From: Heiko Thiery heiko.thiery@gmail.com

[ Upstream commit 6a4d7234ae9a3bb31181f348ade9bbdb55aeb5c5 ]

When accessing the timecounter register on an i.MX8MQ the kernel hangs. This is only the case when the interface is down. This can be reproduced by reading with 'phc_ctrl eth0 get'.

Like described in the change in 91c0d987a9788dcc5fe26baafd73bf9242b68900 the igp clock is disabled when the interface is down and leads to a system hang.

So we check if the ptp clock status before reading the timecounter register.

Signed-off-by: Heiko Thiery heiko.thiery@gmail.com Acked-by: Richard Cochran richardcochran@gmail.com Link: https://lore.kernel.org/r/20210225211514.9115-1-heiko.thiery@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/fec_ptp.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index f9e74461bdc0..123181612595 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -396,9 +396,16 @@ static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) u64 ns; unsigned long flags;

+ mutex_lock(&adapter->ptp_clk_mutex); + /* Check the ptp clock */ + if (!adapter->ptp_clk_on) { + mutex_unlock(&adapter->ptp_clk_mutex); + return -EINVAL; + } spin_lock_irqsave(&adapter->tmreg_lock, flags); ns = timecounter_read(&adapter->tc); spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + mutex_unlock(&adapter->ptp_clk_mutex);

*ts = ns_to_timespec64(ns);

From: Tong Zhang ztong0001@gmail.com

[ Upstream commit 4deb550bc3b698a1f03d0332cde3df154d1b6c1e ]

label err_eni_release is reachable when eni_start() fail. In eni_start() it calls dev->phy->start() in the last step, if start() fail we don't need to call phy->stop(), if start() is never called, we neither need to call phy->stop(), otherwise null-ptr-deref will happen.

In order to fix this issue, don't call phy->stop() in label err_eni_release

[ 4.875714] ================================================================== [ 4.876091] BUG: KASAN: null-ptr-deref in suni_stop+0x47/0x100 [suni] [ 4.876433] Read of size 8 at addr 0000000000000030 by task modprobe/95 [ 4.876778] [ 4.876862] CPU: 0 PID: 95 Comm: modprobe Not tainted 5.11.0-rc7-00090-gdcc0b49040c7 #2 [ 4.877290] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-48-gd94 [ 4.877876] Call Trace: [ 4.878009] dump_stack+0x7d/0xa3 [ 4.878191] kasan_report.cold+0x10c/0x10e [ 4.878410] ? __slab_free+0x2f0/0x340 [ 4.878612] ? suni_stop+0x47/0x100 [suni] [ 4.878832] suni_stop+0x47/0x100 [suni] [ 4.879043] eni_do_release+0x3b/0x70 [eni] [ 4.879269] eni_init_one.cold+0x1152/0x1747 [eni] [ 4.879528] ? _raw_spin_lock_irqsave+0x7b/0xd0 [ 4.879768] ? eni_ioctl+0x270/0x270 [eni] [ 4.879990] ? __mutex_lock_slowpath+0x10/0x10 [ 4.880226] ? eni_ioctl+0x270/0x270 [eni] [ 4.880448] local_pci_probe+0x6f/0xb0 [ 4.880650] pci_device_probe+0x171/0x240 [ 4.880864] ? pci_device_remove+0xe0/0xe0 [ 4.881086] ? kernfs_create_link+0xb6/0x110 [ 4.881315] ? sysfs_do_create_link_sd.isra.0+0x76/0xe0 [ 4.881594] really_probe+0x161/0x420 [ 4.881791] driver_probe_device+0x6d/0xd0 [ 4.882010] device_driver_attach+0x82/0x90 [ 4.882233] ? device_driver_attach+0x90/0x90 [ 4.882465] __driver_attach+0x60/0x100 [ 4.882671] ? device_driver_attach+0x90/0x90 [ 4.882903] bus_for_each_dev+0xe1/0x140 [ 4.883114] ? subsys_dev_iter_exit+0x10/0x10 [ 4.883346] ? klist_node_init+0x61/0x80 [ 4.883557] bus_add_driver+0x254/0x2a0 [ 4.883764] driver_register+0xd3/0x150 [ 4.883971] ? 0xffffffffc0038000 [ 4.884149] do_one_initcall+0x84/0x250 [ 4.884355] ? trace_event_raw_event_initcall_finish+0x150/0x150 [ 4.884674] ? unpoison_range+0xf/0x30 [ 4.884875] ? ____kasan_kmalloc.constprop.0+0x84/0xa0 [ 4.885150] ? unpoison_range+0xf/0x30 [ 4.885352] ? unpoison_range+0xf/0x30 [ 4.885557] do_init_module+0xf8/0x350 [ 4.885760] load_module+0x3fe6/0x4340 [ 4.885960] ? vm_unmap_ram+0x1d0/0x1d0 [ 4.886166] ? ____kasan_kmalloc.constprop.0+0x84/0xa0 [ 4.886441] ? module_frob_arch_sections+0x20/0x20 [ 4.886697] ? __do_sys_finit_module+0x108/0x170 [ 4.886941] __do_sys_finit_module+0x108/0x170 [ 4.887178] ? __ia32_sys_init_module+0x40/0x40 [ 4.887419] ? file_open_root+0x200/0x200 [ 4.887634] ? do_sys_open+0x85/0xe0 [ 4.887826] ? filp_open+0x50/0x50 [ 4.888009] ? fpregs_assert_state_consistent+0x4d/0x60 [ 4.888287] ? exit_to_user_mode_prepare+0x2f/0x130 [ 4.888547] do_syscall_64+0x33/0x40 [ 4.888739] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 4.889010] RIP: 0033:0x7ff62fcf1cf7 [ 4.889202] Code: 48 89 57 30 48 8b 04 24 48 89 47 38 e9 1d a0 02 00 48 89 f8 48 89 f71 [ 4.890172] RSP: 002b:00007ffe6644ade8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 [ 4.890570] RAX: ffffffffffffffda RBX: 0000000000f2ca70 RCX: 00007ff62fcf1cf7 [ 4.890944] RDX: 0000000000000000 RSI: 0000000000f2b9e0 RDI: 0000000000000003 [ 4.891318] RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000001 [ 4.891691] R10: 00007ff62fd55300 R11: 0000000000000246 R12: 0000000000f2b9e0 [ 4.892064] R13: 0000000000000000 R14: 0000000000f2bdd0 R15: 0000000000000001 [ 4.892439] ==================================================================

Signed-off-by: Tong Zhang ztong0001@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/atm/eni.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index 9d16743c4917..2b7786cd548f 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2279,7 +2279,8 @@ static int eni_init_one(struct pci_dev *pci_dev, return rc;

err_eni_release: - eni_do_release(dev); + dev->phy = NULL; + iounmap(ENI_DEV(dev)->ioaddr); err_unregister: atm_dev_deregister(dev); err_free_consistent:

From: Dinghao Liu dinghao.liu@zju.edu.cn

[ Upstream commit 7a766381634da19fc837619b0a34590498d9d29a ]

When ixgbe_fdir_write_perfect_filter_82599() fails, input allocated by kzalloc() has not been freed, which leads to memleak.

Signed-off-by: Dinghao Liu dinghao.liu@zju.edu.cn Reviewed-by: Paul Menzel pmenzel@molgen.mpg.de Tested-by: Tony Brelinski tonyx.brelinski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 36d73bf32f4f..8e2aaf774693 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8677,8 +8677,10 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, ixgbe_atr_compute_perfect_hash_82599(&input->filter, mask); err = ixgbe_fdir_write_perfect_filter_82599(hw, &input->filter, input->sw_idx, queue); - if (!err) - ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx); + if (err) + goto err_out_w_lock; + + ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx); spin_unlock(&adapter->fdir_perfect_lock);

if ((uhtid != 0x800) && (adapter->jump_tables[uhtid]))

From: Denis Efremov efremov@linux.com

[ Upstream commit 155b23e6e53475ca3b8c2a946299b4d4dd6a5a1e ]

RXMAC_BC_FRM_CNT_COUNT added to mp->rx_bcasts twice in a row in niu_xmac_interrupt(). Remove the second addition.

Signed-off-by: Denis Efremov efremov@linux.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/sun/niu.c | 2 -- 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index fe5b0ac8c631..5bf47279f9c1 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -3948,8 +3948,6 @@ static void niu_xmac_interrupt(struct niu *np) mp->rx_mcasts += RXMAC_MC_FRM_CNT_COUNT; if (val & XRXMAC_STATUS_RXBCAST_CNT_EXP) mp->rx_bcasts += RXMAC_BC_FRM_CNT_COUNT; - if (val & XRXMAC_STATUS_RXBCAST_CNT_EXP) - mp->rx_bcasts += RXMAC_BC_FRM_CNT_COUNT; if (val & XRXMAC_STATUS_RXHIST1_CNT_EXP) mp->rx_hist_cnt1 += RXMAC_HIST_CNT1_COUNT; if (val & XRXMAC_STATUS_RXHIST2_CNT_EXP)

From: Frank Sorenson sorenson@redhat.com

[ Upstream commit ad3dbe35c833c2d4d0bbf3f04c785d32f931e7c9 ]

CREATE requests return a post_op_fh3, rather than nfs_fh3. The post_op_fh3 includes an extra word to indicate 'handle_follows'.

