summaryrefslogtreecommitdiff
path: root/arch/powerpc/lib
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/lib')
-rw-r--r--arch/powerpc/lib/Makefile8
-rw-r--r--arch/powerpc/lib/code-patching.c105
-rw-r--r--arch/powerpc/lib/crc-t10dif-glue.c89
-rw-r--r--arch/powerpc/lib/crc32-glue.c92
-rw-r--r--arch/powerpc/lib/crc32-vpmsum_core.S746
-rw-r--r--arch/powerpc/lib/crc32c-vpmsum_asm.S842
-rw-r--r--arch/powerpc/lib/crct10dif-vpmsum_asm.S845
-rw-r--r--arch/powerpc/lib/crtsavres.S2
-rw-r--r--arch/powerpc/lib/feature-fixups.c10
-rw-r--r--arch/powerpc/lib/qspinlock.c10
-rw-r--r--arch/powerpc/lib/sstep.c12
-rw-r--r--arch/powerpc/lib/test-code-patching.c135
-rw-r--r--arch/powerpc/lib/test_emulate_step.c2
-rw-r--r--arch/powerpc/lib/vmx-helper.c2
14 files changed, 2863 insertions, 37 deletions
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 0ab65eeb93ee..dd8a4b52a0cc 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -3,8 +3,6 @@
# Makefile for ppc-specific library files..
#
-ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
-
CFLAGS_code-patching.o += -fno-stack-protector
CFLAGS_feature-fixups.o += -fno-stack-protector
@@ -80,4 +78,10 @@ CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec)
# Enable <altivec.h>
CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include)
+obj-$(CONFIG_CRC32_ARCH) += crc32-powerpc.o
+crc32-powerpc-y := crc32-glue.o crc32c-vpmsum_asm.o
+
+obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-powerpc.o
+crc-t10dif-powerpc-y := crc-t10dif-glue.o crct10dif-vpmsum_asm.o
+
obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index c6ab46156cda..af97fbb3c257 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -17,18 +17,17 @@
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/inst.h>
-static int __patch_instruction(u32 *exec_addr, ppc_inst_t instr, u32 *patch_addr)
+static int __patch_mem(void *exec_addr, unsigned long val, void *patch_addr, bool is_dword)
{
- if (!ppc_inst_prefixed(instr)) {
- u32 val = ppc_inst_val(instr);
+ if (!IS_ENABLED(CONFIG_PPC64) || likely(!is_dword)) {
+ /* For big endian correctness: plain address would use the wrong half */
+ u32 val32 = val;
- __put_kernel_nofault(patch_addr, &val, u32, failed);
+ __put_kernel_nofault(patch_addr, &val32, u32, failed);
} else {
- u64 val = ppc_inst_as_ulong(instr);
-
__put_kernel_nofault(patch_addr, &val, u64, failed);
}
@@ -44,7 +43,10 @@ failed:
int raw_patch_instruction(u32 *addr, ppc_inst_t instr)
{
- return __patch_instruction(addr, instr, addr);
+ if (ppc_inst_prefixed(instr))
+ return __patch_mem(addr, ppc_inst_as_ulong(instr), addr, true);
+ else
+ return __patch_mem(addr, ppc_inst_val(instr), addr, false);
}
struct patch_context {
@@ -225,7 +227,7 @@ void __init poking_init(void)
static unsigned long get_patch_pfn(void *addr)
{
- if (IS_ENABLED(CONFIG_MODULES) && is_vmalloc_or_module_addr(addr))
+ if (IS_ENABLED(CONFIG_EXECMEM) && is_vmalloc_or_module_addr(addr))
return vmalloc_to_pfn(addr);
else
return __pa_symbol(addr) >> PAGE_SHIFT;
@@ -276,7 +278,7 @@ static void unmap_patch_area(unsigned long addr)
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
}
-static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr)
+static int __do_patch_mem_mm(void *addr, unsigned long val, bool is_dword)
{
int err;
u32 *patch_addr;
@@ -305,7 +307,7 @@ static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr)
orig_mm = start_using_temp_mm(patching_mm);
- err = __patch_instruction(addr, instr, patch_addr);
+ err = __patch_mem(addr, val, patch_addr, is_dword);
/* context synchronisation performed by __patch_instruction (isync or exception) */
stop_using_temp_mm(patching_mm, orig_mm);
@@ -322,7 +324,7 @@ static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr)
return err;
}
-static int __do_patch_instruction(u32 *addr, ppc_inst_t instr)
+static int __do_patch_mem(void *addr, unsigned long val, bool is_dword)
{
int err;
u32 *patch_addr;
@@ -339,7 +341,7 @@ static int __do_patch_instruction(u32 *addr, ppc_inst_t instr)
if (radix_enabled())
asm volatile("ptesync": : :"memory");
- err = __patch_instruction(addr, instr, patch_addr);
+ err = __patch_mem(addr, val, patch_addr, is_dword);
pte_clear(&init_mm, text_poke_addr, pte);
flush_tlb_kernel_range(text_poke_addr, text_poke_addr + PAGE_SIZE);
@@ -347,7 +349,7 @@ static int __do_patch_instruction(u32 *addr, ppc_inst_t instr)
return err;
}
-int patch_instruction(u32 *addr, ppc_inst_t instr)
+static int patch_mem(void *addr, unsigned long val, bool is_dword)
{
int err;
unsigned long flags;
@@ -359,22 +361,83 @@ int patch_instruction(u32 *addr, ppc_inst_t instr)
*/
if (!IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) ||
!static_branch_likely(&poking_init_done))
- return raw_patch_instruction(addr, instr);
+ return __patch_mem(addr, val, addr, is_dword);
local_irq_save(flags);
if (mm_patch_enabled())
- err = __do_patch_instruction_mm(addr, instr);
+ err = __do_patch_mem_mm(addr, val, is_dword);
else
- err = __do_patch_instruction(addr, instr);
+ err = __do_patch_mem(addr, val, is_dword);
local_irq_restore(flags);
return err;
}
+
+#ifdef CONFIG_PPC64
+
+int patch_instruction(u32 *addr, ppc_inst_t instr)
+{
+ if (ppc_inst_prefixed(instr))
+ return patch_mem(addr, ppc_inst_as_ulong(instr), true);
+ else
+ return patch_mem(addr, ppc_inst_val(instr), false);
+}
NOKPROBE_SYMBOL(patch_instruction);
+int patch_uint(void *addr, unsigned int val)
+{
+ if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned int)))
+ return -EINVAL;
+
+ return patch_mem(addr, val, false);
+}
+NOKPROBE_SYMBOL(patch_uint);
+
+int patch_ulong(void *addr, unsigned long val)
+{
+ if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned long)))
