summaryrefslogtreecommitdiffstats
path: root/lib
diff options
context:
space:
mode:
Diffstat (limited to 'lib')
-rw-r--r--lib/Kconfig.debug34
-rw-r--r--lib/assoc_array.c2
-rw-r--r--lib/debugobjects.c3
-rw-r--r--lib/locking-selftest.c123
-rw-r--r--lib/mpi/mpicoder.c4
-rw-r--r--lib/radix-tree.c1
-rw-r--r--lib/raid6/Makefile4
-rw-r--r--lib/raid6/algos.c3
-rw-r--r--lib/raid6/neon.uc33
-rw-r--r--lib/raid6/recov_neon.c110
-rw-r--r--lib/raid6/recov_neon_inner.c117
-rw-r--r--lib/swiotlb.c57
12 files changed, 472 insertions, 19 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 98fe715..7396f50 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -374,6 +374,9 @@ config STACK_VALIDATION
pointers (if CONFIG_FRAME_POINTER is enabled). This helps ensure
that runtime stack traces are more reliable.
+ This is also a prerequisite for generation of ORC unwind data, which
+ is needed for CONFIG_ORC_UNWINDER.
+
For more information, see
tools/objtool/Documentation/stack-validation.txt.
@@ -798,6 +801,13 @@ config HARDLOCKUP_DETECTOR_PERF
select SOFTLOCKUP_DETECTOR
#
+# Enables a timestamp based low pass filter to compensate for perf based
+# hard lockup detection which runs too fast due to turbo modes.
+#
+config HARDLOCKUP_CHECK_TIMESTAMP
+ bool
+
+#
# arch/ can define HAVE_HARDLOCKUP_DETECTOR_ARCH to provide their own hard
# lockup detector rather than the perf based detector.
#
@@ -1081,6 +1091,8 @@ config PROVE_LOCKING
select DEBUG_MUTEXES
select DEBUG_RT_MUTEXES if RT_MUTEXES
select DEBUG_LOCK_ALLOC
+ select LOCKDEP_CROSSRELEASE
+ select LOCKDEP_COMPLETIONS
select TRACE_IRQFLAGS
default n
help
@@ -1121,7 +1133,7 @@ config LOCKDEP
bool
depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
select STACKTRACE
- select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !SCORE
+ select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !SCORE && !X86
select KALLSYMS
select KALLSYMS_ALL
@@ -1150,6 +1162,22 @@ config LOCK_STAT
CONFIG_LOCK_STAT defines "contended" and "acquired" lock events.
(CONFIG_LOCKDEP defines "acquire" and "release" events.)
+config LOCKDEP_CROSSRELEASE
+ bool
+ help
+ This makes lockdep work for crosslock which is a lock allowed to
+ be released in a different context from the acquisition context.
+ Normally a lock must be released in the context acquiring the lock.
+ However, relexing this constraint helps synchronization primitives
+ such as page locks or completions can use the lock correctness
+ detector, lockdep.
+
+config LOCKDEP_COMPLETIONS
+ bool
+ help
+ A deadlock caused by wait_for_completion() and complete() can be
+ detected by lockdep using crossrelease feature.
+
config DEBUG_LOCKDEP
bool "Lock dependency engine debugging"
depends on DEBUG_KERNEL && LOCKDEP
@@ -1540,7 +1568,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
depends on !X86_64
select STACKTRACE
- select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !SCORE
+ select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !SCORE && !X86
help
Provide stacktrace filter for fault-injection capabilities
@@ -1549,7 +1577,7 @@ config LATENCYTOP
depends on DEBUG_KERNEL
depends on STACKTRACE_SUPPORT
depends on PROC_FS
- select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC
+ select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !X86
select KALLSYMS
select KALLSYMS_ALL
select STACKTRACE
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index 59fd7c0..155c55d 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -1,6 +1,6 @@
/* Generic associative array implementation.
*
- * See Documentation/assoc_array.txt for information.
+ * See Documentation/core-api/assoc_array.rst for information.
