qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Zhenzhong Duan <zhenzhong.duan@intel.com>
To: qemu-devel@nongnu.org
Cc: alex.williamson@redhat.com, clg@redhat.com,
	eric.auger@redhat.com, mst@redhat.com, peterx@redhat.com,
	jasowang@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com,
	joao.m.martins@oracle.com, clement.mathieu--drif@eviden.com,
	kevin.tian@intel.com, yi.l.liu@intel.com, chao.p.peng@intel.com,
	Yi Sun <yi.y.sun@linux.intel.com>,
	Zhenzhong Duan <zhenzhong.duan@intel.com>,
	Marcel Apfelbaum <marcel.apfelbaum@gmail.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Richard Henderson <richard.henderson@linaro.org>,
	Eduardo Habkost <eduardo@habkost.net>
Subject: [PATCH v1 06/17] intel_iommu: Implement stage-1 translation
Date: Thu, 18 Jul 2024 16:16:25 +0800	[thread overview]
Message-ID: <20240718081636.879544-7-zhenzhong.duan@intel.com> (raw)
In-Reply-To: <20240718081636.879544-1-zhenzhong.duan@intel.com>

From: Yi Liu <yi.l.liu@intel.com>

This adds stage-1 page table walking to support stage-1 only
transltion in scalable modern mode.

Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Co-developed-by: Clément Mathieu--Drif <clement.mathieu--drif@eviden.com>
Signed-off-by: Clément Mathieu--Drif <clement.mathieu--drif@eviden.com>
Signed-off-by: Yi Sun <yi.y.sun@linux.intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
---
 hw/i386/intel_iommu_internal.h |  26 ++++++
 hw/i386/intel_iommu.c          | 146 ++++++++++++++++++++++++++++++++-
 2 files changed, 168 insertions(+), 4 deletions(-)

diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index 1875c2ddd6..36fcc6bb5e 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -440,6 +440,24 @@ typedef union VTDInvDesc VTDInvDesc;
         (0x3ffff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM | VTD_SL_TM)) : \
         (0x3ffff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
 
+/* Rsvd field masks for fpte */
+#define VTD_FS_UPPER_IGNORED 0xfff0000000000000ULL
+#define VTD_FPTE_PAGE_L1_RSVD_MASK(aw) (~(VTD_HAW_MASK(aw)) & \
+                                       (~VTD_FS_UPPER_IGNORED))
+#define VTD_FPTE_PAGE_L2_RSVD_MASK(aw) (~(VTD_HAW_MASK(aw)) & \
+                                       (~VTD_FS_UPPER_IGNORED))
+#define VTD_FPTE_PAGE_L3_RSVD_MASK(aw) (~(VTD_HAW_MASK(aw)) & \
+                                       (~VTD_FS_UPPER_IGNORED))
+#define VTD_FPTE_PAGE_L3_FS1GP_RSVD_MASK(aw) ((0x3fffe000ULL | \
+                                                ~(VTD_HAW_MASK(aw))) \
+                                              & (~VTD_FS_UPPER_IGNORED))
+#define VTD_FPTE_PAGE_L2_FS2MP_RSVD_MASK(aw) ((0x1fe000ULL | \
+                                                ~(VTD_HAW_MASK(aw))) \
+                                              & (~VTD_FS_UPPER_IGNORED))
+#define VTD_FPTE_PAGE_L4_RSVD_MASK(aw) ((0x80ULL | \
+                                            ~(VTD_HAW_MASK(aw))) \
+                                        & (~VTD_FS_UPPER_IGNORED))
+
 #define VTD_INV_DESC_PIOTLB_ALL_IN_PASID  (2ULL << 4)
 #define VTD_INV_DESC_PIOTLB_PSI_IN_PASID  (3ULL << 4)
 
