From: Frank Sorenson sorenson@redhat.com

commit 652727bbe1b17993636346716ae5867627793647 upstream.

A path-based rename returning EBUSY will incorrectly try opening the file with a cifs (NT Create AndX) operation on an smb2+ mount, which causes the server to force a session close.

If the mount is smb2+, skip the fallback.

Signed-off-by: Frank Sorenson sorenson@redhat.com Signed-off-by: Steve French stfrench@microsoft.com CC: Stable stable@vger.kernel.org Reviewed-by: Ronnie Sahlberg lsahlber@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/cifs/inode.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1722,6 +1722,10 @@ cifs_do_rename(const unsigned int xid, s if (rc == 0 || rc != -EBUSY) goto do_rename_exit;

+ /* Don't fall back to using SMB on SMB 2+ mount */ + if (server->vals->protocol_id != 0) + goto do_rename_exit; + /* open-file renames don't work across directories */ if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit;

From: Aurelien Jarno aurelien@aurel32.net

commit 79b4a9cf0e2ea8203ce777c8d5cfa86c71eae86e upstream.

Commit 4c21b8fd8f14 (MIPS: seccomp: Handle indirect system calls (o32)) added indirect syscall detection for O32 processes running on MIPS64, but it did not work correctly for big endian kernel/processes. The reason is that the syscall number is loaded from ARG1 using the lw instruction while this is a 64-bit value, so zero is loaded instead of the syscall number.

Fix the code by using the ld instruction instead. When running a 32-bit processes on a 64 bit CPU, the values are properly sign-extended, so it ensures the value passed to syscall_trace_enter is correct.

Recent systemd versions with seccomp enabled whitelist the getpid syscall for their internal processes (e.g. systemd-journald), but call it through syscall(SYS_getpid). This fix therefore allows O32 big endian systems with a 64-bit kernel to run recent systemd versions.

Signed-off-by: Aurelien Jarno aurelien@aurel32.net Cc: stable@vger.kernel.org # v3.15+ Reviewed-by: Philippe Mathieu-Daudé f4bug@amsat.org Signed-off-by: Paul Burton paul.burton@mips.com Cc: Ralf Baechle ralf@linux-mips.org Cc: James Hogan jhogan@kernel.org Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/mips/kernel/scall64-o32.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -125,7 +125,7 @@ trace_a_syscall: subu t1, v0, __NR_O32_Linux move a1, v0 bnez t1, 1f /* __NR_syscall at offset 0 */ - lw a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ + ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ .set pop

1: jal syscall_trace_enter

From: Josh Collier josh.d.collier@intel.com

commit 7c39f7f671d2acc0a1f39ebbbee4303ad499bbfa upstream.

Current implementation was not properly handling frwr memory registrations. This was uncovered by commit 27f26cec761das ("xprtrdma: Plant XID in on-the-wire RDMA offset (FRWR)") in which xprtrdma, which is used for NFS over RDMA, started failing as it was the first ULP to modify the ib_mr iova resulting in the NFS server getting REMOTE ACCESS ERROR when attempting to perform RDMA Writes to the client.

The fix is to properly capture the true iova, offset, and length in the call to ib_map_mr_sg, and then update the iova when processing the IB_WR_REG_MEM on the send queue.

Fixes: a41081aa5936 ("IB/rdmavt: Add support for ib_map_mr_sg") Cc: stable@vger.kernel.org Reviewed-by: Mike Marciniszyn mike.marciniszyn@intel.com Reviewed-by: Dennis Dalessandro dennis.dalessandro@intel.com Reviewed-by: Michael J. Ruhl michael.j.ruhl@intel.com Signed-off-by: Josh Collier josh.d.collier@intel.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@intel.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/infiniband/sw/rdmavt/mr.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-)

--- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -497,11 +497,6 @@ static int rvt_set_page(struct ib_mr *ib if (unlikely(mapped_segs == mr->mr.max_segs)) return -ENOMEM;

- if (mr->mr.length == 0) { - mr->mr.user_base = addr; - mr->mr.iova = addr; - } - m = mapped_segs / RVT_SEGSZ; n = mapped_segs % RVT_SEGSZ; mr->mr.map[m]->segs[n].vaddr = (void *)addr; @@ -518,17 +513,24 @@ static int rvt_set_page(struct ib_mr *ib * @sg_nents: number of entries in sg * @sg_offset: offset in bytes into sg * + * Overwrite rvt_mr length with mr length calculated by ib_sg_to_pages. + * * Return: number of sg elements mapped to the memory region */ int rvt_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset) { struct rvt_mr *mr = to_imr(ibmr); + int ret;

mr->mr.length = 0; mr->mr.page_shift = PAGE_SHIFT; - return ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, - rvt_set_page); + ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rvt_set_page); + mr->mr.user_base = ibmr->iova; + mr->mr.iova = ibmr->iova; + mr->mr.offset = ibmr->iova - (u64)mr->mr.map[0]->segs[0].vaddr; + mr->mr.length = (size_t)ibmr->length; + return ret; }

/** @@ -559,6 +561,7 @@ int rvt_fast_reg_mr(struct rvt_qp *qp, s ibmr->rkey = key; mr->mr.lkey = key; mr->mr.access_flags = access; + mr->mr.iova = ibmr->iova; atomic_set(&mr->mr.lkey_invalid, 0);

return 0;

From: Jeff Layton jlayton@kernel.org

commit 76a495d666e5043ffc315695f8241f5e94a98849 upstream.

Take the d_lock here to ensure that d_name doesn't change.

Cc: stable@vger.kernel.org Signed-off-by: Jeff Layton jlayton@kernel.org Reviewed-by: "Yan, Zheng" zyan@redhat.com Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ceph/dir.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1471,6 +1471,7 @@ void ceph_dentry_lru_del(struct dentry * unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) { struct ceph_inode_info *dci = ceph_inode(dir); + unsigned hash;

switch (dci->i_dir_layout.dl_dir_hash) { case 0: /* for backward compat */ @@ -1478,8 +1479,11 @@ unsigned ceph_dentry_hash(struct inode * return dn->d_name.hash;

default: - return ceph_str_hash(dci->i_dir_layout.dl_dir_hash, + spin_lock(&dn->d_lock); + hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash, dn->d_name.name, dn->d_name.len); + spin_unlock(&dn->d_lock); + return hash; } }

From: Trond Myklebust trondmy@gmail.com

commit e6abc8caa6deb14be2a206253f7e1c5e37e9515b upstream.

If there are multiple callbacks queued, waiting for the callback slot when the callback gets shut down, then they all currently end up acting as if they hold the slot, and call nfsd4_cb_sequence_done() resulting in interesting side-effects.

In addition, the 'retry_nowait' path in nfsd4_cb_sequence_done() causes a loop back to nfsd4_cb_prepare() without first freeing the slot, which causes a deadlock when nfsd41_cb_get_slot() gets called a second time.

This patch therefore adds a boolean to track whether or not the callback did pick up the slot, so that it can do the right thing in these 2 cases.

Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: J. Bruce Fields bfields@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/nfsd/nfs4callback.c | 8 +++++++- fs/nfsd/state.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-)

--- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -934,8 +934,9 @@ static void nfsd4_cb_prepare(struct rpc_ cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) + if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) return; + cb->cb_holds_slot = true; } rpc_call_start(task); } @@ -962,6 +963,9 @@ static bool nfsd4_cb_sequence_done(struc return true; }

+ if (!cb->cb_holds_slot) + goto need_restart; + switch (cb->cb_seq_status) { case 0: /* @@ -999,6 +1003,7 @@ static bool nfsd4_cb_sequence_done(struc cb->cb_seq_status); }

+ cb->cb_holds_slot = false; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, @@ -1206,6 +1211,7 @@ void nfsd4_init_cb(struct nfsd4_callback cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; + cb->cb_holds_slot = false; }

void nfsd4_run_cb(struct nfsd4_callback *cb) --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -69,6 +69,7 @@ struct nfsd4_callback { int cb_seq_status; int cb_status; bool cb_need_restart; + bool cb_holds_slot; };

struct nfsd4_callback_ops {

From: Lucas Stach l.stach@pengutronix.de

commit 3a349763cf11e63534b8f2d302f2d0c790566497 upstream.

