Merge android-4.9.90 (dd1e37e) into msm-4.9
* refs/heads/tmp-dd1e37e: Linux 4.9.90 usb: gadget: f_hid: fix: Move IN request allocation to set_alt() RDMA/ucma: Don't allow join attempts for unsupported AF family RDMA/ucma: Fix access to non-initialized CM_ID object clk: migrate the count of orphaned clocks at init IB/mlx5: Fix out-of-bounds read in create_raw_packet_qp_rq IB/mlx5: Fix integer overflows in mlx5_ib_create_srq dmaengine: ti-dma-crossbar: Fix event mapping for TPCC_EVT_MUX_60_63 clk: si5351: Rename internal plls to avoid name collisions clk: axi-clkgen: Correctly handle nocount bit in recalc_rate() clk: Don't touch hardware when reparenting during registration nfsd4: permit layoutget of executable-only files ARM: dts: aspeed-evb: Add unit name to memory node RDMA/ocrdma: Fix permissions for OCRDMA_RESET_STATS ip6_vti: adjust vti mtu according to mtu of lower device iommu/vt-d: clean up pr_irq if request_threaded_irq fails pinctrl: rockchip: enable clock when reading pin direction register pinctrl: Really force states during suspend/resume coresight: Fix disabling of CoreSight TPIU pty: cancel pty slave port buf's work in tty_release drm/omap: DMM: Check for DMM readiness after successful transaction commit omapdrm: panel: fix compatible vendor string for td028ttec1 vgacon: Set VGA struct resource types iser-target: avoid reinitializing rdma contexts for isert commands IB/umem: Fix use of npages/nmap fields RDMA/cma: Use correct size when writing netlink stats IB/ipoib: Avoid memory leak if the SA returns a different DGID mmc: avoid removing non-removable hosts during suspend drm/tilcdc: ensure nonatomic iowrite64 is not used dmaengine: zynqmp_dma: Fix race condition in the probe platform/chrome: Use proper protocol transfer function watchdog: Fix potential kref imbalance when opening watchdog cros_ec: fix nul-termination for firmware build info serial: 8250_dw: Disable clock on error qmi_wwan: set FLAG_SEND_ZLP to avoid network initiated disconnect media: [RESEND] media: dvb-frontends: Add delay to Si2168 restart ath10k: handling qos at STA side based on AP WMM enable/disable media: bt8xx: Fix err 'bt878_probe()' rtlwifi: rtl_pci: Fix the bug when inactiveps is enabled. RDMA/iwpm: Fix uninitialized error code in iwpm_send_mapinfo() drm/msm: fix leak in failed get_pages media: c8sectpfe: fix potential NULL pointer dereference in c8sectpfe_timer_interrupt Bluetooth: btqcomsmd: Fix skb double free corruption Bluetooth: hci_qca: Avoid setup failure on missing rampatch block/mq: Cure cpu hotplug lock inversion perf tests kmod-path: Don't fail if compressed modules aren't supported ath10k: fix out of bounds access to local buffer rtc: ds1374: wdt: Fix stop/start ioctl always returning -EINVAL rtc: ds1374: wdt: Fix issue with timeout scaling from secs to wdt ticks mm: hwpoison: call shake_page() after try_to_unmap() for mlocked page mm, vmstat: suppress pcp stats for unpopulated zones in zoneinfo mm: fix check for reclaimable pages in PF_MEMALLOC reclaim throttling cifs: small underflow in cnvrtDosUnixTm() net: hns: fix ethtool_get_strings overflow in hns driver pNFS: Fix a deadlock when coalescing writes and returning the layout sm501fb: don't return zero on failure path in sm501fb_start() video: fbdev: udlfb: Fix buffer on stack x86/xen: split xen_smp_prepare_boot_cpu() tcm_fileio: Prevent information leak for short reads ia64: fix module loading for gcc-5.4 ACPI / power: Delay turning off unused power resources after suspend md/raid10: skip spare disk as 'first' disk IB/rxe: Don't clamp residual length to mtu Input: twl4030-pwrbutton - use correct device for irq request power: supply: pda_power: move from timer to delayed_work power: supply: isp1704: Fix unchecked return value of devm_kzalloc power: supply: bq24190_charger: Add disable-reset device-property bnx2x: Align RX buffers qed: Unlock on error in qed_vf_pf_acquire() vxlan: correctly handle ipv6.disable module parameter Bluetooth: hci_ldisc: Add protocol check to hci_uart_tx_wakeup() Bluetooth: hci_ldisc: Add protocol check to hci_uart_dequeue() soc/fsl/qe: round brg_freq to 1kHz granularity net: ethernet: ucc_geth: fix MEM_PART_MURAM mode ixgbevf: fix size of queue stats length jbd2: Fix lockdep splat with generic/270 test drm/nouveau/kms: Increase max retries in scanout position queries. drm/amdgpu: fix gpu reset crash ACPI / PMIC: xpower: Fix power_table addresses ipmi/watchdog: fix wdog hang on panic waiting for ipmi response platform/x86: asus-wmi: try to set als by default IB/hfi1: Fix softlockup issue IB/rdmavt: restore IRQs on error path in rvt_create_ah() ARM: DRA7: clockdomain: Change the CLKTRCTRL of CM_PCIE_CLKSTCTRL to SW_WKUP netfilter: x_tables: unlock on error in xt_find_table_lock() mmc: sdhci-of-esdhc: limit SD clock for ls1012a/ls1046a mac80211: Fix possible sband related NULL pointer de-reference ipvs: explicitly forbid ipv6 service/dest creation if ipv6 mod is disabled staging: wilc1000: fix unchecked return value staging: unisys: visorhba: fix s-Par to boot with option CONFIG_VMAP_STACK set to y gpio: gpio-wcove: fix GPIO IRQ status mask x86/KASLR: Fix kexec kernel boot crash when KASLR randomization fails mtip32xx: use runtime tag to initialize command header mfd: palmas: Reset the POWERHOLD mux during power off dt-bindings: mfd: axp20x: Add "xpowers,master-mode" property for AXP806 PMICs iio: hid-sensor: fix return of -EINVAL on invalid values in ret or value ACPICA: iasl: Fix IORT SMMU GSI disassembling mac80211: don't parse encrypted management frames in ieee80211_frame_acked orangefs: do not wait for timeout if umounting Btrfs: fix extent map leak during fallocate error path Btrfs: send, fix file hole not being preserved due to inline extent Btrfs: fix incorrect space accounting after failure to insert inline extent rndis_wlan: add return value validation libertas: check return value of alloc_workqueue mt7601u: check return value of alloc_skb iio: st_pressure: st_accel: Initialise sensor platform data properly NFS: don't try to cross a mountpount when there isn't one there. xprtrdma: Cancel refresh worker during buffer shutdown pNFS: Fix use after free issues in pnfs_do_read() infiniband/uverbs: Fix integer overflows scsi: mac_esp: Replace bogus memory barrier with spinlock platform/x86: intel-vbtn: add volume up and down netfilter: nft_dynset: continue to next expr if _OP_ADD succeeded qlcnic: fix unchecked return value wan: pc300too: abort path on failure tipc: check return value of nlmsg_new mmc: host: omap_hsmmc: checking for NULL instead of IS_ERR() netfilter: nf_ct_helper: permit cthelpers with