+ return -EINVAL;
+
+ return patch_mem(addr, val, true);
+}
+NOKPROBE_SYMBOL(patch_ulong);
+
+#else
+
+int patch_instruction(u32 *addr, ppc_inst_t instr)
+{
+ return patch_mem(addr, ppc_inst_val(instr), false);
+}
+NOKPROBE_SYMBOL(patch_instruction)
+
+#endif
+
+static int patch_memset64(u64 *addr, u64 val, size_t count)
+{
+ for (u64 *end = addr + count; addr < end; addr++)
+ __put_kernel_nofault(addr, &val, u64, failed);
+
+ return 0;
+
+failed:
+ return -EPERM;
+}
+
+static int patch_memset32(u32 *addr, u32 val, size_t count)
+{
+ for (u32 *end = addr + count; addr < end; addr++)
+ __put_kernel_nofault(addr, &val, u32, failed);
+
+ return 0;
+
+failed:
+ return -EPERM;
+}
+
static int __patch_instructions(u32 *patch_addr, u32 *code, size_t len, bool repeat_instr)
{
unsigned long start = (unsigned long)patch_addr;
+ int err;
/* Repeat instruction */
if (repeat_instr) {
@@ -383,19 +446,19 @@ static int __patch_instructions(u32 *patch_addr, u32 *code, size_t len, bool rep
if (ppc_inst_prefixed(instr)) {
u64 val = ppc_inst_as_ulong(instr);
- memset64((u64 *)patch_addr, val, len / 8);
+ err = patch_memset64((u64 *)patch_addr, val, len / 8);
} else {
u32 val = ppc_inst_val(instr);
- memset32(patch_addr, val, len / 4);
+ err = patch_memset32(patch_addr, val, len / 4);
}
} else {
- memcpy(patch_addr, code, len);
+ err = copy_to_kernel_nofault(patch_addr, code, len);
}
smp_wmb(); /* smp write barrier */
flush_icache_range(start, start + len);
- return 0;
+ return err;
}
/*
diff --git a/arch/powerpc/lib/crc-t10dif-glue.c b/arch/powerpc/lib/crc-t10dif-glue.c
new file mode 100644
index 000000000000..730850dbc51d
--- /dev/null
+++ b/arch/powerpc/lib/crc-t10dif-glue.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Calculate a CRC T10-DIF with vpmsum acceleration
+ *
+ * Copyright 2017, Daniel Axtens, IBM Corporation.
+ * [based on crc32c-vpmsum_glue.c]
+ */
+
+#include <linux/crc-t10dif.h>
+#include <crypto/internal/simd.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+
+#define VMX_ALIGN 16
+#define VMX_ALIGN_MASK (VMX_ALIGN-1)
+
+#define VECTOR_BREAKPOINT 64
+
+static DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
+
+u32 __crct10dif_vpmsum(u32 crc, unsigned char const *p, size_t len);
+
+u16 crc_t10dif_arch(u16 crci, const u8 *p, size_t len)
+{
+ unsigned int prealign;
+ unsigned int tail;
+ u32 crc = crci;
+
+ if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) ||
+ !static_branch_likely(&have_vec_crypto) || !crypto_simd_usable())
+ 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;
+}
+EXPORT_SYMBOL(crc_t10dif_arch);
+
+static int __init crc_t10dif_powerpc_init(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+ (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
+ static_branch_enable(&have_vec_crypto);
+ return 0;
+}
+arch_initcall(crc_t10dif_powerpc_init);
+
+static void __exit crc_t10dif_powerpc_exit(void)
+{
+}
+module_exit(crc_t10dif_powerpc_exit);
+
+bool crc_t10dif_is_optimized(void)
+{
+ return static_key_enabled(&have_vec_crypto);
+}
+EXPORT_SYMBOL(crc_t10dif_is_optimized);
+
+MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
+MODULE_DESCRIPTION("CRCT10DIF using vector polynomial multiply-sum instructions");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/lib/crc32-glue.c b/arch/powerpc/lib/crc32-glue.c
new file mode 100644
index 000000000000..79cc954f499f
--- /dev/null
+++ b/arch/powerpc/lib/crc32-glue.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/crc32.h>
+#include <crypto/internal/simd.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+
+#define VMX_ALIGN 16
+#define VMX_ALIGN_MASK (VMX_ALIGN-1)
+
+#define VECTOR_BREAKPOINT 512
+
+static DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
+
+u32 __crc32c_vpmsum(u32 crc, const u8 *p, size_t len);
+
+u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
+{
+ return crc32_le_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_le_arch);
+
+u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
+{
+ unsigned int prealign;
+ unsigned int tail;
+
+ if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) ||
+ !static_branch_likely(&have_vec_crypto) || !crypto_simd_usable())
+ return crc32c_le_base(crc, p, len);
+
+ if ((unsigned long)p & VMX_ALIGN_MASK) {
+ prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
+ crc = crc32c_le_base(crc, p, prealign);
+ len -= prealign;
+ p += prealign;
+ }
+
+ 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;
+ if (tail) {
+ p += len & ~VMX_ALIGN_MASK;
+ crc = crc32c_le_base(crc, p, tail);
+ }
+
+ return crc;
+}
+EXPORT_SYMBOL(crc32c_le_arch);
+
+u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
+{
+ return crc32_be_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_be_arch);
+
+static int __init crc32_powerpc_init(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+ (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
+ static_branch_enable(&have_vec_crypto);
+ return 0;
+}
+arch_initcall(crc32_powerpc_init);
+
+static void __exit crc32_powerpc_exit(void)
+{
+}
+module_exit(crc32_powerpc_exit);
+
+u32 crc32_optimizations(void)
+{
+ if (static_key_enabled(&have_vec_crypto))
+ return CRC32C_OPTIMIZATION;
+ return 0;
+}
+EXPORT_SYMBOL(crc32_optimizations);
+
+MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
+MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/lib/crc32-vpmsum_core.S b/arch/powerpc/lib/crc32-vpmsum_core.S
new file mode 100644
index 000000000000..b0f87f595b26
--- /dev/null
+++ b/arch/powerpc/lib/crc32-vpmsum_core.S
@@ -0,0 +1,746 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * 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.
