aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/Kconfig1
-rw-r--r--arch/powerpc/configs/85xx-hw.config3
-rw-r--r--arch/powerpc/configs/85xx/ge_imp3a_defconfig1
-rw-r--r--arch/powerpc/configs/85xx/xes_mpc85xx_defconfig1
-rw-r--r--arch/powerpc/configs/cell_defconfig1
-rw-r--r--arch/powerpc/configs/pasemi_defconfig1
-rw-r--r--arch/powerpc/configs/ppc64_defconfig1
-rw-r--r--arch/powerpc/configs/ppc64e_defconfig1
-rw-r--r--arch/powerpc/configs/ppc6xx_defconfig3
-rw-r--r--arch/powerpc/crypto/Makefile3
-rw-r--r--arch/powerpc/crypto/crc-vpmsum_test.c137
-rw-r--r--arch/powerpc/crypto/crc32-vpmsum_core.S755
-rw-r--r--arch/powerpc/crypto/crc32c-vpmsum_asm.S715
-rw-r--r--arch/powerpc/crypto/crc32c-vpmsum_glue.c3
-rw-r--r--arch/powerpc/crypto/crct10dif-vpmsum_asm.S850
-rw-r--r--arch/powerpc/crypto/crct10dif-vpmsum_glue.c128
-rw-r--r--arch/powerpc/include/asm/bug.h4
-rw-r--r--arch/powerpc/include/asm/exception-64s.h8
-rw-r--r--arch/powerpc/include/asm/extable.h29
-rw-r--r--arch/powerpc/include/asm/mmu_context.h6
-rw-r--r--arch/powerpc/include/asm/uaccess.h96
-rw-r--r--arch/powerpc/include/uapi/asm/socket.h6
-rw-r--r--arch/powerpc/kernel/align.c27
-rw-r--r--arch/powerpc/kernel/entry_64.S6
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S2
-rw-r--r--arch/powerpc/kernel/idle_book3s.S20
-rw-r--r--arch/powerpc/kernel/misc_64.S4
-rw-r--r--arch/powerpc/kernel/nvram_64.c89
-rw-r--r--arch/powerpc/kernel/setup_64.c9
-rw-r--r--arch/powerpc/kernel/smp.c26
-rw-r--r--arch/powerpc/kernel/time.c2
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S2
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c4
-rw-r--r--arch/powerpc/lib/Makefile2
-rw-r--r--arch/powerpc/lib/copy_32.S14
-rw-r--r--arch/powerpc/lib/copyuser_64.S35
-rw-r--r--arch/powerpc/lib/usercopy_64.c41
-rw-r--r--arch/powerpc/mm/hash_native_64.c7
-rw-r--r--arch/powerpc/mm/init_64.c3
39 files changed, 2051 insertions, 995 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 97a8bc8a095c..053382616533 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -117,7 +117,6 @@ config PPC
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL_OLD
select HAVE_ARCH_AUDITSYSCALL
- select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KGDB
select HAVE_ARCH_SECCOMP_FILTER
diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config
index 528ff0e714e6..c03d0fb16665 100644
--- a/arch/powerpc/configs/85xx-hw.config
+++ b/arch/powerpc/configs/85xx-hw.config
@@ -16,9 +16,8 @@ CONFIG_DAVICOM_PHY=y
CONFIG_DMADEVICES=y
CONFIG_E1000E=y
CONFIG_E1000=y
-CONFIG_EDAC_MM_EDAC=y
-CONFIG_EDAC_MPC85XX=y
CONFIG_EDAC=y
+CONFIG_EDAC_MPC85XX=y
CONFIG_EEPROM_AT24=y
CONFIG_EEPROM_LEGACY=y
CONFIG_FB_FSL_DIU=y
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
index c79283be5680..a917f7afb4f9 100644
--- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -155,7 +155,6 @@ CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
CONFIG_USB_STORAGE=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_MPC85XX=y
CONFIG_RTC_CLASS=y
# CONFIG_RTC_INTF_PROC is not set
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index dbd961de251e..72900b84d3e0 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -116,7 +116,6 @@ CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
CONFIG_RTC_DRV_CMOS=y
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 2d7fcbe047ac..aa564599e368 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -179,7 +179,6 @@ CONFIG_INFINIBAND_MTHCA=m
CONFIG_INFINIBAND_IPOIB=m
CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_CELL=y
CONFIG_UIO=m
CONFIG_EXT2_FS=y
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 5553c5ce4274..fe43ff47bd2f 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -142,7 +142,6 @@ CONFIG_USB_UHCI_HCD=y
CONFIG_USB_SL811_HCD=y
CONFIG_USB_STORAGE=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_PASEMI=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 4f1288b04303..f2e03f032041 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -262,7 +262,6 @@ CONFIG_INFINIBAND_IPOIB_CM=y
CONFIG_INFINIBAND_SRP=m
CONFIG_INFINIBAND_ISER=m
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_PASEMI=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 11a3473f9e2e..6340e6c53c54 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -173,7 +173,6 @@ CONFIG_INFINIBAND_MTHCA=m
CONFIG_INFINIBAND_IPOIB=m
CONFIG_INFINIBAND_ISER=m
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
CONFIG_FS_DAX=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 1d2d69dd6409..18d0d60dadbf 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -988,8 +988,7 @@ CONFIG_LEDS_TRIGGER_BACKLIGHT=m
CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
CONFIG_ACCESSIBILITY=y
CONFIG_A11Y_BRAILLE_CONSOLE=y
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=m
+CONFIG_EDAC=m
CONFIG_RTC_CLASS=y
# CONFIG_RTC_HCTOSYS is not set
CONFIG_RTC_DRV_DS1307=m
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 87f40454bad3..67eca3af9fc7 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -10,6 +10,8 @@ obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o
+obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o
aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
md5-ppc-y := md5-asm.o md5-glue.o
@@ -17,3 +19,4 @@ sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
+crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c
new file mode 100644
index 000000000000..0153a9c6f4af
--- /dev/null
+++ b/arch/powerpc/crypto/crc-vpmsum_test.c
@@ -0,0 +1,137 @@
+/*
+ * CRC vpmsum tester
+ * Copyright 2017 Daniel Axtens, IBM Corporation.
+ *
+ * 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/crc-t10dif.h>
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/switch_to.h>
+
+static unsigned long iterations = 10000;
+
+#define MAX_CRC_LENGTH 65535
+
+
+static int __init crc_test_init(void)
+{
+ u16 crc16 = 0, verify16 = 0;
+ u32 crc32 = 0, verify32 = 0;
+ __le32 verify32le = 0;
+ unsigned char *data;
+ unsigned long i;
+ int ret;
+
+ struct crypto_shash *crct10dif_tfm;
+ struct crypto_shash *crc32c_tfm;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ data = kmalloc(MAX_CRC_LENGTH, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
+
+ if (IS_ERR(crct10dif_tfm)) {
+ pr_err("Error allocating crc-t10dif\n");
+ goto free_buf;
+ }
+
+ crc32c_tfm = crypto_alloc_shash("crc32c", 0, 0);
+
+ if (IS_ERR(crc32c_tfm)) {
+ pr_err("Error allocating crc32c\n");
+ goto free_16;
+ }
+
+ do {
+ SHASH_DESC_ON_STACK(crct10dif_shash, crct10dif_tfm);
+ SHASH_DESC_ON_STACK(crc32c_shash, crc32c_tfm);
+
+ crct10dif_shash->tfm = crct10dif_tfm;
+ ret = crypto_shash_init(crct10dif_shash);
+
+ if (ret) {
+ pr_err("Error initing crc-t10dif\n");
+ goto free_32;
+ }
+
+
+ crc32c_shash->tfm = crc32c_tfm;
+ ret = crypto_shash_init(crc32c_shash);
+
+ if (ret) {
+ pr_err("Error initing crc32c\n");
+ goto free_32;
+ }
+
+ pr_info("crc-vpmsum_test begins, %lu iterations\n", iterations);
+ for (i=0; i<iterations; i++) {
+ size_t len, offset;
+
+ get_random_bytes(data, MAX_CRC_LENGTH);
+ get_random_bytes(&len, sizeof(len));
+ get_random_bytes(&offset, sizeof(offset));
+
+ len %= MAX_CRC_LENGTH;
+ offset &= 15;
+ if (len <= offset)
+ continue;
+ len -= offset;
+
+ crypto_shash_update(crct10dif_shash, data+offset, len);
+ crypto_shash_final(crct10dif_shash, (u8 *)(&crc16));
+ verify16 = crc_t10dif_generic(verify16, data+offset, len);
+
+
+ if (crc16 != verify16) {
+ pr_err("FAILURE in CRC16: got 0x%04x expected 0x%04x (len %lu)\n",
+ crc16, verify16, len);
+ break;
+ }
+
+ crypto_shash_update(crc32c_shash, data+offset, len);
+ crypto_shash_final(crc32c_shash, (u8 *)(&crc32));
+ verify32 = le32_to_cpu(verify32le);
+ verify32le = ~cpu_to_le32(__crc32c_le(~verify32, data+offset, len));
+ if (crc32 != (u32)verify32le) {
+ pr_err("FAILURE in CRC32: got 0x%08x expected 0x%08x (len %lu)\n",
+ crc32, verify32, len);
+ break;
+ }
+ }
+ pr_info("crc-vpmsum_test done, completed %lu iterations\n", i);
+ } while (0);
+
+free_32:
+ crypto_free_shash(crc32c_tfm);
+
+free_16:
+ crypto_free_shash(crct10dif_tfm);
+
+free_buf:
+ kfree(data);
+
+ return 0;
+}
+
+static void __exit crc_test_exit(void) {}
+
+module_init(crc_test_init);
+module_exit(crc_test_exit);
+module_param(iterations, long, 0400);
+
+MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
+MODULE_DESCRIPTION("Vector polynomial multiply-sum CRC tester");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/crypto/crc32-vpmsum_core.S
new file mode 100644
index 000000000000..aadb59c96a27
--- /dev/null
+++ b/arch/powerpc/crypto/crc32-vpmsum_core.S
@@ -0,0 +1,755 @@
+/*
+ * Core of the accelerated CRC algorithm.
+ * In your file, define the constants and CRC_FUNCTION_NAME
+ * Then include this file.
+ *
+ * Calculate the checksum of data that is 16 byte aligned and a multiple of
+ * 16 bytes.
+ *
+ * The first step is to reduce it to 1024 bits. We do this in 8 parallel
+ * chunks in order to mask the latency of the vpmsum instructions. If we
+ * have more than 32 kB of data to checksum we repeat this step multiple
+ * times, passing in the previous 1024 bits.
+ *
+ * The next step is to reduce the 1024 bits to 64 bits. This step adds
+ * 32 bits of 0s to the end - this matches what a CRC does. We just
+ * calculate constants that land the data in this 32 bits.
+ *
+ * We then use fixed point Barrett reduction to compute a mod n over GF(2)
+ * for n = CRC using POWER8 instructions. We use x = 32.
+ *
+ * http://en.wikipedia.org/wiki/Barrett_reduction
+ *
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * 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 <asm/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+
+#define MAX_SIZE 32768
+
+ .text
+
+#if defined(__BIG_ENDIAN__) && defined(REFLECT)
+#define BYTESWAP_DATA
+#elif defined(__LITTLE_ENDIAN__) && !defined(REFLECT)
+#define BYTESWAP_DATA
+#else
+#undef BYTESWAP_DATA
+#endif
+
+#define off16 r25
+#define off32 r26
+#define off48 r27
+#define off64 r28
+#define off80 r29
+#define off96 r30
+#define off112 r31
+
+#define const1 v24
+#define const2 v25
+
+#define byteswap v26
+#define mask_32bit v27
+#define mask_64bit v28
+#define zeroes v29
+
+#ifdef BYTESWAP_DATA
+#define VPERM(A, B, C, D) vperm A, B, C, D
+#else
+#define VPERM(A, B, C, D)
+#endif
+
+/* unsigned int CRC_FUNCTION_NAME(unsigned int crc, void *p, unsigned long len) */
+FUNC_START(CRC_FUNCTION_NAME)
+ std r31,-8(r1)
+ std r30,-16(r1)
+ std r29,-24(r1)
+ std r28,-32(r1)
+ std r27,-40(r1)
+ std r26,-48(r1)
+ std r25,-56(r1)
+
+ li off16,16
+ li off32,32
+ li off48,48
+ li off64,64
+ li off80,80
+ li off96,96
+ li off112,112
+ li r0,0
+
+ /* Enough room for saving 10 non volatile VMX registers */
+ subi r6,r1,56+10*16
+ subi r7,r1,56+2*16
+
+ stvx v20,0,r6
+ stvx v21,off16,r6
+ stvx v22,off32,r6
+ stvx v23,off48,r6
+ stvx v24,off64,r6
+ stvx v25,off80,r6
+ stvx v26,off96,r6
+ stvx v27,off112,r6
+ stvx v28,0,r7
+ stvx v29,off16,r7
+
+ mr r10,r3
+
+ vxor zeroes,zeroes,zeroes
+ vspltisw v0,-1
+
+ vsldoi mask_32bit,zeroes,v0,4
+ vsldoi mask_64bit,zeroes,v0,8
+
+ /* Get the initial value into v8 */
+ vxor v8,v8,v8
+ MTVRD(v8, R3)
+#ifdef REFLECT
+ vsldoi v8,zeroes,v8,8 /* shift into bottom 32 bits */
+#else
+ vsldoi v8,v8,zeroes,4 /* shift into top 32 bits */
+#endif
+
+#ifdef BYTESWAP_DATA
+ addis r3,r2,.byteswap_constant@toc@ha
+ addi r3,r3,.byteswap_constant@toc@l
+
+ lvx byteswap,0,r3
+ addi r3,r3,16
+#endif
+
+ cmpdi r5,256
+ blt .Lshort
+
+ rldicr r6,r5,0,56
+
+ /* Checksum in blocks of MAX_SIZE */
+1: lis r7,MAX_SIZE@h
+ ori r7,r7,MAX_SIZE@l
+ mr r9,r7
+ cmpd r6,r7
+ bgt 2f
+ mr r7,r6
+2: subf r6,r7,r6
+
+ /* our main loop does 128 bytes at a time */
+ srdi r7,r7,7
+
+ /*
+ * Work out the offset into the constants table to start at. Each
+ * constant is 16 bytes, and it is used against 128 bytes of input
+ * data - 128 / 16 = 8
+ */
+ sldi r8,r7,4
+ srdi r9,r9,3
+ subf r8,r8,r9
+
+ /* We reduce our final 128 bytes in a separate step */
+ addi r7,r7,-1
+ mtctr r7
+
+ addis r3,r2,.constants@toc@ha
+ addi r3,r3,.constants@toc@l
+
+ /* Find the start of our constants */
+ add r3,r3,r8
+
+ /* zero v0-v7 which will contain our checksums */
+ vxor v0,v0,v0
+ vxor v1,v1,v1
+ vxor v2,v2,v2
+ vxor v3,v3,v3
+ vxor v4,v4,v4
+ vxor v5,v5,v5
+ vxor v6,v6,v6
+ vxor v7,v7,v7
+
+ lvx const1,0,r3
+
+ /*
+ * If we are looping back to consume more data we use the values
+ * already in v16-v23.
