().16b, \t1\().16b, \t5\().16b
+	.ifb		\inv
+	eor		\x2\().16b, \t0\().16b, \t4\().16b
+	eor		\x4\().16b, \x4\().16b, \t3\().16b
+	eor		\x5\().16b, \x5\().16b, \t7\().16b
+	eor		\x3\().16b, \x3\().16b, \t6\().16b
+	eor		\x6\().16b, \x6\().16b, \t2\().16b
+	.else
+	eor		\t3\().16b, \t3\().16b, \x4\().16b
+	eor		\x5\().16b, \x5\().16b, \t7\().16b
+	eor		\x2\().16b, \x3\().16b, \t6\().16b
+	eor		\x3\().16b, \t0\().16b, \t4\().16b
+	eor		\x4\().16b, \x6\().16b, \t2\().16b
+	mov		\x6\().16b, \t3\().16b
+	.endif
+	.endm
+
+	.macro		inv_mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
+				      t0, t1, t2, t3, t4, t5, t6, t7
+	ext		\t0\().16b, \x0\().16b, \x0\().16b, #8
+	ext		\t6\().16b, \x6\().16b, \x6\().16b, #8
+	ext		\t7\().16b, \x7\().16b, \x7\().16b, #8
+	eor		\t0\().16b, \t0\().16b, \x0\().16b
+	ext		\t1\().16b, \x1\().16b, \x1\().16b, #8
+	eor		\t6\().16b, \t6\().16b, \x6\().16b
+	ext		\t2\().16b, \x2\().16b, \x2\().16b, #8
+	eor		\t7\().16b, \t7\().16b, \x7\().16b
+	ext		\t3\().16b, \x3\().16b, \x3\().16b, #8
+	eor		\t1\().16b, \t1\().16b, \x1\().16b
+	ext		\t4\().16b, \x4\().16b, \x4\().16b, #8
+	eor		\t2\().16b, \t2\().16b, \x2\().16b
+	ext		\t5\().16b, \x5\().16b, \x5\().16b, #8
+	eor		\t3\().16b, \t3\().16b, \x3\().16b
+	eor		\t4\().16b, \t4\().16b, \x4\().16b
+	eor		\t5\().16b, \t5\().16b, \x5\().16b
+	eor		\x0\().16b, \x0\().16b, \t6\().16b
+	eor		\x1\().16b, \x1\().16b, \t6\().16b
+	eor		\x2\().16b, \x2\().16b, \t0\().16b
+	eor		\x4\().16b, \x4\().16b, \t2\().16b
+	eor		\x3\().16b, \x3\().16b, \t1\().16b
+	eor		\x1\().16b, \x1\().16b, \t7\().16b
+	eor		\x2\().16b, \x2\().16b, \t7\().16b
+	eor		\x4\().16b, \x4\().16b, \t6\().16b
+	eor		\x5\().16b, \x5\().16b, \t3\().16b
+	eor		\x3\().16b, \x3\().16b, \t6\().16b
+	eor		\x6\().16b, \x6\().16b, \t4\().16b
+	eor		\x4\().16b, \x4\().16b, \t7\().16b
+	eor		\x5\().16b, \x5\().16b, \t7\().16b
+	eor		\x7\().16b, \x7\().16b, \t5\().16b
+	mix_cols	\x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
+			\t0, \t1, \t2, \t3, \t4, \t5, \t6, \t7, 1
+	.endm
+
+	.macro		swapmove_2x, a0, b0, a1, b1, n, mask, t0, t1
+	ushr		\t0\().2d, \b0\().2d, #\n
+	ushr		\t1\().2d, \b1\().2d, #\n
+	eor		\t0\().16b, \t0\().16b, \a0\().16b
+	eor		\t1\().16b, \t1\().16b, \a1\().16b
+	and		\t0\().16b, \t0\().16b, \mask\().16b
+	and		\t1\().16b, \t1\().16b, \mask\().16b
+	eor		\a0\().16b, \a0\().16b, \t0\().16b
+	shl		\t0\().2d, \t0\().2d, #\n
+	eor		\a1\().16b, \a1\().16b, \t1\().16b
+	shl		\t1\().2d, \t1\().2d, #\n
+	eor		\b0\().16b, \b0\().16b, \t0\().16b
+	eor		\b1\().16b, \b1\().16b, \t1\().16b
+	.endm
+
+	.macro		bitslice, x7, x6, x5, x4, x3, x2, x1, x0, t0, t1, t2, t3
+	movi		\t0\().16b, #0x55
+	movi		\t1\().16b, #0x33
+	swapmove_2x	\x0, \x1, \x2, \x3, 1, \t0, \t2, \t3
+	swapmove_2x	\x4, \x5, \x6, \x7, 1, \t0, \t2, \t3
+	movi		\t0\().16b, #0x0f
+	swapmove_2x	\x0, \x2, \x1, \x3, 2, \t1, \t2, \t3
+	swapmove_2x	\x4, \x6, \x5, \x7, 2, \t1, \t2, \t3
+	swapmove_2x	\x0, \x4, \x1, \x5, 4, \t0, \t2, \t3
+	swapmove_2x	\x2, \x6, \x3, \x7, 4, \t0, \t2, \t3
+	.endm
+
+
+	.align		6
+M0:	.octa		0x0004080c0105090d02060a0e03070b0f
+
+M0SR:	.octa		0x0004080c05090d010a0e02060f03070b
+SR:	.octa		0x0f0e0d0c0a09080b0504070600030201
+SRM0:	.octa		0x01060b0c0207080d0304090e00050a0f
+
+M0ISR:	.octa		0x0004080c0d0105090a0e0206070b0f03
+ISR:	.octa		0x0f0e0d0c080b0a090504070602010003
+ISRM0:	.octa		0x0306090c00070a0d01040b0e0205080f
+
+	/*
+	 * void aesbs_convert_key(u8 out[], u32 const rk[], int rounds)
+	 */
+ENTRY(aesbs_convert_key)
+	ld1		{v7.4s}, [x1], #16		// load round 0 key
+	ld1		{v17.4s}, [x1], #16		// load round 1 key
+
+	movi		v8.16b,  #0x01			// bit masks
+	movi		v9.16b,  #0x02
+	movi		v10.16b, #0x04
+	movi		v11.16b, #0x08
+	movi		v12.16b, #0x10
+	movi		v13.16b, #0x20
+	movi		v14.16b, #0x40
+	movi		v15.16b, #0x80
+	ldr		q16, M0
+
+	sub		x2, x2, #1
+	str		q7, [x0], #16		// save round 0 key
+
+.Lkey_loop:
+	tbl		v7.16b ,{v17.16b}, v16.16b
+	ld1		{v17.4s}, [x1], #16		// load next round key
+
+	cmtst		v0.16b, v7.16b, v8.16b
+	cmtst		v1.16b, v7.16b, v9.16b
+	cmtst		v2.16b, v7.16b, v10.16b
+	cmtst		v3.16b, v7.16b, v11.16b
+	cmtst		v4.16b, v7.16b, v12.16b
+	cmtst		v5.16b, v7.16b, v13.16b
+	cmtst		v6.16b, v7.16b, v14.16b
+	cmtst		v7.16b, v7.16b, v15.16b
+	not		v0.16b, v0.16b
+	not		v1.16b, v1.16b
+	not		v5.16b, v5.16b
+	not		v6.16b, v6.16b
+
+	subs		x2, x2, #1
+	stp		q0, q1, [x0], #128
+	stp		q2, q3, [x0, #-96]
+	stp		q4, q5, [x0, #-64]
+	stp		q6, q7, [x0, #-32]
+	b.ne		.Lkey_loop
+
+	movi		v7.16b, #0x63			// compose .L63
+	eor		v17.16b, v17.16b, v7.16b
+	str		q17, [x0]
+	ret
+ENDPROC(aesbs_convert_key)
+
+	.align		4
+aesbs_encrypt8:
+	ldr		q9, [bskey], #16		// round 0 key
+	ldr		q8, M0SR
+	ldr		q24, SR
+
+	eor		v10.16b, v0.16b, v9.16b		// xor with round0 key
+	eor		v11.16b, v1.16b, v9.16b
+	tbl		v0.16b, {v10.16b}, v8.16b
+	eor		v12.16b, v2.16b, v9.16b
+	tbl		v1.16b, {v11.16b}, v8.16b
+	eor		v13.16b, v3.16b, v9.16b
+	tbl		v2.16b, {v12.16b}, v8.16b
+	eor		v14.16b, v4.16b, v9.16b
+	tbl		v3.16b, {v13.16b}, v8.16b
+	eor		v15.16b, v5.16b, v9.16b
+	tbl		v4.16b, {v14.16b}, v8.16b
+	eor		v10.16b, v6.16b, v9.16b
+	tbl		v5.16b, {v15.16b}, v8.16b
+	eor		v11.16b, v7.16b, v9.16b
+	tbl		v6.16b, {v10.16b}, v8.16b
+	tbl		v7.16b, {v11.16b}, v8.16b
+
+	bitslice	v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11
+
+	sub		rounds, rounds, #1
+	b		.Lenc_sbox
+
+.Lenc_loop:
+	shift_rows	v0, v1, v2, v3, v4, v5, v6, v7, v24
+.Lenc_sbox:
+	sbox		v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, \
+								v13, v14, v15
+	subs		rounds, rounds, #1
+	b.cc		.Lenc_done
+
+	enc_next_rk
+
+	mix_cols	v0, v1, v4, v6, v3, v7, v2, v5, v8, v9, v10, v11, v12, \
+								v13, v14, v15
+
+	add_round_key	v0, v1, v2, v3, v4, v5, v6, v7
+
+	b.ne		.Lenc_loop
+	ldr		q24, SRM0
+	b		.Lenc_loop
+
+.Lenc_done:
+	ldr		q12, [bskey]			// last round key
+
+	bitslice	v0, v1, v4, v6, v3, v7, v2, v5, v8, v9, v10, v11
+
+	eor		v0.16b, v0.16b, v12.16b
+	eor		v1.16b, v1.16b, v12.16b
+	eor		v4.16b, v4.16b, v12.16b
+	eor		v6.16b, v6.16b, v12.16b
+	eor		v3.16b, v3.16b, v12.16b
+	eor		v7.16b, v7.16b, v12.16b
+	eor		v2.16b, v2.16b, v12.16b
+	eor		v5.16b, v5.16b, v12.16b
+	ret
+ENDPROC(aesbs_encrypt8)
+
+	.align		4
+aesbs_decrypt8:
+	lsl		x9, rounds, #7
+	add		bskey, bskey, x9
+
+	ldr		q9, [bskey, #-112]!		// round 0 key
+	ldr		q8, M0ISR
+	ldr		q24, ISR
+
+	eor		v10.16b, v0.16b, v9.16b		// xor with round0 key
+	eor		v11.16b, v1.16b, v9.16b
+	tbl		v0.16b, {v10.16b}, v8.16b
+	eor		v12.16b, v2.16b, v9.16b
+	tbl		v1.16b, {v11.16b}, v8.16b
+	eor		v13.16b, v3.16b, v9.16b
+	tbl		v2.16b, {v12.16b}, v8.16b
+	eor		v14.16b, v4.16b, v9.16b
+	tbl		v3.16b, {v13.16b}, v8.16b
+	eor		v15.16b, v5.16b, v9.16b
+	tbl		v4.16b, {v14.16b}, v8.16b
+	eor		v10.16b, v6.16b, v9.16b
+	tbl		v5.16b, {v15.16b}, v8.16b
+	eor		v11.16b, v7.16b, v9.16b
+	tbl		v6.16b, {v10.16b}, v8.16b
+	tbl		v7.16b, {v11.16b}, v8.16b
+
+	bitslice	v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11
+
+	sub		rounds, rounds, #1
+	b		.Ldec_sbox
+
+.Ldec_loop:
+	shift_rows	v0, v1, v2, v3, v4, v5, v6, v7, v24
+.Ldec_sbox:
+	inv_sbox	v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, \
+								v13, v14, v15
+	subs		rounds, rounds, #1
+	b.cc		.Ldec_done
+
+	dec_next_rk
+
+	add_round_key	v0, v1, v6, v4, v2, v7, v3, v5
+
+	inv_mix_cols	v0, v1, v6, v4, v2, v7, v3, v5, v8, v9, v10, v11, v12, \
+								v13, v14, v15
+
+	b.ne		.Ldec_loop
+	ldr		q24, ISRM0
+	b		.Ldec_loop
+.Ldec_done:
+	ldr		q12, [bskey, #-16]		// last round key
+
+	bitslice	v0, v1, v6, v4, v2, v7, v3, v5, v8, v9, v10, v11
+
+	eor		v0.16b, v0.16b, v12.16b
+	eor		v1.16b, v1.16b, v12.16b
+	eor		v6.16b, v6.16b, v12.16b
+	eor		v4.16b, v4.16b, v12.16b
+	eor		v2.16b, v2.16b, v12.16b
+	eor		v7.16b, v7.16b, v12.16b
+	eor		v3.16b, v3.16b, v12.16b
+	eor		v5.16b, v5.16b, v12.16b
+	ret
+ENDPROC(aesbs_decrypt8)
+
+	/*
+	 * aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks)
+	 * aesbs_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks)
+	 */
+	.macro		__ecb_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+99:	mov		x5, #1
+	lsl		x5, x5, x4
+	subs		w4, w4, #8
+	csel		x4, x4, xzr, pl
+	csel		x5, x5, xzr, mi
+
+	ld1		{v0.16b}, [x1], #16
+	tbnz		x5, #1, 0f
+	ld1		{v1.16b}, [x1], #16
+	tbnz		x5, #2, 0f
+	ld1		{v2.16b}, [x1], #16
+	tbnz		x5, #3, 0f
+	ld1		{v3.16b}, [x1], #16
+	tbnz		x5, #4, 0f
+	ld1		{v4.16b}, [x1], #16
+	tbnz		x5, #5, 0f
+	ld1		{v5.16b}, [x1], #16
+	tbnz		x5, #6, 0f
+	ld1		{v6.16b}, [x1], #16
+	tbnz		x5, #7, 0f
+	ld1		{v7.16b}, [x1], #16
+
+0:	mov		bskey, x2
+	mov		rounds, x3
+	bl		\do8
+
+	st1		{\o0\().16b}, [x0], #16
+	tbnz		x5, #1, 1f
+	st1		{\o1\().16b}, [x0], #16
+	tbnz		x5, #2, 1f
+	st1		{\o2\().16b}, [x0], #16
+	tbnz		x5, #3, 1f
+	st1		{\o3\().16b}, [x0], #16
+	tbnz		x5, #4, 1f
+	st1		{\o4\().16b}, [x0], #16
+	tbnz		x5, #5, 1f
+	st1		{\o5\().16b}, [x0], #16
+	tbnz		x5, #6, 1f
+	st1		{\o6\().16b}, [x0], #16
+	tbnz		x5, #7, 1f
+	st1		{\o7\().16b}, [x0], #16
+
+	cbnz		x4, 99b
+
+1:	ldp		x29, x30, [sp], #16
+	ret
+	.endm
+
+	.align		4
+ENTRY(aesbs_ecb_encrypt)
+	__ecb_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
+ENDPROC(aesbs_ecb_encrypt)
+
+	.align		4
+ENTRY(aesbs_ecb_decrypt)
+	__ecb_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
+ENDPROC(aesbs_ecb_decrypt)
+
+	/*
+	 * aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks, u8 iv[])
+	 */
+	.align		4
+ENTRY(aesbs_cbc_decrypt)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+99:	mov		x6, #1
+	lsl		x6, x6, x4
+	subs		w4, w4, #8
+	csel		x4, x4, xzr, pl
+	csel		x6, x6, xzr, mi
+
+	ld1		{v0.16b}, [x1], #16
+	mov		v25.16b, v0.16b
+	tbnz		x6, #1, 0f
+	ld1		{v1.16b}, [x1], #16
+	mov		v26.16b, v1.16b
+	tbnz		x6, #2, 0f
+	ld1		{v2.16b}, [x1], #16
+	mov		v27.16b, v2.16b
+	tbnz		x6, #3, 0f
+	ld1		{v3.16b}, [x1], #16
+	mov		v28.16b, v3.16b
+	tbnz		x6, #4, 0f
+	ld1		{v4.16b}, [x1], #16
+	mov		v29.16b, v4.16b
+	tbnz		x6, #5, 0f
+	ld1		{v5.16b}, [x1], #16
+	mov		v30.16b, v5.16b
+	tbnz		x6, #6, 0f
+	ld1		{v6.16b}, [x1], #16
+	mov		v31.16b, v6.16b
+	tbnz		x6, #7, 0f
+	ld1		{v7.16b}, [x1]
+
+0:	mov		bskey, x2
+	mov		rounds, x3
+	bl		aesbs_decrypt8
+
+	ld1		{v24.16b}, [x5]			// load IV
+
+	eor		v1.16b, v1.16b, v25.16b
+	eor		v6.16b, v6.16b, v26.16b
+	eor		v4.16b, v4.16b, v27.16b
+	eor		v2.16b, v2.16b, v28.16b
+	eor		v7.16b, v7.16b, v29.16b
+	eor		v0.16b, v0.16b, v24.16b
+	eor		v3.16b, v3.16b, v30.16b
+	eor		v5.16b, v5.16b, v31.16b
+
+	st1		{v0.16b}, [x0], #16
+	mov		v24.16b, v25.16b
+	tbnz		x6, #1, 1f
+	st1		{v1.16b}, [x0], #16
+	mov		v24.16b, v26.16b
+	tbnz		x6, #2, 1f
+	st1		{v6.16b}, [x0], #16
+	mov		v24.16b, v27.16b
+	tbnz		x6, #3, 1f
+	st1		{v4.16b}, [x0], #16
+	mov		v24.16b, v28.16b
+	tbnz		x6, #4, 1f
+	st1		{v2.16b}, [x0], #16
+	mov		v24.16b, v29.16b
+	tbnz		x6, #5, 1f
+	st1		{v7.16b}, [x0], #16
+	mov		v24.16b, v30.16b
+	tbnz		x6, #6, 1f
+	st1		{v3.16b}, [x0], #16
+	mov		v24.16b, v31.16b
+	tbnz		x6, #7, 1f
+	ld1		{v24.16b}, [x1], #16
+	st1		{v5.16b}, [x0], #16
+1:	st1		{v24.16b}, [x5]			// store IV
+
+	cbnz		x4, 99b
+
+	ldp		x29, x30, [sp], #16
+	ret
+ENDPROC(aesbs_cbc_decrypt)
+
+	.macro		next_tweak, out, in, const, tmp
+	sshr		\tmp\().2d,  \in\().2d,   #63
+	and		\tmp\().16b, \tmp\().16b, \const\().16b
+	add		\out\().2d,  \in\().2d,   \in\().2d
+	ext		\tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+	eor		\out\().16b, \out\().16b, \tmp\().16b
+	.endm
+
+	.align		4
+.Lxts_mul_x:
+CPU_LE(	.quad		1, 0x87		)
+CPU_BE(	.quad		0x87, 1		)
+
+	/*
+	 * aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks, u8 iv[])
+	 * aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks, u8 iv[])
+	 */
+__xts_crypt8:
+	mov		x6, #1
+	lsl		x6, x6, x4
+	subs		w4, w4, #8
+	csel		x4, x4, xzr, pl
+	csel		x6, x6, xzr, mi
+
+	ld1		{v0.16b}, [x1], #16
+	next_tweak	v26, v25, v30, v31
+	eor		v0.16b, v0.16b, v25.16b
+	tbnz		x6, #1, 0f
+
+	ld1		{v1.16b}, [x1], #16
+	next_tweak	v27, v26, v30, v31
+	eor		v1.16b, v1.16b, v26.16b
+	tbnz		x6, #2, 0f
+
+	ld1		{v2.16b}, [x1], #16
+	next_tweak	v28, v27, v30, v31
+	eor		v2.16b, v2.16b, v27.16b
+	tbnz		x6, #3, 0f
+
+	ld1		{v3.16b}, [x1], #16
+	next_tweak	v29, v28, v30, v31
+	eor		v3.16b, v3.16b, v28.16b
+	tbnz		x6, #4, 0f
+
+	ld1		{v4.16b}, [x1], #16
+	str		q29, [sp, #16]
+	eor		v4.16b, v4.16b, v29.16b
+	next_tweak	v29, v29, v30, v31
+	tbnz		x6, #5, 0f
+
+	ld1		{v5.16b}, [x1], #16
+	str		q29, [sp, #32]
+	eor		v5.16b, v5.16b, v29.16b
+	next_tweak	v29, v29, v30, v31
+	tbnz		x6, #6, 0f
+
+	ld1		{v6.16b}, [x1], #16
+	str		q29, [sp, #48]
+	eor		v6.16b, v6.16b, v29.16b
+	next_tweak	v29, v29, v30, v31
+	tbnz		x6, #7, 0f
+
+	ld1		{v7.16b}, [x1], #16
+	str		q29, [sp, #64]
+	eor		v7.16b, v7.16b, v29.16b
+	next_tweak	v29, v29, v30, v31
+
+0:	mov		bskey, x2
+	mov		rounds, x3
+	br		x7
+ENDPROC(__xts_crypt8)
+
+	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
