--- /dev/null
+From c32ac11da3f83bb42b986702a9b92f0a14ed4182 Mon Sep 17 00:00:00 2001
+From: Ard Biesheuvel <ardb@kernel.org>
+Date: Mon, 26 Jul 2021 16:31:44 +0200
+Subject: efi/libstub: arm64: Double check image alignment at entry
+
+From: Ard Biesheuvel <ardb@kernel.org>
+
+commit c32ac11da3f83bb42b986702a9b92f0a14ed4182 upstream.
+
+On arm64, the stub only moves the kernel image around in memory if
+needed, which is typically only for KASLR, given that relocatable
+kernels (which is the default) can run from any 64k aligned address,
+which is also the minimum alignment communicated to EFI via the PE/COFF
+header.
+
+Unfortunately, some loaders appear to ignore this header, and load the
+kernel at some arbitrary offset in memory. We can deal with this, but
+let's check for this condition anyway, so non-compliant code can be
+spotted and fixed.
+
+Cc: <stable@vger.kernel.org> # v5.10+
+Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
+Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/firmware/efi/libstub/arm64-stub.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+--- a/drivers/firmware/efi/libstub/arm64-stub.c
++++ b/drivers/firmware/efi/libstub/arm64-stub.c
+@@ -119,6 +119,10 @@ efi_status_t handle_kernel_image(unsigne
+ if (image->image_base != _text)
+ efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n");
+
++ if (!IS_ALIGNED((u64)_text, EFI_KIMG_ALIGN))
++ efi_err("FIRMWARE BUG: kernel image not aligned on %ldk boundary\n",
++ EFI_KIMG_ALIGN >> 10);
++
+ kernel_size = _edata - _text;
+ kernel_memsize = kernel_size + (_end - _edata);
+ *reserve_size = kernel_memsize;
--- /dev/null
+From 18712c13709d2de9516c5d3414f707c4f0a9c190 Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <seanjc@google.com>
+Date: Wed, 11 Aug 2021 21:56:15 -0700
+Subject: KVM: nVMX: Use vmx_need_pf_intercept() when deciding if L0 wants a #PF
+
+From: Sean Christopherson <seanjc@google.com>
+
+commit 18712c13709d2de9516c5d3414f707c4f0a9c190 upstream.
+
+Use vmx_need_pf_intercept() when determining if L0 wants to handle a #PF
+in L2 or if the VM-Exit should be forwarded to L1. The current logic fails
+to account for the case where #PF is intercepted to handle
+guest.MAXPHYADDR < host.MAXPHYADDR and ends up reflecting all #PFs into
+L1. At best, L1 will complain and inject the #PF back into L2. At
+worst, L1 will eat the unexpected fault and cause L2 to hang on infinite
+page faults.
+
+Note, while the bug was technically introduced by the commit that added
+support for the MAXPHYADDR madness, the shame is all on commit
+a0c134347baf ("KVM: VMX: introduce vmx_need_pf_intercept").
+
+Fixes: 1dbf5d68af6f ("KVM: VMX: Add guest physical address check in EPT violation and misconfig")
+Cc: stable@vger.kernel.org
+Cc: Peter Shier <pshier@google.com>
+Cc: Oliver Upton <oupton@google.com>
+Cc: Jim Mattson <jmattson@google.com>
+Signed-off-by: Sean Christopherson <seanjc@google.com>
+Message-Id: <20210812045615.3167686-1-seanjc@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/x86/kvm/vmx/nested.c | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+--- a/arch/x86/kvm/vmx/nested.c
++++ b/arch/x86/kvm/vmx/nested.c
+@@ -5779,7 +5779,8 @@ static bool nested_vmx_l0_wants_exit(str
+ if (is_nmi(intr_info))
+ return true;
+ else if (is_page_fault(intr_info))
+- return vcpu->arch.apf.host_apf_flags || !enable_ept;
++ return vcpu->arch.apf.host_apf_flags ||
++ vmx_need_pf_intercept(vcpu);
+ else if (is_debug(intr_info) &&
+ vcpu->guest_debug &
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
--- /dev/null
+From 7b9cae027ba3aaac295ae23a62f47876ed97da73 Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <seanjc@google.com>
+Date: Tue, 10 Aug 2021 10:19:49 -0700
+Subject: KVM: VMX: Use current VMCS to query WAITPKG support for MSR emulation
+
+From: Sean Christopherson <seanjc@google.com>
+
+commit 7b9cae027ba3aaac295ae23a62f47876ed97da73 upstream.
