Skip to contentSkip to conversation

5.10.16-rc1 review

PATCH In review Greg Kroah-Hartman 7 participants 68 messages Feb 11, 2021 – Feb 17, 2021 Stable branch

lore
Share & tools
lore
author maintainer
#10 lore raw

PATCH 10/54 io_uring: replace inflight_wait with tctx->wait

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit c98de08c990e190fc7cc3aaf8079b4a0674c6425 ]

As tasks now cancel only theirs requests, and inflight_wait is awaited only in io_uring_cancel_files(), which should be called with ->in_idle set, instead of keeping a separate inflight_wait use tctx->wait.

That will add some spurious wakeups but actually is safer from point of not hanging the task.

e.g.

task1                   | IRQ
                        | *start* io_complete_rw_common(link)
                        |        link: req1 -> req2 -> req3(with files)
*cancel_files()         |
io_wq_cancel(), etc.    |
                        | put_req(link), adds to io-wq req2
schedule()              |

So, task1 will never try to cancel req2 or req3. If req2 is long-standing (e.g. read(empty_pipe)), this may hang.

---
 fs/io_uring.c |   13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)
fs/io_uring.c +6 -7
@@ -286,7 +286,6 @@ struct io_ring_ctx {
 		struct list_head	timeout_list;
 		struct list_head	cq_overflow_list;
 
-		wait_queue_head_t	inflight_wait;
 		struct io_uring_sqe	*sq_sqes;
 	} ____cacheline_aligned_in_smp;
 
@@ -1220,7 +1219,6 @@ static struct io_ring_ctx *io_ring_ctx_a
 	INIT_LIST_HEAD(&ctx->iopoll_list);
 	INIT_LIST_HEAD(&ctx->defer_list);
 	INIT_LIST_HEAD(&ctx->timeout_list);
-	init_waitqueue_head(&ctx->inflight_wait);
 	spin_lock_init(&ctx->inflight_lock);
 	INIT_LIST_HEAD(&ctx->inflight_list);
 	INIT_DELAYED_WORK(&ctx->file_put_work, io_file_put_work);
@@ -5894,6 +5892,7 @@ static int io_req_defer(struct io_kiocb
 static void io_req_drop_files(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_uring_task *tctx = req->task->io_uring;
 	unsigned long flags;
 
 	if (req->work.flags & IO_WQ_WORK_FILES) {
@@ -5905,8 +5904,8 @@ static void io_req_drop_files(struct io_
 	spin_unlock_irqrestore(&ctx->inflight_lock, flags);
 	req->flags &= ~REQ_F_INFLIGHT;
 	req->work.flags &= ~IO_WQ_WORK_FILES;
-	if (waitqueue_active(&ctx->inflight_wait))
-		wake_up(&ctx->inflight_wait);
+	if (atomic_read(&tctx->in_idle))
+		wake_up(&tctx->wait);
 }
 
 static void __io_clean_op(struct io_kiocb *req)
@@ -8605,8 +8604,8 @@ static void io_uring_cancel_files(struct
 			break;
 		}
 		if (found)
-			prepare_to_wait(&ctx->inflight_wait, &wait,
-						TASK_UNINTERRUPTIBLE);
+			prepare_to_wait(&task->io_uring->wait, &wait,
+					TASK_UNINTERRUPTIBLE);
 		spin_unlock_irq(&ctx->inflight_lock);
 
 		/* We need to keep going until we don't find a matching req */
@@ -8619,7 +8618,7 @@ static void io_uring_cancel_files(struct
 		/* cancellations _may_ trigger task work */
 		io_run_task_work();
 		schedule();
-		finish_wait(&ctx->inflight_wait, &wait);
+		finish_wait(&task->io_uring->wait, &wait);
 	}
 }
 
author maintainer
#20 lore raw

PATCH 20/54 regulator: core: avoid regulator_resolve_supply() race condition

In reply to Greg Kroah-Hartman

From: David Collins <[email protected]>

[ 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.

---
 drivers/regulator/core.c | 39 ++++++++++++++++++++++++++++-----------
 1 file changed, 28 insertions(+), 11 deletions(-)
drivers/regulator/core.c +28 -11
index 42bbd99a36acf..2c31f04ff950f 100644
@@ -1813,23 +1813,34 @@ 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 resolve? */
 	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;
@@ -1837,15 +1848,18 @@ 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);
 	}
@@ -1859,7 +1873,8 @@ 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;
 		}
 	}
 
@@ -1867,13 +1882,13 @@ 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;
 	}
 
 	/*
@@ -1886,11 +1901,13 @@ 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 */
Signature · 1 line
2.27.0
author maintainer
#18 lore raw

PATCH 18/54 powerpc/64/signal: Fix regression in __kernel_sigtramp_rt64() semantics

In reply to Greg Kroah-Hartman

From: Raoni Fassina Firmino <[email protected]>

commit 24321ac668e452a4942598533d267805f291fdc9 upstream.

Commit 0138ba5783ae ("powerpc/64/signal: Balance return predictor stack in signal trampoline") changed __kernel_sigtramp_rt64() VDSO and trampoline code, and introduced a regression in the way glibc's backtrace()[1] detects the signal-handler stack frame. Apart from the practical implications, __kernel_sigtramp_rt64() was a VDSO function with the semantics that it is a function you can call from userspace to end a signal handling. Now this semantics are no longer valid.

I believe the aforementioned change affects all releases since 5.9.

This patch tries to fix both the semantics and practical aspect of __kernel_sigtramp_rt64() returning it to the previous code, whilst keeping the intended behaviour of 0138ba5783ae by adding a new symbol to serve as the jump target from the kernel to the trampoline. Now the trampoline has two parts, a new entry point and the old return point.

[1] https://lists.ozlabs.org/pipermail/linuxppc-dev/2021-January/223194.html

Fixes 0138ba5783ae ("powerpc/64/signal: Balance return predictor stack in signal trampoline")
[mpe: Minor tweaks to change log formatting, add stable tag]
---
 arch/powerpc/kernel/vdso.c              |    2 +-
 arch/powerpc/kernel/vdso64/sigtramp.S   |   11 ++++++++++-
 arch/powerpc/kernel/vdso64/vdso64.lds.S |    1 +
 3 files changed, 12 insertions(+), 2 deletions(-)
arch/powerpc/kernel/vdso.c +1 -1
@@ -475,7 +475,7 @@ static __init void vdso_setup_trampoline
 	 */
 
 #ifdef CONFIG_PPC64
-	vdso64_rt_sigtramp = find_function64(v64, "__kernel_sigtramp_rt64");
+	vdso64_rt_sigtramp = find_function64(v64, "__kernel_start_sigtramp_rt64");
 #endif
 	vdso32_sigtramp	   = find_function32(v32, "__kernel_sigtramp32");
 	vdso32_rt_sigtramp = find_function32(v32, "__kernel_sigtramp_rt32");
arch/powerpc/kernel/vdso64/sigtramp.S +10 -1
@@ -15,11 +15,20 @@
 
 	.text
 
+/*
+ * __kernel_start_sigtramp_rt64 and __kernel_sigtramp_rt64 together
+ * are one function split in two parts. The kernel jumps to the former
+ * and the signal handler indirectly (by blr) returns to the latter.
+ * __kernel_sigtramp_rt64 needs to point to the return address so
+ * glibc can correctly identify the trampoline stack frame.
+ */
 	.balign 8
 	.balign IFETCH_ALIGN_BYTES
-V_FUNCTION_BEGIN(__kernel_sigtramp_rt64)
+V_FUNCTION_BEGIN(__kernel_start_sigtramp_rt64)
 .Lsigrt_start:
 	bctrl	/* call the handler */
+V_FUNCTION_END(__kernel_start_sigtramp_rt64)
+V_FUNCTION_BEGIN(__kernel_sigtramp_rt64)
 	addi	r1, r1, __SIGNAL_FRAMESIZE
 	li	r0,__NR_rt_sigreturn
 	sc
arch/powerpc/kernel/vdso64/vdso64.lds.S +1 -0
@@ -150,6 +150,7 @@ VERSION
 		__kernel_get_tbfreq;
 		__kernel_sync_dicache;
 		__kernel_sync_dicache_p5;
+		__kernel_start_sigtramp_rt64;
 		__kernel_sigtramp_rt64;
 		__kernel_getcpu;
 		__kernel_time;
author maintainer
#5 lore raw

PATCH 5/54 io_uring: always batch cancel in *cancel_files()

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit f6edbabb8359798c541b0776616c5eab3a840d3d ]

Instead of iterating over each request and cancelling it individually in io_uring_cancel_files(), try to cancel all matching requests and use ->inflight_list only to check if there anything left.

In many cases it should be faster, and we can reuse a lot of code from task cancellation.

---
 fs/io-wq.c    |   10 ----
 fs/io-wq.h    |    1 
 fs/io_uring.c |  139 ++++++++--------------------------------------------------
 3 files changed, 20 insertions(+), 130 deletions(-)
fs/io-wq.c +0 -10
@@ -1078,16 +1078,6 @@ enum io_wq_cancel io_wq_cancel_cb(struct
 	return IO_WQ_CANCEL_NOTFOUND;
 }
 
-static bool io_wq_io_cb_cancel_data(struct io_wq_work *work, void *data)
-{
-	return work == data;
-}
-
-enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
-{
-	return io_wq_cancel_cb(wq, io_wq_io_cb_cancel_data, (void *)cwork, false);
-}
-
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 {
 	int ret = -ENOMEM, node;
fs/io-wq.h +0 -1
@@ -130,7 +130,6 @@ static inline bool io_wq_is_hashed(struc
 }
 
 void io_wq_cancel_all(struct io_wq *wq);
-enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
 
 typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
 
fs/io_uring.c +20 -119

202 lines not on this page · raw message

author maintainer
#40 lore raw

PATCH 40/54 SUNRPC: Handle 0 length opaque XDR object data properly

In reply to Greg Kroah-Hartman

From: Dave Wysochanski <[email protected]>

[ 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
---
 net/sunrpc/auth_gss/auth_gss_internal.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
net/sunrpc/auth_gss/auth_gss_internal.h +6 -3
index c5603242b54bf..f6d9631bd9d00 100644
@@ -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;
 }
Signature · 1 line
2.27.0
author maintainer
#44 lore raw

PATCH 44/54 bpf: Fix verifier jmp32 pruning decision logic

In reply to Greg Kroah-Hartman

From: Daniel Borkmann <[email protected]>

commit fd675184fc7abfd1e1c52d23e8e900676b5a1c1a upstream.

Anatoly has been fuzzing with kBdysch harness and reported a hang in one of the outcomes:

func#0 @0
0: R1=ctx(id=0,off=0,imm=0) R10=fp0
0: (b7) r0 = 808464450
1: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R10=fp0
1: (b4) w4 = 808464432
2: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP808464432 R10=fp0
2: (9c) w4 %= w0
3: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R10=fp0 3: (66) if w4 s> 0x30303030 goto pc+0
R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff),s32_max_value=808464432) R10=fp0
4: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff),s32_max_value=808464432) R10=fp0 4: (7f) r0 >>= r0
5: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff),s32_max_value=808464432) R10=fp0 5: (9c) w4 %= w0
6: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0
6: (66) if w0 s> 0x3030 goto pc+0
R0_w=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0
7: R0=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4=invP(id=0) R10=fp0
7: (d6) if w0 s<= 0x303030 goto pc+1
9: R0=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4=invP(id=0) R10=fp0
9: (95) exit
propagating r0

from 6 to 7: safe
4: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umin_value=808464433,umax_value=2147483647,var_off=(0x0; 0x7fffffff)) R10=fp0 4: (7f) r0 >>= r0
5: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umin_value=808464433,umax_value=2147483647,var_off=(0x0; 0x7fffffff)) R10=fp0 5: (9c) w4 %= w0
6: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0
6: (66) if w0 s> 0x3030 goto pc+0
R0_w=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0
propagating r0
7: safe
propagating r0

from 6 to 7: safe
processed 15 insns (limit 1000000) max_states_per_insn 0 total_states 1 peak_states 1 mark_read 1

The underlying program was xlated as follows:

  # bpftool p d x i 10
   0: (b7) r0 = 808464450
   1: (b4) w4 = 808464432
   2: (bc) w0 = w0
   3: (15) if r0 == 0x0 goto pc+1
   4: (9c) w4 %= w0
   5: (66) if w4 s> 0x30303030 goto pc+0
   6: (7f) r0 >>= r0
   7: (bc) w0 = w0
   8: (15) if r0 == 0x0 goto pc+1
   9: (9c) w4 %= w0
  10: (66) if w0 s> 0x3030 goto pc+0
  11: (d6) if w0 s<= 0x303030 goto pc+1
  12: (05) goto pc-1
  13: (95) exit

The verifier rewrote original instructions it recognized as dead code with 'goto pc-1', but reality differs from verifier simulation in that we are actually able to trigger a hang due to hitting the 'goto pc-1' instructions.

Taking a closer look at the verifier analysis, the reason is that it misjudges its pruning decision at the first 'from 6 to 7: safe' occasion. What happens is that while both old/cur registers are marked as precise, they get misjudged for the jmp32 case as range_within() yields true, meaning that the prior verification path with a wider register bound could be verified successfully and therefore the current path with a narrower register bound is deemed safe as well whereas in reality it's not. R0 old/cur path's bounds compare as follows:

old: smin_value=0x8000000000000000,smax_value=0x7fffffffffffffff,umin_value=0x0,umax_value=0xffffffffffffffff,var_off=(0x0; 0xffffffffffffffff)
cur: smin_value=0x8000000000000000,smax_value=0x7fffffff7fffffff,umin_value=0x0,umax_value=0xffffffff7fffffff,var_off=(0x0; 0xffffffff7fffffff)

old: s32_min_value=0x80000000,s32_max_value=0x00003030,u32_min_value=0x00000000,u32_max_value=0xffffffff
cur: s32_min_value=0x00003031,s32_max_value=0x7fffffff,u32_min_value=0x00003031,u32_max_value=0x7fffffff

The 64 bit bounds generally look okay and while the information that got propagated from 32 to 64 bit looks correct as well, it's not precise enough for judging a conditional jmp32. Given the latter only operates on subregisters we also need to take these into account as well for a range_within() probe in order to be able to prune paths. Extending the range_within() constraint to both bounds will be able to tell us that the old signed 32 bit bounds are not wider than the cur signed 32 bit bounds.