*
* Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 17afb04..2f5349c 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -18,6 +18,7 @@
#include <linux/debugfs.h>
#include <linux/slab.h>
#include <linux/hash.h>
+#include <linux/kmemleak.h>
#define ODEBUG_HASH_BITS 14
#define ODEBUG_HASH_SIZE (1 << ODEBUG_HASH_BITS)
@@ -110,6 +111,7 @@ static void fill_pool(void)
if (!new)
return;
+ kmemleak_ignore(new);
raw_spin_lock_irqsave(&pool_lock, flags);
hlist_add_head(&new->node, &obj_pool);
debug_objects_allocated++;
@@ -1080,6 +1082,7 @@ static int __init debug_objects_replace_static_objects(void)
obj = kmem_cache_zalloc(obj_cache, GFP_KERNEL);
if (!obj)
goto free;
+ kmemleak_ignore(obj);
hlist_add_head(&obj->node, &objects);
}
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 6f2b135..cd0b5c9 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -363,6 +363,103 @@ static void rsem_AA3(void)
}
/*
+ * read_lock(A)
+ * spin_lock(B)
+ * spin_lock(B)
+ * write_lock(A)
+ */
+static void rlock_ABBA1(void)
+{
+ RL(X1);
+ L(Y1);
+ U(Y1);
+ RU(X1);
+
+ L(Y1);
+ WL(X1);
+ WU(X1);
+ U(Y1); // should fail
+}
+
+static void rwsem_ABBA1(void)
+{
+ RSL(X1);
+ ML(Y1);
+ MU(Y1);
+ RSU(X1);
+
+ ML(Y1);
+ WSL(X1);
+ WSU(X1);
+ MU(Y1); // should fail
+}
+
+/*
+ * read_lock(A)
+ * spin_lock(B)
+ * spin_lock(B)
+ * read_lock(A)
+ */
+static void rlock_ABBA2(void)
+{
+ RL(X1);
+ L(Y1);
+ U(Y1);
+ RU(X1);
+
+ L(Y1);
+ RL(X1);
+ RU(X1);
+ U(Y1); // should NOT fail
+}
+
+static void rwsem_ABBA2(void)
+{
+ RSL(X1);
+ ML(Y1);
+ MU(Y1);
+ RSU(X1);
+
+ ML(Y1);
+ RSL(X1);
+ RSU(X1);
+ MU(Y1); // should fail
+}
+
+
+/*
+ * write_lock(A)
+ * spin_lock(B)
+ * spin_lock(B)
+ * write_lock(A)
+ */
+static void rlock_ABBA3(void)
+{
+ WL(X1);
+ L(Y1);
+ U(Y1);
+ WU(X1);
+
+ L(Y1);
+ WL(X1);
+ WU(X1);
+ U(Y1); // should fail
+}
+
+static void rwsem_ABBA3(void)
+{
+ WSL(X1);
+ ML(Y1);
+ MU(Y1);
+ WSU(X1);
+
+ ML(Y1);
+ WSL(X1);
+ WSU(X1);
+ MU(Y1); // should fail
+}
+
+/*
* ABBA deadlock:
*/
@@ -1056,8 +1153,6 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask)
if (debug_locks != expected) {
unexpected_testcase_failures++;
pr_cont("FAILED|");
-
- dump_stack();
} else {
testcase_successes++;
pr_cont(" ok |");
@@ -1933,6 +2028,30 @@ void locking_selftest(void)
dotest(rsem_AA3, FAILURE, LOCKTYPE_RWSEM);
pr_cont("\n");
+ print_testname("mixed read-lock/lock-write ABBA");
+ pr_cont(" |");
+ dotest(rlock_ABBA1, FAILURE, LOCKTYPE_RWLOCK);
+ /*
+ * Lockdep does indeed fail here, but there's nothing we can do about
+ * that now. Don't kill lockdep for it.
