From: Alexander Graf <agraf@suse.de>
To: qemu-ppc@nongnu.org
Cc: peter.maydell@linaro.org, qemu-devel@nongnu.org,
Paolo Bonzini <pbonzini@redhat.com>
Subject: [Qemu-devel] [PULL 40/40] softmmu: support up to 12 MMU modes
Date: Wed, 3 Jun 2015 23:45:41 +0200 [thread overview]
Message-ID: <1433367941-119488-41-git-send-email-agraf@suse.de> (raw)
In-Reply-To: <1433367941-119488-1-git-send-email-agraf@suse.de>
From: Paolo Bonzini <pbonzini@redhat.com>
At 8k per TLB (for 64-bit host or target), 8 or more modes
make the TLBs bigger than 64k, and some RISC TCG backends do
not like that. On the affected hosts, cut the TLB size in
half---there is still a measurable speedup on PPC with the
next patch.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <1424436345-37924-3-git-send-email-pbonzini@redhat.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
include/exec/cpu-defs.h | 35 +++++++++++++++-
include/exec/cpu_ldst.h | 104 +++++++++++++++++++++++++++++++++++++++++++++---
2 files changed, 131 insertions(+), 8 deletions(-)
diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h
index 3f56546..d5aecaf 100644
--- a/include/exec/cpu-defs.h
+++ b/include/exec/cpu-defs.h
@@ -27,6 +27,7 @@
#include <inttypes.h>
#include "qemu/osdep.h"
#include "qemu/queue.h"
+#include "tcg-target.h"
#ifndef CONFIG_USER_ONLY
#include "exec/hwaddr.h"
#endif
@@ -70,8 +71,6 @@ typedef uint64_t target_ulong;
#define TB_JMP_PAGE_MASK (TB_JMP_CACHE_SIZE - TB_JMP_PAGE_SIZE)
#if !defined(CONFIG_USER_ONLY)
-#define CPU_TLB_BITS 8
-#define CPU_TLB_SIZE (1 << CPU_TLB_BITS)
/* use a fully associative victim tlb of 8 entries */
#define CPU_VTLB_SIZE 8
@@ -81,6 +80,38 @@ typedef uint64_t target_ulong;
#define CPU_TLB_ENTRY_BITS 5
#endif
+/* TCG_TARGET_TLB_DISPLACEMENT_BITS is used in CPU_TLB_BITS to ensure that
+ * the TLB is not unnecessarily small, but still small enough for the
+ * TLB lookup instruction sequence used by the TCG target.
+ *
+ * TCG will have to generate an operand as large as the distance between
+ * env and the tlb_table[NB_MMU_MODES - 1][0].addend. For simplicity,
+ * the TCG targets just round everything up to the next power of two, and
+ * count bits. This works because: 1) the size of each TLB is a largish
+ * power of two, 2) and because the limit of the displacement is really close
+ * to a power of two, 3) the offset of tlb_table[0][0] inside env is smaller
+ * than the size of a TLB.
+ *
+ * For example, the maximum displacement 0xFFF0 on PPC and MIPS, but TCG
+ * just says "the displacement is 16 bits". TCG_TARGET_TLB_DISPLACEMENT_BITS
+ * then ensures that tlb_table at least 0x8000 bytes large ("not unnecessarily
+ * small": 2^15). The operand then will come up smaller than 0xFFF0 without
+ * any particular care, because the TLB for a single MMU mode is larger than
+ * 0x10000-0xFFF0=16 bytes. In the end, the maximum value of the operand
+ * could be something like 0xC000 (the offset of the last TLB table) plus
+ * 0x18 (the offset of the addend field in each TLB entry) plus the offset
+ * of tlb_table inside env (which is non-trivial but not huge).