With the fix in place, the program will now verify the 'goto' branch case as it should have been:

[...]
6: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0
6: (66) if w0 s> 0x3030 goto pc+0
R0_w=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0
7: R0=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4=invP(id=0) R10=fp0 7: (d6) if w0 s<= 0x303030 goto pc+1
9: R0=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4=invP(id=0) R10=fp0 9: (95) exit

7: R0_w=invP(id=0,smax_value=9223372034707292159,umax_value=18446744071562067967,var_off=(0x0; 0xffffffff7fffffff),s32_min_value=12337,u32_min_value=12337,u32_max_value=2147483647) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 7: (d6) if w0 s<= 0x303030 goto pc+1
R0_w=invP(id=0,smax_value=9223372034707292159,umax_value=18446744071562067967,var_off=(0x0; 0xffffffff7fffffff),s32_min_value=3158065,u32_min_value=3158065,u32_max_value=2147483647) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0
8: R0_w=invP(id=0,smax_value=9223372034707292159,umax_value=18446744071562067967,var_off=(0x0; 0xffffffff7fffffff),s32_min_value=3158065,u32_min_value=3158065,u32_max_value=2147483647) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 8: (30) r0 = *(u8 *)skb[808464432]
BPF_LD_[ABS|IND] uses reserved fields
processed 11 insns (limit 1000000) max_states_per_insn 1 total_states 1 peak_states 1 mark_read 1

The bug is quite subtle in the sense that when verifier would determine that a given branch is dead code, it would (here: wrongly) remove these instructions from the program and hard-wire the taken branch for privileged programs instead of the 'goto pc-1' rewrites which will cause hard to debug problems.

Fixes 3f50f132d840 ("bpf: Verifier, do explicit ALU32 bounds tracking")
---
 kernel/bpf/verifier.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
kernel/bpf/verifier.c +5 -1
@@ -8465,7 +8465,11 @@ static bool range_within(struct bpf_reg_
 	return old->umin_value <= cur->umin_value &&
 	       old->umax_value >= cur->umax_value &&
 	       old->smin_value <= cur->smin_value &&
-	       old->smax_value >= cur->smax_value;
+	       old->smax_value >= cur->smax_value &&
+	       old->u32_min_value <= cur->u32_min_value &&
+	       old->u32_max_value >= cur->u32_max_value &&
+	       old->s32_min_value <= cur->s32_min_value &&
+	       old->s32_max_value >= cur->s32_max_value;
 }
 
 /* Maximum number of register states that can exist at once */
author maintainer
#45 lore raw

PATCH 45/54 bpf: Fix 32 bit src register truncation on div/mod

In reply to Greg Kroah-Hartman

From: Daniel Borkmann <[email protected]>

commit e88b2c6e5a4d9ce30d75391e4d950da74bb2bd90 upstream.

While reviewing a different fix, John and I noticed an oddity in one of the BPF program dumps that stood out, for example:

  # bpftool p d x i 13
   0: (b7) r0 = 808464450
   1: (b4) w4 = 808464432
   2: (bc) w0 = w0
   3: (15) if r0 == 0x0 goto pc+1
   4: (9c) w4 %= w0
  [...]

In line 2 we noticed that the mov32 would 32 bit truncate the original src register for the div/mod operation. While for the two operations the dst register is typically marked unknown e.g. from adjust_scalar_min_max_vals() the src register is not, and thus verifier keeps tracking original bounds, simplified:

0: R1=ctx(id=0,off=0,imm=0) R10=fp0
0: (b7) r0 = -1
1: R0_w=invP-1 R1=ctx(id=0,off=0,imm=0) R10=fp0
1: (b7) r1 = -1
2: R0_w=invP-1 R1_w=invP-1 R10=fp0
2: (3c) w0 /= w1
3: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1_w=invP-1 R10=fp0 3: (77) r1 >>= 32
4: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1_w=invP4294967295 R10=fp0 4: (bf) r0 = r1
5: R0_w=invP4294967295 R1_w=invP4294967295 R10=fp0
5: (95) exit
processed 6 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0

Runtime result of r0 at exit is 0 instead of expected -1. Remove the verifier mov32 src rewrite in div/mod and replace it with a jmp32 test instead. After the fix, we result in the following code generation when having dividend r1 and divisor r6:

div, 64 bit: div, 32 bit:

   0: (b7) r6 = 8                           0: (b7) r6 = 8
   1: (b7) r1 = 8                           1: (b7) r1 = 8
   2: (55) if r6 != 0x0 goto pc+2           2: (56) if w6 != 0x0 goto pc+2
   3: (ac) w1 ^= w1                         3: (ac) w1 ^= w1
   4: (05) goto pc+1                        4: (05) goto pc+1
   5: (3f) r1 /= r6                         5: (3c) w1 /= w6
   6: (b7) r0 = 0                           6: (b7) r0 = 0
   7: (95) exit                             7: (95) exit

mod, 64 bit: mod, 32 bit:

   0: (b7) r6 = 8                           0: (b7) r6 = 8
   1: (b7) r1 = 8                           1: (b7) r1 = 8
   2: (15) if r6 == 0x0 goto pc+1           2: (16) if w6 == 0x0 goto pc+1
   3: (9f) r1 %= r6                         3: (9c) w1 %= w6
   4: (b7) r0 = 0                           4: (b7) r0 = 0
   5: (95) exit                             5: (95) exit

x86 in particular can throw a 'divide error' exception for div instruction not only for divisor being zero, but also for the case when the quotient is too large for the designated register. For the edx:eax and rdx:rax dividend pair it is not an issue in x86 BPF JIT since we always zero edx (rdx). Hence really the only protection needed is against divisor being zero.

---
 kernel/bpf/verifier.c |   28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)
kernel/bpf/verifier.c +13 -15
@@ -10866,30 +10866,28 @@ static int fixup_bpf_calls(struct bpf_ve
 		    insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
 		    insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
 			bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
-			struct bpf_insn mask_and_div[] = {
-				BPF_MOV32_REG(insn->src_reg, insn->src_reg),
+			bool isdiv = BPF_OP(insn->code) == BPF_DIV;
+			struct bpf_insn *patchlet;
+			struct bpf_insn chk_and_div[] = {
 				/* Rx div 0 -> 0 */
-				BPF_JMP_IMM(BPF_JNE, insn->src_reg, 0, 2),
+				BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) |
+					     BPF_JNE | BPF_K, insn->src_reg,
+					     0, 2, 0),
 				BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg),
 				BPF_JMP_IMM(BPF_JA, 0, 0, 1),
 				*insn,
 			};
-			struct bpf_insn mask_and_mod[] = {
-				BPF_MOV32_REG(insn->src_reg, insn->src_reg),
+			struct bpf_insn chk_and_mod[] = {
 				/* Rx mod 0 -> Rx */
-				BPF_JMP_IMM(BPF_JEQ, insn->src_reg, 0, 1),
+				BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) |
+					     BPF_JEQ | BPF_K, insn->src_reg,
+					     0, 1, 0),
 				*insn,
 			};
-			struct bpf_insn *patchlet;
 
-			if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
-			    insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
-				patchlet = mask_and_div + (is64 ? 1 : 0);
-				cnt = ARRAY_SIZE(mask_and_div) - (is64 ? 1 : 0);
-			} else {
-				patchlet = mask_and_mod + (is64 ? 1 : 0);
-				cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 1 : 0);
-			}
+			patchlet = isdiv ? chk_and_div : chk_and_mod;
+			cnt = isdiv ? ARRAY_SIZE(chk_and_div) :
+				      ARRAY_SIZE(chk_and_mod);
 
 			new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt);
 			if (!new_prog)
author maintainer
#46 lore raw

PATCH 46/54 bpf: Fix verifier jsgt branch analysis on max bound

In reply to Greg Kroah-Hartman

From: Daniel Borkmann <[email protected]>

commit ee114dd64c0071500345439fc79dd5e0f9d106ed upstream.

Fix incorrect is_branch{32,64}_taken() analysis for the jsgt case. The return code for both will tell the caller whether a given conditional jump is taken or not, e.g. 1 means branch will be taken [for the involved registers] and the goto target will be executed, 0 means branch will not be taken and instead we fall-through to the next insn, and last but not least a -1 denotes that it is not known at verification time whether a branch will be taken or not. Now while the jsgt has the branch-taken case correct with reg->s32_min_value > sval, the branch-not-taken case is off-by-one when testing for reg->s32_max_value < sval since the branch will also be taken for reg->s32_max_value == sval. The jgt branch analysis, for example, gets this right.

Fixes 3f50f132d840 ("bpf: Verifier, do explicit ALU32 bounds tracking")
Fixes 4f7b3e82589e ("bpf: improve verifier branch analysis")
---
 kernel/bpf/verifier.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
kernel/bpf/verifier.c +2 -2
@@ -6822,7 +6822,7 @@ static int is_branch32_taken(struct bpf_
 	case BPF_JSGT:
 		if (reg->s32_min_value > sval)
 			return 1;
-		else if (reg->s32_max_value < sval)
+		else if (reg->s32_max_value <= sval)
 			return 0;
 		break;
 	case BPF_JLT:
@@ -6895,7 +6895,7 @@ static int is_branch64_taken(struct bpf_
 	case BPF_JSGT:
 		if (reg->smin_value > sval)
 			return 1;
-		else if (reg->smax_value < sval)
+		else if (reg->smax_value <= sval)
 			return 0;
 		break;
 	case BPF_JLT:

Greg Kroah-Hartman

author maintainer
#0 lore raw

cover 5.10.16-rc1 review

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.16-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 5.10.16-rc1

Phillip Lougher <[email protected]>
squashfs: add more sanity checks in xattr id lookup

Phillip Lougher <[email protected]>
squashfs: add more sanity checks in inode lookup

Phillip Lougher <[email protected]>
squashfs: add more sanity checks in id lookup

Phillip Lougher <[email protected]>
squashfs: avoid out of bounds writes in decompressors

Johannes Weiner <[email protected]>
Revert "mm: memcontrol: avoid workload stalls when lowering memory.high"

Joachim Henke <[email protected]>
nilfs2: make splice write available again

Ville Syrjälä <[email protected]>
drm/i915: Skip vswing programming for TBT

Ville Syrjälä <[email protected]>
drm/i915: Fix ICL MG PHY vswing handling

Daniel Borkmann <[email protected]>
bpf: Fix verifier jsgt branch analysis on max bound

Daniel Borkmann <[email protected]>
bpf: Fix 32 bit src register truncation on div/mod

Daniel Borkmann <[email protected]>
bpf: Fix verifier jmp32 pruning decision logic

Mark Brown <[email protected]>
regulator: Fix lockdep warning resolving supplies

Baolin Wang <[email protected]>
blk-cgroup: Use cond_resched() when destroy blkgs

Qii Wang <[email protected]>
i2c: mediatek: Move suspend and resume handling to NOIRQ phase

Dave Wysochanski <[email protected]>
SUNRPC: Handle 0 length opaque XDR object data properly

Dave Wysochanski <[email protected]>
SUNRPC: Move simple_get_bytes and simple_get_netobj into private header

Johannes Berg <[email protected]>
iwlwifi: queue: bail out on invalid freeing

Johannes Berg <[email protected]>
iwlwifi: mvm: guard against device removal in reprobe

Luca Coelho <[email protected]>
iwlwifi: pcie: add rules to match Qu with Hr2

Gregory Greenman <[email protected]>
iwlwifi: mvm: invalidate IDs of internal stations at mvm start

Johannes Berg <[email protected]>
iwlwifi: pcie: fix context info memory leak

Emmanuel Grumbach <[email protected]>
iwlwifi: pcie: add a NULL check in iwl_pcie_txq_unmap

Johannes Berg <[email protected]>
iwlwifi: mvm: take mutex for calling iwl_mvm_get_sync_time()

Sara Sharon <[email protected]>
iwlwifi: mvm: skip power command when unbinding vif during CSA

Libin Yang <[email protected]>
ASoC: Intel: sof_sdw: set proper flags for Dell TGL-H SKU 0A5E

Eliot Blennerhassett <[email protected]>
ASoC: ak4458: correct reset polarity

Bard Liao <[email protected]>
ALSA: hda: intel-dsp-config: add PCI id for TGL-H

Trond Myklebust <[email protected]>
pNFS/NFSv4: Improve rejection of out-of-order layouts

Trond Myklebust <[email protected]>
pNFS/NFSv4: Try to return invalid layout in pnfs_layout_process()

Pan Bian <[email protected]>
chtls: Fix potential resource leak

Ricardo Ribalda <[email protected]>
ASoC: Intel: Skylake: Zero snd_ctl_elem_value

Shay Bar <[email protected]>
mac80211: 160MHz with extended NSS BW in CSA

Ben Skeggs <[email protected]>
drm/nouveau/nvif: fix method count when pushing an array

James Schulman <[email protected]>
ASoC: wm_adsp: Fix control name parsing for multi-fw

David Collins <[email protected]>
regulator: core: avoid regulator_resolve_supply() race condition

Cong Wang <[email protected]>
af_key: relax availability checks for skb size calculation

Raoni Fassina Firmino <[email protected]>
powerpc/64/signal: Fix regression in __kernel_sigtramp_rt64() semantics

Kent Gibson <[email protected]>
gpiolib: cdev: clear debounce period if line set to output

Pavel Begunkov <[email protected]>
io_uring: drop mm/files between task_work_submit

Pavel Begunkov <[email protected]>
io_uring: reinforce cancel on flush during exit

Pavel Begunkov <[email protected]>
io_uring: fix sqo ownership false positive warning

Pavel Begunkov <[email protected]>
io_uring: fix list corruption for splice file_get

Hao Xu <[email protected]>
io_uring: fix flush cqring overflow list while TASK_INTERRUPTIBLE

Pavel Begunkov <[email protected]>
io_uring: fix cancellation taking mutex while TASK_UNINTERRUPTIBLE

Pavel Begunkov <[email protected]>

    io_uring: replace inflight_wait with tctx->wait

Pavel Begunkov <[email protected]>
io_uring: fix __io_uring_files_cancel() with TASK_UNINTERRUPTIBLE

Jens Axboe <[email protected]>
io_uring: if we see flush on exit, cancel related tasks

Jens Axboe <[email protected]>
io_uring: account io_uring internal files as REQ_F_INFLIGHT

Pavel Begunkov <[email protected]>
io_uring: fix files cancellation

Pavel Begunkov <[email protected]>
io_uring: always batch cancel in *cancel_files()

Pavel Begunkov <[email protected]>
io_uring: pass files into kill timeouts/poll

Pavel Begunkov <[email protected]>
io_uring: don't iterate io_uring_cancel_files()

Pavel Begunkov <[email protected]>
io_uring: add a {task,files} pair matching helper

Pavel Begunkov <[email protected]>
io_uring: simplify io_task_match()

-------------

Diffstat:

 Makefile                                           |   4 +-
 arch/powerpc/kernel/vdso.c                         |   2 +-
 arch/powerpc/kernel/vdso64/sigtramp.S              |  11 +-
 arch/powerpc/kernel/vdso64/vdso64.lds.S            |   1 +
 block/blk-cgroup.c                                 |  18 +-
 drivers/gpio/gpiolib-cdev.c                        |   2 +
 drivers/gpu/drm/i915/display/intel_ddi.c           |  13 +-
 drivers/gpu/drm/nouveau/include/nvif/push.h        | 216 ++++++-------
 drivers/i2c/busses/i2c-mt65xx.c                    |  19 +-
 .../chelsio/inline_crypto/chtls/chtls_cm.c         |   7 +-
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c     |  25 ++
 drivers/net/wireless/intel/iwlwifi/iwl-config.h    |   3 +
 .../net/wireless/intel/iwlwifi/mvm/debugfs-vif.c   |   3 +
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c  |   3 +
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c       |   7 +-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c       |   6 +
 .../wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c   |  11 +-
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c      |  10 +
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c       |   5 +
 drivers/net/wireless/intel/iwlwifi/queue/tx.c      |   6 +-
 drivers/regulator/core.c                           |  44 ++-
 fs/io-wq.c                                         |  10 -
 fs/io-wq.h                                         |   1 -
 fs/io_uring.c                                      | 360 ++++++++-------------
 fs/nfs/pnfs.c                                      |  30 +-
 fs/nilfs2/file.c                                   |   1 +
 fs/squashfs/block.c                                |   8 +-
 fs/squashfs/export.c                               |  41 ++-
 fs/squashfs/id.c                                   |  40 ++-
 fs/squashfs/squashfs_fs_sb.h                       |   1 +
 fs/squashfs/super.c                                |   6 +-
 fs/squashfs/xattr.h                                |  10 +-
 fs/squashfs/xattr_id.c                             |  66 +++-
 include/linux/sunrpc/xdr.h                         |   3 +-
 kernel/bpf/verifier.c                              |  38 +--
 mm/memcontrol.c                                    |   5 +-
 net/key/af_key.c                                   |   6 +-
 net/mac80211/spectmgmt.c                           |  10 +-
 net/sunrpc/auth_gss/auth_gss.c                     |  30 +-
 net/sunrpc/auth_gss/auth_gss_internal.h            |  45 +++
 net/sunrpc/auth_gss/gss_krb5_mech.c                |  31 +-
 sound/hda/intel-dsp-config.c                       |   4 +
 sound/soc/codecs/ak4458.c                          |  22 +-
 sound/soc/codecs/wm_adsp.c                         |   3 +
 sound/soc/intel/boards/sof_sdw.c                   |  10 +
 sound/soc/intel/skylake/skl-topology.c             |   2 +-
 46 files changed, 683 insertions(+), 516 deletions(-)
author maintainer
#6 lore raw

PATCH 6/54 io_uring: fix files cancellation

From: Pavel Begunkov <[email protected]>

[ Upstream commit bee749b187ac57d1faf00b2ab356ff322230fce8 ]

io_uring_cancel_files()'s task check condition mistakenly got flipped.

1. There can't be a request in the inflight list without IO_WQ_WORK_FILES, kill this check to keep the whole condition simpler.
2. Also, don't call the function for files==NULL to not do such a check, all that staff is already handled well by its counter part, __io_uring_cancel_task_requests().

With that just flip the task check.

Also, it iowq-cancels all request of current task there, don't forget to set right ->files into struct io_task_cancel.

Fixes c1973b38bf639 ("io_uring: cancel only requests of current task")
Reported-by [email protected]
---
 fs/io_uring.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
fs/io_uring.c +4 -4
@@ -8571,15 +8571,14 @@ static void io_uring_cancel_files(struct
 				  struct files_struct *files)
 {
 	while (!list_empty_careful(&ctx->inflight_list)) {
-		struct io_task_cancel cancel = { .task = task, .files = NULL, };
+		struct io_task_cancel cancel = { .task = task, .files = files };
 		struct io_kiocb *req;
 		DEFINE_WAIT(wait);
 		bool found = false;
 
 		spin_lock_irq(&ctx->inflight_lock);
 		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
-			if (req->task == task &&
-			    (req->work.flags & IO_WQ_WORK_FILES) &&
+			if (req->task != task ||
 			    req->work.identity->files != files)
 				continue;
 			found = true;
@@ -8665,10 +8664,11 @@ static void io_uring_cancel_task_request
 
 	io_cancel_defer_files(ctx, task, files);
 	io_cqring_overflow_flush(ctx, true, task, files);
-	io_uring_cancel_files(ctx, task, files);
 
 	if (!files)
 		__io_uring_cancel_task_requests(ctx, task);
+	else
+		io_uring_cancel_files(ctx, task, files);
 
 	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
 		atomic_dec(&task->io_uring->in_idle);
author maintainer
#42 lore raw

PATCH 42/54 blk-cgroup: Use cond_resched() when destroy blkgs

In reply to Greg Kroah-Hartman

From: Baolin Wang <[email protected]>

[ Upstream commit 6c635caef410aa757befbd8857c1eadde5cc22ed ]

On !PREEMPT kernel, we can get below softlockup when doing stress testing with creating and destroying block cgroup repeatly. The reason is it may take a long time to acquire the queue's lock in the loop of blkcg_destroy_blkgs(), or the system can accumulate a huge number of blkgs in pathological cases. We can add a need_resched() check on each loop and release locks and do cond_resched() if true to avoid this issue, since the blkcg_destroy_blkgs() is not called from atomic contexts.

[ 4757.010308] watchdog: BUG: soft lockup - CPU#11 stuck for 94s!
[ 4757.010698] Call trace:
[ 4757.010700]  blkcg_destroy_blkgs+0x68/0x150
[ 4757.010701]  cgwb_release_workfn+0x104/0x158
[ 4757.010702]  process_one_work+0x1bc/0x3f0
[ 4757.010704]  worker_thread+0x164/0x468
[ 4757.010705]  kthread+0x108/0x138
---
 block/blk-cgroup.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)
block/blk-cgroup.c +13 -5
index 54fbe1e80cc41..f13688c4b9317 100644
@@ -1017,6 +1017,8 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css)
  */
 void blkcg_destroy_blkgs(struct blkcg *blkcg)
 {
+	might_sleep();
+
 	spin_lock_irq(&blkcg->lock);
 
 	while (!hlist_empty(&blkcg->blkg_list)) {
@@ -1024,14 +1026,20 @@ void blkcg_destroy_blkgs(struct blkcg *blkcg)
 						struct blkcg_gq, blkcg_node);
 		struct request_queue *q = blkg->q;
 
-		if (spin_trylock(&q->queue_lock)) {
-			blkg_destroy(blkg);
-			spin_unlock(&q->queue_lock);
-		} else {
+		if (need_resched() || !spin_trylock(&q->queue_lock)) {
+			/*
+			 * Given that the system can accumulate a huge number
+			 * of blkgs in pathological cases, check to see if we
+			 * need to rescheduling to avoid softlockup.
+			 */
 			spin_unlock_irq(&blkcg->lock);
-			cpu_relax();
+			cond_resched();
 			spin_lock_irq(&blkcg->lock);
+			continue;
 		}
+
+		blkg_destroy(blkg);
+		spin_unlock(&q->queue_lock);
 	}
 
 	spin_unlock_irq(&blkcg->lock);
Signature · 1 line
2.27.0
author maintainer
#47 lore raw

PATCH 47/54 drm/i915: Fix ICL MG PHY vswing handling

In reply to Greg Kroah-Hartman

From: Ville Syrjälä <[email protected]>

commit a2a5f5628e5494ca9353f761f7fe783dfa82fb9a upstream.

The MH PHY vswing table does have all the entries these days. Get rid of the old hacks in the code which claim otherwise.

This hack was totally bogus anyway. The correct way to handle the lack of those two entries would have been to declare our max vswing and pre-emph to both be level 2.

Cc José Roberto de Souza <[email protected]>
Cc Clinton Taylor <[email protected]>
Fixes 9f7ffa297978 ("drm/i915/tc/icl: Update TC vswing tables")
(cherry picked from commit 5ec346476e795089b7dac8ab9dcee30c8d80ad84)
---
 drivers/gpu/drm/i915/display/intel_ddi.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)
drivers/gpu/drm/i915/display/intel_ddi.c +3 -4
@@ -2605,12 +2605,11 @@ static void icl_mg_phy_ddi_vswing_sequen
 
 	ddi_translations = icl_get_mg_buf_trans(encoder, type, rate,
 						&n_entries);
-	/* The table does not have values for level 3 and level 9. */
-	if (level >= n_entries || level == 3 || level == 9) {
+	if (level >= n_entries) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "DDI translation not found for level %d. Using %d instead.",
-			    level, n_entries - 2);
-		level = n_entries - 2;
+			    level, n_entries - 1);
+		level = n_entries - 1;
 	}
 
 	/* Set MG_TX_LINK_PARAMS cri_use_fs32 to 0. */
author maintainer
#50 lore raw

PATCH 50/54 Revert "mm: memcontrol: avoid workload stalls when lowering memory.high"

In reply to Greg Kroah-Hartman

From: Johannes Weiner <[email protected]>

commit e82553c10b0899994153f9bf0af333c0a1550fd7 upstream.

This reverts commit 536d3bf261a2fc3b05b3e91e7eef7383443015cf, as it can cause writers to memory.high to get stuck in the kernel forever, performing page reclaim and consuming excessive amounts of CPU cycles.

Before the patch, a write to memory.high would first put the new limit in place for the workload, and then reclaim the requested delta. After the patch, the kernel tries to reclaim the delta before putting the new limit into place, in order to not overwhelm the workload with a sudden, large excess over the limit. However, if reclaim is actively racing with new allocations from the uncurbed workload, it can keep the write() working inside the kernel indefinitely.

This is causing problems in Facebook production. A privileged system-level daemon that adjusts memory.high for various workloads running on a host can get unexpectedly stuck in the kernel and essentially turn into a sort of involuntary kswapd for one of the workloads. We've observed that daemon busy-spin in a write() for minutes at a time, neglecting its other duties on the system, and expending privileged system resources on behalf of a workload.

To remedy this, we have first considered changing the reclaim logic to break out after a couple of loops - whether the workload has converged to the new limit or not - and bound the write() call this way. However, the root cause that inspired the sequence change in the first place has been fixed through other means, and so a revert back to the proven limit-setting sequence, also used by memory.max, is preferable.

The sequence was changed to avoid extreme latencies in the workload when the limit was lowered: the sudden, large excess created by the limit lowering would erroneously trigger the penalty sleeping code that is meant to throttle excessive growth from below. Allocating threads could end up sleeping long after the write() had already reclaimed the delta for which they were being punished.

However, erroneous throttling also caused problems in other scenarios at around the same time. This resulted in commit b3ff92916af3 ("mm, memcg:
reclaim more aggressively before high allocator throttling"), included in the same release as the offending commit. When allocating threads now encounter large excess caused by a racing write() to memory.high, instead of entering punitive sleeps, they will simply be tasked with helping reclaim down the excess, and will be held no longer than it takes to accomplish that. This is in line with regular limit enforcement - i.e. if the workload allocates up against or over an otherwise unchanged limit from below.

With the patch breaking userspace, and the root cause addressed by other means already, revert it again.

Fixes 536d3bf261a2 ("mm: memcontrol: avoid workload stalls when lowering memory.high")
Cc Roman Gushchin <[email protected]>
Cc Shakeel Butt <[email protected]>
Cc Michal Koutný <[email protected]>
Cc <[email protected]> [5.8+]
---
 mm/memcontrol.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
mm/memcontrol.c +2 -3
@@ -6320,6 +6320,8 @@ static ssize_t memory_high_write(struct
 	if (err)
 		return err;
 
+	page_counter_set_high(&memcg->memory, high);
+
 	for (;;) {
 		unsigned long nr_pages = page_counter_read(&memcg->memory);
 		unsigned long reclaimed;
@@ -6343,10 +6345,7 @@ static ssize_t memory_high_write(struct
 			break;
 	}
 
-	page_counter_set_high(&memcg->memory, high);
-
 	memcg_wb_domain_size_changed(memcg);
-
 	return nbytes;
 }
 
author maintainer
#31 lore raw

PATCH 31/54 iwlwifi: mvm: skip power command when unbinding vif during CSA

In reply to Greg Kroah-Hartman

From: Sara Sharon <[email protected]>

[ Upstream commit bf544e9aa570034e094a8a40d5f9e1e2c4916d18 ]

In the new CSA flow, we remain associated during CSA, but still do a unbind-bind to the vif. However, sending the power command right after when vif is unbound but still associated causes FW to assert (0x3400) since it cannot tell the LMAC id.

Just skip this command, we will send it again in a bit, when assigning the new context.

---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +3 -0
index b627e7da7ac9d..d42165559df6e 100644
@@ -4249,6 +4249,9 @@ static void __iwl_mvm_unassign_vif_chanctx(struct iwl_mvm *mvm,
 	iwl_mvm_binding_remove_vif(mvm, vif);
 
 out:
+	if (fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_CHANNEL_SWITCH_CMD) &&
+	    switching_chanctx)
+		return;
 	mvmvif->phy_ctxt = NULL;
 	iwl_mvm_power_update_mac(mvm);
 }
Signature · 1 line
2.27.0
author maintainer
#48 lore raw

PATCH 48/54 drm/i915: Skip vswing programming for TBT

In reply to Greg Kroah-Hartman

From: Ville Syrjälä <[email protected]>

commit eaf5bfe37db871031232d2bf2535b6ca92afbad8 upstream.

In thunderbolt mode the PHY is owned by the thunderbolt controller. We are not supposed to touch it. So skip the vswing programming as well (we already skipped the other steps not applicable to TBT).

Touching this stuff could supposedly interfere with the PHY programming done by the thunderbolt controller.

---
 drivers/gpu/drm/i915/display/intel_ddi.c |    6 ++++++
 1 file changed, 6 insertions(+)
drivers/gpu/drm/i915/display/intel_ddi.c +6 -0
@@ -2597,6 +2597,9 @@ static void icl_mg_phy_ddi_vswing_sequen
 	u32 n_entries, val;
 	int ln, rate = 0;
 
+	if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT)
+		return;
+
 	if (type != INTEL_OUTPUT_HDMI) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
@@ -2741,6 +2744,9 @@ tgl_dkl_phy_ddi_vswing_sequence(struct i
 	u32 n_entries, val, ln, dpcnt_mask, dpcnt_val;
 	int rate = 0;
 
+	if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT)
+		return;
+
 	if (type != INTEL_OUTPUT_HDMI) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
author maintainer
#49 lore raw

PATCH 49/54 nilfs2: make splice write available again

In reply to Greg Kroah-Hartman

From: Joachim Henke <[email protected]>

commit a35d8f016e0b68634035217d06d1c53863456b50 upstream.