different names via nfnetlink openvswitch: Delete conntrack entry clashing with an expectation. netfilter: xt_CT: fix refcnt leak on error path gpio: gpio-wcove: fix irq pending status bit width Fix Express lane queue creation. Fix driver usage of 128B WQEs when WQ_CREATE is V1. netvsc: Deal with rescinded channels correctly ibmvnic: Disable irq prior to close ASoC: Intel: Skylake: Uninitialized variable in probe_codec() IB/mlx5: Set correct SL in completion for RoCE IB/mlx5: Change vma from shared to private IB/mlx5: Take write semaphore when changing the vma struct IB/mlx4: Change vma from shared to private IB/mlx4: Take write semaphore when changing the vma struct HSI: ssi_protocol: double free in ssip_pn_xmit() IB/ipoib: Update broadcast object if PKey value was changed in index 0 IB/ipoib: Fix deadlock between ipoib_stop and mcast join flow ALSA: hda - Fix headset microphone detection for ASUS N551 and N751 e1000e: fix timing for 82579 Gigabit Ethernet controller tcp: remove poll() flakes with FastOpen NFS: Fix missing pg_cleanup after nfs_pageio_cond_complete() md/raid10: wait up frozen array in handle_write_completed iommu/omap: Register driver before setting IOMMU ops irqchip/mips-gic: Separate IPI reservation & usage tracking ARM: 8668/1: ftrace: Fix dynamic ftrace with DEBUG_RODATA and !FRAME_POINTER x86/reboot: Turn off KVM when halting a CPU mwifiex: don't leak 'chan_stats' on reset KVM: PPC: Book3S PR: Exit KVM on failed mapping scsi: virtio_scsi: Always try to read VPD pages iwlwifi: a000: fix memory offsets and lengths iwlwifi: split the handler and the wake parts of the notification infra clk: ns2: Correct SDIO bits ath: Fix updating radar flags for coutry code India powerpc/64s: Remove SAO feature from Power9 DD1 spi: dw: Disable clock after unregistering the host tools/testing/nvdimm: fix nfit_test shutdown crash ASoC: Intel: Atom: update Thinkpad 10 quirk btrfs: fix a bogus warning when converting only data or metadata media/dvb-core: Race condition when writing to CAM net: ipv6: send unsolicited NA on admin up i2c: i2c-scmi: add a MS HID genirq: Use irqd_get_trigger_type to compare the trigger type for shared IRQs cpufreq/sh: Replace racy task affinity logic ACPI/processor: Replace racy task affinity logic ACPI/processor: Fix error handling in __acpi_processor_start() time: Change posix clocks ops interfaces to use timespec64 Input: ar1021_i2c - fix too long name in driver's device table rtc: cmos: Do not assume irq 8 for rtc when there are no legacy irqs x86: i8259: export legacy_pic symbol power: supply: bq24190_charger: Limit over/under voltage fault logging regulator: anatop: set default voltage selector for pcie bonding: handle link transition from FAIL to UP correctly platform/x86: asus-nb-wmi: Add wapf4 quirk for the X302UA led: core: Clear LED_BLINK_SW flag in led_blink_set() Revert "led: core: Fix brightness setting when setting delay_off=0" staging: android: ashmem: Fix possible deadlock in ashmem_ioctl CIFS: Enable encryption during session setup phase SMB3: Validate negotiate request must always be signed ASoC: rsnd: check src mod pointer for rsnd_mod_id() tpm: fix potential buffer overruns caused by bit glitches on the bus BACKPORT, FROMLIST: crypto: arm64/speck - add NEON-accelerated implementation of Speck-XTS ANDROID: debugobjects: Make stack check warning more informative PM / OPP: list_del_rcu should be used in function _remove_opp_dev trace/sched: Fix compilation for 32 bit systems sched/fair: select the most energy-efficient CPU candidate on wake-up sched/fair: fix array out of bounds access in select_energy_cpu_idx() sched/fair: use min capacity when evaluating active cpus sched/fair: use min capacity when evaluating idle backup cpus sched/fair: use min capacity when evaluating placement energy costs sched/fair: introduce minimum capacity capping sched feature arm/topology: link arch_scale_min_freq_capacity to cpufreq arm64/topology: link arch_scale_min_freq_capacity to cpufreq sched: add arch_scale_min_freq_capacity to track minimum capacity caps cpufreq: add scaled minimum capacity tracking for policy changes arm64: enable max frequency capping arm: enable max frequency capping cpufreq: implement max frequency capping sched/fair: introduce an arch scaling function for max frequency capping cpufreq: remove max frequency capping from scale_freq_capacity() Revert "ANDROID: cpufreq: Max freq invariant scheduler load-tracking and cpu capacity support" Revert "ANDROID: arm: Enable max freq invariant scheduler load-tracking and capacity support" Revert "ANDROID: arm64: Enable max freq invariant scheduler load-tracking and capacity support" sched/fair: reduce rounding errors in energy computations sched/fair: re-factor energy_diff to use a single (extensible) energy_env sched/fair: cleanup select_energy_cpu_brute to be more consistent sched/fair: remove capacity tracking from energy_diff sched/fair: remove energy_diff tracepoint in preparation to re-factoring sched/fair: use *p to reference task_structs sched: EAS: Fix the calculation of group util in group_idle_state() Conflicts: drivers/clk/clk.c drivers/gpu/drm/msm/msm_gem.c include/trace/events/sched.h kernel/sched/fair.c kernel/sched/features.h Change-Id: I875b8c298dc6a8151abf740126a2d1881d498203 Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>
This commit is contained in:
Blagovest Kolenichev
commit
dc9767ff92
199 changed files with 2271 additions and 594 deletions
|
|
@ -0,0 +1,30 @@
|
|||
Toppoly TD028TTEC1 Panel
|
||||
========================
|
||||
|
||||
Required properties:
|
||||
- compatible: "tpo,td028ttec1"
|
||||
|
||||
Optional properties:
|
||||
- label: a symbolic name for the panel
|
||||
|
||||
Required nodes:
|
||||
- Video port for DPI input
|
||||
|
||||
Example
|
||||
-------
|
||||
|
||||
lcd-panel: td028ttec1@0 {
|
||||
compatible = "tpo,td028ttec1";
|
||||
reg = <0>;
|
||||
spi-max-frequency = <100000>;
|
||||
spi-cpol;
|
||||
spi-cpha;
|
||||
|
||||
label = "lcd";
|
||||
port {
|
||||
lcd_in: endpoint {
|
||||
remote-endpoint = <&dpi_out>;
|
||||
};
|
||||
};
|
||||
};
|
||||
|
||||
|
|
@ -28,6 +28,9 @@ Optional properties:
|
|||
regulator to drive the OTG VBus, rather then as an input pin
|
||||
which signals whether the board is driving OTG VBus or not.
|
||||
|
||||
- x-powers,master-mode: Boolean (axp806 only). Set this when the PMIC is
|
||||
wired for master mode. The default is slave mode.
|
||||
|
||||
- <input>-supply: a phandle to the regulator supply node. May be omitted if
|
||||
inputs are unregulated, such as using the IPSOUT output
|
||||
from the PMIC.