+ */
+ cmpdi r0,1
+ beq 2f
+
+ /* First warm up pass */
+ lvx v16,0,r4
+ lvx v17,off16,r4
+ VPERM(v16,v16,v16,byteswap)
+ VPERM(v17,v17,v17,byteswap)
+ lvx v18,off32,r4
+ lvx v19,off48,r4
+ VPERM(v18,v18,v18,byteswap)
+ VPERM(v19,v19,v19,byteswap)
+ lvx v20,off64,r4
+ lvx v21,off80,r4
+ VPERM(v20,v20,v20,byteswap)
+ VPERM(v21,v21,v21,byteswap)
+ lvx v22,off96,r4
+ lvx v23,off112,r4
+ VPERM(v22,v22,v22,byteswap)
+ VPERM(v23,v23,v23,byteswap)
+ addi r4,r4,8*16
+
+ /* xor in initial value */
+ vxor v16,v16,v8
+
+2: bdz .Lfirst_warm_up_done
+
+ addi r3,r3,16
+ lvx const2,0,r3
+
+ /* Second warm up pass */
+ VPMSUMD(v8,v16,const1)
+ lvx v16,0,r4
+ VPERM(v16,v16,v16,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v9,v17,const1)
+ lvx v17,off16,r4
+ VPERM(v17,v17,v17,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v10,v18,const1)
+ lvx v18,off32,r4
+ VPERM(v18,v18,v18,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v11,v19,const1)
+ lvx v19,off48,r4
+ VPERM(v19,v19,v19,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v12,v20,const1)
+ lvx v20,off64,r4
+ VPERM(v20,v20,v20,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v13,v21,const1)
+ lvx v21,off80,r4
+ VPERM(v21,v21,v21,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v14,v22,const1)
+ lvx v22,off96,r4
+ VPERM(v22,v22,v22,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v15,v23,const1)
+ lvx v23,off112,r4
+ VPERM(v23,v23,v23,byteswap)
+
+ addi r4,r4,8*16
+
+ bdz .Lfirst_cool_down
+
+ /*
+ * main loop. We modulo schedule it such that it takes three iterations
+ * to complete - first iteration load, second iteration vpmsum, third
+ * iteration xor.
+ */
+ .balign 16
+4: lvx const1,0,r3
+ addi r3,r3,16
+ ori r2,r2,0
+
+ vxor v0,v0,v8
+ VPMSUMD(v8,v16,const2)
+ lvx v16,0,r4
+ VPERM(v16,v16,v16,byteswap)
+ ori r2,r2,0
+
+ vxor v1,v1,v9
+ VPMSUMD(v9,v17,const2)
+ lvx v17,off16,r4
+ VPERM(v17,v17,v17,byteswap)
+ ori r2,r2,0
+
+ vxor v2,v2,v10
+ VPMSUMD(v10,v18,const2)
+ lvx v18,off32,r4
+ VPERM(v18,v18,v18,byteswap)
+ ori r2,r2,0
+
+ vxor v3,v3,v11
+ VPMSUMD(v11,v19,const2)
+ lvx v19,off48,r4
+ VPERM(v19,v19,v19,byteswap)
+ lvx const2,0,r3
+ ori r2,r2,0
+
+ vxor v4,v4,v12
+ VPMSUMD(v12,v20,const1)
+ lvx v20,off64,r4
+ VPERM(v20,v20,v20,byteswap)
+ ori r2,r2,0
+
+ vxor v5,v5,v13
+ VPMSUMD(v13,v21,const1)
+ lvx v21,off80,r4
+ VPERM(v21,v21,v21,byteswap)
+ ori r2,r2,0
+
+ vxor v6,v6,v14
+ VPMSUMD(v14,v22,const1)
+ lvx v22,off96,r4
+ VPERM(v22,v22,v22,byteswap)
+ ori r2,r2,0
+
+ vxor v7,v7,v15
+ VPMSUMD(v15,v23,const1)
+ lvx v23,off112,r4
+ VPERM(v23,v23,v23,byteswap)
+
+ addi r4,r4,8*16
+
+ bdnz 4b
+
+.Lfirst_cool_down:
+ /* First cool down pass */
+ lvx const1,0,r3
+ addi r3,r3,16
+
+ vxor v0,v0,v8
+ VPMSUMD(v8,v16,const1)
+ ori r2,r2,0
+
+ vxor v1,v1,v9
+ VPMSUMD(v9,v17,const1)
+ ori r2,r2,0
+
+ vxor v2,v2,v10
+ VPMSUMD(v10,v18,const1)
+ ori r2,r2,0
+
+ vxor v3,v3,v11
+ VPMSUMD(v11,v19,const1)
+ ori r2,r2,0
+
+ vxor v4,v4,v12
+ VPMSUMD(v12,v20,const1)
+ ori r2,r2,0
+
+ vxor v5,v5,v13
+ VPMSUMD(v13,v21,const1)
+ ori r2,r2,0
+
+ vxor v6,v6,v14
+ VPMSUMD(v14,v22,const1)
+ ori r2,r2,0
+
+ vxor v7,v7,v15
+ VPMSUMD(v15,v23,const1)
+ ori r2,r2,0
+
+.Lsecond_cool_down:
+ /* Second cool down pass */
+ vxor v0,v0,v8
+ vxor v1,v1,v9
+ vxor v2,v2,v10
+ vxor v3,v3,v11
+ vxor v4,v4,v12
+ vxor v5,v5,v13
+ vxor v6,v6,v14
+ vxor v7,v7,v15
+
+#ifdef REFLECT
+ /*
+ * vpmsumd produces a 96 bit result in the least significant bits
+ * of the register. Since we are bit reflected we have to shift it
+ * left 32 bits so it occupies the least significant bits in the
+ * bit reflected domain.
+ */
+ vsldoi v0,v0,zeroes,4
+ vsldoi v1,v1,zeroes,4
+ vsldoi v2,v2,zeroes,4
+ vsldoi v3,v3,zeroes,4
+ vsldoi v4,v4,zeroes,4
+ vsldoi v5,v5,zeroes,4
+ vsldoi v6,v6,zeroes,4
+ vsldoi v7,v7,zeroes,4
+#endif
+
+ /* xor with last 1024 bits */
+ lvx v8,0,r4
+ lvx v9,off16,r4
+ VPERM(v8,v8,v8,byteswap)
+ VPERM(v9,v9,v9,byteswap)
+ lvx v10,off32,r4
+ lvx v11,off48,r4
+ VPERM(v10,v10,v10,byteswap)
+ VPERM(v11,v11,v11,byteswap)
+ lvx v12,off64,r4
+ lvx v13,off80,r4
+ VPERM(v12,v12,v12,byteswap)
+ VPERM(v13,v13,v13,byteswap)
+ lvx v14,off96,r4
+ lvx v15,off112,r4
+ VPERM(v14,v14,v14,byteswap)
+ VPERM(v15,v15,v15,byteswap)
+
+ addi r4,r4,8*16
+
+ vxor v16,v0,v8
+ vxor v17,v1,v9
+ vxor v18,v2,v10
+ vxor v19,v3,v11
+ vxor v20,v4,v12
+ vxor v21,v5,v13
+ vxor v22,v6,v14
+ vxor v23,v7,v15
+
+ li r0,1
+ cmpdi r6,0
+ addi r6,r6,128
+ bne 1b
+
+ /* Work out how many bytes we have left */
+ andi. r5,r5,127
+
+ /* Calculate where in the constant table we need to start */
+ subfic r6,r5,128
+ add r3,r3,r6
+
+ /* How many 16 byte chunks are in the tail */
+ srdi r7,r5,4
+ mtctr r7
+
+ /*
+ * Reduce the previously calculated 1024 bits to 64 bits, shifting
+ * 32 bits to include the trailing 32 bits of zeros
+ */
+ lvx v0,0,r3
+ lvx v1,off16,r3
+ lvx v2,off32,r3
+ lvx v3,off48,r3
+ lvx v4,off64,r3
+ lvx v5,off80,r3
+ lvx v6,off96,r3
+ lvx v7,off112,r3
+ addi r3,r3,8*16
+
+ VPMSUMW(v0,v16,v0)
+ VPMSUMW(v1,v17,v1)
+ VPMSUMW(v2,v18,v2)
+ VPMSUMW(v3,v19,v3)
+ VPMSUMW(v4,v20,v4)
+ VPMSUMW(v5,v21,v5)
+ VPMSUMW(v6,v22,v6)
+ VPMSUMW(v7,v23,v7)
+
+ /* Now reduce the tail (0 - 112 bytes) */
+ cmpdi r7,0
+ beq 1f
+
+ lvx v16,0,r4
+ lvx v17,0,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off16,r4
+ lvx v17,off16,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off32,r4
+ lvx v17,off32,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off48,r4
+ lvx v17,off48,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off64,r4
+ lvx v17,off64,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off80,r4
+ lvx v17,off80,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off96,r4
+ lvx v17,off96,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+
+ /* Now xor all the parallel chunks together */
+1: vxor v0,v0,v1
+ vxor v2,v2,v3
+ vxor v4,v4,v5
+ vxor v6,v6,v7
+
+ vxor v0,v0,v2
+ vxor v4,v4,v6
+
+ vxor v0,v0,v4
+
+.Lbarrett_reduction:
+ /* Barrett constants */
+ addis r3,r2,.barrett_constants@toc@ha
+ addi r3,r3,.barrett_constants@toc@l
+
+ lvx const1,0,r3
+ lvx const2,off16,r3
+
+ vsldoi v1,v0,v0,8
+ vxor v0,v0,v1 /* xor two 64 bit results together */
+
+#ifdef REFLECT
+ /* shift left one bit */
+ vspltisb v1,1
+ vsl v0,v0,v1
+#endif
+
+ vand v0,v0,mask_64bit
+#ifndef REFLECT
+ /*
+ * Now for the Barrett reduction algorithm. The idea is to calculate q,
+ * the multiple of our polynomial that we need to subtract. By
+ * doing the computation 2x bits higher (ie 64 bits) and shifting the
+ * result back down 2x bits, we round down to the nearest multiple.
+ */
+ VPMSUMD(v1,v0,const1) /* ma */
+ vsldoi v1,zeroes,v1,8 /* q = floor(ma/(2^64)) */
+ VPMSUMD(v1,v1,const2) /* qn */
+ vxor v0,v0,v1 /* a - qn, subtraction is xor in GF(2) */
+
+ /*
+ * Get the result into r3. We need to shift it left 8 bytes:
+ * V0 [ 0 1 2 X ]
+ * V0 [ 0 X 2 3 ]
+ */
+ vsldoi v0,v0,zeroes,8 /* shift result into top 64 bits */
+#else
+ /*
+ * The reflected version of Barrett reduction. Instead of bit
+ * reflecting our data (which is expensive to do), we bit reflect our
+ * constants and our algorithm, which means the intermediate data in
+ * our vector registers goes from 0-63 instead of 63-0. We can reflect
+ * the algorithm because we don't carry in mod 2 arithmetic.
+ */
+ vand v1,v0,mask_32bit /* bottom 32 bits of a */
+ VPMSUMD(v1,v1,const1) /* ma */
+ vand v1,v1,mask_32bit /* bottom 32bits of ma */
+ VPMSUMD(v1,v1,const2) /* qn */
+ vxor v0,v0,v1 /* a - qn, subtraction is xor in GF(2) */
+
+ /*
+ * Since we are bit reflected, the result (ie the low 32 bits) is in
+ * the high 32 bits. We just need to shift it left 4 bytes
+ * V0 [ 0 1 X 3 ]
+ * V0 [ 0 X 2 3 ]
+ */
+ vsldoi v0,v0,zeroes,4 /* shift result into top 64 bits of */
+#endif
+
+ /* Get it into r3 */
+ MFVRD(R3, v0)
+
+.Lout:
+ subi r6,r1,56+10*16
+ subi r7,r1,56+2*16
+
+ lvx v20,0,r6
+ lvx v21,off16,r6
+ lvx v22,off32,r6
+ lvx v23,off48,r6
+ lvx v24,off64,r6
+ lvx v25,off80,r6
+ lvx v26,off96,r6
+ lvx v27,off112,r6
+ lvx v28,0,r7
+ lvx v29,off16,r7
+
+ ld r31,-8(r1)
+ ld r30,-16(r1)
+ ld r29,-24(r1)
+ ld r28,-32(r1)
+ ld r27,-40(r1)
+ ld r26,-48(r1)
+ ld r25,-56(r1)
+
+ blr
+
+.Lfirst_warm_up_done:
+ lvx const1,0,r3
+ addi r3,r3,16
+
+ VPMSUMD(v8,v16,const1)
+ VPMSUMD(v9,v17,const1)
+ VPMSUMD(v10,v18,const1)
+ VPMSUMD(v11,v19,const1)
+ VPMSUMD(v12,v20,const1)
+ VPMSUMD(v13,v21,const1)
+ VPMSUMD(v14,v22,const1)
+ VPMSUMD(v15,v23,const1)
+
+ b .Lsecond_cool_down
+
+.Lshort:
+ cmpdi r5,0
+ beq .Lzero
+
+ addis r3,r2,.short_constants@toc@ha
+ addi r3,r3,.short_constants@toc@l
+
+ /* Calculate where in the constant table we need to start */
+ subfic r6,r5,256
+ add r3,r3,r6
+
+ /* How many 16 byte chunks? */
+ srdi r7,r5,4
+ mtctr r7
+
+ vxor v19,v19,v19
+ vxor v20,v20,v20
+
+ lvx v0,0,r4
+ lvx v16,0,r3
+ VPERM(v0,v0,v16,byteswap)
+ vxor v0,v0,v8 /* xor in initial value */
+ VPMSUMW(v0,v0,v16)
+ bdz .Lv0
+
+ lvx v1,off16,r4
+ lvx v17,off16,r3
+ VPERM(v1,v1,v17,byteswap)
+ VPMSUMW(v1,v1,v17)
+ bdz .Lv1
+
+ lvx v2,off32,r4
+ lvx v16,off32,r3
+ VPERM(v2,v2,v16,byteswap)
+ VPMSUMW(v2,v2,v16)
+ bdz .Lv2
+
+ lvx v3,off48,r4
+ lvx v17,off48,r3
+ VPERM(v3,v3,v17,byteswap)
+ VPMSUMW(v3,v3,v17)
+ bdz .Lv3
+
+ lvx v4,off64,r4
+ lvx v16,off64,r3
+ VPERM(v4,v4,v16,byteswap)
+ VPMSUMW(v4,v4,v16)
+ bdz .Lv4
+
+ lvx v5,off80,r4
+ lvx v17,off80,r3
+ VPERM(v5,v5,v17,byteswap)
+ VPMSUMW(v5,v5,v17)
+ bdz .Lv5
+
+ lvx v6,off96,r4
+ lvx v16,off96,r3
+ VPERM(v6,v6,v16,byteswap)
+ VPMSUMW(v6,v6,v16)
+ bdz .Lv6
+
+ lvx v7,off112,r4
+ lvx v17,off112,r3
+ VPERM(v7,v7,v17,byteswap)
+ VPMSUMW(v7,v7,v17)
+ bdz .Lv7
+
+ addi r3,r3,128
+ addi r4,r4,128
+
+ lvx v8,0,r4
+ lvx v16,0,r3
+ VPERM(v8,v8,v16,byteswap)
+ VPMSUMW(v8,v8,v16)
+ bdz .Lv8
+
+ lvx v9,off16,r4
+ lvx v17,off16,r3
+ VPERM(v9,v9,v17,byteswap)
+ VPMSUMW(v9,v9,v17)
+ bdz .Lv9
+
+ lvx v10,off32,r4
+ lvx v16,off32,r3
+ VPERM(v10,v10,v16,byteswap)
+ VPMSUMW(v10,v10,v16)
+ bdz .Lv10
+
+ lvx v11,off48,r4
+ lvx v17,off48,r3
+ VPERM(v11,v11,v17,byteswap)
+ VPMSUMW(v11,v11,v17)
+ bdz .Lv11
+
+ lvx v12,off64,r4
+ lvx v16,off64,r3
+ VPERM(v12,v12,v16,byteswap)
+ VPMSUMW(v12,v12,v16)
+ bdz .Lv12
+
+ lvx v13,off80,r4
+ lvx v17,off80,r3
+ VPERM(v13,v13,v17,byteswap)
+ VPMSUMW(v13,v13,v17)
+ bdz .Lv13
+
+ lvx v14,off96,r4
+ lvx v16,off96,r3
+ VPERM(v14,v14,v16,byteswap)
+ VPMSUMW(v14,v14,v16)
+ bdz .Lv14
+
+ lvx v15,off112,r4
+ lvx v17,off112,r3
+ VPERM(v15,v15,v17,byteswap)
+ VPMSUMW(v15,v15,v17)
+
+.Lv15: vxor v19,v19,v15
+.Lv14: vxor v20,v20,v14
+.Lv13: vxor v19,v19,v13
+.Lv12: vxor v20,v20,v12
+.Lv11: vxor v19,v19,v11
+.Lv10: vxor v20,v20,v10
+.Lv9: vxor v19,v19,v9
+.Lv8: vxor v20,v20,v8
+.Lv7: vxor v19,v19,v7
+.Lv6: vxor v20,v20,v6
+.Lv5: vxor v19,v19,v5
+.Lv4: vxor v20,v20,v4
+.Lv3: vxor v19,v19,v3
+.Lv2: vxor v20,v20,v2
+.Lv1: vxor v19,v19,v1
+.Lv0: vxor v20,v20,v0
+
+ vxor v0,v19,v20
+
+ b .Lbarrett_reduction
+
+.Lzero:
+ mr r3,r10
+ b .Lout
+
+FUNC_END(CRC_FUNCTION_NAME)
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
index dc640b212299..d2bea48051a0 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_asm.S
+++ b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
@@ -1,20 +1,5 @@
/*
- * Calculate the checksum of data that is 16 byte aligned and a multiple of
- * 16 bytes.
