From: Mark Tomlinson stable inclusion from linux-4.19.199 commit 51fc12f4d37622fa0c481604833f98f11b1cac4f category: bugfix issue: #I49DRJ CVE: CVE-2021-38204 -------------------------------- commit b5fdf5c6e6bee35837e160c00ac89327bdad031b upstream. The MAX-3421 USB driver remembers the state of the USB toggles for a device/endpoint. To save SPI writes, this was only done when a new device/endpoint was being used. Unfortunately, if the old device was removed, this would cause writes to freed memory. To fix this, a simpler scheme is used. The toggles are read from hardware when a URB is completed, and the toggles are always written to hardware when any URB transaction is started. This will cause a few more SPI transactions, but no causes kernel panics. Fixes: 2d53139f3162 ("Add support for using a MAX3421E chip as a host driver.") Cc: stable Signed-off-by: Mark Tomlinson Link: https://lore.kernel.org/r/20210625031456.8632-1-mark.tomlinson@alliedtelesis... Signed-off-by: Greg Kroah-Hartman Signed-off-by: Yang Yingliang Reviewed-by: Xiu Jianfeng Signed-off-by: Yang Yingliang Signed-off-by: Yu Changchun --- drivers/usb/host/max3421-hcd.c | 44 +++++++++++----------------------- 1 file changed, 14 insertions(+), 30 deletions(-) diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c index afa321ab55fc..4a33a18dc0b3 100644 --- a/drivers/usb/host/max3421-hcd.c +++ b/drivers/usb/host/max3421-hcd.c @@ -153,8 +153,6 @@ struct max3421_hcd { */ struct urb *curr_urb; enum scheduling_pass sched_pass; - struct usb_device *loaded_dev; /* dev that's loaded into the chip */ - int loaded_epnum; /* epnum whose toggles are loaded */ int urb_done; /* > 0 -> no errors, < 0: errno */ size_t curr_len; u8 hien; @@ -492,39 +490,17 @@ max3421_set_speed(struct usb_hcd *hcd, struct usb_device *dev) * Caller must NOT hold HCD spinlock. */ static void -max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum, - int force_toggles) +max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum) { - struct max3421_hcd *max3421_hcd = hcd_to_max3421(hcd); - int old_epnum, same_ep, rcvtog, sndtog; - struct usb_device *old_dev; + int rcvtog, sndtog; u8 hctl; - old_dev = max3421_hcd->loaded_dev; - old_epnum = max3421_hcd->loaded_epnum; - - same_ep = (dev == old_dev && epnum == old_epnum); - if (same_ep && !force_toggles) - return; - - if (old_dev && !same_ep) { - /* save the old end-points toggles: */ - u8 hrsl = spi_rd8(hcd, MAX3421_REG_HRSL); - - rcvtog = (hrsl >> MAX3421_HRSL_RCVTOGRD_BIT) & 1; - sndtog = (hrsl >> MAX3421_HRSL_SNDTOGRD_BIT) & 1; - - /* no locking: HCD (i.e., we) own toggles, don't we? */ - usb_settoggle(old_dev, old_epnum, 0, rcvtog); - usb_settoggle(old_dev, old_epnum, 1, sndtog); - } /* setup new endpoint's toggle bits: */ rcvtog = usb_gettoggle(dev, epnum, 0); sndtog = usb_gettoggle(dev, epnum, 1); hctl = (BIT(rcvtog + MAX3421_HCTL_RCVTOG0_BIT) | BIT(sndtog + MAX3421_HCTL_SNDTOG0_BIT)); - max3421_hcd->loaded_epnum = epnum; spi_wr8(hcd, MAX3421_REG_HCTL, hctl); /* @@ -532,7 +508,6 @@ max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum, * address-assignment so it's best to just always load the * address whenever the end-point changed/was forced. */ - max3421_hcd->loaded_dev = dev; spi_wr8(hcd, MAX3421_REG_PERADDR, dev->devnum); } @@ -667,7 +642,7 @@ max3421_select_and_start_urb(struct usb_hcd *hcd) struct max3421_hcd *max3421_hcd = hcd_to_max3421(hcd); struct urb *urb, *curr_urb = NULL; struct max3421_ep *max3421_ep; - int epnum, force_toggles = 0; + int epnum; struct usb_host_endpoint *ep; struct list_head *pos; unsigned long flags; @@ -777,7 +752,6 @@ max3421_select_and_start_urb(struct usb_hcd *hcd) usb_settoggle(urb->dev, epnum, 0, 1); usb_settoggle(urb->dev, epnum, 1, 1); max3421_ep->pkt_state = PKT_STATE_SETUP; - force_toggles = 1; } else max3421_ep->pkt_state = PKT_STATE_TRANSFER; } @@ -785,7 +759,7 @@ max3421_select_and_start_urb(struct usb_hcd *hcd) spin_unlock_irqrestore(&max3421_hcd->lock, flags); max3421_ep->last_active = max3421_hcd->frame_number; - max3421_set_address(hcd, urb->dev, epnum, force_toggles); + max3421_set_address(hcd, urb->dev, epnum); max3421_set_speed(hcd, urb->dev); max3421_next_transfer(hcd, 0); return 1; @@ -1380,6 +1354,16 @@ max3421_urb_done(struct usb_hcd *hcd) status = 0; urb = max3421_hcd->curr_urb; if (urb) { + /* save the old end-points toggles: */ + u8 hrsl = spi_rd8(hcd, MAX3421_REG_HRSL); + int rcvtog = (hrsl >> MAX3421_HRSL_RCVTOGRD_BIT) & 1; + int sndtog = (hrsl >> MAX3421_HRSL_SNDTOGRD_BIT) & 1; + int epnum = usb_endpoint_num(&urb->ep->desc); + + /* no locking: HCD (i.e., we) own toggles, don't we? */ + usb_settoggle(urb->dev, epnum, 0, rcvtog); + usb_settoggle(urb->dev, epnum, 1, sndtog); + max3421_hcd->curr_urb = NULL; spin_lock_irqsave(&max3421_hcd->lock, flags); usb_hcd_unlink_urb_from_ep(hcd, urb); -- 2.22.0

From: Trond Myklebust stable inclusion from linux-4.19.198 commit 743f6b973c8ba8a0a5ed15ab11e1d07fa00d5368 category: bugfix issue: #I49DVY CVE: CVE-2021-38199 -------------------------------- [ Upstream commit dd99e9f98fbf423ff6d365b37a98e8879170f17c ] Set up the connection to the NFSv4 server in nfs4_alloc_client(), before we've added the struct nfs_client to the net-namespace's nfs_client_list so that a downed server won't cause other mounts to hang in the trunking detection code. Reported-by: Michael Wakabayashi Fixes: 5c6e5b60aae4 ("NFS: Fix an Oops in the pNFS files and flexfiles connection setup to the DS") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin Signed-off-by: Yang Yingliang Signed-off-by: Yu Changchun --- fs/nfs/nfs4client.c | 82 +++++++++++++++++++++++---------------------- 1 file changed, 42 insertions(+), 40 deletions(-) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index faaabbedc891..ca98dbc6ac0f 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -191,8 +191,11 @@ void nfs40_shutdown_client(struct nfs_client *clp) struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) { - int err; + char buf[INET6_ADDRSTRLEN + 1]; + const char *ip_addr = cl_init->ip_addr; struct nfs_client *clp = nfs_alloc_client(cl_init); + int err; + if (IS_ERR(clp)) return clp; @@ -216,6 +219,44 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) init_waitqueue_head(&clp->cl_lock_waitq); #endif INIT_LIST_HEAD(&clp->pending_cb_stateids); + + if (cl_init->minorversion != 0) + __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags); + __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); + + /* + * Set up the connection to the server before we add add to the + * global list. + */ + err = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_GSS_KRB5I); + if (err == -EINVAL) + err = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX); + if (err < 0) + goto error; + + /* If no clientaddr= option was specified, find a usable cb address */ + if (ip_addr == NULL) { + struct sockaddr_storage cb_addr; + struct sockaddr *sap = (struct sockaddr *)&cb_addr; + + err = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr)); + if (err < 0) + goto error; + err = rpc_ntop(sap, buf, sizeof(buf)); + if (err < 0) + goto error; + ip_addr = (const char *)buf; + } + strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr)); + + err = nfs_idmap_new(clp); + if (err < 0) { + dprintk("%s: failed to create idmapper. Error = %d\n", + __func__, err); + goto error; + } + __set_bit(NFS_CS_IDMAP, &clp->cl_res_state); return clp; error: @@ -368,8 +409,6 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp) struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct nfs_client_initdata *cl_init) { - char buf[INET6_ADDRSTRLEN + 1]; - const char *ip_addr = cl_init->ip_addr; struct