|
||||
|
|
|
|||
2
Makefile
2
Makefile
|
|
@ -1,6 +1,6 @@
|
|||
VERSION = 4
|
||||
PATCHLEVEL = 9
|
||||
SUBLEVEL = 89
|
||||
SUBLEVEL = 90
|
||||
EXTRAVERSION =
|
||||
NAME = Roaring Lionus
|
||||
|
||||
|
|
|
|||
|
|
@ -20,6 +20,7 @@
|
|||
struct pci_controller *pci_vga_hose;
|
||||
static struct resource alpha_vga = {
|
||||
.name = "alpha-vga+",
|
||||
.flags = IORESOURCE_IO,
|
||||
.start = 0x3C0,
|
||||
.end = 0x3DF
|
||||
};
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@
|
|||
bootargs = "console=ttyS4,115200 earlyprintk";
|
||||
};
|
||||
|
||||
memory {
|
||||
memory@80000000 {
|
||||
reg = <0x80000000 0x20000000>;
|
||||
};
|
||||
};
|
||||
|
|
|
|||
|
|
@ -29,11 +29,6 @@
|
|||
#endif
|
||||
|
||||
#ifdef CONFIG_DYNAMIC_FTRACE
|
||||
#ifdef CONFIG_OLD_MCOUNT
|
||||
#define OLD_MCOUNT_ADDR ((unsigned long) mcount)
|
||||
#define OLD_FTRACE_ADDR ((unsigned long) ftrace_caller_old)
|
||||
|
||||
#define OLD_NOP 0xe1a00000 /* mov r0, r0 */
|
||||
|
||||
static int __ftrace_modify_code(void *data)
|
||||
{
|
||||
|
|
@ -51,6 +46,12 @@ void arch_ftrace_update_code(int command)
|
|||
stop_machine(__ftrace_modify_code, &command, NULL);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_OLD_MCOUNT
|
||||
#define OLD_MCOUNT_ADDR ((unsigned long) mcount)
|
||||
#define OLD_FTRACE_ADDR ((unsigned long) ftrace_caller_old)
|
||||
|
||||
#define OLD_NOP 0xe1a00000 /* mov r0, r0 */
|
||||
|
||||
static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec)
|
||||
{
|
||||
return rec->arch.old_mcount ? OLD_NOP : NOP;
|
||||
|
|
|
|||
|
|
@ -524,7 +524,7 @@ static struct clockdomain pcie_7xx_clkdm = {
|
|||
.dep_bit = DRA7XX_PCIE_STATDEP_SHIFT,
|
||||
.wkdep_srcs = pcie_wkup_sleep_deps,
|
||||
.sleepdep_srcs = pcie_wkup_sleep_deps,
|
||||
.flags = CLKDM_CAN_HWSUP_SWSUP,
|
||||
.flags = CLKDM_CAN_SWSUP,
|
||||
};
|
||||
|
||||
static struct clockdomain atl_7xx_clkdm = {
|
||||
|
|
|
|||
|
|
@ -53,4 +53,11 @@ config CRYPTO_CRC32_ARM64
|
|||
tristate "CRC32 and CRC32C using optional ARMv8 instructions"
|
||||
depends on ARM64
|
||||
select CRYPTO_HASH
|
||||
|
||||
config CRYPTO_SPECK_NEON
|
||||
tristate "NEON accelerated Speck cipher algorithms"
|
||||
depends on KERNEL_MODE_NEON
|
||||
select CRYPTO_BLKCIPHER
|
||||
select CRYPTO_GF128MUL
|
||||
select CRYPTO_SPECK
|
||||
endif
|
||||
|
|
|
|||
|
|
@ -30,6 +30,9 @@ aes-ce-blk-y := aes-glue-ce.o aes-ce.o
|
|||
obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
|
||||
aes-neon-blk-y := aes-glue-neon.o aes-neon.o
|
||||
|
||||
obj-$(CONFIG_CRYPTO_SPECK_NEON) += speck-neon.o
|
||||
speck-neon-y := speck-neon-core.o speck-neon-glue.o
|
||||
|
||||
AFLAGS_aes-ce.o := -DINTERLEAVE=4
|
||||
AFLAGS_aes-neon.o := -DINTERLEAVE=4
|
||||
|
||||
|
|
|
|||
352
arch/arm64/crypto/speck-neon-core.S
Normal file
352
arch/arm64/crypto/speck-neon-core.S
Normal file
|
|
@ -0,0 +1,352 @@
|
|||
// SPDX-License-Identifier: GPL-2.0
|
||||
/*
|
||||
* ARM64 NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
|
||||
*
|
||||
* Copyright (c) 2018 Google, Inc
|
||||
*
|
||||
* Author: Eric Biggers <ebiggers@google.com>
|
||||
*/
|
||||
|
||||
#include <linux/linkage.h>
|
||||
|
||||
.text
|
||||
|
||||
// arguments
|
||||
ROUND_KEYS .req x0 // const {u64,u32} *round_keys
|
||||
NROUNDS .req w1 // int nrounds
|
||||
NROUNDS_X .req x1
|
||||
DST .req x2 // void *dst
|
||||
SRC .req x3 // const void *src
|
||||
NBYTES .req w4 // unsigned int nbytes
|
||||
TWEAK .req x5 // void *tweak
|
||||
|
||||
// registers which hold the data being encrypted/decrypted
|
||||
// (underscores avoid a naming collision with ARM64 registers x0-x3)
|
||||
X_0 .req v0
|
||||
Y_0 .req v1
|
||||
X_1 .req v2
|
||||
Y_1 .req v3
|
||||
X_2 .req v4
|
||||
Y_2 .req v5
|
||||
X_3 .req v6
|
||||
Y_3 .req v7
|
||||
|
||||
// the round key, duplicated in all lanes
|
||||
ROUND_KEY .req v8
|
||||
|
||||
// index vector for tbl-based 8-bit rotates
|
||||
ROTATE_TABLE .req v9
|
||||
ROTATE_TABLE_Q .req q9
|
||||
|
||||
// temporary registers
|
||||
TMP0 .req v10
|
||||
TMP1 .req v11
|
||||
TMP2 .req v12
|
||||
TMP3 .req v13
|
||||
|
||||
// multiplication table for updating XTS tweaks
|
||||
GFMUL_TABLE .req v14
|
||||
GFMUL_TABLE_Q .req q14
|
||||
|
||||
// next XTS tweak value(s)
|
||||
TWEAKV_NEXT .req v15
|
||||
|
||||
// XTS tweaks for the blocks currently being encrypted/decrypted
|
||||
TWEAKV0 .req v16
|
||||
TWEAKV1 .req v17
|
||||
TWEAKV2 .req v18
|
||||
TWEAKV3 .req v19
|
||||
TWEAKV4 .req v20
|
||||
TWEAKV5 .req v21
|
||||
TWEAKV6 .req v22
|
||||
TWEAKV7 .req v23
|
||||
|
||||
.align 4
|
||||
.Lror64_8_table:
|
||||
.octa 0x080f0e0d0c0b0a090007060504030201
|
||||
.Lror32_8_table:
|
||||
.octa 0x0c0f0e0d080b0a090407060500030201
|
||||
.Lrol64_8_table:
|
||||
.octa 0x0e0d0c0b0a09080f0605040302010007
|
||||
.Lrol32_8_table:
|
||||
.octa 0x0e0d0c0f0a09080b0605040702010003
|
||||
.Lgf128mul_table:
|
||||
.octa 0x00000000000000870000000000000001
|
||||
.Lgf64mul_table:
|
||||
.octa 0x0000000000000000000000002d361b00
|
||||
|
||||
/*
|
||||
* _speck_round_128bytes() - Speck encryption round on 128 bytes at a time
|
||||
*
|
||||
* Do one Speck encryption round on the 128 bytes (8 blocks for Speck128, 16 for
|
||||
* Speck64) stored in X0-X3 and Y0-Y3, using the round key stored in all lanes
|
||||
* of ROUND_KEY. 'n' is the lane size: 64 for Speck128, or 32 for Speck64.
|
||||
* 'lanes' is the lane specifier: "2d" for Speck128 or "4s" for Speck64.
