From: Xin Xiong xiongx18@fudan.edu.cn

[ Upstream commit 9c9cb23e00ddf45679b21b4dacc11d1ae7961ebe ]

The issue happens on an error path in __xfrm_policy_check(). When the fetching process of the object `pols[1]` fails, the function simply returns 0, forgetting to decrement the reference count of `pols[0]`, which is incremented earlier by either xfrm_sk_policy_lookup() or xfrm_policy_lookup(). This may result in memory leaks.

Fix it by decreasing the reference count of `pols[0]` in that path.

Fixes: 134b0fc544ba ("IPsec: propagate security module errors up from flow_cache_lookup") Signed-off-by: Xin Xiong xiongx18@fudan.edu.cn Signed-off-by: Xin Tan tanxin.ctf@gmail.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_policy.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 0894108f561cb..ae90a273475c0 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2538,6 +2538,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); + xfrm_pol_put(pols[0]); return 0; } pols[1]->curlft.use_time = get_seconds();

From: Bernard Pidoux f6bvp@free.fr

[ Upstream commit 3c53cd65dece47dd1f9d3a809f32e59d1d87b2b8 ]

Commit 3b3fd068c56e3fbea30090859216a368398e39bf added NULL check for `rose_loopback_neigh->dev` in rose_loopback_timer() but omitted to check rose_loopback_neigh->loopback.

It thus prevents *all* rose connect.

The reason is that a special rose_neigh loopback has a NULL device.

/proc/net/rose_neigh illustrates it via rose_neigh_show() function : [...] seq_printf(seq, "%05d %-9s %-4s %3d %3d %3s %3s %3lu %3lu", rose_neigh->number, (rose_neigh->loopback) ? "RSLOOP-0" : ax2asc(buf, &rose_neigh->callsign), rose_neigh->dev ? rose_neigh->dev->name : "???", rose_neigh->count,

/proc/net/rose_neigh displays special rose_loopback_neigh->loopback as callsign RSLOOP-0:

addr callsign dev count use mode restart t0 tf digipeaters 00001 RSLOOP-0 ??? 1 2 DCE yes 0 0

By checking rose_loopback_neigh->loopback, rose_rx_call_request() is called even in case rose_loopback_neigh->dev is NULL. This repairs rose connections.

Verification with rose client application FPAC:

FPAC-Node v 4.1.3 (built Aug 5 2022) for LINUX (help = h) F6BVP-4 (Commands = ?) : u Users - AX.25 Level 2 sessions : Port Callsign Callsign AX.25 state ROSE state NetRom status axudp F6BVP-5 -> F6BVP-9 Connected Connected ---------

Fixes: 3b3fd068c56e ("rose: Fix Null pointer dereference in rose_send_frame()") Signed-off-by: Bernard Pidoux f6bvp@free.fr Suggested-by: Francois Romieu romieu@fr.zoreil.com Cc: Thomas DL9SAU Osterried thomas@osterried.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/rose/rose_loopback.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 0f371e50d9c4e..e6526c8ecacc0 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -99,7 +99,8 @@ static void rose_loopback_timer(unsigned long param) }

if (frametype == ROSE_CALL_REQUEST) { - if (!rose_loopback_neigh->dev) { + if (!rose_loopback_neigh->dev && + !rose_loopback_neigh->loopback) { kfree_skb(skb); continue; }

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 94254f990c07e9ddf1634e0b727fab821c3b5bf9 ]

Instead of offset and length are truncation to u8, report ERANGE.

Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nft_payload.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index f73d47b3ffb72..82bcd14fbcb3d 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -287,6 +287,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, { enum nft_payload_bases base; unsigned int offset, len; + int err;

if (tb[NFTA_PAYLOAD_BASE] == NULL || tb[NFTA_PAYLOAD_OFFSET] == NULL || @@ -312,8 +313,13 @@ nft_payload_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_PAYLOAD_DREG] == NULL) return ERR_PTR(-EINVAL);

- offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); - len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset); + if (err < 0) + return ERR_PTR(err); + + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len); + if (err < 0) + return ERR_PTR(err);

if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER)

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit d2154b0afa73c0159b2856f875c6b4fe7cf6a95e ]

While reading sysctl_tstamp_allow_data, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: b245be1f4db1 ("net-timestamp: no-payload only sysctl") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 22b216629f9bc..022e26c180241 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3905,7 +3905,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { bool ret;

- if (likely(sysctl_tstamp_allow_data || tsonly)) + if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly)) return true;

read_lock_bh(&sk->sk_callback_lock);

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit e59ef36f0795696ab229569c153936bfd068d21c ]

While reading sysctl_net_busy_read, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: 2d48d67fa8cd ("net: poll/select low latency socket support") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/sock.c b/net/core/sock.c index 1845a37d9f7e1..e4b28c10901ec 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2508,7 +2508,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)

#ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_busy_read; + sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif

sk->sk_max_pacing_rate = ~0U;

From: Jacob Keller jacob.e.keller@intel.com

[ Upstream commit 25d7a5f5a6bb15a2dae0a3f39ea5dda215024726 ]

The ixgbe_ptp_start_cyclecounter is intended to be called whenever the cyclecounter parameters need to be changed.