+	stp		x29, x30, [sp, #-80]!
+	mov		x29, sp
+
+	ldr		q30, .Lxts_mul_x
+	ld1		{v25.16b}, [x5]
+
+99:	adr		x7, \do8
+	bl		__xts_crypt8
+
+	ldp		q16, q17, [sp, #16]
+	ldp		q18, q19, [sp, #48]
+
+	eor		\o0\().16b, \o0\().16b, v25.16b
+	eor		\o1\().16b, \o1\().16b, v26.16b
+	eor		\o2\().16b, \o2\().16b, v27.16b
+	eor		\o3\().16b, \o3\().16b, v28.16b
+
+	st1		{\o0\().16b}, [x0], #16
+	mov		v25.16b, v26.16b
+	tbnz		x6, #1, 1f
+	st1		{\o1\().16b}, [x0], #16
+	mov		v25.16b, v27.16b
+	tbnz		x6, #2, 1f
+	st1		{\o2\().16b}, [x0], #16
+	mov		v25.16b, v28.16b
+	tbnz		x6, #3, 1f
+	st1		{\o3\().16b}, [x0], #16
+	mov		v25.16b, v29.16b
+	tbnz		x6, #4, 1f
+
+	eor		\o4\().16b, \o4\().16b, v16.16b
+	eor		\o5\().16b, \o5\().16b, v17.16b
+	eor		\o6\().16b, \o6\().16b, v18.16b
+	eor		\o7\().16b, \o7\().16b, v19.16b
+
+	st1		{\o4\().16b}, [x0], #16
+	tbnz		x6, #5, 1f
+	st1		{\o5\().16b}, [x0], #16
+	tbnz		x6, #6, 1f
+	st1		{\o6\().16b}, [x0], #16
+	tbnz		x6, #7, 1f
+	st1		{\o7\().16b}, [x0], #16
+
+	cbnz		x4, 99b
+
+1:	st1		{v25.16b}, [x5]
+	ldp		x29, x30, [sp], #80
+	ret
+	.endm
+
+ENTRY(aesbs_xts_encrypt)
+	__xts_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
+ENDPROC(aesbs_xts_encrypt)
+
+ENTRY(aesbs_xts_decrypt)
+	__xts_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
+ENDPROC(aesbs_xts_decrypt)
+
+	.macro		next_ctr, v
+	mov		\v\().d[1], x8
+	adds		x8, x8, #1
+	mov		\v\().d[0], x7
+	adc		x7, x7, xzr
+	rev64		\v\().16b, \v\().16b
+	.endm
+
+	/*
+	 * aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+	 *		     int rounds, int blocks, u8 iv[], bool final)
+	 */
+ENTRY(aesbs_ctr_encrypt)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	add		x4, x4, x6		// do one extra block if final
+
+	ldp		x7, x8, [x5]
+	ld1		{v0.16b}, [x5]
+CPU_LE(	rev		x7, x7		)
+CPU_LE(	rev		x8, x8		)
+	adds		x8, x8, #1
+	adc		x7, x7, xzr
+
+99:	mov		x9, #1
+	lsl		x9, x9, x4
+	subs		w4, w4, #8
+	csel		x4, x4, xzr, pl
+	csel		x9, x9, xzr, le
+
+	next_ctr	v1
+	next_ctr	v2
+	next_ctr	v3
+	next_ctr	v4
+	next_ctr	v5
+	next_ctr	v6
+	next_ctr	v7
+
+0:	mov		bskey, x2
+	mov		rounds, x3
+	bl		aesbs_encrypt8
+
+	lsr		x9, x9, x6		// disregard the extra block
+	tbnz		x9, #0, 0f
+
+	ld1		{v8.16b}, [x1], #16
+	eor		v0.16b, v0.16b, v8.16b
+	st1		{v0.16b}, [x0], #16
+	tbnz		x9, #1, 1f
+
+	ld1		{v9.16b}, [x1], #16
+	eor		v1.16b, v1.16b, v9.16b
+	st1		{v1.16b}, [x0], #16
+	tbnz		x9, #2, 2f
+
+	ld1		{v10.16b}, [x1], #16
+	eor		v4.16b, v4.16b, v10.16b
+	st1		{v4.16b}, [x0], #16
+	tbnz		x9, #3, 3f
+
+	ld1		{v11.16b}, [x1], #16
+	eor		v6.16b, v6.16b, v11.16b
+	st1		{v6.16b}, [x0], #16
+	tbnz		x9, #4, 4f
+
+	ld1		{v12.16b}, [x1], #16
+	eor		v3.16b, v3.16b, v12.16b
+	st1		{v3.16b}, [x0], #16
+	tbnz		x9, #5, 5f
+
+	ld1		{v13.16b}, [x1], #16
+	eor		v7.16b, v7.16b, v13.16b
+	st1		{v7.16b}, [x0], #16
+	tbnz		x9, #6, 6f
+
+	ld1		{v14.16b}, [x1], #16
+	eor		v2.16b, v2.16b, v14.16b
+	st1		{v2.16b}, [x0], #16
+	tbnz		x9, #7, 7f
+
+	ld1		{v15.16b}, [x1], #16
+	eor		v5.16b, v5.16b, v15.16b
+	st1		{v5.16b}, [x0], #16
+
+	next_ctr	v0
+	cbnz		x4, 99b
+
+0:	st1		{v0.16b}, [x5]
+8:	ldp		x29, x30, [sp], #16
+	ret
+
+	/*
+	 * If we are handling the tail of the input (x6 == 1), return the
+	 * final keystream block back to the caller via the IV buffer.
+	 */
+1:	cbz		x6, 8b
+	st1		{v1.16b}, [x5]
+	b		8b
+2:	cbz		x6, 8b
+	st1		{v4.16b}, [x5]
+	b		8b
+3:	cbz		x6, 8b
+	st1		{v6.16b}, [x5]
+	b		8b
+4:	cbz		x6, 8b
+	st1		{v3.16b}, [x5]
+	b		8b
+5:	cbz		x6, 8b
+	st1		{v7.16b}, [x5]
+	b		8b
+6:	cbz		x6, 8b
+	st1		{v2.16b}, [x5]
+	b		8b
+7:	cbz		x6, 8b
+	st1		{v5.16b}, [x5]
+	b		8b
+ENDPROC(aesbs_ctr_encrypt)
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
new file mode 100644
index 000000000000..323dd76ae5f0
--- /dev/null
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -0,0 +1,420 @@
+/*
+ * Bit sliced AES using NEON instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <crypto/cbc.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/xts.h>
+#include <linux/module.h>
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+MODULE_ALIAS_CRYPTO("ecb(aes)");
+MODULE_ALIAS_CRYPTO("cbc(aes)");
+MODULE_ALIAS_CRYPTO("ctr(aes)");
+MODULE_ALIAS_CRYPTO("xts(aes)");
+
+asmlinkage void aesbs_convert_key(u8 out[], u32 const rk[], int rounds);
+
+asmlinkage void aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks);
+asmlinkage void aesbs_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks);
+
+asmlinkage void aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[]);
+
+asmlinkage void aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[], bool final);
+
+asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[]);
+asmlinkage void aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[]);
+
+asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
+struct aesbs_ctx {
+	u8	rk[13 * (8 * AES_BLOCK_SIZE) + 32];
+	int	rounds;
+} __aligned(AES_BLOCK_SIZE);
+
+struct aesbs_cbc_ctx {
+	struct aesbs_ctx	key;
+	u32			enc[AES_MAX_KEYLENGTH_U32];
+};
+
+struct aesbs_xts_ctx {
+	struct aesbs_ctx	key;
+	u32			twkey[AES_MAX_KEYLENGTH_U32];
+};
+
+static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			unsigned int key_len)
+{
+	struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_aes_ctx rk;
+	int err;
+
+	err = crypto_aes_expand_key(&rk, in_key, key_len);
+	if (err)
+		return err;
+
+	ctx->rounds = 6 + key_len / 4;
+
+	kernel_neon_begin();
+	aesbs_convert_key(ctx->rk, rk.key_enc, ctx->rounds);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int __ecb_crypt(struct skcipher_request *req,
+		       void (*fn)(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks))
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	kernel_neon_begin();
+	while (walk.nbytes >= AES_BLOCK_SIZE) {
+		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+		if (walk.nbytes < walk.total)
+			blocks = round_down(blocks,
+					    walk.stride / AES_BLOCK_SIZE);
+
+		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk,
+		   ctx->rounds, blocks);
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes - blocks * AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int ecb_encrypt(struct skcipher_request *req)
+{
+	return __ecb_crypt(req, aesbs_ecb_encrypt);
+}
+
+static int ecb_decrypt(struct skcipher_request *req)
+{
+	return __ecb_crypt(req, aesbs_ecb_decrypt);
+}
+
+static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			    unsigned int key_len)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_aes_ctx rk;
+	int err;
+
+	err = crypto_aes_expand_key(&rk, in_key, key_len);
+	if (err)
+		return err;
+
+	ctx->key.rounds = 6 + key_len / 4;
+
+	memcpy(ctx->enc, rk.key_enc, sizeof(ctx->enc));
+
+	kernel_neon_begin();
+	aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static void cbc_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	__aes_arm64_encrypt(ctx->enc, dst, src, ctx->key.rounds);
+}
+
+static int cbc_encrypt(struct skcipher_request *req)
+{
+	return crypto_cbc_encrypt_walk(req, cbc_encrypt_one);
+}
+
+static int cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	kernel_neon_begin();
+	while (walk.nbytes >= AES_BLOCK_SIZE) {
+		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+		if (walk.nbytes < walk.total)
+			blocks = round_down(blocks,
+					    walk.stride / AES_BLOCK_SIZE);
+
+		aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				  ctx->key.rk, ctx->key.rounds, blocks,
+				  walk.iv);
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes - blocks * AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int ctr_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	kernel_neon_begin();
+	while (walk.nbytes > 0) {
+		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+		bool final = (walk.total % AES_BLOCK_SIZE) != 0;
+
+		if (walk.nbytes < walk.total) {
+			blocks = round_down(blocks,
+					    walk.stride / AES_BLOCK_SIZE);
+			final = false;
+		}
+
+		aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				  ctx->rk, ctx->rounds, blocks, walk.iv, final);
+
+		if (final) {
+			u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+			u8 *src = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+
+			if (dst != src)
+				memcpy(dst, src, walk.total % AES_BLOCK_SIZE);
+			crypto_xor(dst, walk.iv, walk.total % AES_BLOCK_SIZE);
+
+			err = skcipher_walk_done(&walk, 0);
+			break;
+		}
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes - blocks * AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			    unsigned int key_len)
+{
+	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_aes_ctx rk;
+	int err;
+
+	err = xts_verify_key(tfm, in_key, key_len);
+	if (err)
+		return err;
+
+	key_len /= 2;
+	err = crypto_aes_expand_key(&rk, in_key + key_len, key_len);
+	if (err)
+		return err;
+
+	memcpy(ctx->twkey, rk.key_enc, sizeof(ctx->twkey));
+
+	return aesbs_setkey(tfm, in_key, key_len);
+}
+
+static int __xts_crypt(struct skcipher_request *req,
+		       void (*fn)(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[]))
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	__aes_arm64_encrypt(ctx->twkey, walk.iv, walk.iv, ctx->key.rounds);
+
+	kernel_neon_begin();
+	while (walk.nbytes >= AES_BLOCK_SIZE) {
+		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+		if (walk.nbytes < walk.total)
+			blocks = round_down(blocks,
+					    walk.stride / AES_BLOCK_SIZE);
+
+		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->key.rk,
+		   ctx->key.rounds, blocks, walk.iv);
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes - blocks * AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int xts_encrypt(struct skcipher_request *req)
+{
+	return __xts_crypt(req, aesbs_xts_encrypt);
+}
+
+static int xts_decrypt(struct skcipher_request *req)
+{
+	return __xts_crypt(req, aesbs_xts_decrypt);
+}
+
+static struct skcipher_alg aes_algs[] = { {
+	.base.cra_name		= "__ecb(aes)",
+	.base.cra_driver_name	= "__ecb-aes-neonbs",
+	.base.cra_priority	= 250,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct aesbs_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.setkey			= aesbs_setkey,
+	.encrypt		= ecb_encrypt,
+	.decrypt		= ecb_decrypt,
+}, {
+	.base.cra_name		= "__cbc(aes)",
+	.base.cra_driver_name	= "__cbc-aes-neonbs",
+	.base.cra_priority	= 250,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct aesbs_cbc_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= aesbs_cbc_setkey,
+	.encrypt		= cbc_encrypt,
+	.decrypt		= cbc_decrypt,
+}, {
+	.base.cra_name		= "__ctr(aes)",
+	.base.cra_driver_name	= "__ctr-aes-neonbs",
+	.base.cra_priority	= 250,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct aesbs_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= aesbs_setkey,
+	.encrypt		= ctr_encrypt,
+	.decrypt		= ctr_encrypt,
+}, {
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "ctr-aes-neonbs",
+	.base.cra_priority	= 250 - 1,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct aesbs_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= aesbs_setkey,
+	.encrypt		= ctr_encrypt,
+	.decrypt		= ctr_encrypt,
+}, {
+	.base.cra_name		= "__xts(aes)",
+	.base.cra_driver_name	= "__xts-aes-neonbs",
+	.base.cra_priority	= 250,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct aesbs_xts_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+
+	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
+	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= aesbs_xts_setkey,
+	.encrypt		= xts_encrypt,
+	.decrypt		= xts_decrypt,
+} };
+
+static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
+
+static void aes_exit(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(aes_simd_algs); i++)
+		if (aes_simd_algs[i])
+			simd_skcipher_free(aes_simd_algs[i]);
+
+	crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static int __init aes_init(void)
+{
+	struct simd_skcipher_alg *simd;
+	const char *basename;
+	const char *algname;
+	const char *drvname;
+	int err;
+	int i;
+
+	if (!(elf_hwcap & HWCAP_ASIMD))
+		return -ENODEV;
+
+	err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+		if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
+			continue;
+
+		algname = aes_algs[i].base.cra_name + 2;
+		drvname = aes_algs[i].base.cra_driver_name + 2;
+		basename = aes_algs[i].base.cra_driver_name;
+		simd = simd_skcipher_create_compat(algname, drvname, basename);
+		err = PTR_ERR(simd);
+		if (IS_ERR(simd))
+			goto unregister_simds;
+
+		aes_simd_algs[i] = simd;
+	}
+	return 0;
+
+unregister_simds:
+	aes_exit();
+	return err;
+}
+
+module_init(aes_init);
+module_exit(aes_exit);
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 5/7] crypto: arm/aes - replace scalar AES cipher
From: Ard Biesheuvel @ 2017-01-11 16:41 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484152915-26517-1-git-send-email-ard.biesheuvel@linaro.org>