Without that additional word, create fails when full 64-byte filehandles are in use.

Add NFS3_post_op_fh_sz, and correct the size calculation for NFS3_createres_sz.

Signed-off-by: Frank Sorenson sorenson@redhat.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs3xdr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 267126d32ec0..4a68837e92ea 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -33,6 +33,7 @@ */ #define NFS3_fhandle_sz (1+16) #define NFS3_fh_sz (NFS3_fhandle_sz) /* shorthand */ +#define NFS3_post_op_fh_sz (1+NFS3_fh_sz) #define NFS3_sattr_sz (15) #define NFS3_filename_sz (1+(NFS3_MAXNAMLEN>>2)) #define NFS3_path_sz (1+(NFS3_MAXPATHLEN>>2)) @@ -70,7 +71,7 @@ #define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1) #define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3) #define NFS3_writeres_sz (1+NFS3_wcc_data_sz+4) -#define NFS3_createres_sz (1+NFS3_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) +#define NFS3_createres_sz (1+NFS3_post_op_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) #define NFS3_renameres_sz (1+(2 * NFS3_wcc_data_sz)) #define NFS3_linkres_sz (1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) #define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2)

From: Tong Zhang ztong0001@gmail.com

[ Upstream commit 3153724fc084d8ef640c611f269ddfb576d1dcb1 ]

dev->dev_data is set in zatm.c, calling zatm_start() will overwrite this dev->dev_data in uPD98402_start() and a subsequent PRIV(dev)->lock (i.e dev->phy_data->lock) will result in a null-ptr-dereference.

I believe this is a typo and what it actually want to do is to allocate phy_data instead of dev_data.

Signed-off-by: Tong Zhang ztong0001@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/atm/uPD98402.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/atm/uPD98402.c b/drivers/atm/uPD98402.c index 5120a96b3a89..b2f4e8df1591 100644 --- a/drivers/atm/uPD98402.c +++ b/drivers/atm/uPD98402.c @@ -210,7 +210,7 @@ static void uPD98402_int(struct atm_dev *dev) static int uPD98402_start(struct atm_dev *dev) { DPRINTK("phy_start\n"); - if (!(dev->dev_data = kmalloc(sizeof(struct uPD98402_priv),GFP_KERNEL))) + if (!(dev->phy_data = kmalloc(sizeof(struct uPD98402_priv),GFP_KERNEL))) return -ENOMEM; spin_lock_init(&PRIV(dev)->lock); memset(&PRIV(dev)->sonet_stats,0,sizeof(struct k_sonet_stats));

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit d5b0e0677bfd5efd17c5bbb00156931f0d41cb85 ]

Jakub reported that:

static struct net_device *rtl8139_init_board(struct pci_dev *pdev) { ... u64_stats_init(&tp->rx_stats.syncp); u64_stats_init(&tp->tx_stats.syncp); ... }

results in lockdep getting confused between the RX and TX stats lock. This is because u64_stats_init() is an inline calling seqcount_init(), which is a macro using a static variable to generate a lockdep class.

By wrapping that in an inline, we negate the effect of the macro and fold the static key variable, hence the confusion.

Fix by also making u64_stats_init() a macro for the case where it matters, leaving the other case an inline for argument validation etc.

Reported-by: Jakub Kicinski kuba@kernel.org Debugged-by: "Ahmed S. Darwish" a.darwish@linutronix.de Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Tested-by: "Erhard F." erhard_f@mailbox.org Link: https://lkml.kernel.org/r/YEXicy6+9MksdLZh@hirez.programming.kicks-ass.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/u64_stats_sync.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 650f3dd6b800..f604a8fe9d2e 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -68,12 +68,13 @@ struct u64_stats_sync { };

+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) +#define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) +#else static inline void u64_stats_init(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) - seqcount_init(&syncp->seq); -#endif } +#endif

static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) {

From: Sergei Trofimovich slyfox@gentoo.org

[ Upstream commit 0ceb1ace4a2778e34a5414e5349712ae4dc41d85 ]

In https://bugs.gentoo.org/769614 Dmitry noticed that `ptrace(PTRACE_GET_SYSCALL_INFO)` does not work for syscalls called via glibc's syscall() wrapper.

ia64 has two ways to call syscalls from userspace: via `break` and via `eps` instructions.

The difference is in stack layout:

1. `eps` creates simple stack frame: no locals, in{0..7} == out{0..8} 2. `break` uses userspace stack frame: may be locals (glibc provides one), in{0..7} == out{0..8}.

Both work fine in syscall handling cde itself.

But `ptrace(PTRACE_GET_SYSCALL_INFO)` uses unwind mechanism to re-extract syscall arguments but it does not account for locals.

The change always skips locals registers. It should not change `eps` path as kernel's handler already enforces locals=0 and fixes `break`.

Tested on v5.10 on rx3600 machine (ia64 9040 CPU).

Link: https://lkml.kernel.org/r/20210221002554.333076-1-slyfox@gentoo.org Link: https://bugs.gentoo.org/769614 Signed-off-by: Sergei Trofimovich slyfox@gentoo.org Reported-by: Dmitry V. Levin ldv@altlinux.org Cc: Oleg Nesterov oleg@redhat.com Cc: John Paul Adrian Glaubitz glaubitz@physik.fu-berlin.de Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/ia64/kernel/ptrace.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c index 36f660da8124..56007258c014 100644 --- a/arch/ia64/kernel/ptrace.c +++ b/arch/ia64/kernel/ptrace.c @@ -2144,27 +2144,39 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data) { struct syscall_get_set_args *args = data; struct pt_regs *pt = args->regs; - unsigned long *krbs, cfm, ndirty; + unsigned long *krbs, cfm, ndirty, nlocals, nouts; int i, count;

if (unw_unwind_to_user(info) < 0) return;

+ /* + * We get here via a few paths: + * - break instruction: cfm is shared with caller. + * syscall args are in out= regs, locals are non-empty. + * - epsinstruction: cfm is set by br.call + * locals don't exist. + * + * For both cases argguments are reachable in cfm.sof - cfm.sol. + * CFM: [ ... | sor: 17..14 | sol : 13..7 | sof : 6..0 ] + */ cfm = pt->cr_ifs; + nlocals = (cfm >> 7) & 0x7f; /* aka sol */ + nouts = (cfm & 0x7f) - nlocals; /* aka sof - sol */ krbs = (unsigned long *)info->task + IA64_RBS_OFFSET/8; ndirty = ia64_rse_num_regs(krbs, krbs + (pt->loadrs >> 19));

count = 0; if (in_syscall(pt)) - count = min_t(int, args->n, cfm & 0x7f); + count = min_t(int, args->n, nouts);

+ /* Iterate over outs. */ for (i = 0; i < count; i++) { + int j = ndirty + nlocals + i + args->i; if (args->rw) - *ia64_rse_skip_regs(krbs, ndirty + i + args->i) = - args->args[i]; + *ia64_rse_skip_regs(krbs, j) = args->args[i]; else - args->args[i] = *ia64_rse_skip_regs(krbs, - ndirty + i + args->i); + args->args[i] = *ia64_rse_skip_regs(krbs, j); }

if (!args->rw) {

From: Borislav Petkov bp@suse.de

Jim Mattson reported that Debian 9 guests using a 4.9-stable kernel are exploding during alternatives patching:

kernel BUG at /build/linux-dqnRSc/linux-4.9.228/arch/x86/kernel/alternative.c:709! invalid opcode: 0000 [#1] SMP Modules linked in: CPU: 1 PID: 1 Comm: swapper/0 Not tainted 4.9.0-13-amd64 #1 Debian 4.9.228-1 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: swap_entry_free swap_entry_free text_poke_bp swap_entry_free arch_jump_label_transform set_debug_rodata __jump_label_update static_key_slow_inc frontswap_register_ops init_zswap init_frontswap do_one_initcall set_debug_rodata kernel_init_freeable rest_init kernel_init ret_from_fork

triggering the BUG_ON in text_poke() which verifies whether patched instruction bytes have actually landed at the destination.

Further debugging showed that the TLB flush before that check is insufficient because there could be global mappings left in the TLB, leading to a stale mapping getting used.

I say "global mappings" because the hardware configuration is a new one: machine is an AMD, which means, KAISER/PTI doesn't need to be enabled there, which also means there's no user/kernel pagetables split and therefore the TLB can have global mappings.

And the configuration is new one for a second reason: because that AMD machine supports PCID and INVPCID, which leads the CPU detection code to set the synthetic X86_FEATURE_INVPCID_SINGLE flag.

Now, __native_flush_tlb_single() does invalidate global mappings when X86_FEATURE_INVPCID_SINGLE is *not* set and returns.

When X86_FEATURE_INVPCID_SINGLE is set, however, it invalidates the requested address from both PCIDs in the KAISER-enabled case. But if KAISER is not enabled and the machine has global mappings in the TLB, then those global mappings do not get invalidated, which would lead to the above mismatch from using a stale TLB entry.

So make sure to flush those global mappings in the KAISER disabled case.