|
||||
*/
|
||||
.macro _speck_round_128bytes n, lanes
|
||||
|
||||
// x = ror(x, 8)
|
||||
tbl X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
|
||||
tbl X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
|
||||
tbl X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
|
||||
tbl X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
|
||||
|
||||
// x += y
|
||||
add X_0.\lanes, X_0.\lanes, Y_0.\lanes
|
||||
add X_1.\lanes, X_1.\lanes, Y_1.\lanes
|
||||
add X_2.\lanes, X_2.\lanes, Y_2.\lanes
|
||||
add X_3.\lanes, X_3.\lanes, Y_3.\lanes
|
||||
|
||||
// x ^= k
|
||||
eor X_0.16b, X_0.16b, ROUND_KEY.16b
|
||||
eor X_1.16b, X_1.16b, ROUND_KEY.16b
|
||||
eor X_2.16b, X_2.16b, ROUND_KEY.16b
|
||||
eor X_3.16b, X_3.16b, ROUND_KEY.16b
|
||||
|
||||
// y = rol(y, 3)
|
||||
shl TMP0.\lanes, Y_0.\lanes, #3
|
||||
shl TMP1.\lanes, Y_1.\lanes, #3
|
||||
shl TMP2.\lanes, Y_2.\lanes, #3
|
||||
shl TMP3.\lanes, Y_3.\lanes, #3
|
||||
sri TMP0.\lanes, Y_0.\lanes, #(\n - 3)
|
||||
sri TMP1.\lanes, Y_1.\lanes, #(\n - 3)
|
||||
sri TMP2.\lanes, Y_2.\lanes, #(\n - 3)
|
||||
sri TMP3.\lanes, Y_3.\lanes, #(\n - 3)
|
||||
|
||||
// y ^= x
|
||||
eor Y_0.16b, TMP0.16b, X_0.16b
|
||||
eor Y_1.16b, TMP1.16b, X_1.16b
|
||||
eor Y_2.16b, TMP2.16b, X_2.16b
|
||||
eor Y_3.16b, TMP3.16b, X_3.16b
|
||||
.endm
|
||||
|
||||
/*
|
||||
* _speck_unround_128bytes() - Speck decryption round on 128 bytes at a time
|
||||
*
|
||||
* This is the inverse of _speck_round_128bytes().
|
||||
*/
|
||||
.macro _speck_unround_128bytes n, lanes
|
||||
|
||||
// y ^= x
|
||||
eor TMP0.16b, Y_0.16b, X_0.16b
|
||||
eor TMP1.16b, Y_1.16b, X_1.16b
|
||||
eor TMP2.16b, Y_2.16b, X_2.16b
|
||||
eor TMP3.16b, Y_3.16b, X_3.16b
|
||||
|
||||
// y = ror(y, 3)
|
||||
ushr Y_0.\lanes, TMP0.\lanes, #3
|
||||
ushr Y_1.\lanes, TMP1.\lanes, #3
|
||||
ushr Y_2.\lanes, TMP2.\lanes, #3
|
||||
ushr Y_3.\lanes, TMP3.\lanes, #3
|
||||
sli Y_0.\lanes, TMP0.\lanes, #(\n - 3)
|
||||
sli Y_1.\lanes, TMP1.\lanes, #(\n - 3)
|
||||
sli Y_2.\lanes, TMP2.\lanes, #(\n - 3)
|
||||
sli Y_3.\lanes, TMP3.\lanes, #(\n - 3)
|
||||
|
||||
// x ^= k
|
||||
eor X_0.16b, X_0.16b, ROUND_KEY.16b
|
||||
eor X_1.16b, X_1.16b, ROUND_KEY.16b
|
||||
eor X_2.16b, X_2.16b, ROUND_KEY.16b
|
||||
eor X_3.16b, X_3.16b, ROUND_KEY.16b
|
||||
|
||||
// x -= y
|
||||
sub X_0.\lanes, X_0.\lanes, Y_0.\lanes
|
||||
sub X_1.\lanes, X_1.\lanes, Y_1.\lanes
|
||||
sub X_2.\lanes, X_2.\lanes, Y_2.\lanes
|
||||
sub X_3.\lanes, X_3.\lanes, Y_3.\lanes
|
||||
|
||||
// x = rol(x, 8)
|
||||
tbl X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
|
||||
tbl X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
|
||||
tbl X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
|
||||
tbl X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
|
||||
.endm
|
||||
|
||||
.macro _next_xts_tweak next, cur, tmp, n
|
||||
.if \n == 64
|
||||
/*
|
||||
* Calculate the next tweak by multiplying the current one by x,
|
||||
* modulo p(x) = x^128 + x^7 + x^2 + x + 1.
|
||||
*/
|
||||
sshr \tmp\().2d, \cur\().2d, #63
|
||||
and \tmp\().16b, \tmp\().16b, GFMUL_TABLE.16b
|
||||
shl \next\().2d, \cur\().2d, #1
|
||||
ext \tmp\().16b, \tmp\().16b, \tmp\().16b, #8
|
||||
eor \next\().16b, \next\().16b, \tmp\().16b
|
||||
.else
|
||||
/*
|
||||
* Calculate the next two tweaks by multiplying the current ones by x^2,
|
||||
* modulo p(x) = x^64 + x^4 + x^3 + x + 1.
|
||||
*/
|
||||
ushr \tmp\().2d, \cur\().2d, #62
|
||||
shl \next\().2d, \cur\().2d, #2
|
||||
tbl \tmp\().16b, {GFMUL_TABLE.16b}, \tmp\().16b
|
||||
eor \next\().16b, \next\().16b, \tmp\().16b
|
||||
.endif
|
||||
.endm
|
||||
|
||||
/*
|
||||
* _speck_xts_crypt() - Speck-XTS encryption/decryption
|
||||
*
|
||||
* Encrypt or decrypt NBYTES bytes of data from the SRC buffer to the DST buffer
|
||||
* using Speck-XTS, specifically the variant with a block size of '2n' and round
|
||||
* count given by NROUNDS. The expanded round keys are given in ROUND_KEYS, and
|
||||
* the current XTS tweak value is given in TWEAK. It's assumed that NBYTES is a
|
||||
* nonzero multiple of 128.
|
||||
*/
|
||||
.macro _speck_xts_crypt n, lanes, decrypting
|
||||
|
||||
/*
|
||||
* If decrypting, modify the ROUND_KEYS parameter to point to the last
|
||||
* round key rather than the first, since for decryption the round keys
|
||||
* are used in reverse order.