This replaces the scalar AES cipher that originates in the OpenSSL project
with a new implementation that is ~15% (*) faster (on modern cores), and
reuses the lookup tables and the key schedule generation routines from the
generic C implementation (which is usually compiled in anyway due to
networking and other subsystems depending on it).

Note that the bit sliced NEON code for AES still depends on the scalar cipher
that this patch replaces, so it is not removed entirely yet.

* On Cortex-A57, the performance increases from 17.0 to 14.9 cycles per byte
  for 128-bit keys.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/crypto/Kconfig           |  20 +--
 arch/arm/crypto/Makefile          |   4 +-
 arch/arm/crypto/aes-cipher-core.S | 179 ++++++++++++++++++++
 arch/arm/crypto/aes-cipher-glue.c |  74 ++++++++
 arch/arm/crypto/aes_glue.c        |  98 -----------
 5 files changed, 256 insertions(+), 119 deletions(-)

diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 2f3339f015d3..f1de658c3c8f 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -62,33 +62,15 @@ config CRYPTO_SHA512_ARM
 	  using optimized ARM assembler and NEON, when available.
 
 config CRYPTO_AES_ARM
-	tristate "AES cipher algorithms (ARM-asm)"
-	depends on ARM
+	tristate "Scalar AES cipher for ARM"
 	select CRYPTO_ALGAPI
 	select CRYPTO_AES
 	help
 	  Use optimized AES assembler routines for ARM platforms.
 
-	  AES cipher algorithms (FIPS-197). AES uses the Rijndael
-	  algorithm.
-
-	  Rijndael appears to be consistently a very good performer in
-	  both hardware and software across a wide range of computing
-	  environments regardless of its use in feedback or non-feedback
-	  modes. Its key setup time is excellent, and its key agility is
-	  good. Rijndael's very low memory requirements make it very well
-	  suited for restricted-space environments, in which it also
-	  demonstrates excellent performance. Rijndael's operations are
-	  among the easiest to defend against power and timing attacks.
-
-	  The AES specifies three key sizes: 128, 192 and 256 bits
-
-	  See <http://csrc.nist.gov/encryption/aes/> for more information.
-
 config CRYPTO_AES_ARM_BS
 	tristate "Bit sliced AES using NEON instructions"
 	depends on KERNEL_MODE_NEON
-	select CRYPTO_AES_ARM
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_SIMD
 	help
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 8d74e55eacd4..8f5de2db701c 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -27,8 +27,8 @@ $(warning $(ce-obj-y) $(ce-obj-m))
 endif
 endif
 