Currently any changed config register values don't take effect, as the function to write them back is called with the wrong register offset.

Fixes: ff8f83708b3e (Input: synaptics-rmi4 - add support for 2D sensors and F11) Signed-off-by: Lucas Stach l.stach@pengutronix.de Reviewed-by: Philipp Zabel p.zabel@pengutronix.de Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/input/rmi4/rmi_f11.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/input/rmi4/rmi_f11.c +++ b/drivers/input/rmi4/rmi_f11.c @@ -1198,7 +1198,7 @@ static int rmi_f11_initialize(struct rmi ctrl->ctrl0_11[11] = ctrl->ctrl0_11[11] & ~BIT(0);

rc = f11_write_control_regs(fn, &f11->sens_query, - &f11->dev_controls, fn->fd.query_base_addr); + &f11->dev_controls, fn->fd.control_base_addr); if (rc) dev_warn(&fn->dev, "Failed to write control registers\n");

From: Ard Biesheuvel ard.biesheuvel@linaro.org

commit e17b1af96b2afc38e684aa2f1033387e2ed10029 upstream.

The EFI stub is entered with the caches and MMU enabled by the firmware, and once the stub is ready to hand over to the decompressor, we clean and disable the caches.

The cache clean routines use CP15 barrier instructions, which can be disabled via SCTLR. Normally, when using the provided cache handling routines to enable the caches and MMU, this bit is enabled as well. However, but since we entered the stub with the caches already enabled, this routine is not executed before we call the cache clean routines, resulting in undefined instruction exceptions if the firmware never enabled this bit.

So set the bit explicitly in the EFI entry code, but do so in a way that guarantees that the resulting code can still run on v6 cores as well (which are guaranteed to have CP15 barriers enabled)

Cc: stable@vger.kernel.org # v4.9+ Acked-by: Marc Zyngier marc.zyngier@arm.com Signed-off-by: Ard Biesheuvel ard.biesheuvel@linaro.org Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/compressed/head.S | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)

--- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1383,7 +1383,21 @@ ENTRY(efi_stub_entry)

@ Preserve return value of efi_entry() in r4 mov r4, r0 - bl cache_clean_flush + + @ our cache maintenance code relies on CP15 barrier instructions + @ but since we arrived here with the MMU and caches configured + @ by UEFI, we must check that the CP15BEN bit is set in SCTLR. + @ Note that this bit is RAO/WI on v6 and earlier, so the ISB in + @ the enable path will be executed on v7+ only. + mrc p15, 0, r1, c1, c0, 0 @ read SCTLR + tst r1, #(1 << 5) @ CP15BEN bit set? + bne 0f + orr r1, r1, #(1 << 5) @ CP15 barrier instructions + mcr p15, 0, r1, c1, c0, 0 @ write SCTLR + ARM( .inst 0xf57ff06f @ v7+ isb ) + THUMB( isb ) + +0: bl cache_clean_flush bl cache_off

@ Set parameters for booting zImage according to boot protocol

From: Maarten Lankhorst maarten.lankhorst@linux.intel.com

commit 462ce5d963f18b71c63f6b7730a35a2ee5273540 upstream.

A pointer to crtc was missing, resulting in the following build error: drivers/gpu/drm/vc4/vc4_crtc.c:1045:44: sparse: sparse: incorrect type in argument 1 (different base types) drivers/gpu/drm/vc4/vc4_crtc.c:1045:44: sparse: expected struct drm_crtc *crtc drivers/gpu/drm/vc4/vc4_crtc.c:1045:44: sparse: got struct drm_crtc_state *state drivers/gpu/drm/vc4/vc4_crtc.c:1045:39: sparse: sparse: not enough arguments for function vc4_crtc_destroy_state

Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reported-by: kbuild test robot lkp@intel.com Cc: Eric Anholt eric@anholt.net Link: https://patchwork.freedesktop.org/patch/msgid/2b6ed5e6-81b0-4276-8860-870b54... Fixes: d08106796a78 ("drm/vc4: Fix memory leak during gpu reset.") Cc: stable@vger.kernel.org # v4.6+ Acked-by: Daniel Vetter daniel.vetter@ffwll.ch Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/vc4/vc4_crtc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -846,7 +846,7 @@ static void vc4_crtc_reset(struct drm_crtc *crtc) { if (crtc->state) - vc4_crtc_destroy_state(crtc->state); + vc4_crtc_destroy_state(crtc, crtc->state);

crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL); if (crtc->state)

From: Kai-Heng Feng kai.heng.feng@canonical.com

commit d7a6c0ce8d26412903c7981503bad9e1cc7c45d2 upstream.

USB Bluetooth controller QCA ROME (0cf3:e007) sometimes stops working after S3: [ 165.110742] Bluetooth: hci0: using NVM file: qca/nvm_usb_00000302.bin [ 168.432065] Bluetooth: hci0: Failed to send body at 4 of 1953 (-110)

After some experiments, I found that disabling LPM can workaround the issue.

On some platforms, the USB power is cut during S3, so the driver uses reset-resume to resume the device. During port resume, LPM gets enabled twice, by usb_reset_and_verify_device() and usb_port_resume().

Consolidate all checks into new LPM helpers to make sure LPM only gets enabled once.

Fixes: de68bab4fa96 ("usb: Don't enable USB 2.0 Link PM by default.”) Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Cc: stable stable@vger.kernel.org # after much soaking Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/core/driver.c | 11 ++++++++--- drivers/usb/core/hub.c | 12 ++++-------- drivers/usb/core/message.c | 3 +-- 3 files changed, 13 insertions(+), 13 deletions(-)

--- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -1893,9 +1893,6 @@ static int usb_set_usb2_hardware_lpm(str struct usb_hcd *hcd = bus_to_hcd(udev->bus); int ret = -EPERM;

- if (enable && !udev->usb2_hw_lpm_allowed) - return 0; - if (hcd->driver->set_usb2_hw_lpm) { ret = hcd->driver->set_usb2_hw_lpm(hcd, udev, enable); if (!ret) @@ -1907,11 +1904,19 @@ static int usb_set_usb2_hardware_lpm(str

int usb_enable_usb2_hardware_lpm(struct usb_device *udev) { + if (!udev->usb2_hw_lpm_capable || + !udev->usb2_hw_lpm_allowed || + udev->usb2_hw_lpm_enabled) + return 0; + return usb_set_usb2_hardware_lpm(udev, 1); }

int usb_disable_usb2_hardware_lpm(struct usb_device *udev) { + if (!udev->usb2_hw_lpm_enabled) + return 0; + return usb_set_usb2_hardware_lpm(udev, 0); }

--- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -3168,8 +3168,7 @@ int usb_port_suspend(struct usb_device * }

/* disable USB2 hardware LPM */ - if (udev->usb2_hw_lpm_enabled == 1) - usb_disable_usb2_hardware_lpm(udev); + usb_disable_usb2_hardware_lpm(udev);

if (usb_disable_ltm(udev)) { dev_err(&udev->dev, "Failed to disable LTM before suspend\n."); @@ -3215,8 +3214,7 @@ int usb_port_suspend(struct usb_device * usb_enable_ltm(udev); err_ltm: /* Try to enable USB2 hardware LPM again */ - if (udev->usb2_hw_lpm_capable == 1) - usb_enable_usb2_hardware_lpm(udev); + usb_enable_usb2_hardware_lpm(udev);

if (udev->do_remote_wakeup) (void) usb_disable_remote_wakeup(udev); @@ -3499,8 +3497,7 @@ int usb_port_resume(struct usb_device *u hub_port_logical_disconnect(hub, port1); } else { /* Try to enable USB2 hardware LPM */ - if (udev->usb2_hw_lpm_capable == 1) - usb_enable_usb2_hardware_lpm(udev); + usb_enable_usb2_hardware_lpm(udev);

/* Try to enable USB3 LTM and LPM */ usb_enable_ltm(udev); @@ -5481,8 +5478,7 @@ static int usb_reset_and_verify_device(s /* Disable USB2 hardware LPM. * It will be re-enabled by the enumeration process. */ - if (udev->usb2_hw_lpm_enabled == 1) - usb_disable_usb2_hardware_lpm(udev); + usb_disable_usb2_hardware_lpm(udev);

/* Disable LPM and LTM while we reset the device and reinstall the alt * settings. Device-initiated LPM settings, and system exit latency --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1181,8 +1181,7 @@ void usb_disable_device(struct usb_devic dev->actconfig->interface[i] = NULL; }

- if (dev->usb2_hw_lpm_enabled == 1) - usb_disable_usb2_hardware_lpm(dev); + usb_disable_usb2_hardware_lpm(dev); usb_unlocked_disable_lpm(dev); usb_disable_ltm(dev);

From: Xin Long lucien.xin@gmail.com

commit 2ac695d1d602ce00b12170242f58c3d3a8e36d04 upstream.