+
+Use the secondary_exec_controls_get() accessor in vmx_has_waitpkg() to
+effectively get the controls for the current VMCS, as opposed to using
+vmx->secondary_exec_controls, which is the cached value of KVM's desired
+controls for vmcs01 and truly not reflective of any particular VMCS.
+
+While the waitpkg control is not dynamic, i.e. vmcs01 will always hold
+the same waitpkg configuration as vmx->secondary_exec_controls, the same
+does not hold true for vmcs02 if the L1 VMM hides the feature from L2.
+If L1 hides the feature _and_ does not intercept MSR_IA32_UMWAIT_CONTROL,
+L2 could incorrectly read/write L1's virtual MSR instead of taking a #GP.
+
+Fixes: 6e3ba4abcea5 ("KVM: vmx: Emulate MSR IA32_UMWAIT_CONTROL")
+Cc: stable@vger.kernel.org
+Signed-off-by: Sean Christopherson <seanjc@google.com>
+Message-Id: <20210810171952.2758100-2-seanjc@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/x86/kvm/vmx/vmx.h | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/arch/x86/kvm/vmx/vmx.h
++++ b/arch/x86/kvm/vmx/vmx.h
+@@ -488,7 +488,7 @@ static inline void decache_tsc_multiplie
+
+ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
+ {
+- return vmx->secondary_exec_control &
++ return secondary_exec_controls_get(vmx) &
+ SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+ }
+
--- /dev/null
+From 689e6b5351573c38ccf92a0dd8b3e2c2241e4aff Mon Sep 17 00:00:00 2001
+From: Thomas Gleixner <tglx@linutronix.de>
+Date: Thu, 29 Jul 2021 23:51:45 +0200
+Subject: PCI/MSI: Correct misleading comments
+
+From: Thomas Gleixner <tglx@linutronix.de>
+
+commit 689e6b5351573c38ccf92a0dd8b3e2c2241e4aff upstream.
+
+The comments about preserving the cached state in pci_msi[x]_shutdown() are
+misleading as the MSI descriptors are freed right after those functions
+return. So there is nothing to restore. Preparatory change.
+
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Tested-by: Marc Zyngier <maz@kernel.org>
+Reviewed-by: Marc Zyngier <maz@kernel.org>
+Cc: stable@vger.kernel.org
+Link: https://lore.kernel.org/r/20210729222542.621609423@linutronix.de
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/pci/msi.c | 5 +----
+ 1 file changed, 1 insertion(+), 4 deletions(-)
+
+--- a/drivers/pci/msi.c
++++ b/drivers/pci/msi.c
+@@ -961,7 +961,6 @@ static void pci_msi_shutdown(struct pci_
+
+ /* Return the device with MSI unmasked as initial states */
+ mask = msi_mask(desc->msi_attrib.multi_cap);
+- /* Keep cached state to be restored */
+ __pci_msi_desc_mask_irq(desc, mask, 0);
+
+ /* Restore dev->irq to its default pin-assertion IRQ */
+@@ -1047,10 +1046,8 @@ static void pci_msix_shutdown(struct pci
+ }
+
+ /* Return the device with MSI-X masked as initial states */
+- for_each_pci_msi_entry(entry, dev) {
+- /* Keep cached states to be restored */
++ for_each_pci_msi_entry(entry, dev)
+ __pci_msix_desc_mask_irq(entry, 1);
+- }
+
+ pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
+ pci_intx_for_msi(dev, 1);
--- /dev/null
+From 361fd37397f77578735907341579397d5bed0a2d Mon Sep 17 00:00:00 2001
+From: Thomas Gleixner <tglx@linutronix.de>
+Date: Thu, 29 Jul 2021 23:51:44 +0200
+Subject: PCI/MSI: Do not set invalid bits in MSI mask
+
+From: Thomas Gleixner <tglx@linutronix.de>
+
+commit 361fd37397f77578735907341579397d5bed0a2d upstream.
