From: David Collins collinsd@codeaurora.org

[ Upstream commit eaa7995c529b54d68d97a30f6344cc6ca2f214a7 ]

The final step in regulator_register() is to call regulator_resolve_supply() for each registered regulator (including the one in the process of being registered). The regulator_resolve_supply() function first checks if rdev->supply is NULL, then it performs various steps to try to find the supply. If successful, rdev->supply is set inside of set_supply().

This procedure can encounter a race condition if two concurrent tasks call regulator_register() near to each other on separate CPUs and one of the regulators has rdev->supply_name specified. There is currently nothing guaranteeing atomicity between the rdev->supply check and set steps. Thus, both tasks can observe rdev->supply==NULL in their regulator_resolve_supply() calls. This then results in both creating a struct regulator for the supply. One ends up actually stored in rdev->supply and the other is lost (though still present in the supply's consumer_list).

Here is a kernel log snippet showing the issue:

[ 12.421768] gpu_cc_gx_gdsc: supplied by pm8350_s5_level [ 12.425854] gpu_cc_gx_gdsc: supplied by pm8350_s5_level [ 12.429064] debugfs: Directory 'regulator.4-SUPPLY' with parent '17a00000.rsc:rpmh-regulator-gfxlvl-pm8350_s5_level' already present!

Avoid this race condition by holding the rdev->mutex lock inside of regulator_resolve_supply() while checking and setting rdev->supply.

Signed-off-by: David Collins collinsd@codeaurora.org Link: https://lore.kernel.org/r/1610068562-4410-1-git-send-email-collinsd@codeauro... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/core.c | 39 ++++++++++++++++++++++++++++----------- 1 file changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 8a6ca06d9c160..fa8f5fc04d8fd 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1567,23 +1567,34 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) { struct regulator_dev *r; struct device *dev = rdev->dev.parent; - int ret; + int ret = 0;

/* No supply to resovle? */ if (!rdev->supply_name) return 0;

- /* Supply already resolved? */ + /* Supply already resolved? (fast-path without locking contention) */ if (rdev->supply) return 0;

+ /* + * Recheck rdev->supply with rdev->mutex lock held to avoid a race + * between rdev->supply null check and setting rdev->supply in + * set_supply() from concurrent tasks. + */ + regulator_lock(rdev); + + /* Supply just resolved by a concurrent task? */ + if (rdev->supply) + goto out; + r = regulator_dev_lookup(dev, rdev->supply_name); if (IS_ERR(r)) { ret = PTR_ERR(r);

/* Did the lookup explicitly defer for us? */ if (ret == -EPROBE_DEFER) - return ret; + goto out;

if (have_full_constraints()) { r = dummy_regulator_rdev; @@ -1591,15 +1602,18 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) } else { dev_err(dev, "Failed to resolve %s-supply for %s\n", rdev->supply_name, rdev->desc->name); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto out; } }

if (r == rdev) { dev_err(dev, "Supply for %s (%s) resolved to itself\n", rdev->desc->name, rdev->supply_name); - if (!have_full_constraints()) - return -EINVAL; + if (!have_full_constraints()) { + ret = -EINVAL; + goto out; + } r = dummy_regulator_rdev; get_device(&r->dev); } @@ -1613,7 +1627,8 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) if (r->dev.parent && r->dev.parent != rdev->dev.parent) { if (!device_is_bound(r->dev.parent)) { put_device(&r->dev); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto out; } }

@@ -1621,13 +1636,13 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) ret = regulator_resolve_supply(r); if (ret < 0) { put_device(&r->dev); - return ret; + goto out; }

ret = set_supply(rdev, r); if (ret < 0) { put_device(&r->dev); - return ret; + goto out; }

/* Cascade always-on state to supply */ @@ -1636,11 +1651,13 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) if (ret < 0) { _regulator_put(rdev->supply); rdev->supply = NULL; - return ret; + goto out; } }

- return 0; +out: + regulator_unlock(rdev); + return ret; }

/* Internal regulator request function */

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit 08bd8dbe88825760e953759d7ec212903a026c75 ]

If the server returns a new stateid that does not match the one in our cache, then try to return the one we hold instead of just invalidating it on the client side. This ensures that both client and server will agree that the stateid is invalid.

Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/pnfs.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 46ca5592b8b0d..2c43583e2aa1c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2301,7 +2301,13 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) * We got an entirely new state ID. Mark all segments for the * inode invalid, and retry the layoutget */ - pnfs_mark_layout_stateid_invalid(lo, &free_me); + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .length = NFS4_MAX_UINT64, + }; + pnfs_set_plh_return_info(lo, IOMODE_ANY, 0); + pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + &range, 0); goto out_forget; }

From: Emmanuel Grumbach emmanuel.grumbach@intel.com

[ Upstream commit 98c7d21f957b10d9c07a3a60a3a5a8f326a197e5 ]

I hit a NULL pointer exception in this function when the init flow went really bad.