Syzbot found a crash:

BUG: KMSAN: uninit-value in tipc_nl_compat_name_table_dump+0x54f/0xcd0 net/tipc/netlink_compat.c:872 Call Trace: tipc_nl_compat_name_table_dump+0x54f/0xcd0 net/tipc/netlink_compat.c:872 __tipc_nl_compat_dumpit+0x59e/0xda0 net/tipc/netlink_compat.c:215 tipc_nl_compat_dumpit+0x63a/0x820 net/tipc/netlink_compat.c:280 tipc_nl_compat_handle net/tipc/netlink_compat.c:1226 [inline] tipc_nl_compat_recv+0x1b5f/0x2750 net/tipc/netlink_compat.c:1265 genl_family_rcv_msg net/netlink/genetlink.c:601 [inline] genl_rcv_msg+0x185f/0x1a60 net/netlink/genetlink.c:626 netlink_rcv_skb+0x431/0x620 net/netlink/af_netlink.c:2477 genl_rcv+0x63/0x80 net/netlink/genetlink.c:637 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0xf3e/0x1020 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x127f/0x1300 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg net/socket.c:632 [inline]

Uninit was created at: __alloc_skb+0x309/0xa20 net/core/skbuff.c:208 alloc_skb include/linux/skbuff.h:1012 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1182 [inline] netlink_sendmsg+0xb82/0x1300 net/netlink/af_netlink.c:1892 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg net/socket.c:632 [inline]

It was supposed to be fixed on commit 974cb0e3e7c9 ("tipc: fix uninit-value in tipc_nl_compat_name_table_dump") by checking TLV_GET_DATA_LEN(msg->req) in cmd->header()/tipc_nl_compat_name_table_dump_header(), which is called ahead of tipc_nl_compat_name_table_dump().

However, tipc_nl_compat_dumpit() doesn't handle the error returned from cmd header function. It means even when the check added in that fix fails, it won't stop calling tipc_nl_compat_name_table_dump(), and the issue will be triggered again.

So this patch is to add the process for the err returned from cmd header function in tipc_nl_compat_dumpit().

Reported-by: syzbot+3ce8520484b0d4e260a5@syzkaller.appspotmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/tipc/netlink_compat.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

--- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -262,8 +262,14 @@ static int tipc_nl_compat_dumpit(struct if (msg->rep_type) tipc_tlv_init(msg->rep, msg->rep_type);

- if (cmd->header) - (*cmd->header)(msg); + if (cmd->header) { + err = (*cmd->header)(msg); + if (err) { + kfree_skb(msg->rep); + msg->rep = NULL; + return err; + } + }

arg = nlmsg_new(0, GFP_KERNEL); if (!arg) {

From: Alexander Shishkin alexander.shishkin@linux.intel.com

commit 91d3f8a629849968dc91d6ce54f2d46abf4feb7f upstream.

Commit 9ed3f22223c3 ("intel_th: Don't reference unassigned outputs") fixes a NULL dereference for all masters except the last one ("256+"), which keeps the stale pointer after the output driver had been unassigned.

Fix the off-by-one.

Signed-off-by: Alexander Shishkin alexander.shishkin@linux.intel.com Fixes: 9ed3f22223c3 ("intel_th: Don't reference unassigned outputs") Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/hwtracing/intel_th/gth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/hwtracing/intel_th/gth.c +++ b/drivers/hwtracing/intel_th/gth.c @@ -605,7 +605,7 @@ static void intel_th_gth_unassign(struct othdev->output.port = -1; othdev->output.active = false; gth->output[port].output = NULL; - for (master = 0; master < TH_CONFIGURABLE_MASTERS; master++) + for (master = 0; master <= TH_CONFIGURABLE_MASTERS; master++) if (gth->master[master] == port) gth->master[master] = -1; spin_unlock(&gth->gth_lock);

From: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp

commit 7c2bd9a39845bfb6d72ddb55ce737650271f6f96 upstream.

syzbot is reporting uninitialized value at rpc_sockaddr2uaddr() [1]. This is because syzbot is setting AF_INET6 to "struct sockaddr_in"->sin_family (which is embedded into user-visible "struct nfs_mount_data" structure) despite nfs23_validate_mount_data() cannot pass sizeof(struct sockaddr_in6) bytes of AF_INET6 address to rpc_sockaddr2uaddr().

Since "struct nfs_mount_data" structure is user-visible, we can't change "struct nfs_mount_data" to use "struct sockaddr_storage". Therefore, assuming that everybody is using AF_INET family when passing address via "struct nfs_mount_data"->addr, reject if its sin_family is not AF_INET.

[1] https://syzkaller.appspot.com/bug?id=599993614e7cbbf66bc2656a919ab2a95fb5d75...

Reported-by: syzbot syzbot+047a11c361b872896a4f@syzkaller.appspotmail.com Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/nfs/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2047,7 +2047,8 @@ static int nfs23_validate_mount_data(voi memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); args->nfs_server.port = ntohs(data->addr.sin_port); - if (!nfs_verify_server_address(sap)) + if (sap->sa_family != AF_INET || + !nfs_verify_server_address(sap)) goto out_no_address;

if (!(data->flags & NFS_MOUNT_TCP))

From: Yue Haibing yuehaibing@huawei.com

commit 01ca667133d019edc9f0a1f70a272447c84ec41f upstream.

Syzkaller report this:

kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN PTI CPU: 0 PID: 4378 Comm: syz-executor.0 Tainted: G C 5.0.0+ #5 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 RIP: 0010:__lock_acquire+0x95b/0x3200 kernel/locking/lockdep.c:3573 Code: 00 0f 85 28 1e 00 00 48 81 c4 08 01 00 00 5b 5d 41 5c 41 5d 41 5e 41 5f c3 4c 89 ea 48 b8 00 00 00 00 00 fc ff df 48 c1 ea 03 <80> 3c 02 00 0f 85 cc 24 00 00 49 81 7d 00 e0 de 03 a6 41 bc 00 00 RSP: 0018:ffff8881e3c07a40 EFLAGS: 00010002 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000010 RSI: 0000000000000000 RDI: 0000000000000080 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: ffff8881e3c07d98 R11: ffff8881c7f21f80 R12: 0000000000000001 R13: 0000000000000080 R14: 0000000000000000 R15: 0000000000000001 FS: 00007fce2252e700(0000) GS:ffff8881f2400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fffc7eb0228 CR3: 00000001e5bea002 CR4: 00000000007606f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: lock_acquire+0xff/0x2c0 kernel/locking/lockdep.c:4211 __mutex_lock_common kernel/locking/mutex.c:925 [inline] __mutex_lock+0xdf/0x1050 kernel/locking/mutex.c:1072 drain_workqueue+0x24/0x3f0 kernel/workqueue.c:2934 destroy_workqueue+0x23/0x630 kernel/workqueue.c:4319 __do_sys_delete_module kernel/module.c:1018 [inline] __se_sys_delete_module kernel/module.c:961 [inline] __x64_sys_delete_module+0x30c/0x480 kernel/module.c:961 do_syscall_64+0x9f/0x450 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462e99 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fce2252dc58 EFLAGS: 00000246 ORIG_RAX: 00000000000000b0 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000020000140 RBP: 0000000000000002 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fce2252e6bc R13: 00000000004bcca9 R14: 00000000006f6b48 R15: 00000000ffffffff

If alloc_workqueue fails, it should return -ENOMEM, otherwise may trigger this NULL pointer dereference while unloading drivers.