+ *
+ * https://en.wikipedia.org/wiki/Barrett_reduction
+ *
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+*/
+
+#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
+ LOAD_REG_ADDR(r3, .byteswap_constant)
+ 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
+
+ LOAD_REG_ADDR(r3, .constants)
+
+ /* 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 */
+ LOAD_REG_ADDR(r3, .barrett_constants)
+
+ 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
+
+ LOAD_REG_ADDR(r3, .short_constants)
+
+ /* 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/lib/crc32c-vpmsum_asm.S b/arch/powerpc/lib/crc32c-vpmsum_asm.S
new file mode 100644
index 000000000000..bf442004ea1f
--- /dev/null
+++ b/arch/powerpc/lib/crc32c-vpmsum_asm.S
@@ -0,0 +1,842 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Calculate a crc32c with vpmsum acceleration
+ *
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ */
+ .section .rodata
+.balign 16
+
+.byteswap_constant:
+ /* byte reverse permute constant */
+ .octa 0x0F0E0D0C0B0A09080706050403020100
+
+.constants:
+
+ /* Reduce 262144 kbits to 1024 bits */
+ /* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */
+ .octa 0x00000000b6ca9e20000000009c37c408
+
+ /* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */
+ .octa 0x00000000350249a800000001b51df26c
+
+ /* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */
+ .octa 0x00000001862dac54000000000724b9d0
+
+ /* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */
+ .octa 0x00000001d87fb48c00000001c00532fe
+
+ /* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */
+ .octa 0x00000001f39b699e00000000f05a9362
+
+ /* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */
+ .octa 0x0000000101da11b400000001e1007970
+
+ /* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */
+ .octa 0x00000001cab571e000000000a57366ee
+
+ /* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */
+ .octa 0x00000000c7020cfe0000000192011284
+
+ /* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */
+ .octa 0x00000000cdaed1ae0000000162716d9a
+
+ /* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */
+ .octa 0x00000001e804effc00000000cd97ecde
+
+ /* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */
+ .octa 0x0000000077c3ea3a0000000058812bc0
+
+ /* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */
+ .octa 0x0000000068df31b40000000088b8c12e
+
+ /* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */
+ .octa 0x00000000b059b6c200000001230b234c
+
+ /* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */
+ .octa 0x0000000145fb8ed800000001120b416e
+
+ /* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */
+ .octa 0x00000000cbc0916800000001974aecb0
+
+ /* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */
+ .octa 0x000000005ceeedc2000000008ee3f226
+
+ /* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */
+ .octa 0x0000000047d74e8600000001089aba9a
+
+ /* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */
+ .octa 0x00000001407e9e220000000065113872
+
+ /* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */
+ .octa 0x00000001da967bda000000005c07ec10
+
+ /* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */
+ .octa 0x000000006c8983680000000187590924
+
+ /* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */
+ .octa 0x00000000f2d14c9800000000e35da7c6
+
+ /* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */
+ .octa 0x00000001993c6ad4000000000415855a
+
+ /* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */
+ .octa 0x000000014683d1ac0000000073617758
+
+ /* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */
+ .octa 0x00000001a7c93e6c0000000176021d28
+
+ /* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */
+ .octa 0x000000010211e90a00000001c358fd0a
+
+ /* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */
+ .octa 0x000000001119403e00000001ff7a2c18
+
+ /* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */
+ .octa 0x000000001c3261aa00000000f2d9f7e4
+
+ /* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */
+ .octa 0x000000014e37a634000000016cf1f9c8
+
+ /* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */
+ .octa 0x0000000073786c0c000000010af9279a
+
+ /* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */
+ .octa 0x000000011dc037f80000000004f101e8
+
+ /* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */
+ .octa 0x0000000031433dfc0000000070bcf184
+
+ /* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */
+ .octa 0x000000009cde8348000000000a8de642
+
+ /* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */
+ .octa 0x0000000038d3c2a60000000062ea130c
+
+ /* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */
+ .octa 0x000000011b25f26000000001eb31cbb2
+
+ /* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */
+ .octa 0x000000001629e6f00000000170783448
+
+ /* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */
+ .octa 0x0000000160838b4c00000001a684b4c6
+
+ /* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */
+ .octa 0x000000007a44011c00000000253ca5b4
+
+ /* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */
+ .octa 0x00000000226f417a0000000057b4b1e2
+
+ /* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */
+ .octa 0x0000000045eb2eb400000000b6bd084c
+
+ /* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */
+ .octa 0x000000014459d70c0000000123c2d592
+
+ /* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */
+ .octa 0x00000001d406ed8200000000159dafce
+
+ /* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */
+ .octa 0x0000000160c8e1a80000000127e1a64e
+
+ /* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */
+ .octa 0x0000000027ba80980000000056860754
+
+ /* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */
+ .octa 0x000000006d92d01800000001e661aae8
+
+ /* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */
+ .octa 0x000000012ed7e3f200000000f82c6166
+
+ /* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */
+ .octa 0x000000002dc8778800000000c4f9c7ae
+
+ /* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */
+ .octa 0x0000000018240bb80000000074203d20
+
+ /* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */
+ .octa 0x000000001ad381580000000198173052
+
+ /* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */
+ .octa 0x00000001396b78f200000001ce8aba54
+
+ /* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */
+ .octa 0x000000011a68133400000001850d5d94
+
+ /* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */
+ .octa 0x000000012104732e00000001d609239c
+
+ /* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */
+ .octa 0x00000000a140d90c000000001595f048
+
+ /* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */
+ .octa 0x00000001b7215eda0000000042ccee08
+
+ /* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */
+ .octa 0x00000001aaf1df3c000000010a389d74
+
+ /* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */
+ .octa 0x0000000029d15b8a000000012a840da6
+
+ /* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */
+ .octa 0x00000000f1a96922000000001d181c0c
+
+ /* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */
+ .octa 0x00000001ac80d03c0000000068b7d1f6
+
+ /* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */
+ .octa 0x000000000f11d56a000000005b0f14fc
+
+ /* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */
+ .octa 0x00000001f1c022a20000000179e9e730
+
+ /* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */
+ .octa 0x0000000173d00ae200000001ce1368d6
+
+ /* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */
+ .octa 0x00000001d4ffe4ac0000000112c3a84c
+
+ /* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */
+ .octa 0x000000016edc5ae400000000de940fee
+
+ /* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */
+ .octa 0x00000001f1a0214000000000fe896b7e
+
+ /* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */
+ .octa 0x00000000ca0b28a000000001f797431c
+
+ /* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */
+ .octa 0x00000001928e30a20000000053e989ba
+
+ /* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */
+ .octa 0x0000000097b1b002000000003920cd16
+
+ /* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */
+ .octa 0x00000000b15bf90600000001e6f579b8
+
+ /* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */
+ .octa 0x00000000411c5d52000000007493cb0a
+
+ /* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */
+ .octa 0x00000001c36f330000000001bdd376d8
+
+ /* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */
+ .octa 0x00000001119227e0000000016badfee6
+
+ /* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */
+ .octa 0x00000000114d47020000000071de5c58
+
+ /* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */
+ .octa 0x00000000458b5b9800000000453f317c
+
+ /* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */
+ .octa 0x000000012e31fb8e0000000121675cce
+
+ /* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */
+ .octa 0x000000005cf619d800000001f409ee92
+
+ /* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */
+ .octa 0x0000000063f4d8b200000000f36b9c88
+
+ /* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */
+ .octa 0x000000004138dc8a0000000036b398f4
+
+ /* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */
+ .octa 0x00000001d29ee8e000000001748f9adc
+
+ /* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */
+ .octa 0x000000006a08ace800000001be94ec00
+
+ /* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */
+ .octa 0x0000000127d4201000000000b74370d6
+
+ /* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */
+ .octa 0x0000000019d76b6200000001174d0b98
+
+ /* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */
+ .octa 0x00000001b1471f6e00000000befc06a4
+
+ /* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */
+ .octa 0x00000001f64c19cc00000001ae125288
+
+ /* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */
+ .octa 0x00000000003c0ea00000000095c19b34
+
+ /* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */
+ .octa 0x000000014d73abf600000001a78496f2
+
+ /* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */
+ .octa 0x00000001620eb84400000001ac5390a0
+
+ /* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */
+ .octa 0x0000000147655048000000002a80ed6e
+
+ /* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */
+ .octa 0x0000000067b5077e00000001fa9b0128
+
+ /* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */
+ .octa 0x0000000010ffe20600000001ea94929e
+
+ /* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */
+ .octa 0x000000000fee8f1e0000000125f4305c
+
+ /* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */
+ .octa 0x00000001da26fbae00000001471e2002
+
+ /* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */
+ .octa 0x00000001b3a8bd880000000132d2253a
+
+ /* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */
+ .octa 0x00000000e8f3898e00000000f26b3592
+
+ /* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */
+ .octa 0x00000000b0d0d28c00000000bc8b67b0
+
+ /* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */
+ .octa 0x0000000030f2a798000000013a826ef2
+
+ /* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */
+ .octa 0x000000000fba10020000000081482c84
+
+ /* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */
+ .octa 0x00000000bdb9bd7200000000e77307c2
+
+ /* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */
+ .octa 0x0000000075d3bf5a00000000d4a07ec8
+
+ /* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */
+ .octa 0x00000000ef1f98a00000000017102100
+
+ /* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */
+ .octa 0x00000000689c760200000000db406486
+
+ /* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */
+ .octa 0x000000016d5fa5fe0000000192db7f88
+
+ /* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */
+ .octa 0x00000001d0d2b9ca000000018bf67b1e
+
+ /* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */
+ .octa 0x0000000041e7b470000000007c09163e
+
+ /* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */
+ .octa 0x00000001cbb6495e000000000adac060
+
+ /* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */
+ .octa 0x000000010052a0b000000000bd8316ae
+
+ /* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */
+ .octa 0x00000001d8effb5c000000019f09ab54
+
+ /* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */
+ .octa 0x00000001d969853c0000000125155542
+
+ /* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */
+ .octa 0x00000000523ccce2000000018fdb5882
+
+ /* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */
+ .octa 0x000000001e2436bc00000000e794b3f4
+
+ /* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */
+ .octa 0x00000000ddd1c3a2000000016f9bb022
+
+ /* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */
+ .octa 0x0000000019fcfe3800000000290c9978
+
+ /* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */
+ .octa 0x00000001ce95db640000000083c0f350
+
+ /* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */
+ .octa 0x00000000af5828060000000173ea6628
+
+ /* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */
+ .octa 0x00000001006388f600000001c8b4e00a
+
