On 2024/11/4 11:05, Duan, Zhenzhong wrote:


-----Original Message-----
From: Liu, Yi L <yi.l....@intel.com>
Sent: Sunday, November 3, 2024 10:22 PM
Subject: Re: [PATCH v4 06/17] intel_iommu: Implement stage-1 translation

On 2024/9/30 17:26, Zhenzhong Duan wrote:
From: Yi Liu <yi.l....@intel.com>

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

Signed-off-by: Yi Liu <yi.l....@intel.com>
Co-developed-by: Clément Mathieu--Drif <clement.mathieu--d...@eviden.com>
Signed-off-by: Clément Mathieu--Drif <clement.mathieu--d...@eviden.com>
Signed-off-by: Yi Sun <yi.y....@linux.intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.d...@intel.com>
Acked-by: Jason Wang <jasow...@redhat.com>
---
   hw/i386/intel_iommu_internal.h |  24 ++++++
   hw/i386/intel_iommu.c          | 143 ++++++++++++++++++++++++++++++++-
   2 files changed, 163 insertions(+), 4 deletions(-)

diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index 20fcc73938..38bf0c7a06 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -428,6 +428,22 @@ typedef union VTDInvDesc VTDInvDesc;
   #define VTD_SPTE_LPAGE_L3_RSVD_MASK(aw) \
           (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_L4_RSVD_MASK(aw) \
+        (0x80ULL | ~(VTD_HAW_MASK(aw) | VTD_FS_UPPER_IGNORED))
+
+#define VTD_FPTE_LPAGE_L2_RSVD_MASK(aw) \
+        (0x1fe000ULL | ~(VTD_HAW_MASK(aw) | VTD_FS_UPPER_IGNORED))
+#define VTD_FPTE_LPAGE_L3_RSVD_MASK(aw) \
+        (0x3fffe000ULL | ~(VTD_HAW_MASK(aw) | VTD_FS_UPPER_IGNORED))
+
   /* Masks for PIOTLB Invalidate Descriptor */
   #define VTD_INV_DESC_PIOTLB_G             (3ULL << 4)
   #define VTD_INV_DESC_PIOTLB_ALL_IN_PASID  (2ULL << 4)
@@ -520,6 +536,14 @@ 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                   (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 6f2414898c..56d5933e93 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(X86IOMMUState *x86_iommu,
                                        VTDPASIDEntry *pe)
@@ -838,6 +845,11 @@ 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;
   }

@@ -973,7 +985,11 @@ 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);
@@ -1060,7 +1076,11 @@ 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);
@@ -1862,6 +1882,104 @@ 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_FPTE_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);
+        if (is_write && !(flpte & VTD_FL_RW)) {
+            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--;
+    }

As I replied in last version, it should check the ir range for the
translation result. I saw your reply, but that only covers the input
address, my comment is about the output addr.

[1]
https://lore.kernel.org/qemu-
devel/SJ0PR11MB6744D2B572D278DAF8BF267692762@SJ0PR11MB6744.nampr
d11.prod.outlook.com/

Oh, I see, you are right! As the check for ir range is common for both stage-2 
and stage-1,
I plan to move it to common place with a separate patch like below, let me know 
if you
prefer to have separate check for both stage-2 and stage-1.

checking it in the common place is ok.


--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -1235,7 +1235,6 @@ static int vtd_iova_to_slpte(IntelIOMMUState *s, 
VTDContextEntry *ce,
      uint32_t offset;
      uint64_t slpte;
      uint64_t access_right_check;
-    uint64_t xlat, size;

      if (!vtd_iova_sl_range_check(s, iova, ce, aw_bits, pasid)) {
          error_report_once("%s: detected IOVA overflow (iova=0x%" PRIx64 ","
@@ -1288,28 +1287,7 @@ static int vtd_iova_to_slpte(IntelIOMMUState *s, 
VTDContextEntry *ce,
          level--;
      }

-    xlat = vtd_get_pte_addr(*slptep, aw_bits);
-    size = ~vtd_pt_level_page_mask(level) + 1;
-
-    /*
-     * From VT-d spec 3.14: Untranslated requests and translation
-     * requests that result in an address in the interrupt range will be
-     * blocked with condition code LGN.4 or SGN.8.
-     */
-    if ((xlat > VTD_INTERRUPT_ADDR_LAST ||
-         xlat + size - 1 < VTD_INTERRUPT_ADDR_FIRST)) {
-        return 0;
-    } else {
-        error_report_once("%s: xlat address is in interrupt range "
-                          "(iova=0x%" PRIx64 ", level=0x%" PRIx32 ", "
-                          "slpte=0x%" PRIx64 ", write=%d, "
-                          "xlat=0x%" PRIx64 ", size=0x%" PRIx64 ", "
-                          "pasid=0x%" PRIx32 ")",
-                          __func__, iova, level, slpte, is_write,
-                          xlat, size, pasid);
-        return s->scalable_mode ? -VTD_FR_SM_INTERRUPT_ADDR :
-                                  -VTD_FR_INTERRUPT_ADDR;
-    }
+    return 0;
  }

  typedef int (*vtd_page_walk_hook)(const IOMMUTLBEvent *event, void *private);
@@ -2201,6 +2179,7 @@ static bool vtd_do_iommu_translate(VTDAddressSpace 
*vtd_as, PCIBus *bus,
      uint8_t access_flags, pgtt;
      bool rid2pasid = (pasid == PCI_NO_PASID) && s->root_scalable;
      VTDIOTLBEntry *iotlb_entry;
+    uint64_t xlat, size;

      /*
       * We have standalone memory region for interrupt addresses, we
@@ -2312,6 +2291,29 @@ static bool vtd_do_iommu_translate(VTDAddressSpace 
*vtd_as, PCIBus *bus,
                                     &reads, &writes, s->aw_bits, pasid);
          pgtt = VTD_SM_PASID_ENTRY_SLT;
      }
+    if (!ret_fr) {
+        xlat = vtd_get_pte_addr(pte, s->aw_bits);
+        size = ~vtd_pt_level_page_mask(level) + 1;
+
+        /*
+         * From VT-d spec 3.14: Untranslated requests and translation
+         * requests that result in an address in the interrupt range will be
+         * blocked with condition code LGN.4 or SGN.8.
+         */
+        if ((xlat <= VTD_INTERRUPT_ADDR_LAST &&
+             xlat + size - 1 >= VTD_INTERRUPT_ADDR_FIRST)) {
+            error_report_once("%s: xlat address is in interrupt range "
+                              "(iova=0x%" PRIx64 ", level=0x%" PRIx32 ", "
+                              "pte=0x%" PRIx64 ", write=%d, "
+                              "xlat=0x%" PRIx64 ", size=0x%" PRIx64 ", "
+                              "pasid=0x%" PRIx32 ")",
+                              __func__, addr, level, pte, is_write,
+                              xlat, size, pasid);
+            ret_fr = s->scalable_mode ? -VTD_FR_SM_INTERRUPT_ADDR :
+                                        -VTD_FR_INTERRUPT_ADDR;
+        }
+    }
+
      if (ret_fr) {
          vtd_report_fault(s, -ret_fr, is_fpd_set, source_id,
                           addr, is_write, pasid != PCI_NO_PASID, pasid);

--
Regards,
Yi Liu

Reply via email to