x86: Native Branch History Injection [XSA-456, CVE-2024-2201]

update to xen 4.17.4, remove patches now included upstream
  rebase xen.gcc12.fixes.patch
x86 HVM hypercalls may trigger Xen bug check [XSA-454, CVE-2023-46842]
x86: Incorrect logic for BTC/SRSO mitigations [XSA-455, CVE-2024-31142]

.gitignore

@@ -6,4 +6,4 @@ lwip-1.3.0.tar.gz
 pciutils-2.2.9.tar.bz2
 zlib-1.2.3.tar.gz
 polarssl-1.1.4-gpl.tgz
-/xen-4.17.2.tar.gz
+/xen-4.17.4.tar.gz

sources

@@ -4,4 +4,4 @@ SHA512 (newlib-1.16.0.tar.gz) = 40eb96bbc6736a16b6399e0cdb73e853d0d90b685c967e77
 SHA512 (zlib-1.2.3.tar.gz) = 021b958fcd0d346c4ba761bcf0cc40f3522de6186cf5a0a6ea34a70504ce9622b1c2626fce40675bc8282cf5f5ade18473656abc38050f72f5d6480507a2106e
 SHA512 (polarssl-1.1.4-gpl.tgz) = 88da614e4d3f4409c4fd3bb3e44c7587ba051e3fed4e33d526069a67e8180212e1ea22da984656f50e290049f60ddca65383e5983c0f8884f648d71f698303ad
 SHA512 (pciutils-2.2.9.tar.bz2) = 2b3d98d027e46d8c08037366dde6f0781ca03c610ef2b380984639e4ef39899ed8d8b8e4cd9c9dc54df101279b95879bd66bfd4d04ad07fef41e847ea7ae32b5
-SHA512 (xen-4.17.2.tar.gz) = 0bc475483676e4aa27735695f9a8d2821059e7a55984adb8a29badb5c09a4e7cf8ea29cbc9691be616cc0d7a5ee6b6dacc59ba29c2b16e0919ebdf7dfc54201a
+SHA512 (xen-4.17.4.tar.gz) = 50dc2efd26e48131afdbc8efb1ca90154a84fe5fba5a6bc81d9801a3c13aebea91c8211872b5c69ce2773644f2c935c31cc56584a05b10b81e8728282d89eb84

xen.gcc12.fixes.patch

@@ -1,7 +1,7 @@
 --- xen-4.16.0/Config.mk.orig	2021-11-30 11:42:42.000000000 +0000
 +++ xen-4.16.0/Config.mk	2022-01-24 20:25:16.687125822 +0000
 @@ -186,6 +186,7 @@
- $(call cc-option-add,CFLAGS,CC,-Wdeclaration-after-statement)
+ 
  $(call cc-option-add,CFLAGS,CC,-Wno-unused-but-set-variable)
  $(call cc-option-add,CFLAGS,CC,-Wno-unused-local-typedefs)
 +$(call cc-option-add,CFLAGS,CC,-Wno-error=array-bounds)

xen.spec

@@ -54,8 +54,8 @@
 
 Summary: Xen is a virtual machine monitor
 Name:    xen
-Version: 4.17.2
-Release: 5%{?dist}
+Version: 4.17.4
+Release: 1%{?dist}
 License: GPLv2+ and LGPLv2+ and BSD
 URL:     http://xen.org/
 Source0: https://downloads.xenproject.org/release/xen/%{version}/xen-%{version}.tar.gz
@@ -112,35 +112,6 @@ Patch46: xen.efi.build.patch
 Patch47: xen.gcc13.fixes.patch
 Patch49: xen.python3.12.patch
 Patch50: xen.ocaml5.fixes.patch
-Patch51: xsa437.patch
-Patch52: xsa438-4.17.patch
-Patch53: xsa439-0001-x86-AMD-extend-Zenbleed-check-to-models-good-ucode-i.patch
-Patch54: xsa439-0002-x86-spec-ctrl-Fix-confusion-between-SPEC_CTRL_EXIT_T.patch
-Patch55: xsa439-0003-x86-spec-ctrl-Fold-DO_SPEC_CTRL_EXIT_TO_XEN-into-it-.patch
-Patch56: xsa439-0004-x86-spec-ctrl-Turn-the-remaining-SPEC_CTRL_-ENTRY-EX.patch
-Patch57: xsa439-0005-x86-spec-ctrl-Improve-all-SPEC_CTRL_-ENTER-EXIT-_-co.patch
-Patch58: xsa439-0006-x86-entry-Adjust-restore_all_xen-to-hold-stack_end-i.patch
-Patch59: xsa439-0007-x86-entry-Track-the-IST-ness-of-an-entry-for-the-exi.patch
-Patch60: xsa439-0008-x86-spec-ctrl-Issue-VERW-during-IST-exit-to-Xen.patch
-Patch61: xsa439-0009-x86-amd-Introduce-is_zen-1-2-_uarch-predicates.patch
-Patch62: xsa439-0010-x86-spec-ctrl-Mitigate-the-Zen1-DIV-leakage.patch
-Patch63: xsa440-4.17.patch
-Patch64: xsa442-4.17.patch
-Patch65: xsa443-4.17-01.patch
-Patch66: xsa443-4.17-02.patch
-Patch67: xsa443-4.17-03.patch
-Patch68: xsa443-4.17-04.patch
-Patch69: xsa443-4.17-05.patch
-Patch70: xsa443-4.17-06.patch
-Patch71: xsa443-4.17-07.patch
-Patch72: xsa443-4.17-08.patch
-Patch73: xsa443-4.17-09.patch
-Patch74: xsa443-4.17-10.patch
-Patch75: xsa443-4.17-11.patch
-Patch76: xsa444-4.17-1.patch
-Patch77: xsa444-4.17-2.patch
-Patch78: xsa445-4.17.patch
-Patch79: xsa446.patch
 
 
 %if %build_qemutrad
@@ -357,35 +328,6 @@ manage Xen virtual machines.
 %if "%dist" != ".fc38"
 %patch 50 -p1
 %endif
-%patch 51 -p1
-%patch 52 -p1
-%patch 53 -p1
-%patch 54 -p1
-%patch 55 -p1
-%patch 56 -p1
-%patch 57 -p1
-%patch 58 -p1
-%patch 59 -p1
-%patch 60 -p1
-%patch 61 -p1
-%patch 62 -p1
-%patch 63 -p1
-%patch 64 -p1
-%patch 65 -p1
-%patch 66 -p1
-%patch 67 -p1
-%patch 68 -p1
-%patch 69 -p1
-%patch 70 -p1
-%patch 71 -p1
-%patch 72 -p1
-%patch 73 -p1
-%patch 74 -p1
-%patch 75 -p1
-%patch 76 -p1
-%patch 77 -p1
-%patch 78 -p1
-%patch 79 -p1
 
 # qemu-xen-traditional patches
 pushd tools/qemu-xen-traditional
@@ -993,6 +935,30 @@ fi
 %endif
 
 %changelog
+* Tue Apr 09 2024 Michael Young <m.a.young@durham.ac.uk> - 4.17.4-1
+- x86: Native Branch History Injection [XSA-456, CVE-2024-2201]
+- update to xen 4.17.4, remove patches now included upstream
+  rebase xen.gcc12.fixes.patch
+- x86 HVM hypercalls may trigger Xen bug check [XSA-454, CVE-2023-46842]
+- x86: Incorrect logic for BTC/SRSO mitigations [XSA-455, CVE-2024-31142]
+
+* Thu Mar 14 2024 Michael Young <m.a.young@durham.ac.uk> - 4.17.2-8
+- x86: Register File Data Sampling [XSA-452, CVE-2023-28746]
+- GhostRace: Speculative Race Conditions [XSA-453, CVE-2024-2193]
+- additional patches so above applies cleanly
+
+* Tue Feb 27 2024 Michael Young <m.a.young@durham.ac.uk> - 4.17.2-7
+- x86: shadow stack vs exceptions from emulation stubs - [XSA-451,
+        CVE-2023-46841] (#2266326)
+
+* Tue Jan 30 2024 Michael Young <m.a.young@durham.ac.uk> - 4.17.2-6
+- arm32: The cache may not be properly cleaned/invalidated (take two)
+	[XSA-447, CVE-2023-46837]
+- pci: phantom functions assigned to incorrect contexts [XSA-449,
+	CVE-2023-46839]
+- VT-d: Failure to quarantine devices in !HVM build [XSA-450,
+	CVE-2023-46840]
+
 * Tue Nov 14 2023 Michael Young <m.a.young@durham.ac.uk> - 4.17.2-5
 - x86/AMD: mismatch in IOMMU quarantine page table levels [XSA-445,
 	CVE-2023-46835]

xsa437.patch

@@ -1,110 +0,0 @@
-From 7fac5971340a13ca9458195305bcfe14df2e52d2 Mon Sep 17 00:00:00 2001
-From: Stefano Stabellini <stefano.stabellini@amd.com>
-Date: Thu, 17 Aug 2023 13:41:35 +0100
-Subject: [PATCH] xen/arm: page: Handle cache flush of an element at the top of
- the address space
-
-The region that needs to be cleaned/invalidated may be at the top
-of the address space. This means that 'end' (i.e. 'p + size') will
-be 0 and therefore nothing will be cleaned/invalidated as the check
-in the loop will always be false.
-
-On Arm64, we only support we only support up to 48-bit Virtual
-address space. So this is not a concern there. However, for 32-bit,
-the mapcache is using the last 2GB of the address space. Therefore
-we may not clean/invalidate properly some pages. This could lead
-to memory corruption or data leakage (the scrubbed value may
-still sit in the cache when the guest could read directly the memory
-and therefore read the old content).
-
-Rework invalidate_dcache_va_range(), clean_dcache_va_range(),
-clean_and_invalidate_dcache_va_range() to handle a cache flush
-with an element at the top of the address space.
-
-This is CVE-2023-34321 / XSA-437.
-
-Reported-by: Julien Grall <jgrall@amazon.com>
-Signed-off-by: Stefano Stabellini <stefano.stabellini@amd.com>
-Signed-off-by: Julien Grall <jgrall@amazon.com>
-Acked-by: Bertrand Marquis <bertrand.marquis@arm.com>
-
----
- xen/arch/arm/include/asm/page.h | 33 ++++++++++++++++++++-------------
- 1 file changed, 20 insertions(+), 13 deletions(-)
-
-diff --git a/xen/arch/arm/include/asm/page.h b/xen/arch/arm/include/asm/page.h
-index e7cd62190c7f..d7fe770a5e49 100644
---- a/xen/arch/arm/include/asm/page.h
-+++ b/xen/arch/arm/include/asm/page.h
-@@ -160,26 +160,25 @@ static inline size_t read_dcache_line_bytes(void)
- 
- static inline int invalidate_dcache_va_range(const void *p, unsigned long size)
- {
--    const void *end = p + size;
-     size_t cacheline_mask = dcache_line_bytes - 1;
- 
-     dsb(sy);           /* So the CPU issues all writes to the range */
- 
-     if ( (uintptr_t)p & cacheline_mask )
-     {
-+        size -= dcache_line_bytes - ((uintptr_t)p & cacheline_mask);
-         p = (void *)((uintptr_t)p & ~cacheline_mask);
-         asm volatile (__clean_and_invalidate_dcache_one(0) : : "r" (p));
-         p += dcache_line_bytes;
-     }
--    if ( (uintptr_t)end & cacheline_mask )
--    {
--        end = (void *)((uintptr_t)end & ~cacheline_mask);
--        asm volatile (__clean_and_invalidate_dcache_one(0) : : "r" (end));
--    }
- 
--    for ( ; p < end; p += dcache_line_bytes )
-+    for ( ; size >= dcache_line_bytes;
-+            p += dcache_line_bytes, size -= dcache_line_bytes )
-         asm volatile (__invalidate_dcache_one(0) : : "r" (p));
- 
-+    if ( size > 0 )
-+        asm volatile (__clean_and_invalidate_dcache_one(0) : : "r" (p));
-+
-     dsb(sy);           /* So we know the flushes happen before continuing */
- 
-     return 0;
-@@ -187,10 +186,14 @@ static inline int invalidate_dcache_va_range(const void *p, unsigned long size)
- 
- static inline int clean_dcache_va_range(const void *p, unsigned long size)
- {
--    const void *end = p + size;
-+    size_t cacheline_mask = dcache_line_bytes - 1;
-+
-     dsb(sy);           /* So the CPU issues all writes to the range */
--    p = (void *)((uintptr_t)p & ~(dcache_line_bytes - 1));
--    for ( ; p < end; p += dcache_line_bytes )
-+    size += (uintptr_t)p & cacheline_mask;
-+    size = (size + cacheline_mask) & ~cacheline_mask;
-+    p = (void *)((uintptr_t)p & ~cacheline_mask);
-+    for ( ; size >= dcache_line_bytes;
-+            p += dcache_line_bytes, size -= dcache_line_bytes )
-         asm volatile (__clean_dcache_one(0) : : "r" (p));
-     dsb(sy);           /* So we know the flushes happen before continuing */
-     /* ARM callers assume that dcache_* functions cannot fail. */
-@@ -200,10 +203,14 @@ static inline int clean_dcache_va_range(const void *p, unsigned long size)
- static inline int clean_and_invalidate_dcache_va_range
-     (const void *p, unsigned long size)
- {
--    const void *end = p + size;
-+    size_t cacheline_mask = dcache_line_bytes - 1;
-+
-     dsb(sy);         /* So the CPU issues all writes to the range */
--    p = (void *)((uintptr_t)p & ~(dcache_line_bytes - 1));
--    for ( ; p < end; p += dcache_line_bytes )
-+    size += (uintptr_t)p & cacheline_mask;
-+    size = (size + cacheline_mask) & ~cacheline_mask;
-+    p = (void *)((uintptr_t)p & ~cacheline_mask);
-+    for ( ; size >= dcache_line_bytes;
-+            p += dcache_line_bytes, size -= dcache_line_bytes )
-         asm volatile (__clean_and_invalidate_dcache_one(0) : : "r" (p));
-     dsb(sy);         /* So we know the flushes happen before continuing */
-     /* ARM callers assume that dcache_* functions cannot fail. */
--- 
-2.40.1
-

