From: Paul Burton <paul.burton@mips.com>
To: "linux-mips@vger.kernel.org" <linux-mips@vger.kernel.org>
Cc: Huacai Chen <chenhc@lemote.com>,
Jiaxun Yang <jiaxun.yang@flygoat.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Paul Burton <pburton@wavecomp.com>
Subject: [PATCH v2 12/36] MIPS: atomic: Emit Loongson3 sync workarounds within asm
Date: Tue, 1 Oct 2019 21:53:20 +0000 [thread overview]
Message-ID: <20191001215249.4157062-13-paul.burton@mips.com> (raw)
In-Reply-To: <20191001215249.4157062-1-paul.burton@mips.com>
Generate the sync instructions required to workaround Loongson3 LL/SC
errata within inline asm blocks, which feels a little safer than doing
it from C where strictly speaking the compiler would be well within its
rights to insert a memory access between the separate asm statements we
previously had, containing sync & ll instructions respectively.
Signed-off-by: Paul Burton <paul.burton@mips.com>
---
Changes in v2: None
arch/mips/include/asm/atomic.h | 20 ++++++++++++++------
1 file changed, 14 insertions(+), 6 deletions(-)
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index b834af5a7382..841ff274ada6 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -21,6 +21,7 @@
#include <asm/cpu-features.h>
#include <asm/cmpxchg.h>
#include <asm/llsc.h>
+#include <asm/sync.h>
#include <asm/war.h>
#define ATOMIC_INIT(i) { (i) }
@@ -56,10 +57,10 @@ static __inline__ void pfx##_##op(type i, pfx##_t * v) \
return; \
} \
\
- loongson_llsc_mb(); \
__asm__ __volatile__( \
" .set push \n" \
" .set " MIPS_ISA_LEVEL " \n" \
+ " " __SYNC(full, loongson3_war) " \n" \
"1: " #ll " %0, %1 # " #pfx "_" #op " \n" \
" " #asm_op " %0, %2 \n" \
" " #sc " %0, %1 \n" \
@@ -85,10 +86,10 @@ static __inline__ type pfx##_##op##_return_relaxed(type i, pfx##_t * v) \
return result; \
} \
\
- loongson_llsc_mb(); \
__asm__ __volatile__( \
" .set push \n" \
" .set " MIPS_ISA_LEVEL " \n" \
+ " " __SYNC(full, loongson3_war) " \n" \
"1: " #ll " %1, %2 # " #pfx "_" #op "_return\n" \
" " #asm_op " %0, %1, %3 \n" \
" " #sc " %0, %2 \n" \
@@ -117,10 +118,10 @@ static __inline__ type pfx##_fetch_##op##_relaxed(type i, pfx##_t * v) \
return result; \
} \
\
- loongson_llsc_mb(); \
__asm__ __volatile__( \
" .set push \n" \
" .set " MIPS_ISA_LEVEL " \n" \
+ " " __SYNC(full, loongson3_war) " \n" \
"1: " #ll " %1, %2 # " #pfx "_fetch_" #op "\n" \
" " #asm_op " %0, %1, %3 \n" \
" " #sc " %0, %2 \n" \
@@ -200,10 +201,10 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
if (kernel_uses_llsc) {
int temp;
- loongson_llsc_mb();
__asm__ __volatile__(
" .set push \n"
" .set "MIPS_ISA_LEVEL" \n"
+ " " __SYNC(full, loongson3_war) " \n"
"1: ll %1, %2 # atomic_sub_if_positive\n"
" .set pop \n"
" subu %0, %1, %3 \n"
@@ -213,7 +214,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
" .set "MIPS_ISA_LEVEL" \n"
" sc %1, %2 \n"
"\t" __SC_BEQZ "%1, 1b \n"
- "2: \n"
+ "2: " __SYNC(full, loongson3_war) " \n"
" .set pop \n"
: "=&r" (result), "=&r" (temp),
"+" GCC_OFF_SMALL_ASM() (v->counter)
@@ -229,7 +230,14 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
raw_local_irq_restore(flags);
}
- smp_llsc_mb();
+ /*
+ * In the Loongson3 workaround case we already have a completion
+ * barrier at 2: above, which is needed due to the bltz that can branch
+ * to code outside of the LL/SC loop. As such, we don't need to emit
+ * another barrier here.