Since commit a9763f3cb54c ("ixgbe: Update PTP to support X550EM_x devices"), this function has cleared the SYSTIME registers and reset the TSAUXC DISABLE_SYSTIME bit.

While these need to be cleared during ixgbe_ptp_reset, it is wrong to clear them during ixgbe_ptp_start_cyclecounter. This function may be called during both reset and link status change. When link changes, the SYSTIME counter is still operating normally, but the cyclecounter should be updated to account for the possibly changed parameters.

Clearing SYSTIME when link changes causes the timecounter to jump because the cycle counter now reads zero.

Extract the SYSTIME initialization out to a new function and call this during ixgbe_ptp_reset. This prevents the timecounter adjustment and avoids an unnecessary reset of the current time.

This also restores the original SYSTIME clearing that occurred during ixgbe_ptp_reset before the commit above.

Reported-by: Steve Payne spayne@aurora.tech Reported-by: Ilya Evenbach ievenbach@aurora.tech Fixes: a9763f3cb54c ("ixgbe: Update PTP to support X550EM_x devices") Signed-off-by: Jacob Keller jacob.e.keller@intel.com Tested-by: Gurucharan gurucharanx.g@intel.com (A Contingent worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 59 +++++++++++++++----- 1 file changed, 46 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index a93a1b3bb8e4d..2ae59af3e16f0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -1080,7 +1080,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) struct cyclecounter cc; unsigned long flags; u32 incval = 0; - u32 tsauxc = 0; u32 fuse0 = 0;

/* For some of the boards below this mask is technically incorrect. @@ -1115,18 +1114,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) case ixgbe_mac_x550em_a: case ixgbe_mac_X550: cc.read = ixgbe_ptp_read_X550; - - /* enable SYSTIME counter */ - IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0); - IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); - IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); - tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); - IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, - tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME); - IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS); - IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC); - - IXGBE_WRITE_FLUSH(hw); break; case ixgbe_mac_X540: cc.read = ixgbe_ptp_read_82599; @@ -1158,6 +1145,50 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) spin_unlock_irqrestore(&adapter->tmreg_lock, flags); }

+/** + * ixgbe_ptp_init_systime - Initialize SYSTIME registers + * @adapter: the ixgbe private board structure + * + * Initialize and start the SYSTIME registers. + */ +static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 tsauxc; + + switch (hw->mac.type) { + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + case ixgbe_mac_X550: + tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); + + /* Reset SYSTIME registers to 0 */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); + + /* Reset interrupt settings */ + IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS); + IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC); + + /* Activate the SYSTIME counter */ + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, + tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME); + break; + case ixgbe_mac_X540: + case ixgbe_mac_82599EB: + /* Reset SYSTIME registers to 0 */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); + break; + default: + /* Other devices aren't supported */ + return; + }; + + IXGBE_WRITE_FLUSH(hw); +} + /** * ixgbe_ptp_reset * @adapter: the ixgbe private board structure @@ -1184,6 +1215,8 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter)

ixgbe_ptp_start_cyclecounter(adapter);

+ ixgbe_ptp_init_systime(adapter); + spin_lock_irqsave(&adapter->tmreg_lock, flags); timecounter_init(&adapter->hw_tc, &adapter->hw_cc, ktime_to_ns(ktime_get_real()));

From: Siddh Raman Pant code@siddh.me

commit c490a0b5a4f36da3918181a8acdc6991d967c5f3 upstream.

The userspace can configure a loop using an ioctl call, wherein a configuration of type loop_config is passed (see lo_ioctl()'s case on line 1550 of drivers/block/loop.c). This proceeds to call loop_configure() which in turn calls loop_set_status_from_info() (see line 1050 of loop.c), passing &config->info which is of type loop_info64*. This function then sets the appropriate values, like the offset.

loop_device has lo_offset of type loff_t (see line 52 of loop.c), which is typdef-chained to long long, whereas loop_info64 has lo_offset of type __u64 (see line 56 of include/uapi/linux/loop.h).

The function directly copies offset from info to the device as follows (See line 980 of loop.c): lo->lo_offset = info->lo_offset;

This results in an overflow, which triggers a warning in iomap_iter() due to a call to iomap_iter_done() which has: WARN_ON_ONCE(iter->iomap.offset > iter->pos);

Thus, check for negative value during loop_set_status_from_info().