-aes-arm-y	:= aes-armv4.o aes_glue.o
-aes-arm-bs-y	:= aesbs-core.o aesbs-glue.o
+aes-arm-y	:= aes-cipher-core.o aes-cipher-glue.o
+aes-arm-bs-y	:= aes-armv4.o aesbs-core.o aesbs-glue.o
 sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
 sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
 sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S
new file mode 100644
index 000000000000..b04261e1e068
--- /dev/null
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -0,0 +1,179 @@
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.align		5
+
+	rk		.req	r0
+	rounds		.req	r1
+	in		.req	r2
+	out		.req	r3
+	tt		.req	ip
+
+	t0		.req	lr
+	t1		.req	r2
+	t2		.req	r3
+
+	.macro		__select, out, in, idx
+	.if		__LINUX_ARM_ARCH__ < 7
+	and		\out, \in, #0xff << (8 * \idx)
+	.else
+	ubfx		\out, \in, #(8 * \idx), #8
+	.endif
+	.endm
+
+	.macro		__load, out, in, idx
+	.if		__LINUX_ARM_ARCH__ < 7 && \idx > 0
+	ldr		\out, [tt, \in, lsr #(8 * \idx) - 2]
+	.else
+	ldr		\out, [tt, \in, lsl #2]
+	.endif
+	.endm
+
+	.macro		__hround, out0, out1, in0, in1, in2, in3, t3, t4, enc
+	__select	\out0, \in0, 0
+	__select	t0, \in1, 1
+	__load		\out0, \out0, 0
+	__load		t0, t0, 1
+
+	.if		\enc
+	__select	\out1, \in1, 0
+	__select	t1, \in2, 1
+	.else
+	__select	\out1, \in3, 0
+	__select	t1, \in0, 1
+	.endif
+	__load		\out1, \out1, 0
+	__select	t2, \in2, 2
+	__load		t1, t1, 1
+	__load		t2, t2, 2
+
+	eor		\out0, \out0, t0, ror #24
+
+	__select	t0, \in3, 3
+	.if		\enc
+	__select	\t3, \in3, 2
+	__select	\t4, \in0, 3
+	.else
+	__select	\t3, \in1, 2
+	__select	\t4, \in2, 3
+	.endif
+	__load		\t3, \t3, 2
+	__load		t0, t0, 3
+	__load		\t4, \t4, 3
+
+	eor		\out1, \out1, t1, ror #24
+	eor		\out0, \out0, t2, ror #16
+	ldm		rk!, {t1, t2}
+	eor		\out1, \out1, \t3, ror #16
+	eor		\out0, \out0, t0, ror #8
+	eor		\out1, \out1, \t4, ror #8
+	eor		\out0, \out0, t1
+	eor		\out1, \out1, t2
+	.endm
+
+	.macro		fround, out0, out1, out2, out3, in0, in1, in2, in3
+	__hround	\out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1
+	__hround	\out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1
+	.endm
+
+	.macro		iround, out0, out1, out2, out3, in0, in1, in2, in3
+	__hround	\out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0
+	__hround	\out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0
+	.endm
+
+	.macro		__rev, out, in
+	.if		__LINUX_ARM_ARCH__ < 6
+	lsl		t0, \in, #24
+	and		t1, \in, #0xff00
+	and		t2, \in, #0xff0000
+	orr		\out, t0, \in, lsr #24
+	orr		\out, \out, t1, lsl #8
+	orr		\out, \out, t2, lsr #8
+	.else
+	rev		\out, \in
+	.endif
+	.endm
+
+	.macro		__adrl, out, sym, c
+	.if		__LINUX_ARM_ARCH__ < 7
+	ldr\c		\out, =\sym
+	.else
+	movw\c		\out, #:lower16:\sym
+	movt\c		\out, #:upper16:\sym
+	.endif
+	.endm
+
+	.macro		do_crypt, round, ttab, ltab
+	push		{r3-r11, lr}
+
+	ldr		r4, [in]
+	ldr		r5, [in, #4]
+	ldr		r6, [in, #8]
+	ldr		r7, [in, #12]
+
+	ldm		rk!, {r8-r11}
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	__rev		r4, r4
+	__rev		r5, r5
+	__rev		r6, r6
+	__rev		r7, r7
+#endif
+
+	eor		r4, r4, r8
+	eor		r5, r5, r9
+	eor		r6, r6, r10
+	eor		r7, r7, r11
+
+	__adrl		tt, \ttab
+
+	tst		rounds, #2
+	bne		1f
+
+0:	\round		r8, r9, r10, r11, r4, r5, r6, r7
+	\round		r4, r5, r6, r7, r8, r9, r10, r11
+
+1:	subs		rounds, rounds, #4
+	\round		r8, r9, r10, r11, r4, r5, r6, r7
+	__adrl		tt, \ltab, ls
+	\round		r4, r5, r6, r7, r8, r9, r10, r11
+	bhi		0b
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	__rev		r4, r4
+	__rev		r5, r5
+	__rev		r6, r6
+	__rev		r7, r7
+#endif
+
+	ldr		out, [sp]
+
+	str		r4, [out]
+	str		r5, [out, #4]
+	str		r6, [out, #8]
+	str		r7, [out, #12]
+
+	pop		{r3-r11, pc}
+
+	.align		3
+	.ltorg
+	.endm
+
+ENTRY(__aes_arm_encrypt)
+	do_crypt	fround, crypto_ft_tab, crypto_fl_tab
+ENDPROC(__aes_arm_encrypt)
+
+ENTRY(__aes_arm_decrypt)
+	do_crypt	iround, crypto_it_tab, crypto_il_tab
+ENDPROC(__aes_arm_decrypt)
diff --git a/arch/arm/crypto/aes-cipher-glue.c b/arch/arm/crypto/aes-cipher-glue.c
new file mode 100644
index 000000000000..c222f6e072ad
--- /dev/null
+++ b/arch/arm/crypto/aes-cipher-glue.c
@@ -0,0 +1,74 @@
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/aes.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+asmlinkage void __aes_arm_encrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
+EXPORT_SYMBOL(__aes_arm_encrypt);
+
+asmlinkage void __aes_arm_decrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
+EXPORT_SYMBOL(__aes_arm_decrypt);
+
+static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int rounds = 6 + ctx->key_length / 4;
+
+	__aes_arm_encrypt(ctx->key_enc, rounds, in, out);
+}
+
+static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int rounds = 6 + ctx->key_length / 4;
+
+	__aes_arm_decrypt(ctx->key_dec, rounds, in, out);
+}
+
+static struct crypto_alg aes_alg = {
+	.cra_name			= "aes",
+	.cra_driver_name		= "aes-arm",
+	.cra_priority			= 200,
+	.cra_flags			= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize			= AES_BLOCK_SIZE,
+	.cra_ctxsize			= sizeof(struct crypto_aes_ctx),
+	.cra_module			= THIS_MODULE,
+
+	.cra_cipher.cia_min_keysize	= AES_MIN_KEY_SIZE,
+	.cra_cipher.cia_max_keysize	= AES_MAX_KEY_SIZE,
+	.cra_cipher.cia_setkey		= crypto_aes_set_key,
+	.cra_cipher.cia_encrypt		= aes_encrypt,
+	.cra_cipher.cia_decrypt		= aes_decrypt,
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	.cra_alignmask			= 3,
+#endif
+};
+
+static int __init aes_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_fini(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_init(aes_init);
+module_exit(aes_fini);
+
+MODULE_DESCRIPTION("Scalar AES cipher for ARM");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c
deleted file mode 100644
index 0409b8f89782..000000000000
--- a/arch/arm/crypto/aes_glue.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * Glue Code for the asm optimized version of the AES Cipher Algorithm
- */
-
-#include <linux/module.h>
-#include <linux/crypto.h>
-#include <crypto/aes.h>
-
-#include "aes_glue.h"
-
-EXPORT_SYMBOL(AES_encrypt);
-EXPORT_SYMBOL(AES_decrypt);
-EXPORT_SYMBOL(private_AES_set_encrypt_key);
-EXPORT_SYMBOL(private_AES_set_decrypt_key);
-
-static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
-	struct AES_CTX *ctx = crypto_tfm_ctx(tfm);
-	AES_encrypt(src, dst, &ctx->enc_key);
-}
-
-static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
-	struct AES_CTX *ctx = crypto_tfm_ctx(tfm);
-	AES_decrypt(src, dst, &ctx->dec_key);
-}
-
-static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
-		unsigned int key_len)
-{
-	struct AES_CTX *ctx = crypto_tfm_ctx(tfm);
-
-	switch (key_len) {
-	case AES_KEYSIZE_128:
-		key_len = 128;
-		break;
-	case AES_KEYSIZE_192:
-		key_len = 192;
-		break;
-	case AES_KEYSIZE_256:
-		key_len = 256;
-		break;
-	default:
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
-
-	if (private_AES_set_encrypt_key(in_key, key_len, &ctx->enc_key) == -1) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
-	/* private_AES_set_decrypt_key expects an encryption key as input */
-	ctx->dec_key = ctx->enc_key;
-	if (private_AES_set_decrypt_key(in_key, key_len, &ctx->dec_key) == -1) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static struct crypto_alg aes_alg = {
-	.cra_name		= "aes",
-	.cra_driver_name	= "aes-asm",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct AES_CTX),
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(aes_alg.cra_list),
-	.cra_u	= {
-		.cipher	= {
-			.cia_min_keysize	= AES_MIN_KEY_SIZE,
-			.cia_max_keysize	= AES_MAX_KEY_SIZE,
-			.cia_setkey		= aes_set_key,
-			.cia_encrypt		= aes_encrypt,
-			.cia_decrypt		= aes_decrypt
-		}
-	}
-};
-
-static int __init aes_init(void)
-{
-	return crypto_register_alg(&aes_alg);
-}
-
-static void __exit aes_fini(void)
-{
-	crypto_unregister_alg(&aes_alg);
-}
-
-module_init(aes_init);
-module_exit(aes_fini);
-
-MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm (ASM)");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CRYPTO("aes");
-MODULE_ALIAS_CRYPTO("aes-asm");
-MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 4/7] crypto: arm64/aes - add scalar implementation
From: Ard Biesheuvel @ 2017-01-11 16:41 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484152915-26517-1-git-send-email-ard.biesheuvel@linaro.org>

This adds a scalar implementation of AES, based on the precomputed tables
that are exposed by the generic AES code. Since rotates are cheap on arm64,
this implementation only uses the 4 core tables (of 1 KB each), and avoids
the prerotated ones, reducing the D-cache footprint by 75%.

On Cortex-A57, this code manages 13.0 cycles per byte, which is ~34% faster
than the generic C code. (Note that this is still >13x slower than the code
that uses the optional ARMv8 Crypto Extensions, which manages <1 cycles per
byte.)

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/Kconfig           |   4 +
 arch/arm64/crypto/Makefile          |   3 +
 arch/arm64/crypto/aes-cipher-core.S | 127 ++++++++++++++++++++
 arch/arm64/crypto/aes-cipher-glue.c |  69 +++++++++++
 4 files changed, 203 insertions(+)

diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 0bf0f531f539..0826f8e599a6 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -41,6 +41,10 @@ config CRYPTO_CRC32_ARM64_CE
 	depends on KERNEL_MODE_NEON && CRC32
 	select CRYPTO_HASH
 
+config CRYPTO_AES_ARM64
+	tristate "AES core cipher using scalar instructions"
+	select CRYPTO_AES
+
 config CRYPTO_AES_ARM64_CE
 	tristate "AES core cipher using ARMv8 Crypto Extensions"
 	depends on ARM64 && KERNEL_MODE_NEON
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index 9d2826c5fccf..a893507629eb 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -44,6 +44,9 @@ sha512-arm64-y := sha512-glue.o sha512-core.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha20-neon.o
 chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o
 
+obj-$(CONFIG_CRYPTO_AES_ARM64) += aes-arm64.o
+aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o
+
 AFLAGS_aes-ce.o		:= -DINTERLEAVE=4
 AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
 
diff --git a/arch/arm64/crypto/aes-cipher-core.S b/arch/arm64/crypto/aes-cipher-core.S
new file mode 100644
index 000000000000..37590ab8121a
--- /dev/null
+++ b/arch/arm64/crypto/aes-cipher-core.S
@@ -0,0 +1,127 @@
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+
+	rk		.req	x0
+	out		.req	x1
+	in		.req	x2
+	rounds		.req	x3
+	tt		.req	x4
+	lt		.req	x2
+
+	.macro		__hround, out0, out1, in0, in1, in2, in3, t0, t1, enc
+	ldp		\out0, \out1, [rk], #8
+
+	ubfx		w13, \in0, #0, #8
+	ubfx		w14, \in1, #8, #8
+	ldr		w13, [tt, w13, uxtw #2]
+	ldr		w14, [tt, w14, uxtw #2]
+
+	.if		\enc
+	ubfx		w17, \in1, #0, #8
+	ubfx		w18, \in2, #8, #8
+	.else
+	ubfx		w17, \in3, #0, #8
+	ubfx		w18, \in0, #8, #8
+	.endif
+	ldr		w17, [tt, w17, uxtw #2]
+	ldr		w18, [tt, w18, uxtw #2]
+
+	ubfx		w15, \in2, #16, #8
+	ubfx		w16, \in3, #24, #8
+	ldr		w15, [tt, w15, uxtw #2]
+	ldr		w16, [tt, w16, uxtw #2]
+
+	.if		\enc
+	ubfx		\t0, \in3, #16, #8
+	ubfx		\t1, \in0, #24, #8
+	.else
+	ubfx		\t0, \in1, #16, #8
+	ubfx		\t1, \in2, #24, #8
+	.endif
+	ldr		\t0, [tt, \t0, uxtw #2]
+	ldr		\t1, [tt, \t1, uxtw #2]
+
+	eor		\out0, \out0, w13
+	eor		\out1, \out1, w17
+	eor		\out0, \out0, w14, ror #24
+	eor		\out1, \out1, w18, ror #24
+	eor		\out0, \out0, w15, ror #16
+	eor		\out1, \out1, \t0, ror #16
+	eor		\out0, \out0, w16, ror #8
+	eor		\out1, \out1, \t1, ror #8
+	.endm
+
+	.macro		fround, out0, out1, out2, out3, in0, in1, in2, in3
+	__hround	\out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1
+	__hround	\out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1
+	.endm
+
+	.macro		iround, out0, out1, out2, out3, in0, in1, in2, in3
+	__hround	\out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0
+	__hround	\out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0
+	.endm
+
+	.macro		do_crypt, round, ttab, ltab
+	ldp		w5, w6, [in]
+	ldp		w7, w8, [in, #8]
+	ldp		w9, w10, [rk], #16
+	ldp		w11, w12, [rk, #-8]
+
+CPU_BE(	rev		w5, w5		)
+CPU_BE(	rev		w6, w6		)
+CPU_BE(	rev		w7, w7		)
+CPU_BE(	rev		w8, w8		)
+
+	eor		w5, w5, w9
+	eor		w6, w6, w10
+	eor		w7, w7, w11
+	eor		w8, w8, w12
+
+	ldr		tt, =\ttab
+	ldr		lt, =\ltab
+
+	tbnz		rounds, #1, 1f
+
+0:	\round		w9, w10, w11, w12, w5, w6, w7, w8
+	\round		w5, w6, w7, w8, w9, w10, w11, w12
+
+1:	subs		rounds, rounds, #4
+	\round		w9, w10, w11, w12, w5, w6, w7, w8
+	csel		tt, tt, lt, hi
+	\round		w5, w6, w7, w8, w9, w10, w11, w12
+	b.hi		0b
+
+CPU_BE(	rev		w5, w5		)
+CPU_BE(	rev		w6, w6		)
+CPU_BE(	rev		w7, w7		)
+CPU_BE(	rev		w8, w8		)
+
+	stp		w5, w6, [out]
+	stp		w7, w8, [out, #8]
+	ret
+
+	.align		4
+	.ltorg
+	.endm
+
+	.align		5
+ENTRY(__aes_arm64_encrypt)
+	do_crypt	fround, crypto_ft_tab, crypto_fl_tab
+ENDPROC(__aes_arm64_encrypt)
+
+	.align		5
+ENTRY(__aes_arm64_decrypt)
+	do_crypt	iround, crypto_it_tab, crypto_il_tab
+ENDPROC(__aes_arm64_decrypt)
diff --git a/arch/arm64/crypto/aes-cipher-glue.c b/arch/arm64/crypto/aes-cipher-glue.c
new file mode 100644
index 000000000000..7288e7cbebff
--- /dev/null
+++ b/arch/arm64/crypto/aes-cipher-glue.c
@@ -0,0 +1,69 @@
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/aes.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+EXPORT_SYMBOL(__aes_arm64_encrypt);
+
+asmlinkage void __aes_arm64_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+EXPORT_SYMBOL(__aes_arm64_decrypt);
+
+static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int rounds = 6 + ctx->key_length / 4;
+
+	__aes_arm64_encrypt(ctx->key_enc, out, in, rounds);
+}
+
+static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int rounds = 6 + ctx->key_length / 4;
+
+	__aes_arm64_decrypt(ctx->key_dec, out, in, rounds);
+}
+
+static struct crypto_alg aes_alg = {
+	.cra_name			= "aes",
+	.cra_driver_name		= "aes-arm64",
+	.cra_priority			= 200,
+	.cra_flags			= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize			= AES_BLOCK_SIZE,
+	.cra_ctxsize			= sizeof(struct crypto_aes_ctx),
+	.cra_module			= THIS_MODULE,
+
+	.cra_cipher.cia_min_keysize	= AES_MIN_KEY_SIZE,
+	.cra_cipher.cia_max_keysize	= AES_MAX_KEY_SIZE,
+	.cra_cipher.cia_setkey		= crypto_aes_set_key,
+	.cra_cipher.cia_encrypt		= aes_encrypt,
+	.cra_cipher.cia_decrypt		= aes_decrypt
+};
+
+static int __init aes_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_fini(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_init(aes_init);
+module_exit(aes_fini);
+
+MODULE_DESCRIPTION("Scalar AES cipher for arm64");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("aes");
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 3/7] crypto: arm64/aes-blk - expose AES-CTR as synchronous cipher as well
From: Ard Biesheuvel @ 2017-01-11 16:41 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484152915-26517-1-git-send-email-ard.biesheuvel@linaro.org>

In addition to wrapping the AES-CTR cipher into the async SIMD wrapper,
which exposes it as an async skcipher that defers processing to process
context, expose our AES-CTR implementation directly as a synchronous cipher
as well, but with a lower priority.