+ /* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */
+ .octa 0x0000000179eca00a00000000de95d6aa
+
+ /* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */
+ .octa 0x0000000122410a6a000000010b7f7248
+
+ /* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */
+ .octa 0x000000004288e87c00000001326e3a06
+
+ /* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */
+ .octa 0x000000016c5490da00000000bb62c2e6
+
+ /* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */
+ .octa 0x00000000d1c71f6e0000000156a4b2c2
+
+ /* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */
+ .octa 0x00000001b4ce08a6000000011dfe763a
+
+ /* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */
+ .octa 0x00000001466ba60c000000007bcca8e2
+
+ /* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */
+ .octa 0x00000001f6c488a40000000186118faa
+
+ /* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */
+ .octa 0x000000013bfb06820000000111a65a88
+
+ /* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */
+ .octa 0x00000000690e9e54000000003565e1c4
+
+ /* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */
+ .octa 0x00000000281346b6000000012ed02a82
+
+ /* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */
+ .octa 0x000000015646402400000000c486ecfc
+
+ /* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */
+ .octa 0x000000016063a8dc0000000001b951b2
+
+ /* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */
+ .octa 0x0000000116a663620000000048143916
+
+ /* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */
+ .octa 0x000000017e8aa4d200000001dc2ae124
+
+ /* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */
+ .octa 0x00000001728eb10c00000001416c58d6
+
+ /* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */
+ .octa 0x00000001b08fd7fa00000000a479744a
+
+ /* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */
+ .octa 0x00000001092a16e80000000096ca3a26
+
+ /* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */
+ .octa 0x00000000a505637c00000000ff223d4e
+
+ /* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */
+ .octa 0x00000000d94869b2000000010e84da42
+
+ /* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */
+ .octa 0x00000001c8b203ae00000001b61ba3d0
+
+ /* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */
+ .octa 0x000000005704aea000000000680f2de8
+
+ /* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */
+ .octa 0x000000012e295fa2000000008772a9a8
+
+ /* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */
+ .octa 0x000000011d0908bc0000000155f295bc
+
+ /* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */
+ .octa 0x0000000193ed97ea00000000595f9282
+
+ /* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */
+ .octa 0x000000013a0f1c520000000164b1c25a
+
+ /* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */
+ .octa 0x000000010c2c40c000000000fbd67c50
+
+ /* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */
+ .octa 0x00000000ff6fac3e0000000096076268
+
+ /* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */
+ .octa 0x000000017b3609c000000001d288e4cc
+
+ /* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */
+ .octa 0x0000000088c8c92200000001eaac1bdc
+
+ /* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */
+ .octa 0x00000001751baae600000001f1ea39e2
+
+ /* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */
+ .octa 0x000000010795297200000001eb6506fc
+
+ /* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */
+ .octa 0x0000000162b00abe000000010f806ffe
+
+ /* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */
+ .octa 0x000000000d7b404c000000010408481e
+
+ /* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */
+ .octa 0x00000000763b13d40000000188260534
+
+ /* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */
+ .octa 0x00000000f6dc22d80000000058fc73e0
+
+ /* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */
+ .octa 0x000000007daae06000000000391c59b8
+
+ /* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */
+ .octa 0x000000013359ab7c000000018b638400
+
+ /* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */
+ .octa 0x000000008add438a000000011738f5c4
+
+ /* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */
+ .octa 0x00000001edbefdea000000008cf7c6da
+
+ /* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */
+ .octa 0x000000004104e0f800000001ef97fb16
+
+ /* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */
+ .octa 0x00000000b48a82220000000102130e20
+
+ /* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */
+ .octa 0x00000001bcb4684400000000db968898
+
+ /* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */
+ .octa 0x000000013293ce0a00000000b5047b5e
+
+ /* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */
+ .octa 0x00000001710d0844000000010b90fdb2
+
+ /* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */
+ .octa 0x0000000117907f6e000000004834a32e
+
+ /* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */
+ .octa 0x0000000087ddf93e0000000059c8f2b0
+
+ /* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */
+ .octa 0x000000005970e9b00000000122cec508
+
+ /* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */
+ .octa 0x0000000185b2b7d0000000000a330cda
+
+ /* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */
+ .octa 0x00000001dcee0efc000000014a47148c
+
+ /* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */
+ .octa 0x0000000030da27220000000042c61cb8
+
+ /* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */
+ .octa 0x000000012f925a180000000012fe6960
+
+ /* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */
+ .octa 0x00000000dd2e357c00000000dbda2c20
+
+ /* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */
+ .octa 0x00000000071c80de000000011122410c
+
+ /* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */
+ .octa 0x000000011513140a00000000977b2070
+
+ /* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */
+ .octa 0x00000001df876e8e000000014050438e
+
+ /* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */
+ .octa 0x000000015f81d6ce0000000147c840e8
+
+ /* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */
+ .octa 0x000000019dd94dbe00000001cc7c88ce
+
+ /* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */
+ .octa 0x00000001373d206e00000001476b35a4
+
+ /* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */
+ .octa 0x00000000668ccade000000013d52d508
+
+ /* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */
+ .octa 0x00000001b192d268000000008e4be32e
+
+ /* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */
+ .octa 0x00000000e30f3a7800000000024120fe
+