@@ -533,6 +551,14 @@ typedef struct VTDRootEntry VTDRootEntry;
 #define VTD_SM_PASID_ENTRY_AW          7ULL /* Adjusted guest-address-width */
 #define VTD_SM_PASID_ENTRY_DID(val)    ((val) & VTD_DOMAIN_ID_MASK)
 
+#define VTD_SM_PASID_ENTRY_FLPM          3ULL
+#define VTD_SM_PASID_ENTRY_FLPTPTR       (~0xfffULL)
+
+/* First Level Paging Structure */
+/* Masks for First Level Paging Entry */
+#define VTD_FL_P                    1ULL
+#define VTD_FL_RW_MASK              (1ULL << 1)
+
 /* Second Level Page Translation Pointer*/
 #define VTD_SM_PASID_ENTRY_SLPTPTR     (~0xfffULL)
 
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 94f6532935..287741b687 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -48,6 +48,8 @@
 
 /* pe operations */
 #define VTD_PE_GET_TYPE(pe) ((pe)->val[0] & VTD_SM_PASID_ENTRY_PGTT)
+#define VTD_PE_GET_FL_LEVEL(pe) \
+    (4 + (((pe)->val[2] >> 2) & VTD_SM_PASID_ENTRY_FLPM))
 #define VTD_PE_GET_SL_LEVEL(pe) \
     (2 + (((pe)->val[0] >> 2) & VTD_SM_PASID_ENTRY_AW))
 
@@ -755,6 +757,11 @@ static inline bool vtd_is_sl_level_supported(IntelIOMMUState *s, uint32_t level)
            (1ULL << (level - 2 + VTD_CAP_SAGAW_SHIFT));
 }
 
+static inline bool vtd_is_fl_level_supported(IntelIOMMUState *s, uint32_t level)
+{
+    return level == VTD_PML4_LEVEL;
+}
+
 /* Return true if check passed, otherwise false */
 static inline bool vtd_pe_type_check(IntelIOMMUState *s, VTDPASIDEntry *pe)
 {
@@ -841,6 +848,11 @@ static int vtd_get_pe_in_pasid_leaf_table(IntelIOMMUState *s,
             return -VTD_FR_PASID_TABLE_ENTRY_INV;
     }
 
+    if (pgtt == VTD_SM_PASID_ENTRY_FLT &&
+        !vtd_is_fl_level_supported(s, VTD_PE_GET_FL_LEVEL(pe))) {
+            return -VTD_FR_PASID_TABLE_ENTRY_INV;
+    }
+
     return 0;
 }
 
@@ -976,7 +988,11 @@ static uint32_t vtd_get_iova_level(IntelIOMMUState *s,
 
     if (s->root_scalable) {
         vtd_ce_get_rid2pasid_entry(s, ce, &pe, pasid);
-        return VTD_PE_GET_SL_LEVEL(&pe);
+        if (s->scalable_modern) {
+            return VTD_PE_GET_FL_LEVEL(&pe);
+        } else {
+            return VTD_PE_GET_SL_LEVEL(&pe);
+        }
     }
 
     return vtd_ce_get_level(ce);
@@ -1063,7 +1079,11 @@ static dma_addr_t vtd_get_iova_pgtbl_base(IntelIOMMUState *s,
 
     if (s->root_scalable) {
         vtd_ce_get_rid2pasid_entry(s, ce, &pe, pasid);
-        return pe.val[0] & VTD_SM_PASID_ENTRY_SLPTPTR;
+        if (s->scalable_modern) {
+            return pe.val[2] & VTD_SM_PASID_ENTRY_FLPTPTR;
+        } else {
+            return pe.val[0] & VTD_SM_PASID_ENTRY_SLPTPTR;
+        }
     }
 
     return vtd_ce_get_slpt_base(ce);
@@ -1865,6 +1885,104 @@ out:
     trace_vtd_pt_enable_fast_path(source_id, success);
 }
 