|
||||
*/
|
||||
.if \decrypting
|
||||
mov NROUNDS, NROUNDS /* zero the high 32 bits */
|
||||
.if \n == 64
|
||||
add ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #3
|
||||
sub ROUND_KEYS, ROUND_KEYS, #8
|
||||
.else
|
||||
add ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #2
|
||||
sub ROUND_KEYS, ROUND_KEYS, #4
|
||||
.endif
|
||||
.endif
|
||||
|
||||
// Load the index vector for tbl-based 8-bit rotates
|
||||
.if \decrypting
|
||||
ldr ROTATE_TABLE_Q, .Lrol\n\()_8_table
|
||||
.else
|
||||
ldr ROTATE_TABLE_Q, .Lror\n\()_8_table
|
||||
.endif
|
||||
|
||||
// One-time XTS preparation
|
||||
.if \n == 64
|
||||
// Load first tweak
|
||||
ld1 {TWEAKV0.16b}, [TWEAK]
|
||||
|
||||
// Load GF(2^128) multiplication table
|
||||
ldr GFMUL_TABLE_Q, .Lgf128mul_table
|
||||
.else
|
||||
// Load first tweak
|
||||
ld1 {TWEAKV0.8b}, [TWEAK]
|
||||
|
||||
// Load GF(2^64) multiplication table
|
||||
ldr GFMUL_TABLE_Q, .Lgf64mul_table
|
||||
|
||||
// Calculate second tweak, packing it together with the first
|
||||
ushr TMP0.2d, TWEAKV0.2d, #63
|
||||
shl TMP1.2d, TWEAKV0.2d, #1
|
||||
tbl TMP0.8b, {GFMUL_TABLE.16b}, TMP0.8b
|
||||
eor TMP0.8b, TMP0.8b, TMP1.8b
|
||||
mov TWEAKV0.d[1], TMP0.d[0]
|
||||
.endif
|
||||
|
||||
.Lnext_128bytes_\@:
|
||||
|
||||
// Calculate XTS tweaks for next 128 bytes
|
||||
_next_xts_tweak TWEAKV1, TWEAKV0, TMP0, \n
|
||||
_next_xts_tweak TWEAKV2, TWEAKV1, TMP0, \n
|
||||
_next_xts_tweak TWEAKV3, TWEAKV2, TMP0, \n
|
||||
_next_xts_tweak TWEAKV4, TWEAKV3, TMP0, \n
|
||||
_next_xts_tweak TWEAKV5, TWEAKV4, TMP0, \n
|
||||
_next_xts_tweak TWEAKV6, TWEAKV5, TMP0, \n
|
||||
_next_xts_tweak TWEAKV7, TWEAKV6, TMP0, \n
|
||||
_next_xts_tweak TWEAKV_NEXT, TWEAKV7, TMP0, \n
|
||||
|
||||
// Load the next source blocks into {X,Y}[0-3]
|
||||
ld1 {X_0.16b-Y_1.16b}, [SRC], #64
|
||||
ld1 {X_2.16b-Y_3.16b}, [SRC], #64
|
||||
|
||||
// XOR the source blocks with their XTS tweaks
|
||||
eor TMP0.16b, X_0.16b, TWEAKV0.16b
|
||||
eor Y_0.16b, Y_0.16b, TWEAKV1.16b
|
||||
eor TMP1.16b, X_1.16b, TWEAKV2.16b
|
||||
eor Y_1.16b, Y_1.16b, TWEAKV3.16b
|
||||
eor TMP2.16b, X_2.16b, TWEAKV4.16b
|
||||
eor Y_2.16b, Y_2.16b, TWEAKV5.16b
|
||||
eor TMP3.16b, X_3.16b, TWEAKV6.16b
|
||||
eor Y_3.16b, Y_3.16b, TWEAKV7.16b
|
||||
|
||||
/*
|
||||
* De-interleave the 'x' and 'y' elements of each block, i.e. make it so
|
||||
* that the X[0-3] registers contain only the second halves of blocks,
|
||||
* and the Y[0-3] registers contain only the first halves of blocks.
|
||||
* (Speck uses the order (y, x) rather than the more intuitive (x, y).)
|
||||
*/
|
||||
uzp2 X_0.\lanes, TMP0.\lanes, Y_0.\lanes
|
||||
uzp1 Y_0.\lanes, TMP0.\lanes, Y_0.\lanes
|
||||
uzp2 X_1.\lanes, TMP1.\lanes, Y_1.\lanes
|
||||
uzp1 Y_1.\lanes, TMP1.\lanes, Y_1.\lanes
|
||||
uzp2 X_2.\lanes, TMP2.\lanes, Y_2.\lanes
|
||||
uzp1 Y_2.\lanes, TMP2.\lanes, Y_2.\lanes
|
||||
uzp2 X_3.\lanes, TMP3.\lanes, Y_3.\lanes
|
||||
uzp1 Y_3.\lanes, TMP3.\lanes, Y_3.\lanes
|
||||
|
||||
// Do the cipher rounds
|
||||
mov x6, ROUND_KEYS
|
||||
mov w7, NROUNDS
|
||||
.Lnext_round_\@:
|
||||
.if \decrypting
|
||||
ld1r {ROUND_KEY.\lanes}, [x6]
|
||||
sub x6, x6, #( \n / 8 )
|
||||
_speck_unround_128bytes \n, \lanes
|
||||
.else
|
||||
ld1r {ROUND_KEY.\lanes}, [x6], #( \n / 8 )
|
||||
_speck_round_128bytes \n, \lanes
|
||||
.endif
|
||||
subs w7, w7, #1
|
||||
bne .Lnext_round_\@
|
||||
|
||||
// Re-interleave the 'x' and 'y' elements of each block
|
||||
zip1 TMP0.\lanes, Y_0.\lanes, X_0.\lanes
|
||||
zip2 Y_0.\lanes, Y_0.\lanes, X_0.\lanes
|
||||
zip1 TMP1.\lanes, Y_1.\lanes, X_1.\lanes
|
||||
zip2 Y_1.\lanes, Y_1.\lanes, X_1.\lanes
|
||||
zip1 TMP2.\lanes, Y_2.\lanes, X_2.\lanes
|
||||
zip2 Y_2.\lanes, Y_2.\lanes, X_2.\lanes
|
||||
zip1 TMP3.\lanes, Y_3.\lanes, X_3.\lanes
|
||||
zip2 Y_3.\lanes, Y_3.\lanes, X_3.\lanes
|
||||
|
||||
// XOR the encrypted/decrypted blocks with the tweaks calculated earlier
|
||||
eor X_0.16b, TMP0.16b, TWEAKV0.16b
|
||||
eor Y_0.16b, Y_0.16b, TWEAKV1.16b
|
||||
eor X_1.16b, TMP1.16b, TWEAKV2.16b
|
||||
eor Y_1.16b, Y_1.16b, TWEAKV3.16b
|
||||
eor X_2.16b, TMP2.16b, TWEAKV4.16b
|
||||
eor Y_2.16b, Y_2.16b, TWEAKV5.16b
|
||||
eor X_3.16b, TMP3.16b, TWEAKV6.16b
|
||||
eor Y_3.16b, Y_3.16b, TWEAKV7.16b
|
||||
mov TWEAKV0.16b, TWEAKV_NEXT.16b
|
||||
|
||||
// Store the ciphertext in the destination buffer
|
||||
st1 {X_0.16b-Y_1.16b}, [DST], #64
|
||||
st1 {X_2.16b-Y_3.16b}, [DST], #64
|
||||
|
||||
// Continue if there are more 128-byte chunks remaining
|
||||
subs NBYTES, NBYTES, #128
|
||||
bne .Lnext_128bytes_\@
|
||||
|
||||
// Store the next tweak and return
|
||||
.if \n == 64
|
||||
st1 {TWEAKV_NEXT.16b}, [TWEAK]
|
||||
.else
|
||||
st1 {TWEAKV_NEXT.8b}, [TWEAK]
|
||||
.endif
|
||||
ret
|
||||
.endm
|
||||
|
||||
ENTRY(speck128_xts_encrypt_neon)
|
||||
_speck_xts_crypt n=64, lanes=2d, decrypting=0
|
||||
ENDPROC(speck128_xts_encrypt_neon)
|
||||
|
||||
ENTRY(speck128_xts_decrypt_neon)
|
||||
_speck_xts_crypt n=64, lanes=2d, decrypting=1
|
||||
ENDPROC(speck128_xts_decrypt_neon)
|
||||
|
||||
ENTRY(speck64_xts_encrypt_neon)
|
||||
_speck_xts_crypt n=32, lanes=4s, decrypting=0
|
||||
ENDPROC(speck64_xts_encrypt_neon)
|
||||
|
||||
ENTRY(speck64_xts_decrypt_neon)
|
||||
_speck_xts_crypt n=32, lanes=4s, decrypting=1
|
||||
ENDPROC(speck64_xts_decrypt_neon)
|
||||
308
arch/arm64/crypto/speck-neon-glue.c
Normal file
308
arch/arm64/crypto/speck-neon-glue.c
Normal file
|
|
@ -0,0 +1,308 @@
|
|||
// SPDX-License-Identifier: GPL-2.0
|
||||
/*
|
||||
* NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
|
||||
* (64-bit version; based on the 32-bit version)
|
||||
*
|
||||
* Copyright (c) 2018 Google, Inc
|
||||
*/
|
||||
|
||||
#include <asm/hwcap.h>
|
||||
#include <asm/neon.h>
|
||||
#include <asm/simd.h>
|
||||
#include <crypto/algapi.h>
|
||||
#include <crypto/gf128mul.h>
|
||||
#include <crypto/speck.h>
|
||||
#include <crypto/xts.h>
|
||||
#include <linux/kernel.h>
|
||||
#include <linux/module.h>
|
||||
|
||||