+ /* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */
+ .octa 0x000000010ef1f7bc00000000ddecddb4
+
+ /* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */
+ .octa 0x00000001f5ac738000000000d4d403bc
+
+ /* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */
+ .octa 0x000000011822ea7000000001734b89aa
+
+ /* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */
+ .octa 0x00000000c3a33848000000010e7a58d6
+
+ /* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */
+ .octa 0x00000001bd151c2400000001f9f04e9c
+
+ /* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */
+ .octa 0x0000000056002d7600000000b692225e
+
+ /* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */
+ .octa 0x000000014657c4f4000000019b8d3f3e
+
+ /* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */
+ .octa 0x0000000113742d7c00000001a874f11e
+
+ /* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */
+ .octa 0x000000019c5920ba000000010d5a4254
+
+ /* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */
+ .octa 0x000000005216d2d600000000bbb2f5d6
+
+ /* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */
+ .octa 0x0000000136f5ad8a0000000179cc0e36
+
+ /* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */
+ .octa 0x000000018b07beb600000001dca1da4a
+
+ /* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */
+ .octa 0x00000000db1e93b000000000feb1a192
+
+ /* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */
+ .octa 0x000000000b96fa3a00000000d1eeedd6
+
+ /* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */
+ .octa 0x00000001d9968af0000000008fad9bb4
+
+ /* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */
+ .octa 0x000000000e4a77a200000001884938e4
+
+ /* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */
+ .octa 0x00000000508c2ac800000001bc2e9bc0
+
+ /* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */
+ .octa 0x0000000021572a8000000001f9658a68
+
+ /* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */
+ .octa 0x00000001b859daf2000000001b9224fc
+
+ /* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */
+ .octa 0x000000016f7884740000000055b2fb84
+
+ /* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */
+ .octa 0x00000001b438810e000000018b090348
+
+ /* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */
+ .octa 0x0000000095ddc6f2000000011ccbd5ea
+
+ /* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */
+ .octa 0x00000001d977c20c0000000007ae47f8
+
+ /* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */
+ .octa 0x00000000ebedb99a0000000172acbec0
+
+ /* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */
+ .octa 0x00000001df9e9e9200000001c6e3ff20
+
+ /* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */
+ .octa 0x00000001a4a3f95200000000e1b38744
+
+ /* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */
+ .octa 0x00000000e2f5122000000000791585b2
+
+ /* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */
+ .octa 0x000000004aa01f3e00000000ac53b894
+
+ /* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */
+ .octa 0x00000000b3e90a5800000001ed5f2cf4
+
+ /* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */
+ .octa 0x000000000c9ca2aa00000001df48b2e0
+
+ /* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */
+ .octa 0x000000015168231600000000049c1c62
+
+ /* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */
+ .octa 0x0000000036fce78c000000017c460c12
+
+ /* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */
+ .octa 0x000000009037dc10000000015be4da7e
+
+ /* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */
+ .octa 0x00000000d3298582000000010f38f668
+
+ /* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */
+ .octa 0x00000001b42e8ad60000000039f40a00
+
+ /* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */
+ .octa 0x00000000142a983800000000bd4c10c4
+
+ /* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */
+ .octa 0x0000000109c7f1900000000042db1d98
+
+ /* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */
+ .octa 0x0000000056ff931000000001c905bae6
+
+ /* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */
+ .octa 0x00000001594513aa00000000069d40ea
+
+ /* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */
+ .octa 0x00000001e3b5b1e8000000008e4fbad0
+
+ /* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */
+ .octa 0x000000011dd5fc080000000047bedd46
+
+ /* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */
+ .octa 0x00000001675f0cc20000000026396bf8
+
+ /* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */
+ .octa 0x00000000d1c8dd4400000000379beb92
+
+ /* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */
+ .octa 0x0000000115ebd3d8000000000abae54a
+
+ /* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */
+ .octa 0x00000001ecbd0dac0000000007e6a128
+
+ /* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */
+ .octa 0x00000000cdf67af2000000000ade29d2
+
+ /* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */
+ .octa 0x000000004c01ff4c00000000f974c45c
+
+ /* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */
+ .octa 0x00000000f2d8657e00000000e77ac60a
+
+ /* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */
+ .octa 0x000000006bae74c40000000145895816
+
+ /* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */
+ .octa 0x0000000152af8aa00000000038e362be
+
+ /* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */
+ .octa 0x0000000004663802000000007f991a64
+
+ /* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */
+ .octa 0x00000001ab2f5afc00000000fa366d3a
+
+ /* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */
+ .octa 0x0000000074a4ebd400000001a2bb34f0
+
+ /* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */
+ .octa 0x00000001d7ab3a4c0000000028a9981e
+
+ /* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */
+ .octa 0x00000001a8da60c600000001dbc672be
+
+ /* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */
+ .octa 0x000000013cf6382000000000b04d77f6
+
+ /* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */
+ .octa 0x00000000bec12e1e0000000124400d96
+
+ /* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */
+ .octa 0x00000001c6368010000000014ca4b414
+
+ /* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */
+ .octa 0x00000001e6e78758000000012fe2c938
+
+ /* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */
+ .octa 0x000000008d7f2b3c00000001faed01e6
+
+ /* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */
+ .octa 0x000000016b4a156e000000007e80ecfe
+
+ /* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */
+ .octa 0x00000001c63cfeb60000000098daee94
+