Co-debugged by Babu Moger babu.moger@amd.com.

Reported-by: Jim Mattson jmattson@google.com Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Hugh Dickins hughd@google.com Reviewed-by: Paolo Bonzini pbonzini@redhat.com Tested-by: Babu Moger babu.moger@amd.com Tested-by: Jim Mattson jmattson@google.com Link: https://lkml.kernel.org/r/CALMp9eRDSW66%2BXvbHVF4ohL7XhThoPoT0BrB0TcS0cgk=dk... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/tlbflush.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index f5ca15622dc9..2bfa4deb8cae 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -245,12 +245,15 @@ static inline void __native_flush_tlb_single(unsigned long addr) * ASID. But, userspace flushes are probably much more * important performance-wise. * - * Make sure to do only a single invpcid when KAISER is - * disabled and we have only a single ASID. + * In the KAISER disabled case, do an INVLPG to make sure + * the mapping is flushed in case it is a global one. */ - if (kaiser_enabled) + if (kaiser_enabled) { invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr); - invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr); + invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr); + } else { + asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); + } }

static inline void __flush_tlb_all(void)

From: Phillip Lougher phillip@squashfs.org.uk

commit 8b44ca2b634527151af07447a8090a5f3a043321 upstream.

The checks for maximum metadata block size is missing SQUASHFS_BLOCK_OFFSET (the two byte length count).

Link: https://lkml.kernel.org/r/2069685113.2081245.1614583677427@webmail.123-reg.c... Fixes: f37aa4c7366e23f ("squashfs: add more sanity checks in id lookup") Signed-off-by: Phillip Lougher phillip@squashfs.org.uk Cc: Sean Nyekjaer sean@geanix.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/squashfs/id.c | 6 ++++-- fs/squashfs/xattr_id.c | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-)

--- a/fs/squashfs/id.c +++ b/fs/squashfs/id.c @@ -110,14 +110,16 @@ __le64 *squashfs_read_id_index_table(str start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]);

- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } }

start = le64_to_cpu(table[indexes - 1]); - if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= id_table_start || (id_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -122,14 +122,16 @@ __le64 *squashfs_read_xattr_id_table(str start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]);

- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } }

start = le64_to_cpu(table[indexes - 1]); - if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= table_start || (table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); }

From: Grygorii Strashko grygorii.strashko@ti.com

[ Upstream commit 7d7275b3e866cf8092bd12553ec53ba26864f7bb ]

The main purpose of l3 IRQs is to catch OCP bus access errors and identify corresponding code places by showing call stack, so it's important to handle L3 interconnect errors as fast as possible. On RT these IRQs will became threaded and will be scheduled much more late from the moment actual error occurred so showing completely useless information.

Hence, mark l3 IRQs as IRQF_NO_THREAD so they will not be forced threaded on RT or if force_irqthreads = true.

Fixes: 0ee7261c9212 ("drivers: bus: Move the OMAP interconnect driver to drivers/bus/") Signed-off-by: Grygorii Strashko grygorii.strashko@ti.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/bus/omap_l3_noc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/omap_l3_noc.c b/drivers/bus/omap_l3_noc.c index 5012e3ad1225..624f74d03a83 100644 --- a/drivers/bus/omap_l3_noc.c +++ b/drivers/bus/omap_l3_noc.c @@ -285,7 +285,7 @@ static int omap_l3_probe(struct platform_device *pdev) */ l3->debug_irq = platform_get_irq(pdev, 0); ret = devm_request_irq(l3->dev, l3->debug_irq, l3_interrupt_handler, - 0x0, "l3-dbg-irq", l3); + IRQF_NO_THREAD, "l3-dbg-irq", l3); if (ret) { dev_err(l3->dev, "request_irq failed for %d\n", l3->debug_irq); @@ -294,7 +294,7 @@ static int omap_l3_probe(struct platform_device *pdev)

l3->app_irq = platform_get_irq(pdev, 1); ret = devm_request_irq(l3->dev, l3->app_irq, l3_interrupt_handler, - 0x0, "l3-app-irq", l3); + IRQF_NO_THREAD, "l3-app-irq", l3); if (ret) dev_err(l3->dev, "request_irq failed for %d\n", l3->app_irq);

From: Florian Fainelli f.fainelli@gmail.com

[ Upstream commit 47142ed6c34d544ae9f0463e58d482289cbe0d46 ]

Similar to commit 92696286f3bb37ba50e4bd8d1beb24afb759a799 ("net: bcmgenet: Set phydev->dev_flags only for internal PHYs") we need to qualify the phydev->dev_flags based on whether the port is connected to an internal or external PHY otherwise we risk having a flags collision with a completely different interpretation depending on the driver.

Fixes: aa9aef77c761 ("net: dsa: bcm_sf2: communicate integrated PHY revision to PHY driver") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/bcm_sf2.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 0c69d5858558..40b3adf7ad99 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -588,8 +588,10 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) * in bits 15:8 and the patch level in bits 7:0 which is exactly what * the REG_PHY_REVISION register layout is. */ - - return priv->hw_params.gphy_rev; + if (priv->int_phy_mask & BIT(port)) + return priv->hw_params.gphy_rev; + else + return 0; }

static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,

From: Dinghao Liu dinghao.liu@zju.edu.cn

[ Upstream commit b52912b8293f2c496f42583e65599aee606a0c18 ]

There is one e1e_wphy() call in e1000_set_d0_lplu_state_82571 that we have caught its return value but lack further handling. Check and terminate the execution flow just like other e1e_wphy() in this function.

Fixes: bc7f75fa9788 ("[E1000E]: New pci-express e1000 driver (currently for ICH9 devices only)") Signed-off-by: Dinghao Liu dinghao.liu@zju.edu.cn Acked-by: Sasha Neftin sasha.neftin@intel.com Tested-by: Dvora Fuxbrumer dvorax.fuxbrumer@linux.intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/e1000e/82571.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 6b03c8553e59..65deaf8f3004 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -917,6 +917,8 @@ static s32 e1000_set_d0_lplu_state_82571(struct e1000_hw *hw, bool active) } else { data &= ~IGP02E1000_PM_D0_LPLU; ret_val = e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, data); + if (ret_val) + return ret_val; /* LPLU and SmartSpeed are mutually exclusive. LPLU is used * during Dx states where the power conservation is most * important. During driver activity we should enable

From: Tong Zhang ztong0001@gmail.com

[ Upstream commit 0429d6d89f97ebff4f17f13f5b5069c66bde8138 ]

There is a UAF in c_can_pci_remove(). dev is released by free_c_can_dev() and is used by pci_iounmap(pdev, priv->base) later. To fix this issue, save the mmio address before releasing dev.

Fixes: 5b92da0443c2 ("c_can_pci: generic module for C_CAN/D_CAN on PCI") Link: https://lore.kernel.org/r/20210301024512.539039-1-ztong0001@gmail.com Signed-off-by: Tong Zhang ztong0001@gmail.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/c_can/c_can_pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c index d065c0e2d18e..f3e0b2124a37 100644 --- a/drivers/net/can/c_can/c_can_pci.c +++ b/drivers/net/can/c_can/c_can_pci.c @@ -239,12 +239,13 @@ static void c_can_pci_remove(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); struct c_can_priv *priv = netdev_priv(dev); + void __iomem *addr = priv->base;

unregister_c_can_dev(dev);

free_c_can_dev(dev);

- pci_iounmap(pdev, priv->base); + pci_iounmap(pdev, addr); pci_disable_msi(pdev); pci_clear_master(pdev); pci_release_regions(pdev);

From: Torin Cooper-Bennun torin@maxiluxsystems.com

[ Upstream commit c0e399f3baf42279f48991554240af8c457535d1 ]

Message loss from RX FIFO 0 is already handled in m_can_handle_lost_msg(), with netdev output included.

Removing this warning also improves driver performance under heavy load, where m_can_do_rx_poll() may be called many times before this interrupt is cleared, causing this message to be output many times (thanks Mariusz Madej for this report).

Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support") Link: https://lore.kernel.org/r/20210303103151.3760532-1-torin@maxiluxsystems.com Reported-by: Mariusz Madej mariusz.madej@xtrack.com Signed-off-by: Torin Cooper-Bennun torin@maxiluxsystems.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/m_can/m_can.c | 3 --- 1 file changed, 3 deletions(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 0bd7e7164796..197c27d8f584 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -428,9 +428,6 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota) }

while ((rxfs & RXFS_FFL_MASK) && (quota > 0)) { - if (rxfs & RXFS_RFL) - netdev_warn(dev, "Rx FIFO 0 Message Lost\n"); - m_can_read_fifo(dev, rxfs);

quota--;

From: Johan Hovold johan@kernel.org

[ Upstream commit c79a707072fe3fea0e3c92edee6ca85c1e53c29f ]

Set the disconnected flag before releasing the data interface in case netdev registration fails to avoid having the disconnect callback try to deregister the never registered netdev (and trigger a WARN_ON()).