Bug report: https://syzkaller.appspot.com/bug?id=c620fe14aac810396d3c3edc9ad73848bf69a29...

Reported-and-tested-by: syzbot+a8e049cd3abd342936b6@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Siddh Raman Pant code@siddh.me Reviewed-by: Christoph Hellwig hch@lst.de Link: https://lore.kernel.org/r/20220823160810.181275-1-code@siddh.me Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/block/loop.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1202,6 +1202,11 @@ loop_get_status(struct loop_device *lo, info->lo_rdevice = huge_encode_dev(lo->lo_device ? stat.rdev : stat.dev); info->lo_offset = lo->lo_offset; info->lo_sizelimit = lo->lo_sizelimit; + + /* loff_t vars have been assigned __u64 */ + if (lo->lo_offset < 0 || lo->lo_sizelimit < 0) + return -EOVERFLOW; + info->lo_flags = lo->lo_flags; memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE); memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE);

From: David Hildenbrand david@redhat.com

commit f96f7a40874d7c746680c0b9f57cef2262ae551f upstream.

Patch series "mm/hugetlb: fix write-fault handling for shared mappings", v2.

I observed that hugetlb does not support/expect write-faults in shared mappings that would have to map the R/O-mapped page writable -- and I found two case where we could currently get such faults and would erroneously map an anon page into a shared mapping.

Reproducers part of the patches.

I propose to backport both fixes to stable trees. The first fix needs a small adjustment.

This patch (of 2):

Staring at hugetlb_wp(), one might wonder where all the logic for shared mappings is when stumbling over a write-protected page in a shared mapping. In fact, there is none, and so far we thought we could get away with that because e.g., mprotect() should always do the right thing and map all pages directly writable.

Looks like we were wrong:

-------------------------------------------------------------------------- #include <stdio.h> #include <stdlib.h> #include <string.h> #include <fcntl.h> #include <unistd.h> #include <errno.h> #include <sys/mman.h>

#define HUGETLB_SIZE (2 * 1024 * 1024u)

static void clear_softdirty(void) { int fd = open("/proc/self/clear_refs", O_WRONLY); const char *ctrl = "4"; int ret;

if (fd < 0) { fprintf(stderr, "open(clear_refs) failed\n"); exit(1); } ret = write(fd, ctrl, strlen(ctrl)); if (ret != strlen(ctrl)) { fprintf(stderr, "write(clear_refs) failed\n"); exit(1); } close(fd); }

int main(int argc, char **argv) { char *map; int fd;

fd = open("/dev/hugepages/tmp", O_RDWR | O_CREAT); if (!fd) { fprintf(stderr, "open() failed\n"); return -errno; } if (ftruncate(fd, HUGETLB_SIZE)) { fprintf(stderr, "ftruncate() failed\n"); return -errno; }

map = mmap(NULL, HUGETLB_SIZE, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); if (map == MAP_FAILED) { fprintf(stderr, "mmap() failed\n"); return -errno; }

*map = 0;

if (mprotect(map, HUGETLB_SIZE, PROT_READ)) { fprintf(stderr, "mmprotect() failed\n"); return -errno; }

clear_softdirty();

if (mprotect(map, HUGETLB_SIZE, PROT_READ|PROT_WRITE)) { fprintf(stderr, "mmprotect() failed\n"); return -errno; }

*map = 0;

return 0; } --------------------------------------------------------------------------

Above test fails with SIGBUS when there is only a single free hugetlb page. # echo 1 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages # ./test Bus error (core dumped)

And worse, with sufficient free hugetlb pages it will map an anonymous page into a shared mapping, for example, messing up accounting during unmap and breaking MAP_SHARED semantics: # echo 2 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages # ./test # cat /proc/meminfo | grep HugePages_ HugePages_Total: 2 HugePages_Free: 1 HugePages_Rsvd: 18446744073709551615 HugePages_Surp: 0

Reason in this particular case is that vma_wants_writenotify() will return "true", removing VM_SHARED in vma_set_page_prot() to map pages write-protected. Let's teach vma_wants_writenotify() that hugetlb does not support softdirty tracking.

Link: https://lkml.kernel.org/r/20220811103435.188481-1-david@redhat.com Link: https://lkml.kernel.org/r/20220811103435.188481-2-david@redhat.com Fixes: 64e455079e1b ("mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY cleared") Signed-off-by: David Hildenbrand david@redhat.com Reviewed-by: Mike Kravetz mike.kravetz@oracle.com Cc: Peter Feiner pfeiner@google.com Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Cyrill Gorcunov gorcunov@openvz.org Cc: Pavel Emelyanov xemul@parallels.com Cc: Jamie Liu jamieliu@google.com Cc: Hugh Dickins hughd@google.com Cc: Naoya Horiguchi n-horiguchi@ah.jp.nec.com Cc: Bjorn Helgaas bhelgaas@google.com Cc: Muchun Song songmuchun@bytedance.com Cc: Peter Xu peterx@redhat.com Cc: stable@vger.kernel.org [3.18+] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: David Hildenbrand david@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/mmap.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/mm/mmap.c +++ b/mm/mmap.c @@ -1593,8 +1593,12 @@ int vma_wants_writenotify(struct vm_area pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0;