+/*
+ * Rsvd field masks for fpte:
+ *     vtd_fpte_rsvd 4k pages
+ *     vtd_fpte_rsvd_large large pages
+ *
+ * We support only 4-level page tables.
+ */
+#define VTD_FPTE_RSVD_LEN 5
+static uint64_t vtd_fpte_rsvd[VTD_FPTE_RSVD_LEN];
+static uint64_t vtd_fpte_rsvd_large[VTD_FPTE_RSVD_LEN];
+
+static bool vtd_flpte_nonzero_rsvd(uint64_t flpte, uint32_t level)
+{
+    uint64_t rsvd_mask;
+
+    /*
+     * We should have caught a guest-mis-programmed level earlier,
+     * via vtd_is_fl_level_supported.
+     */
+    assert(level < VTD_SPTE_RSVD_LEN);
+    /*
+     * Zero level doesn't exist. The smallest level is VTD_PT_LEVEL=1 and
+     * checked by vtd_is_last_pte().
+     */
+    assert(level);
+
+    if ((level == VTD_PD_LEVEL || level == VTD_PDP_LEVEL) &&
+        (flpte & VTD_PT_PAGE_SIZE_MASK)) {
+        /* large page */
+        rsvd_mask = vtd_fpte_rsvd_large[level];
+    } else {
+        rsvd_mask = vtd_fpte_rsvd[level];
+    }
+
+    return flpte & rsvd_mask;
+}
+
+static inline bool vtd_flpte_present(uint64_t flpte)
+{
+    return !!(flpte & VTD_FL_P);
+}
+
+/*
+ * Given the @iova, get relevant @flptep. @flpte_level will be the last level
+ * of the translation, can be used for deciding the size of large page.
+ */
+static int vtd_iova_to_flpte(IntelIOMMUState *s, VTDContextEntry *ce,
+                             uint64_t iova, bool is_write,
+                             uint64_t *flptep, uint32_t *flpte_level,
+                             bool *reads, bool *writes, uint8_t aw_bits,
+                             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;
+
+    while (true) {
+        offset = vtd_iova_level_offset(iova, level);
+        flpte = vtd_get_pte(addr, offset);
+
+        if (flpte == (uint64_t)-1) {
+            if (level == vtd_get_iova_level(s, ce, pasid)) {
+                /* Invalid programming of context-entry */
+                return -VTD_FR_CONTEXT_ENTRY_INV;
+            } else {
+                return -VTD_FR_PAGING_ENTRY_INV;
+            }
+        }
+        if (!vtd_flpte_present(flpte)) {
+            *reads = false;
+            *writes = false;
+            return -VTD_FR_PAGING_ENTRY_INV;
+        }
+        *reads = true;
+        *writes = (*writes) && (flpte & VTD_FL_RW_MASK);
+        if (is_write && !(flpte & VTD_FL_RW_MASK)) {
+            return -VTD_FR_WRITE;
+        }
+        if (vtd_flpte_nonzero_rsvd(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);
+            return -VTD_FR_PAGING_ENTRY_RSVD;
+        }
+
+        if (vtd_is_last_pte(flpte, level)) {
+            *flptep = flpte;
+            *flpte_level = level;
+            return 0;
+        }
+
+        addr = vtd_get_pte_addr(flpte, aw_bits);
+        level--;
+    }
+}
+
 static void vtd_report_fault(IntelIOMMUState *s,
                              int err, bool is_fpd_set,
                              uint16_t source_id,
@@ -2013,8 +2131,13 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus,
         }
     }
 