+ */
+ unexpected_testcase_failures--;
+
+ pr_cont(" |");
+ dotest(rwsem_ABBA1, FAILURE, LOCKTYPE_RWSEM);
+
+ print_testname("mixed read-lock/lock-read ABBA");
+ pr_cont(" |");
+ dotest(rlock_ABBA2, SUCCESS, LOCKTYPE_RWLOCK);
+ pr_cont(" |");
+ dotest(rwsem_ABBA2, FAILURE, LOCKTYPE_RWSEM);
+
+ print_testname("mixed write-lock/lock-write ABBA");
+ pr_cont(" |");
+ dotest(rlock_ABBA3, FAILURE, LOCKTYPE_RWLOCK);
+ pr_cont(" |");
+ dotest(rwsem_ABBA3, FAILURE, LOCKTYPE_RWSEM);
+
printk(" --------------------------------------------------------------------------\n");
/*
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 5a0f75a..eead4b3 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -364,11 +364,11 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
}
miter.consumed = lzeros;
- sg_miter_stop(&miter);
nbytes -= lzeros;
nbits = nbytes * 8;
if (nbits > MAX_EXTERN_MPI_BITS) {
+ sg_miter_stop(&miter);
pr_info("MPI: mpi too large (%u bits)\n", nbits);
return NULL;
}
@@ -376,6 +376,8 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
if (nbytes > 0)
nbits -= count_leading_zeros(*buff) - (BITS_PER_LONG - 8);
+ sg_miter_stop(&miter);
+
nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
val = mpi_alloc(nlimbs);
if (!val)
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 898e879..3527eb3 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -2022,6 +2022,7 @@ void radix_tree_iter_delete(struct radix_tree_root *root,
if (__radix_tree_delete(root, iter->node, slot))
iter->index = iter->next_index;
}
+EXPORT_SYMBOL(radix_tree_iter_delete);
/**
* radix_tree_delete_item - delete an item from a radix tree
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 3057011..a93adf6 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -5,7 +5,7 @@ raid6_pq-y += algos.o recov.o tables.o int1.o int2.o int4.o \
raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o avx512.o recov_avx512.o
raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
-raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o
+raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
raid6_pq-$(CONFIG_TILEGX) += tilegx8.o
raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
@@ -26,7 +26,9 @@ NEON_FLAGS := -ffreestanding
ifeq ($(ARCH),arm)
NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon
endif
+CFLAGS_recov_neon_inner.o += $(NEON_FLAGS)
ifeq ($(ARCH),arm64)
+CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only
CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only
CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only
CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 7857049..4769947 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -113,6 +113,9 @@ const struct raid6_recov_calls *const raid6_recov_algos[] = {
#ifdef CONFIG_S390
&raid6_recov_s390xc,
#endif
+#if defined(CONFIG_KERNEL_MODE_NEON)
+ &raid6_recov_neon,
+#endif
&raid6_recov_intx1,
NULL
};
diff --git a/lib/raid6/neon.uc b/lib/raid6/neon.uc
index 4fa51b7..d5242f5 100644
--- a/lib/raid6/neon.uc
+++ b/lib/raid6/neon.uc
@@ -46,8 +46,12 @@ static inline unative_t SHLBYTE(unative_t v)
*/
static inline unative_t MASK(unative_t v)
{
- const uint8x16_t temp = NBYTES(0);
- return (unative_t)vcltq_s8((int8x16_t)v, (int8x16_t)temp);
+ return (unative_t)vshrq_n_s8((int8x16_t)v, 7);
+}
+
+static inline unative_t PMUL(unative_t v, unative_t u)
+{
+ return (unative_t)vmulq_p8((poly8x16_t)v, (poly8x16_t)u);
}
void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
@@ -110,7 +114,30 @@ void raid6_neon$#_xor_syndrome_real(int disks, int start, int stop,
wq$$ = veorq_u8(w1$$, wd$$);
}
/* P/Q left side optimization */
- for ( z = start-1 ; z >= 0 ; z-- ) {
+ for ( z = start-1 ; z >= 3 ; z -= 4 ) {
+ w2$$ = vshrq_n_u8(wq$$, 4);
+ w1$$ = vshlq_n_u8(wq$$, 4);
+
+ w2$$ = PMUL(w2$$, x1d);