/* The assembly functions only handle multiples of 128 bytes */
|
||||
#define SPECK_NEON_CHUNK_SIZE 128
|
||||
|
||||
/* Speck128 */
|
||||
|
||||
struct speck128_xts_tfm_ctx {
|
||||
struct speck128_tfm_ctx main_key;
|
||||
struct speck128_tfm_ctx tweak_key;
|
||||
};
|
||||
|
||||
asmlinkage void speck128_xts_encrypt_neon(const u64 *round_keys, int nrounds,
|
||||
void *dst, const void *src,
|
||||
unsigned int nbytes, void *tweak);
|
||||
|
||||
asmlinkage void speck128_xts_decrypt_neon(const u64 *round_keys, int nrounds,
|
||||
void *dst, const void *src,
|
||||
unsigned int nbytes, void *tweak);
|
||||
|
||||
typedef void (*speck128_crypt_one_t)(const struct speck128_tfm_ctx *,
|
||||
u8 *, const u8 *);
|
||||
typedef void (*speck128_xts_crypt_many_t)(const u64 *, int, void *,
|
||||
const void *, unsigned int, void *);
|
||||
|
||||
static __always_inline int
|
||||
__speck128_xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
|
||||
struct scatterlist *src, unsigned int nbytes,
|
||||
speck128_crypt_one_t crypt_one,
|
||||
speck128_xts_crypt_many_t crypt_many)
|
||||
{
|
||||
struct crypto_blkcipher *tfm = desc->tfm;
|
||||
const struct speck128_xts_tfm_ctx *ctx = crypto_blkcipher_ctx(tfm);
|
||||
struct blkcipher_walk walk;
|
||||
le128 tweak;
|
||||
int err;
|
||||
|
||||
blkcipher_walk_init(&walk, dst, src, nbytes);
|
||||
err = blkcipher_walk_virt_block(desc, &walk, SPECK_NEON_CHUNK_SIZE);
|
||||
|
||||
crypto_speck128_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
|
||||
|
||||
while (walk.nbytes > 0) {
|
||||
unsigned int nbytes = walk.nbytes;
|
||||
u8 *dst = walk.dst.virt.addr;
|
||||
const u8 *src = walk.src.virt.addr;
|
||||
|
||||
if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
|
||||
unsigned int count;
|
||||
|
||||
count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
|
||||
kernel_neon_begin();
|
||||
(*crypt_many)(ctx->main_key.round_keys,
|
||||
ctx->main_key.nrounds,
|
||||
dst, src, count, &tweak);
|
||||
kernel_neon_end();
|
||||
dst += count;
|
||||
src += count;
|
||||
nbytes -= count;
|
||||
}
|
||||
|
||||
/* Handle any remainder with generic code */
|
||||
while (nbytes >= sizeof(tweak)) {
|
||||
le128_xor((le128 *)dst, (const le128 *)src, &tweak);
|
||||
(*crypt_one)(&ctx->main_key, dst, dst);
|
||||
le128_xor((le128 *)dst, (const le128 *)dst, &tweak);
|
||||
gf128mul_x_ble((be128 *)&tweak, (const be128 *)&tweak);
|
||||
|
||||
dst += sizeof(tweak);
|
||||
src += sizeof(tweak);
|
||||
nbytes -= sizeof(tweak);
|
||||
}
|
||||
err = blkcipher_walk_done(desc, &walk, nbytes);
|
||||
}
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
static int speck128_xts_encrypt(struct blkcipher_desc *desc,
|
||||
struct scatterlist *dst,
|
||||
struct scatterlist *src,
|
||||
unsigned int nbytes)
|
||||
{
|
||||
return __speck128_xts_crypt(desc, dst, src, nbytes,
|
||||
crypto_speck128_encrypt,
|
||||
speck128_xts_encrypt_neon);
|
||||
}
|
||||
|
||||
static int speck128_xts_decrypt(struct blkcipher_desc *desc,
|
||||
struct scatterlist *dst,
|
||||
struct scatterlist *src,
|
||||
unsigned int nbytes)
|
||||
{
|
||||
return __speck128_xts_crypt(desc, dst, src, nbytes,
|
||||
crypto_speck128_decrypt,
|
||||
speck128_xts_decrypt_neon);
|
||||
}
|
||||
|
||||
static int speck128_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
|
||||
unsigned int keylen)
|
||||
{
|
||||
struct speck128_xts_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
|
||||
int err;
|
||||
|
||||
if (keylen % 2)
|
||||
return -EINVAL;
|
||||
|
||||
keylen /= 2;
|
||||
|
||||
err = crypto_speck128_setkey(&ctx->main_key, key, keylen);
|
||||
if (err)
|
||||
return err;
|
||||
|
||||
return crypto_speck128_setkey(&ctx->tweak_key, key + keylen, keylen);
|
||||
}
|
||||
|
||||
/* Speck64 */
|
||||
|
||||
struct speck64_xts_tfm_ctx {
|
||||
struct speck64_tfm_ctx main_key;
|
||||
struct speck64_tfm_ctx tweak_key;
|
||||
};
|
||||
|
||||
asmlinkage void speck64_xts_encrypt_neon(const u32 *round_keys, int nrounds,
|
||||
void *dst, const void *src,
|
||||
unsigned int nbytes, void *tweak);
|
||||
|
||||
asmlinkage void speck64_xts_decrypt_neon(const u32 *round_keys, int nrounds,
|
||||
void *dst, const void *src,
|
||||
unsigned int nbytes, void *tweak);
|
||||
|
||||
typedef void (*speck64_crypt_one_t)(const struct speck64_tfm_ctx *,
|
||||
u8 *, const u8 *);
|
||||
typedef void (*speck64_xts_crypt_many_t)(const u32 *, int, void *,
|
||||
const void *, unsigned int, void *);
|
||||
|
||||
static __always_inline int
|
||||
__speck64_xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
|
||||
struct scatterlist *src, unsigned int nbytes,
|
||||
speck64_crypt_one_t crypt_one,
|
||||
speck64_xts_crypt_many_t crypt_many)
|
||||
{
|
||||
struct crypto_blkcipher *tfm = desc->tfm;
|
||||
const struct speck64_xts_tfm_ctx *ctx = crypto_blkcipher_ctx(tfm);
|
||||
struct blkcipher_walk walk;
|
||||
__le64 tweak;
|
||||
int err;
|
||||
|
||||
blkcipher_walk_init(&walk, dst, src, nbytes);
|
||||
err = blkcipher_walk_virt_block(desc, &walk, SPECK_NEON_CHUNK_SIZE);
|
||||
|
||||
crypto_speck64_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
|
||||
|
||||
while (walk.nbytes > 0) {
|
||||
unsigned int nbytes = walk.nbytes;
|
||||
u8 *dst = walk.dst.virt.addr;
|
||||
const u8 *src = walk.src.virt.addr;
|
||||
|
||||
if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
|
||||
unsigned int count;
|
||||
|
||||
count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
|
||||
kernel_neon_begin();
|
||||
(*crypt_many)(ctx->main_key.round_keys,
|
||||
ctx->main_key.nrounds,
|
||||
dst, src, count, &tweak);
|
||||
kernel_neon_end();
|
||||
dst += count;
|
||||
src += count;
|
||||
nbytes -= count;
|
||||
}
|
||||
|
||||
/* Handle any remainder with generic code */
|
||||
while (nbytes >= sizeof(tweak)) {
|
||||
*(__le64 *)dst = *(__le64 *)src ^ tweak;
|
||||
(*crypt_one)(&ctx->main_key, dst, dst);
|
||||
*(__le64 *)dst ^= tweak;
|
||||
tweak = cpu_to_le64((le64_to_cpu(tweak) << 1) ^
|
||||
((tweak & cpu_to_le64(1ULL << 63)) ?
