From: Ard Biesheuvel
mainline inclusion
from mainline-v5.13-rc1
commit 13150149aa6d
category: bugfix
issue: #I3ZXZF
CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
-----------------------------------------------
Kernel mode NEON can be used in task or softirq context, but only in
a non-nesting manner, i.e., softirq context is only permitted if the
interrupt was not taken at a point where the kernel was using the NEON
in task context.
This means all users of kernel mode NEON have to be aware of this
limitation, and either need to provide scalar fallbacks that may be much
slower (up to 20x for AES instructions) and potentially less safe, or
use an asynchronous interface that defers processing to a later time
when the NEON is guaranteed to be available.
Given that grabbing and releasing the NEON is cheap, we can relax this
restriction, by increasing the granularity of kernel mode NEON code, and
always disabling softirq processing while the NEON is being used in task
context.
Signed-off-by: Ard Biesheuvel
Acked-by: Will Deacon
Link: https://lore.kernel.org/r/20210302090118.30666-4-ardb@kernel.org
Signed-off-by: Catalin Marinas
Signed-off-by: Wei Li
Reviewed-by: Jason Yan
Reviewed-by: Hanjun Guo
Signed-off-by: Chen Jun
Signed-off-by: Yu Changchun
---
arch/arm64/crypto/aes-modes.S | 2 +-
arch/arm64/crypto/sha1-ce-core.S | 2 +-
arch/arm64/crypto/sha2-ce-core.S | 2 +-
arch/arm64/crypto/sha3-ce-core.S | 4 ++--
arch/arm64/crypto/sha512-ce-core.S | 2 +-
arch/arm64/include/asm/assembler.h | 28 +++++++++++++++++++++-------
arch/arm64/kernel/asm-offsets.c | 2 ++
arch/arm64/kernel/fpsimd.c | 4 ++--
8 files changed, 31 insertions(+), 15 deletions(-)
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index ab570aa86a5c..503d9b31795c 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -641,7 +641,7 @@ AES_FUNC_START(aes_mac_update)
cbz w5, .Lmacout
encrypt_block v0, w2, x1, x7, w8
st1 {v0.16b}, [x4] /* return dg */
- cond_yield .Lmacout, x7
+ cond_yield .Lmacout, x7, x8
b .Lmacloop4x
.Lmac1x:
add w3, w3, #4
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 8c02bbc2684e..889ca0f8972b 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -121,7 +121,7 @@ CPU_LE( rev32 v11.16b, v11.16b )
add dgav.4s, dgav.4s, dg0v.4s
cbz w2, 2f
- cond_yield 3f, x5
+ cond_yield 3f, x5, x6
b 0b
/*
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 6cdea7d56059..491179922f49 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -129,7 +129,7 @@ CPU_LE( rev32 v19.16b, v19.16b )
/* handled all input blocks? */
cbz w2, 2f
- cond_yield 3f, x5
+ cond_yield 3f, x5, x6
b 0b
/*
diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S
index 6f5208414fe3..9c77313f5a60 100644
--- a/arch/arm64/crypto/sha3-ce-core.S
+++ b/arch/arm64/crypto/sha3-ce-core.S
@@ -184,11 +184,11 @@ SYM_FUNC_START(sha3_ce_transform)
eor v0.16b, v0.16b, v31.16b
cbnz w8, 3b
- cond_yield 3f, x8
+ cond_yield 4f, x8, x9
cbnz w2, 0b
/* save state */
-3: st1 { v0.1d- v3.1d}, [x0], #32
+4: st1 { v0.1d- v3.1d}, [x0], #32
st1 { v4.1d- v7.1d}, [x0], #32
st1 { v8.1d-v11.1d}, [x0], #32
st1 {v12.1d-v15.1d}, [x0], #32
diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S
index d6e7f6c95fa6..b6a3a36e15f5 100644
--- a/arch/arm64/crypto/sha512-ce-core.S
+++ b/arch/arm64/crypto/sha512-ce-core.S
@@ -195,7 +195,7 @@ CPU_LE( rev64 v19.16b, v19.16b )
add v10.2d, v10.2d, v2.2d
add v11.2d, v11.2d, v3.2d
- cond_yield 3f, x4
+ cond_yield 3f, x4, x5
/* handled all input blocks? */
cbnz w2, 0b
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 21d679bf1e55..c7b9b859a860 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -15,6 +15,7 @@
#include
#include
+#include
#include
#include
#include
@@ -684,19 +685,32 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU
.endm
/*
- * Check whether preempt-disabled code should yield as soon as it
- * is able. This is the case if re-enabling preemption a single
- * time results in a preempt count of zero, and the TIF_NEED_RESCHED
- * flag is set. (Note that the latter is stored negated in the
- * top word of the thread_info::preempt_count field)
+ * Check whether preempt/bh-disabled asm code should yield as soon as
+ * it is able. This is the case if we are currently running in task
+ * context, and either a softirq is pending, or the TIF_NEED_RESCHED
+ * flag is set and re-enabling preemption a single time would result in
+ * a preempt count of zero. (Note that the TIF_NEED_RESCHED flag is
+ * stored negated in the top word of the thread_info::preempt_count
+ * field)
*/
- .macro cond_yield, lbl:req, tmp:req
-#ifdef CONFIG_PREEMPTION
+ .macro cond_yield, lbl:req, tmp:req, tmp2:req
get_current_task \tmp
ldr \tmp, [\tmp, #TSK_TI_PREEMPT]
+ /*
+ * If we are serving a softirq, there is no point in yielding: the
+ * softirq will not be preempted no matter what we do, so we should
+ * run to completion as quickly as we can.
+ */
+ tbnz \tmp, #SOFTIRQ_SHIFT, .Lnoyield_\@
+#ifdef CONFIG_PREEMPTION
sub \tmp, \tmp, #PREEMPT_DISABLE_OFFSET
cbz \tmp, \lbl
#endif
+ adr_l \tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING
+ this_cpu_offset \tmp2
+ ldr w\tmp, [\tmp, \tmp2]
+ cbnz w\tmp, \lbl // yield on pending softirq in task context
+.Lnoyield_\@:
.endm
/*
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 7d32fc959b1a..34ef70877de4 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -93,6 +93,8 @@ int main(void)
DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE);
BLANK();
DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET);
+ DEFINE(SOFTIRQ_SHIFT, SOFTIRQ_SHIFT);
+ DEFINE(IRQ_CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
BLANK();
DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack));
DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task));
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 062b21f30f94..823e3a8a8871 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -180,7 +180,7 @@ static void __get_cpu_fpsimd_context(void)
*/
static void get_cpu_fpsimd_context(void)
{
- preempt_disable();
+ local_bh_disable();
__get_cpu_fpsimd_context();
}
@@ -201,7 +201,7 @@ static void __put_cpu_fpsimd_context(void)
static void put_cpu_fpsimd_context(void)
{
__put_cpu_fpsimd_context();
- preempt_enable();
+ local_bh_enable();
}
static bool have_cpu_fpsimd_context(void)
--
2.22.0