+ /* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */
+ .octa 0x000000015f902670000000010a04edea
+
+ /* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */
+ .octa 0x00000001cd5de11e00000001c00b4524
+
+ /* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */
+ .octa 0x000000001acaec540000000170296550
+
+ /* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */
+ .octa 0x000000002bd0ca780000000181afaa48
+
+ /* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */
+ .octa 0x0000000032d63d5c0000000185a31ffa
+
+ /* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */
+ .octa 0x000000001c6d4e4c000000002469f608
+
+ /* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */
+ .octa 0x0000000106a60b92000000006980102a
+
+ /* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */
+ .octa 0x00000000d3855e120000000111ea9ca8
+
+ /* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */
+ .octa 0x00000000e312563600000001bd1d29ce
+
+ /* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */
+ .octa 0x000000009e8f7ea400000001b34b9580
+
+ /* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */
+ .octa 0x00000001c82e562c000000003076054e
+
+ /* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */
+ .octa 0x00000000ca9f09ce000000012a608ea4
+
+ /* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */
+ .octa 0x00000000c63764e600000000784d05fe
+
+ /* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */
+ .octa 0x0000000168d2e49e000000016ef0d82a
+
+ /* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */
+ .octa 0x00000000e986c1480000000075bda454
+
+ /* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */
+ .octa 0x00000000cfb65894000000003dc0a1c4
+
+ /* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */
+ .octa 0x0000000111cadee400000000e9a5d8be
+
+ /* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */
+ .octa 0x0000000171fb63ce00000001609bc4b4
+
+.short_constants:
+
+ /* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */
+ /* x^1952 mod p(x)`, x^1984 mod p(x)`, x^2016 mod p(x)`, x^2048 mod p(x)` */
+ .octa 0x7fec2963e5bf80485cf015c388e56f72
+
+ /* x^1824 mod p(x)`, x^1856 mod p(x)`, x^1888 mod p(x)`, x^1920 mod p(x)` */
+ .octa 0x38e888d4844752a9963a18920246e2e6
+
+ /* x^1696 mod p(x)`, x^1728 mod p(x)`, x^1760 mod p(x)`, x^1792 mod p(x)` */
+ .octa 0x42316c00730206ad419a441956993a31
+
+ /* x^1568 mod p(x)`, x^1600 mod p(x)`, x^1632 mod p(x)`, x^1664 mod p(x)` */
+ .octa 0x543d5c543e65ddf9924752ba2b830011
+
+ /* x^1440 mod p(x)`, x^1472 mod p(x)`, x^1504 mod p(x)`, x^1536 mod p(x)` */
+ .octa 0x78e87aaf56767c9255bd7f9518e4a304
+
+ /* x^1312 mod p(x)`, x^1344 mod p(x)`, x^1376 mod p(x)`, x^1408 mod p(x)` */
+ .octa 0x8f68fcec1903da7f6d76739fe0553f1e
+
+ /* x^1184 mod p(x)`, x^1216 mod p(x)`, x^1248 mod p(x)`, x^1280 mod p(x)` */
+ .octa 0x3f4840246791d588c133722b1fe0b5c3
+
+ /* x^1056 mod p(x)`, x^1088 mod p(x)`, x^1120 mod p(x)`, x^1152 mod p(x)` */
+ .octa 0x34c96751b04de25a64b67ee0e55ef1f3
+
+ /* x^928 mod p(x)`, x^960 mod p(x)`, x^992 mod p(x)`, x^1024 mod p(x)` */
+ .octa 0x156c8e180b4a395b069db049b8fdb1e7
+
+ /* x^800 mod p(x)`, x^832 mod p(x)`, x^864 mod p(x)`, x^896 mod p(x)` */
+ .octa 0xe0b99ccbe661f7bea11bfaf3c9e90b9e
+
+ /* x^672 mod p(x)`, x^704 mod p(x)`, x^736 mod p(x)`, x^768 mod p(x)` */
+ .octa 0x041d37768cd75659817cdc5119b29a35
+
+ /* x^544 mod p(x)`, x^576 mod p(x)`, x^608 mod p(x)`, x^640 mod p(x)` */
+ .octa 0x3a0777818cfaa9651ce9d94b36c41f1c
+
+ /* x^416 mod p(x)`, x^448 mod p(x)`, x^480 mod p(x)`, x^512 mod p(x)` */
+ .octa 0x0e148e8252377a554f256efcb82be955
+
+ /* x^288 mod p(x)`, x^320 mod p(x)`, x^352 mod p(x)`, x^384 mod p(x)` */
+ .octa 0x9c25531d19e65ddeec1631edb2dea967
+
+ /* x^160 mod p(x)`, x^192 mod p(x)`, x^224 mod p(x)`, x^256 mod p(x)` */
+ .octa 0x790606ff9957c0a65d27e147510ac59a
+
+ /* x^32 mod p(x)`, x^64 mod p(x)`, x^96 mod p(x)`, x^128 mod p(x)` */
+ .octa 0x82f63b786ea2d55ca66805eb18b8ea18
+
+
+.barrett_constants:
+ /* 33 bit reflected Barrett constant m - (4^32)/n */
+ .octa 0x000000000000000000000000dea713f1 /* x^64 div p(x)` */
+ /* 33 bit reflected Barrett constant n */
+ .octa 0x00000000000000000000000105ec76f1
+
+#define CRC_FUNCTION_NAME __crc32c_vpmsum
+#define REFLECT
+#include "crc32-vpmsum_core.S"
diff --git a/arch/powerpc/lib/crct10dif-vpmsum_asm.S b/arch/powerpc/lib/crct10dif-vpmsum_asm.S
new file mode 100644
index 000000000000..f0b93a0fe168
--- /dev/null
+++ b/arch/powerpc/lib/crct10dif-vpmsum_asm.S
@@ -0,0 +1,845 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * 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
+ */
+ .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/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S
index 7e5e1c28e56a..8967903c15e9 100644
--- a/arch/powerpc/lib/crtsavres.S
+++ b/arch/powerpc/lib/crtsavres.S
@@ -46,7 +46,7 @@
.section ".text"
-#ifndef CONFIG_PPC64
+#ifndef __powerpc64__
/* Routines for saving integer registers, called by the compiler. */
/* Called with r11 pointing to the stack header word of the caller of the */
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 4f82581ca203..587c8cf1230f 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -16,7 +16,7 @@
#include <linux/sched/mm.h>
#include <linux/stop_machine.h>
#include <asm/cputable.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/interrupt.h>
#include <asm/page.h>
#include <asm/sections.h>
@@ -25,6 +25,13 @@
#include <asm/firmware.h>
#include <asm/inst.h>
+/*
+ * Used to generate warnings if mmu or cpu feature check functions that
+ * use static keys before they are initialized.
+ */
+bool static_key_feature_checks_initialized __read_mostly;
+EXPORT_SYMBOL_GPL(static_key_feature_checks_initialized);
+
struct fixup_entry {
unsigned long mask;
unsigned long value;
@@ -679,6 +686,7 @@ void __init setup_feature_keys(void)
jump_label_init();
cpu_feature_keys_init();
mmu_feature_keys_init();
+ static_key_feature_checks_initialized = true;
}
static int __init check_features(void)
diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
index 5de4dd549f6e..bcc7e4dff8c3 100644
--- a/arch/powerpc/lib/qspinlock.c
+++ b/arch/powerpc/lib/qspinlock.c
@@ -697,7 +697,15 @@ again:
}
release:
- qnodesp->count--; /* release the node */
+ /*
+ * Clear the lock before releasing the node, as another CPU might see stale
+ * values if an interrupt occurs after we increment qnodesp->count
+ * but before node->lock is initialized. The barrier ensures that
+ * there are no further stores to the node after it has been released.