- *
- * The first step is to reduce it to 1024 bits. We do this in 8 parallel
- * chunks in order to mask the latency of the vpmsum instructions. If we
- * have more than 32 kB of data to checksum we repeat this step multiple
- * times, passing in the previous 1024 bits.
- *
- * The next step is to reduce the 1024 bits to 64 bits. This step adds
- * 32 bits of 0s to the end - this matches what a CRC does. We just
- * calculate constants that land the data in this 32 bits.
- *
- * We then use fixed point Barrett reduction to compute a mod n over GF(2)
- * for n = CRC using POWER8 instructions. We use x = 32.
- *
- * http://en.wikipedia.org/wiki/Barrett_reduction
+ * Calculate a crc32c with vpmsum acceleration
*
* Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
*
@@ -23,9 +8,6 @@
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
-#include <asm/ppc_asm.h>
-#include <asm/ppc-opcode.h>
-
.section .rodata
.balign 16
@@ -33,7 +15,6 @@
/* byte reverse permute constant */
.octa 0x0F0E0D0C0B0A09080706050403020100
-#define MAX_SIZE 32768
.constants:
/* Reduce 262144 kbits to 1024 bits */
@@ -860,694 +841,6 @@
/* 33 bit reflected Barrett constant n */
.octa 0x00000000000000000000000105ec76f1
- .text
-
-#if defined(__BIG_ENDIAN__)
-#define BYTESWAP_DATA
-#else
-#undef BYTESWAP_DATA
-#endif
-
-#define off16 r25
-#define off32 r26
-#define off48 r27
-#define off64 r28
-#define off80 r29
-#define off96 r30
-#define off112 r31
-
-#define const1 v24
-#define const2 v25
-
-#define byteswap v26
-#define mask_32bit v27
-#define mask_64bit v28
-#define zeroes v29
-
-#ifdef BYTESWAP_DATA
-#define VPERM(A, B, C, D) vperm A, B, C, D
-#else
-#define VPERM(A, B, C, D)
-#endif
-
-/* unsigned int __crc32c_vpmsum(unsigned int crc, void *p, unsigned long len) */
-FUNC_START(__crc32c_vpmsum)
- std r31,-8(r1)
- std r30,-16(r1)
- std r29,-24(r1)
- std r28,-32(r1)
- std r27,-40(r1)
- std r26,-48(r1)
- std r25,-56(r1)
-
- li off16,16
- li off32,32
- li off48,48
- li off64,64
- li off80,80
- li off96,96
- li off112,112
- li r0,0
-
- /* Enough room for saving 10 non volatile VMX registers */
- subi r6,r1,56+10*16
- subi r7,r1,56+2*16
-
- stvx v20,0,r6
- stvx v21,off16,r6
- stvx v22,off32,r6
- stvx v23,off48,r6
- stvx v24,off64,r6
- stvx v25,off80,r6
- stvx v26,off96,r6
- stvx v27,off112,r6
- stvx v28,0,r7
- stvx v29,off16,r7
-
- mr r10,r3
-
- vxor zeroes,zeroes,zeroes
- vspltisw v0,-1
-
- vsldoi mask_32bit,zeroes,v0,4
- vsldoi mask_64bit,zeroes,v0,8
-
- /* Get the initial value into v8 */
- vxor v8,v8,v8
- MTVRD(v8, R3)
- vsldoi v8,zeroes,v8,8 /* shift into bottom 32 bits */
-
-#ifdef BYTESWAP_DATA
- addis r3,r2,.byteswap_constant@toc@ha
- addi r3,r3,.byteswap_constant@toc@l
-
- lvx byteswap,0,r3
- addi r3,r3,16
-#endif
-
- cmpdi r5,256
- blt .Lshort
-
- rldicr r6,r5,0,56
-
- /* Checksum in blocks of MAX_SIZE */
-1: lis r7,MAX_SIZE@h
- ori r7,r7,MAX_SIZE@l
- mr r9,r7
- cmpd r6,r7
- bgt 2f
- mr r7,r6
-2: subf r6,r7,r6
-
- /* our main loop does 128 bytes at a time */
- srdi r7,r7,7
-
- /*
- * Work out the offset into the constants table to start at. Each
- * constant is 16 bytes, and it is used against 128 bytes of input
- * data - 128 / 16 = 8
- */
- sldi r8,r7,4
- srdi r9,r9,3
- subf r8,r8,r9
-
- /* We reduce our final 128 bytes in a separate step */
- addi r7,r7,-1
- mtctr r7
-
- addis r3,r2,.constants@toc@ha
- addi r3,r3,.constants@toc@l
-
- /* Find the start of our constants */
- add r3,r3,r8
-
- /* zero v0-v7 which will contain our checksums */
- vxor v0,v0,v0
- vxor v1,v1,v1
- vxor v2,v2,v2
- vxor v3,v3,v3
- vxor v4,v4,v4
- vxor v5,v5,v5
- vxor v6,v6,v6
- vxor v7,v7,v7
-
- lvx const1,0,r3
-
- /*
- * If we are looping back to consume more data we use the values
- * already in v16-v23.
- */
- cmpdi r0,1
- beq 2f
-
- /* First warm up pass */
- lvx v16,0,r4
- lvx v17,off16,r4
- VPERM(v16,v16,v16,byteswap)
- VPERM(v17,v17,v17,byteswap)
- lvx v18,off32,r4
- lvx v19,off48,r4
- VPERM(v18,v18,v18,byteswap)
- VPERM(v19,v19,v19,byteswap)
- lvx v20,off64,r4
- lvx v21,off80,r4
- VPERM(v20,v20,v20,byteswap)
- VPERM(v21,v21,v21,byteswap)
- lvx v22,off96,r4
- lvx v23,off112,r4
- VPERM(v22,v22,v22,byteswap)
- VPERM(v23,v23,v23,byteswap)
- addi r4,r4,8*16
-
- /* xor in initial value */
- vxor v16,v16,v8
-
-2: bdz .Lfirst_warm_up_done
-
- addi r3,r3,16
- lvx const2,0,r3
-
- /* Second warm up pass */
- VPMSUMD(v8,v16,const1)
- lvx v16,0,r4
- VPERM(v16,v16,v16,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v9,v17,const1)
- lvx v17,off16,r4
- VPERM(v17,v17,v17,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v10,v18,const1)
- lvx v18,off32,r4
- VPERM(v18,v18,v18,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v11,v19,const1)
- lvx v19,off48,r4
- VPERM(v19,v19,v19,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v12,v20,const1)
- lvx v20,off64,r4
- VPERM(v20,v20,v20,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v13,v21,const1)
- lvx v21,off80,r4
- VPERM(v21,v21,v21,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v14,v22,const1)
- lvx v22,off96,r4
- VPERM(v22,v22,v22,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v15,v23,const1)
- lvx v23,off112,r4
- VPERM(v23,v23,v23,byteswap)
-
- addi r4,r4,8*16
-
- bdz .Lfirst_cool_down
-
- /*
- * main loop. We modulo schedule it such that it takes three iterations
- * to complete - first iteration load, second iteration vpmsum, third
- * iteration xor.
- */
- .balign 16
-4: lvx const1,0,r3
- addi r3,r3,16
- ori r2,r2,0
-
- vxor v0,v0,v8
- VPMSUMD(v8,v16,const2)
- lvx v16,0,r4
- VPERM(v16,v16,v16,byteswap)
- ori r2,r2,0
-
- vxor v1,v1,v9
- VPMSUMD(v9,v17,const2)
- lvx v17,off16,r4
- VPERM(v17,v17,v17,byteswap)
- ori r2,r2,0
-
- vxor v2,v2,v10
- VPMSUMD(v10,v18,const2)
- lvx v18,off32,r4
- VPERM(v18,v18,v18,byteswap)
- ori r2,r2,0
-
- vxor v3,v3,v11
- VPMSUMD(v11,v19,const2)
- lvx v19,off48,r4
- VPERM(v19,v19,v19,byteswap)
- lvx const2,0,r3
- ori r2,r2,0
-
- vxor v4,v4,v12
- VPMSUMD(v12,v20,const1)
- lvx v20,off64,r4
- VPERM(v20,v20,v20,byteswap)
- ori r2,r2,0
-
- vxor v5,v5,v13
- VPMSUMD(v13,v21,const1)
- lvx v21,off80,r4
- VPERM(v21,v21,v21,byteswap)
- ori r2,r2,0
-
- vxor v6,v6,v14
- VPMSUMD(v14,v22,const1)
- lvx v22,off96,r4
- VPERM(v22,v22,v22,byteswap)
- ori r2,r2,0
-
- vxor v7,v7,v15
- VPMSUMD(v15,v23,const1)
- lvx v23,off112,r4
- VPERM(v23,v23,v23,byteswap)
-
- addi r4,r4,8*16
-
- bdnz 4b
-
-.Lfirst_cool_down:
- /* First cool down pass */
- lvx const1,0,r3
- addi r3,r3,16
-
- vxor v0,v0,v8
- VPMSUMD(v8,v16,const1)
- ori r2,r2,0
-
- vxor v1,v1,v9
- VPMSUMD(v9,v17,const1)
- ori r2,r2,0
-
- vxor v2,v2,v10
- VPMSUMD(v10,v18,const1)
- ori r2,r2,0
-
- vxor v3,v3,v11
- VPMSUMD(v11,v19,const1)
- ori r2,r2,0
-
- vxor v4,v4,v12
- VPMSUMD(v12,v20,const1)
- ori r2,r2,0
-
- vxor v5,v5,v13
- VPMSUMD(v13,v21,const1)
- ori r2,r2,0
-
- vxor v6,v6,v14
- VPMSUMD(v14,v22,const1)
- ori r2,r2,0
-
- vxor v7,v7,v15
- VPMSUMD(v15,v23,const1)
- ori r2,r2,0
-
-.Lsecond_cool_down:
- /* Second cool down pass */
- vxor v0,v0,v8
- vxor v1,v1,v9
- vxor v2,v2,v10
- vxor v3,v3,v11
- vxor v4,v4,v12
- vxor v5,v5,v13
- vxor v6,v6,v14
- vxor v7,v7,v15
-
- /*
- * vpmsumd produces a 96 bit result in the least significant bits
- * of the register. Since we are bit reflected we have to shift it
- * left 32 bits so it occupies the least significant bits in the
- * bit reflected domain.