+
+msi_mask_irq() takes a mask and a flags argument. The mask argument is used
+to mask out bits from the cached mask and the flags argument to set bits.
+
+Some places invoke it with a flags argument which sets bits which are not
+used by the device, i.e. when the device supports up to 8 vectors a full
+unmask in some places sets the mask to 0xFFFFFF00. While devices probably
+do not care, it's still bad practice.
+
+Fixes: 7ba1930db02f ("PCI MSI: Unmask MSI if setup failed")
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Tested-by: Marc Zyngier <maz@kernel.org>
+Reviewed-by: Marc Zyngier <maz@kernel.org>
+Cc: stable@vger.kernel.org
+Link: https://lore.kernel.org/r/20210729222542.568173099@linutronix.de
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/pci/msi.c | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+--- a/drivers/pci/msi.c
++++ b/drivers/pci/msi.c
+@@ -663,21 +663,21 @@ static int msi_capability_init(struct pc
+ /* Configure MSI capability structure */
+ ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
+ if (ret) {
+- msi_mask_irq(entry, mask, ~mask);
++ msi_mask_irq(entry, mask, 0);
+ free_msi_irqs(dev);
+ return ret;
+ }
+
+ ret = msi_verify_entries(dev);
+ if (ret) {
+- msi_mask_irq(entry, mask, ~mask);
++ msi_mask_irq(entry, mask, 0);
+ free_msi_irqs(dev);
+ return ret;
+ }
+
+ ret = populate_msi_sysfs(dev);
+ if (ret) {
+- msi_mask_irq(entry, mask, ~mask);
++ msi_mask_irq(entry, mask, 0);
+ free_msi_irqs(dev);
+ return ret;
+ }
+@@ -962,7 +962,7 @@ static void pci_msi_shutdown(struct pci_
+ /* Return the device with MSI unmasked as initial states */
+ mask = msi_mask(desc->msi_attrib.multi_cap);
+ /* Keep cached state to be restored */
+- __pci_msi_desc_mask_irq(desc, mask, ~mask);
++ __pci_msi_desc_mask_irq(desc, mask, 0);
+
+ /* Restore dev->irq to its default pin-assertion IRQ */
+ dev->irq = desc->msi_attrib.default_irq;
--- /dev/null
+From b9255a7cb51754e8d2645b65dd31805e282b4f3e Mon Sep 17 00:00:00 2001
+From: Thomas Gleixner <tglx@linutronix.de>
+Date: Thu, 29 Jul 2021 23:51:43 +0200
+Subject: PCI/MSI: Enforce MSI[X] entry updates to be visible
+
+From: Thomas Gleixner <tglx@linutronix.de>
+
+commit b9255a7cb51754e8d2645b65dd31805e282b4f3e upstream.
+
+Nothing enforces the posted writes to be visible when the function
+returns. Flush them even if the flush might be redundant when the entry is
+masked already as the unmask will flush as well. This is either setup or a
+rare affinity change event so the extra flush is not the end of the world.
+
+While this is more a theoretical issue especially the logic in the X86
+specific msi_set_affinity() function relies on the assumption that the
+update has reached the hardware when the function returns.