- /* Do we need to track softdirty? */ - if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY)) + /* + * Do we need to track softdirty? hugetlb does not support softdirty + * tracking yet. + */ + if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY) && + !is_vm_hugetlb_page(vma)) return 1;

/* Specialty mapping? */

From: Gerald Schaefer gerald.schaefer@linux.ibm.com

commit 41ac42f137080bc230b5882e3c88c392ab7f2d32 upstream.

For non-protection pXd_none() page faults in do_dat_exception(), we call do_exception() with access == (VM_READ | VM_WRITE | VM_EXEC). In do_exception(), vma->vm_flags is checked against that before calling handle_mm_fault().

Since commit 92f842eac7ee3 ("[S390] store indication fault optimization"), we call handle_mm_fault() with FAULT_FLAG_WRITE, when recognizing that it was a write access. However, the vma flags check is still only checking against (VM_READ | VM_WRITE | VM_EXEC), and therefore also calling handle_mm_fault() with FAULT_FLAG_WRITE in cases where the vma does not allow VM_WRITE.

Fix this by changing access check in do_exception() to VM_WRITE only, when recognizing write access.

Link: https://lkml.kernel.org/r/20220811103435.188481-3-david@redhat.com Fixes: 92f842eac7ee3 ("[S390] store indication fault optimization") Cc: stable@vger.kernel.org Reported-by: David Hildenbrand david@redhat.com Reviewed-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Gerald Schaefer gerald.schaefer@linux.ibm.com Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Gerald Schaefer gerald.schaefer@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/s390/mm/fault.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -409,7 +409,9 @@ static inline int do_exception(struct pt flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (user_mode(regs)) flags |= FAULT_FLAG_USER; - if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) + if ((trans_exc_code & store_indication) == 0x400) + access = VM_WRITE; + if (access == VM_WRITE) flags |= FAULT_FLAG_WRITE; down_read(&mm->mmap_sem);

From: Pawan Gupta pawan.kumar.gupta@linux.intel.com

commit 7df548840c496b0141fb2404b889c346380c2b22 upstream.

Older Intel CPUs that are not in the affected processor list for MMIO Stale Data vulnerabilities currently report "Not affected" in sysfs, which may not be correct. Vulnerability status for these older CPUs is unknown.

Add known-not-affected CPUs to the whitelist. Report "unknown" mitigation status for CPUs that are not in blacklist, whitelist and also don't enumerate MSR ARCH_CAPABILITIES bits that reflect hardware immunity to MMIO Stale Data vulnerabilities.

Mitigation is not deployed when the status is unknown.

[ bp: Massage, fixup. ]

Fixes: 8d50cdf8b834 ("x86/speculation/mmio: Add sysfs reporting for Processor MMIO Stale Data") Suggested-by: Andrew Cooper andrew.cooper3@citrix.com Suggested-by: Tony Luck tony.luck@intel.com Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Borislav Petkov bp@suse.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/a932c154772f2121794a5f2eded1a11013114711.165784626... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/hw-vuln/processor_mmio_stale_data.rst | 14 ++++++++ arch/x86/include/asm/cpufeatures.h | 1 arch/x86/kernel/cpu/bugs.c | 14 +++++++- arch/x86/kernel/cpu/common.c | 34 +++++++++++++------- 4 files changed, 50 insertions(+), 13 deletions(-)

--- a/Documentation/hw-vuln/processor_mmio_stale_data.rst +++ b/Documentation/hw-vuln/processor_mmio_stale_data.rst @@ -230,6 +230,20 @@ The possible values in this file are: * - 'Mitigation: Clear CPU buffers' - The processor is vulnerable and the CPU buffer clearing mitigation is enabled. + * - 'Unknown: No mitigations' + - The processor vulnerability status is unknown because it is + out of Servicing period. Mitigation is not attempted. + +Definitions: +------------ + +Servicing period: The process of providing functional and security updates to +Intel processors or platforms, utilizing the Intel Platform Update (IPU) +process or other similar mechanisms. + +End of Servicing Updates (ESU): ESU is the date at which Intel will no +longer provide Servicing, such as through IPU or other similar update +processes. ESU dates will typically be aligned to end of quarter.

