From: Richard Henderson <rth@twiddle.net>
To: qemu-devel@nongnu.org
Subject: [Qemu-devel] [PATCH 1/2] cputlb: Use memset when flushing entries
Date: Sat, 7 Dec 2013 10:44:51 +1300 [thread overview]
Message-ID: <1386366292-5340-1-git-send-email-rth@twiddle.net> (raw)
The size of tlb_table is 4k on a 64-bit host. For overwriting
memory at this size, cacheline tricks can help.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
cputlb.c | 19 ++-----------------
1 file changed, 2 insertions(+), 17 deletions(-)
diff --git a/cputlb.c b/cputlb.c
index fff0afb..d2da404 100644
--- a/cputlb.c
+++ b/cputlb.c
@@ -33,13 +33,6 @@
/* statistics */
int tlb_flush_count;
-static const CPUTLBEntry s_cputlb_empty_entry = {
- .addr_read = -1,
- .addr_write = -1,
- .addr_code = -1,
- .addend = -1,
-};
-
/* NOTE:
* If flush_global is true (the usual case), flush all tlb entries.
* If flush_global is false, flush (at least) all tlb entries not
@@ -55,7 +48,6 @@ static const CPUTLBEntry s_cputlb_empty_entry = {
void tlb_flush(CPUArchState *env, int flush_global)
{
CPUState *cpu = ENV_GET_CPU(env);
- int i;
#if defined(DEBUG_TLB)
printf("tlb_flush:\n");
@@ -64,14 +56,7 @@ void tlb_flush(CPUArchState *env, int flush_global)
links while we are modifying them */
cpu->current_tb = NULL;
- for (i = 0; i < CPU_TLB_SIZE; i++) {
- int mmu_idx;
-
- for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
- env->tlb_table[mmu_idx][i] = s_cputlb_empty_entry;
- }
- }
-
+ memset(env->tlb_table, -1, sizeof(env->tlb_table));
memset(env->tb_jmp_cache, 0, TB_JMP_CACHE_SIZE * sizeof (void *));
env->tlb_flush_addr = -1;
@@ -87,7 +72,7 @@ static inline void tlb_flush_entry(CPUTLBEntry *tlb_entry, target_ulong addr)
(TARGET_PAGE_MASK | TLB_INVALID_MASK)) ||
addr == (tlb_entry->addr_code &
(TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
- *tlb_entry = s_cputlb_empty_entry;
+ memset(tlb_entry, -1, sizeof(*tlb_entry));
}
}
--
1.8.3.1
next reply other threads:[~2013-12-06 21:45 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-12-06 21:44 Richard Henderson [this message]
2013-12-06 21:44 ` [Qemu-devel] [PATCH 2/2] cputlb: Tidy memset of arrays Richard Henderson
2013-12-22 18:04 ` Aurelien Jarno
2013-12-22 18:04 ` [Qemu-devel] [PATCH 1/2] cputlb: Use memset when flushing entries Aurelien Jarno
2013-12-23 14:37 ` Andreas Färber
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=1386366292-5340-1-git-send-email-rth@twiddle.net \
--to=rth@twiddle.net \
--cc=qemu-devel@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).