|
||||
0x1B : 0));
|
||||
dst += sizeof(tweak);
|
||||
src += sizeof(tweak);
|
||||
nbytes -= sizeof(tweak);
|
||||
}
|
||||
err = blkcipher_walk_done(desc, &walk, nbytes);
|
||||
}
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
static int speck64_xts_encrypt(struct blkcipher_desc *desc,
|
||||
struct scatterlist *dst, struct scatterlist *src,
|
||||
unsigned int nbytes)
|
||||
{
|
||||
return __speck64_xts_crypt(desc, dst, src, nbytes,
|
||||
crypto_speck64_encrypt,
|
||||
speck64_xts_encrypt_neon);
|
||||
}
|
||||
|
||||
static int speck64_xts_decrypt(struct blkcipher_desc *desc,
|
||||
struct scatterlist *dst, struct scatterlist *src,
|
||||
unsigned int nbytes)
|
||||
{
|
||||
return __speck64_xts_crypt(desc, dst, src, nbytes,
|
||||
crypto_speck64_decrypt,
|
||||
speck64_xts_decrypt_neon);
|
||||
}
|
||||
|
||||
static int speck64_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
|
||||
unsigned int keylen)
|
||||
{
|
||||
struct speck64_xts_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
|
||||
int err;
|
||||
|
||||
if (keylen % 2)
|
||||
return -EINVAL;
|
||||
|
||||
keylen /= 2;
|
||||
|
||||
err = crypto_speck64_setkey(&ctx->main_key, key, keylen);
|
||||
if (err)
|
||||
return err;
|
||||
|
||||
return crypto_speck64_setkey(&ctx->tweak_key, key + keylen, keylen);
|
||||
}
|
||||
|
||||
static struct crypto_alg speck_algs[] = {
|
||||
{
|
||||
.cra_name = "xts(speck128)",
|
||||
.cra_driver_name = "xts-speck128-neon",
|
||||
.cra_priority = 300,
|
||||
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
|
||||
.cra_blocksize = SPECK128_BLOCK_SIZE,
|
||||
.cra_type = &crypto_blkcipher_type,
|
||||
.cra_ctxsize = sizeof(struct speck128_xts_tfm_ctx),
|
||||
.cra_alignmask = 7,
|
||||
.cra_module = THIS_MODULE,
|
||||
.cra_u = {
|
||||
.blkcipher = {
|
||||
.min_keysize = 2 * SPECK128_128_KEY_SIZE,
|
||||
.max_keysize = 2 * SPECK128_256_KEY_SIZE,
|
||||
.ivsize = SPECK128_BLOCK_SIZE,
|
||||
.setkey = speck128_xts_setkey,
|
||||
.encrypt = speck128_xts_encrypt,
|
||||
.decrypt = speck128_xts_decrypt,
|
||||
}
|
||||
}
|
||||
}, {
|
||||
.cra_name = "xts(speck64)",
|
||||
.cra_driver_name = "xts-speck64-neon",
|
||||
.cra_priority = 300,
|
||||
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
|
||||
.cra_blocksize = SPECK64_BLOCK_SIZE,
|
||||
.cra_type = &crypto_blkcipher_type,
|
||||
.cra_ctxsize = sizeof(struct speck64_xts_tfm_ctx),
|
||||
.cra_alignmask = 7,
|
||||
.cra_module = THIS_MODULE,
|
||||
.cra_u = {
|
||||
.blkcipher = {
|
||||
.min_keysize = 2 * SPECK64_96_KEY_SIZE,
|
||||
.max_keysize = 2 * SPECK64_128_KEY_SIZE,
|
||||
.ivsize = SPECK64_BLOCK_SIZE,
|
||||
.setkey = speck64_xts_setkey,
|
||||
.encrypt = speck64_xts_encrypt,
|
||||
.decrypt = speck64_xts_decrypt,
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
static int __init speck_neon_module_init(void)
|
||||
{
|
||||
if (!(elf_hwcap & HWCAP_ASIMD))
|
||||
return -ENODEV;
|
||||
return crypto_register_algs(speck_algs, ARRAY_SIZE(speck_algs));
|
||||
}
|
||||
|
||||
static void __exit speck_neon_module_exit(void)
|
||||
{
|
||||
crypto_unregister_algs(speck_algs, ARRAY_SIZE(speck_algs));
|
||||
}
|
||||
|
||||
module_init(speck_neon_module_init);
|
||||
module_exit(speck_neon_module_exit);
|
||||
|
||||
MODULE_DESCRIPTION("Speck block cipher (NEON-accelerated)");
|
||||
MODULE_LICENSE("GPL");
|
||||
MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
|
||||
MODULE_ALIAS_CRYPTO("xts(speck128)");
|
||||
MODULE_ALIAS_CRYPTO("xts-speck128-neon");
|
||||
MODULE_ALIAS_CRYPTO("xts(speck64)");
|
||||
MODULE_ALIAS_CRYPTO("xts-speck64-neon");
|
||||
|
|
@ -153,7 +153,7 @@ slot (const struct insn *insn)
|
|||
static int
|
||||
apply_imm64 (struct module *mod, struct insn *insn, uint64_t val)
|
||||
{
|
||||
if (slot(insn) != 2) {
|
||||
if (slot(insn) != 1 && slot(insn) != 2) {
|
||||
printk(KERN_ERR "%s: invalid slot number %d for IMM64\n",
|
||||
mod->name, slot(insn));
|
||||
return 0;
|
||||
|
|
@ -165,7 +165,7 @@ apply_imm64 (struct module *mod, struct insn *insn, uint64_t val)
|
|||
static int
|
||||
apply_imm60 (struct module *mod, struct insn *insn, uint64_t val)
|
||||
{
|
||||
if (slot(insn) != 2) {
|
||||
if (slot(insn) != 1 && slot(insn) != 2) {
|
||||
printk(KERN_ERR "%s: invalid slot number %d for IMM60\n",
|
||||
mod->name, slot(insn));
|
||||
return 0;
|
||||
|
|
|
|||
|
|
@ -474,7 +474,8 @@ enum {
|
|||
CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
|
||||
CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
|
||||
CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300)
|
||||
#define CPU_FTRS_POWER9_DD1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1)
|
||||
#define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
|
||||
(~CPU_FTR_SAO))
|
||||
#define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
|
||||
CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
|
||||
CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
|
||||
|
|
|
|||
|
|
@ -177,12 +177,15 @@ map_again:
|
|||
ret = mmu_hash_ops.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
|
||||
hpsize, hpsize, MMU_SEGSIZE_256M);
|
||||
|
||||
if (ret < 0) {
|
||||
if (ret == -1) {
|
||||
/* If we couldn't map a primary PTE, try a secondary */
|
||||
hash = ~hash;
|
||||
vflags ^= HPTE_V_SECONDARY;
|
||||
attempt++;
|
||||
goto map_again;
|
||||
} else if (ret < 0) {
|
||||
r = -EIO;
|
||||
goto out_unlock;
|
||||
} else {
|
||||
trace_kvm_book3s_64_mmu_map(rflags, hpteg,
|
||||
vpn, hpaddr, orig_pte);
|
||||
|
|
|
|||
|
|
@ -627,7 +627,11 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
|
|||
kvmppc_mmu_unmap_page(vcpu, &pte);
|
||||
}
|
||||
/* The guest's PTE is not mapped yet. Map on the host */
|
||||
kvmppc_mmu_map_page(vcpu, &pte, iswrite);
|
||||
if (kvmppc_mmu_map_page(vcpu, &pte, iswrite) == -EIO) {
|
||||
/* Exit KVM if mapping failed */
|
||||
run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
|
||||
return RESUME_HOST;
|
||||
}
|
||||
if (data)
|
||||
vcpu->stat.sp_storage++;
|
||||
else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
|
||||
|
|
|
|||
|
|
@ -460,10 +460,17 @@ void choose_random_location(unsigned long input,
|
|||
add_identity_map(random_addr, output_size);
|
||||
*output = random_addr;
|
||||
}
|
||||
|
||||
/*
|
||||
* This loads the identity mapping page table.