If the processor is vulnerable then the following information is appended to the above information: --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -363,5 +363,6 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */

#endif /* _ASM_X86_CPUFEATURES_H */ --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -395,7 +395,8 @@ static void __init mmio_select_mitigatio u64 ia32_cap;

if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || - cpu_mitigations_off()) { + boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || + cpu_mitigations_off()) { mmio_mitigation = MMIO_MITIGATION_OFF; return; } @@ -500,6 +501,8 @@ out: pr_info("TAA: %s\n", taa_strings[taa_mitigation]); if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); + else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + pr_info("MMIO Stale Data: Unknown: No mitigations\n"); }

static void __init md_clear_select_mitigation(void) @@ -1824,6 +1827,9 @@ static ssize_t tsx_async_abort_show_stat

static ssize_t mmio_stale_data_show_state(char *buf) { + if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + return sysfs_emit(buf, "Unknown: No mitigations\n"); + if (mmio_mitigation == MMIO_MITIGATION_OFF) return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);

@@ -1934,6 +1940,7 @@ static ssize_t cpu_show_common(struct de return srbds_show_state(buf);

case X86_BUG_MMIO_STALE_DATA: + case X86_BUG_MMIO_UNKNOWN: return mmio_stale_data_show_state(buf);

default: @@ -1990,6 +1997,9 @@ ssize_t cpu_show_srbds(struct device *de

ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf) { - return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); + if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN); + else + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); } #endif --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -899,6 +899,7 @@ static void identify_cpu_without_cpuid(s #define MSBDS_ONLY BIT(5) #define NO_SWAPGS BIT(6) #define NO_ITLB_MULTIHIT BIT(7) +#define NO_MMIO BIT(8)

#define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -916,6 +917,11 @@ static const __initconst struct x86_cpu_ VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION),

/* Intel Family 6 */ + VULNWL_INTEL(TIGERLAKE, NO_MMIO), + VULNWL_INTEL(TIGERLAKE_L, NO_MMIO), + VULNWL_INTEL(ALDERLAKE, NO_MMIO), + VULNWL_INTEL(ALDERLAKE_L, NO_MMIO), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), @@ -933,9 +939,9 @@ static const __initconst struct x86_cpu_

VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),

- VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),

/* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -946,13 +952,13 @@ static const __initconst struct x86_cpu_ */

/* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),

/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), {} };

@@ -1092,10 +1098,16 @@ static void __init cpu_set_bug_bits(stru * Affected CPU list is generally enough to enumerate the vulnerability, * but for virtualization case check for ARCH_CAP MSR bits also, VMM may * not want the guest to enumerate the bug. + * + * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, + * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (cpu_matches(cpu_vuln_blacklist, MMIO) && - !arch_cap_mmio_immune(ia32_cap)) - setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + if (!arch_cap_mmio_immune(ia32_cap)) { + if (cpu_matches(cpu_vuln_blacklist, MMIO)) + setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) + setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN); + }

if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return;

From: Luiz Augusto von Dentz luiz.von.dentz@intel.com

commit b840304fb46cdf7012722f456bce06f151b3e81b upstream.

This attempts to fix the follow errors:

In function 'memcmp', inlined from 'bacmp' at ./include/net/bluetooth/bluetooth.h:347:9, inlined from 'l2cap_global_chan_by_psm' at net/bluetooth/l2cap_core.c:2003:15: ./include/linux/fortify-string.h:44:33: error: '__builtin_memcmp' specified bound 6 exceeds source size 0 [-Werror=stringop-overread] 44 | #define __underlying_memcmp __builtin_memcmp | ^ ./include/linux/fortify-string.h:420:16: note: in expansion of macro '__underlying_memcmp' 420 | return __underlying_memcmp(p, q, size); | ^~~~~~~~~~~~~~~~~~~ In function 'memcmp', inlined from 'bacmp' at ./include/net/bluetooth/bluetooth.h:347:9, inlined from 'l2cap_global_chan_by_psm' at net/bluetooth/l2cap_core.c:2004:15: ./include/linux/fortify-string.h:44:33: error: '__builtin_memcmp' specified bound 6 exceeds source size 0 [-Werror=stringop-overread] 44 | #define __underlying_memcmp __builtin_memcmp | ^ ./include/linux/fortify-string.h:420:16: note: in expansion of macro '__underlying_memcmp' 420 | return __underlying_memcmp(p, q, size); | ^~~~~~~~~~~~~~~~~~~

Fixes: 332f1795ca20 ("Bluetooth: L2CAP: Fix l2cap_global_chan_by_psm regression") Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Cc: Sudip Mukherjee sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bluetooth/l2cap_core.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1826,11 +1826,11 @@ static struct l2cap_chan *l2cap_global_c src_match = !bacmp(&c->src, src); dst_match = !bacmp(&c->dst, dst); if (src_match && dst_match) { - c = l2cap_chan_hold_unless_zero(c); - if (c) { - read_unlock(&chan_list_lock); - return c; - } + if (!l2cap_chan_hold_unless_zero(c)) + continue; + + read_unlock(&chan_list_lock); + return c; }

/* Closest match */

From: Karthik Alapati mail@karthek.com

commit a5623a203cffe2d2b84d2f6c989d9017db1856af upstream.