nfs_client *old; int error; @@ -377,43 +416,6 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, /* the client is initialised already */ return clp; - /* Check NFS protocol revision and initialize RPC op vector */ - clp->rpc_ops = &nfs_v4_clientops; - - if (clp->cl_minorversion != 0) - __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags); - __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); - __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); - - error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_GSS_KRB5I); - if (error == -EINVAL) - error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX); - if (error < 0) - goto error; - - /* If no clientaddr= option was specified, find a usable cb address */ - if (ip_addr == NULL) { - struct sockaddr_storage cb_addr; - struct sockaddr *sap = (struct sockaddr *)&cb_addr; - - error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr)); - if (error < 0) - goto error; - error = rpc_ntop(sap, buf, sizeof(buf)); - if (error < 0) - goto error; - ip_addr = (const char *)buf; - } - strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr)); - - error = nfs_idmap_new(clp); - if (error < 0) { - dprintk("%s: failed to create idmapper. Error = %d\n", - __func__, error); - goto error; - } - __set_bit(NFS_CS_IDMAP, &clp->cl_res_state); - error = nfs4_init_client_minor_version(clp); if (error < 0) goto error; -- 2.22.0

From: Haoran Luo stable inclusion from linux-4.19.199 commit 6a99bfee7f5625d2577a5c3b09a2bd2a845feb8a category: bugfix issue: #I49DZ2 CVE: CVE-2021-3679 -------------------------------- commit 67f0d6d9883c13174669f88adac4f0ee656cc16a upstream. The "rb_per_cpu_empty()" misinterpret the condition (as not-empty) when "head_page" and "commit_page" of "struct ring_buffer_per_cpu" points to the same buffer page, whose "buffer_data_page" is empty and "read" field is non-zero. An error scenario could be constructed as followed (kernel perspective): 1. All pages in the buffer has been accessed by reader(s) so that all of them will have non-zero "read" field. 2. Read and clear all buffer pages so that "rb_num_of_entries()" will return 0 rendering there's no more data to read. It is also required that the "read_page", "commit_page" and "tail_page" points to the same page, while "head_page" is the next page of them. 3. Invoke "ring_buffer_lock_reserve()" with large enough "length" so that it shot pass the end of current tail buffer page. Now the "head_page", "commit_page" and "tail_page" points to the same page. 4. Discard current event with "ring_buffer_discard_commit()", so that "head_page", "commit_page" and "tail_page" points to a page whose buffer data page is now empty. When the error scenario has been constructed, "tracing_read_pipe" will be trapped inside a deadloop: "trace_empty()" returns 0 since "rb_per_cpu_empty()" returns 0 when it hits the CPU containing such constructed ring buffer. Then "trace_find_next_entry_inc()" always return NULL since "rb_num_of_entries()" reports there's no more entry to read. Finally "trace_seq_to_user()" returns "-EBUSY" spanking "tracing_read_pipe" back to the start of the "waitagain" loop. I've also written a proof-of-concept script to construct the scenario and trigger the bug automatically, you can use it to trace and validate my reasoning above: https://github.com/aegistudio/RingBufferDetonator.git Tests has been carried out on linux kernel 5.14-rc2 (2734d6c1b1a089fb593ef6a23d4b70903526fe0c), my fixed version of kernel (for testing whether my update fixes the bug) and some older kernels (for range of affected kernels). Test result is also attached to the proof-of-concept repository. Link: https://lore.kernel.org/linux-trace-devel/YPaNxsIlb2yjSi5Y@aegistudio/ Link: https://lore.kernel.org/linux-trace-devel/YPgrN85WL9VyrZ55@aegistudio Cc: stable@vger.kernel.org Fixes: bf41a158cacba ("ring-buffer: make reentrant") Suggested-by: Linus Torvalds Signed-off-by: Haoran Luo Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Greg Kroah-Hartman Signed-off-by: Yang Yingliang Signed-off-by: Yu Changchun --- kernel/trace/ring_buffer.c | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index eef05eb3b284..87f614ad4141 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3138,10 +3138,30 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) if (unlikely(!head)) return true; - return reader->read == rb_page_commit(reader) && - (commit == reader || - (commit == head && - head->read == rb_page_commit(commit))); + /* Reader should exhaust content in reader page */ + if (reader->read != rb_page_commit(reader)) + return false; + + /* + * If writers are committing on the reader page, knowing all + * committed content has been read, the ring buffer is empty. + */ + if (commit == reader) + return true; + + /* + * If writers are committing on a page other than reader page + * and head page, there should always be content to read. + */ + if (commit != head) + return false; + + /* + * Writers are committing on the head page, we just need + * to care about there're committed data, and the reader will + * swap reader page with head page when it is to read data. + */ + return rb_page_commit(commit) == 0; } /** -- 2.22.0

From: Lai Jiangshan stable inclusion from linux-4.19.204 commit 4c07e70141eebd3db64297515a427deea4822957 issue: #I49ECL CVE: CVE-2021-38198 -------------------------------- commit b1bd5cba3306691c771d558e94baa73e8b0b96b7 upstream. When computing the access permissions of a shadow page, use the effective permissions of the walk up to that point, i.e. the logic AND of its parents' permissions. Two guest PxE entries that point at the same table gfn need to be shadowed with different shadow pages if their parents' permissions are different. KVM currently uses the effective permissions of the last non-leaf entry for all non-leaf entries. Because all non-leaf SPTEs have full ("uwx") permissions, and the effective permissions are recorded only in role.access and merged into the leaves, this can lead to incorrect reuse of a shadow page and eventually to a missing guest protection page fault. For example, here is a shared pagetable: pgd[] pud[] pmd[] virtual address pointers /->pmd1(u--)->pte1(uw-)->page1 <- ptr1 (u--) /->pud1(uw-)--->pmd2(uw-)->pte2(uw-)->page2 <- ptr2 (uw-) pgd-| (shared pmd[] as above) \->pud2(u--)--->pmd1(u--)->pte1(uw-)->page1 <- ptr3 (u--) \->pmd2(uw-)->pte2(uw-)->page2 <- ptr4 (u--) pud1 and pud2 point to the same pmd table, so: - ptr1 and ptr3 points to the same page. - ptr2 and ptr4 points to the same page. (pud1 and pud2 here are pud entries, while pmd1 and pmd2 here are pmd entries) - First, the guest reads from ptr1 first and KVM prepares a shadow page table with role.access=u--, from ptr1's pud1 and ptr1's pmd1. "u--" comes from the effective permissions of pgd, pud1 and pmd1, which are stored in pt->access. "u--" is used also to get the pagetable for pud1, instead of "uw-". - Then the guest writes to ptr2 and KVM reuses pud1 which is present. The hypervisor set up a shadow page for ptr2 with pt->access is "uw-" even though the pud1 pmd (because of the incorrect argument to kvm_mmu_get_page in the previous step) has role.access="u--". - Then the guest reads from ptr3. The hypervisor reuses pud1's shadow pmd for pud2, because both use "u--" for their permissions. Thus, the shadow pmd already includes entries for both pmd1 and pmd2. - At last, the guest writes to ptr4. This causes no vmexit or pagefault, because pud1's shadow page structures included an "uw-" page even though its role.access was "u--". Any kind of shared pagetable might have the similar problem when in virtual