xsa438-4.17.patch

@@ -1,416 +0,0 @@
-From: Jan Beulich <jbeulich@suse.com>
-Subject: x86/shadow: defer releasing of PV's top-level shadow reference
-
-sh_set_toplevel_shadow() re-pinning the top-level shadow we may be
-running on is not enough (and at the same time unnecessary when the
-shadow isn't what we're running on): That shadow becomes eligible for
-blowing away (from e.g. shadow_prealloc()) immediately after the
-paging lock was dropped. Yet it needs to remain valid until the actual
-page table switch occurred.
-
-Propagate up the call chain the shadow entry that needs releasing
-eventually, and carry out the release immediately after switching page
-tables. Handle update_cr3() failures by switching to idle pagetables.
-Note that various further uses of update_cr3() are HVM-only or only act
-on paused vCPU-s, in which case sh_set_toplevel_shadow() will not defer
-releasing of the reference.
-
-While changing the update_cr3() hook, also convert the "do_locking"
-parameter to boolean.
-
-This is CVE-2023-34322 / XSA-438.
-
-Reported-by: Tim Deegan <tim@xen.org>
-Signed-off-by: Jan Beulich <jbeulich@suse.com>
-Reviewed-by: George Dunlap <george.dunlap@cloud.com>
-
---- a/xen/arch/x86/include/asm/mm.h
-+++ b/xen/arch/x86/include/asm/mm.h
-@@ -552,7 +552,7 @@ void audit_domains(void);
- #endif
- 
- void make_cr3(struct vcpu *v, mfn_t mfn);
--void update_cr3(struct vcpu *v);
-+pagetable_t update_cr3(struct vcpu *v);
- int vcpu_destroy_pagetables(struct vcpu *);
- void *do_page_walk(struct vcpu *v, unsigned long addr);
- 
---- a/xen/arch/x86/include/asm/paging.h
-+++ b/xen/arch/x86/include/asm/paging.h
-@@ -138,7 +138,7 @@ struct paging_mode {
-                                             paddr_t ga, uint32_t *pfec,
-                                             unsigned int *page_order);
- #endif
--    void          (*update_cr3            )(struct vcpu *v, int do_locking,
-+    pagetable_t   (*update_cr3            )(struct vcpu *v, bool do_locking,
-                                             bool noflush);
-     void          (*update_paging_modes   )(struct vcpu *v);
-     bool          (*flush_tlb             )(const unsigned long *vcpu_bitmap);
-@@ -310,9 +310,9 @@ static inline unsigned long paging_ga_to
- /* Update all the things that are derived from the guest's CR3.
-  * Called when the guest changes CR3; the caller can then use v->arch.cr3
-  * as the value to load into the host CR3 to schedule this vcpu */
--static inline void paging_update_cr3(struct vcpu *v, bool noflush)
-+static inline pagetable_t paging_update_cr3(struct vcpu *v, bool noflush)
- {
--    paging_get_hostmode(v)->update_cr3(v, 1, noflush);
-+    return paging_get_hostmode(v)->update_cr3(v, 1, noflush);
- }
- 
- /* Update all the things that are derived from the guest's CR0/CR3/CR4.
---- a/xen/arch/x86/include/asm/shadow.h
-+++ b/xen/arch/x86/include/asm/shadow.h
-@@ -99,6 +99,9 @@ int shadow_set_allocation(struct domain
- 
- int shadow_get_allocation_bytes(struct domain *d, uint64_t *size);
- 
-+/* Helper to invoke for deferred releasing of a top-level shadow's reference. */
-+void shadow_put_top_level(struct domain *d, pagetable_t old);
-+
- #else /* !CONFIG_SHADOW_PAGING */
- 
- #define shadow_vcpu_teardown(v) ASSERT(is_pv_vcpu(v))
-@@ -121,6 +124,11 @@ static inline void shadow_prepare_page_t
- 
- static inline void shadow_blow_tables_per_domain(struct domain *d) {}
- 
-+static inline void shadow_put_top_level(struct domain *d, pagetable_t old)
-+{
-+    ASSERT_UNREACHABLE();
-+}
-+
- static inline int shadow_domctl(struct domain *d,
-                                 struct xen_domctl_shadow_op *sc,
-                                 XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
---- a/xen/arch/x86/mm/hap/hap.c
-+++ b/xen/arch/x86/mm/hap/hap.c
-@@ -739,11 +739,13 @@ static bool cf_check hap_invlpg(struct v
-     return 1;
- }
- 
--static void cf_check hap_update_cr3(
--    struct vcpu *v, int do_locking, bool noflush)
-+static pagetable_t cf_check hap_update_cr3(
-+    struct vcpu *v, bool do_locking, bool noflush)
- {
-     v->arch.hvm.hw_cr[3] = v->arch.hvm.guest_cr[3];
-     hvm_update_guest_cr3(v, noflush);
-+
-+    return pagetable_null();
- }
- 
- static bool flush_vcpu(const struct vcpu *v, const unsigned long *vcpu_bitmap)
---- a/xen/arch/x86/mm/shadow/common.c
-+++ b/xen/arch/x86/mm/shadow/common.c
-@@ -2590,13 +2590,13 @@ void cf_check shadow_update_paging_modes
- }
- 
- /* Set up the top-level shadow and install it in slot 'slot' of shadow_table */
--void sh_set_toplevel_shadow(struct vcpu *v,
--                            unsigned int slot,
--                            mfn_t gmfn,
--                            unsigned int root_type,
--                            mfn_t (*make_shadow)(struct vcpu *v,
--                                                 mfn_t gmfn,
--                                                 uint32_t shadow_type))
-+pagetable_t sh_set_toplevel_shadow(struct vcpu *v,
-+                                   unsigned int slot,
-+                                   mfn_t gmfn,
-+                                   unsigned int root_type,
-+                                   mfn_t (*make_shadow)(struct vcpu *v,
-+                                                        mfn_t gmfn,
-+                                                        uint32_t shadow_type))
- {
-     mfn_t smfn;
-     pagetable_t old_entry, new_entry;
-@@ -2653,20 +2653,37 @@ void sh_set_toplevel_shadow(struct vcpu
-                   mfn_x(gmfn), mfn_x(pagetable_get_mfn(new_entry)));
-     v->arch.paging.shadow.shadow_table[slot] = new_entry;
- 
--    /* Decrement the refcount of the old contents of this slot */
--    if ( !pagetable_is_null(old_entry) )
-+    /*
-+     * Decrement the refcount of the old contents of this slot, unless
-+     * we're still running on that shadow - in that case it'll need holding
-+     * on to until the actual page table switch did occur.
-+     */
-+    if ( !pagetable_is_null(old_entry) && (v != current || !is_pv_domain(d)) )
-     {
--        mfn_t old_smfn = pagetable_get_mfn(old_entry);
--        /* Need to repin the old toplevel shadow if it's been unpinned
--         * by shadow_prealloc(): in PV mode we're still running on this
--         * shadow and it's not safe to free it yet. */
--        if ( !mfn_to_page(old_smfn)->u.sh.pinned && !sh_pin(d, old_smfn) )
--        {
--            printk(XENLOG_G_ERR "can't re-pin %"PRI_mfn"\n", mfn_x(old_smfn));
--            domain_crash(d);
--        }
--        sh_put_ref(d, old_smfn, 0);
-+        sh_put_ref(d, pagetable_get_mfn(old_entry), 0);
-+        old_entry = pagetable_null();
-     }
-+
-+    /*
-+     * 2- and 3-level shadow mode is used for HVM only. Therefore we never run
-+     * on such a shadow, so only call sites requesting an L4 shadow need to pay
-+     * attention to the returned value.
-+     */
-+    ASSERT(pagetable_is_null(old_entry) || root_type == SH_type_l4_64_shadow);
-+
-+    return old_entry;
-+}
-+
-+/*
-+ * Helper invoked when releasing of a top-level shadow's reference was
-+ * deferred in sh_set_toplevel_shadow() above.
-+ */
-+void shadow_put_top_level(struct domain *d, pagetable_t old_entry)
-+{
-+    ASSERT(!pagetable_is_null(old_entry));
-+    paging_lock(d);
-+    sh_put_ref(d, pagetable_get_mfn(old_entry), 0);
-+    paging_unlock(d);
- }
- 
- /**************************************************************************/
---- a/xen/arch/x86/mm/shadow/multi.c
-+++ b/xen/arch/x86/mm/shadow/multi.c
-@@ -3224,7 +3224,8 @@ static void cf_check sh_detach_old_table
-     }
- }
- 
--static void cf_check sh_update_cr3(struct vcpu *v, int do_locking, bool noflush)
-+static pagetable_t cf_check sh_update_cr3(struct vcpu *v, bool do_locking,
-+                                          bool noflush)
- /* Updates vcpu->arch.cr3 after the guest has changed CR3.
-  * Paravirtual guests should set v->arch.guest_table (and guest_table_user,
-  * if appropriate).
-@@ -3238,6 +3239,7 @@ static void cf_check sh_update_cr3(struc
- {
-     struct domain *d = v->domain;
-     mfn_t gmfn;
-+    pagetable_t old_entry = pagetable_null();
- #if GUEST_PAGING_LEVELS == 3
-     const guest_l3e_t *gl3e;
-     unsigned int i, guest_idx;
-@@ -3247,7 +3249,7 @@ static void cf_check sh_update_cr3(struc
-     if ( !is_hvm_domain(d) && !v->is_initialised )
-     {
-         ASSERT(v->arch.cr3 == 0);
--        return;
-+        return old_entry;
-     }
- 
-     if ( do_locking ) paging_lock(v->domain);
-@@ -3320,11 +3322,12 @@ static void cf_check sh_update_cr3(struc
- #if GUEST_PAGING_LEVELS == 4
-     if ( sh_remove_write_access(d, gmfn, 4, 0) != 0 )
-         guest_flush_tlb_mask(d, d->dirty_cpumask);
--    sh_set_toplevel_shadow(v, 0, gmfn, SH_type_l4_shadow, sh_make_shadow);
-+    old_entry = sh_set_toplevel_shadow(v, 0, gmfn, SH_type_l4_shadow,
-+                                       sh_make_shadow);
-     if ( unlikely(pagetable_is_null(v->arch.paging.shadow.shadow_table[0])) )
-     {
-         ASSERT(d->is_dying || d->is_shutting_down);
--        return;
-+        return old_entry;
-     }
-     if ( !shadow_mode_external(d) && !is_pv_32bit_domain(d) )
-     {
-@@ -3368,24 +3371,30 @@ static void cf_check sh_update_cr3(struc
-                 gl2gfn = guest_l3e_get_gfn(gl3e[i]);
-                 gl2mfn = get_gfn_query_unlocked(d, gfn_x(gl2gfn), &p2mt);
-                 if ( p2m_is_ram(p2mt) )
--                    sh_set_toplevel_shadow(v, i, gl2mfn, SH_type_l2_shadow,
--                                           sh_make_shadow);
-+                    old_entry = sh_set_toplevel_shadow(v, i, gl2mfn,
-+                                                       SH_type_l2_shadow,
-+                                                       sh_make_shadow);
-                 else
--                    sh_set_toplevel_shadow(v, i, INVALID_MFN, 0,
--                                           sh_make_shadow);
-+                    old_entry = sh_set_toplevel_shadow(v, i, INVALID_MFN, 0,
-+                                                       sh_make_shadow);
-             }
-             else
--                sh_set_toplevel_shadow(v, i, INVALID_MFN, 0, sh_make_shadow);
-+                old_entry = sh_set_toplevel_shadow(v, i, INVALID_MFN, 0,
-+                                                   sh_make_shadow);
-+
-+            ASSERT(pagetable_is_null(old_entry));
-         }
-     }
- #elif GUEST_PAGING_LEVELS == 2
-     if ( sh_remove_write_access(d, gmfn, 2, 0) != 0 )
-         guest_flush_tlb_mask(d, d->dirty_cpumask);
--    sh_set_toplevel_shadow(v, 0, gmfn, SH_type_l2_shadow, sh_make_shadow);
-+    old_entry = sh_set_toplevel_shadow(v, 0, gmfn, SH_type_l2_shadow,
-+                                       sh_make_shadow);
-+    ASSERT(pagetable_is_null(old_entry));
-     if ( unlikely(pagetable_is_null(v->arch.paging.shadow.shadow_table[0])) )
-     {
-         ASSERT(d->is_dying || d->is_shutting_down);
--        return;
-+        return old_entry;
-     }
- #else
- #error This should never happen
-@@ -3473,6 +3482,8 @@ static void cf_check sh_update_cr3(struc
- 
-     /* Release the lock, if we took it (otherwise it's the caller's problem) */
-     if ( do_locking ) paging_unlock(v->domain);
-+
-+    return old_entry;
- }
- 
- 
---- a/xen/arch/x86/mm/shadow/none.c
-+++ b/xen/arch/x86/mm/shadow/none.c
-@@ -52,9 +52,11 @@ static unsigned long cf_check _gva_to_gf
- }
- #endif
- 
--static void cf_check _update_cr3(struct vcpu *v, int do_locking, bool noflush)
-+static pagetable_t cf_check _update_cr3(struct vcpu *v, bool do_locking,
-+                                        bool noflush)
- {
-     ASSERT_UNREACHABLE();
-+    return pagetable_null();
- }
- 
- static void cf_check _update_paging_modes(struct vcpu *v)
---- a/xen/arch/x86/mm/shadow/private.h
-+++ b/xen/arch/x86/mm/shadow/private.h
-@@ -391,13 +391,13 @@ mfn_t shadow_alloc(struct domain *d,
- void  shadow_free(struct domain *d, mfn_t smfn);
- 
- /* Set up the top-level shadow and install it in slot 'slot' of shadow_table */
--void sh_set_toplevel_shadow(struct vcpu *v,
--                            unsigned int slot,
--                            mfn_t gmfn,
--                            unsigned int root_type,
--                            mfn_t (*make_shadow)(struct vcpu *v,
--                                                 mfn_t gmfn,
--                                                 uint32_t shadow_type));
-+pagetable_t sh_set_toplevel_shadow(struct vcpu *v,
-+                                   unsigned int slot,
-+                                   mfn_t gmfn,
-+                                   unsigned int root_type,
-+                                   mfn_t (*make_shadow)(struct vcpu *v,
-+                                                        mfn_t gmfn,
-+                                                        uint32_t shadow_type));
- 
- /* Update the shadows in response to a pagetable write from Xen */
- int sh_validate_guest_entry(struct vcpu *v, mfn_t gmfn, void *entry, u32 size);
---- a/xen/arch/x86/mm.c
-+++ b/xen/arch/x86/mm.c
-@@ -567,15 +567,12 @@ void write_ptbase(struct vcpu *v)
-  *
-  * Update ref counts to shadow tables appropriately.
-  */
--void update_cr3(struct vcpu *v)
-+pagetable_t update_cr3(struct vcpu *v)
- {
-     mfn_t cr3_mfn;
- 
-     if ( paging_mode_enabled(v->domain) )
--    {
--        paging_update_cr3(v, false);
--        return;
--    }
-+        return paging_update_cr3(v, false);
- 
-     if ( !(v->arch.flags & TF_kernel_mode) )
-         cr3_mfn = pagetable_get_mfn(v->arch.guest_table_user);
-@@ -583,6 +580,8 @@ void update_cr3(struct vcpu *v)
-         cr3_mfn = pagetable_get_mfn(v->arch.guest_table);
- 
-     make_cr3(v, cr3_mfn);
-+
-+    return pagetable_null();
- }
- 
- static inline void set_tlbflush_timestamp(struct page_info *page)
-@@ -3285,6 +3284,7 @@ int new_guest_cr3(mfn_t mfn)
-     struct domain *d = curr->domain;
-     int rc;
-     mfn_t old_base_mfn;
-+    pagetable_t old_shadow;
- 
-     if ( is_pv_32bit_domain(d) )
-     {
-@@ -3352,9 +3352,22 @@ int new_guest_cr3(mfn_t mfn)
-     if ( !VM_ASSIST(d, m2p_strict) )
-         fill_ro_mpt(mfn);
-     curr->arch.guest_table = pagetable_from_mfn(mfn);
--    update_cr3(curr);
-+    old_shadow = update_cr3(curr);
-+
-+    /*
-+     * In shadow mode update_cr3() can fail, in which case here we're still
-+     * running on the prior top-level shadow (which we're about to release).
-+     * Switch to the idle page tables in such an event; the guest will have
-+     * been crashed already.
-+     */
-+    if ( likely(!mfn_eq(pagetable_get_mfn(old_shadow),
-+                        maddr_to_mfn(curr->arch.cr3 & ~X86_CR3_NOFLUSH))) )
-+        write_ptbase(curr);
-+    else
-+        write_ptbase(idle_vcpu[curr->processor]);
- 
--    write_ptbase(curr);
-+    if ( !pagetable_is_null(old_shadow) )
-+        shadow_put_top_level(d, old_shadow);
- 
-     if ( likely(mfn_x(old_base_mfn) != 0) )
-     {
---- a/xen/arch/x86/pv/domain.c
-+++ b/xen/arch/x86/pv/domain.c
-@@ -424,10 +424,13 @@ bool __init xpti_pcid_enabled(void)
- 
- static void _toggle_guest_pt(struct vcpu *v)
- {
-+    bool guest_update;
-+    pagetable_t old_shadow;
-     unsigned long cr3;
- 
-     v->arch.flags ^= TF_kernel_mode;
--    update_cr3(v);
-+    guest_update = v->arch.flags & TF_kernel_mode;
-+    old_shadow = update_cr3(v);
- 
-     /*
-      * Don't flush user global mappings from the TLB. Don't tick TLB clock.
-@@ -436,13 +439,31 @@ static void _toggle_guest_pt(struct vcpu
-      * TLB flush (for just the incoming PCID), as the top level page table may
-      * have changed behind our backs. To be on the safe side, suppress the
-      * no-flush unconditionally in this case.
-+     *
-+     * Furthermore in shadow mode update_cr3() can fail, in which case here
-+     * we're still running on the prior top-level shadow (which we're about
-+     * to release). Switch to the idle page tables in such an event; the
-+     * guest will have been crashed already.
-      */
-     cr3 = v->arch.cr3;
-     if ( shadow_mode_enabled(v->domain) )
-+    {
-         cr3 &= ~X86_CR3_NOFLUSH;
-+
-+        if ( unlikely(mfn_eq(pagetable_get_mfn(old_shadow),
-+                             maddr_to_mfn(cr3))) )
-+        {
-+            cr3 = idle_vcpu[v->processor]->arch.cr3;
-+            /* Also suppress runstate/time area updates below. */
-+            guest_update = false;
-+        }
-+    }
-     write_cr3(cr3);
- 
--    if ( !(v->arch.flags & TF_kernel_mode) )
-+    if ( !pagetable_is_null(old_shadow) )
-+        shadow_put_top_level(v->domain, old_shadow);
-+
-+    if ( !guest_update )
-         return;
- 
-     if ( v->arch.pv.need_update_runstate_area && update_runstate_area(v) )

xsa439-0001-x86-AMD-extend-Zenbleed-check-to-models-good-ucode-i.patch

@@ -1,49 +0,0 @@
-From d2d2dcae879c6cc05227c9620f0a772f35fe6886 Mon Sep 17 00:00:00 2001
-Message-ID: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Jan Beulich <jbeulich@suse.com>
-Date: Wed, 23 Aug 2023 09:26:36 +0200
-Subject: [XEN PATCH 01/10] x86/AMD: extend Zenbleed check to models "good"
- ucode isn't known for
-
-Reportedly the AMD Custom APU 0405 found on SteamDeck, models 0x90 and
-0x91, (quoting the respective Linux commit) is similarly affected. Put
-another instance of our Zen1 vs Zen2 distinction checks in
-amd_check_zenbleed(), forcing use of the chickenbit irrespective of
-ucode version (building upon real hardware never surfacing a version of
-0xffffffff).
-
-Signed-off-by: Jan Beulich <jbeulich@suse.com>
-Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
-(cherry picked from commit 145a69c0944ac70cfcf9d247c85dee9e99d9d302)
----
- xen/arch/x86/cpu/amd.c | 13 ++++++++++---
- 1 file changed, 10 insertions(+), 3 deletions(-)
-
-diff --git a/xen/arch/x86/cpu/amd.c b/xen/arch/x86/cpu/amd.c
-index 3ea214fc2e..1bb3044be1 100644
---- a/xen/arch/x86/cpu/amd.c
-+++ b/xen/arch/x86/cpu/amd.c
-@@ -909,10 +909,17 @@ void amd_check_zenbleed(void)
- 	case 0xa0 ... 0xaf: good_rev = 0x08a00008; break;
- 	default:
- 		/*
--		 * With the Fam17h check above, parts getting here are Zen1.
--		 * They're not affected.
-+		 * With the Fam17h check above, most parts getting here are
-+		 * Zen1.  They're not affected.  Assume Zen2 ones making it
-+		 * here are affected regardless of microcode version.
-+		 *
-+		 * Zen1 vs Zen2 isn't a simple model number comparison, so use
-+		 * STIBP as a heuristic to distinguish.
- 		 */
--		return;
-+		if (!boot_cpu_has(X86_FEATURE_AMD_STIBP))
-+			return;
-+		good_rev = ~0U;
-+		break;
- 	}
- 
- 	rdmsrl(MSR_AMD64_DE_CFG, val);
--- 
-2.41.0
-

xsa439-0002-x86-spec-ctrl-Fix-confusion-between-SPEC_CTRL_EXIT_T.patch

@@ -1,77 +0,0 @@
-From dc28aba565f226f9bec24cfde993e78478acfb4e Mon Sep 17 00:00:00 2001
-Message-ID: <dc28aba565f226f9bec24cfde993e78478acfb4e.1695733540.git.m.a.young@durham.ac.uk>
-In-Reply-To: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-References: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Tue, 12 Sep 2023 15:06:49 +0100
-Subject: [XEN PATCH 02/10] x86/spec-ctrl: Fix confusion between
- SPEC_CTRL_EXIT_TO_XEN{,_IST}
-
-c/s 3fffaf9c13e9 ("x86/entry: Avoid using alternatives in NMI/#MC paths")
-dropped the only user, leaving behind the (incorrect) implication that Xen had
-split exit paths.
-
-Delete the unused SPEC_CTRL_EXIT_TO_XEN and rename SPEC_CTRL_EXIT_TO_XEN_IST
-to SPEC_CTRL_EXIT_TO_XEN for consistency.
-
-No functional change.
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit 1c18d73774533a55ba9d1cbee8bdace03efdb5e7)
----
- xen/arch/x86/include/asm/spec_ctrl_asm.h | 10 ++--------
- xen/arch/x86/x86_64/entry.S              |  2 +-
- 2 files changed, 3 insertions(+), 9 deletions(-)
-
-diff --git a/xen/arch/x86/include/asm/spec_ctrl_asm.h b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-index f23bb105c5..e8fd01243c 100644
---- a/xen/arch/x86/include/asm/spec_ctrl_asm.h
-+++ b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-@@ -79,7 +79,6 @@
-  *  - SPEC_CTRL_ENTRY_FROM_PV
-  *  - SPEC_CTRL_ENTRY_FROM_INTR
-  *  - SPEC_CTRL_ENTRY_FROM_INTR_IST
-- *  - SPEC_CTRL_EXIT_TO_XEN_IST
-  *  - SPEC_CTRL_EXIT_TO_XEN
-  *  - SPEC_CTRL_EXIT_TO_PV
-  *
-@@ -268,11 +267,6 @@
-     ALTERNATIVE "", __stringify(DO_SPEC_CTRL_ENTRY maybexen=1),         \
-         X86_FEATURE_SC_MSR_PV
- 
--/* Use when exiting to Xen context. */
--#define SPEC_CTRL_EXIT_TO_XEN                                           \
--    ALTERNATIVE "",                                                     \
--        DO_SPEC_CTRL_EXIT_TO_XEN, X86_FEATURE_SC_MSR_PV
--
- /* Use when exiting to PV guest context. */
- #define SPEC_CTRL_EXIT_TO_PV                                            \
-     ALTERNATIVE "",                                                     \
-@@ -339,8 +333,8 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
-     UNLIKELY_END(\@_serialise)
- .endm
- 
--/* Use when exiting to Xen in IST context. */
--.macro SPEC_CTRL_EXIT_TO_XEN_IST
-+/* Use when exiting to Xen context. */
-+.macro SPEC_CTRL_EXIT_TO_XEN
- /*
-  * Requires %rbx=stack_end
-  * Clobbers %rax, %rcx, %rdx
-diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
-index 7675a59ff0..b45a09823a 100644
---- a/xen/arch/x86/x86_64/entry.S
-+++ b/xen/arch/x86/x86_64/entry.S
-@@ -673,7 +673,7 @@ UNLIKELY_START(ne, exit_cr3)
- UNLIKELY_END(exit_cr3)
- 
-         /* WARNING! `ret`, `call *`, `jmp *` not safe beyond this point. */
--        SPEC_CTRL_EXIT_TO_XEN_IST /* Req: %rbx=end, Clob: acd */
-+        SPEC_CTRL_EXIT_TO_XEN     /* Req: %rbx=end, Clob: acd */
- 
-         RESTORE_ALL adj=8
-         iretq
--- 
-2.41.0
-

xsa439-0003-x86-spec-ctrl-Fold-DO_SPEC_CTRL_EXIT_TO_XEN-into-it-.patch

@@ -1,88 +0,0 @@
-From 84690fb82c4f4aecb72a6789d8994efa74841e09 Mon Sep 17 00:00:00 2001
-Message-ID: <84690fb82c4f4aecb72a6789d8994efa74841e09.1695733540.git.m.a.young@durham.ac.uk>
-In-Reply-To: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-References: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Tue, 12 Sep 2023 17:03:16 +0100
-Subject: [XEN PATCH 03/10] x86/spec-ctrl: Fold DO_SPEC_CTRL_EXIT_TO_XEN into
- it's single user
-
-With the SPEC_CTRL_EXIT_TO_XEN{,_IST} confusion fixed, it's now obvious that
-there's only a single EXIT_TO_XEN path.  Fold DO_SPEC_CTRL_EXIT_TO_XEN into
-SPEC_CTRL_EXIT_TO_XEN to simplify further fixes.
-
-When merging labels, switch the name to .L\@_skip_sc_msr as "skip" on its own
-is going to be too generic shortly.
-
-No functional change.
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit 694bb0f280fd08a4377e36e32b84b5062def4de2)
----
- xen/arch/x86/include/asm/spec_ctrl_asm.h | 40 ++++++++++--------------
- 1 file changed, 16 insertions(+), 24 deletions(-)
-
-diff --git a/xen/arch/x86/include/asm/spec_ctrl_asm.h b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-index e8fd01243c..d5f65d80ea 100644
---- a/xen/arch/x86/include/asm/spec_ctrl_asm.h
-+++ b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-@@ -211,27 +211,6 @@
-     wrmsr
- .endm
- 
--.macro DO_SPEC_CTRL_EXIT_TO_XEN
--/*
-- * Requires %rbx=stack_end
-- * Clobbers %rax, %rcx, %rdx
-- *
-- * When returning to Xen context, look to see whether SPEC_CTRL shadowing is
-- * in effect, and reload the shadow value.  This covers race conditions which
-- * exist with an NMI/MCE/etc hitting late in the return-to-guest path.
-- */
--    xor %edx, %edx
--
--    testb $SCF_use_shadow, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%rbx)
--    jz .L\@_skip
--
--    mov STACK_CPUINFO_FIELD(shadow_spec_ctrl)(%rbx), %eax
--    mov $MSR_SPEC_CTRL, %ecx
--    wrmsr
--
--.L\@_skip:
--.endm
--
- .macro DO_SPEC_CTRL_EXIT_TO_GUEST
- /*
-  * Requires %eax=spec_ctrl, %rsp=regs/cpuinfo
-@@ -340,11 +319,24 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
-  * Clobbers %rax, %rcx, %rdx
-  */
-     testb $SCF_ist_sc_msr, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%rbx)
--    jz .L\@_skip
-+    jz .L\@_skip_sc_msr
- 
--    DO_SPEC_CTRL_EXIT_TO_XEN
-+    /*
-+     * When returning to Xen context, look to see whether SPEC_CTRL shadowing
-+     * is in effect, and reload the shadow value.  This covers race conditions
-+     * which exist with an NMI/MCE/etc hitting late in the return-to-guest
-+     * path.
-+     */
-+    xor %edx, %edx
- 
--.L\@_skip:
-+    testb $SCF_use_shadow, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%rbx)
-+    jz .L\@_skip_sc_msr
-+
-+    mov STACK_CPUINFO_FIELD(shadow_spec_ctrl)(%rbx), %eax
-+    mov $MSR_SPEC_CTRL, %ecx
-+    wrmsr
-+
-+.L\@_skip_sc_msr:
- .endm
- 
- #endif /* __ASSEMBLY__ */
--- 
-2.41.0
-