Reported-by: Hulk Robot hulkci@huawei.com Fixes: 0a38c17a21a0 ("fm10k: Remove create_workqueue") Signed-off-by: Yue Haibing yuehaibing@huawei.com Tested-by: Andrew Bowers andrewx.bowers@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -58,6 +58,8 @@ static int __init fm10k_init_module(void /* create driver workqueue */ fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, fm10k_driver_name); + if (!fm10k_workqueue) + return -ENOMEM;

fm10k_dbg_init();

From: Xin Long lucien.xin@gmail.com

commit 8c63bf9ab4be8b83bd8c34aacfd2f1d2c8901c8a upstream.

A similar issue as fixed by Patch "tipc: check bearer name with right length in tipc_nl_compat_bearer_enable" was also found by syzbot in tipc_nl_compat_link_set().

The length to check with should be 'TLV_GET_DATA_LEN(msg->req) - offsetof(struct tipc_link_config, name)'.

Reported-by: syzbot+de00a87b8644a582ae79@syzkaller.appspotmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/tipc/netlink_compat.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -768,7 +768,12 @@ static int tipc_nl_compat_link_set(struc

lc = (struct tipc_link_config *)TLV_DATA(msg->req);

- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + len = TLV_GET_DATA_LEN(msg->req); + len -= offsetof(struct tipc_link_config, name); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_LINK_NAME); if (!string_is_valid(lc->name, len)) return -EINVAL;

From: Eric Dumazet edumazet@google.com

[ Upstream commit 20ff83f10f113c88d0bb74589389b05250994c16 ]

Before calling __ip_options_compile(), we need to ensure the network header is a an IPv4 one, and that it is already pulled in skb->head.

RAW sockets going through a tunnel can end up calling ipv4_link_failure() with total garbage in the skb, or arbitrary lengthes.

syzbot report :

BUG: KASAN: stack-out-of-bounds in memcpy include/linux/string.h:355 [inline] BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0x294/0x1120 net/ipv4/ip_options.c:123 Write of size 69 at addr ffff888096abf068 by task syz-executor.4/9204

CPU: 0 PID: 9204 Comm: syz-executor.4 Not tainted 5.1.0-rc5+ #77 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 check_memory_region_inline mm/kasan/generic.c:185 [inline] check_memory_region+0x123/0x190 mm/kasan/generic.c:191 memcpy+0x38/0x50 mm/kasan/common.c:133 memcpy include/linux/string.h:355 [inline] __ip_options_echo+0x294/0x1120 net/ipv4/ip_options.c:123 __icmp_send+0x725/0x1400 net/ipv4/icmp.c:695 ipv4_link_failure+0x29f/0x550 net/ipv4/route.c:1204 dst_link_failure include/net/dst.h:427 [inline] vti6_xmit net/ipv6/ip6_vti.c:514 [inline] vti6_tnl_xmit+0x10d4/0x1c0c net/ipv6/ip6_vti.c:553 __netdev_start_xmit include/linux/netdevice.h:4414 [inline] netdev_start_xmit include/linux/netdevice.h:4423 [inline] xmit_one net/core/dev.c:3292 [inline] dev_hard_start_xmit+0x1b2/0x980 net/core/dev.c:3308 __dev_queue_xmit+0x271d/0x3060 net/core/dev.c:3878 dev_queue_xmit+0x18/0x20 net/core/dev.c:3911 neigh_direct_output+0x16/0x20 net/core/neighbour.c:1527 neigh_output include/net/neighbour.h:508 [inline] ip_finish_output2+0x949/0x1740 net/ipv4/ip_output.c:229 ip_finish_output+0x73c/0xd50 net/ipv4/ip_output.c:317 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip_output+0x21f/0x670 net/ipv4/ip_output.c:405 dst_output include/net/dst.h:444 [inline] NF_HOOK include/linux/netfilter.h:289 [inline] raw_send_hdrinc net/ipv4/raw.c:432 [inline] raw_sendmsg+0x1d2b/0x2f20 net/ipv4/raw.c:663 inet_sendmsg+0x147/0x5d0 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg+0xdd/0x130 net/socket.c:661 sock_write_iter+0x27c/0x3e0 net/socket.c:988 call_write_iter include/linux/fs.h:1866 [inline] new_sync_write+0x4c7/0x760 fs/read_write.c:474 __vfs_write+0xe4/0x110 fs/read_write.c:487 vfs_write+0x20c/0x580 fs/read_write.c:549 ksys_write+0x14f/0x2d0 fs/read_write.c:599 __do_sys_write fs/read_write.c:611 [inline] __se_sys_write fs/read_write.c:608 [inline] __x64_sys_write+0x73/0xb0 fs/read_write.c:608 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x458c29 Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f293b44bc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000458c29 RDX: 0000000000000014 RSI: 00000000200002c0 RDI: 0000000000000003 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f293b44c6d4 R13: 00000000004c8623 R14: 00000000004ded68 R15: 00000000ffffffff

The buggy address belongs to the page: page:ffffea00025aafc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 flags: 0x1fffc0000000000() raw: 01fffc0000000000 0000000000000000 ffffffff025a0101 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff888096abef80: 00 00 00 f2 f2 f2 f2 f2 00 00 00 00 00 00 00 f2 ffff888096abf000: f2 f2 f2 f2 00 00 00 00 00 00 00 00 00 00 00 00

ffff888096abf080: 00 00 f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00

^ ffff888096abf100: 00 00 00 00 f1 f1 f1 f1 00 00 f3 f3 00 00 00 00 ffff888096abf180: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Stephen Suryaputra ssuryaextr@gmail.com Acked-by: Willem de Bruijn willemb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/route.c | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-)

--- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1168,25 +1168,39 @@ static struct dst_entry *ipv4_dst_check( return dst; }

-static void ipv4_link_failure(struct sk_buff *skb) +static void ipv4_send_dest_unreach(struct sk_buff *skb) { struct ip_options opt; - struct rtable *rt; int res;

/* Recompile ip options since IPCB may not be valid anymore. + * Also check we have a reasonable ipv4 header. */ - memset(&opt, 0, sizeof(opt)); - opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - - rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); - rcu_read_unlock(); - - if (res) + if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || + ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) return;

+ memset(&opt, 0, sizeof(opt)); + if (ip_hdr(skb)->ihl > 5) { + if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) + return; + opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); + + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + rcu_read_unlock(); + + if (res) + return; + } __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); +} + +static void ipv4_link_failure(struct sk_buff *skb) +{ + struct rtable *rt; + + ipv4_send_dest_unreach(skb);

rt = skb_rtable(skb); if (rt)

From: Erez Alfasi ereza@mellanox.com

[ Upstream commit ace329f4ab3ba434be2adf618073c752d083b524 ]

Querying EEPROM high pages data for SFP module is currently not supported by our driver and yet queried, resulting in invalid FW queries.

Set the EEPROM ethtool data length to 256 for SFP module will limit the reading for page 0 only and prevent invalid FW queries.

Fixes: bb64143eee8c ("net/mlx5e: Add ethtool support for dump module EEPROM") Signed-off-by: Erez Alfasi ereza@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/port.c | 4 ---- 2 files changed, 1 insertion(+), 5 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1365,7 +1365,7 @@ static int mlx5e_get_module_info(struct break; case MLX5_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH; break; default: netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n", --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -368,10 +368,6 @@ int mlx5_query_module_eeprom(struct mlx5 size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;

i2c_addr = MLX5_I2C_ADDR_LOW; - if (offset >= MLX5_EEPROM_PAGE_LENGTH) { - i2c_addr = MLX5_I2C_ADDR_HIGH; - offset -= MLX5_EEPROM_PAGE_LENGTH; - }

MLX5_SET(mcia_reg, in, l, 0); MLX5_SET(mcia_reg, in, module, module_num);

From: Hangbin Liu liuhangbin@gmail.com

[ Upstream commit 925b0c841e066b488cc3a60272472b2c56300704 ]

If we add a bond device which is already the master of the team interface, we will hold the team->lock in team_add_slave() first and then request the lock in team_set_mac_address() again. The functions are called like:

- team_add_slave() - team_port_add() - team_port_enter() - team_modeop_port_enter() - __set_port_dev_addr() - dev_set_mac_address() - bond_set_mac_address() - dev_set_mac_address() - team_set_mac_address

Although team_upper_dev_link() would check the upper devices but it is called too late. Fix it by adding a checking before processing the slave.

v2: Do not split the string in netdev_err()