Fixes: 87cf65601e17 ("USB host CDC Phonet network interface driver") Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/cdc-phonet.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index ff2270ead2e6..84e0e7f78029 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -406,6 +406,8 @@ static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *i

err = register_netdev(dev); if (err) { + /* Set disconnected flag so that disconnect() returns early. */ + pnd->disconnected = 1; usb_driver_release_interface(&usbpn_driver, data_intf); goto out; }

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

[ Upstream commit c1013ff7a5472db637c56bb6237f8343398c03a7 ]

The upfront allocation of new_bus_id is done to avoid allocating memory under acpi_device_lock, but it doesn't really help, because (1) it leads to many unnecessary memory allocations for _ADR devices, (2) kstrdup_const() is run under that lock anyway and (3) it complicates the code.

Rearrange acpi_device_add() to allocate memory for a new struct acpi_device_bus_id instance only when necessary, eliminate a redundant local variable from it and reduce the number of labels in there.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/scan.c | 57 +++++++++++++++++++++------------------------ 1 file changed, 26 insertions(+), 31 deletions(-)

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 5aa4a01f698f..c1066487c06b 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -622,12 +622,23 @@ void acpi_bus_put_acpi_device(struct acpi_device *adev) put_device(&adev->dev); }

+static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id) +{ + struct acpi_device_bus_id *acpi_device_bus_id; + + /* Find suitable bus_id and instance number in acpi_bus_id_list. */ + list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node) { + if (!strcmp(acpi_device_bus_id->bus_id, dev_id)) + return acpi_device_bus_id; + } + return NULL; +} + int acpi_device_add(struct acpi_device *device, void (*release)(struct device *)) { + struct acpi_device_bus_id *acpi_device_bus_id; int result; - struct acpi_device_bus_id *acpi_device_bus_id, *new_bus_id; - int found = 0;

if (device->handle) { acpi_status status; @@ -653,38 +664,26 @@ int acpi_device_add(struct acpi_device *device, INIT_LIST_HEAD(&device->del_list); mutex_init(&device->physical_node_lock);

- new_bus_id = kzalloc(sizeof(struct acpi_device_bus_id), GFP_KERNEL); - if (!new_bus_id) { - pr_err(PREFIX "Memory allocation error\n"); - result = -ENOMEM; - goto err_detach; - } - mutex_lock(&acpi_device_lock); - /* - * Find suitable bus_id and instance number in acpi_bus_id_list - * If failed, create one and link it into acpi_bus_id_list - */ - list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node) { - if (!strcmp(acpi_device_bus_id->bus_id, - acpi_device_hid(device))) { - acpi_device_bus_id->instance_no++; - found = 1; - kfree(new_bus_id); - break; + + acpi_device_bus_id = acpi_device_bus_id_match(acpi_device_hid(device)); + if (acpi_device_bus_id) { + acpi_device_bus_id->instance_no++; + } else { + acpi_device_bus_id = kzalloc(sizeof(*acpi_device_bus_id), + GFP_KERNEL); + if (!acpi_device_bus_id) { + result = -ENOMEM; + goto err_unlock; } - } - if (!found) { - acpi_device_bus_id = new_bus_id; acpi_device_bus_id->bus_id = kstrdup_const(acpi_device_hid(device), GFP_KERNEL); if (!acpi_device_bus_id->bus_id) { - pr_err(PREFIX "Memory allocation error for bus id\n"); + kfree(acpi_device_bus_id); result = -ENOMEM; - goto err_free_new_bus_id; + goto err_unlock; }

- acpi_device_bus_id->instance_no = 0; list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list); } dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, acpi_device_bus_id->instance_no); @@ -719,13 +718,9 @@ int acpi_device_add(struct acpi_device *device, list_del(&device->node); list_del(&device->wakeup_list);

- err_free_new_bus_id: - if (!found) - kfree(new_bus_id); - + err_unlock: mutex_unlock(&acpi_device_lock);

- err_detach: acpi_detach_data(device->handle, acpi_scan_drop_device); return result; }

From: Adrian Hunter adrian.hunter@intel.com

[ Upstream commit b410ed2a8572d41c68bd9208555610e4b07d0703 ]

The only requirement of an auxtrace queue is that the buffers are in time order. That is achieved by making separate queues for separate perf buffer or AUX area buffer mmaps.

That generally means a separate queue per cpu for per-cpu contexts, and a separate queue per thread for per-task contexts.

When buffers are added to a queue, perf checks that the buffer cpu and thread id (tid) match the queue cpu and thread id.

However, generally, that need not be true, and perf will queue buffers correctly anyway, so the check is not needed.

In addition, the check gets erroneously hit when using sample mode to trace multiple threads.

Consequently, fix that case by removing the check.

Fixes: e502789302a6 ("perf auxtrace: Add helpers for queuing AUX area tracing data") Reported-by: Andi Kleen ak@linux.intel.com Signed-off-by: Adrian Hunter adrian.hunter@intel.com Reviewed-by: Andi Kleen ak@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Link: http://lore.kernel.org/lkml/20210308151143.18338-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/auxtrace.c | 4 ---- 1 file changed, 4 deletions(-)

diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index b87221efdf7e..51fdec9273d7 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -248,10 +248,6 @@ static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues, queue->set = true; queue->tid = buffer->tid; queue->cpu = buffer->cpu; - } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) { - pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n", - queue->cpu, queue->tid, buffer->cpu, buffer->tid); - return -EINVAL; }

buffer->buffer_nr = queues->next_buffer_nr++;

From: Peter Zijlstra peterz@infradead.org

commit 1b367ece0d7e696cab1c8501bab282cc6a538b3f upstream.

Since the futex_q can dissapear the instruction after assigning NULL, this really should be a RELEASE barrier. That stops loads from hitting dead memory too.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104151.604296452@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -1565,8 +1565,7 @@ static void mark_wake_futex(struct wake_ * memory barrier is required here to prevent the following * store to lock_ptr from getting ahead of the plist_del. */ - smp_wmb(); - q->lock_ptr = NULL; + smp_store_release(&q->lock_ptr, NULL); }

/*

From: Peter Zijlstra peterz@infradead.org

commit cfafcd117da0216520568c195cb2f6cd1980c4bb upstream.

By changing futex_lock_pi() to use rt_mutex_*_proxy_lock() all wait_list modifications are done under both hb->lock and wait_lock.

This closes the obvious interleave pattern between futex_lock_pi() and futex_unlock_pi(), but not entirely so. See below:

Before:

futex_lock_pi() futex_unlock_pi() unlock hb->lock

lock hb->lock unlock hb->lock

lock rt_mutex->wait_lock unlock rt_mutex_wait_lock -EAGAIN

lock rt_mutex->wait_lock list_add unlock rt_mutex->wait_lock

schedule()

lock rt_mutex->wait_lock list_del unlock rt_mutex->wait_lock

<idem> -EAGAIN

lock hb->lock

After:

futex_lock_pi() futex_unlock_pi()

lock hb->lock lock rt_mutex->wait_lock list_add unlock rt_mutex->wait_lock unlock hb->lock

schedule() lock hb->lock unlock hb->lock lock hb->lock lock rt_mutex->wait_lock list_del unlock rt_mutex->wait_lock

lock rt_mutex->wait_lock unlock rt_mutex_wait_lock -EAGAIN

unlock hb->lock

It does however solve the earlier starvation/live-lock scenario which got introduced with the -EAGAIN since unlike the before scenario; where the -EAGAIN happens while futex_unlock_pi() doesn't hold any locks; in the after scenario it happens while futex_unlock_pi() actually holds a lock, and then it is serialized on that lock.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104152.062785528@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de [bwh: Backported to 4.9: adjust context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 77 ++++++++++++++++++++++++++++------------ kernel/locking/rtmutex.c | 26 +++---------- kernel/locking/rtmutex_common.h | 1 3 files changed, 62 insertions(+), 42 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -2333,20 +2333,7 @@ queue_unlock(struct futex_hash_bucket *h hb_waiters_dec(hb); }

-/** - * queue_me() - Enqueue the futex_q on the futex_hash_bucket - * @q: The futex_q to enqueue - * @hb: The destination hash bucket - * - * The hb->lock must be held by the caller, and is released here. A call to - * queue_me() is typically paired with exactly one call to unqueue_me(). The - * exceptions involve the PI related operations, which may use unqueue_me_pi() - * or nothing if the unqueue is done as part of the wake process and the unqueue - * state is implicit in the state of woken task (see futex_wait_requeue_pi() for - * an example). - */ -static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) - __releases(&hb->lock) +static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb) { int prio;

@@ -2363,6 +2350,24 @@ static inline void queue_me(struct futex plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); q->task = current; +} + +/** + * queue_me() - Enqueue the futex_q on the futex_hash_bucket + * @q: The futex_q to enqueue + * @hb: The destination hash bucket + * + * The hb->lock must be held by the caller, and is released here. A call to + * queue_me() is typically paired with exactly one call to unqueue_me(). The + * exceptions involve the PI related operations, which may use unqueue_me_pi() + * or nothing if the unqueue is done as part of the wake process and the unqueue + * state is implicit in the state of woken task (see futex_wait_requeue_pi() for + * an example). + */ +static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) + __releases(&hb->lock) +{ + __queue_me(q, hb); spin_unlock(&hb->lock); }