xsa439-0004-x86-spec-ctrl-Turn-the-remaining-SPEC_CTRL_-ENTRY-EX.patch

@@ -1,86 +0,0 @@
-From 3952c73bdbd05f0e666986fce633a591237b3c88 Mon Sep 17 00:00:00 2001
-Message-ID: <3952c73bdbd05f0e666986fce633a591237b3c88.1695733540.git.m.a.young@durham.ac.uk>
-In-Reply-To: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-References: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Fri, 1 Sep 2023 11:38:44 +0100
-Subject: [XEN PATCH 04/10] x86/spec-ctrl: Turn the remaining
- SPEC_CTRL_{ENTRY,EXIT}_* into asm macros
-
-These have grown more complex over time, with some already having been
-converted.
-
-Provide full Requires/Clobbers comments, otherwise missing at this level of
-indirection.
-
-No functional change.
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit 7125429aafb9e3c9c88fc93001fc2300e0ac2cc8)
----
- xen/arch/x86/include/asm/spec_ctrl_asm.h | 37 ++++++++++++++++++------
- 1 file changed, 28 insertions(+), 9 deletions(-)
-
-diff --git a/xen/arch/x86/include/asm/spec_ctrl_asm.h b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-index d5f65d80ea..c6d5f2ad01 100644
---- a/xen/arch/x86/include/asm/spec_ctrl_asm.h
-+++ b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-@@ -231,26 +231,45 @@
- .endm
- 
- /* Use after an entry from PV context (syscall/sysenter/int80/int82/etc). */
--#define SPEC_CTRL_ENTRY_FROM_PV                                         \
-+.macro SPEC_CTRL_ENTRY_FROM_PV
-+/*
-+ * Requires %rsp=regs/cpuinfo, %rdx=0
-+ * Clobbers %rax, %rcx, %rdx
-+ */
-     ALTERNATIVE "", __stringify(DO_SPEC_CTRL_COND_IBPB maybexen=0),     \
--        X86_FEATURE_IBPB_ENTRY_PV;                                      \
--    ALTERNATIVE "", DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_PV;            \
-+        X86_FEATURE_IBPB_ENTRY_PV
-+
-+    ALTERNATIVE "", DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_PV
-+
-     ALTERNATIVE "", __stringify(DO_SPEC_CTRL_ENTRY maybexen=0),         \
-         X86_FEATURE_SC_MSR_PV
-+.endm
- 
- /* Use in interrupt/exception context.  May interrupt Xen or PV context. */
--#define SPEC_CTRL_ENTRY_FROM_INTR                                       \
-+.macro SPEC_CTRL_ENTRY_FROM_INTR
-+/*
-+ * Requires %rsp=regs, %r14=stack_end, %rdx=0
-+ * Clobbers %rax, %rcx, %rdx
-+ */
-     ALTERNATIVE "", __stringify(DO_SPEC_CTRL_COND_IBPB maybexen=1),     \
--        X86_FEATURE_IBPB_ENTRY_PV;                                      \
--    ALTERNATIVE "", DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_PV;            \
-+        X86_FEATURE_IBPB_ENTRY_PV
-+
-+    ALTERNATIVE "", DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_PV
-+
-     ALTERNATIVE "", __stringify(DO_SPEC_CTRL_ENTRY maybexen=1),         \
-         X86_FEATURE_SC_MSR_PV
-+.endm
- 
- /* Use when exiting to PV guest context. */
--#define SPEC_CTRL_EXIT_TO_PV                                            \
--    ALTERNATIVE "",                                                     \
--        DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR_PV;              \
-+.macro SPEC_CTRL_EXIT_TO_PV
-+/*
-+ * Requires %rax=spec_ctrl, %rsp=regs/info
-+ * Clobbers %rcx, %rdx
-+ */
-+    ALTERNATIVE "", DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR_PV
-+
-     DO_SPEC_CTRL_COND_VERW
-+.endm
- 
- /*
-  * Use in IST interrupt/exception context.  May interrupt Xen or PV context.
--- 
-2.41.0
-

xsa439-0005-x86-spec-ctrl-Improve-all-SPEC_CTRL_-ENTER-EXIT-_-co.patch

@@ -1,109 +0,0 @@
-From ba023e93d0b1e60b80251bf080bab694efb9f8e3 Mon Sep 17 00:00:00 2001
-Message-ID: <ba023e93d0b1e60b80251bf080bab694efb9f8e3.1695733540.git.m.a.young@durham.ac.uk>
-In-Reply-To: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-References: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Wed, 30 Aug 2023 20:11:50 +0100
-Subject: [XEN PATCH 05/10] x86/spec-ctrl: Improve all SPEC_CTRL_{ENTER,EXIT}_*
- comments
-
-... to better explain how they're used.
-
-Doing so highlights that SPEC_CTRL_EXIT_TO_XEN is missing a VERW flush for the
-corner case when e.g. an NMI hits late in an exit-to-guest path.
-
-Leave a TODO, which will be addressed in subsequent patches which arrange for
-VERW flushing to be safe within SPEC_CTRL_EXIT_TO_XEN.
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit 45f00557350dc7d0756551069803fc49c29184ca)
----
- xen/arch/x86/include/asm/spec_ctrl_asm.h | 36 ++++++++++++++++++++----
- 1 file changed, 31 insertions(+), 5 deletions(-)
-
-diff --git a/xen/arch/x86/include/asm/spec_ctrl_asm.h b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-index c6d5f2ad01..97c4db31cd 100644
---- a/xen/arch/x86/include/asm/spec_ctrl_asm.h
-+++ b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-@@ -230,7 +230,10 @@
-     wrmsr
- .endm
- 
--/* Use after an entry from PV context (syscall/sysenter/int80/int82/etc). */
-+/*
-+ * Used after an entry from PV context: SYSCALL, SYSENTER, INT,
-+ * etc.  There is always a guest speculation state in context.
-+ */
- .macro SPEC_CTRL_ENTRY_FROM_PV
- /*
-  * Requires %rsp=regs/cpuinfo, %rdx=0
-@@ -245,7 +248,11 @@
-         X86_FEATURE_SC_MSR_PV
- .endm
- 
--/* Use in interrupt/exception context.  May interrupt Xen or PV context. */
-+/*
-+ * Used after an exception or maskable interrupt, hitting Xen or PV context.
-+ * There will either be a guest speculation context, or (barring fatal
-+ * exceptions) a well-formed Xen speculation context.
-+ */
- .macro SPEC_CTRL_ENTRY_FROM_INTR
- /*
-  * Requires %rsp=regs, %r14=stack_end, %rdx=0
-@@ -260,7 +267,10 @@
-         X86_FEATURE_SC_MSR_PV
- .endm
- 
--/* Use when exiting to PV guest context. */
-+/*
-+ * Used when exiting from any entry context, back to PV context.  This
-+ * includes from an IST entry which moved onto the primary stack.
-+ */
- .macro SPEC_CTRL_EXIT_TO_PV
- /*
-  * Requires %rax=spec_ctrl, %rsp=regs/info
-@@ -272,7 +282,13 @@
- .endm
- 
- /*
-- * Use in IST interrupt/exception context.  May interrupt Xen or PV context.
-+ * Used after an IST entry hitting Xen or PV context.  Special care is needed,
-+ * because when hitting Xen context, there may not be a well-formed
-+ * speculation context.  (i.e. it can hit in the middle of
-+ * SPEC_CTRL_{ENTRY,EXIT}_* regions.)
-+ *
-+ * An IST entry which hits PV context moves onto the primary stack and leaves
-+ * via SPEC_CTRL_EXIT_TO_PV, *not* SPEC_CTRL_EXIT_TO_XEN.
-  */
- .macro SPEC_CTRL_ENTRY_FROM_INTR_IST
- /*
-@@ -331,7 +347,14 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
-     UNLIKELY_END(\@_serialise)
- .endm
- 
--/* Use when exiting to Xen context. */
-+/*
-+ * Use when exiting from any entry context, back to Xen context.  This
-+ * includes returning to other SPEC_CTRL_{ENTRY,EXIT}_* regions with an
-+ * incomplete speculation context.
-+ *
-+ * Because we might have interrupted Xen beyond SPEC_CTRL_EXIT_TO_$GUEST, we
-+ * need to treat this as if it were an EXIT_TO_$GUEST case too.
-+ */
- .macro SPEC_CTRL_EXIT_TO_XEN
- /*
-  * Requires %rbx=stack_end
-@@ -356,6 +379,9 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
-     wrmsr
- 
- .L\@_skip_sc_msr:
-+
-+    /* TODO VERW */
-+
- .endm
- 
- #endif /* __ASSEMBLY__ */
--- 
-2.41.0
-

xsa439-0006-x86-entry-Adjust-restore_all_xen-to-hold-stack_end-i.patch

@@ -1,77 +0,0 @@
-From 5f7efd47c8273fde972637d0360851802f76eca9 Mon Sep 17 00:00:00 2001
-Message-ID: <5f7efd47c8273fde972637d0360851802f76eca9.1695733540.git.m.a.young@durham.ac.uk>
-In-Reply-To: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-References: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Wed, 13 Sep 2023 13:48:16 +0100
-Subject: [XEN PATCH 06/10] x86/entry: Adjust restore_all_xen to hold stack_end
- in %r14
-
-All other SPEC_CTRL_{ENTRY,EXIT}_* helpers hold stack_end in %r14.  Adjust it
-for consistency.
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit 7aa28849a1155d856e214e9a80a7e65fffdc3e58)
----
- xen/arch/x86/include/asm/spec_ctrl_asm.h | 8 ++++----
- xen/arch/x86/x86_64/entry.S              | 8 ++++----
- 2 files changed, 8 insertions(+), 8 deletions(-)
-
-diff --git a/xen/arch/x86/include/asm/spec_ctrl_asm.h b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-index 97c4db31cd..66c706496f 100644
---- a/xen/arch/x86/include/asm/spec_ctrl_asm.h
-+++ b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-@@ -357,10 +357,10 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
-  */
- .macro SPEC_CTRL_EXIT_TO_XEN
- /*
-- * Requires %rbx=stack_end
-+ * Requires %r14=stack_end
-  * Clobbers %rax, %rcx, %rdx
-  */
--    testb $SCF_ist_sc_msr, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%rbx)
-+    testb $SCF_ist_sc_msr, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%r14)
-     jz .L\@_skip_sc_msr
- 
-     /*
-@@ -371,10 +371,10 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
-      */
-     xor %edx, %edx
- 
--    testb $SCF_use_shadow, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%rbx)
-+    testb $SCF_use_shadow, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%r14)
-     jz .L\@_skip_sc_msr
- 
--    mov STACK_CPUINFO_FIELD(shadow_spec_ctrl)(%rbx), %eax
-+    mov STACK_CPUINFO_FIELD(shadow_spec_ctrl)(%r14), %eax
-     mov $MSR_SPEC_CTRL, %ecx
-     wrmsr
- 
-diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
-index b45a09823a..92279a225d 100644
---- a/xen/arch/x86/x86_64/entry.S
-+++ b/xen/arch/x86/x86_64/entry.S
-@@ -665,15 +665,15 @@ restore_all_xen:
-          * Check whether we need to switch to the per-CPU page tables, in
-          * case we return to late PV exit code (from an NMI or #MC).
-          */
--        GET_STACK_END(bx)
--        cmpb  $0, STACK_CPUINFO_FIELD(use_pv_cr3)(%rbx)
-+        GET_STACK_END(14)
-+        cmpb  $0, STACK_CPUINFO_FIELD(use_pv_cr3)(%r14)
- UNLIKELY_START(ne, exit_cr3)
--        mov   STACK_CPUINFO_FIELD(pv_cr3)(%rbx), %rax
-+        mov   STACK_CPUINFO_FIELD(pv_cr3)(%r14), %rax
-         mov   %rax, %cr3
- UNLIKELY_END(exit_cr3)
- 
-         /* WARNING! `ret`, `call *`, `jmp *` not safe beyond this point. */
--        SPEC_CTRL_EXIT_TO_XEN     /* Req: %rbx=end, Clob: acd */
-+        SPEC_CTRL_EXIT_TO_XEN     /* Req: %r14=end, Clob: acd */
- 
-         RESTORE_ALL adj=8
-         iretq
--- 
-2.41.0
-

xsa439-0007-x86-entry-Track-the-IST-ness-of-an-entry-for-the-exi.patch

@@ -1,112 +0,0 @@
-From e4a71bc0da0baf7464bb0d8e33053f330e5ea366 Mon Sep 17 00:00:00 2001
-Message-ID: <e4a71bc0da0baf7464bb0d8e33053f330e5ea366.1695733540.git.m.a.young@durham.ac.uk>
-In-Reply-To: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-References: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Wed, 13 Sep 2023 12:20:12 +0100
-Subject: [XEN PATCH 07/10] x86/entry: Track the IST-ness of an entry for the
- exit paths
-
-Use %r12 to hold an ist_exit boolean.  This register is zero elsewhere in the
-entry/exit asm, so it only needs setting in the IST path.
-
-As this is subtle and fragile, add check_ist_exit() to be used in debugging
-builds to cross-check that the ist_exit boolean matches the entry vector.
-
-Write check_ist_exit() it in C, because it's debug only and the logic more
-complicated than I care to maintain in asm.
-
-For now, we only need to use this signal in the exit-to-Xen path, but some
-exit-to-guest paths happen in IST context too.  Check the correctness in all
-exit paths to avoid the logic bit-rotting.
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit 21bdc25b05a0f8ab6bc73520a9ca01327360732c)
-
-x86/entry: Partially revert IST-exit checks
-
-The patch adding check_ist_exit() didn't account for the fact that
-reset_stack_and_jump() is not an ABI-preserving boundary.  The IST-ness in
-%r12 doesn't survive into the next context, and is a stale value C.
-
-This shows up in Gitlab CI for the Clang build:
-
-  https://gitlab.com/xen-project/people/andyhhp/xen/-/jobs/5112783827
-
-and in OSSTest for GCC 8:
-
-  http://logs.test-lab.xenproject.org/osstest/logs/183045/test-amd64-amd64-xl-qemuu-debianhvm-amd64/serial-pinot0.log
-
-There's no straightforward way to reconstruct the IST-exit-ness on the
-exit-to-guest path after a context switch.  For now, we only need IST-exit on
-the return-to-Xen path.
-
-Fixes: 21bdc25b05a0 ("x86/entry: Track the IST-ness of an entry for the exit paths")
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit 9b57c800b79b96769ea3dcd6468578fa664d19f9)
----
- xen/arch/x86/traps.c        | 13 +++++++++++++
- xen/arch/x86/x86_64/entry.S | 13 ++++++++++++-
- 2 files changed, 25 insertions(+), 1 deletion(-)
-
-diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
-index d12004b1c6..e65cc60041 100644
---- a/xen/arch/x86/traps.c
-+++ b/xen/arch/x86/traps.c
-@@ -2315,6 +2315,19 @@ void asm_domain_crash_synchronous(unsigned long addr)
-         do_softirq();
- }
- 
-+#ifdef CONFIG_DEBUG
-+void check_ist_exit(const struct cpu_user_regs *regs, bool ist_exit)
-+{
-+    const unsigned int ist_mask =
-+        (1U << X86_EXC_NMI) | (1U << X86_EXC_DB) |
-+        (1U << X86_EXC_DF)  | (1U << X86_EXC_MC);
-+    uint8_t ev = regs->entry_vector;
-+    bool is_ist = (ev < TRAP_nr) && ((1U << ev) & ist_mask);
-+
-+    ASSERT(is_ist == ist_exit);
-+}
-+#endif
-+
- /*
-  * Local variables:
-  * mode: C
-diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
-index 92279a225d..4cebc4fbe3 100644
---- a/xen/arch/x86/x86_64/entry.S
-+++ b/xen/arch/x86/x86_64/entry.S
-@@ -659,8 +659,15 @@ ENTRY(early_page_fault)
-         .section .text.entry, "ax", @progbits
- 
-         ALIGN
--/* No special register assumptions. */
-+/* %r12=ist_exit */
- restore_all_xen:
-+
-+#ifdef CONFIG_DEBUG
-+        mov   %rsp, %rdi
-+        mov   %r12, %rsi
-+        call  check_ist_exit
-+#endif
-+
-         /*
-          * Check whether we need to switch to the per-CPU page tables, in
-          * case we return to late PV exit code (from an NMI or #MC).
-@@ -1091,6 +1098,10 @@ handle_ist_exception:
- .L_ist_dispatch_done:
-         mov   %r15, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
-         mov   %bl, STACK_CPUINFO_FIELD(use_pv_cr3)(%r14)
-+
-+        /* This is an IST exit */
-+        mov   $1, %r12d
-+
-         cmpb  $TRAP_nmi,UREGS_entry_vector(%rsp)
-         jne   ret_from_intr
- 
--- 
-2.41.0
-

xsa439-0008-x86-spec-ctrl-Issue-VERW-during-IST-exit-to-Xen.patch

@@ -1,92 +0,0 @@
-From 2e2c3efcfc9f183674a8de6ed954ffbe7188b70d Mon Sep 17 00:00:00 2001
-Message-ID: <2e2c3efcfc9f183674a8de6ed954ffbe7188b70d.1695733540.git.m.a.young@durham.ac.uk>
-In-Reply-To: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-References: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Wed, 13 Sep 2023 13:53:33 +0100
-Subject: [XEN PATCH 08/10] x86/spec-ctrl: Issue VERW during IST exit to Xen
-
-There is a corner case where e.g. an NMI hitting an exit-to-guest path after
-SPEC_CTRL_EXIT_TO_* would have run the entire NMI handler *after* the VERW
-flush to scrub potentially sensitive data from uarch buffers.
-
-In order to compensate, issue VERW when exiting to Xen from an IST entry.
-
-SPEC_CTRL_EXIT_TO_XEN already has two reads of spec_ctrl_flags off the stack,
-and we're about to add a third.  Load the field into %ebx, and list the
-register as clobbered.
-
-%r12 has been arranged to be the ist_exit signal, so add this as an input
-dependency and use it to identify when to issue a VERW.
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit 3ee6066bcd737756b0990d417d94eddc0b0d2585)
----
- xen/arch/x86/include/asm/spec_ctrl_asm.h | 20 +++++++++++++++-----
- xen/arch/x86/x86_64/entry.S              |  2 +-
- 2 files changed, 16 insertions(+), 6 deletions(-)
-
-diff --git a/xen/arch/x86/include/asm/spec_ctrl_asm.h b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-index 66c706496f..28a75796e6 100644
---- a/xen/arch/x86/include/asm/spec_ctrl_asm.h
-+++ b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-@@ -357,10 +357,12 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
-  */
- .macro SPEC_CTRL_EXIT_TO_XEN
- /*
-- * Requires %r14=stack_end
-- * Clobbers %rax, %rcx, %rdx
-+ * Requires %r12=ist_exit, %r14=stack_end
-+ * Clobbers %rax, %rbx, %rcx, %rdx
-  */
--    testb $SCF_ist_sc_msr, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%r14)
-+    movzbl STACK_CPUINFO_FIELD(spec_ctrl_flags)(%r14), %ebx
-+
-+    testb $SCF_ist_sc_msr, %bl
-     jz .L\@_skip_sc_msr
- 
-     /*
-@@ -371,7 +373,7 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
-      */
-     xor %edx, %edx
- 
--    testb $SCF_use_shadow, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%r14)
-+    testb $SCF_use_shadow, %bl
-     jz .L\@_skip_sc_msr
- 
-     mov STACK_CPUINFO_FIELD(shadow_spec_ctrl)(%r14), %eax
-@@ -380,8 +382,16 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
- 
- .L\@_skip_sc_msr:
- 
--    /* TODO VERW */
-+    test %r12, %r12
-+    jz .L\@_skip_ist_exit
-+
-+    /* Logically DO_SPEC_CTRL_COND_VERW but without the %rsp=cpuinfo dependency */
-+    testb $SCF_verw, %bl
-+    jz .L\@_skip_verw
-+    verw STACK_CPUINFO_FIELD(verw_sel)(%r14)
-+.L\@_skip_verw:
- 
-+.L\@_skip_ist_exit:
- .endm
- 
- #endif /* __ASSEMBLY__ */
-diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
-index 4cebc4fbe3..c12e011b4d 100644
---- a/xen/arch/x86/x86_64/entry.S
-+++ b/xen/arch/x86/x86_64/entry.S
-@@ -680,7 +680,7 @@ UNLIKELY_START(ne, exit_cr3)
- UNLIKELY_END(exit_cr3)
- 
-         /* WARNING! `ret`, `call *`, `jmp *` not safe beyond this point. */
--        SPEC_CTRL_EXIT_TO_XEN     /* Req: %r14=end, Clob: acd */
-+        SPEC_CTRL_EXIT_TO_XEN     /* Req: %r12=ist_exit %r14=end, Clob: abcd */
- 
-         RESTORE_ALL adj=8
-         iretq
--- 
-2.41.0
-