-    ret_fr = vtd_iova_to_slpte(s, &ce, addr, is_write, &pte, &level,
-                               &reads, &writes, s->aw_bits, pasid);
+    if (s->scalable_modern && s->root_scalable) {
+        ret_fr = vtd_iova_to_flpte(s, &ce, addr, is_write, &pte, &level,
+                                   &reads, &writes, s->aw_bits, pasid);
+    } else {
+        ret_fr = vtd_iova_to_slpte(s, &ce, addr, is_write, &pte, &level,
+                                   &reads, &writes, s->aw_bits, pasid);
+    }
     if (ret_fr) {
         vtd_report_fault(s, -ret_fr, is_fpd_set, source_id,
                          addr, is_write, pasid != PCI_NO_PASID, pasid);
@@ -4231,6 +4354,21 @@ static void vtd_init(IntelIOMMUState *s)
     vtd_spte_rsvd_large[3] = VTD_SPTE_LPAGE_L3_RSVD_MASK(s->aw_bits,
                                                     x86_iommu->dt_supported);
 
+    /*
+     * Rsvd field masks for fpte
+     */
+    vtd_fpte_rsvd[0] = ~0ULL;
+    vtd_fpte_rsvd[1] = VTD_FPTE_PAGE_L1_RSVD_MASK(s->aw_bits);
+    vtd_fpte_rsvd[2] = VTD_FPTE_PAGE_L2_RSVD_MASK(s->aw_bits);
+    vtd_fpte_rsvd[3] = VTD_FPTE_PAGE_L3_RSVD_MASK(s->aw_bits);
+    vtd_fpte_rsvd[4] = VTD_FPTE_PAGE_L4_RSVD_MASK(s->aw_bits);
+
+    vtd_fpte_rsvd_large[0] = ~0ULL;
+    vtd_fpte_rsvd_large[1] = ~0ULL;
+    vtd_fpte_rsvd_large[2] = VTD_FPTE_PAGE_L2_FS2MP_RSVD_MASK(s->aw_bits);
+    vtd_fpte_rsvd_large[3] = VTD_FPTE_PAGE_L3_FS1GP_RSVD_MASK(s->aw_bits);
+    vtd_fpte_rsvd_large[4] = ~0ULL;
+
     if (s->scalable_mode || s->snoop_control) {
         vtd_spte_rsvd[1] &= ~VTD_SPTE_SNP;
         vtd_spte_rsvd_large[2] &= ~VTD_SPTE_SNP;
-- 
2.34.1