+ */
+ node->lock = NULL;
+ barrier();
+ qnodesp->count--;
}
void queued_spin_lock_slowpath(struct qspinlock *lock)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index e65f3fb68d06..ac3ee19531d8 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -780,8 +780,8 @@ static nokprobe_inline int emulate_stq(struct pt_regs *regs, unsigned long ea,
#endif /* __powerpc64 */
#ifdef CONFIG_VSX
-void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
- const void *mem, bool rev)
+static nokprobe_inline void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
+ const void *mem, bool rev)
{
int size, read_size;
int i, j;
@@ -863,11 +863,9 @@ void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
break;
}
}
-EXPORT_SYMBOL_GPL(emulate_vsx_load);
-NOKPROBE_SYMBOL(emulate_vsx_load);
-void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
- void *mem, bool rev)
+static nokprobe_inline void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
+ void *mem, bool rev)
{
int size, write_size;
int i, j;
@@ -955,8 +953,6 @@ void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
break;
}
}
-EXPORT_SYMBOL_GPL(emulate_vsx_store);
-NOKPROBE_SYMBOL(emulate_vsx_store);
static nokprobe_inline int do_vsx_load(struct instruction_op *op,
unsigned long ea, struct pt_regs *regs,
diff --git a/arch/powerpc/lib/test-code-patching.c b/arch/powerpc/lib/test-code-patching.c
index c44823292f73..1440d99630b3 100644
--- a/arch/powerpc/lib/test-code-patching.c
+++ b/arch/powerpc/lib/test-code-patching.c
@@ -6,7 +6,7 @@
#include <linux/vmalloc.h>
#include <linux/init.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
static int __init instr_is_branch_to_addr(const u32 *instr, unsigned long addr)
{
@@ -347,6 +347,137 @@ static void __init test_prefixed_patching(void)
check(!memcmp(iptr, expected, sizeof(expected)));
}
+static void __init test_multi_instruction_patching(void)
+{
+ u32 code[32];
+ void *buf;
+ u32 *addr32;
+ u64 *addr64;
+ ppc_inst_t inst64 = ppc_inst_prefix(OP_PREFIX << 26 | 3UL << 24, PPC_RAW_TRAP());
+ u32 inst32 = PPC_RAW_NOP();
+
+ buf = vzalloc(PAGE_SIZE * 8);
+ check(buf);
+ if (!buf)
+ return;
+
+ /* Test single page 32-bit repeated instruction */
+ addr32 = buf + PAGE_SIZE;
+ check(!patch_instructions(addr32 + 1, &inst32, 12, true));
+
+ check(addr32[0] == 0);
+ check(addr32[1] == inst32);
+ check(addr32[2] == inst32);
+ check(addr32[3] == inst32);
+ check(addr32[4] == 0);
+
+ /* Test single page 64-bit repeated instruction */
+ if (IS_ENABLED(CONFIG_PPC64)) {
+ check(ppc_inst_prefixed(inst64));
+
+ addr64 = buf + PAGE_SIZE * 2;
+ ppc_inst_write(code, inst64);
+ check(!patch_instructions((u32 *)(addr64 + 1), code, 24, true));
+
+ check(addr64[0] == 0);
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[1]), inst64));
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[2]), inst64));
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[3]), inst64));
+ check(addr64[4] == 0);
+ }
+
+ /* Test single page memcpy */
+ addr32 = buf + PAGE_SIZE * 3;
+
+ for (int i = 0; i < ARRAY_SIZE(code); i++)
+ code[i] = i + 1;
+
+ check(!patch_instructions(addr32 + 1, code, sizeof(code), false));
+
+ check(addr32[0] == 0);
+ check(!memcmp(&addr32[1], code, sizeof(code)));
+ check(addr32[ARRAY_SIZE(code) + 1] == 0);
+
+ /* Test multipage 32-bit repeated instruction */
+ addr32 = buf + PAGE_SIZE * 4 - 8;
+ check(!patch_instructions(addr32 + 1, &inst32, 12, true));
+
+ check(addr32[0] == 0);
+ check(addr32[1] == inst32);
+ check(addr32[2] == inst32);
+ check(addr32[3] == inst32);
+ check(addr32[4] == 0);
+
+ /* Test multipage 64-bit repeated instruction */
+ if (IS_ENABLED(CONFIG_PPC64)) {
+ check(ppc_inst_prefixed(inst64));
+
+ addr64 = buf + PAGE_SIZE * 5 - 8;
+ ppc_inst_write(code, inst64);
+ check(!patch_instructions((u32 *)(addr64 + 1), code, 24, true));
+
+ check(addr64[0] == 0);
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[1]), inst64));
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[2]), inst64));
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[3]), inst64));
+ check(addr64[4] == 0);
+ }
+
+ /* Test multipage memcpy */
+ addr32 = buf + PAGE_SIZE * 6 - 12;
+
+ for (int i = 0; i < ARRAY_SIZE(code); i++)
+ code[i] = i + 1;
+
+ check(!patch_instructions(addr32 + 1, code, sizeof(code), false));
+
+ check(addr32[0] == 0);
+ check(!memcmp(&addr32[1], code, sizeof(code)));
+ check(addr32[ARRAY_SIZE(code) + 1] == 0);
+
+ vfree(buf);
+}
+
+static void __init test_data_patching(void)
+{
+ void *buf;
+ u32 *addr32;
+
+ buf = vzalloc(PAGE_SIZE);
+ check(buf);
+ if (!buf)
+ return;
+
+ addr32 = buf + 128;
+
+ addr32[1] = 0xA0A1A2A3;
+ addr32[2] = 0xB0B1B2B3;
+
+ check(!patch_uint(&addr32[1], 0xC0C1C2C3));
+
+ check(addr32[0] == 0);
+ check(addr32[1] == 0xC0C1C2C3);
+ check(addr32[2] == 0xB0B1B2B3);
+ check(addr32[3] == 0);
+
+ /* Unaligned patch_ulong() should fail */
+ if (IS_ENABLED(CONFIG_PPC64))
+ check(patch_ulong(&addr32[1], 0xD0D1D2D3) == -EINVAL);
+
+ check(!patch_ulong(&addr32[2], 0xD0D1D2D3));
+
+ check(addr32[0] == 0);
+ check(addr32[1] == 0xC0C1C2C3);
+ check(*(unsigned long *)(&addr32[2]) == 0xD0D1D2D3);
+
+ if (!IS_ENABLED(CONFIG_PPC64))
+ check(addr32[3] == 0);
+
+ check(addr32[4] == 0);
+
+ vfree(buf);
+}
+
static int __init test_code_patching(void)
{
pr_info("Running code patching self-tests ...\n");
@@ -356,6 +487,8 @@ static int __init test_code_patching(void)
test_create_function_call();
test_translate_branch();
test_prefixed_patching();
+ test_multi_instruction_patching();
+ test_data_patching();
return 0;
}
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 23c7805fb7b3..66b5b4fa1686 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -11,7 +11,7 @@
#include <asm/cpu_has_feature.h>
#include <asm/sstep.h>
#include <asm/ppc-opcode.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/inst.h>
#define MAX_SUBTESTS 16
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index d491da8d1838..58ed6bd613a6 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -45,7 +45,7 @@ int exit_vmx_usercopy(void)
* set and we are preemptible. The hack here is to schedule a
* decrementer to fire here and reschedule for us if necessary.
*/
- if (IS_ENABLED(CONFIG_PREEMPT) && need_resched())
+ if (IS_ENABLED(CONFIG_PREEMPTION) && need_resched())
set_dec(1);
return 0;
}
generated by cgit (git 2.34.1) at 2025-03-23 06:23:18 +0000