xsa439-0009-x86-amd-Introduce-is_zen-1-2-_uarch-predicates.patch

@@ -1,94 +0,0 @@
-From 19ee1e1faa32b79274b3484cb1170a5970f1e602 Mon Sep 17 00:00:00 2001
-Message-ID: <19ee1e1faa32b79274b3484cb1170a5970f1e602.1695733540.git.m.a.young@durham.ac.uk>
-In-Reply-To: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-References: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Fri, 15 Sep 2023 12:13:51 +0100
-Subject: [XEN PATCH 09/10] x86/amd: Introduce is_zen{1,2}_uarch() predicates
-
-We already have 3 cases using STIBP as a Zen1/2 heuristic, and are about to
-introduce a 4th.  Wrap the heuristic into a pair of predicates rather than
-opencoding it, and the explanation of the heuristic, at each usage site.
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit de1d265001397f308c5c3c5d3ffc30e7ef8c0705)
----
- xen/arch/x86/cpu/amd.c         | 18 ++++--------------
- xen/arch/x86/include/asm/amd.h | 11 +++++++++++
- 2 files changed, 15 insertions(+), 14 deletions(-)
-
-diff --git a/xen/arch/x86/cpu/amd.c b/xen/arch/x86/cpu/amd.c
-index 1bb3044be1..e94ba5a0e0 100644
---- a/xen/arch/x86/cpu/amd.c
-+++ b/xen/arch/x86/cpu/amd.c
-@@ -855,15 +855,13 @@ void amd_set_legacy_ssbd(bool enable)
-  * non-branch instructions to be ignored.  It is to be set unilaterally in
-  * newer microcode.
-  *
-- * This chickenbit is something unrelated on Zen1, and Zen1 vs Zen2 isn't a
-- * simple model number comparison, so use STIBP as a heuristic to separate the
-- * two uarches in Fam17h(AMD)/18h(Hygon).
-+ * This chickenbit is something unrelated on Zen1.
-  */
- void amd_init_spectral_chicken(void)
- {
- 	uint64_t val, chickenbit = 1 << 1;
- 
--	if (cpu_has_hypervisor || !boot_cpu_has(X86_FEATURE_AMD_STIBP))
-+	if (cpu_has_hypervisor || !is_zen2_uarch())
- 		return;
- 
- 	if (rdmsr_safe(MSR_AMD64_DE_CFG2, val) == 0 && !(val & chickenbit))
-@@ -912,11 +910,8 @@ void amd_check_zenbleed(void)
- 		 * With the Fam17h check above, most parts getting here are
- 		 * Zen1.  They're not affected.  Assume Zen2 ones making it
- 		 * here are affected regardless of microcode version.
--		 *
--		 * Zen1 vs Zen2 isn't a simple model number comparison, so use
--		 * STIBP as a heuristic to distinguish.
- 		 */
--		if (!boot_cpu_has(X86_FEATURE_AMD_STIBP))
-+		if (is_zen1_uarch())
- 			return;
- 		good_rev = ~0U;
- 		break;
-@@ -1277,12 +1272,7 @@ static int __init cf_check zen2_c6_errata_check(void)
- 	 */
- 	s_time_t delta;
- 
--	/*
--	 * Zen1 vs Zen2 isn't a simple model number comparison, so use STIBP as
--	 * a heuristic to separate the two uarches in Fam17h.
--	 */
--	if (cpu_has_hypervisor || boot_cpu_data.x86 != 0x17 ||
--	    !boot_cpu_has(X86_FEATURE_AMD_STIBP))
-+	if (cpu_has_hypervisor || boot_cpu_data.x86 != 0x17 || !is_zen2_uarch())
- 		return 0;
- 
- 	/*
-diff --git a/xen/arch/x86/include/asm/amd.h b/xen/arch/x86/include/asm/amd.h
-index a975d3de26..82324110ab 100644
---- a/xen/arch/x86/include/asm/amd.h
-+++ b/xen/arch/x86/include/asm/amd.h
-@@ -140,6 +140,17 @@
-                        AMD_MODEL_RANGE(0x11, 0x0, 0x0, 0xff, 0xf),	\
-                        AMD_MODEL_RANGE(0x12, 0x0, 0x0, 0xff, 0xf))
- 
-+/*
-+ * The Zen1 and Zen2 microarchitectures are implemented by AMD (Fam17h) and
-+ * Hygon (Fam18h) but without simple model number rules.  Instead, use STIBP
-+ * as a heuristic that distinguishes the two.
-+ *
-+ * The caller is required to perform the appropriate vendor/family checks
-+ * first.
-+ */
-+#define is_zen1_uarch() (!boot_cpu_has(X86_FEATURE_AMD_STIBP))
-+#define is_zen2_uarch()   boot_cpu_has(X86_FEATURE_AMD_STIBP)
-+
- struct cpuinfo_x86;
- int cpu_has_amd_erratum(const struct cpuinfo_x86 *, int, ...);
- 
--- 
-2.41.0
-

xsa439-0010-x86-spec-ctrl-Mitigate-the-Zen1-DIV-leakage.patch

@@ -1,231 +0,0 @@
-From 9ac2f49f5fa3a5159409241d4f74fb0d721dd4c5 Mon Sep 17 00:00:00 2001
-Message-ID: <9ac2f49f5fa3a5159409241d4f74fb0d721dd4c5.1695733540.git.m.a.young@durham.ac.uk>
-In-Reply-To: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-References: <d2d2dcae879c6cc05227c9620f0a772f35fe6886.1695733540.git.m.a.young@durham.ac.uk>
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Wed, 30 Aug 2023 20:24:25 +0100
-Subject: [XEN PATCH 10/10] x86/spec-ctrl: Mitigate the Zen1 DIV leakage
-
-In the Zen1 microarchitecure, there is one divider in the pipeline which
-services uops from both threads.  In the case of #DE, the latched result from
-the previous DIV to execute will be forwarded speculatively.
-
-This is an interesting covert channel that allows two threads to communicate
-without any system calls.  In also allows userspace to obtain the result of
-the most recent DIV instruction executed (even speculatively) in the core,
-which can be from a higher privilege context.
-
-Scrub the result from the divider by executing a non-faulting divide.  This
-needs performing on the exit-to-guest paths, and ist_exit-to-Xen.
-
-Alternatives in IST context is believed safe now that it's done in NMI
-context.
-
-This is XSA-439 / CVE-2023-20588.
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-(cherry picked from commit b5926c6ecf05c28ee99c6248c42d691ccbf0c315)
----
- docs/misc/xen-command-line.pandoc        |  6 ++-
- xen/arch/x86/hvm/svm/entry.S             |  1 +
- xen/arch/x86/include/asm/cpufeatures.h   |  2 +-
- xen/arch/x86/include/asm/spec_ctrl_asm.h | 17 +++++++++
- xen/arch/x86/spec_ctrl.c                 | 48 +++++++++++++++++++++++-
- 5 files changed, 71 insertions(+), 3 deletions(-)
-
-diff --git a/docs/misc/xen-command-line.pandoc b/docs/misc/xen-command-line.pandoc
-index d9dae740cc..b92c8f969c 100644
---- a/docs/misc/xen-command-line.pandoc
-+++ b/docs/misc/xen-command-line.pandoc
-@@ -2315,7 +2315,7 @@ By default SSBD will be mitigated at runtime (i.e `ssbd=runtime`).
- >              {msr-sc,rsb,md-clear,ibpb-entry}=<bool>|{pv,hvm}=<bool>,
- >              bti-thunk=retpoline|lfence|jmp, {ibrs,ibpb,ssbd,psfd,
- >              eager-fpu,l1d-flush,branch-harden,srb-lock,
-->              unpriv-mmio,gds-mit}=<bool> ]`
-+>              unpriv-mmio,gds-mit,div-scrub}=<bool> ]`
- 
- Controls for speculative execution sidechannel mitigations.  By default, Xen
- will pick the most appropriate mitigations based on compiled in support,
-@@ -2437,6 +2437,10 @@ has elected not to lock the configuration, Xen will use GDS_CTRL to mitigate
- GDS with.  Otherwise, Xen will mitigate by disabling AVX, which blocks the use
- of the AVX2 Gather instructions.
- 
-+On all hardware, the `div-scrub=` option can be used to force or prevent Xen
-+from mitigating the DIV-leakage vulnerability.  By default, Xen will mitigate
-+DIV-leakage on hardware believed to be vulnerable.
-+
- ### sync_console
- > `= <boolean>`
- 
-diff --git a/xen/arch/x86/hvm/svm/entry.S b/xen/arch/x86/hvm/svm/entry.S
-index 981cd82e7c..934f12cf5c 100644
---- a/xen/arch/x86/hvm/svm/entry.S
-+++ b/xen/arch/x86/hvm/svm/entry.S
-@@ -74,6 +74,7 @@ __UNLIKELY_END(nsvm_hap)
- 1:          /* No Spectre v1 concerns.  Execution will hit VMRUN imminently. */
-         .endm
-         ALTERNATIVE "", svm_vmentry_spec_ctrl, X86_FEATURE_SC_MSR_HVM
-+        ALTERNATIVE "", DO_SPEC_CTRL_DIV, X86_FEATURE_SC_DIV
- 
-         pop  %r15
-         pop  %r14
-diff --git a/xen/arch/x86/include/asm/cpufeatures.h b/xen/arch/x86/include/asm/cpufeatures.h
-index da0593de85..c3aad21c3b 100644
---- a/xen/arch/x86/include/asm/cpufeatures.h
-+++ b/xen/arch/x86/include/asm/cpufeatures.h
-@@ -35,7 +35,7 @@ XEN_CPUFEATURE(SC_RSB_HVM,        X86_SYNTH(19)) /* RSB overwrite needed for HVM
- XEN_CPUFEATURE(XEN_SELFSNOOP,     X86_SYNTH(20)) /* SELFSNOOP gets used by Xen itself */
- XEN_CPUFEATURE(SC_MSR_IDLE,       X86_SYNTH(21)) /* Clear MSR_SPEC_CTRL on idle */
- XEN_CPUFEATURE(XEN_LBR,           X86_SYNTH(22)) /* Xen uses MSR_DEBUGCTL.LBR */
--/* Bits 23 unused. */
-+XEN_CPUFEATURE(SC_DIV,            X86_SYNTH(23)) /* DIV scrub needed */
- XEN_CPUFEATURE(SC_RSB_IDLE,       X86_SYNTH(24)) /* RSB overwrite needed for idle. */
- XEN_CPUFEATURE(SC_VERW_IDLE,      X86_SYNTH(25)) /* VERW used by Xen for idle */
- XEN_CPUFEATURE(XEN_SHSTK,         X86_SYNTH(26)) /* Xen uses CET Shadow Stacks */
-diff --git a/xen/arch/x86/include/asm/spec_ctrl_asm.h b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-index 28a75796e6..f4b8b9d956 100644
---- a/xen/arch/x86/include/asm/spec_ctrl_asm.h
-+++ b/xen/arch/x86/include/asm/spec_ctrl_asm.h
-@@ -177,6 +177,19 @@
- .L\@_verw_skip:
- .endm
- 
-+.macro DO_SPEC_CTRL_DIV
-+/*
-+ * Requires nothing
-+ * Clobbers %rax
-+ *
-+ * Issue a DIV for its flushing side effect (Zen1 uarch specific).  Any
-+ * non-faulting DIV will do; a byte DIV has least latency, and doesn't clobber
-+ * %rdx.
-+ */
-+    mov $1, %eax
-+    div %al
-+.endm
-+
- .macro DO_SPEC_CTRL_ENTRY maybexen:req
- /*
-  * Requires %rsp=regs (also cpuinfo if !maybexen)
-@@ -279,6 +292,8 @@
-     ALTERNATIVE "", DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR_PV
- 
-     DO_SPEC_CTRL_COND_VERW
-+
-+    ALTERNATIVE "", DO_SPEC_CTRL_DIV, X86_FEATURE_SC_DIV
- .endm
- 
- /*
-@@ -391,6 +406,8 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise):
-     verw STACK_CPUINFO_FIELD(verw_sel)(%r14)
- .L\@_skip_verw:
- 
-+    ALTERNATIVE "", DO_SPEC_CTRL_DIV, X86_FEATURE_SC_DIV
-+
- .L\@_skip_ist_exit:
- .endm
- 
-diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c
-index 79b98f0fe7..0ff3c895ac 100644
---- a/xen/arch/x86/spec_ctrl.c
-+++ b/xen/arch/x86/spec_ctrl.c
-@@ -79,6 +79,7 @@ static int8_t __initdata opt_srb_lock = -1;
- static bool __initdata opt_unpriv_mmio;
- static bool __ro_after_init opt_fb_clear_mmio;
- static int8_t __initdata opt_gds_mit = -1;
-+static int8_t __initdata opt_div_scrub = -1;
- 
- static int __init cf_check parse_spec_ctrl(const char *s)
- {
-@@ -133,6 +134,7 @@ static int __init cf_check parse_spec_ctrl(const char *s)
-             opt_srb_lock = 0;
-             opt_unpriv_mmio = false;
-             opt_gds_mit = 0;
-+            opt_div_scrub = 0;
-         }
-         else if ( val > 0 )
-             rc = -EINVAL;
-@@ -285,6 +287,8 @@ static int __init cf_check parse_spec_ctrl(const char *s)
-             opt_unpriv_mmio = val;
-         else if ( (val = parse_boolean("gds-mit", s, ss)) >= 0 )
-             opt_gds_mit = val;
-+        else if ( (val = parse_boolean("div-scrub", s, ss)) >= 0 )
-+            opt_div_scrub = val;
-         else
-             rc = -EINVAL;
- 
-@@ -485,7 +489,7 @@ static void __init print_details(enum ind_thunk thunk)
-                "\n");
- 
-     /* Settings for Xen's protection, irrespective of guests. */
--    printk("  Xen settings: BTI-Thunk %s, SPEC_CTRL: %s%s%s%s%s, Other:%s%s%s%s%s\n",
-+    printk("  Xen settings: BTI-Thunk %s, SPEC_CTRL: %s%s%s%s%s, Other:%s%s%s%s%s%s\n",
-            thunk == THUNK_NONE      ? "N/A" :
-            thunk == THUNK_RETPOLINE ? "RETPOLINE" :
-            thunk == THUNK_LFENCE    ? "LFENCE" :
-@@ -510,6 +514,7 @@ static void __init print_details(enum ind_thunk thunk)
-            opt_l1d_flush                             ? " L1D_FLUSH" : "",
-            opt_md_clear_pv || opt_md_clear_hvm ||
-            opt_fb_clear_mmio                         ? " VERW"  : "",
-+           opt_div_scrub                             ? " DIV" : "",
-            opt_branch_harden                         ? " BRANCH_HARDEN" : "");
- 
-     /* L1TF diagnostics, printed if vulnerable or PV shadowing is in use. */
-@@ -967,6 +972,45 @@ static void __init srso_calculations(bool hw_smt_enabled)
-         setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
- }
- 
-+/*
-+ * The Div leakage issue is specific to the AMD Zen1 microarchitecure.
-+ *
-+ * However, there's no $FOO_NO bit defined, so if we're virtualised we have no
-+ * hope of spotting the case where we might move to vulnerable hardware.  We
-+ * also can't make any useful conclusion about SMT-ness.
-+ *
-+ * Don't check the hypervisor bit, so at least we do the safe thing when
-+ * booting on something that looks like a Zen1 CPU.
-+ */
-+static bool __init has_div_vuln(void)
-+{
-+    if ( !(boot_cpu_data.x86_vendor &
-+           (X86_VENDOR_AMD | X86_VENDOR_HYGON)) )
-+        return false;
-+
-+    if ( boot_cpu_data.x86 != 0x17 && boot_cpu_data.x86 != 0x18 )
-+        return false;
-+
-+    return is_zen1_uarch();
-+}
-+
-+static void __init div_calculations(bool hw_smt_enabled)
-+{
-+    bool cpu_bug_div = has_div_vuln();
-+
-+    if ( opt_div_scrub == -1 )
-+        opt_div_scrub = cpu_bug_div;
-+
-+    if ( opt_div_scrub )
-+        setup_force_cpu_cap(X86_FEATURE_SC_DIV);
-+
-+    if ( opt_smt == -1 && !cpu_has_hypervisor && cpu_bug_div && hw_smt_enabled )
-+        warning_add(
-+            "Booted on leaky-DIV hardware with SMT/Hyperthreading\n"
-+            "enabled.  Please assess your configuration and choose an\n"
-+            "explicit 'smt=<bool>' setting.  See XSA-439.\n");
-+}
-+
- static void __init ibpb_calculations(void)
- {
-     bool def_ibpb_entry = false;
-@@ -1726,6 +1770,8 @@ void __init init_speculation_mitigations(void)
- 
-     ibpb_calculations();
- 
-+    div_calculations(hw_smt_enabled);
-+
-     /* Check whether Eager FPU should be enabled by default. */
-     if ( opt_eager_fpu == -1 )
-         opt_eager_fpu = should_use_eager_fpu();
--- 
-2.41.0
-

xsa440-4.17.patch

@@ -1,58 +0,0 @@
-From 5d8b3d1ec98e56155d9650d7f4a70cd8ba9dc27d Mon Sep 17 00:00:00 2001
-From: Julien Grall <jgrall@amazon.com>
-Date: Fri, 22 Sep 2023 11:32:16 +0100
-Subject: tools/xenstored: domain_entry_fix(): Handle conflicting transaction
-
-The function domain_entry_fix() will be initially called to check if the
-quota is correct before attempt to commit any nodes. So it would be
-possible that accounting is temporarily negative. This is the case
-in the following sequence:
-
-  1) Create 50 nodes
-  2) Start two transactions
-  3) Delete all the nodes in each transaction
-  4) Commit the two transactions
-
-Because the first transaction will have succeed and updated the
-accounting, there is no guarantee that 'd->nbentry + num' will still
-be above 0. So the assert() would be triggered.
-The assert() was introduced in dbef1f748289 ("tools/xenstore: simplify
-and fix per domain node accounting") with the assumption that the
-value can't be negative. As this is not true revert to the original
-check but restricted to the path where we don't update. Take the
-opportunity to explain the rationale behind the check.
-
-This CVE-2023-34323 / XSA-440.
-
-Reported-by: Stanislav Uschakow <suschako@amazon.de>
-Fixes: dbef1f748289 ("tools/xenstore: simplify and fix per domain node accounting")
-Signed-off-by: Julien Grall <jgrall@amazon.com>
-Reviewed-by: Juergen Gross <jgross@suse.com>
-
-diff --git a/tools/xenstore/xenstored_domain.c b/tools/xenstore/xenstored_domain.c
-index aa86892fed9e..6074df210c6e 100644
---- a/tools/xenstore/xenstored_domain.c
-+++ b/tools/xenstore/xenstored_domain.c
-@@ -1094,10 +1094,20 @@ int domain_entry_fix(unsigned int domid, int num, bool update)
- 	}
- 
- 	cnt = d->nbentry + num;
--	assert(cnt >= 0);
- 
--	if (update)
-+	if (update) {
-+		assert(cnt >= 0);
- 		d->nbentry = cnt;
-+	} else if (cnt < 0) {
-+		/*
-+		 * In a transaction when a node is being added/removed AND
-+		 * the same node has been added/removed outside the
-+		 * transaction in parallel, the result value may be negative.
-+		 * This is no problem, as the transaction will fail due to
-+		 * the resulting conflict. So override 'cnt'.
-+		 */
-+		cnt = 0;
-+	}
- 
- 	return domid_is_unprivileged(domid) ? cnt : 0;
- }