  parent reply	other threads:[~2024-07-18  8:22 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-07-18  8:16 [PATCH v1 00/17] intel_iommu: Enable stage-1 translation for emulated device Zhenzhong Duan
2024-07-18  8:16 ` [PATCH v1 01/17] intel_iommu: Use the latest fault reasons defined by spec Zhenzhong Duan
2024-07-23  7:12   ` CLEMENT MATHIEU--DRIF
2024-07-29  7:39   ` Yi Liu
2024-07-29  8:42     ` Michael S. Tsirkin
2024-07-29  9:39       ` Yi Liu
2024-07-18  8:16 ` [PATCH v1 02/17] intel_iommu: Make pasid entry type check accurate Zhenzhong Duan
2024-07-18  9:06   ` CLEMENT MATHIEU--DRIF
2024-07-18  8:16 ` [PATCH v1 03/17] intel_iommu: Add a placeholder variable for scalable modern mode Zhenzhong Duan
2024-07-18  9:02   ` CLEMENT MATHIEU--DRIF
2024-07-19  2:47     ` Duan, Zhenzhong
2024-07-19  3:22       ` Yi Liu
2024-07-19  3:37         ` Duan, Zhenzhong
2024-07-19  3:39           ` Duan, Zhenzhong
2024-07-19  4:26             ` CLEMENT MATHIEU--DRIF
2024-07-23  7:12             ` CLEMENT MATHIEU--DRIF
2024-07-23  8:50               ` Duan, Zhenzhong
2024-07-19  4:21       ` CLEMENT MATHIEU--DRIF
2024-07-18  8:16 ` [PATCH v1 04/17] intel_iommu: Flush stage-2 cache in PADID-selective PASID-based iotlb invalidation Zhenzhong Duan
2024-07-23 16:02   ` CLEMENT MATHIEU--DRIF
2024-07-24  2:59     ` Duan, Zhenzhong
2024-07-24  5:16       ` CLEMENT MATHIEU--DRIF
2024-07-24  5:19         ` Duan, Zhenzhong
2024-07-18  8:16 ` [PATCH v1 05/17] intel_iommu: Rename slpte to pte Zhenzhong Duan
2024-07-18  8:16 ` Zhenzhong Duan [this message]
2024-07-18  8:16 ` [PATCH v1 07/17] intel_iommu: Check if the input address is canonical Zhenzhong Duan
2024-07-18  8:16 ` [PATCH v1 08/17] intel_iommu: Set accessed and dirty bits during first stage translation Zhenzhong Duan
2024-07-18  8:16 ` [PATCH v1 09/17] intel_iommu: Flush stage-1 cache in iotlb invalidation Zhenzhong Duan
2024-07-23  7:12   ` CLEMENT MATHIEU--DRIF
2024-07-18  8:16 ` [PATCH v1 10/17] intel_iommu: Process PASID-based " Zhenzhong Duan
2024-07-23 16:18   ` CLEMENT MATHIEU--DRIF
2024-07-18  8:16 ` [PATCH v1 11/17] intel_iommu: Extract device IOTLB invalidation logic Zhenzhong Duan
2024-07-24  8:35   ` CLEMENT MATHIEU--DRIF
2024-07-24  8:42     ` Duan, Zhenzhong
2024-07-18  8:16 ` [PATCH v1 12/17] intel_iommu: Add an internal API to find an address space with PASID Zhenzhong Duan
2024-07-18  8:16 ` [PATCH v1 13/17] intel_iommu: Add support for PASID-based device IOTLB invalidation Zhenzhong Duan
2024-07-18  8:16 ` [PATCH v1 14/17] intel_iommu: piotlb invalidation should notify unmap Zhenzhong Duan
2024-07-24  5:45   ` CLEMENT MATHIEU--DRIF
2024-07-24  6:04     ` CLEMENT MATHIEU--DRIF
2024-07-24  6:07       ` Duan, Zhenzhong
2024-07-24  6:11         ` CLEMENT MATHIEU--DRIF
2024-07-18  8:16 ` [PATCH v1 15/17] intel_iommu: Set default aw_bits to 48 in scalable modren mode Zhenzhong Duan
2024-07-18  9:14   ` CLEMENT MATHIEU--DRIF
2024-07-18  8:16 ` [PATCH v1 16/17] intel_iommu: Modify x-scalable-mode to be string option Zhenzhong Duan
2024-07-18  9:25   ` CLEMENT MATHIEU--DRIF
2024-07-19  2:53     ` Duan, Zhenzhong
2024-07-19  4:23       ` CLEMENT MATHIEU--DRIF
2024-07-18  8:16 ` [PATCH v1 17/17] tests/qtest: Add intel-iommu test Zhenzhong Duan
2024-07-24  5:58   ` CLEMENT MATHIEU--DRIF
2024-07-24  6:14     ` Duan, Zhenzhong

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=20240718081636.879544-7-zhenzhong.duan@intel.com \
    --to=zhenzhong.duan@intel.com \
    --cc=alex.williamson@redhat.com \
    --cc=chao.p.peng@intel.com \
    --cc=clement.mathieu--drif@eviden.com \
    --cc=clg@redhat.com \
    --cc=eduardo@habkost.net \
    --cc=eric.auger@redhat.com \
    --cc=jasowang@redhat.com \
    --cc=jgg@nvidia.com \
    --cc=joao.m.martins@oracle.com \
    --cc=kevin.tian@intel.com \
    --cc=marcel.apfelbaum@gmail.com \
    --cc=mst@redhat.com \
    --cc=nicolinc@nvidia.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=yi.l.liu@intel.com \
    --cc=yi.y.sun@linux.intel.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).