- */
- vsldoi v0,v0,zeroes,4
- vsldoi v1,v1,zeroes,4
- vsldoi v2,v2,zeroes,4
- vsldoi v3,v3,zeroes,4
- vsldoi v4,v4,zeroes,4
- vsldoi v5,v5,zeroes,4
- vsldoi v6,v6,zeroes,4
- vsldoi v7,v7,zeroes,4
-
- /* xor with last 1024 bits */
- lvx v8,0,r4
- lvx v9,off16,r4
- VPERM(v8,v8,v8,byteswap)
- VPERM(v9,v9,v9,byteswap)
- lvx v10,off32,r4
- lvx v11,off48,r4
- VPERM(v10,v10,v10,byteswap)
- VPERM(v11,v11,v11,byteswap)
- lvx v12,off64,r4
- lvx v13,off80,r4
- VPERM(v12,v12,v12,byteswap)
- VPERM(v13,v13,v13,byteswap)
- lvx v14,off96,r4
- lvx v15,off112,r4
- VPERM(v14,v14,v14,byteswap)
- VPERM(v15,v15,v15,byteswap)
-
- addi r4,r4,8*16
-
- vxor v16,v0,v8
- vxor v17,v1,v9
- vxor v18,v2,v10
- vxor v19,v3,v11
- vxor v20,v4,v12
- vxor v21,v5,v13
- vxor v22,v6,v14
- vxor v23,v7,v15
-
- li r0,1
- cmpdi r6,0
- addi r6,r6,128
- bne 1b
-
- /* Work out how many bytes we have left */
- andi. r5,r5,127
-
- /* Calculate where in the constant table we need to start */
- subfic r6,r5,128
- add r3,r3,r6
-
- /* How many 16 byte chunks are in the tail */
- srdi r7,r5,4
- mtctr r7
-
- /*
- * Reduce the previously calculated 1024 bits to 64 bits, shifting
- * 32 bits to include the trailing 32 bits of zeros
- */
- lvx v0,0,r3
- lvx v1,off16,r3
- lvx v2,off32,r3
- lvx v3,off48,r3
- lvx v4,off64,r3
- lvx v5,off80,r3
- lvx v6,off96,r3
- lvx v7,off112,r3
- addi r3,r3,8*16
-
- VPMSUMW(v0,v16,v0)
- VPMSUMW(v1,v17,v1)
- VPMSUMW(v2,v18,v2)
- VPMSUMW(v3,v19,v3)
- VPMSUMW(v4,v20,v4)
- VPMSUMW(v5,v21,v5)
- VPMSUMW(v6,v22,v6)
- VPMSUMW(v7,v23,v7)
-
- /* Now reduce the tail (0 - 112 bytes) */
- cmpdi r7,0
- beq 1f
-
- lvx v16,0,r4
- lvx v17,0,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off16,r4
- lvx v17,off16,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off32,r4
- lvx v17,off32,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off48,r4
- lvx v17,off48,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off64,r4
- lvx v17,off64,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off80,r4
- lvx v17,off80,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off96,r4
- lvx v17,off96,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
-
- /* Now xor all the parallel chunks together */
-1: vxor v0,v0,v1
- vxor v2,v2,v3
- vxor v4,v4,v5
- vxor v6,v6,v7
-
- vxor v0,v0,v2
- vxor v4,v4,v6
-
- vxor v0,v0,v4
-
-.Lbarrett_reduction:
- /* Barrett constants */
- addis r3,r2,.barrett_constants@toc@ha
- addi r3,r3,.barrett_constants@toc@l
-
- lvx const1,0,r3
- lvx const2,off16,r3
-
- vsldoi v1,v0,v0,8
- vxor v0,v0,v1 /* xor two 64 bit results together */
-
- /* shift left one bit */
- vspltisb v1,1
- vsl v0,v0,v1
-
- vand v0,v0,mask_64bit
-
- /*
- * The reflected version of Barrett reduction. Instead of bit
- * reflecting our data (which is expensive to do), we bit reflect our
- * constants and our algorithm, which means the intermediate data in
- * our vector registers goes from 0-63 instead of 63-0. We can reflect
- * the algorithm because we don't carry in mod 2 arithmetic.
- */
- vand v1,v0,mask_32bit /* bottom 32 bits of a */
- VPMSUMD(v1,v1,const1) /* ma */
- vand v1,v1,mask_32bit /* bottom 32bits of ma */
- VPMSUMD(v1,v1,const2) /* qn */
- vxor v0,v0,v1 /* a - qn, subtraction is xor in GF(2) */
-
- /*
- * Since we are bit reflected, the result (ie the low 32 bits) is in
- * the high 32 bits. We just need to shift it left 4 bytes
- * V0 [ 0 1 X 3 ]
- * V0 [ 0 X 2 3 ]
- */
- vsldoi v0,v0,zeroes,4 /* shift result into top 64 bits of */
-
- /* Get it into r3 */
- MFVRD(R3, v0)
-
-.Lout:
- subi r6,r1,56+10*16
- subi r7,r1,56+2*16
-
- lvx v20,0,r6
- lvx v21,off16,r6
- lvx v22,off32,r6
- lvx v23,off48,r6
- lvx v24,off64,r6
- lvx v25,off80,r6
- lvx v26,off96,r6
- lvx v27,off112,r6
- lvx v28,0,r7
- lvx v29,off16,r7
-
- ld r31,-8(r1)
- ld r30,-16(r1)
- ld r29,-24(r1)
- ld r28,-32(r1)
- ld r27,-40(r1)
- ld r26,-48(r1)
- ld r25,-56(r1)
-
- blr
-
-.Lfirst_warm_up_done:
- lvx const1,0,r3
- addi r3,r3,16
-
- VPMSUMD(v8,v16,const1)
- VPMSUMD(v9,v17,const1)
- VPMSUMD(v10,v18,const1)
- VPMSUMD(v11,v19,const1)
- VPMSUMD(v12,v20,const1)
- VPMSUMD(v13,v21,const1)
- VPMSUMD(v14,v22,const1)
- VPMSUMD(v15,v23,const1)
-
- b .Lsecond_cool_down
-
-.Lshort:
- cmpdi r5,0
- beq .Lzero
-
- addis r3,r2,.short_constants@toc@ha
- addi r3,r3,.short_constants@toc@l
-
- /* Calculate where in the constant table we need to start */
- subfic r6,r5,256
- add r3,r3,r6
-
- /* How many 16 byte chunks? */
- srdi r7,r5,4
- mtctr r7
-
- vxor v19,v19,v19
- vxor v20,v20,v20
-
- lvx v0,0,r4
- lvx v16,0,r3
- VPERM(v0,v0,v16,byteswap)
- vxor v0,v0,v8 /* xor in initial value */
- VPMSUMW(v0,v0,v16)
- bdz .Lv0
-
- lvx v1,off16,r4
- lvx v17,off16,r3
- VPERM(v1,v1,v17,byteswap)
- VPMSUMW(v1,v1,v17)
- bdz .Lv1
-
- lvx v2,off32,r4
- lvx v16,off32,r3
- VPERM(v2,v2,v16,byteswap)
- VPMSUMW(v2,v2,v16)
- bdz .Lv2
-
- lvx v3,off48,r4
- lvx v17,off48,r3
- VPERM(v3,v3,v17,byteswap)
- VPMSUMW(v3,v3,v17)
- bdz .Lv3
-
- lvx v4,off64,r4
- lvx v16,off64,r3
- VPERM(v4,v4,v16,byteswap)
- VPMSUMW(v4,v4,v16)
- bdz .Lv4
-
- lvx v5,off80,r4
- lvx v17,off80,r3
- VPERM(v5,v5,v17,byteswap)
- VPMSUMW(v5,v5,v17)
- bdz .Lv5
-
- lvx v6,off96,r4
- lvx v16,off96,r3
- VPERM(v6,v6,v16,byteswap)
- VPMSUMW(v6,v6,v16)
- bdz .Lv6
-
- lvx v7,off112,r4
- lvx v17,off112,r3
- VPERM(v7,v7,v17,byteswap)
- VPMSUMW(v7,v7,v17)
- bdz .Lv7
-
- addi r3,r3,128
- addi r4,r4,128
-
- lvx v8,0,r4
- lvx v16,0,r3
- VPERM(v8,v8,v16,byteswap)
- VPMSUMW(v8,v8,v16)
- bdz .Lv8
-
- lvx v9,off16,r4
- lvx v17,off16,r3
- VPERM(v9,v9,v17,byteswap)
- VPMSUMW(v9,v9,v17)
- bdz .Lv9
-
- lvx v10,off32,r4
- lvx v16,off32,r3
- VPERM(v10,v10,v16,byteswap)
- VPMSUMW(v10,v10,v16)
- bdz .Lv10
-
- lvx v11,off48,r4
- lvx v17,off48,r3
- VPERM(v11,v11,v17,byteswap)
- VPMSUMW(v11,v11,v17)
- bdz .Lv11
-
- lvx v12,off64,r4
- lvx v16,off64,r3
- VPERM(v12,v12,v16,byteswap)
- VPMSUMW(v12,v12,v16)
- bdz .Lv12
-
- lvx v13,off80,r4
- lvx v17,off80,r3
- VPERM(v13,v13,v17,byteswap)
- VPMSUMW(v13,v13,v17)
- bdz .Lv13
-
- lvx v14,off96,r4
- lvx v16,off96,r3
- VPERM(v14,v14,v16,byteswap)
- VPMSUMW(v14,v14,v16)
- bdz .Lv14
-
- lvx v15,off112,r4
- lvx v17,off112,r3
- VPERM(v15,v15,v17,byteswap)
- VPMSUMW(v15,v15,v17)
-
-.Lv15: vxor v19,v19,v15
-.Lv14: vxor v20,v20,v14
-.Lv13: vxor v19,v19,v13
-.Lv12: vxor v20,v20,v12
-.Lv11: vxor v19,v19,v11
-.Lv10: vxor v20,v20,v10
-.Lv9: vxor v19,v19,v9
-.Lv8: vxor v20,v20,v8
-.Lv7: vxor v19,v19,v7
-.Lv6: vxor v20,v20,v6
-.Lv5: vxor v19,v19,v5
-.Lv4: vxor v20,v20,v4
-.Lv3: vxor v19,v19,v3
-.Lv2: vxor v20,v20,v2
-.Lv1: vxor v19,v19,v1
-.Lv0: vxor v20,v20,v0
-
- vxor v0,v19,v20
-
- b .Lbarrett_reduction
-
-.Lzero:
- mr r3,r10
- b .Lout
-
-FUNC_END(__crc32_vpmsum)
+#define CRC_FUNCTION_NAME __crc32c_vpmsum
+#define REFLECT
+#include "crc32-vpmsum_core.S"
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index 411994551afc..f058e0c3e4d4 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -33,10 +33,13 @@ static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len)
}
if (len & ~VMX_ALIGN_MASK) {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+ disable_kernel_altivec();
pagefault_enable();
+ preempt_enable();
}
tail = len & VMX_ALIGN_MASK;
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S b/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
new file mode 100644
index 000000000000..5e3d81a0af1b
--- /dev/null
+++ b/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
@@ -0,0 +1,850 @@
+/*
+ * Calculate a CRC T10DIF with vpmsum acceleration
+ *
+ * Constants generated by crc32-vpmsum, available at
+ * https://github.com/antonblanchard/crc32-vpmsum
+ *
+ * crc32-vpmsum is
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ * and is available under the GPL v2 or later.
+ *
+ * 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.
+ */
+ .section .rodata
+.balign 16
+
+.byteswap_constant:
+ /* byte reverse permute constant */
+ .octa 0x0F0E0D0C0B0A09080706050403020100
+
+.constants:
+
+ /* Reduce 262144 kbits to 1024 bits */
+ /* x^261184 mod p(x), x^261120 mod p(x) */
+ .octa 0x0000000056d300000000000052550000
+
+ /* x^260160 mod p(x), x^260096 mod p(x) */
+ .octa 0x00000000ee67000000000000a1e40000
+
+ /* x^259136 mod p(x), x^259072 mod p(x) */
+ .octa 0x0000000060830000000000004ad10000
+
+ /* x^258112 mod p(x), x^258048 mod p(x) */
+ .octa 0x000000008cfe0000000000009ab40000
+
+ /* x^257088 mod p(x), x^257024 mod p(x) */
+ .octa 0x000000003e93000000000000fdb50000
+
+ /* x^256064 mod p(x), x^256000 mod p(x) */
+ .octa 0x000000003c2000000000000045480000
+
+ /* x^255040 mod p(x), x^254976 mod p(x) */
+ .octa 0x00000000b1fc0000000000008d690000
+
+ /* x^254016 mod p(x), x^253952 mod p(x) */
+ .octa 0x00000000f82b00000000000024ad0000
+
+ /* x^252992 mod p(x), x^252928 mod p(x) */
+ .octa 0x0000000044420000000000009f1a0000
+
+ /* x^251968 mod p(x), x^251904 mod p(x) */
+ .octa 0x00000000e88c00000000000066ec0000
+
+ /* x^250944 mod p(x), x^250880 mod p(x) */
+ .octa 0x00000000385c000000000000c87d0000
+
+ /* x^249920 mod p(x), x^249856 mod p(x) */
+ .octa 0x000000003227000000000000c8ff0000
+
+ /* x^248896 mod p(x), x^248832 mod p(x) */
+ .octa 0x00000000a9a900000000000033440000
+
+ /* x^247872 mod p(x), x^247808 mod p(x) */
+ .octa 0x00000000abaa00000000000066eb0000
+
+ /* x^246848 mod p(x), x^246784 mod p(x) */
+ .octa 0x000000001ac3000000000000c4ef0000
+
+ /* x^245824 mod p(x), x^245760 mod p(x) */
+ .octa 0x0000000063f000000000000056f30000
+
+ /* x^244800 mod p(x), x^244736 mod p(x) */
+ .octa 0x0000000032cc00000000000002050000
+
+ /* x^243776 mod p(x), x^243712 mod p(x) */
+ .octa 0x00000000f8b5000000000000568e0000
+
+ /* x^242752 mod p(x), x^242688 mod p(x) */
+ .octa 0x000000008db100000000000064290000
+
+ /* x^241728 mod p(x), x^241664 mod p(x) */
+ .octa 0x0000000059ca0000000000006b660000
+
+ /* x^240704 mod p(x), x^240640 mod p(x) */
+ .octa 0x000000005f5c00000000000018f80000
+
+ /* x^239680 mod p(x), x^239616 mod p(x) */
+ .octa 0x0000000061af000000000000b6090000
+
+ /* x^238656 mod p(x), x^238592 mod p(x) */
+ .octa 0x00000000e29e000000000000099a0000
+
+ /* x^237632 mod p(x), x^237568 mod p(x) */
+ .octa 0x000000000975000000000000a8360000
+
+ /* x^236608 mod p(x), x^236544 mod p(x) */
+ .octa 0x0000000043900000000000004f570000
+
+ /* x^235584 mod p(x), x^235520 mod p(x) */
+ .octa 0x00000000f9cd000000000000134c0000
+
+ /* x^234560 mod p(x), x^234496 mod p(x) */
+ .octa 0x000000007c29000000000000ec380000
+
+ /* x^233536 mod p(x), x^233472 mod p(x) */
+ .octa 0x000000004c6a000000000000b0d10000
+
+ /* x^232512 mod p(x), x^232448 mod p(x) */
+ .octa 0x00000000e7290000000000007d3e0000
+
+ /* x^231488 mod p(x), x^231424 mod p(x) */
+ .octa 0x00000000f1ab000000000000f0b20000
+
+ /* x^230464 mod p(x), x^230400 mod p(x) */
+ .octa 0x0000000039db0000000000009c270000
+
+ /* x^229440 mod p(x), x^229376 mod p(x) */
+ .octa 0x000000005e2800000000000092890000
+
+ /* x^228416 mod p(x), x^228352 mod p(x) */
+ .octa 0x00000000d44e000000000000d5ee0000
+
+ /* x^227392 mod p(x), x^227328 mod p(x) */
+ .octa 0x00000000cd0a00000000000041f50000
+
+ /* x^226368 mod p(x), x^226304 mod p(x) */
+ .octa 0x00000000c5b400000000000010520000