@@ -2868,6 +2873,7 @@ static int futex_lock_pi(u32 __user *uad { struct hrtimer_sleeper timeout, *to = NULL; struct task_struct *exiting = NULL; + struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; struct futex_q q = futex_q_init; int res, ret; @@ -2928,25 +2934,52 @@ retry_private: } }

+ WARN_ON(!q.pi_state); + /* * Only actually queue now that the atomic ops are done: */ - queue_me(&q, hb); + __queue_me(&q, hb);

- WARN_ON(!q.pi_state); - /* - * Block on the PI mutex: - */ - if (!trylock) { - ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to); - } else { + if (trylock) { ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex); /* Fixup the trylock return value: */ ret = ret ? 0 : -EWOULDBLOCK; + goto no_block; }

+ /* + * We must add ourselves to the rt_mutex waitlist while holding hb->lock + * such that the hb and rt_mutex wait lists match. + */ + rt_mutex_init_waiter(&rt_waiter); + ret = rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); + if (ret) { + if (ret == 1) + ret = 0; + + goto no_block; + } + + spin_unlock(q.lock_ptr); + + if (unlikely(to)) + hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS); + + ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter); + spin_lock(q.lock_ptr); /* + * If we failed to acquire the lock (signal/timeout), we must + * first acquire the hb->lock before removing the lock from the + * rt_mutex waitqueue, such that we can keep the hb and rt_mutex + * wait lists consistent. + */ + if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter)) + ret = 0; + +no_block: + /* * Fixup the pi_state owner and possibly acquire the lock if we * haven't already. */ --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1523,19 +1523,6 @@ int __sched rt_mutex_lock_interruptible( EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);

/* - * Futex variant with full deadlock detection. - * Futex variants must not use the fast-path, see __rt_mutex_futex_unlock(). - */ -int __sched rt_mutex_timed_futex_lock(struct rt_mutex *lock, - struct hrtimer_sleeper *timeout) -{ - might_sleep(); - - return rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, - timeout, RT_MUTEX_FULL_CHAINWALK); -} - -/* * Futex variant, must not use fastpath. */ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) @@ -1808,12 +1795,6 @@ int rt_mutex_wait_proxy_lock(struct rt_m /* sleep on the mutex */ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);

- /* - * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might - * have to fix that up. - */ - fixup_rt_mutex_waiters(lock); - raw_spin_unlock_irq(&lock->wait_lock);

return ret; @@ -1853,6 +1834,13 @@ bool rt_mutex_cleanup_proxy_lock(struct fixup_rt_mutex_waiters(lock); cleanup = true; } + + /* + * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might + * have to fix that up. + */ + fixup_rt_mutex_waiters(lock); + raw_spin_unlock_irq(&lock->wait_lock);

return cleanup; --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -112,7 +112,6 @@ extern int rt_mutex_wait_proxy_lock(stru struct rt_mutex_waiter *waiter); extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter); -extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); extern int rt_mutex_futex_trylock(struct rt_mutex *l); extern int __rt_mutex_futex_trylock(struct rt_mutex *l);

From: Thomas Gleixner tglx@linutronix.de

commit 97181f9bd57405b879403763284537e27d46963d upstream.

Alexander reported a hrtimer debug_object splat:

ODEBUG: free active (active state 0) object type: hrtimer hint: hrtimer_wakeup (kernel/time/hrtimer.c:1423)

debug_object_free (lib/debugobjects.c:603) destroy_hrtimer_on_stack (kernel/time/hrtimer.c:427) futex_lock_pi (kernel/futex.c:2740) do_futex (kernel/futex.c:3399) SyS_futex (kernel/futex.c:3447 kernel/futex.c:3415) do_syscall_64 (arch/x86/entry/common.c:284) entry_SYSCALL64_slow_path (arch/x86/entry/entry_64.S:249)

Which was caused by commit:

cfafcd117da0 ("futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()")

... losing the hrtimer_cancel() in the shuffle. Where previously the hrtimer_cancel() was done by rt_mutex_slowlock() we now need to do it manually.

Reported-by: Alexander Levin alexander.levin@verizon.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Fixes: cfafcd117da0 ("futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()") Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1704101802370.2906@nanos Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -3018,8 +3018,10 @@ out_unlock_put_key: out_put_key: put_futex_key(&q.key); out: - if (to) + if (to) { + hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); + } return ret != -EINTR ? ret : -ERESTARTNOINTR;

uaddr_faulted:

From: Thomas Gleixner tglx@linutronix.de

commit 1a1fb985f2e2b85ec0d3dc2e519ee48389ec2434 upstream.

commit 56222b212e8e ("futex: Drop hb->lock before enqueueing on the rtmutex") changed the locking rules in the futex code so that the hash bucket lock is not longer held while the waiter is enqueued into the rtmutex wait list. This made the lock and the unlock path symmetric, but unfortunately the possible early exit from __rt_mutex_proxy_start() due to a detected deadlock was not updated accordingly. That allows a concurrent unlocker to observe inconsitent state which triggers the warning in the unlock path.

futex_lock_pi() futex_unlock_pi() lock(hb->lock) queue(hb_waiter) lock(hb->lock) lock(rtmutex->wait_lock) unlock(hb->lock) // acquired hb->lock hb_waiter = futex_top_waiter() lock(rtmutex->wait_lock) __rt_mutex_proxy_start() ---> fail remove(rtmutex_waiter); ---> returns -EDEADLOCK unlock(rtmutex->wait_lock) // acquired wait_lock wake_futex_pi() rt_mutex_next_owner() --> returns NULL --> WARN

lock(hb->lock) unqueue(hb_waiter)

The problem is caused by the remove(rtmutex_waiter) in the failure case of __rt_mutex_proxy_start() as this lets the unlocker observe a waiter in the hash bucket but no waiter on the rtmutex, i.e. inconsistent state.

The original commit handles this correctly for the other early return cases (timeout, signal) by delaying the removal of the rtmutex waiter until the returning task reacquired the hash bucket lock.

Treat the failure case of __rt_mutex_proxy_start() in the same way and let the existing cleanup code handle the eventual handover of the rtmutex gracefully. The regular rt_mutex_proxy_start() gains the rtmutex waiter removal for the failure case, so that the other callsites are still operating correctly.

Add proper comments to the code so all these details are fully documented.

Thanks to Peter for helping with the analysis and writing the really valuable code comments.

Fixes: 56222b212e8e ("futex: Drop hb->lock before enqueueing on the rtmutex") Reported-by: Heiko Carstens heiko.carstens@de.ibm.com Co-developed-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Heiko Carstens heiko.carstens@de.ibm.com Cc: Martin Schwidefsky schwidefsky@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Stefan Liebler stli@linux.ibm.com Cc: Sebastian Sewior bigeasy@linutronix.de Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1901292311410.1950@nanos.tec.linut... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 28 ++++++++++++++++++---------- kernel/locking/rtmutex.c | 37 ++++++++++++++++++++++++++++++++----- 2 files changed, 50 insertions(+), 15 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -2958,35 +2958,39 @@ retry_private: * and BUG when futex_unlock_pi() interleaves with this. * * Therefore acquire wait_lock while holding hb->lock, but drop the - * latter before calling rt_mutex_start_proxy_lock(). This still fully - * serializes against futex_unlock_pi() as that does the exact same - * lock handoff sequence. + * latter before calling __rt_mutex_start_proxy_lock(). This + * interleaves with futex_unlock_pi() -- which does a similar lock + * handoff -- such that the latter can observe the futex_q::pi_state + * before __rt_mutex_start_proxy_lock() is done. */ raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); spin_unlock(q.lock_ptr); + /* + * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter + * such that futex_unlock_pi() is guaranteed to observe the waiter when + * it sees the futex_q::pi_state. + */ ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);

if (ret) { if (ret == 1) ret = 0; - - spin_lock(q.lock_ptr); - goto no_block; + goto cleanup; }

- if (unlikely(to)) hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);

ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);

+cleanup: spin_lock(q.lock_ptr); /* - * If we failed to acquire the lock (signal/timeout), we must + * If we failed to acquire the lock (deadlock/signal/timeout), we must * first acquire the hb->lock before removing the lock from the - * rt_mutex waitqueue, such that we can keep the hb and rt_mutex - * wait lists consistent. + * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait + * lists consistent. * * In particular; it is important that futex_unlock_pi() can not * observe this inconsistency. @@ -3093,6 +3097,10 @@ retry: * there is no point where we hold neither; and therefore * wake_futex_pi() must observe a state consistent with what we * observed. + * + * In particular; this forces __rt_mutex_start_proxy() to + * complete such that we're guaranteed to observe the + * rt_waiter. Also see the WARN in wake_futex_pi(). */ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1695,12 +1695,33 @@ void rt_mutex_proxy_unlock(struct rt_mut rt_mutex_set_owner(lock, NULL); }

+/** + * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task + * @lock: the rt_mutex to take + * @waiter: the pre-initialized rt_mutex_waiter + * @task: the task to prepare + * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: does _NOT_ remove the @waiter on failure; must either call + * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this. + * + * Returns: + * 0 - task blocked on lock + * 1 - acquired the lock for task, caller should wake it up + * <0 - error + * + * Special API call for PI-futex support. + */ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task) { int ret;