Free the buffered reports before deleting the list entry.

BUG: memory leak unreferenced object 0xffff88810e72f180 (size 32): comm "softirq", pid 0, jiffies 4294945143 (age 16.080s) hex dump (first 32 bytes): 64 f3 c6 6a d1 88 07 04 00 00 00 00 00 00 00 00 d..j............ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff814ac6c3>] kmemdup+0x23/0x50 mm/util.c:128 [<ffffffff8357c1d2>] kmemdup include/linux/fortify-string.h:440 [inline] [<ffffffff8357c1d2>] hidraw_report_event+0xa2/0x150 drivers/hid/hidraw.c:521 [<ffffffff8356ddad>] hid_report_raw_event+0x27d/0x740 drivers/hid/hid-core.c:1992 [<ffffffff8356e41e>] hid_input_report+0x1ae/0x270 drivers/hid/hid-core.c:2065 [<ffffffff835f0d3f>] hid_irq_in+0x1ff/0x250 drivers/hid/usbhid/hid-core.c:284 [<ffffffff82d3c7f9>] __usb_hcd_giveback_urb+0xf9/0x230 drivers/usb/core/hcd.c:1670 [<ffffffff82d3cc26>] usb_hcd_giveback_urb+0x1b6/0x1d0 drivers/usb/core/hcd.c:1747 [<ffffffff82ef1e14>] dummy_timer+0x8e4/0x14c0 drivers/usb/gadget/udc/dummy_hcd.c:1988 [<ffffffff812f50a8>] call_timer_fn+0x38/0x200 kernel/time/timer.c:1474 [<ffffffff812f5586>] expire_timers kernel/time/timer.c:1519 [inline] [<ffffffff812f5586>] __run_timers.part.0+0x316/0x430 kernel/time/timer.c:1790 [<ffffffff812f56e4>] __run_timers kernel/time/timer.c:1768 [inline] [<ffffffff812f56e4>] run_timer_softirq+0x44/0x90 kernel/time/timer.c:1803 [<ffffffff848000e6>] __do_softirq+0xe6/0x2ea kernel/softirq.c:571 [<ffffffff81246db0>] invoke_softirq kernel/softirq.c:445 [inline] [<ffffffff81246db0>] __irq_exit_rcu kernel/softirq.c:650 [inline] [<ffffffff81246db0>] irq_exit_rcu+0xc0/0x110 kernel/softirq.c:662 [<ffffffff84574f02>] sysvec_apic_timer_interrupt+0xa2/0xd0 arch/x86/kernel/apic/apic.c:1106 [<ffffffff84600c8b>] asm_sysvec_apic_timer_interrupt+0x1b/0x20 arch/x86/include/asm/idtentry.h:649 [<ffffffff8458a070>] native_safe_halt arch/x86/include/asm/irqflags.h:51 [inline] [<ffffffff8458a070>] arch_safe_halt arch/x86/include/asm/irqflags.h:89 [inline] [<ffffffff8458a070>] acpi_safe_halt drivers/acpi/processor_idle.c:111 [inline] [<ffffffff8458a070>] acpi_idle_do_entry+0xc0/0xd0 drivers/acpi/processor_idle.c:554

Link: https://syzkaller.appspot.com/bug?id=19a04b43c75ed1092021010419b5e560a8172c4... Reported-by: syzbot+f59100a0428e6ded9443@syzkaller.appspotmail.com Signed-off-by: Karthik Alapati mail@karthek.com Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/hidraw.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -354,10 +354,13 @@ static int hidraw_release(struct inode * unsigned int minor = iminor(inode); struct hidraw_list *list = file->private_data; unsigned long flags; + int i;

mutex_lock(&minors_lock);

spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags); + for (i = list->tail; i < list->head; i++) + kfree(list->buffer[i].value); list_del(&list->node); spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags); kfree(list);

From: Yang Jihong yangjihong1@huawei.com

commit c3b0f72e805f0801f05fa2aa52011c4bfc694c44 upstream.

ftrace_startup does not remove ops from ftrace_ops_list when ftrace_startup_enable fails:

register_ftrace_function ftrace_startup __register_ftrace_function ... add_ftrace_ops(&ftrace_ops_list, ops) ... ... ftrace_startup_enable // if ftrace failed to modify, ftrace_disabled is set to 1 ... return 0 // ops is in the ftrace_ops_list.

When ftrace_disabled = 1, unregister_ftrace_function simply returns without doing anything: unregister_ftrace_function ftrace_shutdown if (unlikely(ftrace_disabled)) return -ENODEV; // return here, __unregister_ftrace_function is not executed, // as a result, ops is still in the ftrace_ops_list __unregister_ftrace_function ...