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device") Acked-by: Jiri Pirko jiri@mellanox.com Signed-off-by: Hangbin Liu liuhangbin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/team/team.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1163,6 +1163,12 @@ static int team_port_add(struct team *te return -EINVAL; }

+ if (netdev_has_upper_dev(dev, port_dev)) { + netdev_err(dev, "Device %s is already an upper device of the team interface\n", + portname); + return -EBUSY; + } + if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { netdev_err(dev, "Device %s is VLAN challenged and team device has VLAN set up\n",

From: ZhangXiaoxu zhangxiaoxu5@huawei.com

[ Upstream commit 19fad20d15a6494f47f85d869f00b11343ee5c78 ]

There is a UBSAN report as below: UBSAN: Undefined behaviour in net/ipv4/tcp_input.c:2877:56 signed integer overflow: 2147483647 * 1000 cannot be represented in type 'int' CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.1.0-rc4-00058-g582549e #1 Call Trace: <IRQ> dump_stack+0x8c/0xba ubsan_epilogue+0x11/0x60 handle_overflow+0x12d/0x170 ? ttwu_do_wakeup+0x21/0x320 __ubsan_handle_mul_overflow+0x12/0x20 tcp_ack_update_rtt+0x76c/0x780 tcp_clean_rtx_queue+0x499/0x14d0 tcp_ack+0x69e/0x1240 ? __wake_up_sync_key+0x2c/0x50 ? update_group_capacity+0x50/0x680 tcp_rcv_established+0x4e2/0xe10 tcp_v4_do_rcv+0x22b/0x420 tcp_v4_rcv+0xfe8/0x1190 ip_protocol_deliver_rcu+0x36/0x180 ip_local_deliver+0x15b/0x1a0 ip_rcv+0xac/0xd0 __netif_receive_skb_one_core+0x7f/0xb0 __netif_receive_skb+0x33/0xc0 netif_receive_skb_internal+0x84/0x1c0 napi_gro_receive+0x2a0/0x300 receive_buf+0x3d4/0x2350 ? detach_buf_split+0x159/0x390 virtnet_poll+0x198/0x840 ? reweight_entity+0x243/0x4b0 net_rx_action+0x25c/0x770 __do_softirq+0x19b/0x66d irq_exit+0x1eb/0x230 do_IRQ+0x7a/0x150 common_interrupt+0xf/0xf </IRQ>

It can be reproduced by: echo 2147483647 > /proc/sys/net/ipv4/tcp_min_rtt_wlen

Fixes: f672258391b42 ("tcp: track min RTT using windowed min-filter") Signed-off-by: ZhangXiaoxu zhangxiaoxu5@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/networking/ip-sysctl.txt | 1 + net/ipv4/sysctl_net_ipv4.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-)

--- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -405,6 +405,7 @@ tcp_min_rtt_wlen - INTEGER minimum RTT when it is moved to a longer path (e.g., due to traffic engineering). A longer window makes the filter more resistant to RTT inflations such as transient congestion. The unit is seconds. + Possible values: 0 - 86400 (1 day) Default: 300

tcp_moderate_rcvbuf - BOOLEAN --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -41,6 +41,7 @@ static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; +static int one_day_secs = 24 * 3600;

/* Update system visible IP port range */ static void set_local_port_range(struct net *net, int range[2]) @@ -460,7 +461,9 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_min_rtt_wlen, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one_day_secs }, { .procname = "tcp_low_latency",

From: Peter Oskolkov posk@google.com

[ Upstream commit c23f35d19db3b36ffb9e04b08f1d91565d15f84f ]

This is a refactoring patch: without changing runtime behavior, it moves rbtree-related code from IPv4-specific files/functions into .h/.c defrag files shared with IPv6 defragmentation code.

Signed-off-by: Peter Oskolkov posk@google.com Cc: Eric Dumazet edumazet@google.com Cc: Florian Westphal fw@strlen.de Cc: Tom Herbert tom@herbertland.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/inet_frag.h | 16 ++ net/ipv4/inet_fragment.c | 293 ++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/ip_fragment.c | 295 +++++------------------------------------------ 3 files changed, 342 insertions(+), 262 deletions(-)

--- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -76,8 +76,8 @@ struct inet_frag_queue { struct timer_list timer; spinlock_t lock; atomic_t refcnt; - struct sk_buff *fragments; /* Used in IPv6. */ - struct rb_root rb_fragments; /* Used in IPv4. */ + struct sk_buff *fragments; /* used in 6lopwpan IPv6. */ + struct rb_root rb_fragments; /* Used in IPv4/IPv6. */ struct sk_buff *fragments_tail; struct sk_buff *last_run_head; ktime_t stamp; @@ -152,4 +152,16 @@ static inline void add_frag_mem_limit(st

extern const u8 ip_frag_ecn_table[16];

+/* Return values of inet_frag_queue_insert() */ +#define IPFRAG_OK 0 +#define IPFRAG_DUP 1 +#define IPFRAG_OVERLAP 2 +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end); +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent); +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data); +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q); + #endif --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -24,6 +24,62 @@ #include <net/sock.h> #include <net/inet_frag.h> #include <net/inet_ecn.h> +#include <net/ip.h> +#include <net/ipv6.h> + +/* Use skb->cb to track consecutive/adjacent fragments coming at + * the end of the queue. Nodes in the rb-tree queue will + * contain "runs" of one or more adjacent fragments. + * + * Invariants: + * - next_frag is NULL at the tail of a "run"; + * - the head of a "run" has the sum of all fragment lengths in frag_run_len. + */ +struct ipfrag_skb_cb { + union { + struct inet_skb_parm h4; + struct inet6_skb_parm h6; + }; + struct sk_buff *next_frag; + int frag_run_len; +}; + +#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) + +static void fragcb_clear(struct sk_buff *skb) +{ + RB_CLEAR_NODE(&skb->rbnode); + FRAG_CB(skb)->next_frag = NULL; + FRAG_CB(skb)->frag_run_len = skb->len; +} + +/* Append skb to the last "run". */ +static void fragrun_append_to_last(struct inet_frag_queue *q, + struct sk_buff *skb) +{ + fragcb_clear(skb); + + FRAG_CB(q->last_run_head)->frag_run_len += skb->len; + FRAG_CB(q->fragments_tail)->next_frag = skb; + q->fragments_tail = skb; +} + +/* Create a new "run" with the skb. */ +static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); + fragcb_clear(skb); + + if (q->last_run_head) + rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, + &q->last_run_head->rbnode.rb_right); + else + rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + + q->fragments_tail = skb; + q->last_run_head = skb; +}

/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. @@ -122,6 +178,28 @@ static void inet_frag_destroy_rcu(struct kmem_cache_free(f->frags_cachep, q); }