+
+Again, as this never has been enforced the Fixes tag refers to a commit in:
+ git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
+
+Fixes: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support")
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Tested-by: Marc Zyngier <maz@kernel.org>
+Reviewed-by: Marc Zyngier <maz@kernel.org>
+Acked-by: Bjorn Helgaas <bhelgaas@google.com>
+Cc: stable@vger.kernel.org
+Link: https://lore.kernel.org/r/20210729222542.515188147@linutronix.de
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/pci/msi.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+--- a/drivers/pci/msi.c
++++ b/drivers/pci/msi.c
+@@ -339,6 +339,9 @@ void __pci_write_msi_msg(struct msi_desc
+
+ if (unmasked)
+ __pci_msix_desc_mask_irq(entry, 0);
++
++ /* Ensure that the writes are visible in the device */
++ readl(base + PCI_MSIX_ENTRY_DATA);
+ } else {
+ int pos = dev->msi_cap;
+ u16 msgctl;
+@@ -359,6 +362,8 @@ void __pci_write_msi_msg(struct msi_desc
+ pci_write_config_word(dev, pos + PCI_MSI_DATA_32,
+ msg->data);
+ }
++ /* Ensure that the writes are visible in the device */
++ pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
+ }
+
+ skip:
--- /dev/null
+From da181dc974ad667579baece33c2c8d2d1e4558d5 Mon Sep 17 00:00:00 2001
+From: Thomas Gleixner <tglx@linutronix.de>
+Date: Thu, 29 Jul 2021 23:51:42 +0200
+Subject: PCI/MSI: Enforce that MSI-X table entry is masked for update
+
+From: Thomas Gleixner <tglx@linutronix.de>
+
+commit da181dc974ad667579baece33c2c8d2d1e4558d5 upstream.
+
+The specification (PCIe r5.0, sec 6.1.4.5) states:
+
+ For MSI-X, a function is permitted to cache Address and Data values
+ from unmasked MSI-X Table entries. However, anytime software unmasks a
+ currently masked MSI-X Table entry either by clearing its Mask bit or
+ by clearing the Function Mask bit, the function must update any Address
+ or Data values that it cached from that entry. If software changes the
+ Address or Data value of an entry while the entry is unmasked, the
+ result is undefined.
+
+The Linux kernel's MSI-X support never enforced that the entry is masked
+before the entry is modified hence the Fixes tag refers to a commit in:
+ git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
+
+Enforce the entry to be masked across the update.
+
+There is no point in enforcing this to be handled at all possible call
+sites as this is just pointless code duplication and the common update
+function is the obvious place to enforce this.
+
+Fixes: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support")
+Reported-by: Kevin Tian <kevin.tian@intel.com>
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Tested-by: Marc Zyngier <maz@kernel.org>
+Reviewed-by: Marc Zyngier <maz@kernel.org>
+Acked-by: Bjorn Helgaas <bhelgaas@google.com>
+Cc: stable@vger.kernel.org
+Link: https://lore.kernel.org/r/20210729222542.462096385@linutronix.de
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/pci/msi.c | 15 +++++++++++++++
+ 1 file changed, 15 insertions(+)
+
+--- a/drivers/pci/msi.c
++++ b/drivers/pci/msi.c
+@@ -317,13 +317,28 @@ void __pci_write_msi_msg(struct msi_desc
+ /* Don't touch the hardware now */
+ } else if (entry->msi_attrib.is_msix) {
+ void __iomem *base = pci_msix_desc_addr(entry);
++ bool unmasked = !(entry->masked & PCI_MSIX_ENTRY_CTRL_MASKBIT);
+
+ if (!base)
+ goto skip;
+
++ /*
++ * The specification mandates that the entry is masked
++ * when the message is modified:
++ *
++ * "If software changes the Address or Data value of an
++ * entry while the entry is unmasked, the result is
++ * undefined."
++ */
++ if (unmasked)
++ __pci_msix_desc_mask_irq(entry, PCI_MSIX_ENTRY_CTRL_MASKBIT);
++
+ writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR);
+ writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
+ writel(msg->data, base + PCI_MSIX_ENTRY_DATA);
++
++ if (unmasked)
++ __pci_msix_desc_mask_irq(entry, 0);
+ } else {
+ int pos = dev->msi_cap;
+ u16 msgctl;
--- /dev/null
+From 7d5ec3d3612396dc6d4b76366d20ab9fc06f399f Mon Sep 17 00:00:00 2001
+From: Thomas Gleixner <tglx@linutronix.de>
+Date: Thu, 29 Jul 2021 23:51:41 +0200
+Subject: PCI/MSI: Mask all unused MSI-X entries
+
+From: Thomas Gleixner <tglx@linutronix.de>
+
+commit 7d5ec3d3612396dc6d4b76366d20ab9fc06f399f upstream.