+
+ /* x^225344 mod p(x), x^225280 mod p(x) */
+ .octa 0x00000000fd2100000000000042170000
+
+ /* x^224320 mod p(x), x^224256 mod p(x) */
+ .octa 0x000000002f2500000000000095c20000
+
+ /* x^223296 mod p(x), x^223232 mod p(x) */
+ .octa 0x000000001b0100000000000001ce0000
+
+ /* x^222272 mod p(x), x^222208 mod p(x) */
+ .octa 0x000000000d430000000000002aca0000
+
+ /* x^221248 mod p(x), x^221184 mod p(x) */
+ .octa 0x0000000030a6000000000000385e0000
+
+ /* x^220224 mod p(x), x^220160 mod p(x) */
+ .octa 0x00000000e37b0000000000006f7a0000
+
+ /* x^219200 mod p(x), x^219136 mod p(x) */
+ .octa 0x00000000873600000000000024320000
+
+ /* x^218176 mod p(x), x^218112 mod p(x) */
+ .octa 0x00000000e9fb000000000000bd9c0000
+
+ /* x^217152 mod p(x), x^217088 mod p(x) */
+ .octa 0x000000003b9500000000000054bc0000
+
+ /* x^216128 mod p(x), x^216064 mod p(x) */
+ .octa 0x00000000133e000000000000a4660000
+
+ /* x^215104 mod p(x), x^215040 mod p(x) */
+ .octa 0x00000000784500000000000079930000
+
+ /* x^214080 mod p(x), x^214016 mod p(x) */
+ .octa 0x00000000b9800000000000001bb80000
+
+ /* x^213056 mod p(x), x^212992 mod p(x) */
+ .octa 0x00000000687600000000000024400000
+
+ /* x^212032 mod p(x), x^211968 mod p(x) */
+ .octa 0x00000000aff300000000000029e10000
+
+ /* x^211008 mod p(x), x^210944 mod p(x) */
+ .octa 0x0000000024b50000000000005ded0000
+
+ /* x^209984 mod p(x), x^209920 mod p(x) */
+ .octa 0x0000000017e8000000000000b12e0000
+
+ /* x^208960 mod p(x), x^208896 mod p(x) */
+ .octa 0x00000000128400000000000026d20000
+
+ /* x^207936 mod p(x), x^207872 mod p(x) */
+ .octa 0x000000002115000000000000a32a0000
+
+ /* x^206912 mod p(x), x^206848 mod p(x) */
+ .octa 0x000000009595000000000000a1210000
+
+ /* x^205888 mod p(x), x^205824 mod p(x) */
+ .octa 0x00000000281e000000000000ee8b0000
+
+ /* x^204864 mod p(x), x^204800 mod p(x) */
+ .octa 0x0000000006010000000000003d0d0000
+
+ /* x^203840 mod p(x), x^203776 mod p(x) */
+ .octa 0x00000000e2b600000000000034e90000
+
+ /* x^202816 mod p(x), x^202752 mod p(x) */
+ .octa 0x000000001bd40000000000004cdb0000
+
+ /* x^201792 mod p(x), x^201728 mod p(x) */
+ .octa 0x00000000df2800000000000030e90000
+
+ /* x^200768 mod p(x), x^200704 mod p(x) */
+ .octa 0x0000000049c200000000000042590000
+
+ /* x^199744 mod p(x), x^199680 mod p(x) */
+ .octa 0x000000009b97000000000000df950000
+
+ /* x^198720 mod p(x), x^198656 mod p(x) */
+ .octa 0x000000006184000000000000da7b0000
+
+ /* x^197696 mod p(x), x^197632 mod p(x) */
+ .octa 0x00000000461700000000000012510000
+
+ /* x^196672 mod p(x), x^196608 mod p(x) */
+ .octa 0x000000009b40000000000000f37e0000
+
+ /* x^195648 mod p(x), x^195584 mod p(x) */
+ .octa 0x00000000eeb2000000000000ecf10000
+
+ /* x^194624 mod p(x), x^194560 mod p(x) */
+ .octa 0x00000000b2e800000000000050f20000
+
+ /* x^193600 mod p(x), x^193536 mod p(x) */
+ .octa 0x00000000f59a000000000000e0b30000
+
+ /* x^192576 mod p(x), x^192512 mod p(x) */
+ .octa 0x00000000467f0000000000004d5a0000
+
+ /* x^191552 mod p(x), x^191488 mod p(x) */
+ .octa 0x00000000da92000000000000bb010000
+
+ /* x^190528 mod p(x), x^190464 mod p(x) */
+ .octa 0x000000001e1000000000000022a40000
+
+ /* x^189504 mod p(x), x^189440 mod p(x) */
+ .octa 0x0000000058fe000000000000836f0000
+
+ /* x^188480 mod p(x), x^188416 mod p(x) */
+ .octa 0x00000000b9ce000000000000d78d0000
+
+ /* x^187456 mod p(x), x^187392 mod p(x) */
+ .octa 0x0000000022210000000000004f8d0000
+
+ /* x^186432 mod p(x), x^186368 mod p(x) */
+ .octa 0x00000000744600000000000033760000
+
+ /* x^185408 mod p(x), x^185344 mod p(x) */
+ .octa 0x000000001c2e000000000000a1e50000
+
+ /* x^184384 mod p(x), x^184320 mod p(x) */
+ .octa 0x00000000dcc8000000000000a1a40000
+
+ /* x^183360 mod p(x), x^183296 mod p(x) */
+ .octa 0x00000000910f00000000000019a20000
+
+ /* x^182336 mod p(x), x^182272 mod p(x) */
+ .octa 0x0000000055d5000000000000f6ae0000
+
+ /* x^181312 mod p(x), x^181248 mod p(x) */
+ .octa 0x00000000c8ba000000000000a7ac0000
+
+ /* x^180288 mod p(x), x^180224 mod p(x) */
+ .octa 0x0000000031f8000000000000eea20000
+
+ /* x^179264 mod p(x), x^179200 mod p(x) */
+ .octa 0x000000001966000000000000c4d90000
+
+ /* x^178240 mod p(x), x^178176 mod p(x) */
+ .octa 0x00000000b9810000000000002b470000
+
+ /* x^177216 mod p(x), x^177152 mod p(x) */
+ .octa 0x000000008303000000000000f7cf0000
+
+ /* x^176192 mod p(x), x^176128 mod p(x) */
+ .octa 0x000000002ce500000000000035b30000
+
+ /* x^175168 mod p(x), x^175104 mod p(x) */
+ .octa 0x000000002fae0000000000000c7c0000
+
+ /* x^174144 mod p(x), x^174080 mod p(x) */
+ .octa 0x00000000f50c0000000000009edf0000
+
+ /* x^173120 mod p(x), x^173056 mod p(x) */
+ .octa 0x00000000714f00000000000004cd0000
+
+ /* x^172096 mod p(x), x^172032 mod p(x) */
+ .octa 0x00000000c161000000000000541b0000
+
+ /* x^171072 mod p(x), x^171008 mod p(x) */
+ .octa 0x0000000021c8000000000000e2700000
+
+ /* x^170048 mod p(x), x^169984 mod p(x) */
+ .octa 0x00000000b93d00000000000009a60000
+
+ /* x^169024 mod p(x), x^168960 mod p(x) */
+ .octa 0x00000000fbcf000000000000761c0000
+
+ /* x^168000 mod p(x), x^167936 mod p(x) */
+ .octa 0x0000000026350000000000009db30000
+
+ /* x^166976 mod p(x), x^166912 mod p(x) */
+ .octa 0x00000000b64f0000000000003e9f0000
+
+ /* x^165952 mod p(x), x^165888 mod p(x) */
+ .octa 0x00000000bd0e00000000000078590000
+
+ /* x^164928 mod p(x), x^164864 mod p(x) */
+ .octa 0x00000000d9360000000000008bc80000
+
+ /* x^163904 mod p(x), x^163840 mod p(x) */
+ .octa 0x000000002f140000000000008c9f0000
+
+ /* x^162880 mod p(x), x^162816 mod p(x) */
+ .octa 0x000000006a270000000000006af70000
+
+ /* x^161856 mod p(x), x^161792 mod p(x) */
+ .octa 0x000000006685000000000000e5210000
+
+ /* x^160832 mod p(x), x^160768 mod p(x) */
+ .octa 0x0000000062da00000000000008290000
+
+ /* x^159808 mod p(x), x^159744 mod p(x) */
+ .octa 0x00000000bb4b000000000000e4d00000
+
+ /* x^158784 mod p(x), x^158720 mod p(x) */
+ .octa 0x00000000d2490000000000004ae10000
+
+ /* x^157760 mod p(x), x^157696 mod p(x) */
+ .octa 0x00000000c85b00000000000000e70000
+
+ /* x^156736 mod p(x), x^156672 mod p(x) */
+ .octa 0x00000000c37a00000000000015650000
+
+ /* x^155712 mod p(x), x^155648 mod p(x) */
+ .octa 0x0000000018530000000000001c2f0000
+
+ /* x^154688 mod p(x), x^154624 mod p(x) */
+ .octa 0x00000000b46600000000000037bd0000
+
+ /* x^153664 mod p(x), x^153600 mod p(x) */
+ .octa 0x00000000439b00000000000012190000
+
+ /* x^152640 mod p(x), x^152576 mod p(x) */
+ .octa 0x00000000b1260000000000005ece0000
+
+ /* x^151616 mod p(x), x^151552 mod p(x) */
+ .octa 0x00000000d8110000000000002a5e0000
+
+ /* x^150592 mod p(x), x^150528 mod p(x) */
+ .octa 0x00000000099f00000000000052330000
+
+ /* x^149568 mod p(x), x^149504 mod p(x) */
+ .octa 0x00000000f9f9000000000000f9120000
+
+ /* x^148544 mod p(x), x^148480 mod p(x) */
+ .octa 0x000000005cc00000000000000ddc0000
+
+ /* x^147520 mod p(x), x^147456 mod p(x) */
+ .octa 0x00000000343b00000000000012200000
+
+ /* x^146496 mod p(x), x^146432 mod p(x) */
+ .octa 0x000000009222000000000000d12b0000
+
+ /* x^145472 mod p(x), x^145408 mod p(x) */
+ .octa 0x00000000d781000000000000eb2d0000
+
+ /* x^144448 mod p(x), x^144384 mod p(x) */
+ .octa 0x000000000bf400000000000058970000
+
+ /* x^143424 mod p(x), x^143360 mod p(x) */
+ .octa 0x00000000094200000000000013690000
+
+ /* x^142400 mod p(x), x^142336 mod p(x) */
+ .octa 0x00000000d55100000000000051950000
+
+ /* x^141376 mod p(x), x^141312 mod p(x) */
+ .octa 0x000000008f11000000000000954b0000
+
+ /* x^140352 mod p(x), x^140288 mod p(x) */
+ .octa 0x00000000140f000000000000b29e0000
+
+ /* x^139328 mod p(x), x^139264 mod p(x) */
+ .octa 0x00000000c6db000000000000db5d0000
+
+ /* x^138304 mod p(x), x^138240 mod p(x) */
+ .octa 0x00000000715b000000000000dfaf0000
+
+ /* x^137280 mod p(x), x^137216 mod p(x) */
+ .octa 0x000000000dea000000000000e3b60000
+
+ /* x^136256 mod p(x), x^136192 mod p(x) */
+ .octa 0x000000006f94000000000000ddaf0000
+
+ /* x^135232 mod p(x), x^135168 mod p(x) */
+ .octa 0x0000000024e1000000000000e4f70000
+
+ /* x^134208 mod p(x), x^134144 mod p(x) */
+ .octa 0x000000008810000000000000aa110000
+
+ /* x^133184 mod p(x), x^133120 mod p(x) */
+ .octa 0x0000000030c2000000000000a8e60000
+
+ /* x^132160 mod p(x), x^132096 mod p(x) */
+ .octa 0x00000000e6d0000000000000ccf30000
+
+ /* x^131136 mod p(x), x^131072 mod p(x) */
+ .octa 0x000000004da000000000000079bf0000
+
+ /* x^130112 mod p(x), x^130048 mod p(x) */
+ .octa 0x000000007759000000000000b3a30000
+
+ /* x^129088 mod p(x), x^129024 mod p(x) */
+ .octa 0x00000000597400000000000028790000
+
+ /* x^128064 mod p(x), x^128000 mod p(x) */
+ .octa 0x000000007acd000000000000b5820000
+
+ /* x^127040 mod p(x), x^126976 mod p(x) */
+ .octa 0x00000000e6e400000000000026ad0000
+
+ /* x^126016 mod p(x), x^125952 mod p(x) */
+ .octa 0x000000006d49000000000000985b0000
+
+ /* x^124992 mod p(x), x^124928 mod p(x) */
+ .octa 0x000000000f0800000000000011520000
+
+ /* x^123968 mod p(x), x^123904 mod p(x) */
+ .octa 0x000000002c7f000000000000846c0000
+
+ /* x^122944 mod p(x), x^122880 mod p(x) */
+ .octa 0x000000005ce7000000000000ae1d0000
+
+ /* x^121920 mod p(x), x^121856 mod p(x) */
+ .octa 0x00000000d4cb000000000000e21d0000
+
+ /* x^120896 mod p(x), x^120832 mod p(x) */
+ .octa 0x000000003a2300000000000019bb0000
+
+ /* x^119872 mod p(x), x^119808 mod p(x) */
+ .octa 0x000000000e1700000000000095290000
+
+ /* x^118848 mod p(x), x^118784 mod p(x) */
+ .octa 0x000000006e6400000000000050d20000
+
+ /* x^117824 mod p(x), x^117760 mod p(x) */
+ .octa 0x000000008d5c0000000000000cd10000
+
+ /* x^116800 mod p(x), x^116736 mod p(x) */
+ .octa 0x00000000ef310000000000007b570000
+
+ /* x^115776 mod p(x), x^115712 mod p(x) */
+ .octa 0x00000000645d00000000000053d60000
+
+ /* x^114752 mod p(x), x^114688 mod p(x) */
+ .octa 0x0000000018fc00000000000077510000
+
+ /* x^113728 mod p(x), x^113664 mod p(x) */
+ .octa 0x000000000cb3000000000000a7b70000
+
+ /* x^112704 mod p(x), x^112640 mod p(x) */
+ .octa 0x00000000991b000000000000d0780000
+
+ /* x^111680 mod p(x), x^111616 mod p(x) */
+ .octa 0x00000000845a000000000000be3c0000
+
+ /* x^110656 mod p(x), x^110592 mod p(x) */
+ .octa 0x00000000d3a9000000000000df020000
+
+ /* x^109632 mod p(x), x^109568 mod p(x) */
+ .octa 0x0000000017d7000000000000063e0000
+
+ /* x^108608 mod p(x), x^108544 mod p(x) */
+ .octa 0x000000007a860000000000008ab40000
+
+ /* x^107584 mod p(x), x^107520 mod p(x) */
+ .octa 0x00000000fd7c000000000000c7bd0000
+
+ /* x^106560 mod p(x), x^106496 mod p(x) */
+ .octa 0x00000000a56b000000000000efd60000
+
+ /* x^105536 mod p(x), x^105472 mod p(x) */
+ .octa 0x0000000010e400000000000071380000
+
+ /* x^104512 mod p(x), x^104448 mod p(x) */
+ .octa 0x00000000994500000000000004d30000
+
+ /* x^103488 mod p(x), x^103424 mod p(x) */
+ .octa 0x00000000b83c0000000000003b0e0000
+
+ /* x^102464 mod p(x), x^102400 mod p(x) */
+ .octa 0x00000000d6c10000000000008b020000
+
+ /* x^101440 mod p(x), x^101376 mod p(x) */
+ .octa 0x000000009efc000000000000da940000
+
+ /* x^100416 mod p(x), x^100352 mod p(x) */
+ .octa 0x000000005e87000000000000f9f70000
