From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Subject: [PATCH 04/23] accel/tcg: Split out tlbfast_flush_range_locked
Date: Wed, 9 Oct 2024 08:08:36 -0700 [thread overview]
Message-ID: <20241009150855.804605-5-richard.henderson@linaro.org> (raw)
In-Reply-To: <20241009150855.804605-1-richard.henderson@linaro.org>
While this may at present be overly complicated for use
by single page flushes, do so with the expectation that
this will eventually allow simplification of large pages.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
accel/tcg/cputlb.c | 61 +++++++++++++++++++++++++---------------------
1 file changed, 33 insertions(+), 28 deletions(-)
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index e37af24525..6773874f2d 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -520,10 +520,37 @@ static inline void tlb_flush_vtlb_page_locked(CPUState *cpu, int mmu_idx,
tlb_flush_vtlb_page_mask_locked(cpu, mmu_idx, page, -1);
}
+static void tlbfast_flush_range_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast,
+ vaddr addr, vaddr len, vaddr mask)
+{
+ /*
+ * If @mask is smaller than the tlb size, there may be multiple entries
+ * within the TLB; for now, just flush the entire TLB.
+ * Otherwise all addresses that match under @mask hit the same TLB entry.
+ *
+ * If @len is larger than the tlb size, then it will take longer to
+ * test all of the entries in the TLB than it will to flush it all.
+ */
+ if (mask < fast->mask || len > fast->mask) {
+ tlbfast_flush_locked(desc, fast);
+ return;
+ }
+
+ for (vaddr i = 0; i < len; i += TARGET_PAGE_SIZE) {
+ vaddr page = addr + i;
+ CPUTLBEntry *entry = tlbfast_entry(fast, page);
+
+ if (tlb_flush_entry_mask_locked(entry, page, mask)) {
+ desc->n_used_entries--;
+ }
+ }
+}
+
static void tlb_flush_page_locked(CPUState *cpu, int midx, vaddr page)
{
- vaddr lp_addr = cpu->neg.tlb.d[midx].large_page_addr;
- vaddr lp_mask = cpu->neg.tlb.d[midx].large_page_mask;
+ CPUTLBDesc *desc = &cpu->neg.tlb.d[midx];
+ vaddr lp_addr = desc->large_page_addr;
+ vaddr lp_mask = desc->large_page_mask;
/* Check if we need to flush due to large pages. */
if ((page & lp_mask) == lp_addr) {
@@ -532,9 +559,8 @@ static void tlb_flush_page_locked(CPUState *cpu, int midx, vaddr page)
midx, lp_addr, lp_mask);
tlb_flush_one_mmuidx_locked(cpu, midx, get_clock_realtime());
} else {
- if (tlb_flush_entry_locked(tlb_entry(cpu, midx, page), page)) {
- tlb_n_used_entries_dec(cpu, midx);
- }
+ tlbfast_flush_range_locked(desc, &cpu->neg.tlb.f[midx],
+ page, TARGET_PAGE_SIZE, -1);
tlb_flush_vtlb_page_locked(cpu, midx, page);
}
}
@@ -689,24 +715,6 @@ static void tlb_flush_range_locked(CPUState *cpu, int midx,
CPUTLBDescFast *f = &cpu->neg.tlb.f[midx];
vaddr mask = MAKE_64BIT_MASK(0, bits);
- /*
- * If @bits is smaller than the tlb size, there may be multiple entries
- * within the TLB; otherwise all addresses that match under @mask hit
- * the same TLB entry.
- * TODO: Perhaps allow bits to be a few bits less than the size.
- * For now, just flush the entire TLB.
- *
- * If @len is larger than the tlb size, then it will take longer to
- * test all of the entries in the TLB than it will to flush it all.
- */
- if (mask < f->mask || len > f->mask) {
- tlb_debug("forcing full flush midx %d ("
- "%016" VADDR_PRIx "/%016" VADDR_PRIx "+%016" VADDR_PRIx ")\n",
- midx, addr, mask, len);
- tlb_flush_one_mmuidx_locked(cpu, midx, get_clock_realtime());
- return;
- }
-
/*
* Check if we need to flush due to large pages.