This makes the AES-CTR transform usable in places where synchronous
transforms are required, such as the MAC802.11 encryption code, which
executes in sotfirq context, where SIMD processing is allowed on arm64.
Users of the async transform will keep the existing behavior.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/aes-glue.c | 25 ++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 4e3f8adb1793..5164aaf82c6a 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -327,6 +327,23 @@ static struct skcipher_alg aes_algs[] = { {
 	.decrypt	= ctr_encrypt,
 }, {
 	.base = {
+		.cra_name		= "ctr(aes)",
+		.cra_driver_name	= "ctr-aes-" MODE,
+		.cra_priority		= PRIO - 1,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+		.cra_alignmask		= 7,
+		.cra_module		= THIS_MODULE,
+	},
+	.min_keysize	= AES_MIN_KEY_SIZE,
+	.max_keysize	= AES_MAX_KEY_SIZE,
+	.ivsize		= AES_BLOCK_SIZE,
+	.chunksize	= AES_BLOCK_SIZE,
+	.setkey		= skcipher_aes_setkey,
+	.encrypt	= ctr_encrypt,
+	.decrypt	= ctr_encrypt,
+}, {
+	.base = {
 		.cra_name		= "__xts(aes)",
 		.cra_driver_name	= "__xts-aes-" MODE,
 		.cra_priority		= PRIO,
@@ -350,8 +367,9 @@ static void aes_exit(void)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(aes_simd_algs) && aes_simd_algs[i]; i++)
-		simd_skcipher_free(aes_simd_algs[i]);
+	for (i = 0; i < ARRAY_SIZE(aes_simd_algs); i++)
+		if (aes_simd_algs[i])
+			simd_skcipher_free(aes_simd_algs[i]);
 
 	crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 }
@@ -370,6 +388,9 @@ static int __init aes_init(void)
 		return err;
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+		if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
+			continue;
+
 		algname = aes_algs[i].base.cra_name + 2;
 		drvname = aes_algs[i].base.cra_driver_name + 2;
 		basename = aes_algs[i].base.cra_driver_name;
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 2/7] crypto: arm/chacha20 - implement NEON version based on SSE3 code
From: Ard Biesheuvel @ 2017-01-11 16:41 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484152915-26517-1-git-send-email-ard.biesheuvel@linaro.org>

This is a straight port to ARM/NEON of the x86 SSE3 implementation
of the ChaCha20 stream cipher. It uses the new skcipher walksize
attribute to process the input in strides of 4x the block size.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/crypto/Kconfig              |   6 +
 arch/arm/crypto/Makefile             |   2 +
 arch/arm/crypto/chacha20-neon-core.S | 524 ++++++++++++++++++++
 arch/arm/crypto/chacha20-neon-glue.c | 128 +++++
 4 files changed, 660 insertions(+)

diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 13f1b4c289d4..2f3339f015d3 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -130,4 +130,10 @@ config CRYPTO_CRC32_ARM_CE
 	depends on KERNEL_MODE_NEON && CRC32
 	select CRYPTO_HASH
 
+config CRYPTO_CHACHA20_NEON
+	tristate "NEON accelerated ChaCha20 symmetric cipher"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_CHACHA20
+
 endif
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index b578a1820ab1..8d74e55eacd4 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
+obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha20-neon.o
 
 ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -40,6 +41,7 @@ aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
 ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
 crct10dif-arm-ce-y	:= crct10dif-ce-core.o crct10dif-ce-glue.o
 crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o
+chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o
 
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)
diff --git a/arch/arm/crypto/chacha20-neon-core.S b/arch/arm/crypto/chacha20-neon-core.S
new file mode 100644
index 000000000000..ff1d337bdb4a
--- /dev/null
+++ b/arch/arm/crypto/chacha20-neon-core.S
@@ -0,0 +1,524 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539, ARM NEON functions
+ *
+ * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSE3 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.fpu		neon
+	.align		5
+
+ENTRY(chacha20_block_xor_neon)
+	// r0: Input state matrix, s
+	// r1: 1 data block output, o
+	// r2: 1 data block input, i
+
+	//
+	// This function encrypts one ChaCha20 block by loading the state matrix
+	// in four NEON registers. It performs matrix operation on four words in
+	// parallel, but requireds shuffling to rearrange the words after each
+	// round.
+	//
+
+	// x0..3 = s0..3
+	add		ip, r0, #0x20
+	vld1.32		{q0-q1}, [r0]
+	vld1.32		{q2-q3}, [ip]
+
+	vmov		q8, q0
+	vmov		q9, q1
+	vmov		q10, q2
+	vmov		q11, q3
+
+	mov		r3, #10
+
+.Ldoubleround:
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	vadd.i32	q0, q0, q1
+	veor		q4, q3, q0
+	vshl.u32	q3, q4, #16
+	vsri.u32	q3, q4, #16
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	vadd.i32	q2, q2, q3
+	veor		q4, q1, q2
+	vshl.u32	q1, q4, #12
+	vsri.u32	q1, q4, #20
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	vadd.i32	q0, q0, q1
+	veor		q4, q3, q0
+	vshl.u32	q3, q4, #8
+	vsri.u32	q3, q4, #24
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	vadd.i32	q2, q2, q3
+	veor		q4, q1, q2
+	vshl.u32	q1, q4, #7
+	vsri.u32	q1, q4, #25
+
+	// x1 = shuffle32(x1, MASK(0, 3, 2, 1))
+	vext.8		q1, q1, q1, #4
+	// x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	vext.8		q2, q2, q2, #8
+	// x3 = shuffle32(x3, MASK(2, 1, 0, 3))
+	vext.8		q3, q3, q3, #12
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	vadd.i32	q0, q0, q1
+	veor		q4, q3, q0
+	vshl.u32	q3, q4, #16
+	vsri.u32	q3, q4, #16
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	vadd.i32	q2, q2, q3
+	veor		q4, q1, q2
+	vshl.u32	q1, q4, #12
+	vsri.u32	q1, q4, #20
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	vadd.i32	q0, q0, q1
+	veor		q4, q3, q0
+	vshl.u32	q3, q4, #8
+	vsri.u32	q3, q4, #24
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	vadd.i32	q2, q2, q3
+	veor		q4, q1, q2
+	vshl.u32	q1, q4, #7
+	vsri.u32	q1, q4, #25
+
+	// x1 = shuffle32(x1, MASK(2, 1, 0, 3))
+	vext.8		q1, q1, q1, #12
+	// x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	vext.8		q2, q2, q2, #8
+	// x3 = shuffle32(x3, MASK(0, 3, 2, 1))
+	vext.8		q3, q3, q3, #4
+
+	subs		r3, r3, #1
+	bne		.Ldoubleround
+
+	add		ip, r2, #0x20
+	vld1.8		{q4-q5}, [r2]
+	vld1.8		{q6-q7}, [ip]
+
+	// o0 = i0 ^ (x0 + s0)
+	vadd.i32	q0, q0, q8
+	veor		q0, q0, q4
+
+	// o1 = i1 ^ (x1 + s1)
+	vadd.i32	q1, q1, q9
+	veor		q1, q1, q5
+
+	// o2 = i2 ^ (x2 + s2)
+	vadd.i32	q2, q2, q10
+	veor		q2, q2, q6
+
+	// o3 = i3 ^ (x3 + s3)
+	vadd.i32	q3, q3, q11
+	veor		q3, q3, q7
+
+	add		ip, r1, #0x20
+	vst1.8		{q0-q1}, [r1]
+	vst1.8		{q2-q3}, [ip]
+
+	bx		lr
+ENDPROC(chacha20_block_xor_neon)
+
+	.align		5
+ENTRY(chacha20_4block_xor_neon)
+	push		{r4-r6, lr}
+	mov		ip, sp			// preserve the stack pointer
+	sub		r3, sp, #0x20		// allocate a 32 byte buffer
+	bic		r3, r3, #0x1f		// aligned to 32 bytes
+	mov		sp, r3
+
+	// r0: Input state matrix, s
+	// r1: 4 data blocks output, o
+	// r2: 4 data blocks input, i
+
+	//
+	// This function encrypts four consecutive ChaCha20 blocks by loading
+	// the state matrix in NEON registers four times. The algorithm performs
+	// each operation on the corresponding word of each state matrix, hence
+	// requires no word shuffling. For final XORing step we transpose the
+	// matrix by interleaving 32- and then 64-bit words, which allows us to
+	// do XOR in NEON registers.
+	//
+
+	// x0..15[0-3] = s0..3[0..3]
+	add		r3, r0, #0x20
+	vld1.32		{q0-q1}, [r0]
+	vld1.32		{q2-q3}, [r3]
+
+	adr		r3, CTRINC
+	vdup.32		q15, d7[1]
+	vdup.32		q14, d7[0]
+	vld1.32		{q11}, [r3, :128]
+	vdup.32		q13, d6[1]
+	vdup.32		q12, d6[0]
+	vadd.i32	q12, q12, q11		// x12 += counter values 0-3
+	vdup.32		q11, d5[1]
+	vdup.32		q10, d5[0]
+	vdup.32		q9, d4[1]
+	vdup.32		q8, d4[0]
+	vdup.32		q7, d3[1]
+	vdup.32		q6, d3[0]
+	vdup.32		q5, d2[1]
+	vdup.32		q4, d2[0]
+	vdup.32		q3, d1[1]
+	vdup.32		q2, d1[0]
+	vdup.32		q1, d0[1]
+	vdup.32		q0, d0[0]
+
+	mov		r3, #10
+
+.Ldoubleround4:
+	// x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+	// x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+	// x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+	// x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+	vadd.i32	q0, q0, q4
+	vadd.i32	q1, q1, q5
+	vadd.i32	q2, q2, q6
+	vadd.i32	q3, q3, q7
+
+	veor		q12, q12, q0
+	veor		q13, q13, q1
+	veor		q14, q14, q2
+	veor		q15, q15, q3
+
+	vrev32.16	q12, q12
+	vrev32.16	q13, q13
+	vrev32.16	q14, q14
+	vrev32.16	q15, q15
+
+	// x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+	// x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+	// x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+	// x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+	vadd.i32	q8, q8, q12
+	vadd.i32	q9, q9, q13
+	vadd.i32	q10, q10, q14
+	vadd.i32	q11, q11, q15
+
+	vst1.32		{q8-q9}, [sp, :256]
+
+	veor		q8, q4, q8
+	veor		q9, q5, q9
+	vshl.u32	q4, q8, #12
+	vshl.u32	q5, q9, #12
+	vsri.u32	q4, q8, #20
+	vsri.u32	q5, q9, #20
+
+	veor		q8, q6, q10
+	veor		q9, q7, q11
+	vshl.u32	q6, q8, #12
+	vshl.u32	q7, q9, #12
+	vsri.u32	q6, q8, #20
+	vsri.u32	q7, q9, #20
+
