qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Thomas Huth <thuth@redhat.com>
To: Stefan Hajnoczi <stefanha@redhat.com>, qemu-devel@nongnu.org
Cc: Matthew Rosato <mjrosato@linux.ibm.com>,
	Eric Farman <farman@linux.ibm.com>
Subject: [PULL 01/23] s390x/pci: coalesce unmap operations
Date: Wed, 14 Dec 2022 11:08:49 +0100	[thread overview]
Message-ID: <20221214100911.165291-2-thuth@redhat.com> (raw)
In-Reply-To: <20221214100911.165291-1-thuth@redhat.com>

From: Matthew Rosato <mjrosato@linux.ibm.com>

Currently, each unmapped page is handled as an individual iommu
region notification.  Attempt to group contiguous unmap operations
into fewer notifications to reduce overhead.

Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Message-Id: <20221028194758.204007-3-mjrosato@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
 hw/s390x/s390-pci-inst.c | 51 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c
index 7cc4bcf850..66e764f901 100644
--- a/hw/s390x/s390-pci-inst.c
+++ b/hw/s390x/s390-pci-inst.c
@@ -640,6 +640,8 @@ static uint32_t s390_pci_update_iotlb(S390PCIIOMMU *iommu,
         }
         g_hash_table_remove(iommu->iotlb, &entry->iova);
         inc_dma_avail(iommu);
+        /* Don't notify the iommu yet, maybe we can bundle contiguous unmaps */
+        goto out;
     } else {
         if (cache) {
             if (cache->perm == entry->perm &&
@@ -663,15 +665,44 @@ static uint32_t s390_pci_update_iotlb(S390PCIIOMMU *iommu,
         dec_dma_avail(iommu);
     }
 
+    /*
+     * All associated iotlb entries have already been cleared, trigger the
+     * unmaps.
+     */
     memory_region_notify_iommu(&iommu->iommu_mr, 0, event);
 
 out:
     return iommu->dma_limit ? iommu->dma_limit->avail : 1;
 }
 
+static void s390_pci_batch_unmap(S390PCIIOMMU *iommu, uint64_t iova,
+                                 uint64_t len)
+{
+    uint64_t remain = len, start = iova, end = start + len - 1, mask, size;
+    IOMMUTLBEvent event = {
+        .type = IOMMU_NOTIFIER_UNMAP,
+        .entry = {
+            .target_as = &address_space_memory,
+            .translated_addr = 0,
+            .perm = IOMMU_NONE,
+        },
+    };
+
+    while (remain >= TARGET_PAGE_SIZE) {
+        mask = dma_aligned_pow2_mask(start, end, 64);
+        size = mask + 1;
+        event.entry.iova = start;
+        event.entry.addr_mask = mask;
+        memory_region_notify_iommu(&iommu->iommu_mr, 0, event);
+        start += size;
+        remain -= size;
+    }
+}
+
 int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
 {
     CPUS390XState *env = &cpu->env;
+    uint64_t iova, coalesce = 0;
     uint32_t fh;
     uint16_t error = 0;
     S390PCIBusDevice *pbdev;
@@ -742,6 +773,21 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
             break;
         }
 
+        /*
+         * If this is an unmap of a PTE, let's try to coalesce multiple unmaps
+         * into as few notifier events as possible.
+         */
+        if (entry.perm == IOMMU_NONE && entry.len == TARGET_PAGE_SIZE) {
+            if (coalesce == 0) {
+                iova = entry.iova;
+            }
+            coalesce += entry.len;
+        } else if (coalesce > 0) {
+            /* Unleash the coalesced unmap before processing a new map */
+            s390_pci_batch_unmap(iommu, iova, coalesce);
+            coalesce = 0;
+        }
+
         start += entry.len;
         while (entry.iova < start && entry.iova < end) {
             if (dma_avail > 0 || entry.perm == IOMMU_NONE) {
@@ -759,6 +805,11 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
             }
         }
     }
+    if (coalesce) {
+            /* Unleash the coalesced unmap before finishing rpcit */
+            s390_pci_batch_unmap(iommu, iova, coalesce);
+            coalesce = 0;
+    }
     if (again && dma_avail > 0)
         goto retry;
 err:
-- 
2.31.1