+
+When MSI-X is enabled the ordering of calls is:
+
+ msix_map_region();
+ msix_setup_entries();
+ pci_msi_setup_msi_irqs();
+ msix_program_entries();
+
+This has a few interesting issues:
+
+ 1) msix_setup_entries() allocates the MSI descriptors and initializes them
+ except for the msi_desc:masked member which is left zero initialized.
+
+ 2) pci_msi_setup_msi_irqs() allocates the interrupt descriptors and sets
+ up the MSI interrupts which ends up in pci_write_msi_msg() unless the
+ interrupt chip provides its own irq_write_msi_msg() function.
+
+ 3) msix_program_entries() does not do what the name suggests. It solely
+ updates the entries array (if not NULL) and initializes the masked
+ member for each MSI descriptor by reading the hardware state and then
+ masks the entry.
+
+Obviously this has some issues:
+
+ 1) The uninitialized masked member of msi_desc prevents the enforcement
+ of masking the entry in pci_write_msi_msg() depending on the cached
+ masked bit. Aside of that half initialized data is a NONO in general
+
+ 2) msix_program_entries() only ensures that the actually allocated entries
+ are masked. This is wrong as experimentation with crash testing and
+ crash kernel kexec has shown.
+
+ This limited testing unearthed that when the production kernel had more
+ entries in use and unmasked when it crashed and the crash kernel
+ allocated a smaller amount of entries, then a full scan of all entries
+ found unmasked entries which were in use in the production kernel.
+
+ This is obviously a device or emulation issue as the device reset
+ should mask all MSI-X table entries, but obviously that's just part
+ of the paper specification.
+
+Cure this by:
+
+ 1) Masking all table entries in hardware
+ 2) Initializing msi_desc::masked in msix_setup_entries()
+ 3) Removing the mask dance in msix_program_entries()
+ 4) Renaming msix_program_entries() to msix_update_entries() to
+ reflect the purpose of that function.
+
+As the masking of unused entries has never been done the Fixes tag refers
+to a commit in:
+ git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
+
+Fixes: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support")
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Tested-by: Marc Zyngier <maz@kernel.org>
+Reviewed-by: Marc Zyngier <maz@kernel.org>
+Acked-by: Bjorn Helgaas <bhelgaas@google.com>
+Cc: stable@vger.kernel.org
+Link: https://lore.kernel.org/r/20210729222542.403833459@linutronix.de
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/pci/msi.c | 45 +++++++++++++++++++++++++++------------------
+ 1 file changed, 27 insertions(+), 18 deletions(-)
+
+--- a/drivers/pci/msi.c
++++ b/drivers/pci/msi.c
+@@ -698,6 +698,7 @@ static int msix_setup_entries(struct pci
+ {
+ struct irq_affinity_desc *curmsk, *masks = NULL;
+ struct msi_desc *entry;
++ void __iomem *addr;
+ int ret, i;
+ int vec_count = pci_msix_vec_count(dev);
+
+@@ -718,6 +719,7 @@ static int msix_setup_entries(struct pci
+
+ entry->msi_attrib.is_msix = 1;
+ entry->msi_attrib.is_64 = 1;
++
+ if (entries)
+ entry->msi_attrib.entry_nr = entries[i].entry;
+ else
+@@ -729,6 +731,10 @@ static int msix_setup_entries(struct pci
+ entry->msi_attrib.default_irq = dev->irq;
+ entry->mask_base = base;
+
++ addr = pci_msix_desc_addr(entry);
++ if (addr)
++ entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
++
+ list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
+ if (masks)
+ curmsk++;
+@@ -739,26 +745,25 @@ out:
+ return ret;
+ }
+
+-static void msix_program_entries(struct pci_dev *dev,
+- struct msix_entry *entries)
++static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries)
+ {
+ struct msi_desc *entry;
+- int i = 0;
+- void __iomem *desc_addr;
+
+ for_each_pci_msi_entry(entry, dev) {
+- if (entries)
+- entries[i++].vector = entry->irq;
++ if (entries) {
++ entries->vector = entry->irq;
++ entries++;
++ }
++ }
++}
+
+- desc_addr = pci_msix_desc_addr(entry);