xsa442-4.17.patch

@@ -1,185 +0,0 @@
-From 5b2ccb60ff22fbff44dd66214c2956a434ee6271 Mon Sep 17 00:00:00 2001
-From: Roger Pau Monne <roger.pau@citrix.com>
-Date: Tue, 13 Jun 2023 15:01:05 +0200
-Subject: [PATCH] iommu/amd-vi: flush IOMMU TLB when flushing the DTE
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-The caching invalidation guidelines from the AMD-Vi specification (48882—Rev
-3.07-PUB—Oct 2022) seem to be misleading on some hardware, as devices will
-malfunction (see stale DMA mappings) if some fields of the DTE are updated but
-the IOMMU TLB is not flushed. This has been observed in practice on AMD
-systems.  Due to the lack of guidance from the currently published
-specification this patch aims to increase the flushing done in order to prevent
-device malfunction.
-
-In order to fix, issue an INVALIDATE_IOMMU_PAGES command from
-amd_iommu_flush_device(), flushing all the address space.  Note this requires
-callers to be adjusted in order to pass the DomID on the DTE previous to the
-modification.
-
-Some call sites don't provide a valid DomID to amd_iommu_flush_device() in
-order to avoid the flush.  That's because the device had address translations
-disabled and hence the previous DomID on the DTE is not valid.  Note the
-current logic relies on the entity disabling address translations to also flush
-the TLB of the in use DomID.
-
-Device I/O TLB flushing when ATS are enabled is not covered by the current
-change, as ATS usage is not security supported.
-
-This is XSA-442 / CVE-2023-34326
-
-Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
----
- xen/drivers/passthrough/amd/iommu.h         |  3 ++-
- xen/drivers/passthrough/amd/iommu_cmd.c     | 10 +++++++++-
- xen/drivers/passthrough/amd/iommu_guest.c   |  5 +++--
- xen/drivers/passthrough/amd/iommu_init.c    |  6 +++++-
- xen/drivers/passthrough/amd/pci_amd_iommu.c | 14 ++++++++++----
- 5 files changed, 29 insertions(+), 9 deletions(-)
-
-diff --git a/xen/drivers/passthrough/amd/iommu.h b/xen/drivers/passthrough/amd/iommu.h
-index 5429ada58ef5..a58be28bf96d 100644
---- a/xen/drivers/passthrough/amd/iommu.h
-+++ b/xen/drivers/passthrough/amd/iommu.h
-@@ -283,7 +283,8 @@ void amd_iommu_flush_pages(struct domain *d, unsigned long dfn,
-                            unsigned int order);
- void amd_iommu_flush_iotlb(u8 devfn, const struct pci_dev *pdev,
-                            uint64_t gaddr, unsigned int order);
--void amd_iommu_flush_device(struct amd_iommu *iommu, uint16_t bdf);
-+void amd_iommu_flush_device(struct amd_iommu *iommu, uint16_t bdf,
-+                            domid_t domid);
- void amd_iommu_flush_intremap(struct amd_iommu *iommu, uint16_t bdf);
- void amd_iommu_flush_all_caches(struct amd_iommu *iommu);
- 
-diff --git a/xen/drivers/passthrough/amd/iommu_cmd.c b/xen/drivers/passthrough/amd/iommu_cmd.c
-index 40ddf366bb4d..cb28b36abc38 100644
---- a/xen/drivers/passthrough/amd/iommu_cmd.c
-+++ b/xen/drivers/passthrough/amd/iommu_cmd.c
-@@ -363,10 +363,18 @@ void amd_iommu_flush_pages(struct domain *d,
-     _amd_iommu_flush_pages(d, __dfn_to_daddr(dfn), order);
- }
- 
--void amd_iommu_flush_device(struct amd_iommu *iommu, uint16_t bdf)
-+void amd_iommu_flush_device(struct amd_iommu *iommu, uint16_t bdf,
-+                            domid_t domid)
- {
-     invalidate_dev_table_entry(iommu, bdf);
-     flush_command_buffer(iommu, 0);
-+
-+    /* Also invalidate IOMMU TLB entries when flushing the DTE. */
-+    if ( domid != DOMID_INVALID )
-+    {
-+        invalidate_iommu_pages(iommu, INV_IOMMU_ALL_PAGES_ADDRESS, domid, 0);
-+        flush_command_buffer(iommu, 0);
-+    }
- }
- 
- void amd_iommu_flush_intremap(struct amd_iommu *iommu, uint16_t bdf)
-diff --git a/xen/drivers/passthrough/amd/iommu_guest.c b/xen/drivers/passthrough/amd/iommu_guest.c
-index 80a331f546ed..be86bce6fb03 100644
---- a/xen/drivers/passthrough/amd/iommu_guest.c
-+++ b/xen/drivers/passthrough/amd/iommu_guest.c
-@@ -385,7 +385,7 @@ static int do_completion_wait(struct domain *d, cmd_entry_t *cmd)
- 
- static int do_invalidate_dte(struct domain *d, cmd_entry_t *cmd)
- {
--    uint16_t gbdf, mbdf, req_id, gdom_id, hdom_id;
-+    uint16_t gbdf, mbdf, req_id, gdom_id, hdom_id, prev_domid;
-     struct amd_iommu_dte *gdte, *mdte, *dte_base;
-     struct amd_iommu *iommu = NULL;
-     struct guest_iommu *g_iommu;
-@@ -445,13 +445,14 @@ static int do_invalidate_dte(struct domain *d, cmd_entry_t *cmd)
-     req_id = get_dma_requestor_id(iommu->seg, mbdf);
-     dte_base = iommu->dev_table.buffer;
-     mdte = &dte_base[req_id];
-+    prev_domid = mdte->domain_id;
- 
-     spin_lock_irqsave(&iommu->lock, flags);
-     dte_set_gcr3_table(mdte, hdom_id, gcr3_mfn << PAGE_SHIFT, gv, glx);
- 
-     spin_unlock_irqrestore(&iommu->lock, flags);
- 
--    amd_iommu_flush_device(iommu, req_id);
-+    amd_iommu_flush_device(iommu, req_id, prev_domid);
- 
-     return 0;
- }
-diff --git a/xen/drivers/passthrough/amd/iommu_init.c b/xen/drivers/passthrough/amd/iommu_init.c
-index 166570648d26..101a60ce1794 100644
---- a/xen/drivers/passthrough/amd/iommu_init.c
-+++ b/xen/drivers/passthrough/amd/iommu_init.c
-@@ -1547,7 +1547,11 @@ static int cf_check _invalidate_all_devices(
-         req_id = ivrs_mappings[bdf].dte_requestor_id;
-         if ( iommu )
-         {
--            amd_iommu_flush_device(iommu, req_id);
-+            /*
-+             * IOMMU TLB flush performed separately (see
-+             * invalidate_all_domain_pages()).
-+             */
-+            amd_iommu_flush_device(iommu, req_id, DOMID_INVALID);
-             amd_iommu_flush_intremap(iommu, req_id);
-         }
-     }
-diff --git a/xen/drivers/passthrough/amd/pci_amd_iommu.c b/xen/drivers/passthrough/amd/pci_amd_iommu.c
-index 94e37755064b..8641b84712a0 100644
---- a/xen/drivers/passthrough/amd/pci_amd_iommu.c
-+++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c
-@@ -192,10 +192,13 @@ static int __must_check amd_iommu_setup_domain_device(
- 
-         spin_unlock_irqrestore(&iommu->lock, flags);
- 
--        amd_iommu_flush_device(iommu, req_id);
-+        /* DTE didn't have DMA translations enabled, do not flush the TLB. */
-+        amd_iommu_flush_device(iommu, req_id, DOMID_INVALID);
-     }
-     else if ( dte->pt_root != mfn_x(page_to_mfn(root_pg)) )
-     {
-+        domid_t prev_domid = dte->domain_id;
-+
-         /*
-          * Strictly speaking if the device is the only one with this requestor
-          * ID, it could be allowed to be re-assigned regardless of unity map
-@@ -252,7 +255,7 @@ static int __must_check amd_iommu_setup_domain_device(
- 
-         spin_unlock_irqrestore(&iommu->lock, flags);
- 
--        amd_iommu_flush_device(iommu, req_id);
-+        amd_iommu_flush_device(iommu, req_id, prev_domid);
-     }
-     else
-         spin_unlock_irqrestore(&iommu->lock, flags);
-@@ -421,6 +424,8 @@ static void amd_iommu_disable_domain_device(const struct domain *domain,
-     spin_lock_irqsave(&iommu->lock, flags);
-     if ( dte->tv || dte->v )
-     {
-+        domid_t prev_domid = dte->domain_id;
-+
-         /* See the comment in amd_iommu_setup_device_table(). */
-         dte->int_ctl = IOMMU_DEV_TABLE_INT_CONTROL_ABORTED;
-         smp_wmb();
-@@ -439,7 +444,7 @@ static void amd_iommu_disable_domain_device(const struct domain *domain,
- 
-         spin_unlock_irqrestore(&iommu->lock, flags);
- 
--        amd_iommu_flush_device(iommu, req_id);
-+        amd_iommu_flush_device(iommu, req_id, prev_domid);
- 
-         AMD_IOMMU_DEBUG("Disable: device id = %#x, "
-                         "domain = %d, paging mode = %d\n",
-@@ -610,7 +615,8 @@ static int cf_check amd_iommu_add_device(u8 devfn, struct pci_dev *pdev)
- 
-         spin_unlock_irqrestore(&iommu->lock, flags);
- 
--        amd_iommu_flush_device(iommu, bdf);
-+        /* DTE didn't have DMA translations enabled, do not flush the TLB. */
-+        amd_iommu_flush_device(iommu, bdf, DOMID_INVALID);
-     }
- 
-     if ( amd_iommu_reserve_domain_unity_map(
--- 
-2.42.0
-

xsa443-4.17-01.patch

@@ -1,70 +0,0 @@
-From 7e48562bf34e90f907491a0595782d2daa1ff3ad Mon Sep 17 00:00:00 2001
-From: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Date: Thu, 14 Sep 2023 13:22:50 +0100
-Subject: [PATCH 01/11] libfsimage/xfs: Remove dead code
-
-xfs_info.agnolog (and related code) and XFS_INO_AGBNO_BITS are dead code
-that serve no purpose.
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
----
- tools/libfsimage/xfs/fsys_xfs.c | 18 ------------------
- 1 file changed, 18 deletions(-)
-
-diff --git a/tools/libfsimage/xfs/fsys_xfs.c b/tools/libfsimage/xfs/fsys_xfs.c
-index d735a88e55f3..2800699f5985 100644
---- a/tools/libfsimage/xfs/fsys_xfs.c
-+++ b/tools/libfsimage/xfs/fsys_xfs.c
-@@ -37,7 +37,6 @@ struct xfs_info {
- 	int blklog;
- 	int inopblog;
- 	int agblklog;
--	int agnolog;
- 	unsigned int nextents;
- 	xfs_daddr_t next;
- 	xfs_daddr_t daddr;
-@@ -65,9 +64,7 @@ static struct xfs_info xfs;
- 
- #define	XFS_INO_MASK(k)		((xfs_uint32_t)((1ULL << (k)) - 1))
- #define	XFS_INO_OFFSET_BITS	xfs.inopblog
--#define	XFS_INO_AGBNO_BITS	xfs.agblklog
- #define	XFS_INO_AGINO_BITS	(xfs.agblklog + xfs.inopblog)
--#define	XFS_INO_AGNO_BITS	xfs.agnolog
- 
- static inline xfs_agblock_t
- agino2agbno (xfs_agino_t agino)
-@@ -149,20 +146,6 @@ xt_len (xfs_bmbt_rec_32_t *r)
- 	return le32(r->l3) & mask32lo(21);
- }
- 
--static inline int
--xfs_highbit32(xfs_uint32_t v)
--{
--	int i;
--
--	if (--v) {
--		for (i = 0; i < 31; i++, v >>= 1) {
--			if (v == 0)
--				return i;
--		}
--	}
--	return 0;
--}
--
- static int
- isinxt (xfs_fileoff_t key, xfs_fileoff_t offset, xfs_filblks_t len)
- {
-@@ -472,7 +455,6 @@ xfs_mount (fsi_file_t *ffi, const char *options)
- 
- 	xfs.inopblog = super.sb_inopblog;
- 	xfs.agblklog = super.sb_agblklog;
--	xfs.agnolog = xfs_highbit32 (le32(super.sb_agcount));
- 
- 	xfs.btnode_ptr0_off =
- 		((xfs.bsize - sizeof(xfs_btree_block_t)) /
--- 
-2.42.0
-

xsa443-4.17-02.patch

@@ -1,32 +0,0 @@
-From c26327795b78c93f6fa6d5d46e34f59dc4046601 Mon Sep 17 00:00:00 2001
-From: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Date: Thu, 14 Sep 2023 13:22:51 +0100
-Subject: [PATCH 02/11] libfsimage/xfs: Amend mask32lo() to allow the value 32
-
-agblklog could plausibly be 32, but that would overflow this shift.
-Perform the shift as ULL and cast to u32 at the end instead.
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Acked-by: Jan Beulich <jbeulich@suse.com>
----
- tools/libfsimage/xfs/fsys_xfs.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/tools/libfsimage/xfs/fsys_xfs.c b/tools/libfsimage/xfs/fsys_xfs.c
-index 2800699f5985..4720bb4505c8 100644
---- a/tools/libfsimage/xfs/fsys_xfs.c
-+++ b/tools/libfsimage/xfs/fsys_xfs.c
-@@ -60,7 +60,7 @@ static struct xfs_info xfs;
- #define inode		((xfs_dinode_t *)((char *)FSYS_BUF + 8192))
- #define icore		(inode->di_core)
- 
--#define	mask32lo(n)	(((xfs_uint32_t)1 << (n)) - 1)
-+#define	mask32lo(n)	((xfs_uint32_t)((1ull << (n)) - 1))
- 
- #define	XFS_INO_MASK(k)		((xfs_uint32_t)((1ULL << (k)) - 1))
- #define	XFS_INO_OFFSET_BITS	xfs.inopblog
--- 
-2.42.0
-

xsa443-4.17-03.patch

@@ -1,137 +0,0 @@
-From 199f0538bbec052028679a55ea512437170854c9 Mon Sep 17 00:00:00 2001
-From: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Date: Thu, 14 Sep 2023 13:22:52 +0100
-Subject: [PATCH 03/11] libfsimage/xfs: Sanity-check the superblock during
- mounts
-
-Sanity-check the XFS superblock for wellformedness at the mount handler.
-This forces pygrub to abort parsing a potentially malformed filesystem and
-ensures the invariants assumed throughout the rest of the code hold.
-
-Also, derive parameters from previously sanitized parameters where possible
-(rather than reading them off the superblock)
-
-The code doesn't try to avoid overflowing the end of the disk, because
-that's an unlikely and benign error. Parameters used in calculations of
-xfs_daddr_t (like the root inode index) aren't in critical need of being
-sanitized.
-
-The sanitization of agblklog is basically checking that no obvious
-overflows happen on agblklog, and then ensuring agblocks is contained in
-the range (2^(sb_agblklog-1), 2^sb_agblklog].
-
-This is part of XSA-443 / CVE-2023-34325
-
-Reported-by: Ferdinand Nölscher <noelscher@google.com>
-Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
----
- tools/libfsimage/xfs/fsys_xfs.c | 48 ++++++++++++++++++++++++++-------
- tools/libfsimage/xfs/xfs.h      | 12 +++++++++
- 2 files changed, 50 insertions(+), 10 deletions(-)
-
-diff --git a/tools/libfsimage/xfs/fsys_xfs.c b/tools/libfsimage/xfs/fsys_xfs.c
-index 4720bb4505c8..e4eb7e1ee26f 100644
---- a/tools/libfsimage/xfs/fsys_xfs.c
-+++ b/tools/libfsimage/xfs/fsys_xfs.c
-@@ -17,6 +17,7 @@
-  *  along with this program; If not, see <http://www.gnu.org/licenses/>.
-  */
- 
-+#include <stdbool.h>
- #include <xenfsimage_grub.h>
- #include "xfs.h"
- 
-@@ -433,29 +434,56 @@ first_dentry (fsi_file_t *ffi, xfs_ino_t *ino)
- 	return next_dentry (ffi, ino);
- }
- 
-+static bool
-+xfs_sb_is_invalid (const xfs_sb_t *super)
-+{
-+	return (le32(super->sb_magicnum) != XFS_SB_MAGIC)
-+	    || ((le16(super->sb_versionnum) & XFS_SB_VERSION_NUMBITS) !=
-+	        XFS_SB_VERSION_4)
-+	    || (super->sb_inodelog < XFS_SB_INODELOG_MIN)
-+	    || (super->sb_inodelog > XFS_SB_INODELOG_MAX)
-+	    || (super->sb_blocklog < XFS_SB_BLOCKLOG_MIN)
-+	    || (super->sb_blocklog > XFS_SB_BLOCKLOG_MAX)
-+	    || (super->sb_blocklog < super->sb_inodelog)
-+	    || (super->sb_agblklog > XFS_SB_AGBLKLOG_MAX)
-+	    || ((1ull << super->sb_agblklog) < le32(super->sb_agblocks))
-+	    || (((1ull << super->sb_agblklog) >> 1) >=
-+	        le32(super->sb_agblocks))
-+	    || ((super->sb_blocklog + super->sb_dirblklog) >=
-+	        XFS_SB_DIRBLK_NUMBITS);
-+}
-+
- static int
- xfs_mount (fsi_file_t *ffi, const char *options)
- {
- 	xfs_sb_t super;
- 
- 	if (!devread (ffi, 0, 0, sizeof(super), (char *)&super)
--	    || (le32(super.sb_magicnum) != XFS_SB_MAGIC)
--	    || ((le16(super.sb_versionnum) 
--		& XFS_SB_VERSION_NUMBITS) != XFS_SB_VERSION_4) ) {
-+	    || xfs_sb_is_invalid(&super)) {
- 		return 0;
- 	}
- 
--	xfs.bsize = le32 (super.sb_blocksize);
--	xfs.blklog = super.sb_blocklog;
--	xfs.bdlog = xfs.blklog - SECTOR_BITS;
-+	/*
-+	 * Not sanitized. It's exclusively used to generate disk addresses,
-+	 * so it's not important from a security standpoint.
-+	 */
- 	xfs.rootino = le64 (super.sb_rootino);
--	xfs.isize = le16 (super.sb_inodesize);
--	xfs.agblocks = le32 (super.sb_agblocks);
--	xfs.dirbsize = xfs.bsize << super.sb_dirblklog;
- 
--	xfs.inopblog = super.sb_inopblog;
-+	/*
-+	 * Sanitized to be consistent with each other, only used to
-+	 * generate disk addresses, so it's safe
-+	 */
-+	xfs.agblocks = le32 (super.sb_agblocks);
- 	xfs.agblklog = super.sb_agblklog;
- 
-+	/* Derived from sanitized parameters */
-+	xfs.bsize = 1 << super.sb_blocklog;
-+	xfs.blklog = super.sb_blocklog;
-+	xfs.bdlog = super.sb_blocklog - SECTOR_BITS;
-+	xfs.isize = 1 << super.sb_inodelog;
-+	xfs.dirbsize = 1 << (super.sb_blocklog + super.sb_dirblklog);
-+	xfs.inopblog = super.sb_blocklog - super.sb_inodelog;
-+
- 	xfs.btnode_ptr0_off =
- 		((xfs.bsize - sizeof(xfs_btree_block_t)) /
- 		(sizeof (xfs_bmbt_key_t) + sizeof (xfs_bmbt_ptr_t)))
-diff --git a/tools/libfsimage/xfs/xfs.h b/tools/libfsimage/xfs/xfs.h
-index 40699281e44d..b87e37d3d7e9 100644
---- a/tools/libfsimage/xfs/xfs.h
-+++ b/tools/libfsimage/xfs/xfs.h
-@@ -134,6 +134,18 @@ typedef struct xfs_sb
-         xfs_uint8_t       sb_dummy[7];    /* padding */
- } xfs_sb_t;
- 
-+/* Bound taken from xfs.c in GRUB2. It doesn't exist in the spec */
-+#define	XFS_SB_DIRBLK_NUMBITS	27
-+/* Implied by the XFS specification. The minimum block size is 512 octets */
-+#define	XFS_SB_BLOCKLOG_MIN	9
-+/* Implied by the XFS specification. The maximum block size is 65536 octets */
-+#define	XFS_SB_BLOCKLOG_MAX	16
-+/* Implied by the XFS specification. The minimum inode size is 256 octets */
-+#define	XFS_SB_INODELOG_MIN	8
-+/* Implied by the XFS specification. The maximum inode size is 2048 octets */
-+#define	XFS_SB_INODELOG_MAX	11
-+/* High bound for sb_agblklog */
-+#define	XFS_SB_AGBLKLOG_MAX	32
- 
- /* those are from xfs_btree.h */
- 
--- 
-2.42.0
-

xsa443-4.17-04.patch

@@ -1,61 +0,0 @@
-From c66fd01277939634c624c8340838682d9d4fd839 Mon Sep 17 00:00:00 2001
-From: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Date: Thu, 14 Sep 2023 13:22:53 +0100
-Subject: [PATCH 04/11] libfsimage/xfs: Add compile-time check to libfsimage
-
-Adds the common tools include folder to the -I compile flags
-of libfsimage. This allows us to use:
-  xen-tools/common-macros.h:BUILD_BUG_ON()
-
-With it, statically assert a sanitized "blocklog - SECTOR_BITS" cannot
-underflow.
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
----
- tools/libfsimage/common.mk      | 2 +-
- tools/libfsimage/xfs/fsys_xfs.c | 4 +++-
- 2 files changed, 4 insertions(+), 2 deletions(-)
-
-diff --git a/tools/libfsimage/common.mk b/tools/libfsimage/common.mk
-index 4fc8c6679599..e4336837d045 100644
---- a/tools/libfsimage/common.mk
-+++ b/tools/libfsimage/common.mk
-@@ -1,7 +1,7 @@
- include $(XEN_ROOT)/tools/Rules.mk
- 
- FSDIR := $(libdir)/xenfsimage
--CFLAGS += -Wno-unknown-pragmas -I$(XEN_ROOT)/tools/libfsimage/common/ -DFSIMAGE_FSDIR=\"$(FSDIR)\"
-+CFLAGS += -Wno-unknown-pragmas -I$(XEN_ROOT)/tools/libfsimage/common/ $(CFLAGS_xeninclude) -DFSIMAGE_FSDIR=\"$(FSDIR)\"
- CFLAGS += -D_GNU_SOURCE
- LDFLAGS += -L../common/
- 
-diff --git a/tools/libfsimage/xfs/fsys_xfs.c b/tools/libfsimage/xfs/fsys_xfs.c
-index e4eb7e1ee26f..4a8dd6f2397b 100644
---- a/tools/libfsimage/xfs/fsys_xfs.c
-+++ b/tools/libfsimage/xfs/fsys_xfs.c
-@@ -19,6 +19,7 @@
- 
- #include <stdbool.h>
- #include <xenfsimage_grub.h>
-+#include <xen-tools/libs.h>
- #include "xfs.h"
- 
- #define MAX_LINK_COUNT	8
-@@ -477,9 +478,10 @@ xfs_mount (fsi_file_t *ffi, const char *options)
- 	xfs.agblklog = super.sb_agblklog;
- 
- 	/* Derived from sanitized parameters */
-+	BUILD_BUG_ON(XFS_SB_BLOCKLOG_MIN < SECTOR_BITS);
-+	xfs.bdlog = super.sb_blocklog - SECTOR_BITS;
- 	xfs.bsize = 1 << super.sb_blocklog;
- 	xfs.blklog = super.sb_blocklog;
--	xfs.bdlog = super.sb_blocklog - SECTOR_BITS;
- 	xfs.isize = 1 << super.sb_inodelog;
- 	xfs.dirbsize = 1 << (super.sb_blocklog + super.sb_dirblklog);
- 	xfs.inopblog = super.sb_blocklog - super.sb_inodelog;
--- 
-2.42.0
-