machine without TDP enabled if the permissions are different from different ancestors. In order to fix the problem, we change pt->access to be an array, and any access in it will not include permissions ANDed from child ptes. The test code is: https://lore.kernel.org/kvm/20210603050537.19605-1-jiangshanlai@gmail.com/ Remember to test it with TDP disabled. The problem had existed long before the commit 41074d07c78b ("KVM: MMU: Fix inherited permissions for emulated guest pte updates"), and it is hard to find which is the culprit. So there is no fixes tag here. Signed-off-by: Lai Jiangshan Message-Id: <20210603052455.21023-1-jiangshanlai@gmail.com> Cc: stable@vger.kernel.org Fixes: cea0f0e7ea54 ("[PATCH] KVM: MMU: Shadow page table caching") Signed-off-by: Paolo Bonzini [OP: - apply arch/x86/kvm/mmu/* changes to arch/x86/kvm - apply documentation changes to Documentation/virtual/kvm/mmu.txt - adjusted context in arch/x86/kvm/paging_tmpl.h] Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman Signed-off-by: Yang Yingliang Reviewed-by: Xiu Jianfeng Signed-off-by: Yang Yingliang Signed-off-by: Yu Changchun --- Documentation/virtual/kvm/mmu.txt | 4 ++-- arch/x86/kvm/paging_tmpl.h | 14 +++++++++----- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index e507a9e0421e..851a8abcadce 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -152,8 +152,8 @@ Shadow pages contain the following information: shadow pages) so role.quadrant takes values in the range 0..3. Each quadrant maps 1GB virtual address space. role.access: - Inherited guest access permissions in the form uwx. Note execute - permission is positive, not negative. + Inherited guest access permissions from the parent ptes in the form uwx. + Note execute permission is positive, not negative. role.invalid: The page is invalid and should not be used. It is a root page that is currently pinned (by a cpu hardware register pointing to it); once it is diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 8220190b0605..9e15818de973 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -93,8 +93,8 @@ struct guest_walker { gpa_t pte_gpa[PT_MAX_FULL_LEVELS]; pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS]; bool pte_writable[PT_MAX_FULL_LEVELS]; - unsigned pt_access; - unsigned pte_access; + unsigned int pt_access[PT_MAX_FULL_LEVELS]; + unsigned int pte_access; gfn_t gfn; struct x86_exception fault; }; @@ -388,13 +388,15 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, } walker->ptes[walker->level - 1] = pte; + + /* Convert to ACC_*_MASK flags for struct guest_walker. */ + walker->pt_access[walker->level - 1] = FNAME(gpte_access)(pt_access ^ walk_nx_mask); } while (!is_last_gpte(mmu, walker->level, pte)); pte_pkey = FNAME(gpte_pkeys)(vcpu, pte); accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0; /* Convert to ACC_*_MASK flags for struct guest_walker. */ - walker->pt_access = FNAME(gpte_access)(pt_access ^ walk_nx_mask); walker->pte_access = FNAME(gpte_access)(pte_access ^ walk_nx_mask); errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access); if (unlikely(errcode)) @@ -433,7 +435,8 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, } pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, walker->pte_access, walker->pt_access); + __func__, (u64)pte, walker->pte_access, + walker->pt_access[walker->level - 1]); return 1; error: @@ -602,7 +605,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; - unsigned direct_access, access = gw->pt_access; + unsigned int direct_access, access; int top_level, ret; gfn_t gfn, base_gfn; @@ -634,6 +637,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, sp = NULL; if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; + access = gw->pt_access[it.level - 2]; sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, false, access); } -- 2.22.0