+ lockdep_assert_held(&lock->wait_lock); + if (try_to_take_rt_mutex(lock, task, NULL)) return 1;

@@ -1718,9 +1739,6 @@ int __rt_mutex_start_proxy_lock(struct r ret = 0; }

- if (unlikely(ret)) - remove_waiter(lock, waiter); - debug_rt_mutex_print_deadlock(waiter);

return ret; @@ -1732,12 +1750,18 @@ int __rt_mutex_start_proxy_lock(struct r * @waiter: the pre-initialized rt_mutex_waiter * @task: the task to prepare * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter + * on failure. + * * Returns: * 0 - task blocked on lock * 1 - acquired the lock for task, caller should wake it up * <0 - error * - * Special API call for FUTEX_REQUEUE_PI support. + * Special API call for PI-futex support. */ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, @@ -1747,6 +1771,8 @@ int rt_mutex_start_proxy_lock(struct rt_

raw_spin_lock_irq(&lock->wait_lock); ret = __rt_mutex_start_proxy_lock(lock, waiter, task); + if (unlikely(ret)) + remove_waiter(lock, waiter); raw_spin_unlock_irq(&lock->wait_lock);

return ret; @@ -1814,7 +1840,8 @@ int rt_mutex_wait_proxy_lock(struct rt_m * @lock: the rt_mutex we were woken on * @waiter: the pre-initialized rt_mutex_waiter * - * Attempt to clean up after a failed rt_mutex_wait_proxy_lock(). + * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or + * rt_mutex_wait_proxy_lock(). * * Unless we acquired the lock; we're still enqueued on the wait-list and can * in fact still be granted ownership until we're removed. Therefore we can

From: Will Deacon will.deacon@arm.com

commit 6b4f4bc9cb22875f97023984a625386f0c7cc1c0 upstream.

Some futex() operations, including FUTEX_WAKE_OP, require the kernel to perform an atomic read-modify-write of the futex word via the userspace mapping. These operations are implemented by each architecture in arch_futex_atomic_op_inuser() and futex_atomic_cmpxchg_inatomic(), which are called in atomic context with the relevant hash bucket locks held.

Although these routines may return -EFAULT in response to a page fault generated when accessing userspace, they are expected to succeed (i.e. return 0) in all other cases. This poses a problem for architectures that do not provide bounded forward progress guarantees or fairness of contended atomic operations and can lead to starvation in some cases.

In these problematic scenarios, we must return back to the core futex code so that we can drop the hash bucket locks and reschedule if necessary, much like we do in the case of a page fault.

Allow architectures to return -EAGAIN from their implementations of arch_futex_atomic_op_inuser() and futex_atomic_cmpxchg_inatomic(), which will cause the core futex code to reschedule if necessary and return back to the architecture code later on.

Cc: stable@kernel.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [bwh: Backported to 4.9: adjust context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 185 +++++++++++++++++++++++++++++++++++---------------------- 1 file changed, 115 insertions(+), 70 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -1407,13 +1407,15 @@ static int lookup_pi_state(u32 __user *u

static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) { + int err; u32 uninitialized_var(curval);

if (unlikely(should_fail_futex(true))) return -EFAULT;

- if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))) - return -EFAULT; + err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval); + if (unlikely(err)) + return err;

/* If user space value changed, let the caller retry */ return curval != uval ? -EAGAIN : 0; @@ -1606,10 +1608,8 @@ static int wake_futex_pi(u32 __user *uad if (unlikely(should_fail_futex(true))) ret = -EFAULT;

- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) { - ret = -EFAULT; - - } else if (curval != uval) { + ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval); + if (!ret && (curval != uval)) { /* * If a unconditional UNLOCK_PI operation (user space did not * try the TID->0 transition) raced with a waiter setting the @@ -1795,32 +1795,32 @@ retry_private: double_lock_hb(hb1, hb2); op_ret = futex_atomic_op_inuser(op, uaddr2); if (unlikely(op_ret < 0)) { - double_unlock_hb(hb1, hb2);

-#ifndef CONFIG_MMU - /* - * we don't get EFAULT from MMU faults if we don't have an MMU, - * but we might get them from range checking - */ - ret = op_ret; - goto out_put_keys; -#endif - - if (unlikely(op_ret != -EFAULT)) { + if (!IS_ENABLED(CONFIG_MMU) || + unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) { + /* + * we don't get EFAULT from MMU faults if we don't have + * an MMU, but we might get them from range checking + */ ret = op_ret; goto out_put_keys; }

- ret = fault_in_user_writeable(uaddr2); - if (ret) - goto out_put_keys; + if (op_ret == -EFAULT) { + ret = fault_in_user_writeable(uaddr2); + if (ret) + goto out_put_keys; + }

- if (!(flags & FLAGS_SHARED)) + if (!(flags & FLAGS_SHARED)) { + cond_resched(); goto retry_private; + }

put_futex_key(&key2); put_futex_key(&key1); + cond_resched(); goto retry; }

@@ -2516,14 +2516,17 @@ retry: if (!pi_state->owner) newtid |= FUTEX_OWNER_DIED;

- if (get_futex_value_locked(&uval, uaddr)) - goto handle_fault; + err = get_futex_value_locked(&uval, uaddr); + if (err) + goto handle_err;

for (;;) { newval = (uval & FUTEX_OWNER_DIED) | newtid;

- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) - goto handle_fault; + err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval); + if (err) + goto handle_err; + if (curval == uval) break; uval = curval; @@ -2538,23 +2541,36 @@ retry: return argowner == current;

/* - * To handle the page fault we need to drop the locks here. That gives - * the other task (either the highest priority waiter itself or the - * task which stole the rtmutex) the chance to try the fixup of the - * pi_state. So once we are back from handling the fault we need to - * check the pi_state after reacquiring the locks and before trying to - * do another fixup. When the fixup has been done already we simply - * return. + * In order to reschedule or handle a page fault, we need to drop the + * locks here. In the case of a fault, this gives the other task + * (either the highest priority waiter itself or the task which stole + * the rtmutex) the chance to try the fixup of the pi_state. So once we + * are back from handling the fault we need to check the pi_state after + * reacquiring the locks and before trying to do another fixup. When + * the fixup has been done already we simply return. * * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely * drop hb->lock since the caller owns the hb -> futex_q relation. * Dropping the pi_mutex->wait_lock requires the state revalidate. */ -handle_fault: +handle_err: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(q->lock_ptr);

- err = fault_in_user_writeable(uaddr); + switch (err) { + case -EFAULT: + err = fault_in_user_writeable(uaddr); + break; + + case -EAGAIN: + cond_resched(); + err = 0; + break; + + default: + WARN_ON_ONCE(1); + break; + }

spin_lock(q->lock_ptr); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); @@ -3128,10 +3144,8 @@ retry: * A unconditional UNLOCK_PI op raced against a waiter * setting the FUTEX_WAITERS bit. Try again. */ - if (ret == -EAGAIN) { - put_futex_key(&key); - goto retry; - } + if (ret == -EAGAIN) + goto pi_retry; /* * wake_futex_pi has detected invalid state. Tell user * space. @@ -3146,9 +3160,19 @@ retry: * preserve the WAITERS bit not the OWNER_DIED one. We are the * owner. */ - if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) { + if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) { spin_unlock(&hb->lock); - goto pi_faulted; + switch (ret) { + case -EFAULT: + goto pi_faulted; + + case -EAGAIN: + goto pi_retry; + + default: + WARN_ON_ONCE(1); + goto out_putkey; + } }

/* @@ -3162,6 +3186,11 @@ out_putkey: put_futex_key(&key); return ret;

+pi_retry: + put_futex_key(&key); + cond_resched(); + goto retry; + pi_faulted: put_futex_key(&key);

@@ -3504,6 +3533,7 @@ err_unlock: static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) { u32 uval, uninitialized_var(nval), mval; + int err;

/* Futex address must be 32bit aligned */ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) @@ -3513,42 +3543,57 @@ retry: if (get_user(uval, uaddr)) return -1;

- if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) { - /* - * Ok, this dying thread is truly holding a futex - * of interest. Set the OWNER_DIED bit atomically - * via cmpxchg, and if the value had FUTEX_WAITERS - * set, wake up a waiter (if any). (We have to do a - * futex_wake() even if OWNER_DIED is already set - - * to handle the rare but possible case of recursive - * thread-death.) The rest of the cleanup is done in - * userspace. - */ - mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; - /* - * We are not holding a lock here, but we want to have - * the pagefault_disable/enable() protection because - * we want to handle the fault gracefully. If the - * access fails we try to fault in the futex with R/W - * verification via get_user_pages. get_user() above - * does not guarantee R/W access. If that fails we - * give up and leave the futex locked. - */ - if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) { + if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) + return 0; + + /* + * Ok, this dying thread is truly holding a futex + * of interest. Set the OWNER_DIED bit atomically + * via cmpxchg, and if the value had FUTEX_WAITERS + * set, wake up a waiter (if any). (We have to do a + * futex_wake() even if OWNER_DIED is already set - + * to handle the rare but possible case of recursive + * thread-death.) The rest of the cleanup is done in + * userspace. + */ + mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; + + /* + * We are not holding a lock here, but we want to have + * the pagefault_disable/enable() protection because + * we want to handle the fault gracefully. If the + * access fails we try to fault in the futex with R/W + * verification via get_user_pages. get_user() above + * does not guarantee R/W access. If that fails we + * give up and leave the futex locked. + */ + if ((err = cmpxchg_futex_value_locked(&nval, uaddr, uval, mval))) { + switch (err) { + case -EFAULT: if (fault_in_user_writeable(uaddr)) return -1; goto retry; - } - if (nval != uval) + + case -EAGAIN: + cond_resched(); goto retry;

- /* - * Wake robust non-PI futexes here. The wakeup of - * PI futexes happens in exit_pi_state(): - */ - if (!pi && (uval & FUTEX_WAITERS)) - futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + default: + WARN_ON_ONCE(1); + return err; + } } + + if (nval != uval) + goto retry; + + /* + * Wake robust non-PI futexes here. The wakeup of + * PI futexes happens in exit_pi_state(): + */ + if (!pi && (uval & FUTEX_WAITERS)) + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + return 0; }

From: Yang Tao yang.tao172@zte.com.cn

commit ca16d5bee59807bf04deaab0a8eccecd5061528c upstream.