xsa443-4.17-05.patch

@@ -1,59 +0,0 @@
-From ad5d0db5e68e5d4e79255fa85d9cb0069bb1c5d5 Mon Sep 17 00:00:00 2001
-From: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Date: Mon, 25 Sep 2023 18:32:21 +0100
-Subject: [PATCH 05/11] tools/pygrub: Remove unnecessary hypercall
-
-There's a hypercall being issued in order to determine whether PV64 is
-supported, but since Xen 4.3 that's strictly true so it's not required.
-
-Plus, this way we can avoid mapping the privcmd interface altogether in the
-depriv pygrub.
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
----
- tools/pygrub/src/pygrub | 12 +-----------
- 1 file changed, 1 insertion(+), 11 deletions(-)
-
-diff --git a/tools/pygrub/src/pygrub b/tools/pygrub/src/pygrub
-index ce7ab0eb8cf3..ce4e07d3e823 100755
---- a/tools/pygrub/src/pygrub
-+++ b/tools/pygrub/src/pygrub
-@@ -18,7 +18,6 @@ import os, sys, string, struct, tempfile, re, traceback, stat, errno
- import copy
- import logging
- import platform
--import xen.lowlevel.xc
- 
- import curses, _curses, curses.textpad, curses.ascii
- import getopt
-@@ -668,14 +667,6 @@ def run_grub(file, entry, fs, cfg_args):
- 
-     return grubcfg
- 
--def supports64bitPVguest():
--    xc = xen.lowlevel.xc.xc()
--    caps = xc.xeninfo()['xen_caps'].split(" ")
--    for cap in caps:
--        if cap == "xen-3.0-x86_64":
--            return True
--    return False
--
- # If nothing has been specified, look for a Solaris domU. If found, perform the
- # necessary tweaks.
- def sniff_solaris(fs, cfg):
-@@ -684,8 +675,7 @@ def sniff_solaris(fs, cfg):
-         return cfg
- 
-     if not cfg["kernel"]:
--        if supports64bitPVguest() and \
--          fs.file_exists("/platform/i86xpv/kernel/amd64/unix"):
-+        if fs.file_exists("/platform/i86xpv/kernel/amd64/unix"):
-             cfg["kernel"] = "/platform/i86xpv/kernel/amd64/unix"
-             cfg["ramdisk"] = "/platform/i86pc/amd64/boot_archive"
-         elif fs.file_exists("/platform/i86xpv/kernel/unix"):
--- 
-2.42.0
-

xsa443-4.17-06.patch

@@ -1,65 +0,0 @@
-From d3ceb0b314005a656dd2ca4b2821575a36f8426d Mon Sep 17 00:00:00 2001
-From: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Date: Mon, 25 Sep 2023 18:32:22 +0100
-Subject: [PATCH 06/11] tools/pygrub: Small refactors
-
-Small tidy up to ensure output_directory always has a trailing '/' to ease
-concatenating paths and that `output` can only be a filename or None.
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
----
- tools/pygrub/src/pygrub | 10 +++++-----
- 1 file changed, 5 insertions(+), 5 deletions(-)
-
-diff --git a/tools/pygrub/src/pygrub b/tools/pygrub/src/pygrub
-index ce4e07d3e823..1042c05b8676 100755
---- a/tools/pygrub/src/pygrub
-+++ b/tools/pygrub/src/pygrub
-@@ -793,7 +793,7 @@ if __name__ == "__main__":
-     debug = False
-     not_really = False
-     output_format = "sxp"
--    output_directory = "/var/run/xen/pygrub"
-+    output_directory = "/var/run/xen/pygrub/"
- 
-     # what was passed in
-     incfg = { "kernel": None, "ramdisk": None, "args": "" }
-@@ -815,7 +815,8 @@ if __name__ == "__main__":
-             usage()
-             sys.exit()
-         elif o in ("--output",):
--            output = a
-+            if a != "-":
-+                output = a
-         elif o in ("--kernel",):
-             incfg["kernel"] = a
-         elif o in ("--ramdisk",):
-@@ -847,12 +848,11 @@ if __name__ == "__main__":
-             if not os.path.isdir(a):
-                 print("%s is not an existing directory" % a)
-                 sys.exit(1)
--            output_directory = a
-+            output_directory = a + '/'
- 
-     if debug:
-         logging.basicConfig(level=logging.DEBUG)
- 
--
-     try:
-         os.makedirs(output_directory, 0o700)
-     except OSError as e:
-@@ -861,7 +861,7 @@ if __name__ == "__main__":
-         else:
-             raise
- 
--    if output is None or output == "-":
-+    if output is None:
-         fd = sys.stdout.fileno()
-     else:
-         fd = os.open(output, os.O_WRONLY)
--- 
-2.42.0
-

xsa443-4.17-07.patch

@@ -1,105 +0,0 @@
-From 9e80cfecde338cea0db136c2fb5ed78d6081e05f Mon Sep 17 00:00:00 2001
-From: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Date: Mon, 25 Sep 2023 18:32:23 +0100
-Subject: [PATCH 07/11] tools/pygrub: Open the output files earlier
-
-This patch allows pygrub to get ahold of every RW file descriptor it needs
-early on. A later patch will clamp the filesystem it can access so it can't
-obtain any others.
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
----
- tools/pygrub/src/pygrub | 37 ++++++++++++++++++++++---------------
- 1 file changed, 22 insertions(+), 15 deletions(-)
-
-diff --git a/tools/pygrub/src/pygrub b/tools/pygrub/src/pygrub
-index 1042c05b8676..91e2ec2ab105 100755
---- a/tools/pygrub/src/pygrub
-+++ b/tools/pygrub/src/pygrub
-@@ -738,8 +738,7 @@ if __name__ == "__main__":
-     def usage():
-         print("Usage: %s [-q|--quiet] [-i|--interactive] [-l|--list-entries] [-n|--not-really] [--output=] [--kernel=] [--ramdisk=] [--args=] [--entry=] [--output-directory=] [--output-format=sxp|simple|simple0] [--offset=] <image>" %(sys.argv[0],), file=sys.stderr)
- 
--    def copy_from_image(fs, file_to_read, file_type, output_directory,
--                        not_really):
-+    def copy_from_image(fs, file_to_read, file_type, fd_dst, path_dst, not_really):
-         if not_really:
-             if fs.file_exists(file_to_read):
-                 return "<%s:%s>" % (file_type, file_to_read)
-@@ -750,21 +749,18 @@ if __name__ == "__main__":
-         except Exception as e:
-             print(e, file=sys.stderr)
-             sys.exit("Error opening %s in guest" % file_to_read)
--        (tfd, ret) = tempfile.mkstemp(prefix="boot_"+file_type+".",
--                                      dir=output_directory)
-         dataoff = 0
-         while True:
-             data = datafile.read(FS_READ_MAX, dataoff)
-             if len(data) == 0:
--                os.close(tfd)
-+                os.close(fd_dst)
-                 del datafile
--                return ret
-+                return
-             try:
--                os.write(tfd, data)
-+                os.write(fd_dst, data)
-             except Exception as e:
-                 print(e, file=sys.stderr)
--                os.close(tfd)
--                os.unlink(ret)
-+                os.unlink(path_dst)
-                 del datafile
-                 sys.exit("Error writing temporary copy of "+file_type)
-             dataoff += len(data)
-@@ -861,6 +857,14 @@ if __name__ == "__main__":
-         else:
-             raise
- 
-+    if not_really:
-+        fd_kernel =  path_kernel = fd_ramdisk = path_ramdisk = None
-+    else:
-+        (fd_kernel, path_kernel) = tempfile.mkstemp(prefix="boot_kernel.",
-+                                                    dir=output_directory)
-+        (fd_ramdisk, path_ramdisk) = tempfile.mkstemp(prefix="boot_ramdisk.",
-+                                                      dir=output_directory)
-+
-     if output is None:
-         fd = sys.stdout.fileno()
-     else:
-@@ -920,20 +924,23 @@ if __name__ == "__main__":
-     if fs is None:
-         raise RuntimeError("Unable to find partition containing kernel")
- 
--    bootcfg["kernel"] = copy_from_image(fs, chosencfg["kernel"], "kernel",
--                                        output_directory, not_really)
-+    copy_from_image(fs, chosencfg["kernel"], "kernel",
-+                    fd_kernel, path_kernel, not_really)
-+    bootcfg["kernel"] = path_kernel
- 
-     if chosencfg["ramdisk"]:
-         try:
--            bootcfg["ramdisk"] = copy_from_image(fs, chosencfg["ramdisk"],
--                                                 "ramdisk", output_directory,
--                                                 not_really)
-+            copy_from_image(fs, chosencfg["ramdisk"], "ramdisk",
-+                            fd_ramdisk, path_ramdisk, not_really)
-         except:
-             if not not_really:
--                os.unlink(bootcfg["kernel"])
-+                os.unlink(path_kernel)
-             raise
-+        bootcfg["ramdisk"] = path_ramdisk
-     else:
-         initrd = None
-+        if not not_really:
-+            os.unlink(path_ramdisk)
- 
-     args = None
-     if chosencfg["args"]:
--- 
-2.42.0
-

xsa443-4.17-08.patch

@@ -1,126 +0,0 @@
-From 2fb4cdcedd8720f78c4bd44739a5d30dd1a7d9a5 Mon Sep 17 00:00:00 2001
-From: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Date: Mon, 25 Sep 2023 18:32:24 +0100
-Subject: [PATCH 08/11] tools/libfsimage: Export a new function to preload all
- plugins
-
-This is work required in order to let pygrub operate in highly deprivileged
-chroot mode. This patch adds a function that preloads every plugin, hence
-ensuring that a on function exit, every shared library is loaded in memory.
-
-The new "init" function is supposed to be used before depriv, but that's
-fine because it's not acting on untrusted data.
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
----
- tools/libfsimage/common/fsimage_plugin.c |  4 ++--
- tools/libfsimage/common/mapfile-GNU      |  1 +
- tools/libfsimage/common/mapfile-SunOS    |  1 +
- tools/libfsimage/common/xenfsimage.h     |  8 ++++++++
- tools/pygrub/src/fsimage/fsimage.c       | 15 +++++++++++++++
- 5 files changed, 27 insertions(+), 2 deletions(-)
-
-diff --git a/tools/libfsimage/common/fsimage_plugin.c b/tools/libfsimage/common/fsimage_plugin.c
-index de1412b4233a..d0cb9e96a654 100644
---- a/tools/libfsimage/common/fsimage_plugin.c
-+++ b/tools/libfsimage/common/fsimage_plugin.c
-@@ -119,7 +119,7 @@ fail:
- 	return (-1);
- }
- 
--static int load_plugins(void)
-+int fsi_init(void)
- {
- 	const char *fsdir = getenv("XEN_FSIMAGE_FSDIR");
- 	struct dirent *dp = NULL;
-@@ -180,7 +180,7 @@ int find_plugin(fsi_t *fsi, const char *path, const char *options)
- 	fsi_plugin_t *fp;
- 	int ret = 0;
- 
--	if (plugins == NULL && (ret = load_plugins()) != 0)
-+	if (plugins == NULL && (ret = fsi_init()) != 0)
- 		goto out;
- 
- 	for (fp = plugins; fp != NULL; fp = fp->fp_next) {
-diff --git a/tools/libfsimage/common/mapfile-GNU b/tools/libfsimage/common/mapfile-GNU
-index 26d4d7a69ec7..2d54d527d7f5 100644
---- a/tools/libfsimage/common/mapfile-GNU
-+++ b/tools/libfsimage/common/mapfile-GNU
-@@ -1,6 +1,7 @@
- VERSION {
- 	libfsimage.so.1.0 {
- 		global:
-+			fsi_init;
- 			fsi_open_fsimage;
- 			fsi_close_fsimage;
- 			fsi_file_exists;
-diff --git a/tools/libfsimage/common/mapfile-SunOS b/tools/libfsimage/common/mapfile-SunOS
-index e99b90b65077..48deedb4252f 100644
---- a/tools/libfsimage/common/mapfile-SunOS
-+++ b/tools/libfsimage/common/mapfile-SunOS
-@@ -1,5 +1,6 @@
- libfsimage.so.1.0 {
- 	global:
-+		fsi_init;
- 		fsi_open_fsimage;
- 		fsi_close_fsimage;
- 		fsi_file_exists;
-diff --git a/tools/libfsimage/common/xenfsimage.h b/tools/libfsimage/common/xenfsimage.h
-index 201abd54f23a..341883b2d71a 100644
---- a/tools/libfsimage/common/xenfsimage.h
-+++ b/tools/libfsimage/common/xenfsimage.h
-@@ -35,6 +35,14 @@ extern C {
- typedef struct fsi fsi_t;
- typedef struct fsi_file fsi_file_t;
- 
-+/*
-+ * Optional initialization function. If invoked it loads the associated
-+ * dynamic libraries for the backends ahead of time. This is required if
-+ * the library is to run as part of a highly deprivileged executable, as
-+ * the libraries may not be reachable after depriv.
-+ */
-+int fsi_init(void);
-+
- fsi_t *fsi_open_fsimage(const char *, uint64_t, const char *);
- void fsi_close_fsimage(fsi_t *);
- 
-diff --git a/tools/pygrub/src/fsimage/fsimage.c b/tools/pygrub/src/fsimage/fsimage.c
-index 2ebbbe35df92..92fbf2851f01 100644
---- a/tools/pygrub/src/fsimage/fsimage.c
-+++ b/tools/pygrub/src/fsimage/fsimage.c
-@@ -286,6 +286,15 @@ fsimage_getbootstring(PyObject *o, PyObject *args)
- 	return Py_BuildValue("s", bootstring);
- }
- 
-+static PyObject *
-+fsimage_init(PyObject *o, PyObject *args)
-+{
-+	if (!PyArg_ParseTuple(args, ""))
-+		return (NULL);
-+
-+	return Py_BuildValue("i", fsi_init());
-+}
-+
- PyDoc_STRVAR(fsimage_open__doc__,
-     "open(name, [offset=off]) - Open the given file as a filesystem image.\n"
-     "\n"
-@@ -297,7 +306,13 @@ PyDoc_STRVAR(fsimage_getbootstring__doc__,
-     "getbootstring(fs) - Return the boot string needed for this file system "
-     "or NULL if none is needed.\n");
- 
-+PyDoc_STRVAR(fsimage_init__doc__,
-+    "init() - Loads every dynamic library contained in xenfsimage "
-+    "into memory so that it can be used in chrooted environments.\n");
-+
- static struct PyMethodDef fsimage_module_methods[] = {
-+	{ "init", (PyCFunction)fsimage_init,
-+	    METH_VARARGS, fsimage_init__doc__ },
- 	{ "open", (PyCFunction)fsimage_open,
- 	    METH_VARARGS|METH_KEYWORDS, fsimage_open__doc__ },
- 	{ "getbootstring", (PyCFunction)fsimage_getbootstring,
--- 
-2.42.0
-