If ops is dynamically allocated, it will be free later, in this case, is_ftrace_trampoline accesses NULL pointer:

is_ftrace_trampoline ftrace_ops_trampoline do_for_each_ftrace_op(op, ftrace_ops_list) // OOPS! op may be NULL!

Syzkaller reports as follows: [ 1203.506103] BUG: kernel NULL pointer dereference, address: 000000000000010b [ 1203.508039] #PF: supervisor read access in kernel mode [ 1203.508798] #PF: error_code(0x0000) - not-present page [ 1203.509558] PGD 800000011660b067 P4D 800000011660b067 PUD 130fb8067 PMD 0 [ 1203.510560] Oops: 0000 [#1] SMP KASAN PTI [ 1203.511189] CPU: 6 PID: 29532 Comm: syz-executor.2 Tainted: G B W 5.10.0 #8 [ 1203.512324] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 1203.513895] RIP: 0010:is_ftrace_trampoline+0x26/0xb0 [ 1203.514644] Code: ff eb d3 90 41 55 41 54 49 89 fc 55 53 e8 f2 00 fd ff 48 8b 1d 3b 35 5d 03 e8 e6 00 fd ff 48 8d bb 90 00 00 00 e8 2a 81 26 00 <48> 8b ab 90 00 00 00 48 85 ed 74 1d e8 c9 00 fd ff 48 8d bb 98 00 [ 1203.518838] RSP: 0018:ffffc900012cf960 EFLAGS: 00010246 [ 1203.520092] RAX: 0000000000000000 RBX: 000000000000007b RCX: ffffffff8a331866 [ 1203.521469] RDX: 0000000000000000 RSI: 0000000000000008 RDI: 000000000000010b [ 1203.522583] RBP: 0000000000000000 R08: 0000000000000000 R09: ffffffff8df18b07 [ 1203.523550] R10: fffffbfff1be3160 R11: 0000000000000001 R12: 0000000000478399 [ 1203.524596] R13: 0000000000000000 R14: ffff888145088000 R15: 0000000000000008 [ 1203.525634] FS: 00007f429f5f4700(0000) GS:ffff8881daf00000(0000) knlGS:0000000000000000 [ 1203.526801] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1203.527626] CR2: 000000000000010b CR3: 0000000170e1e001 CR4: 00000000003706e0 [ 1203.528611] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1203.529605] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Therefore, when ftrace_startup_enable fails, we need to rollback registration process and remove ops from ftrace_ops_list.

Link: https://lkml.kernel.org/r/20220818032659.56209-1-yangjihong1@huawei.com

Suggested-by: Steven Rostedt rostedt@goodmis.org Signed-off-by: Yang Jihong yangjihong1@huawei.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/ftrace.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

--- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2737,6 +2737,16 @@ static int ftrace_startup(struct ftrace_

ftrace_startup_enable(command);

+ /* + * If ftrace is in an undefined state, we just remove ops from list + * to prevent the NULL pointer, instead of totally rolling it back and + * free trampoline, because those actions could cause further damage. + */ + if (unlikely(ftrace_disabled)) { + __unregister_ftrace_function(ops); + return -ENODEV; + } + ops->flags &= ~FTRACE_OPS_FL_ADDING;

return 0;

From: Juergen Gross jgross@suse.com

[ Upstream commit 7b6670b03641ac308aaa6fa2e6f964ac993b5ea3 ]

When booting under KVM the following error messages are issued:

hypfs.7f5705: The hardware system does not support hypfs hypfs.7a79f0: Initialization of hypfs failed with rc=-61

Demote the severity of first message from "error" to "info" and issue the second message only in other error cases.

Signed-off-by: Juergen Gross jgross@suse.com Acked-by: Heiko Carstens hca@linux.ibm.com Acked-by: Christian Borntraeger borntraeger@linux.ibm.com Link: https://lore.kernel.org/r/20220620094534.18967-1-jgross@suse.com [arch/s390/hypfs/hypfs_diag.c changed description] Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/hypfs/hypfs_diag.c | 2 +- arch/s390/hypfs/inode.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 794bebb43d23d..64448c0998eb5 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -436,7 +436,7 @@ __init int hypfs_diag_init(void) int rc;

if (diag204_probe()) { - pr_err("The hardware system does not support hypfs\n"); + pr_info("The hardware system does not support hypfs\n"); return -ENODATA; } if (diag204_info_type == DIAG204_INFO_EXT) { diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 224aeda1e8ccf..d73d2d001a620 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -493,9 +493,9 @@ static int __init hypfs_init(void) hypfs_vm_exit(); fail_hypfs_diag_exit: hypfs_diag_exit(); + pr_err("Initialization of hypfs failed with rc=%i\n", rc); fail_dbfs_exit: hypfs_dbfs_exit(); - pr_err("Initialization of hypfs failed with rc=%i\n", rc); return rc; }

