qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org, qemu-ppc@nongu.org, qemu-s390x@nongnu.org,
	qemu-riscv@nongnu.org
Subject: [PATCH v3 08/12] target/ppc: Improve helper_dcbz for user-only
Date: Fri, 19 Jul 2024 11:07:03 +1000	[thread overview]
Message-ID: <20240719010707.1319675-9-richard.henderson@linaro.org> (raw)
In-Reply-To: <20240719010707.1319675-1-richard.henderson@linaro.org>

Mark the reserve_addr check unlikely.  Use tlb_vaddr_to_host
instead of probe_write, relying on the memset itself to test
for page writability.  Use set/clear_helper_retaddr so that
we can properly unwind on segfault.

With this, a trivial loop around guest memset will spend
nearly 50% of runtime within helper_dcbz and host memset.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/ppc/mem_helper.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c
index 24bae3b80c..953dd08d5d 100644
--- a/target/ppc/mem_helper.c
+++ b/target/ppc/mem_helper.c
@@ -280,20 +280,27 @@ static void dcbz_common(CPUPPCState *env, target_ulong addr,
     addr &= mask;
 
     /* Check reservation */
-    if ((env->reserve_addr & mask) == addr)  {
+    if (unlikely((env->reserve_addr & mask) == addr))  {
         env->reserve_addr = (target_ulong)-1ULL;
     }
 
     /* Try fast path translate */
+#ifdef CONFIG_USER_ONLY
+    haddr = tlb_vaddr_to_host(env, addr, MMU_DATA_STORE, mmu_idx);
+#else
     haddr = probe_write(env, addr, dcbz_size, mmu_idx, retaddr);
-    if (haddr) {
-        memset(haddr, 0, dcbz_size);
-    } else {
+    if (unlikely(!haddr)) {
         /* Slow path */
         for (int i = 0; i < dcbz_size; i += 8) {
             cpu_stq_mmuidx_ra(env, addr + i, 0, mmu_idx, retaddr);
         }
+        return;
     }
+#endif
+
+    set_helper_retaddr(retaddr);
+    memset(haddr, 0, dcbz_size);
+    clear_helper_retaddr();
 }
 
 void helper_dcbz(CPUPPCState *env, target_ulong addr, int mmu_idx)
-- 
2.43.0



  parent reply	other threads:[~2024-07-19  1:09 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-07-19  1:06 [PATCH v3 00/12] Fixes for user-only munmap races Richard Henderson
2024-07-19  1:06 ` [PATCH v3 01/12] accel/tcg: Move {set, clear}_helper_retaddr to cpu_ldst.h Richard Henderson
2024-07-19  1:06 ` [PATCH v3 02/12] target/arm: Use set/clear_helper_retaddr in helper-a64.c Richard Henderson
2024-07-19  1:06 ` [PATCH v3 03/12] target/arm: Use set/clear_helper_retaddr in SVE and SME helpers Richard Henderson
2024-07-22 11:56   ` Peter Maydell
2024-07-19  1:06 ` [PATCH v3 04/12] target/ppc/mem_helper.c: Remove a conditional from dcbz_common() Richard Henderson
2024-07-19  1:07 ` [PATCH v3 05/12] target/ppc: Hoist dcbz_size out of dcbz_common Richard Henderson
2024-07-19  1:07 ` [PATCH v3 06/12] target/ppc: Split out helper_dbczl for 970 Richard Henderson
2024-10-20 21:20   ` Guenter Roeck
2024-10-21 10:40     ` BALATON Zoltan
2024-07-19  1:07 ` [PATCH v3 07/12] target/ppc: Merge helper_{dcbz,dcbzep} Richard Henderson
2024-07-19  1:07 ` Richard Henderson [this message]
2024-07-22 12:08   ` [PATCH v3 08/12] target/ppc: Improve helper_dcbz for user-only Peter Maydell
2024-07-19  1:07 ` [PATCH v3 09/12] target/s390x: Use user_or_likely in do_access_memset Richard Henderson
2024-07-19  1:07 ` [PATCH v3 10/12] target/s390x: Use user_or_likely in access_memmove Richard Henderson
2024-07-22 12:10   ` Peter Maydell
2024-07-19  1:07 ` [PATCH v3 11/12] target/s390x: Use set/clear_helper_retaddr in mem_helper.c Richard Henderson
2024-07-22 12:15   ` Peter Maydell
2024-07-19  1:07 ` [PATCH v3 12/12] target/riscv: Simplify probing in vext_ldff Richard Henderson
2024-07-22 16:49   ` Max Chou

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=20240719010707.1319675-9-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongu.org \
    --cc=qemu-riscv@nongnu.org \
    --cc=qemu-s390x@nongnu.org \
    /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;
as well as URLs for NNTP newsgroup(s).