xsa443-4.17-09.patch

@@ -1,307 +0,0 @@
-From 150771ce86a07e469e34941a63c56e2cf242223b Mon Sep 17 00:00:00 2001
-From: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Date: Mon, 25 Sep 2023 18:32:25 +0100
-Subject: [PATCH 09/11] tools/pygrub: Deprivilege pygrub
-
-Introduce a --runas=<uid> flag to deprivilege pygrub on Linux and *BSDs. It
-also implicitly creates a chroot env where it drops a deprivileged forked
-process. The chroot itself is cleaned up at the end.
-
-If the --runas arg is present, then pygrub forks, leaving the child to
-deprivilege itself, and waiting for it to complete. When the child exists,
-the parent performs cleanup and exits with the same error code.
-
-This is roughly what the child does:
-  1. Initialize libfsimage (this loads every .so in memory so the chroot
-     can avoid bind-mounting /{,usr}/lib*
-  2. Create a temporary empty chroot directory
-  3. Mount tmpfs in it
-  4. Bind mount the disk inside, because libfsimage expects a path, not a
-     file descriptor.
-  5. Remount the root tmpfs to be stricter (ro,nosuid,nodev)
-  6. Set RLIMIT_FSIZE to a sensibly high amount (128 MiB)
-  7. Depriv gid, groups and uid
-
-With this scheme in place, the "output" files are writable (up to
-RLIMIT_FSIZE octets) and the exposed filesystem is immutable and contains
-the single only file we can't easily get rid of (the disk).
-
-If running on Linux, the child process also unshares mount, IPC, and
-network namespaces before dropping its privileges.
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
-Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
----
- tools/pygrub/setup.py   |   2 +-
- tools/pygrub/src/pygrub | 162 +++++++++++++++++++++++++++++++++++++---
- 2 files changed, 154 insertions(+), 10 deletions(-)
-
-diff --git a/tools/pygrub/setup.py b/tools/pygrub/setup.py
-index 0e4e3d02d372..06b96733d020 100644
---- a/tools/pygrub/setup.py
-+++ b/tools/pygrub/setup.py
-@@ -17,7 +17,7 @@ xenfsimage = Extension("xenfsimage",
- pkgs = [ 'grub' ]
- 
- setup(name='pygrub',
--      version='0.6',
-+      version='0.7',
-       description='Boot loader that looks a lot like grub for Xen',
-       author='Jeremy Katz',
-       author_email='katzj@redhat.com',
-diff --git a/tools/pygrub/src/pygrub b/tools/pygrub/src/pygrub
-index 91e2ec2ab105..7cea496ade08 100755
---- a/tools/pygrub/src/pygrub
-+++ b/tools/pygrub/src/pygrub
-@@ -16,8 +16,11 @@ from __future__ import print_function
- 
- import os, sys, string, struct, tempfile, re, traceback, stat, errno
- import copy
-+import ctypes, ctypes.util
- import logging
- import platform
-+import resource
-+import subprocess
- 
- import curses, _curses, curses.textpad, curses.ascii
- import getopt
-@@ -27,10 +30,135 @@ import grub.GrubConf
- import grub.LiloConf
- import grub.ExtLinuxConf
- 
--PYGRUB_VER = 0.6
-+PYGRUB_VER = 0.7
- FS_READ_MAX = 1024 * 1024
- SECTOR_SIZE = 512
- 
-+# Unless provided through the env variable PYGRUB_MAX_FILE_SIZE_MB, then
-+# this is the maximum filesize allowed for files written by the depriv
-+# pygrub
-+LIMIT_FSIZE = 128 << 20
-+
-+CLONE_NEWNS = 0x00020000 # mount namespace
-+CLONE_NEWNET = 0x40000000 # network namespace
-+CLONE_NEWIPC = 0x08000000 # IPC namespace
-+
-+def unshare(flags):
-+    if not sys.platform.startswith("linux"):
-+        print("skip_unshare reason=not_linux platform=%s", sys.platform, file=sys.stderr)
-+        return
-+
-+    libc = ctypes.CDLL(ctypes.util.find_library('c'), use_errno=True)
-+    unshare_prototype = ctypes.CFUNCTYPE(ctypes.c_int, ctypes.c_int, use_errno=True)
-+    unshare = unshare_prototype(('unshare', libc))
-+
-+    if unshare(flags) < 0:
-+        raise OSError(ctypes.get_errno(), os.strerror(ctypes.get_errno()))
-+
-+def bind_mount(src, dst, options):
-+    open(dst, "a").close() # touch
-+
-+    rc = subprocess.call(["mount", "--bind", "-o", options, src, dst])
-+    if rc != 0:
-+        raise RuntimeError("bad_mount: src=%s dst=%s opts=%s" %
-+                           (src, dst, options))
-+
-+def downgrade_rlimits():
-+    # Wipe the authority to use unrequired resources
-+    resource.setrlimit(resource.RLIMIT_NPROC,    (0, 0))
-+    resource.setrlimit(resource.RLIMIT_CORE,     (0, 0))
-+    resource.setrlimit(resource.RLIMIT_MEMLOCK,  (0, 0))
-+
-+    # py2's resource module doesn't know about resource.RLIMIT_MSGQUEUE
-+    #
-+    # TODO: Use resource.RLIMIT_MSGQUEUE after python2 is deprecated
-+    if sys.platform.startswith('linux'):
-+        RLIMIT_MSGQUEUE = 12
-+        resource.setrlimit(RLIMIT_MSGQUEUE, (0, 0))
-+
-+    # The final look of the filesystem for this process is fully RO, but
-+    # note we have some file descriptor already open (notably, kernel and
-+    # ramdisk). In order to avoid a compromised pygrub from filling up the
-+    # filesystem we set RLIMIT_FSIZE to a high bound, so that the file
-+    # write permissions are bound.
-+    fsize = LIMIT_FSIZE
-+    if "PYGRUB_MAX_FILE_SIZE_MB" in os.environ.keys():
-+        fsize = os.environ["PYGRUB_MAX_FILE_SIZE_MB"] << 20
-+
-+    resource.setrlimit(resource.RLIMIT_FSIZE, (fsize, fsize))
-+
-+def depriv(output_directory, output, device, uid, path_kernel, path_ramdisk):
-+    # The only point of this call is to force the loading of libfsimage.
-+    # That way, we don't need to bind-mount it into the chroot
-+    rc = xenfsimage.init()
-+    if rc != 0:
-+        os.unlink(path_ramdisk)
-+        os.unlink(path_kernel)
-+        raise RuntimeError("bad_xenfsimage: rc=%d" % rc)
-+
-+    # Create a temporary directory for the chroot
-+    chroot = tempfile.mkdtemp(prefix=str(uid)+'-', dir=output_directory) + '/'
-+    device_path = '/device'
-+
-+    pid = os.fork()
-+    if pid:
-+        # parent
-+        _, rc = os.waitpid(pid, 0)
-+
-+        for path in [path_kernel, path_ramdisk]:
-+            # If the child didn't write anything, just get rid of it,
-+            # otherwise we end up consuming a 0-size file when parsing
-+            # systems without a ramdisk that the ultimate caller of pygrub
-+            # may just be unaware of
-+            if rc != 0 or os.path.getsize(path) == 0:
-+                os.unlink(path)
-+
-+        # Normally, unshare(CLONE_NEWNS) will ensure this is not required.
-+        # However, this syscall doesn't exist in *BSD systems and doesn't
-+        # auto-unmount everything on older Linux kernels (At least as of
-+        # Linux 4.19, but it seems fixed in 5.15). Either way,
-+        # recursively unmount everything if needed. Quietly.
-+        with open('/dev/null', 'w') as devnull:
-+            subprocess.call(["umount", "-f", chroot + device_path],
-+                            stdout=devnull, stderr=devnull)
-+            subprocess.call(["umount", "-f", chroot],
-+                            stdout=devnull, stderr=devnull)
-+        os.rmdir(chroot)
-+
-+        sys.exit(rc)
-+
-+    # By unsharing the namespace we're making sure it's all bulk-released
-+    # at the end, when the namespaces disappear. This means the kernel does
-+    # (almost) all the cleanup for us and the parent just has to remove the
-+    # temporary directory.
-+    unshare(CLONE_NEWNS | CLONE_NEWIPC | CLONE_NEWNET)
-+
-+    # Set sensible limits using the setrlimit interface
-+    downgrade_rlimits()
-+
-+    # We'll mount tmpfs on the chroot to ensure the deprivileged child
-+    # cannot affect the persistent state. It's RW now in order to
-+    # bind-mount the device, but note it's remounted RO after that.
-+    rc = subprocess.call(["mount", "-t", "tmpfs", "none", chroot])
-+    if rc != 0:
-+        raise RuntimeError("mount_tmpfs rc=%d dst=\"%s\"" % (rc, chroot))
-+
-+    # Bind the untrusted device RO
-+    bind_mount(device, chroot + device_path, "ro,nosuid,noexec")
-+
-+    rc = subprocess.call(["mount", "-t", "tmpfs", "-o", "remount,ro,nosuid,noexec,nodev", "none", chroot])
-+    if rc != 0:
-+        raise RuntimeError("remount_tmpfs rc=%d dst=\"%s\"" % (rc, chroot))
-+
-+    # Drop superpowers!
-+    os.chroot(chroot)
-+    os.chdir('/')
-+    os.setgid(uid)
-+    os.setgroups([uid])
-+    os.setuid(uid)
-+
-+    return device_path
-+
- def read_size_roundup(fd, size):
-     if platform.system() != 'FreeBSD':
-         return size
-@@ -736,7 +864,7 @@ if __name__ == "__main__":
-     sel = None
-     
-     def usage():
--        print("Usage: %s [-q|--quiet] [-i|--interactive] [-l|--list-entries] [-n|--not-really] [--output=] [--kernel=] [--ramdisk=] [--args=] [--entry=] [--output-directory=] [--output-format=sxp|simple|simple0] [--offset=] <image>" %(sys.argv[0],), file=sys.stderr)
-+        print("Usage: %s [-q|--quiet] [-i|--interactive] [-l|--list-entries] [-n|--not-really] [--output=] [--kernel=] [--ramdisk=] [--args=] [--entry=] [--output-directory=] [--output-format=sxp|simple|simple0] [--runas=] [--offset=] <image>" %(sys.argv[0],), file=sys.stderr)
- 
-     def copy_from_image(fs, file_to_read, file_type, fd_dst, path_dst, not_really):
-         if not_really:
-@@ -760,7 +888,8 @@ if __name__ == "__main__":
-                 os.write(fd_dst, data)
-             except Exception as e:
-                 print(e, file=sys.stderr)
--                os.unlink(path_dst)
-+                if path_dst:
-+                    os.unlink(path_dst)
-                 del datafile
-                 sys.exit("Error writing temporary copy of "+file_type)
-             dataoff += len(data)
-@@ -769,7 +898,7 @@ if __name__ == "__main__":
-         opts, args = getopt.gnu_getopt(sys.argv[1:], 'qilnh::',
-                                    ["quiet", "interactive", "list-entries", "not-really", "help",
-                                     "output=", "output-format=", "output-directory=", "offset=",
--                                    "entry=", "kernel=", 
-+                                    "runas=", "entry=", "kernel=",
-                                     "ramdisk=", "args=", "isconfig", "debug"])
-     except getopt.GetoptError:
-         usage()
-@@ -790,6 +919,7 @@ if __name__ == "__main__":
-     not_really = False
-     output_format = "sxp"
-     output_directory = "/var/run/xen/pygrub/"
-+    uid = None
- 
-     # what was passed in
-     incfg = { "kernel": None, "ramdisk": None, "args": "" }
-@@ -813,6 +943,13 @@ if __name__ == "__main__":
-         elif o in ("--output",):
-             if a != "-":
-                 output = a
-+        elif o in ("--runas",):
-+            try:
-+                uid = int(a)
-+            except ValueError:
-+                print("runas value must be an integer user id")
-+                usage()
-+                sys.exit(1)
-         elif o in ("--kernel",):
-             incfg["kernel"] = a
-         elif o in ("--ramdisk",):
-@@ -849,6 +986,10 @@ if __name__ == "__main__":
-     if debug:
-         logging.basicConfig(level=logging.DEBUG)
- 
-+    if interactive and uid:
-+        print("In order to use --runas, you must also set --entry or -q", file=sys.stderr)
-+        sys.exit(1)
-+
-     try:
-         os.makedirs(output_directory, 0o700)
-     except OSError as e:
-@@ -870,6 +1011,9 @@ if __name__ == "__main__":
-     else:
-         fd = os.open(output, os.O_WRONLY)
- 
-+    if uid:
-+        file = depriv(output_directory, output, file, uid, path_kernel, path_ramdisk)
-+
-     # debug
-     if isconfig:
-         chosencfg = run_grub(file, entry, fs, incfg["args"])
-@@ -925,21 +1069,21 @@ if __name__ == "__main__":
-         raise RuntimeError("Unable to find partition containing kernel")
- 
-     copy_from_image(fs, chosencfg["kernel"], "kernel",
--                    fd_kernel, path_kernel, not_really)
-+                    fd_kernel, None if uid else path_kernel, not_really)
-     bootcfg["kernel"] = path_kernel
- 
-     if chosencfg["ramdisk"]:
-         try:
-             copy_from_image(fs, chosencfg["ramdisk"], "ramdisk",
--                            fd_ramdisk, path_ramdisk, not_really)
-+                            fd_ramdisk, None if uid else path_ramdisk, not_really)
-         except:
--            if not not_really:
--                os.unlink(path_kernel)
-+            if not uid and not not_really:
-+                    os.unlink(path_kernel)
-             raise
-         bootcfg["ramdisk"] = path_ramdisk
-     else:
-         initrd = None
--        if not not_really:
-+        if not uid and not not_really:
-             os.unlink(path_ramdisk)
- 
-     args = None
--- 
-2.42.0
-

xsa443-4.17-10.patch

@@ -1,250 +0,0 @@
-From 698b451473a6d868ca0f60a124fc4f31d81cd7b1 Mon Sep 17 00:00:00 2001
-From: Roger Pau Monne <roger.pau@citrix.com>
-Date: Mon, 25 Sep 2023 14:30:20 +0200
-Subject: [PATCH 10/11] libxl: add support for running bootloader in restricted
- mode
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Much like the device model depriv mode, add the same kind of support for the
-bootloader.  Such feature allows passing a UID as a parameter for the
-bootloader to run as, together with the bootloader itself taking the necessary
-actions to isolate.
-
-Note that the user to run the bootloader as must have the right permissions to
-access the guest disk image (in read mode only), and that the bootloader will
-be run in non-interactive mode when restricted.
-
-If enabled bootloader restrict mode will attempt to re-use the user(s) from the
-QEMU depriv implementation if no user is provided on the configuration file or
-the environment.  See docs/features/qemu-deprivilege.pandoc for more
-information about how to setup those users.
-
-Bootloader restrict mode is not enabled by default as it requires certain
-setup to be done first (setup of the user(s) to use in restrict mode).
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
-Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
----
- docs/man/xl.1.pod.in                | 33 +++++++++++
- tools/libs/light/libxl_bootloader.c | 89 ++++++++++++++++++++++++++++-
- tools/libs/light/libxl_dm.c         |  8 +--
- tools/libs/light/libxl_internal.h   |  8 +++
- 4 files changed, 131 insertions(+), 7 deletions(-)
-
-diff --git a/docs/man/xl.1.pod.in b/docs/man/xl.1.pod.in
-index 101e14241d1c..4831e122427d 100644
---- a/docs/man/xl.1.pod.in
-+++ b/docs/man/xl.1.pod.in
-@@ -1957,6 +1957,39 @@ ignored:
- 
- =back
- 
-+=head1 ENVIRONMENT VARIABLES
-+
-+The following environment variables shall affect the execution of xl:
-+
-+=over 4
-+
-+=item LIBXL_BOOTLOADER_RESTRICT
-+
-+Attempt to restrict the bootloader after startup, to limit the
-+consequences of security vulnerabilities due to parsing guest
-+owned image files.
-+
-+See docs/features/qemu-deprivilege.pandoc for more information
-+on how to setup the unprivileged users.
-+
-+Note that running the bootloader in restricted mode also implies using
-+non-interactive mode, and the disk image must be readable by the
-+restricted user.
-+
-+Having this variable set is equivalent to enabling the option, even if the
-+value is 0.
-+
-+=item LIBXL_BOOTLOADER_USER
-+
-+When using bootloader_restrict, run the bootloader as this user.  If
-+not set the default QEMU restrict users will be used.
-+
-+NOTE: Each domain MUST have a SEPARATE username.
-+
-+See docs/features/qemu-deprivilege.pandoc for more information.
-+
-+=back
-+
- =head1 SEE ALSO
- 
- The following man pages:
-diff --git a/tools/libs/light/libxl_bootloader.c b/tools/libs/light/libxl_bootloader.c
-index 108329b4a5bb..23c0ef3e8935 100644
---- a/tools/libs/light/libxl_bootloader.c
-+++ b/tools/libs/light/libxl_bootloader.c
-@@ -14,6 +14,7 @@
- 
- #include "libxl_osdeps.h" /* must come before any other headers */
- 
-+#include <pwd.h>
- #include <termios.h>
- #ifdef HAVE_UTMP_H
- #include <utmp.h>
-@@ -42,8 +43,71 @@ static void bootloader_arg(libxl__bootloader_state *bl, const char *arg)
-     bl->args[bl->nargs++] = arg;
- }
- 
--static void make_bootloader_args(libxl__gc *gc, libxl__bootloader_state *bl,
--                                 const char *bootloader_path)
-+static int bootloader_uid(libxl__gc *gc, domid_t guest_domid,
-+                          const char *user, uid_t *intended_uid)
-+{
-+    struct passwd *user_base, user_pwbuf;
-+    int rc;
-+
-+    if (user) {
-+        rc = userlookup_helper_getpwnam(gc, user, &user_pwbuf, &user_base);
-+        if (rc) return rc;
-+
-+        if (!user_base) {
-+            LOGD(ERROR, guest_domid, "Couldn't find user %s", user);
-+            return ERROR_INVAL;
-+        }
-+
-+        *intended_uid = user_base->pw_uid;
-+        return 0;
-+    }
-+
-+    /* Re-use QEMU user range for the bootloader. */
-+    rc = userlookup_helper_getpwnam(gc, LIBXL_QEMU_USER_RANGE_BASE,
-+                                    &user_pwbuf, &user_base);
-+    if (rc) return rc;
-+
-+    if (user_base) {
-+        struct passwd *user_clash, user_clash_pwbuf;
-+        uid_t temp_uid = user_base->pw_uid + guest_domid;
-+
-+        rc = userlookup_helper_getpwuid(gc, temp_uid, &user_clash_pwbuf,
-+                                        &user_clash);
-+        if (rc) return rc;
-+
-+        if (user_clash) {
-+            LOGD(ERROR, guest_domid,
-+                 "wanted to use uid %ld (%s + %d) but that is user %s !",
-+                 (long)temp_uid, LIBXL_QEMU_USER_RANGE_BASE,
-+                 guest_domid, user_clash->pw_name);
-+            return ERROR_INVAL;
-+        }
-+
-+        *intended_uid = temp_uid;
-+        return 0;
-+    }
-+
-+    rc = userlookup_helper_getpwnam(gc, LIBXL_QEMU_USER_SHARED, &user_pwbuf,
-+                                    &user_base);
-+    if (rc) return rc;
-+
-+    if (user_base) {
-+        LOGD(WARN, guest_domid, "Could not find user %s, falling back to %s",
-+             LIBXL_QEMU_USER_RANGE_BASE, LIBXL_QEMU_USER_SHARED);
-+        *intended_uid = user_base->pw_uid;
-+
-+        return 0;
-+    }
-+
-+    LOGD(ERROR, guest_domid,
-+    "Could not find user %s or range base pseudo-user %s, cannot restrict",
-+         LIBXL_QEMU_USER_SHARED, LIBXL_QEMU_USER_RANGE_BASE);
-+
-+    return ERROR_INVAL;
-+}
-+
-+static int make_bootloader_args(libxl__gc *gc, libxl__bootloader_state *bl,
-+                                const char *bootloader_path)
- {
-     const libxl_domain_build_info *info = bl->info;
- 
-@@ -61,6 +125,23 @@ static void make_bootloader_args(libxl__gc *gc, libxl__bootloader_state *bl,
-         ARG(GCSPRINTF("--ramdisk=%s", info->ramdisk));
-     if (info->cmdline && *info->cmdline != '\0')
-         ARG(GCSPRINTF("--args=%s", info->cmdline));
-+    if (getenv("LIBXL_BOOTLOADER_RESTRICT") ||
-+        getenv("LIBXL_BOOTLOADER_USER")) {
-+        uid_t uid = -1;
-+        int rc = bootloader_uid(gc, bl->domid, getenv("LIBXL_BOOTLOADER_USER"),
-+                                &uid);
-+
-+        if (rc) return rc;
-+
-+        assert(uid != -1);
-+        if (!uid) {
-+            LOGD(ERROR, bl->domid, "bootloader restrict UID is 0 (root)!");
-+            return ERROR_INVAL;
-+        }
-+        LOGD(DEBUG, bl->domid, "using uid %ld", (long)uid);
-+        ARG(GCSPRINTF("--runas=%ld", (long)uid));
-+        ARG("--quiet");
-+    }
- 
-     ARG(GCSPRINTF("--output=%s", bl->outputpath));
-     ARG("--output-format=simple0");
-@@ -79,6 +160,7 @@ static void make_bootloader_args(libxl__gc *gc, libxl__bootloader_state *bl,
-     /* Sentinel for execv */
-     ARG(NULL);
- 
-+    return 0;
- #undef ARG
- }
- 
-@@ -443,7 +525,8 @@ static void bootloader_disk_attached_cb(libxl__egc *egc,
-             bootloader = bltmp;
-     }
- 
--    make_bootloader_args(gc, bl, bootloader);
-+    rc = make_bootloader_args(gc, bl, bootloader);
-+    if (rc) goto out;
- 
-     bl->openpty.ao = ao;
-     bl->openpty.callback = bootloader_gotptys;
-diff --git a/tools/libs/light/libxl_dm.c b/tools/libs/light/libxl_dm.c
-index fc264a3a13a6..14b593110f7c 100644
---- a/tools/libs/light/libxl_dm.c
-+++ b/tools/libs/light/libxl_dm.c
-@@ -80,10 +80,10 @@ static int libxl__create_qemu_logfile(libxl__gc *gc, char *name)
-  *  On error, return a libxl-style error code.
-  */
- #define DEFINE_USERLOOKUP_HELPER(NAME,SPEC_TYPE,STRUCTNAME,SYSCONF)     \
--    static int userlookup_helper_##NAME(libxl__gc *gc,                  \
--                                        SPEC_TYPE spec,                 \
--                                        struct STRUCTNAME *resultbuf,   \
--                                        struct STRUCTNAME **out)        \
-+    int userlookup_helper_##NAME(libxl__gc *gc,                         \
-+                                 SPEC_TYPE spec,                        \
-+                                 struct STRUCTNAME *resultbuf,          \
-+                                 struct STRUCTNAME **out)               \
-     {                                                                   \
-         struct STRUCTNAME *resultp = NULL;                              \
-         char *buf = NULL;                                               \
-diff --git a/tools/libs/light/libxl_internal.h b/tools/libs/light/libxl_internal.h
-index 7ad38de30e0b..f1e3a9a15b13 100644
---- a/tools/libs/light/libxl_internal.h
-+++ b/tools/libs/light/libxl_internal.h
-@@ -4873,6 +4873,14 @@ struct libxl__cpu_policy {
-     struct xc_msr *msr;
- };
- 
-+struct passwd;
-+_hidden int userlookup_helper_getpwnam(libxl__gc*, const char *user,
-+                                       struct passwd *res,
-+                                       struct passwd **out);
-+_hidden int userlookup_helper_getpwuid(libxl__gc*, uid_t uid,
-+                                       struct passwd *res,
-+                                       struct passwd **out);
-+
- #endif
- 
- /*
--- 
-2.42.0
-

xsa443-4.17-11.patch

@@ -1,157 +0,0 @@
-From 9d480426bfa2c68843ac8395b512e06fbdbcf53e Mon Sep 17 00:00:00 2001
-From: Roger Pau Monne <roger.pau@citrix.com>
-Date: Thu, 28 Sep 2023 12:22:35 +0200
-Subject: [PATCH 11/11] libxl: limit bootloader execution in restricted mode
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Introduce a timeout for bootloader execution when running in restricted mode.
-
-Allow overwriting the default time out with an environment provided value.
-
-This is part of XSA-443 / CVE-2023-34325
-
-Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
-Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
----
- docs/man/xl.1.pod.in                |  8 ++++++
- tools/libs/light/libxl_bootloader.c | 40 +++++++++++++++++++++++++++++
- tools/libs/light/libxl_internal.h   |  2 ++
- 3 files changed, 50 insertions(+)
-
-diff --git a/docs/man/xl.1.pod.in b/docs/man/xl.1.pod.in
-index 4831e122427d..c3eb6570ab8b 100644
---- a/docs/man/xl.1.pod.in
-+++ b/docs/man/xl.1.pod.in
-@@ -1988,6 +1988,14 @@ NOTE: Each domain MUST have a SEPARATE username.
- 
- See docs/features/qemu-deprivilege.pandoc for more information.
- 
-+=item LIBXL_BOOTLOADER_TIMEOUT
-+
-+Timeout in seconds for bootloader execution when running in restricted mode.
-+Otherwise the build time default in LIBXL_BOOTLOADER_TIMEOUT will be used.
-+
-+If defined the value must be an unsigned integer between 0 and INT_MAX,
-+otherwise behavior is undefined.  Setting to 0 disables the timeout.
-+
- =back
- 
- =head1 SEE ALSO
-diff --git a/tools/libs/light/libxl_bootloader.c b/tools/libs/light/libxl_bootloader.c
-index 23c0ef3e8935..ee26d08f3765 100644
---- a/tools/libs/light/libxl_bootloader.c
-+++ b/tools/libs/light/libxl_bootloader.c
-@@ -30,6 +30,8 @@ static void bootloader_keystrokes_copyfail(libxl__egc *egc,
-        libxl__datacopier_state *dc, int rc, int onwrite, int errnoval);
- static void bootloader_display_copyfail(libxl__egc *egc,
-        libxl__datacopier_state *dc, int rc, int onwrite, int errnoval);
-+static void bootloader_timeout(libxl__egc *egc, libxl__ev_time *ev,
-+                               const struct timeval *requested_abs, int rc);
- static void bootloader_domaindeath(libxl__egc*, libxl__domaindeathcheck *dc,
-                                    int rc);
- static void bootloader_finished(libxl__egc *egc, libxl__ev_child *child,
-@@ -297,6 +299,7 @@ void libxl__bootloader_init(libxl__bootloader_state *bl)
-     bl->ptys[0].master = bl->ptys[0].slave = 0;
-     bl->ptys[1].master = bl->ptys[1].slave = 0;
-     libxl__ev_child_init(&bl->child);
-+    libxl__ev_time_init(&bl->time);
-     libxl__domaindeathcheck_init(&bl->deathcheck);
-     bl->keystrokes.ao = bl->ao;  libxl__datacopier_init(&bl->keystrokes);
-     bl->display.ao = bl->ao;     libxl__datacopier_init(&bl->display);
-@@ -314,6 +317,7 @@ static void bootloader_cleanup(libxl__egc *egc, libxl__bootloader_state *bl)
-     libxl__domaindeathcheck_stop(gc,&bl->deathcheck);
-     libxl__datacopier_kill(&bl->keystrokes);
-     libxl__datacopier_kill(&bl->display);
-+    libxl__ev_time_deregister(gc, &bl->time);
-     for (i=0; i<2; i++) {
-         libxl__carefd_close(bl->ptys[i].master);
-         libxl__carefd_close(bl->ptys[i].slave);
-@@ -375,6 +379,7 @@ static void bootloader_stop(libxl__egc *egc,
- 
-     libxl__datacopier_kill(&bl->keystrokes);
-     libxl__datacopier_kill(&bl->display);
-+    libxl__ev_time_deregister(gc, &bl->time);
-     if (libxl__ev_child_inuse(&bl->child)) {
-         r = kill(bl->child.pid, SIGTERM);
-         if (r) LOGED(WARN, bl->domid, "%sfailed to kill bootloader [%lu]",
-@@ -637,6 +642,25 @@ static void bootloader_gotptys(libxl__egc *egc, libxl__openpty_state *op)
- 
-     struct termios termattr;
- 
-+    if (getenv("LIBXL_BOOTLOADER_RESTRICT") ||
-+        getenv("LIBXL_BOOTLOADER_USER")) {
-+        const char *timeout_env = getenv("LIBXL_BOOTLOADER_TIMEOUT");
-+        int timeout = timeout_env ? atoi(timeout_env)
-+                                  : LIBXL_BOOTLOADER_TIMEOUT;
-+
-+        if (timeout) {
-+            /* Set execution timeout */
-+            rc = libxl__ev_time_register_rel(ao, &bl->time,
-+                                            bootloader_timeout,
-+                                            timeout * 1000);
-+            if (rc) {
-+                LOGED(ERROR, bl->domid,
-+                      "unable to register timeout for bootloader execution");
-+                goto out;
-+            }
-+        }
-+    }
-+
-     pid_t pid = libxl__ev_child_fork(gc, &bl->child, bootloader_finished);
-     if (pid == -1) {
-         rc = ERROR_FAIL;
-@@ -702,6 +726,21 @@ static void bootloader_display_copyfail(libxl__egc *egc,
-     libxl__bootloader_state *bl = CONTAINER_OF(dc, *bl, display);
-     bootloader_copyfail(egc, "bootloader output", bl, 1, rc,onwrite,errnoval);
- }
-+static void bootloader_timeout(libxl__egc *egc, libxl__ev_time *ev,
-+                               const struct timeval *requested_abs, int rc)
-+{
-+    libxl__bootloader_state *bl = CONTAINER_OF(ev, *bl, time);
-+    STATE_AO_GC(bl->ao);
-+
-+    libxl__ev_time_deregister(gc, &bl->time);
-+
-+    assert(libxl__ev_child_inuse(&bl->child));
-+    LOGD(ERROR, bl->domid, "killing bootloader because of timeout");
-+
-+    libxl__ev_child_kill_deregister(ao, &bl->child, SIGKILL);
-+
-+    bootloader_callback(egc, bl, rc);
-+}
- 
- static void bootloader_domaindeath(libxl__egc *egc,
-                                    libxl__domaindeathcheck *dc,
-@@ -718,6 +757,7 @@ static void bootloader_finished(libxl__egc *egc, libxl__ev_child *child,
-     STATE_AO_GC(bl->ao);
-     int rc;
- 
-+    libxl__ev_time_deregister(gc, &bl->time);
-     libxl__datacopier_kill(&bl->keystrokes);
-     libxl__datacopier_kill(&bl->display);
- 
-diff --git a/tools/libs/light/libxl_internal.h b/tools/libs/light/libxl_internal.h
-index f1e3a9a15b13..d05783617ff5 100644
---- a/tools/libs/light/libxl_internal.h
-+++ b/tools/libs/light/libxl_internal.h
-@@ -102,6 +102,7 @@
- #define LIBXL_QMP_CMD_TIMEOUT 10
- #define LIBXL_STUBDOM_START_TIMEOUT 30
- #define LIBXL_QEMU_BODGE_TIMEOUT 2
-+#define LIBXL_BOOTLOADER_TIMEOUT 120
- #define LIBXL_XENCONSOLE_LIMIT 1048576
- #define LIBXL_XENCONSOLE_PROTOCOL "vt100"
- #define LIBXL_MAXMEM_CONSTANT 1024
-@@ -3744,6 +3745,7 @@ struct libxl__bootloader_state {
-     libxl__openpty_state openpty;
-     libxl__openpty_result ptys[2];  /* [0] is for bootloader */
-     libxl__ev_child child;
-+    libxl__ev_time time;
-     libxl__domaindeathcheck deathcheck;
-     int nargs, argsspace;
-     const char **args;
--- 
-2.42.0
-