+ */
+#define CPU_TLB_BITS \
+ MIN(8, \
+ TCG_TARGET_TLB_DISPLACEMENT_BITS - CPU_TLB_ENTRY_BITS - \
+ (NB_MMU_MODES <= 1 ? 0 : \
+ NB_MMU_MODES <= 2 ? 1 : \
+ NB_MMU_MODES <= 4 ? 2 : \
+ NB_MMU_MODES <= 8 ? 3 : 4))
+
+#define CPU_TLB_SIZE (1 << CPU_TLB_BITS)
+
typedef struct CPUTLBEntry {
/* bit TARGET_LONG_BITS to TARGET_PAGE_BITS : virtual address
bit TARGET_PAGE_BITS-1..4 : Nonzero for accesses that should not
diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h
index 1673287..0ec398c 100644
--- a/include/exec/cpu_ldst.h
+++ b/include/exec/cpu_ldst.h
@@ -263,12 +263,104 @@ uint64_t helper_ldq_cmmu(CPUArchState *env, target_ulong addr, int mmu_idx);
#undef MEMSUFFIX
#endif /* (NB_MMU_MODES >= 7) */
-#if (NB_MMU_MODES > 7)
-/* Note that supporting NB_MMU_MODES == 9 would require
- * changes to at least the ARM TCG backend.
- */
-#error "NB_MMU_MODES > 7 is not supported for now"
-#endif /* (NB_MMU_MODES > 7) */
+#if (NB_MMU_MODES >= 8) && defined(MMU_MODE7_SUFFIX)
+
+#define CPU_MMU_INDEX 7
+#define MEMSUFFIX MMU_MODE7_SUFFIX
+#define DATA_SIZE 1
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 2
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 4
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 8
+#include "exec/cpu_ldst_template.h"
+#undef CPU_MMU_INDEX
+#undef MEMSUFFIX
+#endif /* (NB_MMU_MODES >= 8) */
+
+#if (NB_MMU_MODES >= 9) && defined(MMU_MODE8_SUFFIX)
+
+#define CPU_MMU_INDEX 8
+#define MEMSUFFIX MMU_MODE8_SUFFIX
+#define DATA_SIZE 1
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 2
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 4
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 8
+#include "exec/cpu_ldst_template.h"
+#undef CPU_MMU_INDEX
+#undef MEMSUFFIX
+#endif /* (NB_MMU_MODES >= 9) */
+
+#if (NB_MMU_MODES >= 10) && defined(MMU_MODE9_SUFFIX)
+
+#define CPU_MMU_INDEX 9
+#define MEMSUFFIX MMU_MODE9_SUFFIX
+#define DATA_SIZE 1
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 2
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 4
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 8
+#include "exec/cpu_ldst_template.h"
+#undef CPU_MMU_INDEX
+#undef MEMSUFFIX
+#endif /* (NB_MMU_MODES >= 10) */
+
+#if (NB_MMU_MODES >= 11) && defined(MMU_MODE10_SUFFIX)
+
+#define CPU_MMU_INDEX 10
+#define MEMSUFFIX MMU_MODE10_SUFFIX
+#define DATA_SIZE 1
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 2
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 4
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 8
+#include "exec/cpu_ldst_template.h"
+#undef CPU_MMU_INDEX
+#undef MEMSUFFIX
+#endif /* (NB_MMU_MODES >= 11) */
+
+#if (NB_MMU_MODES >= 12) && defined(MMU_MODE11_SUFFIX)
+
+#define CPU_MMU_INDEX 11
+#define MEMSUFFIX MMU_MODE11_SUFFIX
+#define DATA_SIZE 1
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 2
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 4
+#include "exec/cpu_ldst_template.h"
+
+#define DATA_SIZE 8
+#include "exec/cpu_ldst_template.h"
+#undef CPU_MMU_INDEX
+#undef MEMSUFFIX
+#endif /* (NB_MMU_MODES >= 12) */
+
+#if (NB_MMU_MODES > 12)
+#error "NB_MMU_MODES > 12 is not supported for now"
+#endif /* (NB_MMU_MODES > 12) */
/* these access are slower, they must be as rare as possible */
#define CPU_MMU_INDEX (cpu_mmu_index(env))
--
1.8.1.4
next prev parent reply other threads:[~2015-06-03 21:46 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-03 21:45 [Qemu-devel] [PULL 00/40] ppc patch queue 2015-06-03 Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 01/40] macio: Convert to realize() Alexander Graf
2015-06-03 21:53 ` Peter Maydell
2015-06-03 22:00 ` Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 02/40] dtc: Update dtc / libfdt submodule to version 1.4.0 Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 03/40] configure: Check for libfdt " Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 04/40] spapr_pci: Fix unsafe signed/unsigned comparisons Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 05/40] spapr_iommu: Disable in-kernel IOMMU tables for >4GB windows Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 06/40] spapr_iommu: Make H_PUT_TCE_INDIRECT endian-safe Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 07/40] spapr_pci: Introduce a liobn number generating macros Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 08/40] spapr_vio: " Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 09/40] spapr_pci: Define default DMA window size as a