* Because large_page_mask contains all 1's from the msb,
@@ -720,13 +728,10 @@ static void tlb_flush_range_locked(CPUState *cpu, int midx,
return;
}
+ tlbfast_flush_range_locked(d, f, addr, len, mask);
+
for (vaddr i = 0; i < len; i += TARGET_PAGE_SIZE) {
vaddr page = addr + i;
- CPUTLBEntry *entry = tlb_entry(cpu, midx, page);
-
- if (tlb_flush_entry_mask_locked(entry, page, mask)) {
- tlb_n_used_entries_dec(cpu, midx);
- }
tlb_flush_vtlb_page_mask_locked(cpu, midx, page, mask);
}
}
--
2.43.0
next prev parent reply other threads:[~2024-10-09 15:09 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-09 15:08 [RFC PATCH 00/23] accel/tcg: Convert victim tlb to IntervalTree Richard Henderson
2024-10-09 15:08 ` [PATCH 01/23] util/interval-tree: Introduce interval_tree_free_nodes Richard Henderson
2024-10-09 22:51 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 02/23] accel/tcg: Split out tlbfast_flush_locked Richard Henderson
2024-10-09 18:54 ` Philippe Mathieu-Daudé
2024-10-09 22:53 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 03/23] accel/tcg: Split out tlbfast_{index,entry} Richard Henderson
2024-10-09 22:55 ` Pierrick Bouvier
2024-10-09 15:08 ` Richard Henderson [this message]
2024-10-09 23:05 ` [PATCH 04/23] accel/tcg: Split out tlbfast_flush_range_locked Pierrick Bouvier
2024-10-10 1:20 ` Richard Henderson
2024-10-11 17:09 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 05/23] accel/tcg: Fix flags usage in mmu_lookup1, atomic_mmu_lookup Richard Henderson
2024-10-09 23:18 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 06/23] accel/tcg: Early exit for zero length in tlb_flush_range_by_mmuidx* Richard Henderson
2024-10-09 18:53 ` Philippe Mathieu-Daudé
2024-10-09 23:20 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 07/23] accel/tcg: Flush entire tlb when a masked range wraps Richard Henderson
2024-10-09 23:28 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 08/23] accel/tcg: Add IntervalTreeRoot to CPUTLBDesc Richard Henderson
2024-10-09 23:31 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 09/23] accel/tcg: Populate IntervalTree in tlb_set_page_full Richard Henderson
2024-10-09 23:50 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 10/23] accel/tcg: Remove IntervalTree entry in tlb_flush_page_locked Richard Henderson
2024-10-09 23:53 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 11/23] accel/tcg: Remove IntervalTree entries in tlb_flush_range_locked Richard Henderson
2024-10-09 23:57 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 12/23] accel/tcg: Process IntervalTree entries in tlb_reset_dirty Richard Henderson
2024-10-10 0:03 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 13/23] accel/tcg: Process IntervalTree entries in tlb_set_dirty Richard Henderson
2024-10-10 0:04 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 14/23] accel/tcg: Replace victim_tlb_hit with tlbtree_hit Richard Henderson
2024-10-10 0:10 ` Pierrick Bouvier
2024-10-10 19:29 ` Richard Henderson
2024-10-11 17:11 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 15/23] accel/tcg: Remove the victim tlb Richard Henderson
2024-10-10 0:12 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 16/23] include/exec/tlb-common: Move CPUTLBEntryFull from hw/core/cpu.h Richard Henderson
2024-10-10 0:17 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 17/23] accel/tcg: Delay plugin adjustment in probe_access_internal Richard Henderson
2024-10-10 0:19 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 18/23] accel/tcg: Call cpu_ld*_code_mmu from cpu_ld*_code Richard Henderson
2024-10-09 18:51 ` Philippe Mathieu-Daudé
2024-10-10 0:23 ` Pierrick Bouvier
2024-10-10 19:31 ` Richard Henderson
2024-10-09 15:08 ` [PATCH 19/23] accel/tcg: Always use IntervalTree for code lookups Richard Henderson
2024-10-10 0:35 ` Pierrick Bouvier
2024-10-11 14:47 ` Richard Henderson
2024-10-11 17:55 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 20/23] accel/tcg: Link CPUTLBEntry to CPUTLBEntryTree Richard Henderson
2024-10-10 0:37 ` Pierrick Bouvier
2024-10-09 15:08 ` [PATCH 21/23] accel/tcg: Remove CPUTLBDesc.fulltlb Richard Henderson
2024-10-10 0:38 ` Pierrick Bouvier
2024-10-09 15:08 ` [NOTYET PATCH 22/23] accel/tcg: Drop TCGCPUOps.tlb_fill Richard Henderson
2024-10-10 0:40 ` Pierrick Bouvier
2024-10-09 15:08 ` [NOTYET PATCH 23/23] accel/tcg: Unexport tlb_set_page* Richard Henderson
2024-10-09 16:27 ` [RFC PATCH 00/23] accel/tcg: Convert victim tlb to IntervalTree BALATON Zoltan
2024-10-09 17:10 ` Richard Henderson
2024-10-10 0:50 ` Pierrick Bouvier
2024-10-15 0:07 ` 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=20241009150855.804605-5-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--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).