+ wq$$ = veorq_u8(w1$$, w2$$);
+ }
+
+ switch (z) {
+ case 2:
+ w2$$ = vshrq_n_u8(wq$$, 5);
+ w1$$ = vshlq_n_u8(wq$$, 3);
+
+ w2$$ = PMUL(w2$$, x1d);
+ wq$$ = veorq_u8(w1$$, w2$$);
+ break;
+ case 1:
+ w2$$ = vshrq_n_u8(wq$$, 6);
+ w1$$ = vshlq_n_u8(wq$$, 2);
+
+ w2$$ = PMUL(w2$$, x1d);
+ wq$$ = veorq_u8(w1$$, w2$$);
+ break;
+ case 0:
w2$$ = MASK(wq$$);
w1$$ = SHLBYTE(wq$$);
diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c
new file mode 100644
index 0000000..eeb5c40
--- /dev/null
+++ b/lib/raid6/recov_neon.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2012 Intel Corporation
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/raid/pq.h>
+
+#ifdef __KERNEL__
+#include <asm/neon.h>
+#else
+#define kernel_neon_begin()
+#define kernel_neon_end()
+#define cpu_has_neon() (1)
+#endif
+
+static int raid6_has_neon(void)
+{
+ return cpu_has_neon();
+}
+
+void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
+ uint8_t *dq, const uint8_t *pbmul,
+ const uint8_t *qmul);
+
+void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
+ const uint8_t *qmul);
+
+static void raid6_2data_recov_neon(int disks, size_t bytes, int faila,
+ int failb, void **ptrs)
+{
+ u8 *p, *q, *dp, *dq;
+ const u8 *pbmul; /* P multiplier table for B data */
+ const u8 *qmul; /* Q multiplier table (for both) */
+
+ p = (u8 *)ptrs[disks - 2];
+ q = (u8 *)ptrs[disks - 1];
+
+ /*
+ * Compute syndrome with zero for the missing data pages
+ * Use the dead data pages as temporary storage for
+ * delta p and delta q
+ */
+ dp = (u8 *)ptrs[faila];
+ ptrs[faila] = (void *)raid6_empty_zero_page;
+ ptrs[disks - 2] = dp;
+ dq = (u8 *)ptrs[failb];
+ ptrs[failb] = (void *)raid6_empty_zero_page;
+ ptrs[disks - 1] = dq;
+
+ raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+ /* Restore pointer table */
+ ptrs[faila] = dp;
+ ptrs[failb] = dq;
+ ptrs[disks - 2] = p;
+ ptrs[disks - 1] = q;
+
+ /* Now, pick the proper data tables */
+ pbmul = raid6_vgfmul[raid6_gfexi[failb-faila]];
+ qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
+ raid6_gfexp[failb]]];
+
+ kernel_neon_begin();
+ __raid6_2data_recov_neon(bytes, p, q, dp, dq, pbmul, qmul);
+ kernel_neon_end();
+}
+
+static void raid6_datap_recov_neon(int disks, size_t bytes, int faila,
+ void **ptrs)
+{
+ u8 *p, *q, *dq;
+ const u8 *qmul; /* Q multiplier table */
+
+ p = (u8 *)ptrs[disks - 2];
+ q = (u8 *)ptrs[disks - 1];
+
+ /*
+ * Compute syndrome with zero for the missing data page
+ * Use the dead data page as temporary storage for delta q
+ */
+ dq = (u8 *)ptrs[faila];
+ ptrs[faila] = (void *)raid6_empty_zero_page;
+ ptrs[disks - 1] = dq;
+
+ raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+ /* Restore pointer table */
+ ptrs[faila] = dq;
+ ptrs[disks - 1] = q;
+
+ /* Now, pick the proper data tables */
+ qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
+
+ kernel_neon_begin();
+ __raid6_datap_recov_neon(bytes, p, q, dq, qmul);
+ kernel_neon_end();
+}
+
+const struct raid6_recov_calls raid6_recov_neon = {
+ .data2 = raid6_2data_recov_neon,
+ .datap = raid6_datap_recov_neon,
+ .valid = raid6_has_neon,
+ .name = "neon",
+ .priority = 10,
+};
diff --git a/lib/raid6/recov_neon_inner.c b/lib/raid6/recov_neon_inner.c
new file mode 100644
index 0000000..8cd20c9
--- /dev/null
+++ b/lib/raid6/recov_neon_inner.c
@@ -0,0 +1,117 @@
+/*
+ * Copyright (C) 2012 Intel Corporation
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <arm_neon.h>
+
+static const uint8x16_t x0f = {
+ 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
+ 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
+};
+
+#ifdef CONFIG_ARM
+/*
+ * AArch32 does not provide this intrinsic natively because it does not
+ * implement the underlying instruction. AArch32 only provides a 64-bit
+ * wide vtbl.8 instruction, so use that instead.