+	// x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+	// x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+	// x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+	// x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+	vadd.i32	q0, q0, q4
+	vadd.i32	q1, q1, q5
+	vadd.i32	q2, q2, q6
+	vadd.i32	q3, q3, q7
+
+	veor		q8, q12, q0
+	veor		q9, q13, q1
+	vshl.u32	q12, q8, #8
+	vshl.u32	q13, q9, #8
+	vsri.u32	q12, q8, #24
+	vsri.u32	q13, q9, #24
+
+	veor		q8, q14, q2
+	veor		q9, q15, q3
+	vshl.u32	q14, q8, #8
+	vshl.u32	q15, q9, #8
+	vsri.u32	q14, q8, #24
+	vsri.u32	q15, q9, #24
+
+	vld1.32		{q8-q9}, [sp, :256]
+
+	// x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+	// x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+	// x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+	// x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+	vadd.i32	q8, q8, q12
+	vadd.i32	q9, q9, q13
+	vadd.i32	q10, q10, q14
+	vadd.i32	q11, q11, q15
+
+	vst1.32		{q8-q9}, [sp, :256]
+
+	veor		q8, q4, q8
+	veor		q9, q5, q9
+	vshl.u32	q4, q8, #7
+	vshl.u32	q5, q9, #7
+	vsri.u32	q4, q8, #25
+	vsri.u32	q5, q9, #25
+
+	veor		q8, q6, q10
+	veor		q9, q7, q11
+	vshl.u32	q6, q8, #7
+	vshl.u32	q7, q9, #7
+	vsri.u32	q6, q8, #25
+	vsri.u32	q7, q9, #25
+
+	vld1.32		{q8-q9}, [sp, :256]
+
+	// x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+	// x1 += x6, x12 = rotl32(x12 ^ x1, 16)
+	// x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+	// x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+	vadd.i32	q0, q0, q5
+	vadd.i32	q1, q1, q6
+	vadd.i32	q2, q2, q7
+	vadd.i32	q3, q3, q4
+
+	veor		q15, q15, q0
+	veor		q12, q12, q1
+	veor		q13, q13, q2
+	veor		q14, q14, q3
+
+	vrev32.16	q15, q15
+	vrev32.16	q12, q12
+	vrev32.16	q13, q13
+	vrev32.16	q14, q14
+
+	// x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+	// x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+	// x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+	// x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+	vadd.i32	q10, q10, q15
+	vadd.i32	q11, q11, q12
+	vadd.i32	q8, q8, q13
+	vadd.i32	q9, q9, q14
+
+	vst1.32		{q8-q9}, [sp, :256]
+
+	veor		q8, q7, q8
+	veor		q9, q4, q9
+	vshl.u32	q7, q8, #12
+	vshl.u32	q4, q9, #12
+	vsri.u32	q7, q8, #20
+	vsri.u32	q4, q9, #20
+
+	veor		q8, q5, q10
+	veor		q9, q6, q11
+	vshl.u32	q5, q8, #12
+	vshl.u32	q6, q9, #12
+	vsri.u32	q5, q8, #20
+	vsri.u32	q6, q9, #20
+
+	// x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+	// x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+	// x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+	// x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+	vadd.i32	q0, q0, q5
+	vadd.i32	q1, q1, q6
+	vadd.i32	q2, q2, q7
+	vadd.i32	q3, q3, q4
+
+	veor		q8, q15, q0
+	veor		q9, q12, q1
+	vshl.u32	q15, q8, #8
+	vshl.u32	q12, q9, #8
+	vsri.u32	q15, q8, #24
+	vsri.u32	q12, q9, #24
+
+	veor		q8, q13, q2
+	veor		q9, q14, q3
+	vshl.u32	q13, q8, #8
+	vshl.u32	q14, q9, #8
+	vsri.u32	q13, q8, #24
+	vsri.u32	q14, q9, #24
+
+	vld1.32		{q8-q9}, [sp, :256]
+
+	// x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+	// x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+	// x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+	// x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+	vadd.i32	q10, q10, q15
+	vadd.i32	q11, q11, q12
+	vadd.i32	q8, q8, q13
+	vadd.i32	q9, q9, q14
+
+	vst1.32		{q8-q9}, [sp, :256]
+
+	veor		q8, q7, q8
+	veor		q9, q4, q9
+	vshl.u32	q7, q8, #7
+	vshl.u32	q4, q9, #7
+	vsri.u32	q7, q8, #25
+	vsri.u32	q4, q9, #25
+
+	veor		q8, q5, q10
+	veor		q9, q6, q11
+	vshl.u32	q5, q8, #7
+	vshl.u32	q6, q9, #7
+	vsri.u32	q5, q8, #25
+	vsri.u32	q6, q9, #25
+
+	subs		r3, r3, #1
+	beq		0f
+
+	vld1.32		{q8-q9}, [sp, :256]
+	b		.Ldoubleround4
+
+	// x0[0-3] += s0[0]
+	// x1[0-3] += s0[1]
+	// x2[0-3] += s0[2]
+	// x3[0-3] += s0[3]
+0:	ldmia		r0!, {r3-r6}
+	vdup.32		q8, r3
+	vdup.32		q9, r4
+	vadd.i32	q0, q0, q8
+	vadd.i32	q1, q1, q9
+	vdup.32		q8, r5
+	vdup.32		q9, r6
+	vadd.i32	q2, q2, q8
+	vadd.i32	q3, q3, q9
+
+	// x4[0-3] += s1[0]
+	// x5[0-3] += s1[1]
+	// x6[0-3] += s1[2]
+	// x7[0-3] += s1[3]
+	ldmia		r0!, {r3-r6}
+	vdup.32		q8, r3
+	vdup.32		q9, r4
+	vadd.i32	q4, q4, q8
+	vadd.i32	q5, q5, q9
+	vdup.32		q8, r5
+	vdup.32		q9, r6
+	vadd.i32	q6, q6, q8
+	vadd.i32	q7, q7, q9
+
+	// interleave 32-bit words in state n, n+1
+	vzip.32		q0, q1
+	vzip.32		q2, q3
+	vzip.32		q4, q5
+	vzip.32		q6, q7
+
+	// interleave 64-bit words in state n, n+2
+	vswp		d1, d4
+	vswp		d3, d6
+	vswp		d9, d12
+	vswp		d11, d14
+
+	// xor with corresponding input, write to output
+	vld1.8		{q8-q9}, [r2]!
+	veor		q8, q8, q0
+	veor		q9, q9, q4
+	vst1.8		{q8-q9}, [r1]!
+
+	vld1.32		{q8-q9}, [sp, :256]
+
+	// x8[0-3] += s2[0]
+	// x9[0-3] += s2[1]
+	// x10[0-3] += s2[2]
+	// x11[0-3] += s2[3]
+	ldmia		r0!, {r3-r6}
+	vdup.32		q0, r3
+	vdup.32		q4, r4
+	vadd.i32	q8, q8, q0
+	vadd.i32	q9, q9, q4
+	vdup.32		q0, r5
+	vdup.32		q4, r6
+	vadd.i32	q10, q10, q0
+	vadd.i32	q11, q11, q4
+
+	// x12[0-3] += s3[0]
+	// x13[0-3] += s3[1]
+	// x14[0-3] += s3[2]
+	// x15[0-3] += s3[3]
+	ldmia		r0!, {r3-r6}
+	vdup.32		q0, r3
+	vdup.32		q4, r4
+	adr		r3, CTRINC
+	vadd.i32	q12, q12, q0
+	vld1.32		{q0}, [r3, :128]
+	vadd.i32	q13, q13, q4
+	vadd.i32	q12, q12, q0		// x12 += counter values 0-3
+
+	vdup.32		q0, r5
+	vdup.32		q4, r6
+	vadd.i32	q14, q14, q0
+	vadd.i32	q15, q15, q4
+
+	// interleave 32-bit words in state n, n+1
+	vzip.32		q8, q9
+	vzip.32		q10, q11
+	vzip.32		q12, q13
+	vzip.32		q14, q15
+
+	// interleave 64-bit words in state n, n+2
+	vswp		d17, d20
+	vswp		d19, d22
+	vswp		d25, d28
+	vswp		d27, d30
+
+	vmov		q4, q1
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q8
+	veor		q1, q1, q12
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q2
+	veor		q1, q1, q6
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q10
+	veor		q1, q1, q14
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q4
+	veor		q1, q1, q5
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q9
+	veor		q1, q1, q13
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q3
+	veor		q1, q1, q7
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]
+	veor		q0, q0, q11
+	veor		q1, q1, q15
+	vst1.8		{q0-q1}, [r1]
+
+	mov		sp, ip
+	pop		{r4-r6, pc}
+ENDPROC(chacha20_4block_xor_neon)
+
+	.align		4
+CTRINC:	.word		0, 1, 2, 3
+
diff --git a/arch/arm/crypto/chacha20-neon-glue.c b/arch/arm/crypto/chacha20-neon-glue.c
new file mode 100644
index 000000000000..592f75ae4fa1
--- /dev/null
+++ b/arch/arm/crypto/chacha20-neon-glue.c
@@ -0,0 +1,128 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539, ARM NEON functions
+ *
+ * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/chacha20.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void chacha20_block_xor_neon(u32 *state, u8 *dst, const u8 *src);
+asmlinkage void chacha20_4block_xor_neon(u32 *state, u8 *dst, const u8 *src);
+
+static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src,
+			    unsigned int bytes)
+{
+	u8 buf[CHACHA20_BLOCK_SIZE];
+
+	while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
+		chacha20_4block_xor_neon(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE * 4;
+		src += CHACHA20_BLOCK_SIZE * 4;
+		dst += CHACHA20_BLOCK_SIZE * 4;
+		state[12] += 4;
+	}
+	while (bytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_block_xor_neon(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE;
+		src += CHACHA20_BLOCK_SIZE;
+		dst += CHACHA20_BLOCK_SIZE;
+		state[12]++;
+	}
+	if (bytes) {
+		memcpy(buf, src, bytes);
+		chacha20_block_xor_neon(state, buf, buf);
+		memcpy(dst, buf, bytes);
+	}
+}
+
+static int chacha20_neon(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	u32 state[16];
+	int err;
+
+	if (req->cryptlen <= CHACHA20_BLOCK_SIZE || !may_use_simd())
+		return crypto_chacha20_crypt(req);
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	crypto_chacha20_init(state, ctx, walk.iv);
+
+	kernel_neon_begin();
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
+
+		chacha20_doneon(state, walk.dst.virt.addr, walk.src.virt.addr,
+				nbytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static struct skcipher_alg alg = {
+	.base.cra_name		= "chacha20",
+	.base.cra_driver_name	= "chacha20-neon",
+	.base.cra_priority	= 300,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct chacha20_ctx),
+	.base.cra_alignmask	= 1,
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= CHACHA20_KEY_SIZE,
+	.max_keysize		= CHACHA20_KEY_SIZE,
+	.ivsize			= CHACHA20_IV_SIZE,
+	.chunksize		= CHACHA20_BLOCK_SIZE,
+	.walksize		= 4 * CHACHA20_BLOCK_SIZE,
+	.setkey			= crypto_chacha20_setkey,
+	.encrypt		= chacha20_neon,
+	.decrypt		= chacha20_neon,
+};
+
+static int __init chacha20_simd_mod_init(void)
+{
+	if (!(elf_hwcap & HWCAP_NEON))
+		return -ENODEV;
+
+	return crypto_register_skcipher(&alg);
+}
+
+static void __exit chacha20_simd_mod_fini(void)
+{
+	crypto_unregister_skcipher(&alg);
+}
+
+module_init(chacha20_simd_mod_init);
+module_exit(chacha20_simd_mod_fini);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("chacha20");
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 1/7] crypto: arm64/chacha20 - implement NEON version based on SSE3 code
From: Ard Biesheuvel @ 2017-01-11 16:41 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1484152915-26517-1-git-send-email-ard.biesheuvel@linaro.org>

