[PULL 36/97] intel_iommu: Return page walk level even when the translation fails

Michael S. Tsirkin posted 97 patches 5 months ago
Maintainers: Richard Henderson <richard.henderson@linaro.org>, Paolo Bonzini <pbonzini@redhat.com>, "Philippe Mathieu-Daudé" <philmd@linaro.org>, "Michael S. Tsirkin" <mst@redhat.com>, Igor Mammedov <imammedo@redhat.com>, Ani Sinha <anisinha@redhat.com>, Marcel Apfelbaum <marcel.apfelbaum@gmail.com>, Aurelien Jarno <aurelien@aurel32.net>, Peter Maydell <peter.maydell@linaro.org>, Beniamino Galvani <b.galvani@gmail.com>, Strahinja Jankovic <strahinja.p.jankovic@gmail.com>, Tyrone Ting <kfting@nuvoton.com>, Hao Wu <wuhaotsh@google.com>, Shannon Zhao <shannon.zhaosl@gmail.com>, John Snow <jsnow@redhat.com>, Kevin Wolf <kwolf@redhat.com>, Hanna Reitz <hreitz@redhat.com>, Raphael Norwitz <raphael@enfabrica.net>, Stefano Garzarella <sgarzare@redhat.com>, Palmer Dabbelt <palmer@dabbelt.com>, Alistair Francis <alistair.francis@wdc.com>, Weiwei Li <liwei1518@gmail.com>, Daniel Henrique Barboza <dbarboza@ventanamicro.com>, Liu Zhiwei <zhiwei_liu@linux.alibaba.com>, "Marc-André Lureau" <marcandre.lureau@redhat.com>, Eduardo Habkost <eduardo@habkost.net>, Yanan Wang <wangyanan55@huawei.com>, Zhao Liu <zhao1.liu@intel.com>, "Daniel P. Berrangé" <berrange@redhat.com>, Jonathan Cameron <jonathan.cameron@huawei.com>, Fan Ni <fan.ni@samsung.com>, Helge Deller <deller@gmx.de>, Gerd Hoffmann <kraxel@redhat.com>, Jason Wang <jasowang@redhat.com>, Yi Liu <yi.l.liu@intel.com>, "Clément Mathieu--Drif" <clement.mathieu--drif@eviden.com>, Song Gao <gaosong@loongson.cn>, Bibo Mao <maobibo@loongson.cn>, Jiaxun Yang <jiaxun.yang@flygoat.com>, Pavel Pisa <pisa@cmp.felk.cvut.cz>, Francisco Iglesias <francisco.iglesias@amd.com>, Vikram Garhwal <vikram.garhwal@bytedance.com>, Dmitry Fleytman <dmitry.fleytman@gmail.com>, Nicholas Piggin <npiggin@gmail.com>, "Frédéric Barrat" <fbarrat@linux.ibm.com>, Bernhard Beschow <shentey@gmail.com>, Yoshinori Sato <yoshinori.sato@nifty.com>, Magnus Damm <magnus.damm@gmail.com>, Sunil V L <sunilvl@ventanamicro.com>, Matthew Rosato <mjrosato@linux.ibm.com>, Eric Farman <farman@linux.ibm.com>, Halil Pasic <pasic@linux.ibm.com>, Christian Borntraeger <borntraeger@linux.ibm.com>, Thomas Huth <thuth@redhat.com>, David Hildenbrand <david@redhat.com>, Ilya Leoshkevich <iii@linux.ibm.com>, Alex Williamson <alex.williamson@redhat.com>, "Cédric Le Goater" <clg@redhat.com>, Alexander Graf <agraf@csgraf.de>, Phil Dennis-Jordan <phil@philjordan.eu>, "Alex Bennée" <alex.bennee@linaro.org>, Pierrick Bouvier <pierrick.bouvier@linaro.org>, Peter Xu <peterx@redhat.com>, Riku Voipio <riku.voipio@iki.fi>, Manos Pitsidianakis <manos.pitsidianakis@linaro.org>, Fabiano Rosas <farosas@suse.de>, Laurent Vivier <lvivier@redhat.com>, Huacai Chen <chenhuacai@kernel.org>, Aleksandar Rikalo <arikalo@gmail.com>, Alexandre Iooss <erdnaxe@crans.org>, Mahmoud Mandour <ma.mandourr@gmail.com>
[PULL 36/97] intel_iommu: Return page walk level even when the translation fails
Posted by Michael S. Tsirkin 5 months ago
From: CLEMENT MATHIEU--DRIF <clement.mathieu--drif@eviden.com>