+ */
+static uint8x16_t vqtbl1q_u8(uint8x16_t a, uint8x16_t b)
+{
+ union {
+ uint8x16_t val;
+ uint8x8x2_t pair;
+ } __a = { a };
+
+ return vcombine_u8(vtbl2_u8(__a.pair, vget_low_u8(b)),
+ vtbl2_u8(__a.pair, vget_high_u8(b)));
+}
+#endif
+
+void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
+ uint8_t *dq, const uint8_t *pbmul,
+ const uint8_t *qmul)
+{
+ uint8x16_t pm0 = vld1q_u8(pbmul);
+ uint8x16_t pm1 = vld1q_u8(pbmul + 16);
+ uint8x16_t qm0 = vld1q_u8(qmul);
+ uint8x16_t qm1 = vld1q_u8(qmul + 16);
+
+ /*
+ * while ( bytes-- ) {
+ * uint8_t px, qx, db;
+ *
+ * px = *p ^ *dp;
+ * qx = qmul[*q ^ *dq];
+ * *dq++ = db = pbmul[px] ^ qx;
+ * *dp++ = db ^ px;
+ * p++; q++;
+ * }
+ */
+
+ while (bytes) {
+ uint8x16_t vx, vy, px, qx, db;
+
+ px = veorq_u8(vld1q_u8(p), vld1q_u8(dp));
+ vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
+
+ vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4);
+ vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
+ vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f));
+ qx = veorq_u8(vx, vy);
+
+ vy = (uint8x16_t)vshrq_n_s16((int16x8_t)px, 4);
+ vx = vqtbl1q_u8(pm0, vandq_u8(px, x0f));
+ vy = vqtbl1q_u8(pm1, vandq_u8(vy, x0f));
+ vx = veorq_u8(vx, vy);
+ db = veorq_u8(vx, qx);
+
+ vst1q_u8(dq, db);
+ vst1q_u8(dp, veorq_u8(db, px));
+
+ bytes -= 16;
+ p += 16;
+ q += 16;
+ dp += 16;
+ dq += 16;
+ }
+}
+
+void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
+ const uint8_t *qmul)
+{
+ uint8x16_t qm0 = vld1q_u8(qmul);
+ uint8x16_t qm1 = vld1q_u8(qmul + 16);
+
+ /*
+ * while (bytes--) {
+ * *p++ ^= *dq = qmul[*q ^ *dq];
+ * q++; dq++;
+ * }
+ */
+
+ while (bytes) {
+ uint8x16_t vx, vy;
+
+ vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
+
+ vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4);
+ vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
+ vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f));
+ vx = veorq_u8(vx, vy);
+ vy = veorq_u8(vx, vld1q_u8(p));
+
+ vst1q_u8(dq, vx);
+ vst1q_u8(p, vy);
+
+ bytes -= 16;
+ p += 16;
+ q += 16;
+ dq += 16;
+ }
+}
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index a8d74a7..8c6c83e 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -30,6 +30,7 @@
#include <linux/highmem.h>
#include <linux/gfp.h>
#include <linux/scatterlist.h>
+#include <linux/mem_encrypt.h>
#include <asm/io.h>
#include <asm/dma.h>
@@ -155,6 +156,15 @@ unsigned long swiotlb_size_or_default(void)
return size ? size : (IO_TLB_DEFAULT_SIZE);
}
+void __weak swiotlb_set_mem_attributes(void *vaddr, unsigned long size) { }
+
+/* For swiotlb, clear memory encryption mask from dma addresses */
+static dma_addr_t swiotlb_phys_to_dma(struct device *hwdev,
+ phys_addr_t address)
+{
+ return __sme_clr(phys_to_dma(hwdev, address));
+}
+
/* Note that this doesn't work with highmem page */
static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
volatile void *address)
@@ -183,6 +193,31 @@ void swiotlb_print_info(void)
bytes >> 20, vstart, vend - 1);
}
+/*
+ * Early SWIOTLB allocation may be too early to allow an architecture to
+ * perform the desired operations. This function allows the architecture to
+ * call SWIOTLB when the operations are possible. It needs to be called
+ * before the SWIOTLB memory is used.