+unsigned int inet_frag_rbtree_purge(struct rb_root *root) +{ + struct rb_node *p = rb_first(root); + unsigned int sum = 0; + + while (p) { + struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); + + p = rb_next(p); + rb_erase(&skb->rbnode, root); + while (skb) { + struct sk_buff *next = FRAG_CB(skb)->next_frag; + + sum += skb->truesize; + kfree_skb(skb); + skb = next; + } + } + return sum; +} +EXPORT_SYMBOL(inet_frag_rbtree_purge); + void inet_frag_destroy(struct inet_frag_queue *q) { struct sk_buff *fp; @@ -223,3 +301,218 @@ struct inet_frag_queue *inet_frag_find(s return fq; } EXPORT_SYMBOL(inet_frag_find); + +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end) +{ + struct sk_buff *last = q->fragments_tail; + + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments) MUST be silently discarded. + * + * Duplicates, however, should be ignored (i.e. skb dropped, but the + * queue/fragments kept for later reassembly). + */ + if (!last) + fragrun_create(q, skb); /* First fragment. */ + else if (last->ip_defrag_offset + last->len < end) { + /* This is the common case: skb goes to the end. */ + /* Detect and discard overlaps. */ + if (offset < last->ip_defrag_offset + last->len) + return IPFRAG_OVERLAP; + if (offset == last->ip_defrag_offset + last->len) + fragrun_append_to_last(q, skb); + else + fragrun_create(q, skb); + } else { + /* Binary search. Note that skb can become the first fragment, + * but not the last (covered above). + */ + struct rb_node **rbn, *parent; + + rbn = &q->rb_fragments.rb_node; + do { + struct sk_buff *curr; + int curr_run_end; + + parent = *rbn; + curr = rb_to_skb(parent); + curr_run_end = curr->ip_defrag_offset + + FRAG_CB(curr)->frag_run_len; + if (end <= curr->ip_defrag_offset) + rbn = &parent->rb_left; + else if (offset >= curr_run_end) + rbn = &parent->rb_right; + else if (offset >= curr->ip_defrag_offset && + end <= curr_run_end) + return IPFRAG_DUP; + else + return IPFRAG_OVERLAP; + } while (*rbn); + /* Here we have parent properly set, and rbn pointing to + * one of its NULL left/right children. Insert skb. + */ + fragcb_clear(skb); + rb_link_node(&skb->rbnode, parent, rbn); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + } + + skb->ip_defrag_offset = offset; + + return IPFRAG_OK; +} +EXPORT_SYMBOL(inet_frag_queue_insert); + +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent) +{ + struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); + struct sk_buff **nextp; + int delta; + + if (head != skb) { + fp = skb_clone(skb, GFP_ATOMIC); + if (!fp) + return NULL; + FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; + if (RB_EMPTY_NODE(&skb->rbnode)) + FRAG_CB(parent)->next_frag = fp; + else + rb_replace_node(&skb->rbnode, &fp->rbnode, + &q->rb_fragments); + if (q->fragments_tail == skb) + q->fragments_tail = fp; + skb_morph(skb, head); + FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + consume_skb(head); + head = skb; + } + WARN_ON(head->ip_defrag_offset != 0); + + delta = -head->truesize; + + /* Head of list must not be cloned. */ + if (skb_unclone(head, GFP_ATOMIC)) + return NULL; + + delta += head->truesize; + if (delta) + add_frag_mem_limit(q->net, delta); + + /* If the first fragment is fragmented itself, we split + * it to two chunks: the first with data and paged part + * and the second, holding only fragments. + */ + if (skb_has_frag_list(head)) { + struct sk_buff *clone; + int i, plen = 0; + + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) + return NULL; + skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; + skb_frag_list_init(head); + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); + clone->data_len = head->data_len - plen; + clone->len = clone->data_len; + head->truesize += clone->truesize; + clone->csum = 0; + clone->ip_summed = head->ip_summed; + add_frag_mem_limit(q->net, clone->truesize); + skb_shinfo(head)->frag_list = clone; + nextp = &clone->next; + } else { + nextp = &skb_shinfo(head)->frag_list; + } + + return nextp; +} +EXPORT_SYMBOL(inet_frag_reasm_prepare); + +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data) +{ + struct sk_buff **nextp = (struct sk_buff **)reasm_data; + struct rb_node *rbn; + struct sk_buff *fp; + + skb_push(head, head->data - skb_network_header(head)); + + /* Traverse the tree in order, to build frag_list. */ + fp = FRAG_CB(head)->next_frag; + rbn = rb_next(&head->rbnode); + rb_erase(&head->rbnode, &q->rb_fragments); + while (rbn || fp) { + /* fp points to the next sk_buff in the current run; + * rbn points to the next run. + */ + /* Go through the current run. */ + while (fp) { + *nextp = fp; + nextp = &fp->next; + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; + head->data_len += fp->len; + head->len += fp->len; + if (head->ip_summed != fp->ip_summed) + head->ip_summed = CHECKSUM_NONE; + else if (head->ip_summed == CHECKSUM_COMPLETE) + head->csum = csum_add(head->csum, fp->csum); + head->truesize += fp->truesize; + fp = FRAG_CB(fp)->next_frag; + } + /* Move to the next run. */ + if (rbn) { + struct rb_node *rbnext = rb_next(rbn); + + fp = rb_to_skb(rbn); + rb_erase(rbn, &q->rb_fragments); + rbn = rbnext; + } + } + sub_frag_mem_limit(q->net, head->truesize); + + *nextp = NULL; + head->next = NULL; + head->prev = NULL; + head->tstamp = q->stamp; +} +EXPORT_SYMBOL(inet_frag_reasm_finish); + +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) +{ + struct sk_buff *head; + + if (q->fragments) { + head = q->fragments; + q->fragments = head->next; + } else { + struct sk_buff *skb; + + head = skb_rb_first(&q->rb_fragments); + if (!head) + return NULL; + skb = FRAG_CB(head)->next_frag; + if (skb) + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + else + rb_erase(&head->rbnode, &q->rb_fragments); + memset(&head->rbnode, 0, sizeof(head->rbnode)); + barrier(); + } + if (head == q->fragments_tail) + q->fragments_tail = NULL; + + sub_frag_mem_limit(q->net, head->truesize); + + return head; +} +EXPORT_SYMBOL(inet_frag_pull_head); --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -56,57 +56,6 @@ */ static const char ip_frag_cache_name[] = "ip4-frags";

-/* Use skb->cb to track consecutive/adjacent fragments coming at - * the end of the queue. Nodes in the rb-tree queue will - * contain "runs" of one or more adjacent fragments. - * - * Invariants: - * - next_frag is NULL at the tail of a "run"; - * - the head of a "run" has the sum of all fragment lengths in frag_run_len. - */ -struct ipfrag_skb_cb { - struct inet_skb_parm h; - struct sk_buff *next_frag; - int frag_run_len; -}; - -#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) - -static void ip4_frag_init_run(struct sk_buff *skb) -{ - BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); - - FRAG_CB(skb)->next_frag = NULL; - FRAG_CB(skb)->frag_run_len = skb->len; -} - -/* Append skb to the last "run". */ -static void ip4_frag_append_to_last_run(struct inet_frag_queue *q, - struct sk_buff *skb) -{ - RB_CLEAR_NODE(&skb->rbnode); - FRAG_CB(skb)->next_frag = NULL; - - FRAG_CB(q->last_run_head)->frag_run_len += skb->len; - FRAG_CB(q->fragments_tail)->next_frag = skb; - q->fragments_tail = skb; -} - -/* Create a new "run" with the skb. */ -static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb) -{ - if (q->last_run_head) - rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, - &q->last_run_head->rbnode.rb_right); - else - rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); - rb_insert_color(&skb->rbnode, &q->rb_fragments); - - ip4_frag_init_run(skb); - q->fragments_tail = skb; - q->last_run_head = skb; -} - /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; @@ -210,27 +159,9 @@ static void ip_expire(unsigned long arg) * pull the head out of the tree in order to be able to * deal with head->dev. */ - if (qp->q.fragments) { - head = qp->q.fragments; - qp->q.fragments = head->next; - } else { - head = skb_rb_first(&qp->q.rb_fragments); - if (!head) - goto out; - if (FRAG_CB(head)->next_frag) - rb_replace_node(&head->rbnode, - &FRAG_CB(head)->next_frag->rbnode, - &qp->q.rb_fragments); - else - rb_erase(&head->rbnode, &qp->q.rb_fragments); - memset(&head->rbnode, 0, sizeof(head->rbnode)); - barrier(); - } - if (head == qp->q.fragments_tail) - qp->q.fragments_tail = NULL; - - sub_frag_mem_limit(qp->q.net, head->truesize); - + head = inet_frag_pull_head(&qp->q); + if (!head) + goto out; head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; @@ -343,12 +274,10 @@ static int ip_frag_reinit(struct ipq *qp static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); - struct rb_node **rbn, *parent; - struct sk_buff *skb1, *prev_tail; - int ihl, end, skb1_run_end; + int ihl, end, flags, offset; + struct sk_buff *prev_tail; struct net_device *dev; unsigned int fragsize; - int flags, offset; int err = -ENOENT; u8 ecn;

@@ -380,7 +309,7 @@ static int ip_frag_queue(struct ipq *qp, */ if (end < qp->q.len || ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) - goto err; + goto discard_qp; qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { @@ -392,82 +321,33 @@ static int ip_frag_queue(struct ipq *qp, if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ if (qp->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_qp; qp->q.len = end; } } if (end == offset) - goto err; + goto discard_qp;

err = -ENOMEM; if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) - goto err; + goto discard_qp;

err = pskb_trim_rcsum(skb, end - offset); if (err) - goto err; + goto discard_qp;

/* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier();