This is a straight port to arm64/NEON of the x86 SSE3 implementation
of the ChaCha20 stream cipher. It uses the new skcipher walksize
attribute to process the input in strides of 4x the block size.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/Kconfig              |   6 +
 arch/arm64/crypto/Makefile             |   3 +
 arch/arm64/crypto/chacha20-neon-core.S | 450 ++++++++++++++++++++
 arch/arm64/crypto/chacha20-neon-glue.c | 127 ++++++
 4 files changed, 586 insertions(+)

diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 450a85df041a..0bf0f531f539 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -72,4 +72,10 @@ config CRYPTO_CRC32_ARM64
 	depends on ARM64
 	select CRYPTO_HASH
 
+config CRYPTO_CHACHA20_NEON
+	tristate "NEON accelerated ChaCha20 symmetric cipher"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_CHACHA20
+
 endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index aa8888d7b744..9d2826c5fccf 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -41,6 +41,9 @@ sha256-arm64-y := sha256-glue.o sha256-core.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM64) += sha512-arm64.o
 sha512-arm64-y := sha512-glue.o sha512-core.o
 
+obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha20-neon.o
+chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o
+
 AFLAGS_aes-ce.o		:= -DINTERLEAVE=4
 AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
 
diff --git a/arch/arm64/crypto/chacha20-neon-core.S b/arch/arm64/crypto/chacha20-neon-core.S
new file mode 100644
index 000000000000..13c85e272c2a
--- /dev/null
+++ b/arch/arm64/crypto/chacha20-neon-core.S
@@ -0,0 +1,450 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539, arm64 NEON functions
+ *
+ * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.align		6
+
+ENTRY(chacha20_block_xor_neon)
+	// x0: Input state matrix, s
+	// x1: 1 data block output, o
+	// x2: 1 data block input, i
+
+	//
+	// This function encrypts one ChaCha20 block by loading the state matrix
+	// in four NEON registers. It performs matrix operation on four words in
+	// parallel, but requires shuffling to rearrange the words after each
+	// round.
+	//
+
+	// x0..3 = s0..3
+	adr		x3, ROT8
+	ld1		{v0.4s-v3.4s}, [x0]
+	ld1		{v8.4s-v11.4s}, [x0]
+	ld1		{v12.4s}, [x3]
+
+	mov		x3, #10
+
+.Ldoubleround:
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	add		v0.4s, v0.4s, v1.4s
+	eor		v3.16b, v3.16b, v0.16b
+	rev32		v3.8h, v3.8h
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	add		v2.4s, v2.4s, v3.4s
+	eor		v4.16b, v1.16b, v2.16b
+	shl		v1.4s, v4.4s, #12
+	sri		v1.4s, v4.4s, #20
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	add		v0.4s, v0.4s, v1.4s
+	eor		v3.16b, v3.16b, v0.16b
+	tbl		v3.16b, {v3.16b}, v12.16b
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	add		v2.4s, v2.4s, v3.4s
+	eor		v4.16b, v1.16b, v2.16b
+	shl		v1.4s, v4.4s, #7
+	sri		v1.4s, v4.4s, #25
+
+	// x1 = shuffle32(x1, MASK(0, 3, 2, 1))
+	ext		v1.16b, v1.16b, v1.16b, #4
+	// x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	ext		v2.16b, v2.16b, v2.16b, #8
+	// x3 = shuffle32(x3, MASK(2, 1, 0, 3))
+	ext		v3.16b, v3.16b, v3.16b, #12
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	add		v0.4s, v0.4s, v1.4s
+	eor		v3.16b, v3.16b, v0.16b
+	rev32		v3.8h, v3.8h
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	add		v2.4s, v2.4s, v3.4s
+	eor		v4.16b, v1.16b, v2.16b
+	shl		v1.4s, v4.4s, #12
+	sri		v1.4s, v4.4s, #20
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	add		v0.4s, v0.4s, v1.4s
+	eor		v3.16b, v3.16b, v0.16b
+	tbl		v3.16b, {v3.16b}, v12.16b
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	add		v2.4s, v2.4s, v3.4s
+	eor		v4.16b, v1.16b, v2.16b
+	shl		v1.4s, v4.4s, #7
+	sri		v1.4s, v4.4s, #25
+
+	// x1 = shuffle32(x1, MASK(2, 1, 0, 3))
+	ext		v1.16b, v1.16b, v1.16b, #12
+	// x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	ext		v2.16b, v2.16b, v2.16b, #8
+	// x3 = shuffle32(x3, MASK(0, 3, 2, 1))
+	ext		v3.16b, v3.16b, v3.16b, #4
+
+	subs		x3, x3, #1
+	b.ne		.Ldoubleround
+
+	ld1		{v4.16b-v7.16b}, [x2]
+
+	// o0 = i0 ^ (x0 + s0)
+	add		v0.4s, v0.4s, v8.4s
+	eor		v0.16b, v0.16b, v4.16b
+
+	// o1 = i1 ^ (x1 + s1)
+	add		v1.4s, v1.4s, v9.4s
+	eor		v1.16b, v1.16b, v5.16b
+
+	// o2 = i2 ^ (x2 + s2)
+	add		v2.4s, v2.4s, v10.4s
+	eor		v2.16b, v2.16b, v6.16b
+
+	// o3 = i3 ^ (x3 + s3)
+	add		v3.4s, v3.4s, v11.4s
+	eor		v3.16b, v3.16b, v7.16b
+
+	st1		{v0.16b-v3.16b}, [x1]
+
+	ret
+ENDPROC(chacha20_block_xor_neon)
+
+	.align		6
+ENTRY(chacha20_4block_xor_neon)
+	// x0: Input state matrix, s
+	// x1: 4 data blocks output, o
+	// x2: 4 data blocks input, i
+
+	//
+	// This function encrypts four consecutive ChaCha20 blocks by loading
+	// the state matrix in NEON registers four times. The algorithm performs
+	// each operation on the corresponding word of each state matrix, hence
+	// requires no word shuffling. For final XORing step we transpose the
+	// matrix by interleaving 32- and then 64-bit words, which allows us to
+	// do XOR in NEON registers.
+	//
+	adr		x3, CTRINC		// ... and ROT8
+	ld1		{v30.4s-v31.4s}, [x3]
+
+	// x0..15[0-3] = s0..3[0..3]
+	mov		x4, x0
+	ld4r		{ v0.4s- v3.4s}, [x4], #16
+	ld4r		{ v4.4s- v7.4s}, [x4], #16
+	ld4r		{ v8.4s-v11.4s}, [x4], #16
+	ld4r		{v12.4s-v15.4s}, [x4]
+
+	// x12 += counter values 0-3
+	add		v12.4s, v12.4s, v30.4s
+
+	mov		x3, #10
+
+.Ldoubleround4:
+	// x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+	// x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+	// x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+	// x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+	add		v0.4s, v0.4s, v4.4s
+	add		v1.4s, v1.4s, v5.4s
+	add		v2.4s, v2.4s, v6.4s
+	add		v3.4s, v3.4s, v7.4s
+
+	eor		v12.16b, v12.16b, v0.16b
+	eor		v13.16b, v13.16b, v1.16b
+	eor		v14.16b, v14.16b, v2.16b
+	eor		v15.16b, v15.16b, v3.16b
+
+	rev32		v12.8h, v12.8h
+	rev32		v13.8h, v13.8h
+	rev32		v14.8h, v14.8h
+	rev32		v15.8h, v15.8h
+
+	// x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+	// x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+	// x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+	// x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+	add		v8.4s, v8.4s, v12.4s
+	add		v9.4s, v9.4s, v13.4s
+	add		v10.4s, v10.4s, v14.4s
+	add		v11.4s, v11.4s, v15.4s
+
+	eor		v16.16b, v4.16b, v8.16b
+	eor		v17.16b, v5.16b, v9.16b
+	eor		v18.16b, v6.16b, v10.16b
+	eor		v19.16b, v7.16b, v11.16b
+
+	shl		v4.4s, v16.4s, #12
+	shl		v5.4s, v17.4s, #12
+	shl		v6.4s, v18.4s, #12
+	shl		v7.4s, v19.4s, #12
+
+	sri		v4.4s, v16.4s, #20
+	sri		v5.4s, v17.4s, #20
+	sri		v6.4s, v18.4s, #20
+	sri		v7.4s, v19.4s, #20
+
+	// x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+	// x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+	// x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+	// x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+	add		v0.4s, v0.4s, v4.4s
+	add		v1.4s, v1.4s, v5.4s
+	add		v2.4s, v2.4s, v6.4s
+	add		v3.4s, v3.4s, v7.4s
+
+	eor		v12.16b, v12.16b, v0.16b
+	eor		v13.16b, v13.16b, v1.16b
+	eor		v14.16b, v14.16b, v2.16b
+	eor		v15.16b, v15.16b, v3.16b
+
+	tbl		v12.16b, {v12.16b}, v31.16b
+	tbl		v13.16b, {v13.16b}, v31.16b
+	tbl		v14.16b, {v14.16b}, v31.16b
+	tbl		v15.16b, {v15.16b}, v31.16b
+
+	// x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+	// x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+	// x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+	// x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+	add		v8.4s, v8.4s, v12.4s
+	add		v9.4s, v9.4s, v13.4s
+	add		v10.4s, v10.4s, v14.4s
+	add		v11.4s, v11.4s, v15.4s
+
+	eor		v16.16b, v4.16b, v8.16b
+	eor		v17.16b, v5.16b, v9.16b
+	eor		v18.16b, v6.16b, v10.16b
+	eor		v19.16b, v7.16b, v11.16b
+
+	shl		v4.4s, v16.4s, #7
+	shl		v5.4s, v17.4s, #7
+	shl		v6.4s, v18.4s, #7
+	shl		v7.4s, v19.4s, #7
+
+	sri		v4.4s, v16.4s, #25
+	sri		v5.4s, v17.4s, #25
+	sri		v6.4s, v18.4s, #25
+	sri		v7.4s, v19.4s, #25
+
+	// x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+	// x1 += x6, x12 = rotl32(x12 ^ x1, 16)
+	// x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+	// x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+	add		v0.4s, v0.4s, v5.4s
+	add		v1.4s, v1.4s, v6.4s
+	add		v2.4s, v2.4s, v7.4s
+	add		v3.4s, v3.4s, v4.4s
+
+	eor		v15.16b, v15.16b, v0.16b
+	eor		v12.16b, v12.16b, v1.16b
+	eor		v13.16b, v13.16b, v2.16b
+	eor		v14.16b, v14.16b, v3.16b
+
+	rev32		v15.8h, v15.8h
+	rev32		v12.8h, v12.8h
+	rev32		v13.8h, v13.8h
+	rev32		v14.8h, v14.8h
+
+	// x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+	// x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+	// x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+	// x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+	add		v10.4s, v10.4s, v15.4s
+	add		v11.4s, v11.4s, v12.4s
+	add		v8.4s, v8.4s, v13.4s
+	add		v9.4s, v9.4s, v14.4s
+
+	eor		v16.16b, v5.16b, v10.16b
+	eor		v17.16b, v6.16b, v11.16b
+	eor		v18.16b, v7.16b, v8.16b
+	eor		v19.16b, v4.16b, v9.16b
+
+	shl		v5.4s, v16.4s, #12
+	shl		v6.4s, v17.4s, #12
+	shl		v7.4s, v18.4s, #12
+	shl		v4.4s, v19.4s, #12
+
+	sri		v5.4s, v16.4s, #20
+	sri		v6.4s, v17.4s, #20
+	sri		v7.4s, v18.4s, #20
+	sri		v4.4s, v19.4s, #20
+
+	// x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+	// x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+	// x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+	// x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+	add		v0.4s, v0.4s, v5.4s
+	add		v1.4s, v1.4s, v6.4s
+	add		v2.4s, v2.4s, v7.4s
+	add		v3.4s, v3.4s, v4.4s
+
+	eor		v15.16b, v15.16b, v0.16b
+	eor		v12.16b, v12.16b, v1.16b
+	eor		v13.16b, v13.16b, v2.16b
+	eor		v14.16b, v14.16b, v3.16b
+
+	tbl		v15.16b, {v15.16b}, v31.16b
+	tbl		v12.16b, {v12.16b}, v31.16b
+	tbl		v13.16b, {v13.16b}, v31.16b
+	tbl		v14.16b, {v14.16b}, v31.16b
+
+	// x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+	// x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+	// x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+	// x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+	add		v10.4s, v10.4s, v15.4s
+	add		v11.4s, v11.4s, v12.4s
+	add		v8.4s, v8.4s, v13.4s
+	add		v9.4s, v9.4s, v14.4s
+
+	eor		v16.16b, v5.16b, v10.16b
+	eor		v17.16b, v6.16b, v11.16b
+	eor		v18.16b, v7.16b, v8.16b
+	eor		v19.16b, v4.16b, v9.16b
+
+	shl		v5.4s, v16.4s, #7
+	shl		v6.4s, v17.4s, #7
+	shl		v7.4s, v18.4s, #7
+	shl		v4.4s, v19.4s, #7
+
+	sri		v5.4s, v16.4s, #25
+	sri		v6.4s, v17.4s, #25
+	sri		v7.4s, v18.4s, #25
+	sri		v4.4s, v19.4s, #25
+
+	subs		x3, x3, #1
+	b.ne		.Ldoubleround4
+
+	ld4r		{v16.4s-v19.4s}, [x0], #16
+	ld4r		{v20.4s-v23.4s}, [x0], #16
+
+	// x12 += counter values 0-3
+	add		v12.4s, v12.4s, v30.4s
+
+	// x0[0-3] += s0[0]
+	// x1[0-3] += s0[1]
+	// x2[0-3] += s0[2]
+	// x3[0-3] += s0[3]
+	add		v0.4s, v0.4s, v16.4s
+	add		v1.4s, v1.4s, v17.4s
+	add		v2.4s, v2.4s, v18.4s
+	add		v3.4s, v3.4s, v19.4s
+
+	ld4r		{v24.4s-v27.4s}, [x0], #16
+	ld4r		{v28.4s-v31.4s}, [x0]
+
+	// x4[0-3] += s1[0]
+	// x5[0-3] += s1[1]
+	// x6[0-3] += s1[2]
+	// x7[0-3] += s1[3]
+	add		v4.4s, v4.4s, v20.4s
+	add		v5.4s, v5.4s, v21.4s
+	add		v6.4s, v6.4s, v22.4s
+	add		v7.4s, v7.4s, v23.4s
+
+	// x8[0-3] += s2[0]
+	// x9[0-3] += s2[1]
+	// x10[0-3] += s2[2]
+	// x11[0-3] += s2[3]
+	add		v8.4s, v8.4s, v24.4s
+	add		v9.4s, v9.4s, v25.4s
+	add		v10.4s, v10.4s, v26.4s
+	add		v11.4s, v11.4s, v27.4s
+
+	// x12[0-3] += s3[0]
+	// x13[0-3] += s3[1]
+	// x14[0-3] += s3[2]
+	// x15[0-3] += s3[3]
+	add		v12.4s, v12.4s, v28.4s
+	add		v13.4s, v13.4s, v29.4s
+	add		v14.4s, v14.4s, v30.4s
+	add		v15.4s, v15.4s, v31.4s
+
+	// interleave 32-bit words in state n, n+1
+	zip1		v16.4s, v0.4s, v1.4s
+	zip2		v17.4s, v0.4s, v1.4s
+	zip1		v18.4s, v2.4s, v3.4s
+	zip2		v19.4s, v2.4s, v3.4s
+	zip1		v20.4s, v4.4s, v5.4s
+	zip2		v21.4s, v4.4s, v5.4s
+	zip1		v22.4s, v6.4s, v7.4s
+	zip2		v23.4s, v6.4s, v7.4s
+	zip1		v24.4s, v8.4s, v9.4s
+	zip2		v25.4s, v8.4s, v9.4s
+	zip1		v26.4s, v10.4s, v11.4s
+	zip2		v27.4s, v10.4s, v11.4s
+	zip1		v28.4s, v12.4s, v13.4s
+	zip2		v29.4s, v12.4s, v13.4s
+	zip1		v30.4s, v14.4s, v15.4s
+	zip2		v31.4s, v14.4s, v15.4s
+
+	// interleave 64-bit words in state n, n+2
+	zip1		v0.2d, v16.2d, v18.2d
+	zip2		v4.2d, v16.2d, v18.2d
+	zip1		v8.2d, v17.2d, v19.2d
+	zip2		v12.2d, v17.2d, v19.2d
+	ld1		{v16.16b-v19.16b}, [x2], #64
+
+	zip1		v1.2d, v20.2d, v22.2d
+	zip2		v5.2d, v20.2d, v22.2d
+	zip1		v9.2d, v21.2d, v23.2d
+	zip2		v13.2d, v21.2d, v23.2d
+	ld1		{v20.16b-v23.16b}, [x2], #64
+
+	zip1		v2.2d, v24.2d, v26.2d
+	zip2		v6.2d, v24.2d, v26.2d
+	zip1		v10.2d, v25.2d, v27.2d
+	zip2		v14.2d, v25.2d, v27.2d
+	ld1		{v24.16b-v27.16b}, [x2], #64
+
+	zip1		v3.2d, v28.2d, v30.2d
+	zip2		v7.2d, v28.2d, v30.2d
+	zip1		v11.2d, v29.2d, v31.2d
+	zip2		v15.2d, v29.2d, v31.2d
+	ld1		{v28.16b-v31.16b}, [x2]
+
+	// xor with corresponding input, write to output
+	eor		v16.16b, v16.16b, v0.16b
+	eor		v17.16b, v17.16b, v1.16b
+	eor		v18.16b, v18.16b, v2.16b
+	eor		v19.16b, v19.16b, v3.16b
+	eor		v20.16b, v20.16b, v4.16b
+	eor		v21.16b, v21.16b, v5.16b
+	st1		{v16.16b-v19.16b}, [x1], #64
+	eor		v22.16b, v22.16b, v6.16b
+	eor		v23.16b, v23.16b, v7.16b
+	eor		v24.16b, v24.16b, v8.16b
+	eor		v25.16b, v25.16b, v9.16b
+	st1		{v20.16b-v23.16b}, [x1], #64
+	eor		v26.16b, v26.16b, v10.16b
+	eor		v27.16b, v27.16b, v11.16b
+	eor		v28.16b, v28.16b, v12.16b
+	st1		{v24.16b-v27.16b}, [x1], #64
+	eor		v29.16b, v29.16b, v13.16b
+	eor		v30.16b, v30.16b, v14.16b
+	eor		v31.16b, v31.16b, v15.16b
+	st1		{v28.16b-v31.16b}, [x1]
+
+	ret
+ENDPROC(chacha20_4block_xor_neon)
+
+CTRINC:	.word		0, 1, 2, 3
+ROT8:	.word		0x02010003, 0x06050407, 0x0a09080b, 0x0e0d0c0f
diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c
new file mode 100644
index 000000000000..a7f2337d46cf
--- /dev/null
+++ b/arch/arm64/crypto/chacha20-neon-glue.c
@@ -0,0 +1,127 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539, arm64 NEON functions
+ *
+ * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/chacha20.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+
+asmlinkage void chacha20_block_xor_neon(u32 *state, u8 *dst, const u8 *src);
+asmlinkage void chacha20_4block_xor_neon(u32 *state, u8 *dst, const u8 *src);
+
+static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src,
+			    unsigned int bytes)
+{
+	u8 buf[CHACHA20_BLOCK_SIZE];
+
+	while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
+		chacha20_4block_xor_neon(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE * 4;
+		src += CHACHA20_BLOCK_SIZE * 4;
+		dst += CHACHA20_BLOCK_SIZE * 4;
+		state[12] += 4;
+	}
+	while (bytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_block_xor_neon(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE;
+		src += CHACHA20_BLOCK_SIZE;
+		dst += CHACHA20_BLOCK_SIZE;
+		state[12]++;
+	}
+	if (bytes) {
+		memcpy(buf, src, bytes);
+		chacha20_block_xor_neon(state, buf, buf);
+		memcpy(dst, buf, bytes);
+	}
+}
+
+static int chacha20_neon(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	u32 state[16];
+	int err;
+
+	if (req->cryptlen <= CHACHA20_BLOCK_SIZE)
+		return crypto_chacha20_crypt(req);
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	crypto_chacha20_init(state, ctx, walk.iv);
+
+	kernel_neon_begin();
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
+
+		chacha20_doneon(state, walk.dst.virt.addr, walk.src.virt.addr,
+				nbytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static struct skcipher_alg alg = {
+	.base.cra_name		= "chacha20",
+	.base.cra_driver_name	= "chacha20-neon",
+	.base.cra_priority	= 300,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct chacha20_ctx),
+	.base.cra_alignmask	= 1,
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= CHACHA20_KEY_SIZE,
+	.max_keysize		= CHACHA20_KEY_SIZE,
+	.ivsize			= CHACHA20_IV_SIZE,
+	.chunksize		= CHACHA20_BLOCK_SIZE,
+	.walksize		= 4 * CHACHA20_BLOCK_SIZE,
+	.setkey			= crypto_chacha20_setkey,
+	.encrypt		= chacha20_neon,
+	.decrypt		= chacha20_neon,
+};
+
+static int __init chacha20_simd_mod_init(void)
+{
+	if (!(elf_hwcap & HWCAP_ASIMD))
+		return -ENODEV;
+
+	return crypto_register_skcipher(&alg);
+}
+
+static void __exit chacha20_simd_mod_fini(void)
+{
+	crypto_unregister_skcipher(&alg);
+}
+
+module_init(chacha20_simd_mod_init);
+module_exit(chacha20_simd_mod_fini);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("chacha20");
-- 
2.7.4