Signed-off-by: Emmanuel Grumbach emmanuel.grumbach@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/iwlwifi.20210115130252.2e8da9f2c132.I0234d4b8ddaf7... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index b73582ec03a08..b1a71539ca3e5 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -631,6 +631,11 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id) struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct iwl_txq *txq = trans_pcie->txq[txq_id];

+ if (!txq) { + IWL_ERR(trans, "Trying to free a queue that wasn't allocated?\n"); + return; + } + spin_lock_bh(&txq->lock); while (txq->write_ptr != txq->read_ptr) { IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n",

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 7a21b1d4a728a483f07c638ccd8610d4b4f12684 ]

If we get into a problem severe enough to attempt a reprobe, we schedule a worker to do that. However, if the problem gets more severe and the device is actually destroyed before this worker has a chance to run, we use a free device. Bump up the reference count of the device until the worker runs to avoid this situation.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/iwlwifi.20210122144849.871f0892e4b2.I94819e11afd68... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 0e26619fb330b..d932171617e6a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -1192,6 +1192,7 @@ static void iwl_mvm_reprobe_wk(struct work_struct *wk) reprobe = container_of(wk, struct iwl_mvm_reprobe, work); if (device_reprobe(reprobe->dev)) dev_err(reprobe->dev, "reprobe failed!\n"); + put_device(reprobe->dev); kfree(reprobe); module_put(THIS_MODULE); } @@ -1242,7 +1243,7 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error) module_put(THIS_MODULE); return; } - reprobe->dev = mvm->trans->dev; + reprobe->dev = get_device(mvm->trans->dev); INIT_WORK(&reprobe->work, iwl_mvm_reprobe_wk); schedule_work(&reprobe->work); } else if (mvm->fwrt.cur_fw_img == IWL_UCODE_REGULAR &&

From: Dave Wysochanski dwysocha@redhat.com

[ Upstream commit e4a7d1f7707eb44fd953a31dd59eff82009d879c ]

When handling an auth_gss downcall, it's possible to get 0-length opaque object for the acceptor. In the case of a 0-length XDR object, make sure simple_get_netobj() fills in dest->data = NULL, and does not continue to kmemdup() which will set dest->data = ZERO_SIZE_PTR for the acceptor.

The trace event code can handle NULL but not ZERO_SIZE_PTR for a string, and so without this patch the rpcgss_context trace event will crash the kernel as follows:

[ 162.887992] BUG: kernel NULL pointer dereference, address: 0000000000000010 [ 162.898693] #PF: supervisor read access in kernel mode [ 162.900830] #PF: error_code(0x0000) - not-present page [ 162.902940] PGD 0 P4D 0 [ 162.904027] Oops: 0000 [#1] SMP PTI [ 162.905493] CPU: 4 PID: 4321 Comm: rpc.gssd Kdump: loaded Not tainted 5.10.0 #133 [ 162.908548] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [ 162.910978] RIP: 0010:strlen+0x0/0x20 [ 162.912505] Code: 48 89 f9 74 09 48 83 c1 01 80 39 00 75 f7 31 d2 44 0f b6 04 16 44 88 04 11 48 83 c2 01 45 84 c0 75 ee c3 0f 1f 80 00 00 00 00 <80> 3f 00 74 10 48 89 f8 48 83 c0 01 80 38 00 75 f7 48 29 f8 c3 31 [ 162.920101] RSP: 0018:ffffaec900c77d90 EFLAGS: 00010202 [ 162.922263] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000000fffde697 [ 162.925158] RDX: 000000000000002f RSI: 0000000000000080 RDI: 0000000000000010 [ 162.928073] RBP: 0000000000000010 R08: 0000000000000e10 R09: 0000000000000000 [ 162.930976] R10: ffff8e698a590cb8 R11: 0000000000000001 R12: 0000000000000e10 [ 162.933883] R13: 00000000fffde697 R14: 000000010034d517 R15: 0000000000070028 [ 162.936777] FS: 00007f1e1eb93700(0000) GS:ffff8e6ab7d00000(0000) knlGS:0000000000000000 [ 162.940067] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 162.942417] CR2: 0000000000000010 CR3: 0000000104eba000 CR4: 00000000000406e0 [ 162.945300] Call Trace: [ 162.946428] trace_event_raw_event_rpcgss_context+0x84/0x140 [auth_rpcgss] [ 162.949308] ? __kmalloc_track_caller+0x35/0x5a0 [ 162.951224] ? gss_pipe_downcall+0x3a3/0x6a0 [auth_rpcgss] [ 162.953484] gss_pipe_downcall+0x585/0x6a0 [auth_rpcgss] [ 162.955953] rpc_pipe_write+0x58/0x70 [sunrpc] [ 162.957849] vfs_write+0xcb/0x2c0 [ 162.959264] ksys_write+0x68/0xe0 [ 162.960706] do_syscall_64+0x33/0x40 [ 162.962238] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 162.964346] RIP: 0033:0x7f1e1f1e57df

Signed-off-by: Dave Wysochanski dwysocha@redhat.com Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sunrpc/auth_gss/auth_gss_internal.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h index c5603242b54bf..f6d9631bd9d00 100644 --- a/net/sunrpc/auth_gss/auth_gss_internal.h +++ b/net/sunrpc/auth_gss/auth_gss_internal.h @@ -34,9 +34,12 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) q = (const void *)((const char *)p + len); if (unlikely(q > end || q < p)) return ERR_PTR(-EFAULT); - dest->data = kmemdup(p, len, GFP_NOFS); - if (unlikely(dest->data == NULL)) - return ERR_PTR(-ENOMEM); + if (len) { + dest->data = kmemdup(p, len, GFP_NOFS); + if (unlikely(dest->data == NULL)) + return ERR_PTR(-ENOMEM); + } else + dest->data = NULL; dest->len = len; return q; }