+ */
+void __init swiotlb_update_mem_attributes(void)
+{
+ void *vaddr;
+ unsigned long bytes;
+
+ if (no_iotlb_memory || late_alloc)
+ return;
+
+ vaddr = phys_to_virt(io_tlb_start);
+ bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
+ swiotlb_set_mem_attributes(vaddr, bytes);
+ memset(vaddr, 0, bytes);
+
+ vaddr = phys_to_virt(io_tlb_overflow_buffer);
+ bytes = PAGE_ALIGN(io_tlb_overflow);
+ swiotlb_set_mem_attributes(vaddr, bytes);
+ memset(vaddr, 0, bytes);
+}
+
int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
{
void *v_overflow_buffer;
@@ -320,6 +355,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
io_tlb_start = virt_to_phys(tlb);
io_tlb_end = io_tlb_start + bytes;
+ swiotlb_set_mem_attributes(tlb, bytes);
memset(tlb, 0, bytes);
/*
@@ -330,6 +366,8 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
if (!v_overflow_buffer)
goto cleanup2;
+ swiotlb_set_mem_attributes(v_overflow_buffer, io_tlb_overflow);
+ memset(v_overflow_buffer, 0, io_tlb_overflow);
io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
/*
@@ -469,6 +507,9 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
if (no_iotlb_memory)
panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+ if (sme_active())
+ pr_warn_once("SME is active and system is using DMA bounce buffers\n");
+
mask = dma_get_seg_boundary(hwdev);
tbl_dma_addr &= mask;
@@ -581,7 +622,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size,
return SWIOTLB_MAP_ERROR;
}
- start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
+ start_dma_addr = swiotlb_phys_to_dma(hwdev, io_tlb_start);
return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
dir, attrs);
}
@@ -702,7 +743,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
goto err_warn;
ret = phys_to_virt(paddr);
- dev_addr = phys_to_dma(hwdev, paddr);
+ dev_addr = swiotlb_phys_to_dma(hwdev, paddr);
/* Confirm address can be DMA'd by device */
if (dev_addr + size - 1 > dma_mask) {
@@ -812,10 +853,10 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
map = map_single(dev, phys, size, dir, attrs);
if (map == SWIOTLB_MAP_ERROR) {
swiotlb_full(dev, size, dir, 1);
- return phys_to_dma(dev, io_tlb_overflow_buffer);
+ return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
}
- dev_addr = phys_to_dma(dev, map);
+ dev_addr = swiotlb_phys_to_dma(dev, map);
/* Ensure that the address returned is DMA'ble */
if (dma_capable(dev, dev_addr, size))
@@ -824,7 +865,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
attrs |= DMA_ATTR_SKIP_CPU_SYNC;
swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
- return phys_to_dma(dev, io_tlb_overflow_buffer);
+ return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
}
EXPORT_SYMBOL_GPL(swiotlb_map_page);
@@ -958,7 +999,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
sg_dma_len(sgl) = 0;
return 0;
}
- sg->dma_address = phys_to_dma(hwdev, map);
+ sg->dma_address = swiotlb_phys_to_dma(hwdev, map);
} else
sg->dma_address = dev_addr;
sg_dma_len(sg) = sg->length;
@@ -1026,7 +1067,7 @@ EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
int
swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
{
- return (dma_addr == phys_to_dma(hwdev, io_tlb_overflow_buffer));
+ return (dma_addr == swiotlb_phys_to_dma(hwdev, io_tlb_overflow_buffer));
}
EXPORT_SYMBOL(swiotlb_dma_mapping_error);
@@ -1039,6 +1080,6 @@ EXPORT_SYMBOL(swiotlb_dma_mapping_error);
int
swiotlb_dma_supported(struct device *hwdev, u64 mask)
{
- return phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
+ return swiotlb_phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
}
EXPORT_SYMBOL(swiotlb_dma_supported);
OpenPOWER on IntegriCloud