+ */
+ if (!__SYNC_loongson3_war)
+ smp_llsc_mb();
return result;
}
--
2.23.0
next prev parent reply other threads:[~2019-10-01 21:53 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-01 21:53 [PATCH v2 00/36] MIPS: barriers & atomics cleanups Paul Burton
2019-10-01 21:53 ` [PATCH v2 01/36] MIPS: Unify sc beqz definition Paul Burton
2019-10-01 21:53 ` [PATCH v2 02/36] MIPS: Use compact branch for LL/SC loops on MIPSr6+ Paul Burton
2019-10-01 21:53 ` [PATCH v2 03/36] MIPS: barrier: Add __SYNC() infrastructure Paul Burton
2019-10-01 21:53 ` [PATCH v2 04/36] MIPS: barrier: Clean up rmb() & wmb() definitions Paul Burton
2019-10-01 21:53 ` [PATCH v2 05/36] MIPS: barrier: Clean up __smp_mb() definition Paul Burton
2019-10-01 21:53 ` [PATCH v2 06/36] MIPS: barrier: Remove fast_mb() Octeon #ifdef'ery Paul Burton
2019-10-01 21:53 ` [PATCH v2 07/36] MIPS: barrier: Clean up __sync() definition Paul Burton
2019-10-01 21:53 ` [PATCH v2 08/36] MIPS: barrier: Clean up sync_ginv() Paul Burton
2019-10-01 21:53 ` [PATCH v2 09/36] MIPS: atomic: Fix whitespace in ATOMIC_OP macros Paul Burton
2019-10-01 21:53 ` [PATCH v2 10/36] MIPS: atomic: Handle !kernel_uses_llsc first Paul Burton
2019-10-01 21:53 ` [PATCH v2 11/36] MIPS: atomic: Use one macro to generate 32b & 64b functions Paul Burton
2019-10-01 21:53 ` Paul Burton [this message]
2019-10-01 21:53 ` [PATCH v2 13/36] MIPS: atomic: Use _atomic barriers in atomic_sub_if_positive() Paul Burton
2019-10-01 21:53 ` [PATCH v2 14/36] MIPS: atomic: Unify 32b & 64b sub_if_positive Paul Burton
2019-10-01 21:53 ` [PATCH v2 15/36] MIPS: atomic: Deduplicate 32b & 64b read, set, xchg, cmpxchg Paul Burton
2019-10-01 21:53 ` [PATCH v2 16/36] MIPS: bitops: Handle !kernel_uses_llsc first Paul Burton
2019-10-01 21:53 ` [PATCH v2 17/36] MIPS: bitops: Only use ins for bit 16 or higher Paul Burton
2019-10-01 21:53 ` [PATCH v2 18/36] MIPS: bitops: Use MIPS_ISA_REV, not #ifdefs Paul Burton
2019-10-01 21:53 ` [PATCH v2 19/36] MIPS: bitops: ins start position is always an immediate Paul Burton
2019-10-01 21:53 ` [PATCH v2 20/36] MIPS: bitops: Implement test_and_set_bit() in terms of _lock variant Paul Burton
2019-10-01 21:53 ` [PATCH v2 21/36] MIPS: bitops: Allow immediates in test_and_{set,clear,change}_bit Paul Burton
2019-10-01 21:53 ` [PATCH v2 22/36] MIPS: bitops: Use the BIT() macro Paul Burton
2019-10-01 21:53 ` [PATCH v2 23/36] MIPS: bitops: Avoid redundant zero-comparison for non-LLSC Paul Burton
2019-10-01 21:53 ` [PATCH v2 24/36] MIPS: bitops: Abstract LL/SC loops Paul Burton
2019-10-01 21:53 ` [PATCH v2 25/36] MIPS: bitops: Use BIT_WORD() & BITS_PER_LONG Paul Burton
2019-10-01 21:53 ` [PATCH v2 26/36] MIPS: bitops: Emit Loongson3 sync workarounds within asm Paul Burton
2019-10-01 21:53 ` [PATCH v2 27/36] MIPS: bitops: Use smp_mb__before_atomic in test_* ops Paul Burton
2019-10-01 21:53 ` [PATCH v2 28/36] MIPS: cmpxchg: Emit Loongson3 sync workarounds within asm Paul Burton
2019-10-01 21:53 ` [PATCH v2 30/36] MIPS: futex: " Paul Burton
2019-10-01 21:53 ` [PATCH v2 29/36] MIPS: cmpxchg: Omit redundant barriers for Loongson3 Paul Burton
2019-10-01 21:53 ` [PATCH v2 31/36] MIPS: syscall: Emit Loongson3 sync workarounds within asm Paul Burton
2019-10-01 21:53 ` [PATCH v2 32/36] MIPS: barrier: Remove loongson_llsc_mb() Paul Burton
2019-10-01 21:53 ` [PATCH v2 33/36] MIPS: barrier: Make __smp_mb__before_atomic() a no-op for Loongson3 Paul Burton
2019-10-01 21:53 ` [PATCH v2 34/36] MIPS: genex: Add Loongson3 LL/SC workaround to ejtag_debug_handler Paul Burton
2019-10-01 21:53 ` [PATCH v2 35/36] MIPS: genex: Don't reload address unnecessarily Paul Burton
2019-10-01 21:53 ` [PATCH v2 36/36] MIPS: Check Loongson3 LL/SC errata workaround correctness Paul Burton
2019-10-07 17:51 ` [PATCH v2 00/36] MIPS: barriers & atomics cleanups Paul Burton
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191001215249.4157062-13-paul.burton@mips.com \
--to=paul.burton@mips.com \
--cc=chenhc@lemote.com \
--cc=jiaxun.yang@flygoat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mips@vger.kernel.org \
--cc=pburton@wavecomp.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®