macro Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 10/40] spapr_iommu: Add separate trace points for PCI DMA operations Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 11/40] spapr_pci: Make find_phb()/find_dev() public Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 12/40] spapr_iommu: Make spapr_tce_find_by_liobn() public Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 13/40] spapr_pci: Rework device-tree rendering Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 14/40] spapr_iommu: Give unique QOM name to TCE table Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 15/40] hw/ppc/spapr_iommu: Fix the check for invalid upper bits in liobn Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 16/40] pseries: Add pseries-2.4 machine type Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 17/40] hw/ppc/spapr: Fix error message when firmware could not be loaded Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 18/40] hw/ppc/spapr: Use error_report() instead of hw_error() Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 19/40] docs: add sPAPR hotplug/dynamic-reconfiguration documentation Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 20/40] spapr_drc: initial implementation of sPAPRDRConnector device Alexander Graf
2015-07-09 14:16 ` Paolo Bonzini
2015-06-03 21:45 ` [Qemu-devel] [PULL 21/40] spapr_rtas: add get/set-power-level RTAS interfaces Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 22/40] spapr_rtas: add set-indicator RTAS interface Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 23/40] spapr_rtas: add get-sensor-state " Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 24/40] spapr: add rtas_st_buffer_direct() helper Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 25/40] spapr_rtas: add ibm, configure-connector RTAS interface Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 26/40] spapr_events: re-use EPOW event infrastructure for hotplug events Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 27/40] spapr_events: event-scan RTAS interface Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 28/40] spapr_drc: add spapr_drc_populate_dt() Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 29/40] spapr_pci: add dynamic-reconfiguration option for spapr-pci-host-bridge Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 30/40] spapr_pci: create DRConnectors for each PCI slot during PHB realize Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 31/40] pci: make pci_bar useable outside pci.c Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 32/40] spapr_pci: enable basic hotplug operations Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 33/40] spapr_pci: emit hotplug add/remove events during hotplug Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 34/40] machine: add default_ram_size to machine class Alexander Graf
2015-06-05 7:27 ` Laurent Desnogues
2015-06-03 21:45 ` [Qemu-devel] [PULL 35/40] spapr: override default ram size to 512MB Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 36/40] pseries: Enable in-kernel H_LOGICAL_CI_{LOAD, STORE} implementations Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 37/40] Add David Gibson for sPAPR in MAINTAINERS file Alexander Graf
2015-11-18 20:46 ` Andreas Färber
2015-11-18 20:51 ` Eric Blake
2015-11-18 20:58 ` Andreas Färber
2015-06-03 21:45 ` [Qemu-devel] [PULL 38/40] tci: do not use CPUArchState in tcg-target.h Alexander Graf
2015-06-03 21:45 ` [Qemu-devel] [PULL 39/40] tcg: add TCG_TARGET_TLB_DISPLACEMENT_BITS Alexander Graf
2015-06-03 21:45 ` Alexander Graf [this message]
2015-06-04 17:28 ` [Qemu-devel] [PULL 00/40] ppc patch queue 2015-06-03 Peter Maydell
2015-06-05 13:33 ` Peter Maydell
2015-06-05 14:35 ` Paolo Bonzini
2015-06-05 14:40 ` Peter Maydell
2015-06-05 15:02 ` Paolo Bonzini
2015-06-05 15:08 ` Peter Maydell
2015-06-05 15:20 ` Paolo Bonzini
2015-06-05 15:45 ` Peter Maydell
2015-06-05 15:55 ` [Qemu-devel] undefined behavior of signed left shifts (was Re: [PULL 00/40] ppc patch queue 2015-06-03) Paolo Bonzini
2015-06-05 17:21 ` Joseph Myers
2015-06-05 17:33 ` Peter Maydell
2015-07-21 11:42 ` [Qemu-devel] [PULL 00/40] ppc patch queue 2015-06-03 Peter Maydell
2015-07-21 23:32 ` Michael Roth
2015-06-05 15:24 ` Eric Blake
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=1433367941-119488-41-git-send-email-agraf@suse.de \
--to=agraf@suse.de \
--cc=pbonzini@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@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).