- /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - * - * We do the same here for IPv4 (and increment an snmp counter) but - * we do not want to drop the whole queue in response to a duplicate - * fragment. - */ - - err = -EINVAL; - /* Find out where to put this fragment. */ prev_tail = qp->q.fragments_tail; - if (!prev_tail) - ip4_frag_create_run(&qp->q, skb); /* First fragment. */ - else if (prev_tail->ip_defrag_offset + prev_tail->len < end) { - /* This is the common case: skb goes to the end. */ - /* Detect and discard overlaps. */ - if (offset < prev_tail->ip_defrag_offset + prev_tail->len) - goto discard_qp; - if (offset == prev_tail->ip_defrag_offset + prev_tail->len) - ip4_frag_append_to_last_run(&qp->q, skb); - else - ip4_frag_create_run(&qp->q, skb); - } else { - /* Binary search. Note that skb can become the first fragment, - * but not the last (covered above). - */ - rbn = &qp->q.rb_fragments.rb_node; - do { - parent = *rbn; - skb1 = rb_to_skb(parent); - skb1_run_end = skb1->ip_defrag_offset + - FRAG_CB(skb1)->frag_run_len; - if (end <= skb1->ip_defrag_offset) - rbn = &parent->rb_left; - else if (offset >= skb1_run_end) - rbn = &parent->rb_right; - else if (offset >= skb1->ip_defrag_offset && - end <= skb1_run_end) - goto err; /* No new data, potential duplicate */ - else - goto discard_qp; /* Found an overlap */ - } while (*rbn); - /* Here we have parent properly set, and rbn pointing to - * one of its NULL left/right children. Insert skb. - */ - ip4_frag_init_run(skb); - rb_link_node(&skb->rbnode, parent, rbn); - rb_insert_color(&skb->rbnode, &qp->q.rb_fragments); - } + err = inet_frag_queue_insert(&qp->q, skb, offset, end); + if (err) + goto insert_error;

if (dev) qp->iif = dev->ifindex; - skb->ip_defrag_offset = offset;

qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; @@ -492,15 +372,24 @@ static int ip_frag_queue(struct ipq *qp, skb->_skb_refdst = 0UL; err = ip_frag_reasm(qp, skb, prev_tail, dev); skb->_skb_refdst = orefdst; + if (err) + inet_frag_kill(&qp->q); return err; }

skb_dst_drop(skb); return -EINPROGRESS;

+insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; + __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q); - __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); + __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb(skb); return err; @@ -512,12 +401,8 @@ static int ip_frag_reasm(struct ipq *qp, { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct iphdr *iph; - struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments); - struct sk_buff **nextp; /* To build frag_list. */ - struct rb_node *rbn; - int len; - int ihlen; - int err; + void *reasm_data; + int len, err; u8 ecn;

ipq_kill(qp); @@ -527,111 +412,23 @@ static int ip_frag_reasm(struct ipq *qp, err = -EINVAL; goto out_fail; } - /* Make the one we just received the head. */ - if (head != skb) { - fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - goto out_nomem; - FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; - if (RB_EMPTY_NODE(&skb->rbnode)) - FRAG_CB(prev_tail)->next_frag = fp; - else - rb_replace_node(&skb->rbnode, &fp->rbnode, - &qp->q.rb_fragments); - if (qp->q.fragments_tail == skb) - qp->q.fragments_tail = fp; - skb_morph(skb, head); - FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; - rb_replace_node(&head->rbnode, &skb->rbnode, - &qp->q.rb_fragments); - consume_skb(head); - head = skb; - } - - WARN_ON(head->ip_defrag_offset != 0);

- /* Allocate a new buffer for the datagram. */ - ihlen = ip_hdrlen(head); - len = ihlen + qp->q.len; + /* Make the one we just received the head. */ + reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); + if (!reasm_data) + goto out_nomem;

+ len = ip_hdrlen(skb) + qp->q.len; err = -E2BIG; if (len > 65535) goto out_oversize;

- /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_nomem; - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_nomem; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->truesize += clone->truesize; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(qp->q.net, clone->truesize); - skb_shinfo(head)->frag_list = clone; - nextp = &clone->next; - } else { - nextp = &skb_shinfo(head)->frag_list; - } - - skb_push(head, head->data - skb_network_header(head)); - - /* Traverse the tree in order, to build frag_list. */ - fp = FRAG_CB(head)->next_frag; - rbn = rb_next(&head->rbnode); - rb_erase(&head->rbnode, &qp->q.rb_fragments); - while (rbn || fp) { - /* fp points to the next sk_buff in the current run; - * rbn points to the next run. - */ - /* Go through the current run. */ - while (fp) { - *nextp = fp; - nextp = &fp->next; - fp->prev = NULL; - memset(&fp->rbnode, 0, sizeof(fp->rbnode)); - fp->sk = NULL; - head->data_len += fp->len; - head->len += fp->len; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp = FRAG_CB(fp)->next_frag; - } - /* Move to the next run. */ - if (rbn) { - struct rb_node *rbnext = rb_next(rbn); - - fp = rb_to_skb(rbn); - rb_erase(rbn, &qp->q.rb_fragments); - rbn = rbnext; - } - } - sub_frag_mem_limit(qp->q.net, head->truesize); + inet_frag_reasm_finish(&qp->q, skb, reasm_data);

- *nextp = NULL; - head->next = NULL; - head->prev = NULL; - head->dev = dev; - head->tstamp = qp->q.stamp; - IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); + skb->dev = dev; + IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size);

- iph = ip_hdr(head); + iph = ip_hdr(skb); iph->tot_len = htons(len); iph->tos |= ecn;

@@ -644,7 +441,7 @@ static int ip_frag_reasm(struct ipq *qp, * from one very small df-fragment and one large non-df frag. */ if (qp->max_df_size == qp->q.max_size) { - IPCB(head)->flags |= IPSKB_FRAG_PMTU; + IPCB(skb)->flags |= IPSKB_FRAG_PMTU; iph->frag_off = htons(IP_DF); } else { iph->frag_off = 0; @@ -742,28 +539,6 @@ struct sk_buff *ip_check_defrag(struct n } EXPORT_SYMBOL(ip_check_defrag);

-unsigned int inet_frag_rbtree_purge(struct rb_root *root) -{ - struct rb_node *p = rb_first(root); - unsigned int sum = 0; - - while (p) { - struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); - - p = rb_next(p); - rb_erase(&skb->rbnode, root); - while (skb) { - struct sk_buff *next = FRAG_CB(skb)->next_frag; - - sum += skb->truesize; - kfree_skb(skb); - skb = next; - } - } - return sum; -} -EXPORT_SYMBOL(inet_frag_rbtree_purge); - #ifdef CONFIG_SYSCTL static int dist_min;

From: Peter Oskolkov posk@google.com

[ Upstream commit d4289fcc9b16b89619ee1c54f829e05e56de8b9a ]

Currently, IPv6 defragmentation code drops non-last fragments that are smaller than 1280 bytes: see commit 0ed4229b08c1 ("ipv6: defrag: drop non-last frags smaller than min mtu")

This behavior is not specified in IPv6 RFCs and appears to break compatibility with some IPv6 implemenations, as reported here: https://www.spinics.net/lists/netdev/msg543846.html

This patch re-uses common IP defragmentation queueing and reassembly code in IPv6, removing the 1280 byte restriction.