+
+ /* x^99392 mod p(x), x^99328 mod p(x) */
+ .octa 0x000000006c9b00000000000045e40000
+
+ /* x^98368 mod p(x), x^98304 mod p(x) */
+ .octa 0x00000000178a00000000000083940000
+
+ /* x^97344 mod p(x), x^97280 mod p(x) */
+ .octa 0x00000000f0c8000000000000f0a00000
+
+ /* x^96320 mod p(x), x^96256 mod p(x) */
+ .octa 0x00000000f699000000000000b74b0000
+
+ /* x^95296 mod p(x), x^95232 mod p(x) */
+ .octa 0x00000000316d000000000000c1cf0000
+
+ /* x^94272 mod p(x), x^94208 mod p(x) */
+ .octa 0x00000000987e00000000000072680000
+
+ /* x^93248 mod p(x), x^93184 mod p(x) */
+ .octa 0x00000000acff000000000000e0ab0000
+
+ /* x^92224 mod p(x), x^92160 mod p(x) */
+ .octa 0x00000000a1f6000000000000c5a80000
+
+ /* x^91200 mod p(x), x^91136 mod p(x) */
+ .octa 0x0000000061bd000000000000cf690000
+
+ /* x^90176 mod p(x), x^90112 mod p(x) */
+ .octa 0x00000000c9f2000000000000cbcc0000
+
+ /* x^89152 mod p(x), x^89088 mod p(x) */
+ .octa 0x000000005a33000000000000de050000
+
+ /* x^88128 mod p(x), x^88064 mod p(x) */
+ .octa 0x00000000e416000000000000ccd70000
+
+ /* x^87104 mod p(x), x^87040 mod p(x) */
+ .octa 0x0000000058930000000000002f670000
+
+ /* x^86080 mod p(x), x^86016 mod p(x) */
+ .octa 0x00000000a9d3000000000000152f0000
+
+ /* x^85056 mod p(x), x^84992 mod p(x) */
+ .octa 0x00000000c114000000000000ecc20000
+
+ /* x^84032 mod p(x), x^83968 mod p(x) */
+ .octa 0x00000000b9270000000000007c890000
+
+ /* x^83008 mod p(x), x^82944 mod p(x) */
+ .octa 0x000000002e6000000000000006ee0000
+
+ /* x^81984 mod p(x), x^81920 mod p(x) */
+ .octa 0x00000000dfc600000000000009100000
+
+ /* x^80960 mod p(x), x^80896 mod p(x) */
+ .octa 0x000000004911000000000000ad4e0000
+
+ /* x^79936 mod p(x), x^79872 mod p(x) */
+ .octa 0x00000000ae1b000000000000b04d0000
+
+ /* x^78912 mod p(x), x^78848 mod p(x) */
+ .octa 0x0000000005fa000000000000e9900000
+
+ /* x^77888 mod p(x), x^77824 mod p(x) */
+ .octa 0x0000000004a1000000000000cc6f0000
+
+ /* x^76864 mod p(x), x^76800 mod p(x) */
+ .octa 0x00000000af73000000000000ed110000
+
+ /* x^75840 mod p(x), x^75776 mod p(x) */
+ .octa 0x0000000082530000000000008f7e0000
+
+ /* x^74816 mod p(x), x^74752 mod p(x) */
+ .octa 0x00000000cfdc000000000000594f0000
+
+ /* x^73792 mod p(x), x^73728 mod p(x) */
+ .octa 0x00000000a6b6000000000000a8750000
+
+ /* x^72768 mod p(x), x^72704 mod p(x) */
+ .octa 0x00000000fd76000000000000aa0c0000
+
+ /* x^71744 mod p(x), x^71680 mod p(x) */
+ .octa 0x0000000006f500000000000071db0000
+
+ /* x^70720 mod p(x), x^70656 mod p(x) */
+ .octa 0x0000000037ca000000000000ab0c0000
+
+ /* x^69696 mod p(x), x^69632 mod p(x) */
+ .octa 0x00000000d7ab000000000000b7a00000
+
+ /* x^68672 mod p(x), x^68608 mod p(x) */
+ .octa 0x00000000440800000000000090d30000
+
+ /* x^67648 mod p(x), x^67584 mod p(x) */
+ .octa 0x00000000186100000000000054730000
+
+ /* x^66624 mod p(x), x^66560 mod p(x) */
+ .octa 0x000000007368000000000000a3a20000
+
+ /* x^65600 mod p(x), x^65536 mod p(x) */
+ .octa 0x0000000026d0000000000000f9040000
+
+ /* x^64576 mod p(x), x^64512 mod p(x) */
+ .octa 0x00000000fe770000000000009c0a0000
+
+ /* x^63552 mod p(x), x^63488 mod p(x) */
+ .octa 0x000000002cba000000000000d1e70000
+
+ /* x^62528 mod p(x), x^62464 mod p(x) */
+ .octa 0x00000000f8bd0000000000005ac10000
+
+ /* x^61504 mod p(x), x^61440 mod p(x) */
+ .octa 0x000000007372000000000000d68d0000
+
+ /* x^60480 mod p(x), x^60416 mod p(x) */
+ .octa 0x00000000f37f00000000000089f60000
+
+ /* x^59456 mod p(x), x^59392 mod p(x) */
+ .octa 0x00000000078400000000000008a90000
+
+ /* x^58432 mod p(x), x^58368 mod p(x) */
+ .octa 0x00000000d3e400000000000042360000
+
+ /* x^57408 mod p(x), x^57344 mod p(x) */
+ .octa 0x00000000eba800000000000092d50000
+
+ /* x^56384 mod p(x), x^56320 mod p(x) */
+ .octa 0x00000000afbe000000000000b4d50000
+
+ /* x^55360 mod p(x), x^55296 mod p(x) */
+ .octa 0x00000000d8ca000000000000c9060000
+
+ /* x^54336 mod p(x), x^54272 mod p(x) */
+ .octa 0x00000000c2d00000000000008f4f0000
+
+ /* x^53312 mod p(x), x^53248 mod p(x) */
+ .octa 0x00000000373200000000000028690000
+
+ /* x^52288 mod p(x), x^52224 mod p(x) */
+ .octa 0x0000000046ae000000000000c3b30000
+
+ /* x^51264 mod p(x), x^51200 mod p(x) */
+ .octa 0x00000000b243000000000000f8700000
+
+ /* x^50240 mod p(x), x^50176 mod p(x) */
+ .octa 0x00000000f7f500000000000029eb0000
+
+ /* x^49216 mod p(x), x^49152 mod p(x) */
+ .octa 0x000000000c7e000000000000fe730000
+
+ /* x^48192 mod p(x), x^48128 mod p(x) */
+ .octa 0x00000000c38200000000000096000000
+
+ /* x^47168 mod p(x), x^47104 mod p(x) */
+ .octa 0x000000008956000000000000683c0000
+
+ /* x^46144 mod p(x), x^46080 mod p(x) */
+ .octa 0x00000000422d0000000000005f1e0000
+
+ /* x^45120 mod p(x), x^45056 mod p(x) */
+ .octa 0x00000000ac0f0000000000006f810000
+
+ /* x^44096 mod p(x), x^44032 mod p(x) */
+ .octa 0x00000000ce30000000000000031f0000
+
+ /* x^43072 mod p(x), x^43008 mod p(x) */
+ .octa 0x000000003d43000000000000455a0000
+
+ /* x^42048 mod p(x), x^41984 mod p(x) */
+ .octa 0x000000007ebe000000000000a6050000
+
+ /* x^41024 mod p(x), x^40960 mod p(x) */
+ .octa 0x00000000976e00000000000077eb0000
+
+ /* x^40000 mod p(x), x^39936 mod p(x) */
+ .octa 0x000000000872000000000000389c0000
+
+ /* x^38976 mod p(x), x^38912 mod p(x) */
+ .octa 0x000000008979000000000000c7b20000
+
+ /* x^37952 mod p(x), x^37888 mod p(x) */
+ .octa 0x000000005c1e0000000000001d870000
+
+ /* x^36928 mod p(x), x^36864 mod p(x) */
+ .octa 0x00000000aebb00000000000045810000
+
+ /* x^35904 mod p(x), x^35840 mod p(x) */
+ .octa 0x000000004f7e0000000000006d4a0000
+
+ /* x^34880 mod p(x), x^34816 mod p(x) */
+ .octa 0x00000000ea98000000000000b9200000
+
+ /* x^33856 mod p(x), x^33792 mod p(x) */
+ .octa 0x00000000f39600000000000022f20000
+
+ /* x^32832 mod p(x), x^32768 mod p(x) */
+ .octa 0x000000000bc500000000000041ca0000
+
+ /* x^31808 mod p(x), x^31744 mod p(x) */
+ .octa 0x00000000786400000000000078500000
+
+ /* x^30784 mod p(x), x^30720 mod p(x) */
+ .octa 0x00000000be970000000000009e7e0000
+
+ /* x^29760 mod p(x), x^29696 mod p(x) */
+ .octa 0x00000000dd6d000000000000a53c0000
+
+ /* x^28736 mod p(x), x^28672 mod p(x) */
+ .octa 0x000000004c3f00000000000039340000
+
+ /* x^27712 mod p(x), x^27648 mod p(x) */
+ .octa 0x0000000093a4000000000000b58e0000
+
+ /* x^26688 mod p(x), x^26624 mod p(x) */
+ .octa 0x0000000050fb00000000000062d40000
+
+ /* x^25664 mod p(x), x^25600 mod p(x) */
+ .octa 0x00000000f505000000000000a26f0000
+
+ /* x^24640 mod p(x), x^24576 mod p(x) */
+ .octa 0x0000000064f900000000000065e60000
+
+ /* x^23616 mod p(x), x^23552 mod p(x) */
+ .octa 0x00000000e8c2000000000000aad90000
+
+ /* x^22592 mod p(x), x^22528 mod p(x) */
+ .octa 0x00000000720b000000000000a3b00000
+
+ /* x^21568 mod p(x), x^21504 mod p(x) */
+ .octa 0x00000000e992000000000000d2680000
+
+ /* x^20544 mod p(x), x^20480 mod p(x) */
+ .octa 0x000000009132000000000000cf4c0000
+
+ /* x^19520 mod p(x), x^19456 mod p(x) */
+ .octa 0x00000000608a00000000000076610000
+
+ /* x^18496 mod p(x), x^18432 mod p(x) */
+ .octa 0x000000009948000000000000fb9f0000
+
+ /* x^17472 mod p(x), x^17408 mod p(x) */
+ .octa 0x00000000173000000000000003770000
+
+ /* x^16448 mod p(x), x^16384 mod p(x) */
+ .octa 0x000000006fe300000000000004880000
+
+ /* x^15424 mod p(x), x^15360 mod p(x) */
+ .octa 0x00000000e15300000000000056a70000
+
+ /* x^14400 mod p(x), x^14336 mod p(x) */
+ .octa 0x0000000092d60000000000009dfd0000
+
+ /* x^13376 mod p(x), x^13312 mod p(x) */
+ .octa 0x0000000002fd00000000000074c80000
+
+ /* x^12352 mod p(x), x^12288 mod p(x) */
+ .octa 0x00000000c78b000000000000a3ec0000
+
+ /* x^11328 mod p(x), x^11264 mod p(x) */
+ .octa 0x000000009262000000000000b3530000
+
+ /* x^10304 mod p(x), x^10240 mod p(x) */
+ .octa 0x0000000084f200000000000047bf0000
+
+ /* x^9280 mod p(x), x^9216 mod p(x) */
+ .octa 0x0000000067ee000000000000e97c0000
+
+ /* x^8256 mod p(x), x^8192 mod p(x) */
+ .octa 0x00000000535b00000000000091e10000
+
+ /* x^7232 mod p(x), x^7168 mod p(x) */
+ .octa 0x000000007ebb00000000000055060000
+
+ /* x^6208 mod p(x), x^6144 mod p(x) */
+ .octa 0x00000000c6a1000000000000fd360000
+
+ /* x^5184 mod p(x), x^5120 mod p(x) */
+ .octa 0x000000001be500000000000055860000
+
+ /* x^4160 mod p(x), x^4096 mod p(x) */
+ .octa 0x00000000ae0e0000000000005bd00000
+
+ /* x^3136 mod p(x), x^3072 mod p(x) */
+ .octa 0x0000000022040000000000008db20000
+
+ /* x^2112 mod p(x), x^2048 mod p(x) */
+ .octa 0x00000000c9eb000000000000efe20000
+
+ /* x^1088 mod p(x), x^1024 mod p(x) */
+ .octa 0x0000000039b400000000000051d10000
+
+.short_constants:
+
+ /* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */
+ /* x^2048 mod p(x), x^2016 mod p(x), x^1984 mod p(x), x^1952 mod p(x) */
+ .octa 0xefe20000dccf00009440000033590000
+
+ /* x^1920 mod p(x), x^1888 mod p(x), x^1856 mod p(x), x^1824 mod p(x) */
+ .octa 0xee6300002f3f000062180000e0ed0000
+
+ /* x^1792 mod p(x), x^1760 mod p(x), x^1728 mod p(x), x^1696 mod p(x) */
+ .octa 0xcf5f000017ef0000ccbe000023d30000
+
+ /* x^1664 mod p(x), x^1632 mod p(x), x^1600 mod p(x), x^1568 mod p(x) */
+ .octa 0x6d0c0000a30e00000920000042630000
+
+ /* x^1536 mod p(x), x^1504 mod p(x), x^1472 mod p(x), x^1440 mod p(x) */
+ .octa 0x21d30000932b0000a7a00000efcc0000
+
+ /* x^1408 mod p(x), x^1376 mod p(x), x^1344 mod p(x), x^1312 mod p(x) */
+ .octa 0x10be00000b310000666f00000d1c0000
+
+ /* x^1280 mod p(x), x^1248 mod p(x), x^1216 mod p(x), x^1184 mod p(x) */
+ .octa 0x1f240000ce9e0000caad0000589e0000
+
+ /* x^1152 mod p(x), x^1120 mod p(x), x^1088 mod p(x), x^1056 mod p(x) */
+ .octa 0x29610000d02b000039b400007cf50000
+
+ /* x^1024 mod p(x), x^992 mod p(x), x^960 mod p(x), x^928 mod p(x) */
+ .octa 0x51d100009d9d00003c0e0000bfd60000
+
+ /* x^896 mod p(x), x^864 mod p(x), x^832 mod p(x), x^800 mod p(x) */
+ .octa 0xda390000ceae000013830000713c0000
+
+ /* x^768 mod p(x), x^736 mod p(x), x^704 mod p(x), x^672 mod p(x) */
+ .octa 0xb67800001e16000085c0000080a60000
+
+ /* x^640 mod p(x), x^608 mod p(x), x^576 mod p(x), x^544 mod p(x) */
+ .octa 0x0db40000f7f90000371d0000e6580000
+
+ /* x^512 mod p(x), x^480 mod p(x), x^448 mod p(x), x^416 mod p(x) */
+ .octa 0x87e70000044c0000aadb0000a4970000
+
+ /* x^384 mod p(x), x^352 mod p(x), x^320 mod p(x), x^288 mod p(x) */
+ .octa 0x1f990000ad180000d8b30000e7b50000
+
+ /* x^256 mod p(x), x^224 mod p(x), x^192 mod p(x), x^160 mod p(x) */
+ .octa 0xbe6c00006ee300004c1a000006df0000
+
+ /* x^128 mod p(x), x^96 mod p(x), x^64 mod p(x), x^32 mod p(x) */
+ .octa 0xfb0b00002d560000136800008bb70000
+
+
+.barrett_constants:
+ /* Barrett constant m - (4^32)/n */
+ .octa 0x000000000000000000000001f65a57f8 /* x^64 div p(x) */
+ /* Barrett constant n */
+ .octa 0x0000000000000000000000018bb70000
+
+#define CRC_FUNCTION_NAME __crct10dif_vpmsum
+#include "crc32-vpmsum_core.S"
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
new file mode 100644
index 000000000000..02ea277863d1
--- /dev/null
+++ b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
@@ -0,0 +1,128 @@
+/*
+ * Calculate a CRC T10-DIF with vpmsum acceleration
+ *
+ * Copyright 2017, Daniel Axtens, IBM Corporation.