Since 5.10, splice() or sendfile() to NILFS2 return EINVAL. This was caused by commit 36e2c7421f02 ("fs: don't allow splice read/write without explicit ops").

This patch initializes the splice_write field in file_operations, like most file systems do, to restore the functionality.

---
 fs/nilfs2/file.c |    1 +
 1 file changed, 1 insertion(+)
fs/nilfs2/file.c +1 -0
@@ -141,6 +141,7 @@ const struct file_operations nilfs_file_
 	/* .release	= nilfs_release_file, */
 	.fsync		= nilfs_sync_file,
 	.splice_read	= generic_file_splice_read,
+	.splice_write   = iter_file_splice_write,
 };
 
 const struct inode_operations nilfs_file_inode_operations = {
author maintainer
#8 lore raw

PATCH 8/54 io_uring: if we see flush on exit, cancel related tasks

In reply to Greg Kroah-Hartman

From: Jens Axboe <[email protected]>

[ Upstream commit 84965ff8a84f0368b154c9b367b62e59c1193f30 ]

Ensure we match tasks that belong to a dead or dying task as well, as we need to reap those in addition to those belonging to the exiting task.

---
 fs/io_uring.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
fs/io_uring.c +8 -1
@@ -1014,8 +1014,12 @@ static bool io_match_task(struct io_kioc
 {
 	struct io_kiocb *link;
 
-	if (task && head->task != task)
+	if (task && head->task != task) {
+		/* in terms of cancelation, always match if req task is dead */
+		if (head->task->flags & PF_EXITING)
+			return true;
 		return false;
+	}
 	if (!files)
 		return true;
 	if (__io_match_files(head, files))
@@ -8844,6 +8848,9 @@ static int io_uring_flush(struct file *f
 	struct io_uring_task *tctx = current->io_uring;
 	struct io_ring_ctx *ctx = file->private_data;
 
+	if (fatal_signal_pending(current) || (current->flags & PF_EXITING))
+		io_uring_cancel_task_requests(ctx, NULL);
+
 	if (!tctx)
 		return 0;
 
author maintainer
#9 lore raw

PATCH 9/54 io_uring: fix __io_uring_files_cancel() with TASK_UNINTERRUPTIBLE

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit a1bb3cd58913338e1b627ea6b8c03c2ae82d293f ]

If the tctx inflight number haven't changed because of cancellation, __io_uring_task_cancel() will continue leaving the task in TASK_UNINTERRUPTIBLE state, that's not expected by __io_uring_files_cancel(). Ensure we always call finish_wait() before retrying.

---
 fs/io_uring.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
fs/io_uring.c +6 -6
@@ -8829,15 +8829,15 @@ void __io_uring_task_cancel(void)
 		prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
 
 		/*
-		 * If we've seen completions, retry. This avoids a race where
-		 * a completion comes in before we did prepare_to_wait().
+		 * If we've seen completions, retry without waiting. This
+		 * avoids a race where a completion comes in before we did
+		 * prepare_to_wait().
 		 */
-		if (inflight != tctx_inflight(tctx))
-			continue;
-		schedule();
+		if (inflight == tctx_inflight(tctx))
+			schedule();
+		finish_wait(&tctx->wait, &wait);
 	} while (1);
 
-	finish_wait(&tctx->wait, &wait);
 	atomic_dec(&tctx->in_idle);
 
 	io_uring_remove_task_files(tctx);
author maintainer
#41 lore raw

PATCH 41/54 i2c: mediatek: Move suspend and resume handling to NOIRQ phase

In reply to Greg Kroah-Hartman

From: Qii Wang <[email protected]>

[ Upstream commit de96c3943f591018727b862f51953c1b6c55bcc3 ]

Some i2c device driver indirectly uses I2C driver when it is now being suspended. The i2c devices driver is suspended during the NOIRQ phase and this cannot be changed due to other dependencies. Therefore, we also need to move the suspend handling for the I2C controller driver to the NOIRQ phase as well.

---
 drivers/i2c/busses/i2c-mt65xx.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)
drivers/i2c/busses/i2c-mt65xx.c +16 -3
index 0818d3e507347..2ffd2f354d0ae 100644
@@ -1275,7 +1275,8 @@ static int mtk_i2c_probe(struct platform_device *pdev)
 	mtk_i2c_clock_disable(i2c);
 
 	ret = devm_request_irq(&pdev->dev, irq, mtk_i2c_irq,
-			       IRQF_TRIGGER_NONE, I2C_DRV_NAME, i2c);
+			       IRQF_NO_SUSPEND | IRQF_TRIGGER_NONE,
+			       I2C_DRV_NAME, i2c);
 	if (ret < 0) {
 		dev_err(&pdev->dev,
 			"Request I2C IRQ %d fail\n", irq);
@@ -1302,7 +1303,16 @@ static int mtk_i2c_remove(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_PM_SLEEP
-static int mtk_i2c_resume(struct device *dev)
+static int mtk_i2c_suspend_noirq(struct device *dev)
+{
+	struct mtk_i2c *i2c = dev_get_drvdata(dev);
+
+	i2c_mark_adapter_suspended(&i2c->adap);
+
+	return 0;
+}
+
+static int mtk_i2c_resume_noirq(struct device *dev)
 {
 	int ret;
 	struct mtk_i2c *i2c = dev_get_drvdata(dev);
@@ -1317,12 +1327,15 @@ static int mtk_i2c_resume(struct device *dev)
 
 	mtk_i2c_clock_disable(i2c);
 
+	i2c_mark_adapter_resumed(&i2c->adap);
+
 	return 0;
 }
 #endif
 
 static const struct dev_pm_ops mtk_i2c_pm = {
-	SET_SYSTEM_SLEEP_PM_OPS(NULL, mtk_i2c_resume)
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_i2c_suspend_noirq,
+				      mtk_i2c_resume_noirq)
 };
 
 static struct platform_driver mtk_i2c_driver = {
Signature · 1 line
2.27.0
author maintainer
#7 lore raw

PATCH 7/54 io_uring: account io_uring internal files as REQ_F_INFLIGHT

In reply to Greg Kroah-Hartman

From: Jens Axboe <[email protected]>

[ Upstream commit 02a13674fa0e8dd326de8b9f4514b41b03d99003 ]

We need to actively cancel anything that introduces a potential circular loop, where io_uring holds a reference to itself. If the file in question is an io_uring file, then add the request to the inflight list.

---
 fs/io_uring.c |   32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)
fs/io_uring.c +24 -8
@@ -1000,6 +1000,9 @@ static inline void io_clean_op(struct io
 static inline bool __io_match_files(struct io_kiocb *req,
 				    struct files_struct *files)
 {
+	if (req->file && req->file->f_op == &io_uring_fops)
+		return true;
+
 	return ((req->flags & REQ_F_WORK_INITIALIZED) &&
 	        (req->work.flags & IO_WQ_WORK_FILES)) &&
 		req->work.identity->files == files;
@@ -1398,11 +1401,14 @@ static bool io_grab_identity(struct io_k
 			return false;
 		atomic_inc(&id->files->count);
 		get_nsproxy(id->nsproxy);
-		req->flags |= REQ_F_INFLIGHT;
 
-		spin_lock_irq(&ctx->inflight_lock);
-		list_add(&req->inflight_entry, &ctx->inflight_list);
-		spin_unlock_irq(&ctx->inflight_lock);
+		if (!(req->flags & REQ_F_INFLIGHT)) {
+			req->flags |= REQ_F_INFLIGHT;
+
+			spin_lock_irq(&ctx->inflight_lock);
+			list_add(&req->inflight_entry, &ctx->inflight_list);
+			spin_unlock_irq(&ctx->inflight_lock);
+		}
 		req->work.flags |= IO_WQ_WORK_FILES;
 	}
 	if (!(req->work.flags & IO_WQ_WORK_MM) &&
@@ -5886,8 +5892,10 @@ static void io_req_drop_files(struct io_
 	struct io_ring_ctx *ctx = req->ctx;
 	unsigned long flags;
 
-	put_files_struct(req->work.identity->files);
-	put_nsproxy(req->work.identity->nsproxy);
+	if (req->work.flags & IO_WQ_WORK_FILES) {
+		put_files_struct(req->work.identity->files);
+		put_nsproxy(req->work.identity->nsproxy);
+	}
 	spin_lock_irqsave(&ctx->inflight_lock, flags);
 	list_del(&req->inflight_entry);
 	spin_unlock_irqrestore(&ctx->inflight_lock, flags);
@@ -6159,6 +6167,15 @@ static struct file *io_file_get(struct i
 		file = __io_file_get(state, fd);
 	}
 
+	if (file && file->f_op == &io_uring_fops) {
+		io_req_init_async(req);
+		req->flags |= REQ_F_INFLIGHT;
+
+		spin_lock_irq(&ctx->inflight_lock);
+		list_add(&req->inflight_entry, &ctx->inflight_list);
+		spin_unlock_irq(&ctx->inflight_lock);
+	}
+
 	return file;
 }
 
@@ -8578,8 +8595,7 @@ static void io_uring_cancel_files(struct
 
 		spin_lock_irq(&ctx->inflight_lock);
 		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
-			if (req->task != task ||
-			    req->work.identity->files != files)
+			if (!io_match_task(req, task, files))
 				continue;
 			found = true;
 			break;
author maintainer
#43 lore raw

PATCH 43/54 regulator: Fix lockdep warning resolving supplies

In reply to Greg Kroah-Hartman

From: Mark Brown <[email protected]>

[ Upstream commit 14a71d509ac809dcf56d7e3ca376b15d17bd0ddd ]

With commit eaa7995c529b54 (regulator: core: avoid regulator_resolve_supply() race condition) we started holding the rdev lock while resolving supplies, an operation that requires holding the regulator_list_mutex. This results in lockdep warnings since in other places we take the list mutex then the mutex on an individual rdev.

Since the goal is to make sure that we don't call set_supply() twice rather than a concern about the cost of resolution pull the rdev lock and check for duplicate resolution down to immediately before we do the set_supply() and drop it again once the allocation is done.

Fixes eaa7995c529b54 (regulator: core: avoid regulator_resolve_supply() race condition)
---
 drivers/regulator/core.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)
drivers/regulator/core.c +17 -12
index 2c31f04ff950f..35098dbd32a3c 100644
@@ -1823,17 +1823,6 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 	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);
@@ -1885,12 +1874,29 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 		goto out;
 	}
 
+	/*
+	 * 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) {
+		regulator_unlock(rdev);
+		put_device(&r->dev);
+		goto out;
+	}
+
 	ret = set_supply(rdev, r);
 	if (ret < 0) {
+		regulator_unlock(rdev);
 		put_device(&r->dev);
 		goto out;
 	}
 
+	regulator_unlock(rdev);
+
 	/*
 	 * In set_machine_constraints() we may have turned this regulator on
 	 * but we couldn't propagate to the supply if it hadn't been resolved
@@ -1906,7 +1912,6 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 	}
 
 out:
-	regulator_unlock(rdev);
 	return ret;
 }
 
Signature · 1 line
2.27.0
author maintainer
#51 lore raw

PATCH 51/54 squashfs: avoid out of bounds writes in decompressors

In reply to Greg Kroah-Hartman

From: Phillip Lougher <[email protected]>

commit e812cbbbbbb15adbbbee176baa1e8bda53059bf0 upstream.

Patch series "Squashfs: fix BIO migration regression and add sanity checks".

Patch [1/4] fixes a regression introduced by the "migrate from ll_rw_block usage to BIO" patch, which has produced a number of Sysbot/Syzkaller reports.

Patches [2/4], [3/4], and [4/4] fix a number of filesystem corruption issues which have produced Sysbot reports in the id, inode and xattr lookup code.

Each patch has been tested against the Sysbot reproducers using the given kernel configuration. They have the appropriate "Reported-by:" lines added.

Additionally, all of the reproducer filesystems are indirectly fixed by patch [4/4] due to the fact they all have xattr corruption which is now detected there.

Additional testing with other configurations and architectures (32bit, big endian), and normal filesystems has also been done to trap any inadvertent regressions caused by the additional sanity checks.

This patch (of 4):

This is a regression introduced by the patch "migrate from ll_rw_block usage to BIO".

Sysbot/Syskaller has reported a number of "out of bounds writes" and "unable to handle kernel paging request in squashfs_decompress" errors which have been identified as a regression introduced by the above patch.

Specifically, the patch removed the following sanity check

        if (length < 0 || length > output->length ||
		(index + length) > msblk->bytes_used)

This check did two things:

1. It ensured any reads were not beyond the end of the filesystem

2. It ensured that the "length" field read from the filesystem was within the expected maximum length. Without this any corrupted values can over-run allocated buffers.

---
 fs/squashfs/block.c |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
fs/squashfs/block.c +7 -1
@@ -196,9 +196,15 @@ int squashfs_read_data(struct super_bloc
 		length = SQUASHFS_COMPRESSED_SIZE(length);
 		index += 2;
 
-		TRACE("Block @ 0x%llx, %scompressed size %d\n", index,
+		TRACE("Block @ 0x%llx, %scompressed size %d\n", index - 2,
 		      compressed ? "" : "un", length);
 	}
+	if (length < 0 || length > output->length ||
+			(index + length) > msblk->bytes_used) {
+		res = -EIO;
+		goto out;
+	}
+
 	if (next_index)
 		*next_index = index + length;
 
author maintainer
#32 lore raw

PATCH 32/54 iwlwifi: mvm: take mutex for calling iwl_mvm_get_sync_time()

In reply to Greg Kroah-Hartman

From: Johannes Berg <[email protected]>

[ Upstream commit 5c56d862c749669d45c256f581eac4244be00d4d ]

We need to take the mutex to call iwl_mvm_get_sync_time(), do it.

---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c +3 -0
index f043eefabb4ec..7b1d2dac6ceb8 100644
@@ -514,7 +514,10 @@ static ssize_t iwl_dbgfs_os_device_timediff_read(struct file *file,
 	const size_t bufsz = sizeof(buf);
 	int pos = 0;
 
+	mutex_lock(&mvm->mutex);
 	iwl_mvm_get_sync_time(mvm, &curr_gp2, &curr_os);
+	mutex_unlock(&mvm->mutex);
+
 	do_div(curr_os, NSEC_PER_USEC);
 	diff = curr_os - curr_gp2;
 	pos += scnprintf(buf + pos, bufsz - pos, "diff=%lld\n", diff);
Signature · 1 line
2.27.0
author maintainer
#35 lore raw

PATCH 35/54 iwlwifi: mvm: invalidate IDs of internal stations at mvm start

In reply to Greg Kroah-Hartman

From: Gregory Greenman <[email protected]>

[ Upstream commit e223e42aac30bf81f9302c676cdf58cf2bf36950 ]

Having sta_id not set for aux_sta and snif_sta can potentially lead to a hard to debug issue in case remove station is called without an add. In this case sta_id 0, an unrelated regular station, will be removed.

