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, balaton@eik.bme.hu, max.chou@sifive.com
Subject: [PATCH v2 13/13] target/riscv: Simplify probing in vext_ldff
Date: Tue,  9 Jul 2024 20:28:14 -0700	[thread overview]
Message-ID: <20240710032814.104643-14-richard.henderson@linaro.org> (raw)
In-Reply-To: <20240710032814.104643-1-richard.henderson@linaro.org>

The current pairing of tlb_vaddr_to_host with extra is either
inefficient (user-only, with page_check_range) or incorrect
(system, with probe_pages).

For proper non-fault behaviour, use probe_access_flags with
its nonfault parameter set to true.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/riscv/vector_helper.c | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 1b4d5a8e37..4d72eb74d3 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -474,7 +474,6 @@ vext_ldff(void *vd, void *v0, target_ulong base,
           vext_ldst_elem_fn *ldst_elem,
           uint32_t log2_esz, uintptr_t ra)
 {
-    void *host;
     uint32_t i, k, vl = 0;
     uint32_t nf = vext_nf(desc);
     uint32_t vm = vext_vm(desc);
@@ -493,27 +492,31 @@ vext_ldff(void *vd, void *v0, target_ulong base,
         }
         addr = adjust_addr(env, base + i * (nf << log2_esz));
         if (i == 0) {
+            /* Allow fault on first element. */
             probe_pages(env, addr, nf << log2_esz, ra, MMU_DATA_LOAD);
         } else {
-            /* if it triggers an exception, no need to check watchpoint */
             remain = nf << log2_esz;
             while (remain > 0) {
+                void *host;
+                int flags;
+
                 offset = -(addr | TARGET_PAGE_MASK);
-                host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, mmu_index);
-                if (host) {
-#ifdef CONFIG_USER_ONLY
-                    if (!page_check_range(addr, offset, PAGE_READ)) {
-                        vl = i;
-                        goto ProbeSuccess;
-                    }
-#else
-                    probe_pages(env, addr, offset, ra, MMU_DATA_LOAD);
-#endif
-                } else {
+
+                /* Probe nonfault on subsequent elements. */
+                flags = probe_access_flags(env, addr, offset, MMU_DATA_LOAD,
+                                           mmu_index, true, &host, 0);
+                if (flags) {
+                    /*
+                     * Stop any flag bit set:
+                     *   invalid (unmapped)
+                     *   mmio (transaction failed)
+                     *   watchpoint (debug)
+                     * In all cases, handle as the first load next time.
+                     */
                     vl = i;
-                    goto ProbeSuccess;
+                    break;
                 }
-                if (remain <=  offset) {
+                if (remain <= offset) {
                     break;
                 }
                 remain -= offset;
@@ -521,7 +524,6 @@ vext_ldff(void *vd, void *v0, target_ulong base,
             }
         }
     }
-ProbeSuccess:
     /* load bytes from guest memory */
     if (vl != 0) {
         env->vl = vl;
-- 
2.43.0



  parent reply	other threads:[~2024-07-10  3:30 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-07-10  3:28 [PATCH v2 00/13] Fixes for user-only munmap races Richard Henderson
2024-07-10  3:28 ` [PATCH v2 01/13] accel/tcg: Move {set, clear}_helper_retaddr to cpu_ldst.h Richard Henderson
2024-07-12 12:48   ` Peter Maydell
2024-07-10  3:28 ` [PATCH v2 02/13] target/arm: Use cpu_env in cpu_untagged_addr Richard Henderson
2024-07-12 12:49   ` Peter Maydell
2024-07-10  3:28 ` [PATCH v2 03/13] target/arm: Use set/clear_helper_retaddr in helper-a64.c Richard Henderson
2024-07-12 12:53   ` Peter Maydell
2024-07-10  3:28 ` [PATCH v2 04/13] target/arm: Use set/clear_helper_retaddr in SVE and SME helpers Richard Henderson
2024-07-12 13:00   ` Peter Maydell
2024-07-10  3:28 ` [PATCH v2 05/13] target/ppc/mem_helper.c: Remove a conditional from dcbz_common() Richard Henderson
2024-07-10  3:28 ` [PATCH v2 06/13] target/ppc: Hoist dcbz_size out of dcbz_common Richard Henderson
2024-07-10 12:11   ` BALATON Zoltan
2024-07-10 14:36     ` Richard Henderson
2024-07-10  3:28 ` [PATCH v2 07/13] target/ppc: Split out helper_dbczl for 970 Richard Henderson
2024-07-10 12:17   ` BALATON Zoltan
2024-07-10  3:28 ` [PATCH v2 08/13] target/ppc: Merge helper_{dcbz,dcbzep} Richard Henderson
2024-07-10 12:20   ` BALATON Zoltan
2024-07-10 14:41     ` Richard Henderson
2024-07-10  3:28 ` [PATCH v2 09/13] target/ppc: Improve helper_dcbz for user-only Richard Henderson
2024-07-10 12:25   ` BALATON Zoltan
2024-07-10 14:42     ` Richard Henderson
2024-07-10  3:28 ` [PATCH v2 10/13] target/s390x: Use user_or_likely in do_access_memset Richard Henderson
2024-07-12 13:02   ` Peter Maydell
2024-07-10  3:28 ` [PATCH v2 11/13] target/s390x: Use user_or_likely in access_memmove Richard Henderson
2024-07-10  3:28 ` [PATCH v2 12/13] target/s390x: Use set/clear_helper_retaddr in mem_helper.c Richard Henderson
2024-07-10  3:28 ` Richard Henderson [this message]
2024-07-10  4:09   ` [PATCH v2 13/13] target/riscv: Simplify probing in vext_ldff Alistair Francis
2024-07-15  7:06   ` Max Chou
2024-07-15 21:42     ` Richard Henderson

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=20240710032814.104643-14-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=balaton@eik.bme.hu \
    --cc=max.chou@sifive.com \
    --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).