  reply	other threads:[~2022-12-14 10:10 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-12-14 10:08 [PULL 00/23] First batch of s390x, qtest, CI and misc patches for 8.0 Thomas Huth
2022-12-14 10:08 ` Thomas Huth [this message]
2022-12-14 10:08 ` [PULL 02/23] s390x/pci: shrink DMA aperture to be bound by vfio DMA limit Thomas Huth
2022-12-14 10:08 ` [PULL 03/23] s390x/pci: reset ISM passthrough devices on shutdown and system reset Thomas Huth
2022-12-14 10:08 ` [PULL 04/23] target/s390x/tcg/mem_helper: Test the right bits in psw_key_valid() Thomas Huth
2022-12-14 10:08 ` [PULL 05/23] target/s390x: The MVCP and MVCS instructions are not privileged Thomas Huth
2022-12-14 10:08 ` [PULL 06/23] monitor/misc: Remove superfluous include statements Thomas Huth
2022-12-14 10:08 ` [PULL 07/23] scripts/make-release: Add a simple help text for the script Thomas Huth
2022-12-14 10:08 ` [PULL 08/23] scripts/make-release: Only clone single branches to speed up " Thomas Huth
2022-12-14 10:08 ` [PULL 09/23] util/qemu-config: Fix "query-command-line-options" to provide the right values Thomas Huth
2022-12-14 10:08 ` [PULL 10/23] util/oslib-win32: Remove obsolete reference to g_poll code Thomas Huth
2022-12-14 10:08 ` [PULL 11/23] MAINTAINERS: Add documentation files to the corresponding sections Thomas Huth
2022-12-14 10:09 ` [PULL 12/23] hw: Include the VMWare devices only in the x86 targets Thomas Huth
2022-12-14 10:09 ` [PULL 13/23] tests/qtest/libqos/e1000e: Remove "other" interrupts Thomas Huth
2022-12-14 10:09 ` [PULL 14/23] tests/qtest/e1000e-test: De-duplicate constants Thomas Huth
2022-12-14 10:09 ` [PULL 15/23] tests/qtest/libqos/e1000e: Correctly group register accesses Thomas Huth
2022-12-14 10:09 ` [PULL 16/23] .gitlab-ci.d/windows.yml: Unify the prerequisite packages Thomas Huth
2022-12-14 10:09 ` [PULL 17/23] .gitlab-ci.d/windows.yml: Keep 64-bit and 32-bit build scripts consistent Thomas Huth
2022-12-14 10:09 ` [PULL 18/23] .gitlab-ci.d/windows.yml: Exclude qTests from 64-bit CI job for now Thomas Huth
2022-12-14 10:09 ` [PULL 19/23] tests/qtest: Enable qtest build on Windows Thomas Huth
2022-12-14 10:09 ` [PULL 20/23] FreeBSD: Upgrade to 12.4 release Thomas Huth
2022-12-14 10:09 ` [PULL 21/23] gitlab-ci: Check building ppc64 without TCG Thomas Huth
2022-12-14 10:09 ` [PULL 22/23] .gitlab/issue_templates: Move suggestions into comments Thomas Huth
2022-12-14 10:09 ` [PULL 23/23] tests/qtest/vhost-user-blk-test: don't abort all qtests on missing envar Thomas Huth
2022-12-15 13:38 ` [PULL 00/23] First batch of s390x, qtest, CI and misc patches for 8.0 Peter Maydell
2022-12-15 14:14   ` Thomas Huth

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=20221214100911.165291-2-thuth@redhat.com \
    --to=thuth@redhat.com \
    --cc=farman@linux.ibm.com \
    --cc=mjrosato@linux.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@redhat.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).