In fact, we do have a FW assert that occures rarely and from the debug data analysis it looks like sta_id 0 is removed by mistake, though it's hard to pinpoint the exact flow. The WARN_ON in this patch should help to find it.

---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 4 ++++
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 6 ++++++
 2 files changed, 10 insertions(+)
drivers/net/wireless/intel/iwlwifi/mvm/ops.c +4 -0
index 0d1118f66f0d5..cea8e397fe0f2 100644
@@ -845,6 +845,10 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	if (!mvm->scan_cmd)
 		goto out_free;
 
+	/* invalidate ids to prevent accidental removal of sta_id 0 */
+	mvm->aux_sta.sta_id = IWL_MVM_INVALID_STA;
+	mvm->snif_sta.sta_id = IWL_MVM_INVALID_STA;
+
 	/* Set EBS as successful as long as not stated otherwise by the FW. */
 	mvm->last_ebs_successful = true;
 
drivers/net/wireless/intel/iwlwifi/mvm/sta.c +6 -0
index 799d8219463cb..a66a5c19474a9 100644
@@ -2103,6 +2103,9 @@ int iwl_mvm_rm_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (WARN_ON_ONCE(mvm->snif_sta.sta_id == IWL_MVM_INVALID_STA))
+		return -EINVAL;
+
 	iwl_mvm_disable_txq(mvm, NULL, mvm->snif_queue, IWL_MAX_TID_COUNT, 0);
 	ret = iwl_mvm_rm_sta_common(mvm, mvm->snif_sta.sta_id);
 	if (ret)
@@ -2117,6 +2120,9 @@ int iwl_mvm_rm_aux_sta(struct iwl_mvm *mvm)
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (WARN_ON_ONCE(mvm->aux_sta.sta_id == IWL_MVM_INVALID_STA))
+		return -EINVAL;
+
 	iwl_mvm_disable_txq(mvm, NULL, mvm->aux_queue, IWL_MAX_TID_COUNT, 0);
 	ret = iwl_mvm_rm_sta_common(mvm, mvm->aux_sta.sta_id);
 	if (ret)
Signature · 1 line
2.27.0
author maintainer
#54 lore raw

PATCH 54/54 squashfs: add more sanity checks in xattr id lookup

In reply to Greg Kroah-Hartman

From: Phillip Lougher <[email protected]>

commit 506220d2ba21791314af569211ffd8870b8208fa upstream.

Sysbot has reported a warning where a kmalloc() attempt exceeds the maximum limit. This has been identified as corruption of the xattr_ids count when reading the xattr id lookup table.

This patch adds a number of additional sanity checks to detect this corruption and others.

1. It checks for a corrupted xattr index read from the inode. This could be because the metadata block is uncompressed, or because the "compression" bit has been corrupted (turning a compressed block into an uncompressed block). This would cause an out of bounds read.

2. It checks against corruption of the xattr_ids count. This can either lead to the above kmalloc failure, or a smaller than expected table to be read.

3. It checks the contents of the index table for corruption.

---
 fs/squashfs/xattr_id.c |   66 ++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 57 insertions(+), 9 deletions(-)
fs/squashfs/xattr_id.c +57 -9
@@ -31,10 +31,15 @@ int squashfs_xattr_lookup(struct super_b
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
 	int block = SQUASHFS_XATTR_BLOCK(index);
 	int offset = SQUASHFS_XATTR_BLOCK_OFFSET(index);
-	u64 start_block = le64_to_cpu(msblk->xattr_id_table[block]);
+	u64 start_block;
 	struct squashfs_xattr_id id;
 	int err;
 
+	if (index >= msblk->xattr_ids)
+		return -EINVAL;
+
+	start_block = le64_to_cpu(msblk->xattr_id_table[block]);
+
 	err = squashfs_read_metadata(sb, &id, &start_block, &offset,
 							sizeof(id));
 	if (err < 0)
@@ -50,13 +55,17 @@ int squashfs_xattr_lookup(struct super_b
 /*
  * Read uncompressed xattr id lookup table indexes from disk into memory
  */
-__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start,
+__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
 		u64 *xattr_table_start, int *xattr_ids)
 {
-	unsigned int len;
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	unsigned int len, indexes;
 	struct squashfs_xattr_id_table *id_table;
+	__le64 *table;
+	u64 start, end;
+	int n;
 
-	id_table = squashfs_read_table(sb, start, sizeof(*id_table));
+	id_table = squashfs_read_table(sb, table_start, sizeof(*id_table));
 	if (IS_ERR(id_table))
 		return (__le64 *) id_table;
 
@@ -70,13 +79,52 @@ __le64 *squashfs_read_xattr_id_table(str
 	if (*xattr_ids == 0)
 		return ERR_PTR(-EINVAL);
 
-	/* xattr_table should be less than start */
-	if (*xattr_table_start >= start)
+	len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids);
+	indexes = SQUASHFS_XATTR_BLOCKS(*xattr_ids);
+
+	/*
+	 * The computed size of the index table (len bytes) should exactly
+	 * match the table start and end points
+	 */
+	start = table_start + sizeof(*id_table);
+	end = msblk->bytes_used;
+
+	if (len != (end - start))
 		return ERR_PTR(-EINVAL);
 
-	len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids);
+	table = squashfs_read_table(sb, start, len);
+	if (IS_ERR(table))
+		return table;
+
+	/* table[0], table[1], ... table[indexes - 1] store the locations
+	 * of the compressed xattr id blocks.  Each entry should be less than
+	 * the next (i.e. table[0] < table[1]), and the difference between them
+	 * should be SQUASHFS_METADATA_SIZE or less.  table[indexes - 1]
+	 * should be less than table_start, and again the difference
+	 * shouls be SQUASHFS_METADATA_SIZE or less.
+	 *
+	 * Finally xattr_table_start should be less than table[0].
+	 */
+	for (n = 0; n < (indexes - 1); n++) {
+		start = le64_to_cpu(table[n]);
+		end = le64_to_cpu(table[n + 1]);
+
+		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+			kfree(table);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	start = le64_to_cpu(table[indexes - 1]);
+	if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) {
+		kfree(table);
+		return ERR_PTR(-EINVAL);
+	}
 
-	TRACE("In read_xattr_index_table, length %d\n", len);
+	if (*xattr_table_start >= le64_to_cpu(table[0])) {
+		kfree(table);
+		return ERR_PTR(-EINVAL);
+	}
 
-	return squashfs_read_table(sb, start + sizeof(*id_table), len);
+	return table;
 }
author maintainer
#39 lore raw

PATCH 39/54 SUNRPC: Move simple_get_bytes and simple_get_netobj into private header

In reply to Greg Kroah-Hartman

From: Dave Wysochanski <[email protected]>

[ Upstream commit ba6dfce47c4d002d96cd02a304132fca76981172 ]

Remove duplicated helper functions to parse opaque XDR objects and place inside new file net/sunrpc/auth_gss/auth_gss_internal.h. In the new file carry the license and copyright from the source file net/sunrpc/auth_gss/auth_gss.c. Finally, update the comment inside include/linux/sunrpc/xdr.h since lockd is not the only user of struct xdr_netobj.

---
 include/linux/sunrpc/xdr.h              |  3 +-
 net/sunrpc/auth_gss/auth_gss.c          | 30 +-----------------
 net/sunrpc/auth_gss/auth_gss_internal.h | 42 +++++++++++++++++++++++++
 net/sunrpc/auth_gss/gss_krb5_mech.c     | 31 ++----------------
 4 files changed, 46 insertions(+), 60 deletions(-)
 create mode 100644 net/sunrpc/auth_gss/auth_gss_internal.h
include/linux/sunrpc/xdr.h +1 -2
index 9548d075e06da..b998e4b736912 100644
@@ -25,8 +25,7 @@ struct rpc_rqst;
 #define XDR_QUADLEN(l)		(((l) + 3) >> 2)
 
 /*
- * Generic opaque `network object.' At the kernel level, this type
- * is used only by lockd.
+ * Generic opaque `network object.'
  */
 #define XDR_MAX_NETOBJ		1024
 struct xdr_netobj {
net/sunrpc/auth_gss/auth_gss.c +1 -29
index 4ecc2a9595674..5f42aa5fc6128 100644
@@ -29,6 +29,7 @@
 #include <linux/uaccess.h>
 #include <linux/hashtable.h>
 
+#include "auth_gss_internal.h"
 #include "../netns.h"
 
 #include <trace/events/rpcgss.h>
@@ -125,35 +126,6 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx)
 	clear_bit(RPCAUTH_CRED_NEW, &cred->cr_flags);
 }
 
-static const void *
-simple_get_bytes(const void *p, const void *end, void *res, size_t len)
-{
-	const void *q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	memcpy(res, p, len);
-	return q;
-}
-
-static inline const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
-{
-	const void *q;
-	unsigned int len;
-
-	p = simple_get_bytes(p, end, &len, sizeof(len));
-	if (IS_ERR(p))
-		return p;
-	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);
-	dest->len = len;
-	return q;
-}
-
 static struct gss_cl_ctx *
 gss_cred_get_ctx(struct rpc_cred *cred)
 {
net/sunrpc/auth_gss/auth_gss_internal.h new file +42 -0

42 lines not on this page · raw message

net/sunrpc/auth_gss/gss_krb5_mech.c +2 -29
index ae9acf3a73898..1c092b05c2bba 100644
@@ -21,6 +21,8 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/gss_krb5_enctypes.h>
 
+#include "auth_gss_internal.h"
+
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
@@ -143,35 +145,6 @@ get_gss_krb5_enctype(int etype)
 	return NULL;
 }
 
-static const void *
-simple_get_bytes(const void *p, const void *end, void *res, int len)
-{
-	const void *q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	memcpy(res, p, len);
-	return q;
-}
-
-static const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
-{
-	const void *q;
-	unsigned int len;
-
-	p = simple_get_bytes(p, end, &len, sizeof(len));
-	if (IS_ERR(p))
-		return p;
-	q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	res->data = kmemdup(p, len, GFP_NOFS);
-	if (unlikely(res->data == NULL))
-		return ERR_PTR(-ENOMEM);
-	res->len = len;
-	return q;
-}
-
 static inline const void *
 get_key(const void *p, const void *end,
 	struct krb5_ctx *ctx, struct crypto_sync_skcipher **res)
Signature · 1 line
2.27.0
author maintainer
#36 lore raw

PATCH 36/54 iwlwifi: pcie: add rules to match Qu with Hr2

In reply to Greg Kroah-Hartman

From: Luca Coelho <[email protected]>

[ Upstream commit 16062c12edb8ed2dfb15e6a914ff4edf858ab9e0 ]

Until now we have been relying on matching the PCI ID and subsystem device ID in order to recognize Qu devices with Hr2. Add rules to match these devices, so that we don't have to add a new rule for every new ID we get.

---
 .../net/wireless/intel/iwlwifi/cfg/22000.c    | 25 +++++++++++++++++++
 .../net/wireless/intel/iwlwifi/iwl-config.h   |  3 +++
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 10 ++++++++
 3 files changed, 38 insertions(+)
drivers/net/wireless/intel/iwlwifi/cfg/22000.c +25 -0
index d2bbe6a735142..92c50efd48fc3 100644
@@ -358,6 +358,7 @@ const struct iwl_cfg_trans_params iwl_ma_trans_cfg = {
 const char iwl_ax101_name[] = "Intel(R) Wi-Fi 6 AX101";
 const char iwl_ax200_name[] = "Intel(R) Wi-Fi 6 AX200 160MHz";
 const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz";
+const char iwl_ax203_name[] = "Intel(R) Wi-Fi 6 AX203";
 const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6 AX211 160MHz";
 const char iwl_ax411_name[] = "Intel(R) Wi-Fi 6 AX411 160MHz";
 const char iwl_ma_name[] = "Intel(R) Wi-Fi 6";
@@ -384,6 +385,18 @@ const struct iwl_cfg iwl_qu_b0_hr1_b0 = {
 	.num_rbds = IWL_NUM_RBDS_22000_HE,
 };
 
+const struct iwl_cfg iwl_qu_b0_hr_b0 = {
+	.fw_name_pre = IWL_QU_B_HR_B_FW_PRE,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
+	.num_rbds = IWL_NUM_RBDS_22000_HE,
+};
+
 const struct iwl_cfg iwl_ax201_cfg_qu_hr = {
 	.name = "Intel(R) Wi-Fi 6 AX201 160MHz",
 	.fw_name_pre = IWL_QU_B_HR_B_FW_PRE,
@@ -410,6 +423,18 @@ const struct iwl_cfg iwl_qu_c0_hr1_b0 = {
 	.num_rbds = IWL_NUM_RBDS_22000_HE,
 };
 
+const struct iwl_cfg iwl_qu_c0_hr_b0 = {
+	.fw_name_pre = IWL_QU_C_HR_B_FW_PRE,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
+	.num_rbds = IWL_NUM_RBDS_22000_HE,
+};
+
 const struct iwl_cfg iwl_ax201_cfg_qu_c0_hr_b0 = {
 	.name = "Intel(R) Wi-Fi 6 AX201 160MHz",
 	.fw_name_pre = IWL_QU_C_HR_B_FW_PRE,
drivers/net/wireless/intel/iwlwifi/iwl-config.h +3 -0
index e82e3fc963be2..9b91aa9b2e7f1 100644
@@ -544,6 +544,7 @@ extern const char iwl9260_killer_1550_name[];
 extern const char iwl9560_killer_1550i_name[];
 extern const char iwl9560_killer_1550s_name[];
 extern const char iwl_ax200_name[];
+extern const char iwl_ax203_name[];
 extern const char iwl_ax201_name[];
 extern const char iwl_ax101_name[];
 extern const char iwl_ax200_killer_1650w_name[];
@@ -627,6 +628,8 @@ extern const struct iwl_cfg iwl9560_2ac_cfg_soc;
 extern const struct iwl_cfg iwl_qu_b0_hr1_b0;
 extern const struct iwl_cfg iwl_qu_c0_hr1_b0;
 extern const struct iwl_cfg iwl_quz_a0_hr1_b0;
+extern const struct iwl_cfg iwl_qu_b0_hr_b0;
+extern const struct iwl_cfg iwl_qu_c0_hr_b0;
 extern const struct iwl_cfg iwl_ax200_cfg_cc;
 extern const struct iwl_cfg iwl_ax201_cfg_qu_hr;
 extern const struct iwl_cfg iwl_ax201_cfg_qu_hr;
drivers/net/wireless/intel/iwlwifi/pcie/drv.c +10 -0
index 7b5ece380fbfb..2823a1e81656d 100644
@@ -966,6 +966,11 @@ static const struct iwl_dev_info iwl_dev_info_table[] = {
 		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_qu_b0_hr1_b0, iwl_ax101_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
+		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_qu_b0_hr_b0, iwl_ax203_name),
 
 	/* Qu C step */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
@@ -973,6 +978,11 @@ static const struct iwl_dev_info iwl_dev_info_table[] = {
 		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_qu_c0_hr1_b0, iwl_ax101_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
+		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_qu_c0_hr_b0, iwl_ax203_name),
 
 	/* QuZ */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
Signature · 1 line
2.27.0
author maintainer
#52 lore raw

PATCH 52/54 squashfs: add more sanity checks in id lookup

In reply to Greg Kroah-Hartman

From: Phillip Lougher <[email protected]>

commit f37aa4c7366e23f91b81d00bafd6a7ab54e4a381 upstream.