^ permalink raw reply related

* [PATCH v2 0/7] crypto: ARM/arm64 - AES and ChaCha20 updates for v4.11
From: Ard Biesheuvel @ 2017-01-11 16:41 UTC (permalink / raw)
  To: linux-arm-kernel

This adds ARM and arm64 implementations of ChaCha20, scalar AES and SIMD
AES (using bit slicing). The SIMD algorithms in this series take advantage
of the new skcipher walksize attribute to iterate over the input in the most
efficient manner possible.

Patch #1 adds a NEON implementation of ChaCha20 for ARM.

Patch #2 adds a NEON implementation of ChaCha20 for arm64.

Patch #3 modifies the existing NEON and ARMv8 Crypto Extensions implementations
of AES-CTR to be available as a synchronous skcipher as well. This is intended
for the mac80211 code, which uses synchronous encapsulations of ctr(aes)
[ccm, gcm] in softirq context, during which arm64 supports use of SIMD code.

Patch #4 adds a scalar implementation of AES for arm64, using the key schedule
generation routines and lookup tables of the generic code in crypto/aes_generic.

Patch #5 does the same for ARM, replacing existing scalar code that originated
in the OpenSSL project, and contains redundant key schedule generation routines
and lookup tables (and is slightly slower on modern cores)

Patch #6 replaces the ARM bit sliced NEON code with a new implementation that
has a number of advantages over the original code (which also originated in the
OpenSSL project.) The performance should be identical.

Patch #7 adds a port of the ARM bit-sliced AES code to arm64, in ECB, CBC, CTR
and XTS modes.

Due to the size of patch #7, it may be difficult to apply these patches from
patchwork, so I pushed them here as well:

  git://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git crypto-arm-v4.11
  https://git.kernel.org/cgit/linux/kernel/git/ardb/linux.git/log/?h=crypto-arm-v4.11

Ard Biesheuvel (7):
  crypto: arm64/chacha20 - implement NEON version based on SSE3 code
  crypto: arm/chacha20 - implement NEON version based on SSE3 code
  crypto: arm64/aes-blk - expose AES-CTR as synchronous cipher as well
  crypto: arm64/aes - add scalar implementation
  crypto: arm/aes - replace scalar AES cipher
  crypto: arm/aes - replace bit-sliced OpenSSL NEON code
  crypto: arm64/aes - reimplement bit-sliced ARM/NEON implementation for
    arm64

 arch/arm/crypto/Kconfig                |   27 +-
 arch/arm/crypto/Makefile               |   11 +-
 arch/arm/crypto/aes-armv4.S            | 1089 ---------
 arch/arm/crypto/aes-cipher-core.S      |  179 ++
 arch/arm/crypto/aes-cipher-glue.c      |   74 +
 arch/arm/crypto/aes-neonbs-core.S      | 1021 ++++++++
 arch/arm/crypto/aes-neonbs-glue.c      |  405 ++++
 arch/arm/crypto/aes_glue.c             |   98 -
 arch/arm/crypto/aes_glue.h             |   19 -
 arch/arm/crypto/aesbs-core.S_shipped   | 2548 --------------------
 arch/arm/crypto/aesbs-glue.c           |  367 ---
 arch/arm/crypto/bsaes-armv7.pl         | 2471 -------------------
 arch/arm/crypto/chacha20-neon-core.S   |  524 ++++
 arch/arm/crypto/chacha20-neon-glue.c   |  128 +
 arch/arm64/crypto/Kconfig              |   17 +
 arch/arm64/crypto/Makefile             |    9 +
 arch/arm64/crypto/aes-cipher-core.S    |  127 +
 arch/arm64/crypto/aes-cipher-glue.c    |   69 +
 arch/arm64/crypto/aes-glue.c           |   25 +-
 arch/arm64/crypto/aes-neonbs-core.S    |  963 ++++++++
 arch/arm64/crypto/aes-neonbs-glue.c    |  420 ++++
 arch/arm64/crypto/chacha20-neon-core.S |  450 ++++
 arch/arm64/crypto/chacha20-neon-glue.c |  127 +
 23 files changed, 4549 insertions(+), 6619 deletions(-)
 delete mode 100644 arch/arm/crypto/aes-armv4.S
 create mode 100644 arch/arm/crypto/aes-cipher-core.S
 create mode 100644 arch/arm/crypto/aes-cipher-glue.c
 create mode 100644 arch/arm/crypto/aes-neonbs-core.S
 create mode 100644 arch/arm/crypto/aes-neonbs-glue.c
 delete mode 100644 arch/arm/crypto/aes_glue.c
 delete mode 100644 arch/arm/crypto/aes_glue.h
 delete mode 100644 arch/arm/crypto/aesbs-core.S_shipped
 delete mode 100644 arch/arm/crypto/aesbs-glue.c
 delete mode 100644 arch/arm/crypto/bsaes-armv7.pl
 create mode 100644 arch/arm/crypto/chacha20-neon-core.S
 create mode 100644 arch/arm/crypto/chacha20-neon-glue.c
 create mode 100644 arch/arm64/crypto/aes-cipher-core.S
 create mode 100644 arch/arm64/crypto/aes-cipher-glue.c
 create mode 100644 arch/arm64/crypto/aes-neonbs-core.S
 create mode 100644 arch/arm64/crypto/aes-neonbs-glue.c
 create mode 100644 arch/arm64/crypto/chacha20-neon-core.S
 create mode 100644 arch/arm64/crypto/chacha20-neon-glue.c

-- 
2.7.4

^ permalink raw reply

* [PATCH net-next] net: thunderx: Fix error return code in nicvf_open()
From: Wei Yongjun @ 2017-01-11 16:32 UTC (permalink / raw)
  To: linux-arm-kernel

From: Wei Yongjun <weiyongjun1@huawei.com>

Fix to return a negative error code from the error handling
case instead of 0, as done elsewhere in this function.

Fixes: 712c31853440 ("net: thunderx: Program LMAC credits based on MTU")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 273eafd..a25bb6e 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1274,7 +1274,8 @@ int nicvf_open(struct net_device *netdev)
 	/* Configure receive side scaling and MTU */
 	if (!nic->sqs_mode) {
 		nicvf_rss_init(nic);
-		if (nicvf_update_hw_max_frs(nic, netdev->mtu))
+		err = nicvf_update_hw_max_frs(nic, netdev->mtu);
+		if (err)
 			goto cleanup;
 
 		/* Clear percpu stats */

^ permalink raw reply related

* [kvm-unit-tests PATCH 6/6] run_tests: allow passing of options to QEMU
From: Alex Bennée @ 2017-01-11 16:28 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20170111162841.15569-1-alex.bennee@linaro.org>

This allows additional options to be passed to QEMU. It follows the
convention of passing parameters after a -- to the child process. In
my case I'm using it to toggle MTTCG on an off:

  ./run_tests.sh -- --accel tcg,thread=multi

Signed-off-by: Alex Benn?e <alex.bennee@linaro.org>

---
v1
  - changes from -o to --
  - fixed whitespace damage
---
 README.md              |  6 ++++++
 run_tests.sh           | 13 +++++++++++--
 scripts/functions.bash |  7 ++++---
 3 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index fa3a445..1bd6dcb 100644
--- a/README.md
+++ b/README.md
@@ -55,6 +55,12 @@ To extend or disable the timeouts:
 
     TIMEOUT=0 ./run_tests.sh
 
+Any arguments past the end-of-arguments marker (--) is passed on down
+to the QEMU invocation. This can of course be combined with the other
+modifiers:
+
+    ACCEL=tcg ./run_tests.sh -v -- --accel tcg,thread=multi
+
 # Contributing
 
 ## Directory structure
diff --git a/run_tests.sh b/run_tests.sh
index 254129d..3270fba 100755
--- a/run_tests.sh
+++ b/run_tests.sh
@@ -13,7 +13,7 @@ function usage()
 {
 cat <<EOF
 
-Usage: $0 [-g group] [-h] [-v]
+Usage: $0 [-g group] [-h] [-v] [-- QEMU options]
 
     -g: Only execute tests in the given group
     -h: Output this help text
@@ -22,6 +22,8 @@ Usage: $0 [-g group] [-h] [-v]
 Set the environment variable QEMU=/path/to/qemu-system-ARCH to
 specify the appropriate qemu binary for ARCH-run.
 
+All options specified after -- are passed on to QEMU.
+
 EOF
 }
 
@@ -29,6 +31,7 @@ RUNTIME_arch_run="./$TEST_DIR/run"
 source scripts/runtime.bash
 
 while getopts "g:hv" opt; do
+
     case $opt in
         g)
             only_group=$OPTARG
@@ -46,6 +49,12 @@ while getopts "g:hv" opt; do
     esac
 done
 
+# Any options left for QEMU?
+shift $((OPTIND-1))
+if [ "$#" -gt  0 ]; then
+    extra_opts="$@"
+fi
+
 RUNTIME_log_stderr () { cat >> test.log; }
 RUNTIME_log_stdout () {
     if [ "$PRETTY_PRINT_STACKS" = "yes" ]; then
@@ -59,4 +68,4 @@ RUNTIME_log_stdout () {
 config=$TEST_DIR/unittests.cfg
 rm -f test.log
 printf "BUILD_HEAD=$(cat build-head)\n\n" > test.log
-for_each_unittest $config run
+for_each_unittest $config run "$extra_opts"
diff --git a/scripts/functions.bash b/scripts/functions.bash
index ee9143c..60fbc6a 100644
--- a/scripts/functions.bash
+++ b/scripts/functions.bash
@@ -3,10 +3,11 @@ function for_each_unittest()
 {
 	local unittests="$1"
 	local cmd="$2"
+	local extra_opts=$3
 	local testname
 	local smp
 	local kernel
-	local opts
+	local opts=$extra_opts
 	local groups
 	local arch
 	local check
@@ -21,7 +22,7 @@ function for_each_unittest()
 			testname=${BASH_REMATCH[1]}
 			smp=1
 			kernel=""
-			opts=""
+			opts=$extra_opts
 			groups=""
 			arch=""
 			check=""
@@ -32,7 +33,7 @@ function for_each_unittest()
 		elif [[ $line =~ ^smp\ *=\ *(.*)$ ]]; then
 			smp=${BASH_REMATCH[1]}
 		elif [[ $line =~ ^extra_params\ *=\ *(.*)$ ]]; then
-			opts=${BASH_REMATCH[1]}
+			opts="$opts ${BASH_REMATCH[1]}"
 		elif [[ $line =~ ^groups\ *=\ *(.*)$ ]]; then
 			groups=${BASH_REMATCH[1]}
 		elif [[ $line =~ ^arch\ *=\ *(.*)$ ]]; then
-- 
2.11.0

^ permalink raw reply related

* [kvm-unit-tests PATCH 5/6] docs: mention modifying env vars in README
From: Alex Bennée @ 2017-01-11 16:28 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20170111162841.15569-1-alex.bennee@linaro.org>

I had started adding a series of flags to control the run-time
behaviour of the tests but it was pointed out env vars can already do
that. Mention them in the README so others can find out to.

Signed-off-by: Alex Benn?e <alex.bennee@linaro.org>
---
 README.md | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/README.md b/README.md
index 9462824..fa3a445 100644
--- a/README.md
+++ b/README.md
@@ -47,6 +47,14 @@ environment variable:
 
     QEMU=/tmp/qemu/x86_64-softmmu/qemu-system-x86_64 ./x86-run ./x86/msr.flat
 
+To force the acceleration mode:
+
+    ACCEL=tcg ./run_tests.sh
+
+To extend or disable the timeouts:
+
+    TIMEOUT=0 ./run_tests.sh
+
 # Contributing
 
 ## Directory structure
-- 
2.11.0

^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox