--- /dev/null
+From 8e19c9732ad1d127b5575a10f4fbcacf740500ff Mon Sep 17 00:00:00 2001
+From: Josef Bacik <josef@toxicpanda.com>
+Date: Wed, 4 Mar 2020 11:18:23 -0500
+Subject: btrfs: drop block from cache on error in relocation
+
+From: Josef Bacik <josef@toxicpanda.com>
+
+commit 8e19c9732ad1d127b5575a10f4fbcacf740500ff upstream.
+
+If we have an error while building the backref tree in relocation we'll
+process all the pending edges and then free the node. However if we
+integrated some edges into the cache we'll lose our link to those edges
+by simply freeing this node, which means we'll leak memory and
+references to any roots that we've found.
+
+Instead we need to use remove_backref_node(), which walks through all of
+the edges that are still linked to this node and free's them up and
+drops any root references we may be holding.
+
+CC: stable@vger.kernel.org # 4.9+
+Reviewed-by: Qu Wenruo <wqu@suse.com>
+Signed-off-by: Josef Bacik <josef@toxicpanda.com>
+Reviewed-by: David Sterba <dsterba@suse.com>
+Signed-off-by: David Sterba <dsterba@suse.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/btrfs/relocation.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/fs/btrfs/relocation.c
++++ b/fs/btrfs/relocation.c
+@@ -1194,7 +1194,7 @@ out:
+ free_backref_node(cache, lower);
+ }
+
+- free_backref_node(cache, node);
++ remove_backref_node(cache, node);
+ return ERR_PTR(err);
+ }
+ ASSERT(!node || !node->detached);
--- /dev/null
+From 97adda8b3ab703de8e4c8d27646ddd54fe22879c Mon Sep 17 00:00:00 2001
+From: Yilu Lin <linyilu@huawei.com>
+Date: Wed, 18 Mar 2020 11:59:19 +0800
+Subject: CIFS: Fix bug which the return value by asynchronous read is error
+
+From: Yilu Lin <linyilu@huawei.com>
+
+commit 97adda8b3ab703de8e4c8d27646ddd54fe22879c upstream.
+
+This patch is used to fix the bug in collect_uncached_read_data()
+that rc is automatically converted from a signed number to an
+unsigned number when the CIFS asynchronous read fails.
+It will cause ctx->rc is error.
+
+Example:
+Share a directory and create a file on the Windows OS.
+Mount the directory to the Linux OS using CIFS.
+On the CIFS client of the Linux OS, invoke the pread interface to
+deliver the read request.
+
+The size of the read length plus offset of the read request is greater
+than the maximum file size.
+
+In this case, the CIFS server on the Windows OS returns a failure
+message (for example, the return value of
+smb2.nt_status is STATUS_INVALID_PARAMETER).
+
+After receiving the response message, the CIFS client parses
+smb2.nt_status to STATUS_INVALID_PARAMETER
+and converts it to the Linux error code (rdata->result=-22).
+
+Then the CIFS client invokes the collect_uncached_read_data function to
+assign the value of rdata->result to rc, that is, rc=rdata->result=-22.
+
+The type of the ctx->total_len variable is unsigned integer,
+the type of the rc variable is integer, and the type of
+the ctx->rc variable is ssize_t.
+
+Therefore, during the ternary operation, the value of rc is
+automatically converted to an unsigned number. The final result is
+ctx->rc=4294967274. However, the expected result is ctx->rc=-22.
+
+Signed-off-by: Yilu Lin <linyilu@huawei.com>
+Signed-off-by: Steve French <stfrench@microsoft.com>
+CC: Stable <stable@vger.kernel.org>
+Acked-by: Ronnie Sahlberg <lsahlber@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/cifs/file.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/fs/cifs/file.c
++++ b/fs/cifs/file.c
+@@ -3303,7 +3303,7 @@ again:
+ if (rc == -ENODATA)
+ rc = 0;
+
+- ctx->rc = (rc == 0) ? ctx->total_len : rc;
++ ctx->rc = (rc == 0) ? (ssize_t)ctx->total_len : rc;
+
+ mutex_unlock(&ctx->aio_mutex);
+
--- /dev/null
+From fa03481b6e2e82355c46644147b614f18c7a8161 Mon Sep 17 00:00:00 2001
+From: Rosioru Dragos <dragos.rosioru@nxp.com>
+Date: Tue, 25 Feb 2020 17:05:52 +0200
+Subject: crypto: mxs-dcp - fix scatterlist linearization for hash
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Rosioru Dragos <dragos.rosioru@nxp.com>
+
+commit fa03481b6e2e82355c46644147b614f18c7a8161 upstream.
+
+The incorrect traversal of the scatterlist, during the linearization phase
+lead to computing the hash value of the wrong input buffer.
+New implementation uses scatterwalk_map_and_copy()
+to address this issue.
+
+Cc: <stable@vger.kernel.org>
+Fixes: 15b59e7c3733 ("crypto: mxs - Add Freescale MXS DCP driver")
+Signed-off-by: Rosioru Dragos <dragos.rosioru@nxp.com>
+Reviewed-by: Horia Geantă <horia.geanta@nxp.com>
+Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/crypto/mxs-dcp.c | 54 ++++++++++++++++++++++-------------------------
+ 1 file changed, 26 insertions(+), 28 deletions(-)
+
+--- a/drivers/crypto/mxs-dcp.c
++++ b/drivers/crypto/mxs-dcp.c
+@@ -25,6 +25,7 @@
+ #include <crypto/sha.h>
+ #include <crypto/internal/hash.h>
+ #include <crypto/internal/skcipher.h>
++#include <crypto/scatterwalk.h>
+
+ #define DCP_MAX_CHANS 4
+ #define DCP_BUF_SZ PAGE_SIZE
+@@ -621,49 +622,46 @@ static int dcp_sha_req_to_buf(struct cry
+ struct dcp_async_ctx *actx = crypto_ahash_ctx(tfm);
+ struct dcp_sha_req_ctx *rctx = ahash_request_ctx(req);
+ struct hash_alg_common *halg = crypto_hash_alg_common(tfm);
+- const int nents = sg_nents(req->src);
+
+ uint8_t *in_buf = sdcp->coh->sha_in_buf;
+ uint8_t *out_buf = sdcp->coh->sha_out_buf;
+
+- uint8_t *src_buf;
+-
+ struct scatterlist *src;
+
+- unsigned int i, len, clen;
++ unsigned int i, len, clen, oft = 0;
+ int ret;
+
+ int fin = rctx->fini;
+ if (fin)
+ rctx->fini = 0;
+
+- for_each_sg(req->src, src, nents, i) {
+- src_buf = sg_virt(src);
+- len = sg_dma_len(src);
++ src = req->src;
++ len = req->nbytes;
+
+- do {
+- if (actx->fill + len > DCP_BUF_SZ)
+- clen = DCP_BUF_SZ - actx->fill;
+- else
+- clen = len;
++ while (len) {
++ if (actx->fill + len > DCP_BUF_SZ)
++ clen = DCP_BUF_SZ - actx->fill;
++ else
++ clen = len;
+
+- memcpy(in_buf + actx->fill, src_buf, clen);
+- len -= clen;
+- src_buf += clen;
+- actx->fill += clen;
++ scatterwalk_map_and_copy(in_buf + actx->fill, src, oft, clen,
++ 0);
+
+- /*
+- * If we filled the buffer and still have some
+- * more data, submit the buffer.
+- */
+- if (len && actx->fill == DCP_BUF_SZ) {
+- ret = mxs_dcp_run_sha(req);
+- if (ret)
+- return ret;
+- actx->fill = 0;
+- rctx->init = 0;
+- }
+- } while (len);
++ len -= clen;
++ oft += clen;
++ actx->fill += clen;
++
++ /*
++ * If we filled the buffer and still have some
++ * more data, submit the buffer.
++ */
++ if (len && actx->fill == DCP_BUF_SZ) {
++ ret = mxs_dcp_run_sha(req);
++ if (ret)
++ return ret;
++ actx->fill = 0;
++ rctx->init = 0;
++ }
+ }
+
+ if (fin) {
--- /dev/null
+From a1c77abb8d93381e25a8d2df3a917388244ba776 Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <sean.j.christopherson@intel.com>
+Date: Mon, 2 Mar 2020 22:27:35 -0800
+Subject: KVM: nVMX: Properly handle userspace interrupt window request
+
+From: Sean Christopherson <sean.j.christopherson@intel.com>
+
+commit a1c77abb8d93381e25a8d2df3a917388244ba776 upstream.
+
+Return true for vmx_interrupt_allowed() if the vCPU is in L2 and L1 has
+external interrupt exiting enabled. IRQs are never blocked in hardware
+if the CPU is in the guest (L2 from L1's perspective) when IRQs trigger
+VM-Exit.
+
+The new check percolates up to kvm_vcpu_ready_for_interrupt_injection()
+and thus vcpu_run(), and so KVM will exit to userspace if userspace has
+requested an interrupt window (to inject an IRQ into L1).
+
+Remove the @external_intr param from vmx_check_nested_events(), which is
+actually an indicator that userspace wants an interrupt window, e.g.
+it's named @req_int_win further up the stack. Injecting a VM-Exit into
+L1 to try and bounce out to L0 userspace is all kinds of broken and is
+no longer necessary.
+
+Remove the hack in nested_vmx_vmexit() that attempted to workaround the
+breakage in vmx_check_nested_events() by only filling interrupt info if
+there's an actual interrupt pending. The hack actually made things
+worse because it caused KVM to _never_ fill interrupt info when the
+LAPIC resides in userspace (kvm_cpu_has_interrupt() queries
+interrupt.injected, which is always cleared by prepare_vmcs12() before
+reaching the hack in nested_vmx_vmexit()).
+
+Fixes: 6550c4df7e50 ("KVM: nVMX: Fix interrupt window request with "Acknowledge interrupt on exit"")
+Cc: stable@vger.kernel.org
+Cc: Liran Alon <liran.alon@oracle.com>
+Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/x86/include/asm/kvm_host.h | 2 +-
+ arch/x86/kvm/vmx.c | 27 +++++++++++----------------
+ arch/x86/kvm/x86.c | 10 +++++-----
+ 3 files changed, 17 insertions(+), 22 deletions(-)
+
+--- a/arch/x86/include/asm/kvm_host.h
++++ b/arch/x86/include/asm/kvm_host.h
+@@ -1032,7 +1032,7 @@ struct kvm_x86_ops {
+ bool (*mpx_supported)(void);
+ bool (*xsaves_supported)(void);
+
+- int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
++ int (*check_nested_events)(struct kvm_vcpu *vcpu);
+
+ void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
+
+--- a/arch/x86/kvm/vmx.c
++++ b/arch/x86/kvm/vmx.c
+@@ -6198,8 +6198,13 @@ static int vmx_nmi_allowed(struct kvm_vc
+
+ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
+ {
+- return (!to_vmx(vcpu)->nested.nested_run_pending &&
+- vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
++ if (to_vmx(vcpu)->nested.nested_run_pending)
++ return false;
++
++ if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
++ return true;
++
++ return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+ !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+ (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
+ }
+@@ -11659,7 +11664,7 @@ static void vmcs12_save_pending_event(st
+ }
+ }
+
+-static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
++static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
+ {
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long exit_qual;
+@@ -11697,8 +11702,7 @@ static int vmx_check_nested_events(struc
+ return 0;
+ }
+
+- if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
+- nested_exit_on_intr(vcpu)) {
++ if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) {
+ if (block_nested_events)
+ return -EBUSY;
+ nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
+@@ -12254,17 +12258,8 @@ static void nested_vmx_vmexit(struct kvm
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+ if (likely(!vmx->fail)) {
+- /*
+- * TODO: SDM says that with acknowledge interrupt on
+- * exit, bit 31 of the VM-exit interrupt information
+- * (valid interrupt) is always set to 1 on
+- * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't
+- * need kvm_cpu_has_interrupt(). See the commit
+- * message for details.
+- */
+- if (nested_exit_intr_ack_set(vcpu) &&
+- exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+- kvm_cpu_has_interrupt(vcpu)) {
++ if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
++ nested_exit_intr_ack_set(vcpu)) {
+ int irq = kvm_cpu_get_interrupt(vcpu);
+ WARN_ON(irq < 0);
+ vmcs12->vm_exit_intr_info = irq |
+--- a/arch/x86/kvm/x86.c
++++ b/arch/x86/kvm/x86.c
+@@ -6638,7 +6638,7 @@ static void update_cr8_intercept(struct
+ kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
+ }
+
+-static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
++static int inject_pending_event(struct kvm_vcpu *vcpu)
+ {
+ int r;
+
+@@ -6665,7 +6665,7 @@ static int inject_pending_event(struct k
+ }
+
+ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+- r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
++ r = kvm_x86_ops->check_nested_events(vcpu);
+ if (r != 0)
+ return r;
+ }
+@@ -6706,7 +6706,7 @@ static int inject_pending_event(struct k
+ * KVM_REQ_EVENT only on certain events and not unconditionally?
+ */
+ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+- r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
++ r = kvm_x86_ops->check_nested_events(vcpu);
+ if (r != 0)
+ return r;
+ }
+@@ -7152,7 +7152,7 @@ static int vcpu_enter_guest(struct kvm_v
+ goto out;
+ }
+
+- if (inject_pending_event(vcpu, req_int_win) != 0)
++ if (inject_pending_event(vcpu) != 0)
+ req_immediate_exit = true;
+ else {
+ /* Enable NMI/IRQ window open exits if needed.
+@@ -7360,7 +7360,7 @@ static inline int vcpu_block(struct kvm
+ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
+ {
+ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events)
+- kvm_x86_ops->check_nested_events(vcpu, false);
++ kvm_x86_ops->check_nested_events(vcpu);
+
+ return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
+ !vcpu->arch.apf.halted);
--- /dev/null
+From 4d4cee96fb7a3cc53702a9be8299bf525be4ee98 Mon Sep 17 00:00:00 2001
+From: David Hildenbrand <david@redhat.com>
+Date: Fri, 3 Apr 2020 17:30:47 +0200
+Subject: KVM: s390: vsie: Fix delivery of addressing exceptions
+
+From: David Hildenbrand <david@redhat.com>
+
+commit 4d4cee96fb7a3cc53702a9be8299bf525be4ee98 upstream.
+
+Whenever we get an -EFAULT, we failed to read in guest 2 physical
+address space. Such addressing exceptions are reported via a program
+intercept to the nested hypervisor.
+
+We faked the intercept, we have to return to guest 2. Instead, right
+now we would be returning -EFAULT from the intercept handler, eventually
+crashing the VM.
+the correct thing to do is to return 1 as rc == 1 is the internal
+representation of "we have to go back into g2".
+
+Addressing exceptions can only happen if the g2->g3 page tables
+reference invalid g2 addresses (say, either a table or the final page is
+not accessible - so something that basically never happens in sane
+environments.
+
+Identified by manual code inspection.
+
+Fixes: a3508fbe9dc6 ("KVM: s390: vsie: initial support for nested virtualization")
+Cc: <stable@vger.kernel.org> # v4.8+
+Signed-off-by: David Hildenbrand <david@redhat.com>
+Link: https://lore.kernel.org/r/20200403153050.20569-3-david@redhat.com
+Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
+Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
+[borntraeger@de.ibm.com: fix patch description]
+Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/s390/kvm/vsie.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/arch/s390/kvm/vsie.c
++++ b/arch/s390/kvm/vsie.c
+@@ -1027,6 +1027,7 @@ static int vsie_run(struct kvm_vcpu *vcp
+ scb_s->iprcc = PGM_ADDRESSING;
+ scb_s->pgmilc = 4;
+ scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, 4);
++ rc = 1;
+ }
+ return rc;
+ }
--- /dev/null
+From a1d032a49522cb5368e5dfb945a85899b4c74f65 Mon Sep 17 00:00:00 2001
+From: David Hildenbrand <david@redhat.com>
+Date: Fri, 3 Apr 2020 17:30:46 +0200
+Subject: KVM: s390: vsie: Fix region 1 ASCE sanity shadow address checks
+
+From: David Hildenbrand <david@redhat.com>
+
+commit a1d032a49522cb5368e5dfb945a85899b4c74f65 upstream.
+
+In case we have a region 1 the following calculation
+(31 + ((gmap->asce & _ASCE_TYPE_MASK) >> 2)*11)
+results in 64. As shifts beyond the size are undefined the compiler is
+free to use instructions like sllg. sllg will only use 6 bits of the
+shift value (here 64) resulting in no shift at all. That means that ALL
+addresses will be rejected.
+
+The can result in endless loops, e.g. when prefix cannot get mapped.
+
+Fixes: 4be130a08420 ("s390/mm: add shadow gmap support")
+Tested-by: Janosch Frank <frankja@linux.ibm.com>
+Reported-by: Janosch Frank <frankja@linux.ibm.com>
+Cc: <stable@vger.kernel.org> # v4.8+
+Signed-off-by: David Hildenbrand <david@redhat.com>
+Link: https://lore.kernel.org/r/20200403153050.20569-2-david@redhat.com
+Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
+Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
+[borntraeger@de.ibm.com: fix patch description, remove WARN_ON_ONCE]
+Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/s390/mm/gmap.c | 6 +++++-
+ 1 file changed, 5 insertions(+), 1 deletion(-)
+
+--- a/arch/s390/mm/gmap.c
++++ b/arch/s390/mm/gmap.c
+@@ -762,14 +762,18 @@ static void gmap_call_notifier(struct gm
+ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
+ unsigned long gaddr, int level)
+ {
++ const int asce_type = gmap->asce & _ASCE_TYPE_MASK;
+ unsigned long *table;
+
+ if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4))
+ return NULL;
+ if (gmap_is_shadow(gmap) && gmap->removed)
+ return NULL;
+- if (gaddr & (-1UL << (31 + ((gmap->asce & _ASCE_TYPE_MASK) >> 2)*11)))
++
++ if (asce_type != _ASCE_TYPE_REGION1 &&
++ gaddr & (-1UL << (31 + (asce_type >> 2) * 11)))
+ return NULL;
++
+ table = gmap->table;
+ switch (gmap->asce & _ASCE_TYPE_MASK) {
+ case _ASCE_TYPE_REGION1:
--- /dev/null
+From 31603d4fc2bb4f0815245d496cb970b27b4f636a Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <sean.j.christopherson@intel.com>
+Date: Sat, 21 Mar 2020 12:37:49 -0700
+Subject: KVM: VMX: Always VMCLEAR in-use VMCSes during crash with kexec support
+
+From: Sean Christopherson <sean.j.christopherson@intel.com>
+
+commit 31603d4fc2bb4f0815245d496cb970b27b4f636a upstream.
+
+VMCLEAR all in-use VMCSes during a crash, even if kdump's NMI shootdown
+interrupted a KVM update of the percpu in-use VMCS list.
+
+Because NMIs are not blocked by disabling IRQs, it's possible that
+crash_vmclear_local_loaded_vmcss() could be called while the percpu list
+of VMCSes is being modified, e.g. in the middle of list_add() in
+vmx_vcpu_load_vmcs(). This potential corner case was called out in the
+original commit[*], but the analysis of its impact was wrong.
+
+Skipping the VMCLEARs is wrong because it all but guarantees that a
+loaded, and therefore cached, VMCS will live across kexec and corrupt
+memory in the new kernel. Corruption will occur because the CPU's VMCS
+cache is non-coherent, i.e. not snooped, and so the writeback of VMCS
+memory on its eviction will overwrite random memory in the new kernel.
+The VMCS will live because the NMI shootdown also disables VMX, i.e. the
+in-progress VMCLEAR will #UD, and existing Intel CPUs do not flush the
+VMCS cache on VMXOFF.
+
+Furthermore, interrupting list_add() and list_del() is safe due to
+crash_vmclear_local_loaded_vmcss() using forward iteration. list_add()
+ensures the new entry is not visible to forward iteration unless the
+entire add completes, via WRITE_ONCE(prev->next, new). A bad "prev"
+pointer could be observed if the NMI shootdown interrupted list_del() or
+list_add(), but list_for_each_entry() does not consume ->prev.
+
+In addition to removing the temporary disabling of VMCLEAR, open code
+loaded_vmcs_init() in __loaded_vmcs_clear() and reorder VMCLEAR so that
+the VMCS is deleted from the list only after it's been VMCLEAR'd.
+Deleting the VMCS before VMCLEAR would allow a race where the NMI
+shootdown could arrive between list_del() and vmcs_clear() and thus
+neither flow would execute a successful VMCLEAR. Alternatively, more
+code could be moved into loaded_vmcs_init(), but that gets rather silly
+as the only other user, alloc_loaded_vmcs(), doesn't need the smp_wmb()
+and would need to work around the list_del().
+
+Update the smp_*() comments related to the list manipulation, and
+opportunistically reword them to improve clarity.
+
+[*] https://patchwork.kernel.org/patch/1675731/#3720461
+
+Fixes: 8f536b7697a0 ("KVM: VMX: provide the vmclear function and a bitmap to support VMCLEAR in kdump")
+Cc: stable@vger.kernel.org
+Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
+Message-Id: <20200321193751.24985-2-sean.j.christopherson@intel.com>
+Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/x86/kvm/vmx.c | 67 ++++++++++++-----------------------------------------
+ 1 file changed, 16 insertions(+), 51 deletions(-)
+
+--- a/arch/x86/kvm/vmx.c
++++ b/arch/x86/kvm/vmx.c
+@@ -1674,43 +1674,15 @@ static void vmcs_load(struct vmcs *vmcs)
+ }
+
+ #ifdef CONFIG_KEXEC_CORE
+-/*
+- * This bitmap is used to indicate whether the vmclear
+- * operation is enabled on all cpus. All disabled by
+- * default.
+- */
+-static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
+-
+-static inline void crash_enable_local_vmclear(int cpu)
+-{
+- cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
+-}
+-
+-static inline void crash_disable_local_vmclear(int cpu)
+-{
+- cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
+-}
+-
+-static inline int crash_local_vmclear_enabled(int cpu)
+-{
+- return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
+-}
+-
+ static void crash_vmclear_local_loaded_vmcss(void)
+ {
+ int cpu = raw_smp_processor_id();
+ struct loaded_vmcs *v;
+
+- if (!crash_local_vmclear_enabled(cpu))
+- return;
+-
+ list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
+ loaded_vmcss_on_cpu_link)
+ vmcs_clear(v->vmcs);
+ }
+-#else
+-static inline void crash_enable_local_vmclear(int cpu) { }
+-static inline void crash_disable_local_vmclear(int cpu) { }
+ #endif /* CONFIG_KEXEC_CORE */
+
+ static void __loaded_vmcs_clear(void *arg)
+@@ -1722,19 +1694,24 @@ static void __loaded_vmcs_clear(void *ar
+ return; /* vcpu migration can race with cpu offline */
+ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
+ per_cpu(current_vmcs, cpu) = NULL;
+- crash_disable_local_vmclear(cpu);
++
++ vmcs_clear(loaded_vmcs->vmcs);
++ if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
++ vmcs_clear(loaded_vmcs->shadow_vmcs);
++
+ list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
+
+ /*
+- * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link
+- * is before setting loaded_vmcs->vcpu to -1 which is done in
+- * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist
+- * then adds the vmcs into percpu list before it is deleted.
++ * Ensure all writes to loaded_vmcs, including deleting it from its
++ * current percpu list, complete before setting loaded_vmcs->vcpu to
++ * -1, otherwise a different cpu can see vcpu == -1 first and add
++ * loaded_vmcs to its percpu list before it's deleted from this cpu's
++ * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs().
+ */
+ smp_wmb();
+
+- loaded_vmcs_init(loaded_vmcs);
+- crash_enable_local_vmclear(cpu);
++ loaded_vmcs->cpu = -1;
++ loaded_vmcs->launched = 0;
+ }
+
+ static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
+@@ -2497,18 +2474,17 @@ static void vmx_vcpu_load(struct kvm_vcp
+ if (!already_loaded) {
+ loaded_vmcs_clear(vmx->loaded_vmcs);
+ local_irq_disable();
+- crash_disable_local_vmclear(cpu);
+
+ /*
+- * Read loaded_vmcs->cpu should be before fetching
+- * loaded_vmcs->loaded_vmcss_on_cpu_link.
+- * See the comments in __loaded_vmcs_clear().
++ * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to
++ * this cpu's percpu list, otherwise it may not yet be deleted
++ * from its previous cpu's percpu list. Pairs with the
++ * smb_wmb() in __loaded_vmcs_clear().
+ */
+ smp_rmb();
+
+ list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
+ &per_cpu(loaded_vmcss_on_cpu, cpu));
+- crash_enable_local_vmclear(cpu);
+ local_irq_enable();
+ }
+
+@@ -3804,17 +3780,6 @@ static int hardware_enable(void)
+ INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+ spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+
+- /*
+- * Now we can enable the vmclear operation in kdump
+- * since the loaded_vmcss_on_cpu list on this cpu
+- * has been initialized.
+- *
+- * Though the cpu is not in VMX operation now, there
+- * is no problem to enable the vmclear operation
+- * for the loaded_vmcss_on_cpu list is empty!
+- */
+- crash_enable_local_vmclear(cpu);
+-
+ rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
+
+ test_bits = FEATURE_CONTROL_LOCKED;
--- /dev/null
+From dbef2808af6c594922fe32833b30f55f35e9da6d Mon Sep 17 00:00:00 2001
+From: Vitaly Kuznetsov <vkuznets@redhat.com>
+Date: Wed, 1 Apr 2020 10:13:48 +0200
+Subject: KVM: VMX: fix crash cleanup when KVM wasn't used
+
+From: Vitaly Kuznetsov <vkuznets@redhat.com>
+
+commit dbef2808af6c594922fe32833b30f55f35e9da6d upstream.
+
+If KVM wasn't used at all before we crash the cleanup procedure fails with
+ BUG: unable to handle page fault for address: ffffffffffffffc8
+ #PF: supervisor read access in kernel mode
+ #PF: error_code(0x0000) - not-present page
+ PGD 23215067 P4D 23215067 PUD 23217067 PMD 0
+ Oops: 0000 [#8] SMP PTI
+ CPU: 0 PID: 3542 Comm: bash Kdump: loaded Tainted: G D 5.6.0-rc2+ #823
+ RIP: 0010:crash_vmclear_local_loaded_vmcss.cold+0x19/0x51 [kvm_intel]
+
+The root cause is that loaded_vmcss_on_cpu list is not yet initialized,
+we initialize it in hardware_enable() but this only happens when we start
+a VM.
+
+Previously, we used to have a bitmap with enabled CPUs and that was
+preventing [masking] the issue.
+
+Initialized loaded_vmcss_on_cpu list earlier, right before we assign
+crash_vmclear_loaded_vmcss pointer. blocked_vcpu_on_cpu list and
+blocked_vcpu_on_cpu_lock are moved altogether for consistency.
+
+Fixes: 31603d4fc2bb ("KVM: VMX: Always VMCLEAR in-use VMCSes during crash with kexec support")
+Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+Message-Id: <20200401081348.1345307-1-vkuznets@redhat.com>
+Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/x86/kvm/vmx.c | 12 +++++++-----
+ 1 file changed, 7 insertions(+), 5 deletions(-)
+
+--- a/arch/x86/kvm/vmx.c
++++ b/arch/x86/kvm/vmx.c
+@@ -3776,10 +3776,6 @@ static int hardware_enable(void)
+ if (cr4_read_shadow() & X86_CR4_VMXE)
+ return -EBUSY;
+
+- INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+- INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+- spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+-
+ rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
+
+ test_bits = FEATURE_CONTROL_LOCKED;
+@@ -12900,7 +12896,7 @@ module_exit(vmx_exit)
+
+ static int __init vmx_init(void)
+ {
+- int r;
++ int r, cpu;
+
+ r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+ __alignof__(struct vcpu_vmx), THIS_MODULE);
+@@ -12922,6 +12918,12 @@ static int __init vmx_init(void)
+ }
+ }
+
++ for_each_possible_cpu(cpu) {
++ INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
++ INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
++ spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
++ }
++
+ #ifdef CONFIG_KEXEC_CORE
+ rcu_assign_pointer(crash_vmclear_loaded_vmcss,
+ crash_vmclear_local_loaded_vmcss);
--- /dev/null
+From edd4fa37baa6ee8e44dc65523b27bd6fe44c94de Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <sean.j.christopherson@intel.com>
+Date: Tue, 18 Feb 2020 13:07:15 -0800
+Subject: KVM: x86: Allocate new rmap and large page tracking when moving memslot
+
+From: Sean Christopherson <sean.j.christopherson@intel.com>
+
+commit edd4fa37baa6ee8e44dc65523b27bd6fe44c94de upstream.
+
+Reallocate a rmap array and recalcuate large page compatibility when
+moving an existing memslot to correctly handle the alignment properties
+of the new memslot. The number of rmap entries required at each level
+is dependent on the alignment of the memslot's base gfn with respect to
+that level, e.g. moving a large-page aligned memslot so that it becomes
+unaligned will increase the number of rmap entries needed at the now
+unaligned level.
+
+Not updating the rmap array is the most obvious bug, as KVM accesses
+garbage data beyond the end of the rmap. KVM interprets the bad data as
+pointers, leading to non-canonical #GPs, unexpected #PFs, etc...
+
+ general protection fault: 0000 [#1] SMP
+ CPU: 0 PID: 1909 Comm: move_memory_reg Not tainted 5.4.0-rc7+ #139
+ Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
+ RIP: 0010:rmap_get_first+0x37/0x50 [kvm]
+ Code: <48> 8b 3b 48 85 ff 74 ec e8 6c f4 ff ff 85 c0 74 e3 48 89 d8 5b c3
+ RSP: 0018:ffffc9000021bbc8 EFLAGS: 00010246
+ RAX: ffff00617461642e RBX: ffff00617461642e RCX: 0000000000000012
+ RDX: ffff88827400f568 RSI: ffffc9000021bbe0 RDI: ffff88827400f570
+ RBP: 0010000000000000 R08: ffffc9000021bd00 R09: ffffc9000021bda8
+ R10: ffffc9000021bc48 R11: 0000000000000000 R12: 0030000000000000
+ R13: 0000000000000000 R14: ffff88827427d700 R15: ffffc9000021bce8
+ FS: 00007f7eda014700(0000) GS:ffff888277a00000(0000) knlGS:0000000000000000
+ CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+ CR2: 00007f7ed9216ff8 CR3: 0000000274391003 CR4: 0000000000162eb0
+ Call Trace:
+ kvm_mmu_slot_set_dirty+0xa1/0x150 [kvm]
+ __kvm_set_memory_region.part.64+0x559/0x960 [kvm]
+ kvm_set_memory_region+0x45/0x60 [kvm]
+ kvm_vm_ioctl+0x30f/0x920 [kvm]
+ do_vfs_ioctl+0xa1/0x620
+ ksys_ioctl+0x66/0x70
+ __x64_sys_ioctl+0x16/0x20
+ do_syscall_64+0x4c/0x170
+ entry_SYSCALL_64_after_hwframe+0x44/0xa9
+ RIP: 0033:0x7f7ed9911f47
+ Code: <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 21 6f 2c 00 f7 d8 64 89 01 48
+ RSP: 002b:00007ffc00937498 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
+ RAX: ffffffffffffffda RBX: 0000000001ab0010 RCX: 00007f7ed9911f47
+ RDX: 0000000001ab1350 RSI: 000000004020ae46 RDI: 0000000000000004
+ RBP: 000000000000000a R08: 0000000000000000 R09: 00007f7ed9214700
+ R10: 00007f7ed92149d0 R11: 0000000000000246 R12: 00000000bffff000
+ R13: 0000000000000003 R14: 00007f7ed9215000 R15: 0000000000000000
+ Modules linked in: kvm_intel kvm irqbypass
+ ---[ end trace 0c5f570b3358ca89 ]---
+
+The disallow_lpage tracking is more subtle. Failure to update results
+in KVM creating large pages when it shouldn't, either due to stale data
+or again due to indexing beyond the end of the metadata arrays, which
+can lead to memory corruption and/or leaking data to guest/userspace.
+
+Note, the arrays for the old memslot are freed by the unconditional call
+to kvm_free_memslot() in __kvm_set_memory_region().
+
+Fixes: 05da45583de9b ("KVM: MMU: large page support")
+Cc: stable@vger.kernel.org
+Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
+Reviewed-by: Peter Xu <peterx@redhat.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/x86/kvm/x86.c | 11 +++++++++++
+ 1 file changed, 11 insertions(+)
+
+--- a/arch/x86/kvm/x86.c
++++ b/arch/x86/kvm/x86.c
+@@ -8584,6 +8584,13 @@ int kvm_arch_create_memslot(struct kvm *
+ {
+ int i;
+
++ /*
++ * Clear out the previous array pointers for the KVM_MR_MOVE case. The
++ * old arrays will be freed by __kvm_set_memory_region() if installing
++ * the new memslot is successful.
++ */
++ memset(&slot->arch, 0, sizeof(slot->arch));
++
+ for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
+ struct kvm_lpage_info *linfo;
+ unsigned long ugfn;
+@@ -8657,6 +8664,10 @@ int kvm_arch_prepare_memory_region(struc
+ const struct kvm_userspace_memory_region *mem,
+ enum kvm_mr_change change)
+ {
++ if (change == KVM_MR_MOVE)
++ return kvm_arch_create_memslot(kvm, memslot,
++ mem->memory_size >> PAGE_SHIFT);
++
+ return 0;
+ }
+
ath9k-handle-txpower-changes-even-when-tpc-is-disabled.patch
signal-extend-exec_id-to-64bits.patch
x86-entry-32-add-missing-asm_clac-to-general_protection-entry.patch
+kvm-nvmx-properly-handle-userspace-interrupt-window-request.patch
+kvm-s390-vsie-fix-region-1-asce-sanity-shadow-address-checks.patch
+kvm-s390-vsie-fix-delivery-of-addressing-exceptions.patch
+kvm-x86-allocate-new-rmap-and-large-page-tracking-when-moving-memslot.patch
+kvm-vmx-always-vmclear-in-use-vmcses-during-crash-with-kexec-support.patch
+kvm-vmx-fix-crash-cleanup-when-kvm-wasn-t-used.patch
+cifs-fix-bug-which-the-return-value-by-asynchronous-read-is-error.patch
+btrfs-drop-block-from-cache-on-error-in-relocation.patch
+crypto-mxs-dcp-fix-scatterlist-linearization-for-hash.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