xsa444-4.17-1.patch

@@ -1,93 +0,0 @@
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Subject: x86/svm: Fix asymmetry with AMD DR MASK context switching
-
-The handling of MSR_DR{0..3}_MASK is asymmetric between PV and HVM guests.
-
-HVM guests context switch in based on the guest view of DBEXT, whereas PV
-guest switch in base on the host capability.  Both guest types leave the
-context dirty for the next vCPU.
-
-This leads to the following issue:
-
- * PV or HVM guest has debugging active (%dr7 + mask)
- * Switch-out deactivates %dr7 but leaves other state stale in hardware
- * Another HVM guest with masks unavailable has debugging active
- * Switch in loads %dr7 but leaves the mask MSRs alone
-
-Now, the second guest's vCPU is operating in the context of the prior vCPU's
-mask MSR, while the environment the vCPU can see says there are no mask MSRs.
-
-As a stopgap, adjust the HVM path to switch in the masks based on host
-capabilities rather than guest visibility (i.e. like the PV path).  Adjustment
-of the intercepts still needs to be dependent on the guest visibility of
-DBEXT.
-
-This is part of XSA-444 / CVE-2023-34327
-
-Fixes: c097f54912d3 ("x86/SVM: support data breakpoint extension registers")
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-
-diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c
-index e8f50e7c5ec7..fd32600ae364 100644
---- a/xen/arch/x86/hvm/svm/svm.c
-+++ b/xen/arch/x86/hvm/svm/svm.c
-@@ -339,6 +339,10 @@ static void svm_save_dr(struct vcpu *v)
-     v->arch.hvm.flag_dr_dirty = 0;
-     vmcb_set_dr_intercepts(vmcb, ~0u);
- 
-+    /*
-+     * The guest can only have changed the mask MSRs if we previous dropped
-+     * intercepts.  Re-read them from hardware.
-+     */
-     if ( v->domain->arch.cpuid->extd.dbext )
-     {
-         svm_intercept_msr(v, MSR_AMD64_DR0_ADDRESS_MASK, MSR_INTERCEPT_RW);
-@@ -370,17 +374,25 @@ static void __restore_debug_registers(struct vmcb_struct *vmcb, struct vcpu *v)
- 
-     ASSERT(v == current);
- 
--    if ( v->domain->arch.cpuid->extd.dbext )
-+    /*
-+     * Both the PV and HVM paths leave stale DR_MASK values in hardware on
-+     * context-switch-out.  If we're activating %dr7 for the guest, we must
-+     * sync the DR_MASKs too, whether or not the guest can see them.
-+     */
-+    if ( boot_cpu_has(X86_FEATURE_DBEXT) )
-     {
--        svm_intercept_msr(v, MSR_AMD64_DR0_ADDRESS_MASK, MSR_INTERCEPT_NONE);
--        svm_intercept_msr(v, MSR_AMD64_DR1_ADDRESS_MASK, MSR_INTERCEPT_NONE);
--        svm_intercept_msr(v, MSR_AMD64_DR2_ADDRESS_MASK, MSR_INTERCEPT_NONE);
--        svm_intercept_msr(v, MSR_AMD64_DR3_ADDRESS_MASK, MSR_INTERCEPT_NONE);
--
-         wrmsrl(MSR_AMD64_DR0_ADDRESS_MASK, v->arch.msrs->dr_mask[0]);
-         wrmsrl(MSR_AMD64_DR1_ADDRESS_MASK, v->arch.msrs->dr_mask[1]);
-         wrmsrl(MSR_AMD64_DR2_ADDRESS_MASK, v->arch.msrs->dr_mask[2]);
-         wrmsrl(MSR_AMD64_DR3_ADDRESS_MASK, v->arch.msrs->dr_mask[3]);
-+
-+        if ( v->domain->arch.cpuid->extd.dbext )
-+        {
-+            svm_intercept_msr(v, MSR_AMD64_DR0_ADDRESS_MASK, MSR_INTERCEPT_NONE);
-+            svm_intercept_msr(v, MSR_AMD64_DR1_ADDRESS_MASK, MSR_INTERCEPT_NONE);
-+            svm_intercept_msr(v, MSR_AMD64_DR2_ADDRESS_MASK, MSR_INTERCEPT_NONE);
-+            svm_intercept_msr(v, MSR_AMD64_DR3_ADDRESS_MASK, MSR_INTERCEPT_NONE);
-+        }
-     }
- 
-     write_debugreg(0, v->arch.dr[0]);
-diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
-index e65cc6004148..06c4f3868b7a 100644
---- a/xen/arch/x86/traps.c
-+++ b/xen/arch/x86/traps.c
-@@ -2281,6 +2281,11 @@ void activate_debugregs(const struct vcpu *curr)
-     if ( curr->arch.dr7 & DR7_ACTIVE_MASK )
-         write_debugreg(7, curr->arch.dr7);
- 
-+    /*
-+     * Both the PV and HVM paths leave stale DR_MASK values in hardware on
-+     * context-switch-out.  If we're activating %dr7 for the guest, we must
-+     * sync the DR_MASKs too, whether or not the guest can see them.
-+     */
-     if ( boot_cpu_has(X86_FEATURE_DBEXT) )
-     {
-         wrmsrl(MSR_AMD64_DR0_ADDRESS_MASK, curr->arch.msrs->dr_mask[0]);

xsa444-4.17-2.patch

@@ -1,72 +0,0 @@
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Subject: x86/pv: Correct the auditing of guest breakpoint addresses
-
-The use of access_ok() is buggy, because it permits access to the compat
-translation area.  64bit PV guests don't use the XLAT area, but on AMD
-hardware, the DBEXT feature allows a breakpoint to match up to a 4G aligned
-region, allowing the breakpoint to reach outside of the XLAT area.
-
-Prior to c/s cda16c1bb223 ("x86: mirror compat argument translation area for
-32-bit PV"), the live GDT was within 4G of the XLAT area.
-
-All together, this allowed a malicious 64bit PV guest on AMD hardware to place
-a breakpoint over the live GDT, and trigger a #DB livelock (CVE-2015-8104).
-
-Introduce breakpoint_addr_ok() and explain why __addr_ok() happens to be an
-appropriate check in this case.
-
-For Xen 4.14 and later, this is a latent bug because the XLAT area has moved
-to be on its own with nothing interesting adjacent.  For Xen 4.13 and older on
-AMD hardware, this fixes a PV-trigger-able DoS.
-
-This is part of XSA-444 / CVE-2023-34328.
-
-Fixes: 65e355490817 ("x86/PV: support data breakpoint extension registers")
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
-
-diff --git a/xen/arch/x86/include/asm/debugreg.h b/xen/arch/x86/include/asm/debugreg.h
-index c57914efc6e8..cc298265244b 100644
---- a/xen/arch/x86/include/asm/debugreg.h
-+++ b/xen/arch/x86/include/asm/debugreg.h
-@@ -77,6 +77,26 @@
-     asm volatile ( "mov %%db" #reg ",%0" : "=r" (__val) );  \
-     __val;                                                  \
- })
-+
-+/*
-+ * Architecturally, %dr{0..3} can have any arbitrary value.  However, Xen
-+ * can't allow the guest to breakpoint the Xen address range, so we limit the
-+ * guest to the lower canonical half, or above the Xen range in the higher
-+ * canonical half.
-+ *
-+ * Breakpoint lengths are specified to mask the low order address bits,
-+ * meaning all breakpoints are naturally aligned.  With %dr7, the widest
-+ * breakpoint is 8 bytes.  With DBEXT, the widest breakpoint is 4G.  Both of
-+ * the Xen boundaries have >4G alignment.
-+ *
-+ * In principle we should account for HYPERVISOR_COMPAT_VIRT_START(d), but
-+ * 64bit Xen has never enforced this for compat guests, and there's no problem
-+ * (to Xen) if the guest breakpoints it's alias of the M2P.  Skipping this
-+ * aspect simplifies the logic, and causes us not to reject a migrating guest
-+ * which operated fine on prior versions of Xen.
-+ */
-+#define breakpoint_addr_ok(a) __addr_ok(a)
-+
- long set_debugreg(struct vcpu *, unsigned int reg, unsigned long value);
- void activate_debugregs(const struct vcpu *);
- 
-diff --git a/xen/arch/x86/pv/misc-hypercalls.c b/xen/arch/x86/pv/misc-hypercalls.c
-index aaaf70eb6330..f8636de907ae 100644
---- a/xen/arch/x86/pv/misc-hypercalls.c
-+++ b/xen/arch/x86/pv/misc-hypercalls.c
-@@ -72,7 +72,7 @@ long set_debugreg(struct vcpu *v, unsigned int reg, unsigned long value)
-     switch ( reg )
-     {
-     case 0 ... 3:
--        if ( !access_ok(value, sizeof(long)) )
-+        if ( !breakpoint_addr_ok(value) )
-             return -EPERM;
- 
-         v->arch.dr[reg] = value;

xsa445-4.17.patch

@@ -1,63 +0,0 @@
-From a43127d4f1f9a364334fe16b6239c211b35fd238 Mon Sep 17 00:00:00 2001
-From: Roger Pau Monne <roger.pau@citrix.com>
-Date: Wed, 11 Oct 2023 13:14:21 +0200
-Subject: [PATCH] iommu/amd-vi: use correct level for quarantine domain page
- tables
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-The current setup of the quarantine page tables assumes that the quarantine
-domain (dom_io) has been initialized with an address width of
-DEFAULT_DOMAIN_ADDRESS_WIDTH (48).
-
-However dom_io being a PV domain gets the AMD-Vi IOMMU page tables levels based
-on the maximum (hot pluggable) RAM address, and hence on systems with no RAM
-above the 512GB mark only 3 page-table levels are configured in the IOMMU.
-
-On systems without RAM above the 512GB boundary amd_iommu_quarantine_init()
-will setup page tables for the scratch page with 4 levels, while the IOMMU will
-be configured to use 3 levels only.  The page destined to be used as level 1,
-and to contain a directory of PTEs ends up being the address in a PTE itself,
-and thus level 1 page becomes the leaf page.  Without the level mismatch it's
-level 0 page that should be the leaf page instead.
-
-The level 1 page won't be used as such, and hence it's not possible to use it
-to gain access to other memory on the system.  However that page is not cleared
-in amd_iommu_quarantine_init() as part of re-initialization of the device
-quarantine page tables, and hence data on the level 1 page can be leaked
-between device usages.
-
-Fix this by making sure the paging levels setup by amd_iommu_quarantine_init()
-match the number configured on the IOMMUs.
-
-Note that IVMD regions are not affected by this issue, as those areas are
-mapped taking the configured paging levels into account.
-
-This is XSA-445 / CVE-2023-46835
-
-Fixes: ea38867831da ('x86 / iommu: set up a scratch page in the quarantine domain')
-Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
-Reviewed-by: Jan Beulich <jbeulich@suse.com>
----
- xen/drivers/passthrough/amd/iommu_map.c | 4 +---
- 1 file changed, 1 insertion(+), 3 deletions(-)
-
-diff --git a/xen/drivers/passthrough/amd/iommu_map.c b/xen/drivers/passthrough/amd/iommu_map.c
-index 993bac6f8878..e0f4fe736a8d 100644
---- a/xen/drivers/passthrough/amd/iommu_map.c
-+++ b/xen/drivers/passthrough/amd/iommu_map.c
-@@ -837,9 +837,7 @@ static int fill_qpt(union amd_iommu_pte *this, unsigned int level,
- int cf_check amd_iommu_quarantine_init(struct pci_dev *pdev, bool scratch_page)
- {
-     struct domain_iommu *hd = dom_iommu(dom_io);
--    unsigned long end_gfn =
--        1ul << (DEFAULT_DOMAIN_ADDRESS_WIDTH - PAGE_SHIFT);
--    unsigned int level = amd_iommu_get_paging_mode(end_gfn);
-+    unsigned int level = hd->arch.amd.paging_mode;
-     unsigned int req_id = get_dma_requestor_id(pdev->seg, pdev->sbdf.bdf);
-     const struct ivrs_mappings *ivrs_mappings = get_ivrs_mappings(pdev->seg);
-     int rc;
--- 
-2.42.0
-

xsa446.patch

@@ -1,115 +0,0 @@
-From 80d5aada598c3a800a350003d5d582931545e13c Mon Sep 17 00:00:00 2001
-From: Andrew Cooper <andrew.cooper3@citrix.com>
-Date: Thu, 26 Oct 2023 14:37:38 +0100
-Subject: [PATCH] x86/spec-ctrl: Remove conditional IRQs-on-ness for INT
- $0x80/0x82 paths
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Before speculation defences, some paths in Xen could genuinely get away with
-being IRQs-on at entry.  But XPTI invalidated this property on most paths, and
-attempting to maintain it on the remaining paths was a mistake.
-
-Fast forward, and DO_SPEC_CTRL_COND_IBPB (protection for AMD BTC/SRSO) is not
-IRQ-safe, running with IRQs enabled in some cases.  The other actions taken on
-these paths happen to be IRQ-safe.
-
-Make entry_int82() and int80_direct_trap() unconditionally Interrupt Gates
-rather than Trap Gates.  Remove the conditional re-adjustment of
-int80_direct_trap() in smp_prepare_cpus(), and have entry_int82() explicitly
-enable interrupts when safe to do so.
-
-In smp_prepare_cpus(), with the conditional re-adjustment removed, the
-clearing of pv_cr3 is the only remaining action gated on XPTI, and it is out
-of place anyway, repeating work already done by smp_prepare_boot_cpu().  Drop
-the entire if() condition to avoid leaving an incorrect vestigial remnant.
-
-Also drop comments which make incorrect statements about when its safe to
-enable interrupts.
-
-This is XSA-446 / CVE-2023-46836
-
-Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
-Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
----
- xen/arch/x86/pv/traps.c            |  4 ++--
- xen/arch/x86/smpboot.c             | 14 --------------
- xen/arch/x86/x86_64/compat/entry.S |  2 ++
- xen/arch/x86/x86_64/entry.S        |  1 -
- 4 files changed, 4 insertions(+), 17 deletions(-)
-
-diff --git a/xen/arch/x86/pv/traps.c b/xen/arch/x86/pv/traps.c
-index 74f333da7e1c..240d1a2db7a3 100644
---- a/xen/arch/x86/pv/traps.c
-+++ b/xen/arch/x86/pv/traps.c
-@@ -139,11 +139,11 @@ void __init pv_trap_init(void)
- #ifdef CONFIG_PV32
-     /* The 32-on-64 hypercall vector is only accessible from ring 1. */
-     _set_gate(idt_table + HYPERCALL_VECTOR,
--              SYS_DESC_trap_gate, 1, entry_int82);
-+              SYS_DESC_irq_gate, 1, entry_int82);
- #endif
- 
-     /* Fast trap for int80 (faster than taking the #GP-fixup path). */
--    _set_gate(idt_table + LEGACY_SYSCALL_VECTOR, SYS_DESC_trap_gate, 3,
-+    _set_gate(idt_table + LEGACY_SYSCALL_VECTOR, SYS_DESC_irq_gate, 3,
-               &int80_direct_trap);
- 
-     open_softirq(NMI_SOFTIRQ, nmi_softirq);
-diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
-index 3a1a659082c6..4c54ecbc91d7 100644
---- a/xen/arch/x86/smpboot.c
-+++ b/xen/arch/x86/smpboot.c
-@@ -1158,20 +1158,6 @@ void __init smp_prepare_cpus(void)
- 
-     stack_base[0] = (void *)((unsigned long)stack_start & ~(STACK_SIZE - 1));
- 
--    if ( opt_xpti_hwdom || opt_xpti_domu )
--    {
--        get_cpu_info()->pv_cr3 = 0;
--
--#ifdef CONFIG_PV
--        /*
--         * All entry points which may need to switch page tables have to start
--         * with interrupts off. Re-write what pv_trap_init() has put there.
--         */
--        _set_gate(idt_table + LEGACY_SYSCALL_VECTOR, SYS_DESC_irq_gate, 3,
--                  &int80_direct_trap);
--#endif
--    }
--
-     set_nr_sockets();
- 
-     socket_cpumask = xzalloc_array(cpumask_t *, nr_sockets);
-diff --git a/xen/arch/x86/x86_64/compat/entry.S b/xen/arch/x86/x86_64/compat/entry.S
-index bd5abd8040bd..fcc3a721f147 100644
---- a/xen/arch/x86/x86_64/compat/entry.S
-+++ b/xen/arch/x86/x86_64/compat/entry.S
-@@ -21,6 +21,8 @@ ENTRY(entry_int82)
-         SPEC_CTRL_ENTRY_FROM_PV /* Req: %rsp=regs/cpuinfo, %rdx=0, Clob: acd */
-         /* WARNING! `ret`, `call *`, `jmp *` not safe before this point. */
- 
-+        sti
-+
-         CR4_PV32_RESTORE
- 
-         GET_CURRENT(bx)
-diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
-index 5ca74f5f62b2..9a7b129aa7e4 100644
---- a/xen/arch/x86/x86_64/entry.S
-+++ b/xen/arch/x86/x86_64/entry.S
-@@ -327,7 +327,6 @@ ENTRY(sysenter_entry)
- #ifdef CONFIG_XEN_SHSTK
-         ALTERNATIVE "", "setssbsy", X86_FEATURE_XEN_SHSTK
- #endif
--        /* sti could live here when we don't switch page tables below. */
-         pushq $FLAT_USER_SS
-         pushq $0
-         pushfq
-
-base-commit: 7befef87cc9b1bb8ca15d866ce1ecd9165ccb58c
-prerequisite-patch-id: 142a87c707411d49e136c3fb76f1b14963ec6dc8
--- 
-2.30.2
-