+ * [based on crc32c-vpmsum_glue.c]
+ *
+ * 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/crc-t10dif.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/switch_to.h>
+
+#define VMX_ALIGN 16
+#define VMX_ALIGN_MASK (VMX_ALIGN-1)
+
+#define VECTOR_BREAKPOINT 64
+
+u32 __crct10dif_vpmsum(u32 crc, unsigned char const *p, size_t len);
+
+static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len)
+{
+ unsigned int prealign;
+ unsigned int tail;
+ u32 crc = crci;
+
+ if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt())
+ return crc_t10dif_generic(crc, p, len);
+
+ if ((unsigned long)p & VMX_ALIGN_MASK) {
+ prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
+ crc = crc_t10dif_generic(crc, p, prealign);
+ len -= prealign;
+ p += prealign;
+ }
+
+ if (len & ~VMX_ALIGN_MASK) {
+ crc <<= 16;
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_altivec();
+ crc = __crct10dif_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+ disable_kernel_altivec();
+ pagefault_enable();
+ preempt_enable();
+ crc >>= 16;
+ }
+
+ tail = len & VMX_ALIGN_MASK;
+ if (tail) {
+ p += len & ~VMX_ALIGN_MASK;
+ crc = crc_t10dif_generic(crc, p, tail);
+ }
+
+ return crc & 0xffff;
+}
+
+static int crct10dif_vpmsum_init(struct shash_desc *desc)
+{
+ u16 *crc = shash_desc_ctx(desc);
+
+ *crc = 0;
+ return 0;
+}
+
+static int crct10dif_vpmsum_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ u16 *crc = shash_desc_ctx(desc);
+
+ *crc = crct10dif_vpmsum(*crc, data, length);
+
+ return 0;
+}
+
+
+static int crct10dif_vpmsum_final(struct shash_desc *desc, u8 *out)
+{
+ u16 *crcp = shash_desc_ctx(desc);
+
+ *(u16 *)out = *crcp;
+ return 0;
+}
+
+static struct shash_alg alg = {
+ .init = crct10dif_vpmsum_init,
+ .update = crct10dif_vpmsum_update,
+ .final = crct10dif_vpmsum_final,
+ .descsize = CRC_T10DIF_DIGEST_SIZE,
+ .digestsize = CRC_T10DIF_DIGEST_SIZE,
+ .base = {
+ .cra_name = "crct10dif",
+ .cra_driver_name = "crct10dif-vpmsum",
+ .cra_priority = 200,
+ .cra_blocksize = CRC_T10DIF_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init crct10dif_vpmsum_mod_init(void)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ return crypto_register_shash(&alg);
+}
+
+static void __exit crct10dif_vpmsum_mod_fini(void)
+{
+ crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crct10dif_vpmsum_mod_init);
+module_exit(crct10dif_vpmsum_mod_fini);
+
+MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
+MODULE_DESCRIPTION("CRCT10DIF using vector polynomial multiply-sum instructions");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-vpmsum");
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 3a39283333c3..f2c562a0a427 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -85,12 +85,12 @@
} \
} while (0)
-#define __WARN_TAINT(taint) do { \
+#define __WARN_FLAGS(flags) do { \
__asm__ __volatile__( \
"1: twi 31,0,0\n" \
_EMIT_BUG_ENTRY \
: : "i" (__FILE__), "i" (__LINE__), \
- "i" (BUGFLAG_TAINT(taint)), \
+ "i" (BUGFLAG_WARNING|(flags)), \
"i" (sizeof(struct bug_entry))); \
} while (0)
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 14752eee3d0c..ed3beadd2cc5 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -236,9 +236,9 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
mtctr reg; \
bctr
-#define BRANCH_LINK_TO_FAR(reg, label) \
- __LOAD_FAR_HANDLER(reg, label); \
- mtctr reg; \
+#define BRANCH_LINK_TO_FAR(label) \
+ __LOAD_FAR_HANDLER(r12, label); \
+ mtctr r12; \
bctrl
/*
@@ -265,7 +265,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
#define BRANCH_TO_COMMON(reg, label) \
b label
-#define BRANCH_LINK_TO_FAR(reg, label) \
+#define BRANCH_LINK_TO_FAR(label) \
bl label
#define BRANCH_TO_KVM(reg, label) \
diff --git a/arch/powerpc/include/asm/extable.h b/arch/powerpc/include/asm/extable.h
new file mode 100644
index 000000000000..07cc45cd86d9
--- /dev/null
+++ b/arch/powerpc/include/asm/extable.h
@@ -0,0 +1,29 @@
+#ifndef _ARCH_POWERPC_EXTABLE_H
+#define _ARCH_POWERPC_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative addresses: the first is
+ * the address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out what
+ * to do.
+ *
+ * All the routines below use bits of fixup code that are out of line with the
+ * main instruction path. This means when everything is well, we don't even
+ * have to jump over them. Further, they do not intrude on our cache or tlb
+ * entries.
+ */
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+struct exception_table_entry {
+ int insn;
+ int fixup;
+};
+
+static inline unsigned long extable_fixup(const struct exception_table_entry *x)
+{
+ return (unsigned long)&x->fixup + x->fixup;
+}
+
+#endif
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b9e3f0aca261..ecf9885ab660 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -163,11 +163,5 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
/* by default, allow everything */
return true;
}
-
-static inline bool arch_pte_access_permitted(pte_t pte, bool write)
-{
- /* by default, allow everything */
- return true;
-}
#endif /* __KERNEL__ */
#endif /* __ASM_POWERPC_MMU_CONTEXT_H */
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 0e6add3187bc..5c0d8a8cdae5 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -1,18 +1,11 @@
#ifndef _ARCH_POWERPC_UACCESS_H
#define _ARCH_POWERPC_UACCESS_H
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-#include <linux/errno.h>
#include <asm/asm-compat.h>
#include <asm/ppc_asm.h>
#include <asm/processor.h>
#include <asm/page.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
+#include <asm/extable.h>
/*
* The fs value determines whether argument validity checking should be
@@ -64,31 +57,6 @@
__access_ok((__force unsigned long)(addr), (size), get_fs()))
/*
- * The exception table consists of pairs of relative addresses: the first is
- * the address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out what
- * to do.
- *
- * All the routines below use bits of fixup code that are out of line with the
- * main instruction path. This means when everything is well, we don't even
- * have to jump over them. Further, they do not intrude on our cache or tlb
- * entries.
- */
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-struct exception_table_entry {
- int insn;
- int fixup;
-};
-
-static inline unsigned long extable_fixup(const struct exception_table_entry *x)
-{
- return (unsigned long)&x->fixup + x->fixup;
-}
-
-/*
* These are the main single-value transfer routines. They automatically
* use the right size if we just have the right pointer type.
*
@@ -301,42 +269,19 @@ extern unsigned long __copy_tofrom_user(void __user *to,
#ifndef __powerpc64__
-static inline unsigned long copy_from_user(void *to,
- const void __user *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_READ, from, n))) {
- check_object_size(to, n, false);
- return __copy_tofrom_user((__force void __user *)to, from, n);
- }
- memset(to, 0, n);
- return n;
-}
-
-static inline unsigned long copy_to_user(void __user *to,
- const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n)) {
- check_object_size(from, n, true);
- return __copy_tofrom_user(to, (__force void __user *)from, n);
- }
- return n;
-}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
#else /* __powerpc64__ */
-#define __copy_in_user(to, from, size) \
- __copy_tofrom_user((to), (from), (size))
-
-extern unsigned long copy_from_user(void *to, const void __user *from,
- unsigned long n);
-extern unsigned long copy_to_user(void __user *to, const void *from,
- unsigned long n);
-extern unsigned long copy_in_user(void __user *to, const void __user *from,
- unsigned long n);
-
+static inline unsigned long
+raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
+{
+ return __copy_tofrom_user(to, from, n);
+}
#endif /* __powerpc64__ */
-static inline unsigned long __copy_from_user_inatomic(void *to,
+static inline unsigned long raw_copy_from_user(void *to,
const void __user *from, unsigned long n)
{
if (__builtin_constant_p(n) && (n <= 8)) {
@@ -360,12 +305,10 @@ static inline unsigned long __copy_from_user_inatomic(void *to,
return 0;
}
- check_object_size(to, n, false);
-
return __copy_tofrom_user((__force void __user *)to, from, n);
}
-static inline unsigned long __copy_to_user_inatomic(void __user *to,
+static inline unsigned long raw_copy_to_user(void __user *to,
const void *from, unsigned long n)
{
if (__builtin_constant_p(n) && (n <= 8)) {
@@ -389,25 +332,9 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to,
return 0;
}
- check_object_size(from, n, true);
-
return __copy_tofrom_user(to, (__force const void __user *)from, n);
}
-static inline unsigned long __copy_from_user(void *to,
- const void __user *from, unsigned long size)
-{
- might_fault();
- return __copy_from_user_inatomic(to, from, size);
-}
-
-static inline unsigned long __copy_to_user(void __user *to,
- const void *from, unsigned long size)
-{
- might_fault();
- return __copy_to_user_inatomic(to, from, size);
-}
-
extern unsigned long __clear_user(void __user *addr, unsigned long size);
static inline unsigned long clear_user(void __user *addr, unsigned long size)
@@ -422,7 +349,4 @@ extern long strncpy_from_user(char *dst, const char __user *src, long count);
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
#endif /* _ARCH_POWERPC_UACCESS_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 44583a52f882..58e2ec0310fc 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -99,4 +99,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index cbc7c42cdb74..ec7a8b099dd9 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -807,14 +807,25 @@ int fix_alignment(struct pt_regs *regs)
nb = aligninfo[instr].len;
flags = aligninfo[instr].flags;
- /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
- if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
- nb = 8;
- flags = LD+SW;
- } else if (IS_XFORM(instruction) &&
- ((instruction >> 1) & 0x3ff) == 660) {
- nb = 8;
- flags = ST+SW;
+ /*
+ * Handle some cases which give overlaps in the DSISR values.
+ */
+ if (IS_XFORM(instruction)) {
+ switch (get_xop(instruction)) {
+ case 532: /* ldbrx */
+ nb = 8;
+ flags = LD+SW;
+ break;
+ case 660: /* stdbrx */
+ nb = 8;
+ flags = ST+SW;
+ break;
+ case 20: /* lwarx */
+ case 84: /* ldarx */
+ case 116: /* lharx */
+ case 276: /* lqarx */
+ return 0; /* not emulated ever */
+ }
}
/* Byteswap little endian loads and stores */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 6432d4bf08c8..767ef6d68c9e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -689,7 +689,7 @@ resume_kernel:
addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */
- lwz r3,GPR1(r1)
+ ld r3,GPR1(r1)
subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */
mr r4,r1 /* src: current exception frame */
mr r1,r3 /* Reroute the trampoline frame to r1 */
@@ -703,8 +703,8 @@ resume_kernel:
addi r6,r6,8
bdnz 2b
- /* Do real store operation to complete stwu */
- lwz r5,GPR1(r1)
+ /* Do real store operation to complete stdu */
+ ld r5,GPR1(r1)
std r8,0(r5)
/* Clear _TIF_EMULATE_STACK_STORE flag */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 857bf7c5b946..6353019966e6 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -982,7 +982,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early)
EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN)
EXCEPTION_PROLOG_COMMON_3(0xe60)
addi r3,r1,STACK_FRAME_OVERHEAD
- BRANCH_LINK_TO_FAR(r4, hmi_exception_realmode)
+ BRANCH_LINK_TO_FAR(hmi_exception_realmode) /* Function call ABI */
/* Windup the stack. */
/* Move original HSRR0 and HSRR1 into the respective regs */
ld r9,_MSR(r1)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 995728736677..6fd08219248d 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -449,9 +449,23 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
_GLOBAL(pnv_wakeup_tb_loss)
ld r1,PACAR1(r13)
/*
- * Before entering any idle state, the NVGPRs are saved in the stack
- * and they are restored before switching to the process context. Hence
- * until they are restored, they are free to be used.
+ * Before entering any idle state, the NVGPRs are saved in the stack.
+ * If there was a state loss, or PACA_NAPSTATELOST was set, then the
+ * NVGPRs are restored. If we are here, it is likely that state is lost,
+ * but not guaranteed -- neither ISA207 nor ISA300 tests to reach
+ * here are the same as the test to restore NVGPRS:
+ * PACA_THREAD_IDLE_STATE test for ISA207, PSSCR test for ISA300,
+ * and SRR1 test for restoring NVGPRs.
+ *
+ * We are about to clobber NVGPRs now, so set NAPSTATELOST to
+ * guarantee they will always be restored. This might be tightened
+ * with careful reading of specs (particularly for ISA300) but this
+ * is already a slow wakeup path and it's simpler to be safe.