+- if (desc_addr)
+- entry->masked = readl(desc_addr +
+- PCI_MSIX_ENTRY_VECTOR_CTRL);
+- else
+- entry->masked = 0;
++static void msix_mask_all(void __iomem *base, int tsize)
++{
++ u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
++ int i;
+
+- msix_mask_irq(entry, 1);
+- }
++ for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
++ writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
+ }
+
+ /**
+@@ -775,9 +780,9 @@ static void msix_program_entries(struct
+ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
+ int nvec, struct irq_affinity *affd)
+ {
+- int ret;
+- u16 control;
+ void __iomem *base;
++ int ret, tsize;
++ u16 control;
+
+ /*
+ * Some devices require MSI-X to be enabled before the MSI-X
+@@ -789,12 +794,16 @@ static int msix_capability_init(struct p
+
+ pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
+ /* Request & Map MSI-X table region */
+- base = msix_map_region(dev, msix_table_size(control));
++ tsize = msix_table_size(control);
++ base = msix_map_region(dev, tsize);
+ if (!base) {
+ ret = -ENOMEM;
+ goto out_disable;
+ }
+
++ /* Ensure that all table entries are masked. */
++ msix_mask_all(base, tsize);
++
+ ret = msix_setup_entries(dev, base, entries, nvec, affd);
+ if (ret)
+ goto out_disable;
+@@ -808,7 +817,7 @@ static int msix_capability_init(struct p
+ if (ret)
+ goto out_free;
+
+- msix_program_entries(dev, entries);
++ msix_update_entries(dev, entries);
+
+ ret = populate_msi_sysfs(dev);
+ if (ret)
--- /dev/null
+From 77e89afc25f30abd56e76a809ee2884d7c1b63ce Mon Sep 17 00:00:00 2001
+From: Thomas Gleixner <tglx@linutronix.de>
+Date: Thu, 29 Jul 2021 23:51:47 +0200
+Subject: PCI/MSI: Protect msi_desc::masked for multi-MSI
+
+From: Thomas Gleixner <tglx@linutronix.de>
+
+commit 77e89afc25f30abd56e76a809ee2884d7c1b63ce upstream.
+
+Multi-MSI uses a single MSI descriptor and there is a single mask register
+when the device supports per vector masking. To avoid reading back the mask
+register the value is cached in the MSI descriptor and updates are done by
+clearing and setting bits in the cache and writing it to the device.
+
+But nothing protects msi_desc::masked and the mask register from being
+modified concurrently on two different CPUs for two different Linux
+interrupts which belong to the same multi-MSI descriptor.
+
+Add a lock to struct device and protect any operation on the mask and the
+mask register with it.
+
+This makes the update of msi_desc::masked unconditional, but there is no
+place which requires a modification of the hardware register without
+updating the masked cache.
+
+msi_mask_irq() is now an empty wrapper which will be cleaned up in follow
+up changes.
+
+The problem goes way back to the initial support of multi-MSI, but picking
+the commit which introduced the mask cache is a valid cut off point
+(2.6.30).
+
+Fixes: f2440d9acbe8 ("PCI MSI: Refactor interrupt masking code")
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Tested-by: Marc Zyngier <maz@kernel.org>
+Reviewed-by: Marc Zyngier <maz@kernel.org>
+Cc: stable@vger.kernel.org
+Link: https://lore.kernel.org/r/20210729222542.726833414@linutronix.de
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/base/core.c | 1 +
+ drivers/pci/msi.c | 19 ++++++++++---------
+ include/linux/device.h | 1 +
+ include/linux/msi.h | 2 +-
+ 4 files changed, 13 insertions(+), 10 deletions(-)
+
+--- a/drivers/base/core.c
++++ b/drivers/base/core.c
+@@ -2452,6 +2452,7 @@ void device_initialize(struct device *de
+ device_pm_init(dev);
+ set_dev_node(dev, -1);
+ #ifdef CONFIG_GENERIC_MSI_IRQ
++ raw_spin_lock_init(&dev->msi_lock);
+ INIT_LIST_HEAD(&dev->msi_list);
+ #endif
+ INIT_LIST_HEAD(&dev->links.consumers);
+--- a/drivers/pci/msi.c
++++ b/drivers/pci/msi.c
+@@ -171,24 +171,25 @@ static inline __attribute_const__ u32 ms
+ * reliably as devices without an INTx disable bit will then generate a
+ * level IRQ which will never be cleared.
+ */
+-u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
++void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+ {
+- u32 mask_bits = desc->masked;
++ raw_spinlock_t *lock = &desc->dev->msi_lock;
++ unsigned long flags;
+
+ if (pci_msi_ignore_mask || !desc->msi_attrib.maskbit)
+- return 0;
++ return;
+
+- mask_bits &= ~mask;
+- mask_bits |= flag;
++ raw_spin_lock_irqsave(lock, flags);
++ desc->masked &= ~mask;
++ desc->masked |= flag;
+ pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos,
+- mask_bits);
+-
+- return mask_bits;
++ desc->masked);
++ raw_spin_unlock_irqrestore(lock, flags);
+ }
+
+ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+ {
+- desc->masked = __pci_msi_desc_mask_irq(desc, mask, flag);
++ __pci_msi_desc_mask_irq(desc, mask, flag);
+ }
+
+ static void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
+--- a/include/linux/device.h
++++ b/include/linux/device.h
+@@ -497,6 +497,7 @@ struct device {
+ struct dev_pin_info *pins;
+ #endif
+ #ifdef CONFIG_GENERIC_MSI_IRQ
++ raw_spinlock_t msi_lock;
+ struct list_head msi_list;
+ #endif
+ #ifdef CONFIG_DMA_OPS
+--- a/include/linux/msi.h
++++ b/include/linux/msi.h
+@@ -194,7 +194,7 @@ void __pci_read_msi_msg(struct msi_desc
+ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+
+ u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag);
+-u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
++void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
+ void pci_msi_mask_irq(struct irq_data *data);
+ void pci_msi_unmask_irq(struct irq_data *data);
+
--- /dev/null
+From d28d4ad2a1aef27458b3383725bb179beb8d015c Mon Sep 17 00:00:00 2001
+From: Thomas Gleixner <tglx@linutronix.de>
+Date: Thu, 29 Jul 2021 23:51:46 +0200
+Subject: PCI/MSI: Use msi_mask_irq() in pci_msi_shutdown()
+
+From: Thomas Gleixner <tglx@linutronix.de>
+
+commit d28d4ad2a1aef27458b3383725bb179beb8d015c upstream.
+
+No point in using the raw write function from shutdown. Preparatory change
+to introduce proper serialization for the msi_desc::masked cache.
+
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Tested-by: Marc Zyngier <maz@kernel.org>
+Reviewed-by: Marc Zyngier <maz@kernel.org>
+Cc: stable@vger.kernel.org
+Link: https://lore.kernel.org/r/20210729222542.674391354@linutronix.de
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/pci/msi.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/drivers/pci/msi.c
++++ b/drivers/pci/msi.c
+@@ -961,7 +961,7 @@ static void pci_msi_shutdown(struct pci_
+
+ /* Return the device with MSI unmasked as initial states */
+ mask = msi_mask(desc->msi_attrib.multi_cap);
+- __pci_msi_desc_mask_irq(desc, mask, 0);
++ msi_mask_irq(desc, mask, 0);
+
+ /* Restore dev->irq to its default pin-assertion IRQ */
+ dev->irq = desc->msi_attrib.default_irq;
--- /dev/null
+From 8241461536f21bbe51308a6916d1c9fb2e6b75a7 Mon Sep 17 00:00:00 2001
+From: Christophe Leroy <christophe.leroy@csgroup.eu>
+Date: Wed, 4 Aug 2021 18:24:10 +0000
+Subject: powerpc/smp: Fix OOPS in topology_init()
+
+From: Christophe Leroy <christophe.leroy@csgroup.eu>
+
+commit 8241461536f21bbe51308a6916d1c9fb2e6b75a7 upstream.