Robust futexes utilize the robust_list mechanism to allow the kernel to release futexes which are held when a task exits. The exit can be voluntary or caused by a signal or fault. This prevents that waiters block forever.

The futex operations in user space store a pointer to the futex they are either locking or unlocking in the op_pending member of the per task robust list.

After a lock operation has succeeded the futex is queued in the robust list linked list and the op_pending pointer is cleared.

After an unlock operation has succeeded the futex is removed from the robust list linked list and the op_pending pointer is cleared.

The robust list exit code checks for the pending operation and any futex which is queued in the linked list. It carefully checks whether the futex value is the TID of the exiting task. If so, it sets the OWNER_DIED bit and tries to wake up a potential waiter.

This is race free for the lock operation but unlock has two race scenarios where waiters might not be woken up. These issues can be observed with regular robust pthread mutexes. PI aware pthread mutexes are not affected.

(1) Unlocking task is killed after unlocking the futex value in user space before being able to wake a waiter.

pthread_mutex_unlock() | V atomic_exchange_rel (&mutex->__data.__lock, 0) <------------------------killed lll_futex_wake () | | |(__lock = 0) |(enter kernel) | V do_exit() exit_mm() mm_release() exit_robust_list() handle_futex_death() | |(__lock = 0) |(uval = 0) | V if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) return 0;

The sanity check which ensures that the user space futex is owned by the exiting task prevents the wakeup of waiters which in consequence block infinitely.

(2) Waiting task is killed after a wakeup and before it can acquire the futex in user space.

OWNER WAITER futex_wait() pthread_mutex_unlock() | | | |(__lock = 0) | | | V | futex_wake() ------------> wakeup() | |(return to userspace) |(__lock = 0) | V oldval = mutex->__data.__lock <-----------------killed atomic_compare_and_exchange_val_acq (&mutex->__data.__lock, | id | assume_other_futex_waiters, 0) | | | (enter kernel)| | V do_exit() | | V handle_futex_death() | |(__lock = 0) |(uval = 0) | V if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) return 0;

The sanity check which ensures that the user space futex is owned by the exiting task prevents the wakeup of waiters, which seems to be correct as the exiting task does not own the futex value, but the consequence is that other waiters wont be woken up and block infinitely.

In both scenarios the following conditions are true:

- task->robust_list->list_op_pending != NULL - user space futex value == 0 - Regular futex (not PI)

If these conditions are met then it is reasonably safe to wake up a potential waiter in order to prevent the above problems.

As this might be a false positive it can cause spurious wakeups, but the waiter side has to handle other types of unrelated wakeups, e.g. signals gracefully anyway. So such a spurious wakeup will not affect the correctness of these operations.

This workaround must not touch the user space futex value and cannot set the OWNER_DIED bit because the lock value is 0, i.e. uncontended. Setting OWNER_DIED in this case would result in inconsistent state and subsequently in malfunction of the owner died handling in user space.

The rest of the user space state is still consistent as no other task can observe the list_op_pending entry in the exiting tasks robust list.

The eventually woken up waiter will observe the uncontended lock value and take it over.

[ tglx: Massaged changelog and comment. Made the return explicit and not depend on the subsequent check and added constants to hand into handle_futex_death() instead of plain numbers. Fixed a few coding style issues. ]

Fixes: 0771dfefc9e5 ("[PATCH] lightweight robust futexes: core") Signed-off-by: Yang Tao yang.tao172@zte.com.cn Signed-off-by: Yi Wang wang.yi59@zte.com.cn Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Ingo Molnar mingo@kernel.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1573010582-35297-1-git-send-email-wang.yi59@zte.co... Link: https://lkml.kernel.org/r/20191106224555.943191378@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 51 insertions(+), 7 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -3526,11 +3526,16 @@ err_unlock: return ret; }

+/* Constants for the pending_op argument of handle_futex_death */ +#define HANDLE_DEATH_PENDING true +#define HANDLE_DEATH_LIST false + /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ -static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) +static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, + bool pi, bool pending_op) { u32 uval, uninitialized_var(nval), mval; int err; @@ -3543,6 +3548,42 @@ retry: if (get_user(uval, uaddr)) return -1;

+ /* + * Special case for regular (non PI) futexes. The unlock path in + * user space has two race scenarios: + * + * 1. The unlock path releases the user space futex value and + * before it can execute the futex() syscall to wake up + * waiters it is killed. + * + * 2. A woken up waiter is killed before it can acquire the + * futex in user space. + * + * In both cases the TID validation below prevents a wakeup of + * potential waiters which can cause these waiters to block + * forever. + * + * In both cases the following conditions are met: + * + * 1) task->robust_list->list_op_pending != NULL + * @pending_op == true + * 2) User space futex value == 0 + * 3) Regular futex: @pi == false + * + * If these conditions are met, it is safe to attempt waking up a + * potential waiter without touching the user space futex value and + * trying to set the OWNER_DIED bit. The user space futex value is + * uncontended and the rest of the user space mutex state is + * consistent, so a woken waiter will just take over the + * uncontended futex. Setting the OWNER_DIED bit would create + * inconsistent state and malfunction of the user space owner died + * handling. + */ + if (pending_op && !pi && !uval) { + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + return 0; + } + if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) return 0;

@@ -3662,10 +3703,11 @@ static void exit_robust_list(struct task * A pending lock might already be on the list, so * don't process it twice: */ - if (entry != pending) + if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, - curr, pi)) + curr, pi, HANDLE_DEATH_LIST)) return; + } if (rc) return; entry = next_entry; @@ -3679,9 +3721,10 @@ static void exit_robust_list(struct task cond_resched(); }

- if (pending) + if (pending) { handle_futex_death((void __user *)pending + futex_offset, - curr, pip); + curr, pip, HANDLE_DEATH_PENDING); + } }

static void futex_cleanup(struct task_struct *tsk) @@ -3964,7 +4007,8 @@ void compat_exit_robust_list(struct task if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset);

- if (handle_futex_death(uaddr, curr, pi)) + if (handle_futex_death(uaddr, curr, pi, + HANDLE_DEATH_LIST)) return; } if (rc) @@ -3983,7 +4027,7 @@ void compat_exit_robust_list(struct task if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset);

- handle_futex_death(uaddr, curr, pip); + handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } }

From: Mike Galbraith efault@gmx.de

commit 9f5d1c336a10c0d24e83e40b4c1b9539f7dba627 upstream.

Gratian managed to trigger the BUG_ON(!newowner) in fixup_pi_state_owner(). This is one possible chain of events leading to this:

Task Prio Operation T1 120 lock(F) T2 120 lock(F) -> blocks (top waiter) T3 50 (RT) lock(F) -> boosts T1 and blocks (new top waiter) XX timeout/ -> wakes T2 signal T1 50 unlock(F) -> wakes T3 (rtmutex->owner == NULL, waiter bit is set) T2 120 cleanup -> try_to_take_mutex() fails because T3 is the top waiter and the lower priority T2 cannot steal the lock. -> fixup_pi_state_owner() sees newowner == NULL -> BUG_ON()

The comment states that this is invalid and rt_mutex_real_owner() must return a non NULL owner when the trylock failed, but in case of a queued and woken up waiter rt_mutex_real_owner() == NULL is a valid transient state. The higher priority waiter has simply not yet managed to take over the rtmutex.

The BUG_ON() is therefore wrong and this is just another retry condition in fixup_pi_state_owner().

Drop the locks, so that T3 can make progress, and then try the fixup again.

Gratian provided a great analysis, traces and a reproducer. The analysis is to the point, but it confused the hell out of that tglx dude who had to page in all the futex horrors again. Condensed version is above.

[ tglx: Wrote comment and changelog ]

Fixes: c1e2f0eaf015 ("futex: Avoid violating the 10th rule of futex") Reported-by: Gratian Crisan gratian.crisan@ni.com Signed-off-by: Mike Galbraith efault@gmx.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87a6w6x7bb.fsf@ni.com Link: https://lore.kernel.org/r/87sg9pkvf7.fsf@nanos.tec.linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -2497,10 +2497,22 @@ retry: }

/* - * Since we just failed the trylock; there must be an owner. + * The trylock just failed, so either there is an owner or + * there is a higher priority waiter than this one. */ newowner = rt_mutex_owner(&pi_state->pi_mutex); - BUG_ON(!newowner); + /* + * If the higher priority waiter has not yet taken over the + * rtmutex then newowner is NULL. We can't return here with + * that state because it's inconsistent vs. the user space + * state. So drop the locks and try again. It's a valid + * situation and not any different from the other retry + * conditions. + */ + if (unlikely(!newowner)) { + err = -EAGAIN; + goto handle_err; + } } else { WARN_ON_ONCE(argowner != current); if (oldowner == current) {

From: Eric Dumazet edumazet@google.com

commit e323d865b36134e8c5c82c834df89109a5c60dab upstream.

iproute2 package is well behaved, but malicious user space can provide illegal shift values and trigger UBSAN reports.

Add stab parameter to red_check_params() to validate user input.

syzbot reported:

UBSAN: shift-out-of-bounds in ./include/net/red.h:312:18 shift exponent 111 is too large for 64-bit type 'long unsigned int' CPU: 1 PID: 14662 Comm: syz-executor.3 Not tainted 5.12.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x141/0x1d7 lib/dump_stack.c:120 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:327 red_calc_qavg_from_idle_time include/net/red.h:312 [inline] red_calc_qavg include/net/red.h:353 [inline] choke_enqueue.cold+0x18/0x3dd net/sched/sch_choke.c:221 __dev_xmit_skb net/core/dev.c:3837 [inline] __dev_queue_xmit+0x1943/0x2e00 net/core/dev.c:4150 neigh_hh_output include/net/neighbour.h:499 [inline] neigh_output include/net/neighbour.h:508 [inline] ip6_finish_output2+0x911/0x1700 net/ipv6/ip6_output.c:117 __ip6_finish_output net/ipv6/ip6_output.c:182 [inline] __ip6_finish_output+0x4c1/0xe10 net/ipv6/ip6_output.c:161 ip6_finish_output+0x35/0x200 net/ipv6/ip6_output.c:192 NF_HOOK_COND include/linux/netfilter.h:290 [inline] ip6_output+0x1e4/0x530 net/ipv6/ip6_output.c:215 dst_output include/net/dst.h:448 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] NF_HOOK include/linux/netfilter.h:295 [inline] ip6_xmit+0x127e/0x1eb0 net/ipv6/ip6_output.c:320 inet6_csk_xmit+0x358/0x630 net/ipv6/inet6_connection_sock.c:135 dccp_transmit_skb+0x973/0x12c0 net/dccp/output.c:138 dccp_send_reset+0x21b/0x2b0 net/dccp/output.c:535 dccp_finish_passive_close net/dccp/proto.c:123 [inline] dccp_finish_passive_close+0xed/0x140 net/dccp/proto.c:118 dccp_terminate_connection net/dccp/proto.c:958 [inline] dccp_close+0xb3c/0xe60 net/dccp/proto.c:1028 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 inet6_release+0x4c/0x70 net/ipv6/af_inet6.c:478 __sock_release+0xcd/0x280 net/socket.c:599 sock_close+0x18/0x20 net/socket.c:1258 __fput+0x288/0x920 fs/file_table.c:280 task_work_run+0xdd/0x1a0 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline]

Fixes: 8afa10cbe281 ("net_sched: red: Avoid illegal values") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/red.h | 10 +++++++++- net/sched/sch_choke.c | 7 ++++--- net/sched/sch_gred.c | 2 +- net/sched/sch_red.c | 7 +++++-- net/sched/sch_sfq.c | 2 +- 5 files changed, 20 insertions(+), 8 deletions(-)

--- a/include/net/red.h +++ b/include/net/red.h @@ -167,7 +167,8 @@ static inline void red_set_vars(struct r v->qcount = -1; }

-static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log) +static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, + u8 Scell_log, u8 *stab) { if (fls(qth_min) + Wlog > 32) return false; @@ -177,6 +178,13 @@ static inline bool red_check_params(u32 return false; if (qth_max < qth_min) return false; + if (stab) { + int i; + + for (i = 0; i < RED_STAB_SIZE; i++) + if (stab[i] >= 32) + return false; + } return true; }

--- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -409,6 +409,7 @@ static int choke_change(struct Qdisc *sc struct sk_buff **old = NULL; unsigned int mask; u32 max_P; + u8 *stab;

if (opt == NULL) return -EINVAL; @@ -424,8 +425,8 @@ static int choke_change(struct Qdisc *sc max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0;

ctl = nla_data(tb[TCA_CHOKE_PARMS]); - - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) + stab = nla_data(tb[TCA_CHOKE_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL;

if (ctl->limit > CHOKE_MAX_QUEUE) @@ -478,7 +479,7 @@ static int choke_change(struct Qdisc *sc

red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_CHOKE_STAB]), + stab, max_P); red_set_vars(&q->vars);

--- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -356,7 +356,7 @@ static inline int gred_change_vq(struct struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp];

- if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL;

if (!q) { --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -169,6 +169,7 @@ static int red_change(struct Qdisc *sch, struct Qdisc *child = NULL; int err; u32 max_P; + u8 *stab;

if (opt == NULL) return -EINVAL; @@ -184,7 +185,9 @@ static int red_change(struct Qdisc *sch, max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0;

ctl = nla_data(tb[TCA_RED_PARMS]); - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) + stab = nla_data(tb[TCA_RED_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, + ctl->Scell_log, stab)) return -EINVAL;

if (ctl->limit > 0) { @@ -206,7 +209,7 @@ static int red_change(struct Qdisc *sch, red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_RED_STAB]), + stab, max_P); red_set_vars(&q->vars);

--- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -645,7 +645,7 @@ static int sfq_change(struct Qdisc *sch, }

if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, - ctl_v1->Wlog, ctl_v1->Scell_log)) + ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) return -EINVAL; if (ctl_v1 && ctl_v1->qth_min) { p = kmalloc(sizeof(*p), GFP_KERNEL);

From: Markus Theil markus.theil@tu-ilmenau.de

commit 3bd801b14e0c5d29eeddc7336558beb3344efaa3 upstream.

Clear beacon ie pointer and ie length after free in order to prevent double free.

================================================================== BUG: KASAN: double-free or invalid-free \ in ieee80211_ibss_leave+0x83/0xe0 net/mac80211/ibss.c:1876

CPU: 0 PID: 8472 Comm: syz-executor100 Not tainted 5.11.0-rc6-syzkaller #0 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x107/0x163 lib/dump_stack.c:120 print_address_description.constprop.0.cold+0x5b/0x2c6 mm/kasan/report.c:230 kasan_report_invalid_free+0x51/0x80 mm/kasan/report.c:355 ____kasan_slab_free+0xcc/0xe0 mm/kasan/common.c:341 kasan_slab_free include/linux/kasan.h:192 [inline] __cache_free mm/slab.c:3424 [inline] kfree+0xed/0x270 mm/slab.c:3760 ieee80211_ibss_leave+0x83/0xe0 net/mac80211/ibss.c:1876 rdev_leave_ibss net/wireless/rdev-ops.h:545 [inline] __cfg80211_leave_ibss+0x19a/0x4c0 net/wireless/ibss.c:212 __cfg80211_leave+0x327/0x430 net/wireless/core.c:1172 cfg80211_leave net/wireless/core.c:1221 [inline] cfg80211_netdev_notifier_call+0x9e8/0x12c0 net/wireless/core.c:1335 notifier_call_chain+0xb5/0x200 kernel/notifier.c:83 call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:2040 call_netdevice_notifiers_extack net/core/dev.c:2052 [inline] call_netdevice_notifiers net/core/dev.c:2066 [inline] __dev_close_many+0xee/0x2e0 net/core/dev.c:1586 __dev_close net/core/dev.c:1624 [inline] __dev_change_flags+0x2cb/0x730 net/core/dev.c:8476 dev_change_flags+0x8a/0x160 net/core/dev.c:8549 dev_ifsioc+0x210/0xa70 net/core/dev_ioctl.c:265 dev_ioctl+0x1b1/0xc40 net/core/dev_ioctl.c:511 sock_do_ioctl+0x148/0x2d0 net/socket.c:1060 sock_ioctl+0x477/0x6a0 net/socket.c:1177 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __x64_sys_ioctl+0x193/0x200 fs/ioctl.c:739 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported-by: syzbot+93976391bf299d425f44@syzkaller.appspotmail.com Signed-off-by: Markus Theil markus.theil@tu-ilmenau.de Link: https://lore.kernel.org/r/20210213133653.367130-1-markus.theil@tu-ilmenau.de Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mac80211/ibss.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1862,6 +1862,8 @@ int ieee80211_ibss_leave(struct ieee8021

/* remove beacon */ kfree(sdata->u.ibss.ie); + sdata->u.ibss.ie = NULL; + sdata->u.ibss.ie_len = 0;

/* on the next join, re-program HT parameters */ memset(&ifibss->ht_capa, 0, sizeof(ifibss->ht_capa));