+ */
+ li r0,1
+ stb r0,PACA_NAPSTATELOST(r13)
+
+ /*
*
* Save SRR1 and LR in NVGPRs as they might be clobbered in
* opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index ae179cb1bb3c..c119044cad0d 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -67,7 +67,7 @@ PPC64_CACHES:
* flush all bytes from start through stop-1 inclusive
*/
-_GLOBAL(flush_icache_range)
+_GLOBAL_TOC(flush_icache_range)
BEGIN_FTR_SECTION
PURGE_PREFETCHED_INS
blr
@@ -120,7 +120,7 @@ EXPORT_SYMBOL(flush_icache_range)
*
* flush all bytes from start to stop-1 inclusive
*/
-_GLOBAL(flush_dcache_range)
+_GLOBAL_TOC(flush_dcache_range)
/*
* Flush the data cache to memory
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index d5e2b8309939..eae61b044e9e 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -389,51 +389,40 @@ static int nvram_pstore_open(struct pstore_info *psi)
/**
* nvram_pstore_write - pstore write callback for nvram
- * @type: Type of message logged
- * @reason: reason behind dump (oops/panic)
- * @id: identifier to indicate the write performed
- * @part: pstore writes data to registered buffer in parts,
- * part number will indicate the same.
- * @count: Indicates oops count
- * @compressed: Flag to indicate the log is compressed
- * @size: number of bytes written to the registered buffer
- * @psi: registered pstore_info structure
+ * @record: pstore record to write, with @id to be set
*
* Called by pstore_dump() when an oops or panic report is logged in the
* printk buffer.
* Returns 0 on successful write.
*/
-static int nvram_pstore_write(enum pstore_type_id type,
- enum kmsg_dump_reason reason,
- u64 *id, unsigned int part, int count,
- bool compressed, size_t size,
- struct pstore_info *psi)
+static int nvram_pstore_write(struct pstore_record *record)
{
int rc;
unsigned int err_type = ERR_TYPE_KERNEL_PANIC;
struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf;
/* part 1 has the recent messages from printk buffer */
- if (part > 1 || (type != PSTORE_TYPE_DMESG))
+ if (record->part > 1 || (record->type != PSTORE_TYPE_DMESG))
return -1;
if (clobbering_unread_rtas_event())
return -1;
oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
- oops_hdr->report_length = cpu_to_be16(size);
+ oops_hdr->report_length = cpu_to_be16(record->size);
oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
- if (compressed)
+ if (record->compressed)
err_type = ERR_TYPE_KERNEL_PANIC_GZ;
rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
- (int) (sizeof(*oops_hdr) + size), err_type, count);
+ (int) (sizeof(*oops_hdr) + record->size), err_type,
+ record->count);
if (rc != 0)
return rc;
- *id = part;
+ record->id = record->part;
return 0;
}
@@ -442,10 +431,7 @@ static int nvram_pstore_write(enum pstore_type_id type,
* Returns the length of the data we read from each partition.
* Returns 0 if we've been called before.
*/
-static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
- int *count, struct timespec *time, char **buf,
- bool *compressed, ssize_t *ecc_notice_size,
- struct pstore_info *psi)
+static ssize_t nvram_pstore_read(struct pstore_record *record)
{
struct oops_log_info *oops_hdr;
unsigned int err_type, id_no, size = 0;
@@ -459,40 +445,40 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
switch (nvram_type_ids[read_type]) {
case PSTORE_TYPE_DMESG:
part = &oops_log_partition;
- *type = PSTORE_TYPE_DMESG;
+ record->type = PSTORE_TYPE_DMESG;
break;
case PSTORE_TYPE_PPC_COMMON:
sig = NVRAM_SIG_SYS;
part = &common_partition;
- *type = PSTORE_TYPE_PPC_COMMON;
- *id = PSTORE_TYPE_PPC_COMMON;
- time->tv_sec = 0;
- time->tv_nsec = 0;
+ record->type = PSTORE_TYPE_PPC_COMMON;
+ record->id = PSTORE_TYPE_PPC_COMMON;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
break;
#ifdef CONFIG_PPC_PSERIES
case PSTORE_TYPE_PPC_RTAS:
part = &rtas_log_partition;
- *type = PSTORE_TYPE_PPC_RTAS;
- time->tv_sec = last_rtas_event;
- time->tv_nsec = 0;
+ record->type = PSTORE_TYPE_PPC_RTAS;
+ record->time.tv_sec = last_rtas_event;
+ record->time.tv_nsec = 0;
break;
case PSTORE_TYPE_PPC_OF:
sig = NVRAM_SIG_OF;
part = &of_config_partition;
- *type = PSTORE_TYPE_PPC_OF;
- *id = PSTORE_TYPE_PPC_OF;
- time->tv_sec = 0;
- time->tv_nsec = 0;
+ record->type = PSTORE_TYPE_PPC_OF;
+ record->id = PSTORE_TYPE_PPC_OF;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
break;
#endif
#ifdef CONFIG_PPC_POWERNV
case PSTORE_TYPE_PPC_OPAL:
sig = NVRAM_SIG_FW;
part = &skiboot_partition;
- *type = PSTORE_TYPE_PPC_OPAL;
- *id = PSTORE_TYPE_PPC_OPAL;
- time->tv_sec = 0;
- time->tv_nsec = 0;
+ record->type = PSTORE_TYPE_PPC_OPAL;
+ record->id = PSTORE_TYPE_PPC_OPAL;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
break;
#endif
default:
@@ -520,10 +506,10 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
return 0;
}
- *count = 0;
+ record->count = 0;
if (part->os_partition)
- *id = id_no;
+ record->id = id_no;
if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
size_t length, hdr_size;
@@ -533,34 +519,35 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
/* Old format oops header had 2-byte record size */
hdr_size = sizeof(u16);
length = be16_to_cpu(oops_hdr->version);
- time->tv_sec = 0;
- time->tv_nsec = 0;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
} else {
hdr_size = sizeof(*oops_hdr);
length = be16_to_cpu(oops_hdr->report_length);
- time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
- time->tv_nsec = 0;
+ record->time.tv_sec = be64_to_cpu(oops_hdr->timestamp);
+ record->time.tv_nsec = 0;
}
- *buf = kmemdup(buff + hdr_size, length, GFP_KERNEL);
+ record->buf = kmemdup(buff + hdr_size, length, GFP_KERNEL);
kfree(buff);
- if (*buf == NULL)
+ if (record->buf == NULL)
return -ENOMEM;
- *ecc_notice_size = 0;
+ record->ecc_notice_size = 0;
if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
- *compressed = true;
+ record->compressed = true;
else
- *compressed = false;
+ record->compressed = false;
return length;
}
- *buf = buff;
+ record->buf = buff;
return part->size;
}
static struct pstore_info nvram_pstore_info = {
.owner = THIS_MODULE,
.name = "nvram",
+ .flags = PSTORE_FLAGS_DMESG,
.open = nvram_pstore_open,
.read = nvram_pstore_read,
.write = nvram_pstore_write,
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 9cfaa8b69b5f..f997154dfc41 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -236,6 +236,15 @@ static void cpu_ready_for_interrupts(void)
mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
}
+ /*
+ * Fixup HFSCR:TM based on CPU features. The bit is set by our
+ * early asm init because at that point we haven't updated our
+ * CPU features from firmware and device-tree. Here we have,
+ * so let's do it.
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP))
+ mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
+
/* Set IR and DR in PACA MSR */
get_paca()->kernel_msr = MSR_KERNEL;
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 46f89e66a273..d68ed1f004a3 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -787,24 +787,21 @@ static struct sched_domain_topology_level powerpc_topology[] = {
{ NULL, },
};
-void __init smp_cpus_done(unsigned int max_cpus)
+static __init long smp_setup_cpu_workfn(void *data __always_unused)
{
- cpumask_var_t old_mask;
+ smp_ops->setup_cpu(boot_cpuid);
+ return 0;
+}
- /* We want the setup_cpu() here to be called from CPU 0, but our
- * init thread may have been "borrowed" by another CPU in the meantime
- * se we pin us down to CPU 0 for a short while
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+ /*
+ * We want the setup_cpu() here to be called on the boot CPU, but
+ * init might run on any CPU, so make sure it's invoked on the boot
+ * CPU.
*/
- alloc_cpumask_var(&old_mask, GFP_NOWAIT);
- cpumask_copy(old_mask, &current->cpus_allowed);
- set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
-
if (smp_ops && smp_ops->setup_cpu)
- smp_ops->setup_cpu(boot_cpuid);
-
- set_cpus_allowed_ptr(current, old_mask);
-
- free_cpumask_var(old_mask);
+ work_on_cpu_safe(boot_cpuid, smp_setup_cpu_workfn, NULL);
if (smp_ops && smp_ops->bringup_done)
smp_ops->bringup_done();
@@ -812,7 +809,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
dump_numa_cpu_topology();
set_sched_topology(powerpc_topology);
-
}
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 07b90725855e..2b33cfaac7b8 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -995,8 +995,10 @@ static void __init init_decrementer_clockevent(void)
decrementer_clockevent.max_delta_ns =
clockevent_delta2ns(decrementer_max, &decrementer_clockevent);
+ decrementer_clockevent.max_delta_ticks = decrementer_max;
decrementer_clockevent.min_delta_ns =
clockevent_delta2ns(2, &decrementer_clockevent);
+ decrementer_clockevent.min_delta_ticks = 2;
register_decrementer_clockevent(cpu);
}
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 7394b770ae1f..1c24c894c908 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -312,6 +312,8 @@ SECTIONS
NOSAVE_DATA
}
+ BUG_TABLE
+
. = ALIGN(PAGE_SIZE);
_edata = .;
PROVIDE32 (edata = .);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 8c68145ba1bd..710e491206ed 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1487,6 +1487,10 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
/* start new resize */
resize = kzalloc(sizeof(*resize), GFP_KERNEL);
+ if (!resize) {
+ ret = -ENOMEM;
+ goto out;
+ }
resize->order = shift;
resize->kvm = kvm;
INIT_WORK(&resize->work, resize_hpt_prepare_work);
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 2b5e09020cfe..ed7dfce331e0 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -14,7 +14,7 @@ obj-y += string.o alloc.o crtsavres.o code-patching.o \
obj-$(CONFIG_PPC32) += div64.o copy_32.o
-obj64-y += copypage_64.o copyuser_64.o usercopy_64.o mem_64.o hweight_64.o \
+obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
copyuser_power7.o string_64.o copypage_power7.o memcpy_power7.o \
memcpy_64.o memcmp_64.o
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index ff0d894d7ff9..8aedbb5f4b86 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -477,18 +477,6 @@ _GLOBAL(__copy_tofrom_user)
bdnz 130b
/* then clear out the destination: r3 bytes starting at 4(r6) */
132: mfctr r3
- srwi. r0,r3,2
- li r9,0
- mtctr r0
- beq 113f
-112: stwu r9,4(r6)
- bdnz 112b
-113: andi. r0,r3,3
- mtctr r0
- beq 120f
-114: stb r9,4(r6)
- addi r6,r6,1
- bdnz 114b
120: blr
EX_TABLE(30b,108b)
@@ -497,7 +485,5 @@ _GLOBAL(__copy_tofrom_user)
EX_TABLE(41b,111b)
EX_TABLE(130b,132b)
EX_TABLE(131b,120b)
- EX_TABLE(112b,120b)
- EX_TABLE(114b,120b)
EXPORT_SYMBOL(__copy_tofrom_user)
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index aee6e24e81ab..08da06e1bd72 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -319,32 +319,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
blr
/*
- * here we have trapped again, need to clear ctr bytes starting at r3
+ * here we have trapped again, amount remaining is in ctr.
*/
-143: mfctr r5
- li r0,0
- mr r4,r3
- mr r3,r5 /* return the number of bytes not copied */
-1: andi. r9,r4,7
- beq 3f
-90: stb r0,0(r4)
- addic. r5,r5,-1
- addi r4,r4,1
- bne 1b
- blr
-3: cmpldi cr1,r5,8
- srdi r9,r5,3
- andi. r5,r5,7
- blt cr1,93f
- mtctr r9
-91: std r0,0(r4)
- addi r4,r4,8
- bdnz 91b
-93: beqlr
- mtctr r5
-92: stb r0,0(r4)
- addi r4,r4,1
- bdnz 92b
+143: mfctr r3
blr
/*
@@ -389,10 +366,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
ld r5,-8(r1)
add r6,r6,r5
subf r3,r3,r6 /* #bytes not copied */
-190:
-191:
-192:
- blr /* #bytes not copied in r3 */
+ blr
EX_TABLE(20b,120b)
EX_TABLE(220b,320b)
@@ -451,9 +425,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
EX_TABLE(88b,188b)
EX_TABLE(43b,143b)
EX_TABLE(89b,189b)
- EX_TABLE(90b,190b)
- EX_TABLE(91b,191b)
- EX_TABLE(92b,192b)
/*
* Routine to copy a whole page of data, optimized for POWER4.
diff --git a/arch/powerpc/lib/usercopy_64.c b/arch/powerpc/lib/usercopy_64.c
deleted file mode 100644
index 9bd3a3dad78d..000000000000
--- a/arch/powerpc/lib/usercopy_64.c
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * Functions which are too large to be inlined.
- *
- * 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/module.h>
-#include <linux/uaccess.h>
-
-unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_READ, from, n)))
- n = __copy_from_user(to, from, n);
- else
- memset(to, 0, n);
- return n;
-}
-
-unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_WRITE, to, n)))
- n = __copy_to_user(to, from, n);
- return n;
-}
-
-unsigned long copy_in_user(void __user *to, const void __user *from,
- unsigned long n)
-{
- might_sleep();
- if (likely(access_ok(VERIFY_READ, from, n) &&
- access_ok(VERIFY_WRITE, to, n)))
- n =__copy_tofrom_user(to, from, n);
- return n;
-}
-
-EXPORT_SYMBOL(copy_from_user);
-EXPORT_SYMBOL(copy_to_user);
-EXPORT_SYMBOL(copy_in_user);
-
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index cc332608e656..65bb8f33b399 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -638,6 +638,10 @@ static void native_flush_hash_range(unsigned long number, int local)
unsigned long psize = batch->psize;
int ssize = batch->ssize;
int i;
+ unsigned int use_local;
+
+ use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
+ mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
local_irq_save(flags);
@@ -667,8 +671,7 @@ static void native_flush_hash_range(unsigned long number, int local)
} pte_iterate_hashed_end();
}
- if (mmu_has_feature(MMU_FTR_TLBIEL) &&
- mmu_psize_defs[psize].tlbiel && local) {
+ if (use_local) {
asm volatile("ptesync":::"memory");
for (i = 0; i < number; i++) {
vpn = batch->vpn[i];
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 9be992083d2a..c22f207aa656 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -397,8 +397,7 @@ static void early_check_vec5(void)
void __init mmu_early_init_devtree(void)
{
/* Disable radix mode based on kernel command line. */
- /* We don't yet have the machinery to do radix as a guest. */
- if (disable_radix || !(mfmsr() & MSR_HV))
+ if (disable_radix)
cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
/*