|
||||
* This should only be done if a new physical address
|
||||
* is found for the kernel, otherwise we should keep
|
||||
* the old page table to make it be like the "nokaslr"
|
||||
* case.
|
||||
*/
|
||||
finalize_identity_maps();
|
||||
}
|
||||
|
||||
/* This actually loads the identity pagetable on x86_64. */
|
||||
finalize_identity_maps();
|
||||
|
||||
/* Pick random virtual address starting from LOAD_PHYSICAL_ADDR. */
|
||||
if (IS_ENABLED(CONFIG_X86_64))
|
||||
|
|
|
|||
|
|
@ -418,6 +418,7 @@ struct legacy_pic default_legacy_pic = {
|
|||
};
|
||||
|
||||
struct legacy_pic *legacy_pic = &default_legacy_pic;
|
||||
EXPORT_SYMBOL(legacy_pic);
|
||||
|
||||
static int __init i8259A_init_ops(void)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -33,6 +33,7 @@
|
|||
#include <asm/mce.h>
|
||||
#include <asm/trace/irq_vectors.h>
|
||||
#include <asm/kexec.h>
|
||||
#include <asm/virtext.h>
|
||||
|
||||
/*
|
||||
* Some notes on x86 processor bugs affecting SMP operation:
|
||||
|
|
@ -162,6 +163,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
|
|||
if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
|
||||
return NMI_HANDLED;
|
||||
|
||||
cpu_emergency_vmxoff();
|
||||
stop_this_cpu(NULL);
|
||||
|
||||
return NMI_HANDLED;
|
||||
|
|
@ -174,6 +176,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
|
|||
asmlinkage __visible void smp_reboot_interrupt(void)
|
||||
{
|
||||
ipi_entering_ack_irq();
|
||||
cpu_emergency_vmxoff();
|
||||
stop_this_cpu(NULL);
|
||||
irq_exit();
|
||||
}
|
||||
|
|
|
|||
|
|
@ -299,35 +299,46 @@ static void __init xen_filter_cpu_maps(void)
|
|||
|
||||
}
|
||||
|
||||
static void __init xen_smp_prepare_boot_cpu(void)
|
||||
static void __init xen_pv_smp_prepare_boot_cpu(void)
|
||||
{
|
||||
BUG_ON(smp_processor_id() != 0);
|
||||
native_smp_prepare_boot_cpu();
|
||||
|
||||
if (xen_pv_domain()) {
|
||||
if (!xen_feature(XENFEAT_writable_page_tables))
|
||||
/* We've switched to the "real" per-cpu gdt, so make
|
||||
* sure the old memory can be recycled. */
|
||||
make_lowmem_page_readwrite(xen_initial_gdt);
|
||||
if (!xen_feature(XENFEAT_writable_page_tables))
|
||||
/* We've switched to the "real" per-cpu gdt, so make
|
||||
* sure the old memory can be recycled. */
|
||||
make_lowmem_page_readwrite(xen_initial_gdt);
|
||||
|
||||
#ifdef CONFIG_X86_32
|
||||
/*
|
||||
* Xen starts us with XEN_FLAT_RING1_DS, but linux code
|
||||
* expects __USER_DS
|
||||
*/
|
||||
loadsegment(ds, __USER_DS);
|
||||
loadsegment(es, __USER_DS);
|
||||
/*
|
||||
* Xen starts us with XEN_FLAT_RING1_DS, but linux code
|
||||
* expects __USER_DS
|
||||
*/
|
||||
loadsegment(ds, __USER_DS);
|
||||
loadsegment(es, __USER_DS);
|
||||
#endif
|
||||
|
||||
xen_filter_cpu_maps();
|
||||
xen_setup_vcpu_info_placement();
|
||||
}
|
||||
xen_filter_cpu_maps();
|
||||
xen_setup_vcpu_info_placement();
|
||||
|
||||
/*
|
||||
* The alternative logic (which patches the unlock/lock) runs before
|
||||
* the smp bootup up code is activated. Hence we need to set this up
|
||||
* the core kernel is being patched. Otherwise we will have only
|
||||
* modules patched but not core code.
|
||||
*/
|
||||
xen_init_spinlocks();
|
||||
}
|
||||
|
||||
static void __init xen_hvm_smp_prepare_boot_cpu(void)
|
||||
{
|
||||
BUG_ON(smp_processor_id() != 0);
|
||||
native_smp_prepare_boot_cpu();
|
||||
|
||||
/*
|
||||
* Setup vcpu_info for boot CPU.
|
||||
*/
|
||||
if (xen_hvm_domain())
|
||||
xen_vcpu_setup(0);
|
||||
xen_vcpu_setup(0);
|
||||
|
||||
/*
|
||||
* The alternative logic (which patches the unlock/lock) runs before
|
||||
|
|
@ -733,7 +744,7 @@ static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
|
|||
}
|
||||
|
||||
static const struct smp_ops xen_smp_ops __initconst = {
|
||||
.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu,
|
||||
.smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu,
|
||||
.smp_prepare_cpus = xen_smp_prepare_cpus,
|
||||
.smp_cpus_done = xen_smp_cpus_done,
|
||||
|
||||
|
|
@ -772,5 +783,5 @@ void __init xen_hvm_smp_init(void)
|
|||
smp_ops.cpu_die = xen_cpu_die;
|
||||
smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
|
||||
smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
|
||||
smp_ops.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu;
|
||||
smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -2014,15 +2014,15 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
|
|||
|
||||
blk_mq_init_cpu_queues(q, set->nr_hw_queues);
|
||||
|
||||
get_online_cpus();
|
||||
mutex_lock(&all_q_mutex);
|
||||
get_online_cpus();
|
||||
|
||||
list_add_tail(&q->all_q_node, &all_q_list);
|
||||
blk_mq_add_queue_tag_set(set, q);
|
||||
blk_mq_map_swqueue(q, cpu_online_mask);
|
||||
|
||||
mutex_unlock(&all_q_mutex);
|
||||
put_online_cpus();
|
||||
mutex_unlock(&all_q_mutex);
|
||||
|
||||
return q;
|
||||
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Reference in a new issue