qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Alvise Rigo <a.rigo@virtualopensystems.com>
To: mttcg@listserver.greensocs.com, alex.bennee@linaro.org
Cc: qemu-devel@nongnu.org, jani.kokkonen@huawei.com,
	claudio.fontana@huawei.com, tech@virtualopensystems.com,
	fred.konrad@greensocs.com, pbonzini@redhat.com, rth@twiddle.net,
	serge.fdrv@gmail.com, cota@braap.org, peter.maydell@linaro.org,
	Alvise Rigo <a.rigo@virtualopensystems.com>
Subject: [Qemu-devel]  [RFC 06/10] cputlb: Add tlb_tables_flush_bitmap()
Date: Thu, 26 May 2016 18:35:45 +0200	[thread overview]
Message-ID: <20160526163549.3276-7-a.rigo@virtualopensystems.com> (raw)
In-Reply-To: <20160526163549.3276-1-a.rigo@virtualopensystems.com>

Add a simple helper function to flush the TLB at the indexes specified
by a bitmap. The function will be more useful in the following patches,
when it will be possible to query tlb_flush_by_mmuidx() to VCPUs.

Signed-off-by: Alvise Rigo <a.rigo@virtualopensystems.com>
---
 cputlb.c | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/cputlb.c b/cputlb.c
index 55f7447..5bbbf1b 100644
--- a/cputlb.c
+++ b/cputlb.c
@@ -129,15 +129,34 @@ void tlb_flush(CPUState *cpu, int flush_global)
     }
 }
 
-static inline void v_tlb_flush_by_mmuidx(CPUState *cpu, va_list argp)
+/* Flush tlb_table[] and tlb_v_table[] of @cpu at MMU indexes given by @bitmap.
+ * Flush also tb_jmp_cache. */
+static inline void tlb_tables_flush_bitmap(CPUState *cpu, unsigned long *bitmap)
 {
-    CPUArchState *env = cpu->env_ptr;
+    int mmu_idx;
 
     tlb_debug("start\n");
     /* must reset current TB so that interrupts cannot modify the
        links while we are modifying them */
     cpu->current_tb = NULL;
 
+    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
+        if (test_bit(mmu_idx, bitmap)) {
+            CPUArchState *env = cpu->env_ptr;
+
+            tlb_debug("%d\n", mmu_idx);
+
+            memset(env->tlb_table[mmu_idx], -1, sizeof(env->tlb_table[0]));
+            memset(env->tlb_v_table[mmu_idx], -1, sizeof(env->tlb_v_table[0]));
+        }
+    }
+    memset(cpu->tb_jmp_cache, 0, sizeof(cpu->tb_jmp_cache));
+}
+
+static inline void v_tlb_flush_by_mmuidx(CPUState *cpu, va_list argp)
+{
+    DECLARE_BITMAP(idxmap, NB_MMU_MODES) = { 0 };
+
     for (;;) {
         int mmu_idx = va_arg(argp, int);
 
@@ -145,13 +164,10 @@ static inline void v_tlb_flush_by_mmuidx(CPUState *cpu, va_list argp)
             break;
         }
 
-        tlb_debug("%d\n", mmu_idx);
-
-        memset(env->tlb_table[mmu_idx], -1, sizeof(env->tlb_table[0]));
-        memset(env->tlb_v_table[mmu_idx], -1, sizeof(env->tlb_v_table[0]));
+        set_bit(mmu_idx, idxmap);
     }
 
-    memset(cpu->tb_jmp_cache, 0, sizeof(cpu->tb_jmp_cache));
+    tlb_tables_flush_bitmap(cpu, idxmap);
 }
 
 void tlb_flush_by_mmuidx(CPUState *cpu, ...)
-- 
2.8.3

  parent reply	other threads:[~2016-05-26 16:36 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-05-26 16:35 [Qemu-devel] [RFC 00/10] MTTCG: Slow-path for atomic insns Alvise Rigo
2016-05-26 16:35 ` [Qemu-devel] [RFC 01/10] exec: Introduce tcg_exclusive_{lock, unlock}() Alvise Rigo
2016-05-31 15:03   ` Pranith Kumar
2016-06-02 16:21     ` alvise rigo
2016-06-08  9:21   ` Alex Bennée
2016-06-08 10:00     ` alvise rigo
2016-06-08 11:32       ` Peter Maydell
2016-06-08 13:52       ` Alex Bennée
2016-05-26 16:35 ` [Qemu-devel] [RFC 02/10] softmmu_llsc_template.h: Move to multi-threading Alvise Rigo
2016-06-10 15:21   ` Sergey Fedorov
2016-06-10 15:53     ` alvise rigo
2016-06-10 16:00       ` Sergey Fedorov
2016-06-10 16:04         ` alvise rigo
2016-06-14 12:00       ` Alex Bennée
2016-06-14 12:58         ` alvise rigo
2016-06-14 13:14           ` Alex Bennée
2016-06-10 16:15     ` Alex Bennée
2016-06-11 19:53       ` Sergey Fedorov
2016-06-14  8:37       ` Alex Bennée
2016-06-14  9:31         ` Sergey Fedorov
2016-05-26 16:35 ` [Qemu-devel] [RFC 03/10] cpus: Introduce async_wait_run_on_cpu() Alvise Rigo
2016-06-08 13:54   ` Alex Bennée
2016-06-08 14:10     ` alvise rigo
2016-06-08 14:53       ` Sergey Fedorov
2016-06-08 15:20         ` Alex Bennée
2016-06-08 16:24           ` alvise rigo
2016-06-13  9:26             ` Alex Bennée
2016-05-26 16:35 ` [Qemu-devel] [RFC 04/10] cputlb: Introduce tlb_flush_other() Alvise Rigo
2016-05-26 16:35 ` [Qemu-devel] [RFC 05/10] target-arm: End TB after ldrex instruction Alvise Rigo
2016-05-26 16:35 ` Alvise Rigo [this message]
2016-05-26 16:35 ` [Qemu-devel] [RFC 07/10] cputlb: Query tlb_flush_by_mmuidx Alvise Rigo
2016-05-26 16:35 ` [Qemu-devel] [RFC 08/10] cputlb: Query tlb_flush_page_by_mmuidx Alvise Rigo
2016-05-26 16:35 ` [Qemu-devel] [RFC 09/10] cputlb: Query tlb_flush_page_all Alvise Rigo
2016-05-26 16:35 ` [Qemu-devel] [RFC 10/10] cpus: Do not sleep if some work item is pending Alvise Rigo
2016-06-10 15:21 ` [Qemu-devel] [RFC 00/10] MTTCG: Slow-path for atomic insns Alex Bennée
2016-06-10 15:30   ` alvise rigo

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=20160526163549.3276-7-a.rigo@virtualopensystems.com \
    --to=a.rigo@virtualopensystems.com \
    --cc=alex.bennee@linaro.org \
    --cc=claudio.fontana@huawei.com \
    --cc=cota@braap.org \
    --cc=fred.konrad@greensocs.com \
    --cc=jani.kokkonen@huawei.com \
    --cc=mttcg@listserver.greensocs.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=rth@twiddle.net \
    --cc=serge.fdrv@gmail.com \
    --cc=tech@virtualopensystems.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;
as well as URLs for NNTP newsgroup(s).