We will use this information in vtd_do_iommu_translate to populate the
IOMMUTLBEntry and indicate the correct page mask. This prevents ATS
devices from sending many useless translation requests when a megapage
or gigapage is not present.

Signed-off-by: Clement Mathieu--Drif <clement.mathieu--drif@eviden.com>
Message-Id: <20250628180226.133285-9-clement.mathieu--drif@eviden.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 hw/i386/intel_iommu.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 234c452849..bff307b9bc 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -1987,9 +1987,9 @@ static int vtd_iova_to_flpte(IntelIOMMUState *s, VTDContextEntry *ce,
                              uint32_t pasid)
 {
     dma_addr_t addr = vtd_get_iova_pgtbl_base(s, ce, pasid);
-    uint32_t level = vtd_get_iova_level(s, ce, pasid);
     uint32_t offset;
     uint64_t flpte, flag_ad = VTD_FL_A;
+    *flpte_level = vtd_get_iova_level(s, ce, pasid);
 
     if (!vtd_iova_fl_check_canonical(s, iova, ce, pasid)) {
         error_report_once("%s: detected non canonical IOVA (iova=0x%" PRIx64 ","
@@ -1998,11 +1998,11 @@ static int vtd_iova_to_flpte(IntelIOMMUState *s, VTDContextEntry *ce,
     }
 
     while (true) {
-        offset = vtd_iova_level_offset(iova, level);
+        offset = vtd_iova_level_offset(iova, *flpte_level);
         flpte = vtd_get_pte(addr, offset);
 
         if (flpte == (uint64_t)-1) {
-            if (level == vtd_get_iova_level(s, ce, pasid)) {
+            if (*flpte_level == vtd_get_iova_level(s, ce, pasid)) {
                 /* Invalid programming of pasid-entry */
                 return -VTD_FR_PASID_ENTRY_FSPTPTR_INV;
             } else {
@@ -2028,15 +2028,15 @@ static int vtd_iova_to_flpte(IntelIOMMUState *s, VTDContextEntry *ce,
         if (is_write && !(flpte & VTD_FL_RW)) {
             return -VTD_FR_SM_WRITE;
         }
-        if (vtd_flpte_nonzero_rsvd(flpte, level)) {
+        if (vtd_flpte_nonzero_rsvd(flpte, *flpte_level)) {
             error_report_once("%s: detected flpte reserved non-zero "
                               "iova=0x%" PRIx64 ", level=0x%" PRIx32
                               "flpte=0x%" PRIx64 ", pasid=0x%" PRIX32 ")",
-                              __func__, iova, level, flpte, pasid);
+                              __func__, iova, *flpte_level, flpte, pasid);
             return -VTD_FR_FS_PAGING_ENTRY_RSVD;
         }
 
-        if (vtd_is_last_pte(flpte, level) && is_write) {
+        if (vtd_is_last_pte(flpte, *flpte_level) && is_write) {
             flag_ad |= VTD_FL_D;
         }
 
@@ -2044,14 +2044,13 @@ static int vtd_iova_to_flpte(IntelIOMMUState *s, VTDContextEntry *ce,
             return -VTD_FR_FS_BIT_UPDATE_FAILED;
         }
 
-        if (vtd_is_last_pte(flpte, level)) {
+        if (vtd_is_last_pte(flpte, *flpte_level)) {
             *flptep = flpte;
-            *flpte_level = level;
             return 0;
         }
 
         addr = vtd_get_pte_addr(flpte, aw_bits);
-        level--;
+        (*flpte_level)--;
     }
 }
 
-- 
MST