From: Jann Horn jannh@google.com

commit 2555283eb40df89945557273121e9393ef9b542b upstream.

anon_vma->degree tracks the combined number of child anon_vmas and VMAs that use the anon_vma as their ->anon_vma.

anon_vma_clone() then assumes that for any anon_vma attached to src->anon_vma_chain other than src->anon_vma, it is impossible for it to be a leaf node of the VMA tree, meaning that for such VMAs ->degree is elevated by 1 because of a child anon_vma, meaning that if ->degree equals 1 there are no VMAs that use the anon_vma as their ->anon_vma.

This assumption is wrong because the ->degree optimization leads to leaf nodes being abandoned on anon_vma_clone() - an existing anon_vma is reused and no new parent-child relationship is created. So it is possible to reuse an anon_vma for one VMA while it is still tied to another VMA.

This is an issue because is_mergeable_anon_vma() and its callers assume that if two VMAs have the same ->anon_vma, the list of anon_vmas attached to the VMAs is guaranteed to be the same. When this assumption is violated, vma_merge() can merge pages into a VMA that is not attached to the corresponding anon_vma, leading to dangling page->mapping pointers that will be dereferenced during rmap walks.

Fix it by separately tracking the number of child anon_vmas and the number of VMAs using the anon_vma as their ->anon_vma.

Fixes: 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy") Cc: stable@kernel.org Acked-by: Michal Hocko mhocko@suse.com Acked-by: Vlastimil Babka vbabka@suse.cz Signed-off-by: Jann Horn jannh@google.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org [manually fixed up different indentation in stable] Signed-off-by: Jann Horn jannh@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/rmap.h | 7 +++++-- mm/rmap.c | 31 +++++++++++++++++-------------- 2 files changed, 22 insertions(+), 16 deletions(-)

--- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -37,12 +37,15 @@ struct anon_vma { atomic_t refcount;

/* - * Count of child anon_vmas and VMAs which points to this anon_vma. + * Count of child anon_vmas. Equals to the count of all anon_vmas that + * have ->parent pointing to this one, including itself. * * This counter is used for making decision about reusing anon_vma * instead of forking new one. See comments in function anon_vma_clone. */ - unsigned degree; + unsigned long num_children; + /* Count of VMAs whose ->anon_vma pointer points to this object. */ + unsigned long num_active_vmas;

struct anon_vma *parent; /* Parent of this anon_vma */

--- a/mm/rmap.c +++ b/mm/rmap.c @@ -78,7 +78,8 @@ static inline struct anon_vma *anon_vma_ anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); - anon_vma->degree = 1; /* Reference for first vma */ + anon_vma->num_children = 0; + anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called @@ -187,6 +188,7 @@ int anon_vma_prepare(struct vm_area_stru anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; + anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; }

@@ -196,8 +198,7 @@ int anon_vma_prepare(struct vm_area_stru if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); - /* vma reference or self-parent link for new root */ - anon_vma->degree++; + anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } @@ -276,19 +277,19 @@ int anon_vma_clone(struct vm_area_struct anon_vma_chain_link(dst, avc, anon_vma);

/* - * Reuse existing anon_vma if its degree lower than two, - * that means it has no vma and only one anon_vma child. + * Reuse existing anon_vma if it has no vma and only one + * anon_vma child. * - * Do not chose parent anon_vma, otherwise first child - * will always reuse it. Root anon_vma is never reused: + * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ - if (!dst->anon_vma && anon_vma != src->anon_vma && - anon_vma->degree < 2) + if (!dst->anon_vma && + anon_vma->num_children < 2 && + anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) - dst->anon_vma->degree++; + dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0;

@@ -338,6 +339,7 @@ int anon_vma_fork(struct vm_area_struct anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; + anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; @@ -358,7 +360,7 @@ int anon_vma_fork(struct vm_area_struct vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); - anon_vma->parent->degree++; + anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma);

return 0; @@ -390,7 +392,7 @@ void unlink_anon_vmas(struct vm_area_str * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root)) { - anon_vma->parent->degree--; + anon_vma->parent->num_children--; continue; }

@@ -398,7 +400,7 @@ void unlink_anon_vmas(struct vm_area_str anon_vma_chain_free(avc); } if (vma->anon_vma) - vma->anon_vma->degree--; + vma->anon_vma->num_active_vmas--; unlock_anon_vma_root(root);

/* @@ -409,7 +411,8 @@ void unlink_anon_vmas(struct vm_area_str list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma;

- VM_WARN_ON(anon_vma->degree); + VM_WARN_ON(anon_vma->num_children); + VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma);

list_del(&avc->same_vma);