+
+Running an SMP kernel on an UP platform not prepared for it,
+I encountered the following OOPS:
+
+ BUG: Kernel NULL pointer dereference on read at 0x00000034
+ Faulting instruction address: 0xc0a04110
+ Oops: Kernel access of bad area, sig: 11 [#1]
+ BE PAGE_SIZE=4K SMP NR_CPUS=2 CMPCPRO
+ Modules linked in:
+ CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.13.0-pmac-00001-g230fedfaad21 #5234
+ NIP: c0a04110 LR: c0a040d8 CTR: c0a04084
+ REGS: e100dda0 TRAP: 0300 Not tainted (5.13.0-pmac-00001-g230fedfaad21)
+ MSR: 00009032 <EE,ME,IR,DR,RI> CR: 84000284 XER: 00000000
+ DAR: 00000034 DSISR: 20000000
+ GPR00: c0006bd4 e100de60 c1033320 00000000 00000000 c0942274 00000000 00000000
+ GPR08: 00000000 00000000 00000001 00000063 00000007 00000000 c0006f30 00000000
+ GPR16: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000005
+ GPR24: c0c67d74 c0c67f1c c0c60000 c0c67d70 c0c0c558 1efdf000 c0c00020 00000000
+ NIP [c0a04110] topology_init+0x8c/0x138
+ LR [c0a040d8] topology_init+0x54/0x138
+ Call Trace:
+ [e100de60] [80808080] 0x80808080 (unreliable)
+ [e100de90] [c0006bd4] do_one_initcall+0x48/0x1bc
+ [e100def0] [c0a0150c] kernel_init_freeable+0x1c8/0x278
+ [e100df20] [c0006f44] kernel_init+0x14/0x10c
+ [e100df30] [c00190fc] ret_from_kernel_thread+0x14/0x1c
+ Instruction dump:
+ 7c692e70 7d290194 7c035040 7c7f1b78 5529103a 546706fe 5468103a 39400001
+ 7c641b78 40800054 80c690b4 7fb9402e <81060034> 7fbeea14 2c080000 7fa3eb78
+ ---[ end trace b246ffbc6bbbb6fb ]---
+
+Fix it by checking smp_ops before using it, as already done in
+several other places in the arch/powerpc/kernel/smp.c
+
+Fixes: 39f87561454d ("powerpc/smp: Move ppc_md.cpu_die() to smp_ops.cpu_offline_self()")
+Cc: stable@vger.kernel.org
+Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
+Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
+Link: https://lore.kernel.org/r/75287841cbb8740edd44880fe60be66d489160d9.1628097995.git.christophe.leroy@csgroup.eu
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/powerpc/kernel/sysfs.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/arch/powerpc/kernel/sysfs.c
++++ b/arch/powerpc/kernel/sysfs.c
+@@ -1167,7 +1167,7 @@ static int __init topology_init(void)
+ * CPU. For instance, the boot cpu might never be valid
+ * for hotplugging.
+ */
+- if (smp_ops->cpu_offline_self)
++ if (smp_ops && smp_ops->cpu_offline_self)
+ c->hotpluggable = 1;
+ #endif
+
genirq-msi-ensure-deactivation-on-teardown.patch
genirq-timings-prevent-potential-array-overflow-in-__irq_timings_store.patch
pci-msi-enable-and-mask-msi-x-early.patch
+pci-msi-mask-all-unused-msi-x-entries.patch
+pci-msi-enforce-that-msi-x-table-entry-is-masked-for-update.patch
+pci-msi-enforce-msi-entry-updates-to-be-visible.patch
+pci-msi-do-not-set-invalid-bits-in-msi-mask.patch
+pci-msi-correct-misleading-comments.patch
+pci-msi-use-msi_mask_irq-in-pci_msi_shutdown.patch
+pci-msi-protect-msi_desc-masked-for-multi-msi.patch
+powerpc-smp-fix-oops-in-topology_init.patch
+efi-libstub-arm64-double-check-image-alignment-at-entry.patch
+kvm-vmx-use-current-vmcs-to-query-waitpkg-support-for-msr-emulation.patch
+kvm-nvmx-use-vmx_need_pf_intercept-when-deciding-if-l0-wants-a-pf.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