Signed-off-by: Peter Oskolkov posk@google.com Reported-by: Tom Herbert tom@herbertland.com Cc: Eric Dumazet edumazet@google.com Cc: Florian Westphal fw@strlen.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/ipv6_frag.h | 11 +- net/ipv6/reassembly.c | 248 ++++++++++++++---------------------------------- 2 files changed, 82 insertions(+), 177 deletions(-)

--- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -82,8 +82,15 @@ ip6frag_expire_frag_queue(struct net *ne __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);

/* Don't send error if the first segment did not arrive. */ - head = fq->q.fragments; - if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head) + if (!(fq->q.flags & INET_FRAG_FIRST_IN)) + goto out; + + /* sk_buff::dev and sk_buff::rbnode are unionized. So we + * pull the head out of the tree in order to be able to + * deal with head->dev. + */ + head = inet_frag_pull_head(&fq->q); + if (!head) goto out;

head->dev = dev; --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -62,13 +62,6 @@

static const char ip6_frag_cache_name[] = "ip6-frags";

-struct ip6frag_skb_cb { - struct inet6_skb_parm h; - int offset; -}; - -#define FRAG6_CB(skb) ((struct ip6frag_skb_cb *)((skb)->cb)) - static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) { return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); @@ -76,8 +69,8 @@ static u8 ip6_frag_ecn(const struct ipv6

static struct inet_frags ip6_frags;

-static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev); +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev);

static void ip6_frag_expire(unsigned long data) { @@ -117,21 +110,26 @@ static int ip6_frag_queue(struct frag_qu struct frag_hdr *fhdr, int nhoff, u32 *prob_offset) { - struct sk_buff *prev, *next; - struct net_device *dev; - int offset, end; struct net *net = dev_net(skb_dst(skb)->dev); + int offset, end, fragsize; + struct sk_buff *prev_tail; + struct net_device *dev; + int err = -ENOENT; u8 ecn;

if (fq->q.flags & INET_FRAG_COMPLETE) goto err;

+ err = -EINVAL; offset = ntohs(fhdr->frag_off) & ~0x7; end = offset + (ntohs(ipv6_hdr(skb)->payload_len) - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));

if ((unsigned int)end > IPV6_MAXPLEN) { *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb); + /* note that if prob_offset is set, the skb is freed elsewhere, + * we do not free it here. + */ return -1; }

@@ -151,7 +149,7 @@ static int ip6_frag_queue(struct frag_qu */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) - goto err; + goto discard_fq; fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { @@ -168,75 +166,45 @@ static int ip6_frag_queue(struct frag_qu if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_fq; fq->q.len = end; } }

if (end == offset) - goto err; + goto discard_fq;

+ err = -ENOMEM; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) - goto err; - - if (pskb_trim_rcsum(skb, end - offset)) - goto err; - - /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ - prev = fq->q.fragments_tail; - if (!prev || FRAG6_CB(prev)->offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = fq->q.fragments; next != NULL; next = next->next) { - if (FRAG6_CB(next)->offset >= offset) - break; /* bingo! */ - prev = next; - } - -found: - /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - */ - - /* Check for overlap with preceding fragment. */ - if (prev && - (FRAG6_CB(prev)->offset + prev->len) > offset) goto discard_fq;

- /* Look for overlap with succeeding segment. */ - if (next && FRAG6_CB(next)->offset < end) + err = pskb_trim_rcsum(skb, end - offset); + if (err) goto discard_fq;

- FRAG6_CB(skb)->offset = offset; + /* Note : skb->rbnode and skb->dev share the same location. */ + dev = skb->dev; + /* Makes sure compiler wont do silly aliasing games */ + barrier();

- /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - fq->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - fq->q.fragments = skb; + prev_tail = fq->q.fragments_tail; + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) + goto insert_error;

- dev = skb->dev; - if (dev) { + if (dev) fq->iif = dev->ifindex; - skb->dev = NULL; - } + fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; fq->ecn |= ecn; add_frag_mem_limit(fq->q.net, skb->truesize);

+ fragsize = -skb_network_offset(skb) + skb->len; + if (fragsize > fq->q.max_size) + fq->q.max_size = fragsize; + /* The first fragment. * nhoffset is obtained from the first fragment, of course. */ @@ -247,44 +215,48 @@ found:

if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { - int res; unsigned long orefdst = skb->_skb_refdst;

skb->_skb_refdst = 0UL; - res = ip6_frag_reasm(fq, prev, dev); + err = ip6_frag_reasm(fq, skb, prev_tail, dev); skb->_skb_refdst = orefdst; - return res; + return err; }

skb_dst_drop(skb); - return -1; + return -EINPROGRESS;

+insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASM_OVERLAPS); discard_fq: inet_frag_kill(&fq->q); -err: __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); +err: kfree_skb(skb); - return -1; + return err; }

/* * Check if this packet is complete. - * Returns NULL on failure by any reason, and pointer - * to current nexthdr field in reassembled frame. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ -static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev) +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev) { struct net *net = container_of(fq->q.net, struct net, ipv6.frags); - struct sk_buff *fp, *head = fq->q.fragments; - int payload_len; unsigned int nhoff; - int sum_truesize; + void *reasm_data; + int payload_len; u8 ecn;

inet_frag_kill(&fq->q); @@ -293,113 +265,40 @@ static int ip6_frag_reasm(struct frag_qu if (unlikely(ecn == 0xff)) goto out_fail;

- /* Make the one we just received the head. */ - if (prev) { - head = prev->next; - fp = skb_clone(head, GFP_ATOMIC); - - if (!fp) - goto out_oom; - - fp->next = head->next; - if (!fp->next) - fq->q.fragments_tail = fp; - prev->next = fp; - - skb_morph(head, fq->q.fragments); - head->next = fq->q.fragments->next; - - consume_skb(fq->q.fragments); - fq->q.fragments = head; - } - - WARN_ON(head == NULL); - WARN_ON(FRAG6_CB(head)->offset != 0); + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto out_oom;

- /* Unfragmented part is taken from the first segment. */ - payload_len = ((head->data - skb_network_header(head)) - + payload_len = ((skb->data - skb_network_header(skb)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) goto out_oversize;

- /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_oom; - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_oom; - clone->next = head->next; - head->next = clone; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(fq->q.net, clone->truesize); - } - /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ nhoff = fq->nhoffset; - skb_network_header(head)[nhoff] = skb_transport_header(head)[0]; - memmove(head->head + sizeof(struct frag_hdr), head->head, - (head->data - head->head) - sizeof(struct frag_hdr)); - if (skb_mac_header_was_set(head)) - head->mac_header += sizeof(struct frag_hdr); - head->network_header += sizeof(struct frag_hdr); - - skb_reset_transport_header(head); - skb_push(head, head->data - skb_network_header(head)); - - sum_truesize = head->truesize; - for (fp = head->next; fp;) { - bool headstolen; - int delta; - struct sk_buff *next = fp->next; - - sum_truesize += fp->truesize; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - - if (skb_try_coalesce(head, fp, &headstolen, &delta)) { - kfree_skb_partial(fp, headstolen); - } else { - if (!skb_shinfo(head)->frag_list) - skb_shinfo(head)->frag_list = fp; - head->data_len += fp->len; - head->len += fp->len; - head->truesize += fp->truesize; - } - fp = next; - } - sub_frag_mem_limit(fq->q.net, sum_truesize); - - head->next = NULL; - head->dev = dev; - head->tstamp = fq->q.stamp; - ipv6_hdr(head)->payload_len = htons(payload_len); - ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); - IP6CB(head)->nhoff = nhoff; - IP6CB(head)->flags |= IP6SKB_FRAGMENTED; + skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0]; + memmove(skb->head + sizeof(struct frag_hdr), skb->head, + (skb->data - skb->head) - sizeof(struct frag_hdr)); + if (skb_mac_header_was_set(skb)) + skb->mac_header += sizeof(struct frag_hdr); + skb->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(skb); + + inet_frag_reasm_finish(&fq->q, skb, reasm_data); + + skb->dev = dev; + ipv6_hdr(skb)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); + IP6CB(skb)->nhoff = nhoff; + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + IP6CB(skb)->frag_max_size = fq->q.max_size;

/* Yes, and fold redundant checksum back. 8) */ - skb_postpush_rcsum(head, skb_network_header(head), - skb_network_header_len(head)); + skb_postpush_rcsum(skb, skb_network_header(skb), + skb_network_header_len(skb));

rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); @@ -407,6 +306,7 @@ static int ip6_frag_reasm(struct frag_qu fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; return 1;

out_oversize: @@ -418,6 +318,7 @@ out_fail: rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); rcu_read_unlock(); + inet_frag_kill(&fq->q); return -1; }

@@ -456,10 +357,6 @@ static int ipv6_frag_rcv(struct sk_buff return 1; }

- if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && - fhdr->frag_off & htons(IP6_MF)) - goto fail_hdr; - iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { @@ -477,6 +374,7 @@ static int ipv6_frag_rcv(struct sk_buff if (prob_offset) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); + /* icmpv6_param_prob() calls kfree_skb(skb) */ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset); } return ret;