Sysbot has reported a number of "slab-out-of-bounds reads" and "use-after-free read" errors which has been identified as being caused by a corrupted index value read from the inode. This could be because the metadata block is uncompressed, or because the "compression" bit has been corrupted (turning a compressed block into an uncompressed block).

This patch adds additional sanity checks to detect this, and the following corruption.

1. It checks against corruption of the ids count. This can either lead to a larger table to be read, or a smaller than expected table to be read.

In the case of a too large ids count, this would often have been trapped by the existing sanity checks, but this patch introduces a more exact check, which can identify too small values.

2. It checks the contents of the index table for corruption.

---
 fs/squashfs/id.c             |   40 ++++++++++++++++++++++++++++++++--------
 fs/squashfs/squashfs_fs_sb.h |    1 +
 fs/squashfs/super.c          |    6 +++---
 fs/squashfs/xattr.h          |   10 +++++++++-
 4 files changed, 45 insertions(+), 12 deletions(-)
fs/squashfs/id.c +32 -8
@@ -35,10 +35,15 @@ int squashfs_get_id(struct super_block *
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
 	int block = SQUASHFS_ID_BLOCK(index);
 	int offset = SQUASHFS_ID_BLOCK_OFFSET(index);
-	u64 start_block = le64_to_cpu(msblk->id_table[block]);
+	u64 start_block;
 	__le32 disk_id;
 	int err;
 
+	if (index >= msblk->ids)
+		return -EINVAL;
+
+	start_block = le64_to_cpu(msblk->id_table[block]);
+
 	err = squashfs_read_metadata(sb, &disk_id, &start_block, &offset,
 							sizeof(disk_id));
 	if (err < 0)
@@ -56,7 +61,10 @@ __le64 *squashfs_read_id_index_table(str
 		u64 id_table_start, u64 next_table, unsigned short no_ids)
 {
 	unsigned int length = SQUASHFS_ID_BLOCK_BYTES(no_ids);
+	unsigned int indexes = SQUASHFS_ID_BLOCKS(no_ids);
+	int n;
 	__le64 *table;
+	u64 start, end;
 
 	TRACE("In read_id_index_table, length %d\n", length);
 
@@ -67,20 +75,36 @@ __le64 *squashfs_read_id_index_table(str
 		return ERR_PTR(-EINVAL);
 
 	/*
-	 * length bytes should not extend into the next table - this check
-	 * also traps instances where id_table_start is incorrectly larger
-	 * than the next table start
+	 * The computed size of the index table (length bytes) should exactly
+	 * match the table start and end points
 	 */
-	if (id_table_start + length > next_table)
+	if (length != (next_table - id_table_start))
 		return ERR_PTR(-EINVAL);
 
 	table = squashfs_read_table(sb, id_table_start, length);
+	if (IS_ERR(table))
+		return table;
 
 	/*
-	 * table[0] points to the first id lookup table metadata block, this
-	 * should be less than id_table_start
+	 * table[0], table[1], ... table[indexes - 1] store the locations
+	 * of the compressed id blocks.   Each entry should be less than
+	 * the next (i.e. table[0] < table[1]), and the difference between them
+	 * should be SQUASHFS_METADATA_SIZE or less.  table[indexes - 1]
+	 * should be less than id_table_start, and again the difference
+	 * should be SQUASHFS_METADATA_SIZE or less
 	 */
-	if (!IS_ERR(table) && le64_to_cpu(table[0]) >= id_table_start) {
+	for (n = 0; n < (indexes - 1); n++) {
+		start = le64_to_cpu(table[n]);
+		end = le64_to_cpu(table[n + 1]);
+
+		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+			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) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}
fs/squashfs/squashfs_fs_sb.h +1 -0
@@ -64,5 +64,6 @@ struct squashfs_sb_info {
 	unsigned int				inodes;
 	unsigned int				fragments;
 	int					xattr_ids;
+	unsigned int				ids;
 };
 #endif
fs/squashfs/super.c +3 -3
@@ -166,6 +166,7 @@ static int squashfs_fill_super(struct su
 	msblk->directory_table = le64_to_cpu(sblk->directory_table_start);
 	msblk->inodes = le32_to_cpu(sblk->inodes);
 	msblk->fragments = le32_to_cpu(sblk->fragments);
+	msblk->ids = le16_to_cpu(sblk->no_ids);
 	flags = le16_to_cpu(sblk->flags);
 
 	TRACE("Found valid superblock on %pg\n", sb->s_bdev);
@@ -177,7 +178,7 @@ static int squashfs_fill_super(struct su
 	TRACE("Block size %d\n", msblk->block_size);
 	TRACE("Number of inodes %d\n", msblk->inodes);
 	TRACE("Number of fragments %d\n", msblk->fragments);
-	TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids));
+	TRACE("Number of ids %d\n", msblk->ids);
 	TRACE("sblk->inode_table_start %llx\n", msblk->inode_table);
 	TRACE("sblk->directory_table_start %llx\n", msblk->directory_table);
 	TRACE("sblk->fragment_table_start %llx\n",
@@ -236,8 +237,7 @@ static int squashfs_fill_super(struct su
 allocate_id_index_table:
 	/* Allocate and read id index table */
 	msblk->id_table = squashfs_read_id_index_table(sb,
-		le64_to_cpu(sblk->id_table_start), next_table,
-		le16_to_cpu(sblk->no_ids));
+		le64_to_cpu(sblk->id_table_start), next_table, msblk->ids);
 	if (IS_ERR(msblk->id_table)) {
 		errorf(fc, "unable to read id index table");
 		err = PTR_ERR(msblk->id_table);
fs/squashfs/xattr.h +9 -1
@@ -17,8 +17,16 @@ extern int squashfs_xattr_lookup(struct
 static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb,
 		u64 start, u64 *xattr_table_start, int *xattr_ids)
 {
+	struct squashfs_xattr_id_table *id_table;
+
+	id_table = squashfs_read_table(sb, start, sizeof(*id_table));
+	if (IS_ERR(id_table))
+		return (__le64 *) id_table;
+
+	*xattr_table_start = le64_to_cpu(id_table->xattr_table_start);
+	kfree(id_table);
+
 	ERROR("Xattrs in filesystem, these will be ignored\n");
-	*xattr_table_start = start;
 	return ERR_PTR(-ENOTSUPP);
 }
 
author maintainer
#37 lore raw

PATCH 37/54 iwlwifi: mvm: guard against device removal in reprobe

In reply to Greg Kroah-Hartman

From: Johannes Berg <[email protected]>

[ 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.

---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/mvm/ops.c +2 -1
index cea8e397fe0f2..cb83490f1016f 100644
@@ -1249,6 +1249,7 @@ 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);
 }
@@ -1299,7 +1300,7 @@ 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 (test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED,
Signature · 1 line
2.27.0
author maintainer
#33 lore raw

PATCH 33/54 iwlwifi: pcie: add a NULL check in iwl_pcie_txq_unmap

In reply to Greg Kroah-Hartman

From: Emmanuel Grumbach <[email protected]>

[ Upstream commit 98c7d21f957b10d9c07a3a60a3a5a8f326a197e5 ]

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

---
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 5 +++++
 1 file changed, 5 insertions(+)
drivers/net/wireless/intel/iwlwifi/pcie/tx.c +5 -0
index 966be5689d63a..ed54d04e43964 100644
@@ -299,6 +299,11 @@ 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->txqs.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",
Signature · 1 line
2.27.0
author maintainer
#38 lore raw

PATCH 38/54 iwlwifi: queue: bail out on invalid freeing

In reply to Greg Kroah-Hartman

From: Johannes Berg <[email protected]>

[ Upstream commit 0bed6a2a14afaae240cc431e49c260568488b51c ]

If we find an entry without an SKB, we currently continue, but that will just result in an infinite loop since we won't increment the read pointer, and will try the same thing over and over again. Fix this.

---
 drivers/net/wireless/intel/iwlwifi/queue/tx.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)
drivers/net/wireless/intel/iwlwifi/queue/tx.c +2 -4
index af0b27a68d84d..9181221a2434d 100644
@@ -887,10 +887,8 @@ void iwl_txq_gen2_unmap(struct iwl_trans *trans, int txq_id)
 			int idx = iwl_txq_get_cmd_index(txq, txq->read_ptr);
 			struct sk_buff *skb = txq->entries[idx].skb;
 
-			if (WARN_ON_ONCE(!skb))
-				continue;
-
-			iwl_txq_free_tso_page(trans, skb);
+			if (!WARN_ON_ONCE(!skb))
+				iwl_txq_free_tso_page(trans, skb);
 		}
 		iwl_txq_gen2_free_tfd(trans, txq);
 		txq->read_ptr = iwl_txq_inc_wrap(trans, txq->read_ptr);
Signature · 1 line
2.27.0
author maintainer
#34 lore raw

PATCH 34/54 iwlwifi: pcie: fix context info memory leak

In reply to Greg Kroah-Hartman

From: Johannes Berg <[email protected]>

[ Upstream commit 2d6bc752cc2806366d9a4fd577b3f6c1f7a7e04e ]

If the image loader allocation fails, we leak all the previously allocated memory. Fix this.

---
 .../net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c  | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +9 -2
index d719e433a59bf..2d43899fbdd7a 100644
@@ -245,8 +245,10 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 	/* Allocate IML */
 	iml_img = dma_alloc_coherent(trans->dev, trans->iml_len,
 				     &trans_pcie->iml_dma_addr, GFP_KERNEL);
-	if (!iml_img)
-		return -ENOMEM;
+	if (!iml_img) {
+		ret = -ENOMEM;
+		goto err_free_ctxt_info;
+	}
 
 	memcpy(iml_img, trans->iml, trans->iml_len);
 
@@ -284,6 +286,11 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 
 	return 0;
 
+err_free_ctxt_info:
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_gen3),
+			  trans_pcie->ctxt_info_gen3,
+			  trans_pcie->ctxt_info_dma_addr);
+	trans_pcie->ctxt_info_gen3 = NULL;
 err_free_prph_info:
 	dma_free_coherent(trans->dev,
 			  sizeof(*prph_info),
Signature · 1 line
2.27.0
author maintainer
#2 lore raw

PATCH 2/54 io_uring: add a {task,files} pair matching helper

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit 08d23634643c239ddae706758f54d3a8e0c24962 ]

Add io_match_task() that matches both task and files.

---
 fs/io_uring.c |   63 +++++++++++++++++++++++++++++-----------------------------
 1 file changed, 32 insertions(+), 31 deletions(-)
fs/io_uring.c +32 -31
@@ -997,6 +997,36 @@ static inline void io_clean_op(struct io
 		__io_clean_op(req);
 }
 
+static inline bool __io_match_files(struct io_kiocb *req,
+				    struct files_struct *files)
+{
+	return ((req->flags & REQ_F_WORK_INITIALIZED) &&
+	        (req->work.flags & IO_WQ_WORK_FILES)) &&
+		req->work.identity->files == files;
+}
+
+static bool io_match_task(struct io_kiocb *head,
+			  struct task_struct *task,
+			  struct files_struct *files)
+{
+	struct io_kiocb *link;
+
+	if (task && head->task != task)
+		return false;
+	if (!files)
+		return true;
+	if (__io_match_files(head, files))
+		return true;
+	if (head->flags & REQ_F_LINK_HEAD) {
+		list_for_each_entry(link, &head->link_list, link_list) {
+			if (__io_match_files(link, files))
+				return true;
+		}
+	}
+	return false;
+}
+
+
 static void io_sq_thread_drop_mm(void)
 {
 	struct mm_struct *mm = current->mm;
@@ -1612,32 +1642,6 @@ static void io_cqring_mark_overflow(stru
 	}
 }
 
-static inline bool __io_match_files(struct io_kiocb *req,
-				    struct files_struct *files)
-{
-	return ((req->flags & REQ_F_WORK_INITIALIZED) &&
-	        (req->work.flags & IO_WQ_WORK_FILES)) &&
-		req->work.identity->files == files;
-}
-
-static bool io_match_files(struct io_kiocb *req,
-			   struct files_struct *files)
-{
-	struct io_kiocb *link;
-
-	if (!files)
-		return true;
-	if (__io_match_files(req, files))
-		return true;
-	if (req->flags & REQ_F_LINK_HEAD) {
-		list_for_each_entry(link, &req->link_list, link_list) {
-			if (__io_match_files(link, files))
-				return true;
-		}
-	}
-	return false;
-}
-
 /* Returns true if there are no backlogged entries after the flush */
 static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
 				       struct task_struct *tsk,
@@ -1659,9 +1663,7 @@ static bool __io_cqring_overflow_flush(s
 
 	cqe = NULL;
 	list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) {
-		if (tsk && req->task != tsk)
-			continue;
-		if (!io_match_files(req, files))
+		if (!io_match_task(req, tsk, files))
 			continue;
 
 		cqe = io_get_cqring(ctx);
@@ -8635,8 +8637,7 @@ static void io_cancel_defer_files(struct
 
 	spin_lock_irq(&ctx->completion_lock);
 	list_for_each_entry_reverse(de, &ctx->defer_list, list) {
-		if (io_task_match(de->req, task) &&
-		    io_match_files(de->req, files)) {
+		if (io_match_task(de->req, task, files)) {
 			list_cut_position(&list, &ctx->defer_list, &de->list);
 			break;
 		}
author maintainer
#19 lore raw

PATCH 19/54 af_key: relax availability checks for skb size calculation

In reply to Greg Kroah-Hartman

From: Cong Wang <[email protected]>

[ Upstream commit afbc293add6466f8f3f0c3d944d85f53709c170f ]

xfrm_probe_algs() probes kernel crypto modules and changes the availability of struct xfrm_algo_desc. But there is a small window where ealg->available and aalg->available get changed between count_ah_combs()/count_esp_combs() and dump_ah_combs()/dump_esp_combs(), in this case we may allocate a smaller skb but later put a larger amount of data and trigger the panic in skb_put().

Fix this by relaxing the checks when counting the size, that is, skipping the test of ->available. We may waste some memory for a few of sizeof(struct sadb_comb), but it is still much better than a panic.

---
 net/key/af_key.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
net/key/af_key.c +3 -3
index c12dbc51ef5fe..ef9b4ac03e7b7 100644
@@ -2902,7 +2902,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t)
 			break;
 		if (!aalg->pfkey_supported)
 			continue;
-		if (aalg_tmpl_set(t, aalg) && aalg->available)
+		if (aalg_tmpl_set(t, aalg))
 			sz += sizeof(struct sadb_comb);
 	}
 	return sz + sizeof(struct sadb_prop);
@@ -2920,7 +2920,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 		if (!ealg->pfkey_supported)
 			continue;
 
-		if (!(ealg_tmpl_set(t, ealg) && ealg->available))
+		if (!(ealg_tmpl_set(t, ealg)))
 			continue;
 
 		for (k = 1; ; k++) {
@@ -2931,7 +2931,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 			if (!aalg->pfkey_supported)
 				continue;
 
-			if (aalg_tmpl_set(t, aalg) && aalg->available)
+			if (aalg_tmpl_set(t, aalg))
 				sz += sizeof(struct sadb_comb);
 		}
 	}
Signature · 1 line
2.27.0
author maintainer
#21 lore raw

PATCH 21/54 ASoC: wm_adsp: Fix control name parsing for multi-fw

In reply to Greg Kroah-Hartman

From: James Schulman <[email protected]>

[ Upstream commit a8939f2e138e418c2b059056ff5b501eaf2eae54 ]

When switching between firmware types, the wrong control can be selected when requesting control in kernel API. Use the currently selected DSP firwmare type to select the proper mixer control.

---
 sound/soc/codecs/wm_adsp.c | 3 +++
 1 file changed, 3 insertions(+)
sound/soc/codecs/wm_adsp.c +3 -0
index dec8716aa8ef5..985b2dcecf138 100644
@@ -2031,11 +2031,14 @@ static struct wm_coeff_ctl *wm_adsp_get_ctl(struct wm_adsp *dsp,
 					     unsigned int alg)
 {
 	struct wm_coeff_ctl *pos, *rslt = NULL;
+	const char *fw_txt = wm_adsp_fw_text[dsp->fw];
 
 	list_for_each_entry(pos, &dsp->ctl_list, list) {
 		if (!pos->subname)
 			continue;
 		if (strncmp(pos->subname, name, pos->subname_len) == 0 &&
+		    strncmp(pos->fw_name, fw_txt,
+			    SNDRV_CTL_ELEM_ID_NAME_MAXLEN) == 0 &&
 				pos->alg_region.alg == alg &&
 				pos->alg_region.type == type) {
 			rslt = pos;
Signature · 1 line
2.27.0
author maintainer
#24 lore raw

PATCH 24/54 ASoC: Intel: Skylake: Zero snd_ctl_elem_value

In reply to Greg Kroah-Hartman

From: Ricardo Ribalda <[email protected]>

[ Upstream commit 1d8fe0648e118fd495a2cb393a34eb8d428e7808 ]

Clear struct snd_ctl_elem_value before calling ->put() to avoid any data leak.

---
 sound/soc/intel/skylake/skl-topology.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
sound/soc/intel/skylake/skl-topology.c +1 -1
index d699e61eca3d0..0955cbb4e9187 100644
@@ -3632,7 +3632,7 @@ static void skl_tplg_complete(struct snd_soc_component *component)
 		sprintf(chan_text, "c%d", mach->mach_params.dmic_num);
 
 		for (i = 0; i < se->items; i++) {
-			struct snd_ctl_elem_value val;
+			struct snd_ctl_elem_value val = {};
 
 			if (strstr(texts[i], chan_text)) {
 				val.value.enumerated.item[0] = i;
Signature · 1 line
2.27.0
author maintainer
#1 lore raw

PATCH 1/54 io_uring: simplify io_task_match()

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit 06de5f5973c641c7ae033f133ecfaaf64fe633a6 ]

If IORING_SETUP_SQPOLL is set all requests belong to the corresponding SQPOLL task, so skip task checking in that case and always match.

---
 fs/io_uring.c |    6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)
fs/io_uring.c +1 -5
@@ -1472,11 +1472,7 @@ static bool io_task_match(struct io_kioc
 
 	if (!tsk || req->task == tsk)
 		return true;
-	if (ctx->flags & IORING_SETUP_SQPOLL) {
-		if (ctx->sq_data && req->task == ctx->sq_data->thread)
-			return true;
-	}
-	return false;
+	return (ctx->flags & IORING_SETUP_SQPOLL);
 }
 
 /*
author maintainer
#17 lore raw

PATCH 17/54 gpiolib: cdev: clear debounce period if line set to output

In reply to Greg Kroah-Hartman

From: Kent Gibson <[email protected]>

commit 03a58ea5905fdbd93ff9e52e670d802600ba38cd upstream.

When set_config changes a line from input to output debounce is implicitly disabled, as debounce makes no sense for outputs, but the debounce period is not being cleared and is still reported in the line info.

So clear the debounce period when the debouncer is stopped in edge_detector_stop().

Fixes 65cff7046406 ("gpiolib: cdev: support setting debounce")
---
 drivers/gpio/gpiolib-cdev.c |    2 ++
 1 file changed, 2 insertions(+)
drivers/gpio/gpiolib-cdev.c +2 -0
@@ -756,6 +756,8 @@ static void edge_detector_stop(struct li
 	cancel_delayed_work_sync(&line->work);
 	WRITE_ONCE(line->sw_debounced, 0);
 	line->eflags = 0;
+	if (line->desc)
+		WRITE_ONCE(line->desc->debounce_period_us, 0);
 	/* do not change line->level - see comment in debounced_value() */
 }
 
author maintainer
#25 lore raw

PATCH 25/54 chtls: Fix potential resource leak

In reply to Greg Kroah-Hartman

From: Pan Bian <[email protected]>

[ Upstream commit b6011966ac6f402847eb5326beee8da3a80405c7 ]

The dst entry should be released if no neighbour is found. Goto label free_dst to fix the issue. Besides, the check of ndev against NULL is redundant.

---
 .../net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c    | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)
drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +3 -4
index 5beec901713fb..a262c949ed76b 100644
@@ -1158,11 +1158,9 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 #endif
 	}
 	if (!n || !n->dev)
-		goto free_sk;
+		goto free_dst;
 
 	ndev = n->dev;
-	if (!ndev)
-		goto free_dst;
 	if (is_vlan_dev(ndev))
 		ndev = vlan_dev_real_dev(ndev);
 
@@ -1249,7 +1247,8 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 free_csk:
 	chtls_sock_release(&csk->kref);
 free_dst:
-	neigh_release(n);
+	if (n)
+		neigh_release(n);
 	dst_release(dst);
 free_sk:
 	inet_csk_prepare_forced_close(newsk);
Signature · 1 line
2.27.0
author maintainer
#14 lore raw

PATCH 14/54 io_uring: fix sqo ownership false positive warning

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit 70b2c60d3797bffe182dddb9bb55975b9be5889a ]

WARNING: CPU: 0 PID: 21359 at fs/io_uring.c:9042
    io_uring_cancel_task_requests+0xe55/0x10c0 fs/io_uring.c:9042
Call Trace:
 io_uring_flush+0x47b/0x6e0 fs/io_uring.c:9227
 filp_close+0xb4/0x170 fs/open.c:1295
 close_files fs/file.c:403 [inline]
 put_files_struct fs/file.c:418 [inline]
 put_files_struct+0x1cc/0x350 fs/file.c:415
 exit_files+0x7e/0xa0 fs/file.c:435
 do_exit+0xc22/0x2ae0 kernel/exit.c:820
 do_group_exit+0x125/0x310 kernel/exit.c:922
 get_signal+0x427/0x20f0 kernel/signal.c:2773
 arch_do_signal_or_restart+0x2a8/0x1eb0 arch/x86/kernel/signal.c:811
 handle_signal_work kernel/entry/common.c:147 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0x148/0x250 kernel/entry/common.c:201
 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline]
 syscall_exit_to_user_mode+0x19/0x50 kernel/entry/common.c:302
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Now io_uring_cancel_task_requests() can be called not through file notes but directly, remove a WARN_ONCE() there that give us false positives. That check is not very important and we catch it in other places.

Fixes 84965ff8a84f0 ("io_uring: if we see flush on exit, cancel related tasks")
Reported-by [email protected]
---
 fs/io_uring.c |    2 --
 1 file changed, 2 deletions(-)
fs/io_uring.c +0 -2
@@ -8683,8 +8683,6 @@ static void io_uring_cancel_task_request
 	struct task_struct *task = current;
 
 	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
-		/* for SQPOLL only sqo_task has task notes */
-		WARN_ON_ONCE(ctx->sqo_task != current);
 		io_disable_sqo_submit(ctx);
 		task = ctx->sq_data->thread;
 		atomic_inc(&task->io_uring->in_idle);
author maintainer
#11 lore raw

PATCH 11/54 io_uring: fix cancellation taking mutex while TASK_UNINTERRUPTIBLE

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit ca70f00bed6cb255b7a9b91aa18a2717c9217f70 ]

do not call blocking ops when !TASK_RUNNING; state=2 set at

	[<00000000ced9dbfc>] prepare_to_wait+0x1f4/0x3b0
	kernel/sched/wait.c:262
WARNING: CPU: 1 PID: 19888 at kernel/sched/core.c:7853
	__might_sleep+0xed/0x100 kernel/sched/core.c:7848
RIP: 0010:__might_sleep+0xed/0x100 kernel/sched/core.c:7848
Call Trace:
 __mutex_lock_common+0xc4/0x2ef0 kernel/locking/mutex.c:935
 __mutex_lock kernel/locking/mutex.c:1103 [inline]
 mutex_lock_nested+0x1a/0x20 kernel/locking/mutex.c:1118
 io_wq_submit_work+0x39a/0x720 fs/io_uring.c:6411
 io_run_cancel fs/io-wq.c:856 [inline]
 io_wqe_cancel_pending_work fs/io-wq.c:990 [inline]
 io_wq_cancel_cb+0x614/0xcb0 fs/io-wq.c:1027
 io_uring_cancel_files fs/io_uring.c:8874 [inline]
 io_uring_cancel_task_requests fs/io_uring.c:8952 [inline]
 __io_uring_files_cancel+0x115d/0x19e0 fs/io_uring.c:9038
 io_uring_files_cancel include/linux/io_uring.h:51 [inline]
 do_exit+0x2e6/0x2490 kernel/exit.c:780
 do_group_exit+0x168/0x2d0 kernel/exit.c:922
 get_signal+0x16b5/0x2030 kernel/signal.c:2770
 arch_do_signal_or_restart+0x8e/0x6a0 arch/x86/kernel/signal.c:811
 handle_signal_work kernel/entry/common.c:147 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0xac/0x1e0 kernel/entry/common.c:201
 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline]
 syscall_exit_to_user_mode+0x48/0x190 kernel/entry/common.c:302
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Rewrite io_uring_cancel_files() to mimic __io_uring_task_cancel()'s counting scheme, so it does all the heavy work before setting TASK_UNINTERRUPTIBLE.

Reported-by [email protected]
[axboe: fix inverted task check]
---
 fs/io_uring.c |   39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)
fs/io_uring.c +22 -17
@@ -8586,30 +8586,31 @@ static void io_cancel_defer_files(struct
 	}
 }
 
+static int io_uring_count_inflight(struct io_ring_ctx *ctx,
+				   struct task_struct *task,
+				   struct files_struct *files)
+{
+	struct io_kiocb *req;
+	int cnt = 0;
+
+	spin_lock_irq(&ctx->inflight_lock);
+	list_for_each_entry(req, &ctx->inflight_list, inflight_entry)
+		cnt += io_match_task(req, task, files);
+	spin_unlock_irq(&ctx->inflight_lock);
+	return cnt;
+}
+
 static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 				  struct task_struct *task,
 				  struct files_struct *files)
 {
 	while (!list_empty_careful(&ctx->inflight_list)) {
 		struct io_task_cancel cancel = { .task = task, .files = files };
-		struct io_kiocb *req;
 		DEFINE_WAIT(wait);
-		bool found = false;
+		int inflight;
 
-		spin_lock_irq(&ctx->inflight_lock);
-		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
-			if (!io_match_task(req, task, files))
-				continue;
-			found = true;
-			break;
-		}
-		if (found)
-			prepare_to_wait(&task->io_uring->wait, &wait,
-					TASK_UNINTERRUPTIBLE);
-		spin_unlock_irq(&ctx->inflight_lock);
-
-		/* We need to keep going until we don't find a matching req */
-		if (!found)
+		inflight = io_uring_count_inflight(ctx, task, files);
+		if (!inflight)
 			break;
 
 		io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true);
@@ -8617,7 +8618,11 @@ static void io_uring_cancel_files(struct
 		io_kill_timeouts(ctx, task, files);
 		/* cancellations _may_ trigger task work */
 		io_run_task_work();
-		schedule();
+
+		prepare_to_wait(&task->io_uring->wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		if (inflight == io_uring_count_inflight(ctx, task, files))
+			schedule();
 		finish_wait(&task->io_uring->wait, &wait);
 	}
 }
author maintainer
#12 lore raw

PATCH 12/54 io_uring: fix flush cqring overflow list while TASK_INTERRUPTIBLE

In reply to Greg Kroah-Hartman

From: Hao Xu <[email protected]>

[ Upstream commit 6195ba09822c87cad09189bbf550d0fbe714687a ]

Abaci reported the follow warning:

[   27.073425] do not call blocking ops when !TASK_RUNNING; state=1 set at [] prepare_to_wait_exclusive+0x3a/0xc0
[   27.075805] WARNING: CPU: 0 PID: 951 at kernel/sched/core.c:7853 __might_sleep+0x80/0xa0
[   27.077604] Modules linked in:
[   27.078379] CPU: 0 PID: 951 Comm: a.out Not tainted 5.11.0-rc3+ #1
[   27.079637] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[   27.080852] RIP: 0010:__might_sleep+0x80/0xa0
[   27.081835] Code: 65 48 8b 04 25 80 71 01 00 48 8b 90 c0 15 00 00 48 8b 70 18 48 c7 c7 08 39 95 82 c6 05 f9 5f de 08 01 48 89 d1 e8 00 c6 fa ff  0b eb bf 41 0f b6 f5 48 c7 c7 40 23 c9 82 e8 f3 48 ec 00 eb a7
[   27.084521] RSP: 0018:ffffc90000fe3ce8 EFLAGS: 00010286
[   27.085350] RAX: 0000000000000000 RBX: ffffffff82956083 RCX: 0000000000000000
[   27.086348] RDX: ffff8881057a0000 RSI: ffffffff8118cc9e RDI: ffff88813bc28570
[   27.087598] RBP: 00000000000003a7 R08: 0000000000000001 R09: 0000000000000001
[   27.088819] R10: ffffc90000fe3e00 R11: 00000000fffef9f0 R12: 0000000000000000
[   27.089819] R13: 0000000000000000 R14: ffff88810576eb80 R15: ffff88810576e800
[   27.091058] FS:  00007f7b144cf740(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000
[   27.092775] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   27.093796] CR2: 00000000022da7b8 CR3: 000000010b928002 CR4: 00000000003706f0
[   27.094778] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   27.095780] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   27.097011] Call Trace:
[   27.097685]  __mutex_lock+0x5d/0xa30
[   27.098565]  ? prepare_to_wait_exclusive+0x71/0xc0
[   27.099412]  ? io_cqring_overflow_flush.part.101+0x6d/0x70
[   27.100441]  ? lockdep_hardirqs_on_prepare+0xe9/0x1c0
[   27.101537]  ? _raw_spin_unlock_irqrestore+0x2d/0x40
[   27.102656]  ? trace_hardirqs_on+0x46/0x110
[   27.103459]  ? io_cqring_overflow_flush.part.101+0x6d/0x70
[   27.104317]  io_cqring_overflow_flush.part.101+0x6d/0x70
[   27.105113]  io_cqring_wait+0x36e/0x4d0
[   27.105770]  ? find_held_lock+0x28/0xb0
[   27.106370]  ? io_uring_remove_task_files+0xa0/0xa0
[   27.107076]  __x64_sys_io_uring_enter+0x4fb/0x640
[   27.107801]  ? rcu_read_lock_sched_held+0x59/0xa0
[   27.108562]  ? lockdep_hardirqs_on_prepare+0xe9/0x1c0
[   27.109684]  ? syscall_enter_from_user_mode+0x26/0x70
[   27.110731]  do_syscall_64+0x2d/0x40
[   27.111296]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   27.112056] RIP: 0033:0x7f7b13dc8239
[   27.112663] Code: 01 00 48 81 c4 80 00 00 00 e9 f1 fe ff ff 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05  3d 01 f0 ff ff 73 01 c3 48 8b 0d 27 ec 2c 00 f7 d8 64 89 01 48
[   27.115113] RSP: 002b:00007ffd6d7f5c88 EFLAGS: 00000286 ORIG_RAX: 00000000000001aa
[   27.116562] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7b13dc8239
[   27.117961] RDX: 000000000000478e RSI: 0000000000000000 RDI: 0000000000000003
[   27.118925] RBP: 00007ffd6d7f5cb0 R08: 0000000020000040 R09: 0000000000000008
[   27.119773] R10: 0000000000000001 R11: 0000000000000286 R12: 0000000000400480
[   27.120614] R13: 00007ffd6d7f5d90 R14: 0000000000000000 R15: 0000000000000000
[   27.121490] irq event stamp: 5635
[   27.121946] hardirqs last  enabled at (5643): [] console_unlock+0x5c4/0x740
[   27.123476] hardirqs last disabled at (5652): [] console_unlock+0x4e7/0x740
[   27.125192] softirqs last  enabled at (5272): [] __do_softirq+0x3c5/0x5aa
[   27.126430] softirqs last disabled at (5267): [] asm_call_irq_on_stack+0xf/0x20
[   27.127634] ---[ end trace 289d7e28fa60f928 ]---

This is caused by calling io_cqring_overflow_flush() which may sleep after calling prepare_to_wait_exclusive() which set task state to TASK_INTERRUPTIBLE

Fixes 6c503150ae33 ("io_uring: patch up IOPOLL overflow_flush sync")
---
 fs/io_uring.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
fs/io_uring.c +6 -2
@@ -7000,14 +7000,18 @@ static int io_cqring_wait(struct io_ring
 						TASK_INTERRUPTIBLE);
 		/* make sure we run task_work before checking for signals */
 		ret = io_run_task_work_sig();
-		if (ret > 0)
+		if (ret > 0) {
+			finish_wait(&ctx->wait, &iowq.wq);
 			continue;
+		}
 		else if (ret < 0)
 			break;
 		if (io_should_wake(&iowq))
 			break;
-		if (test_bit(0, &ctx->cq_check_overflow))
+		if (test_bit(0, &ctx->cq_check_overflow)) {
+			finish_wait(&ctx->wait, &iowq.wq);
 			continue;
+		}
 		schedule();
 	} while (1);
 	finish_wait(&ctx->wait, &iowq.wq);
author maintainer
#13 lore raw

PATCH 13/54 io_uring: fix list corruption for splice file_get

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit f609cbb8911e40e15f9055e8f945f926ac906924 ]

kernel BUG at lib/list_debug.c:29!

Call Trace:
 __list_add include/linux/list.h:67 [inline]
 list_add include/linux/list.h:86 [inline]
 io_file_get+0x8cc/0xdb0 fs/io_uring.c:6466
 __io_splice_prep+0x1bc/0x530 fs/io_uring.c:3866
 io_splice_prep fs/io_uring.c:3920 [inline]
 io_req_prep+0x3546/0x4e80 fs/io_uring.c:6081
 io_queue_sqe+0x609/0x10d0 fs/io_uring.c:6628
 io_submit_sqe fs/io_uring.c:6705 [inline]
 io_submit_sqes+0x1495/0x2720 fs/io_uring.c:6953
 __do_sys_io_uring_enter+0x107d/0x1f30 fs/io_uring.c:9353
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

io_file_get() may be called from splice, and so REQ_F_INFLIGHT may already be set.

Fixes 02a13674fa0e8 ("io_uring: account io_uring internal files as REQ_F_INFLIGHT")
Reported-by [email protected]
---
 fs/io_uring.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
fs/io_uring.c +2 -1
@@ -6170,7 +6170,8 @@ static struct file *io_file_get(struct i
 		file = __io_file_get(state, fd);
 	}
 
-	if (file && file->f_op == &io_uring_fops) {
+	if (file && file->f_op == &io_uring_fops &&
+	    !(req->flags & REQ_F_INFLIGHT)) {
 		io_req_init_async(req);
 		req->flags |= REQ_F_INFLIGHT;
 
author maintainer
#16 lore raw

PATCH 16/54 io_uring: drop mm/files between task_work_submit

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit aec18a57edad562d620f7d19016de1fc0cc2208c ]

Since SQPOLL task can be shared and so task_work entries can be a mix of them, we need to drop mm and files before trying to issue next request.

---
 fs/io_uring.c |    3 +++
 1 file changed, 3 insertions(+)
fs/io_uring.c +3 -0
@@ -2084,6 +2084,9 @@ static void __io_req_task_submit(struct
 	else
 		__io_req_task_cancel(req, -EFAULT);
 	mutex_unlock(&ctx->uring_lock);
+
+	if (ctx->flags & IORING_SETUP_SQPOLL)
+		io_sq_thread_drop_mm();
 }
 
 static void io_req_task_submit(struct callback_head *cb)
author maintainer
#29 lore raw

PATCH 29/54 ASoC: ak4458: correct reset polarity

In reply to Greg Kroah-Hartman

From: Eliot Blennerhassett <[email protected]>

[ Upstream commit e953daeb68b1abd8a7d44902786349fdeef5c297 ]

Reset (aka power off) happens when the reset gpio is made active. Change function name to ak4458_reset to match devicetree property "reset-gpios"

---
 sound/soc/codecs/ak4458.c | 22 +++++++---------------
 1 file changed, 7 insertions(+), 15 deletions(-)
sound/soc/codecs/ak4458.c +7 -15
index 1010c9ee2e836..472caad17012e 100644
@@ -595,18 +595,10 @@ static struct snd_soc_dai_driver ak4497_dai = {
 	.ops = &ak4458_dai_ops,
 };
 
-static void ak4458_power_off(struct ak4458_priv *ak4458)
+static void ak4458_reset(struct ak4458_priv *ak4458, bool active)
 {
 	if (ak4458->reset_gpiod) {
-		gpiod_set_value_cansleep(ak4458->reset_gpiod, 0);
-		usleep_range(1000, 2000);
-	}
-}
-
-static void ak4458_power_on(struct ak4458_priv *ak4458)
-{
-	if (ak4458->reset_gpiod) {
-		gpiod_set_value_cansleep(ak4458->reset_gpiod, 1);
+		gpiod_set_value_cansleep(ak4458->reset_gpiod, active);
 		usleep_range(1000, 2000);
 	}
 }
@@ -620,7 +612,7 @@ static int ak4458_init(struct snd_soc_component *component)
 	if (ak4458->mute_gpiod)
 		gpiod_set_value_cansleep(ak4458->mute_gpiod, 1);
 
-	ak4458_power_on(ak4458);
+	ak4458_reset(ak4458, false);
 
 	ret = snd_soc_component_update_bits(component, AK4458_00_CONTROL1,
 			    0x80, 0x80);   /* ACKS bit = 1; 10000000 */
@@ -650,7 +642,7 @@ static void ak4458_remove(struct snd_soc_component *component)
 {
 	struct ak4458_priv *ak4458 = snd_soc_component_get_drvdata(component);
 
-	ak4458_power_off(ak4458);
+	ak4458_reset(ak4458, true);
 }
 
 #ifdef CONFIG_PM
@@ -660,7 +652,7 @@ static int __maybe_unused ak4458_runtime_suspend(struct device *dev)
 
 	regcache_cache_only(ak4458->regmap, true);
 
-	ak4458_power_off(ak4458);
+	ak4458_reset(ak4458, true);
 
 	if (ak4458->mute_gpiod)
 		gpiod_set_value_cansleep(ak4458->mute_gpiod, 0);
@@ -685,8 +677,8 @@ static int __maybe_unused ak4458_runtime_resume(struct device *dev)
 	if (ak4458->mute_gpiod)
 		gpiod_set_value_cansleep(ak4458->mute_gpiod, 1);
 
-	ak4458_power_off(ak4458);
-	ak4458_power_on(ak4458);
+	ak4458_reset(ak4458, true);
+	ak4458_reset(ak4458, false);
 
 	regcache_cache_only(ak4458->regmap, false);
 	regcache_mark_dirty(ak4458->regmap);
Signature · 1 line
2.27.0
author maintainer
#3 lore raw

PATCH 3/54 io_uring: dont iterate io_uring_cancel_files()

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit b52fda00dd9df8b4a6de5784df94f9617f6133a1 ]

io_uring_cancel_files() guarantees to cancel all matching requests, that's not necessary to do that in a loop. Move it up in the callchain into io_uring_cancel_task_requests().

---
 fs/io_uring.c |   34 ++++++++++++----------------------
 1 file changed, 12 insertions(+), 22 deletions(-)
fs/io_uring.c +12 -22
@@ -8654,16 +8654,10 @@ static void io_cancel_defer_files(struct
 	}
 }
 
-/*
- * Returns true if we found and killed one or more files pinning requests
- */
-static bool io_uring_cancel_files(struct io_ring_ctx *ctx,
+static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 				  struct task_struct *task,
 				  struct files_struct *files)
 {
-	if (list_empty_careful(&ctx->inflight_list))
-		return false;
-
 	while (!list_empty_careful(&ctx->inflight_list)) {
 		struct io_kiocb *cancel_req = NULL, *req;
 		DEFINE_WAIT(wait);
@@ -8698,8 +8692,6 @@ static bool io_uring_cancel_files(struct
 		schedule();
 		finish_wait(&ctx->inflight_wait, &wait);
 	}
-
-	return true;
 }
 
 static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
@@ -8710,15 +8702,12 @@ static bool io_cancel_task_cb(struct io_
 	return io_task_match(req, task);
 }
 
-static bool __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
-					    struct task_struct *task,
-					    struct files_struct *files)
+static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
+					    struct task_struct *task)
 {
-	bool ret;
-
-	ret = io_uring_cancel_files(ctx, task, files);
-	if (!files) {
+	while (1) {
 		enum io_wq_cancel cret;
+		bool ret = false;
 
 		cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, task, true);
 		if (cret != IO_WQ_CANCEL_NOTFOUND)
@@ -8734,9 +8723,11 @@ static bool __io_uring_cancel_task_reque
 
 		ret |= io_poll_remove_all(ctx, task);
 		ret |= io_kill_timeouts(ctx, task);
+		if (!ret)
+			break;
+		io_run_task_work();
+		cond_resched();
 	}
-
-	return ret;
 }
 
 static void io_disable_sqo_submit(struct io_ring_ctx *ctx)
@@ -8771,11 +8762,10 @@ static void io_uring_cancel_task_request
 
 	io_cancel_defer_files(ctx, task, files);
 	io_cqring_overflow_flush(ctx, true, task, files);
+	io_uring_cancel_files(ctx, task, files);
 
-	while (__io_uring_cancel_task_requests(ctx, task, files)) {
-		io_run_task_work();
-		cond_resched();
-	}
+	if (!files)
+		__io_uring_cancel_task_requests(ctx, task);
 
 	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
 		atomic_dec(&task->io_uring->in_idle);
author maintainer
#4 lore raw

PATCH 4/54 io_uring: pass files into kill timeouts/poll

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit 6b81928d4ca8668513251f9c04cdcb9d38ef51c7 ]

Make io_poll_remove_all() and io_kill_timeouts() to match against files as well. A preparation patch, effectively not used by now.

---
 fs/io_uring.c |   18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)
fs/io_uring.c +10 -8
@@ -1508,14 +1508,15 @@ static bool io_task_match(struct io_kioc
 /*
  * Returns true if we found and killed one or more timeouts
  */
-static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk)
+static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
+			     struct files_struct *files)
 {
 	struct io_kiocb *req, *tmp;
 	int canceled = 0;
 
 	spin_lock_irq(&ctx->completion_lock);
 	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
-		if (io_task_match(req, tsk)) {
+		if (io_match_task(req, tsk, files)) {
 			io_kill_timeout(req);
 			canceled++;
 		}
@@ -5312,7 +5313,8 @@ static bool io_poll_remove_one(struct io
 /*
  * Returns true if we found and killed one or more poll requests
  */
-static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk)
+static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk,
+			       struct files_struct *files)
 {
 	struct hlist_node *tmp;
 	struct io_kiocb *req;
@@ -5324,7 +5326,7 @@ static bool io_poll_remove_all(struct io
 
 		list = &ctx->cancel_hash[i];
 		hlist_for_each_entry_safe(req, tmp, list, hash_node) {
-			if (io_task_match(req, tsk))
+			if (io_match_task(req, tsk, files))
 				posted += io_poll_remove_one(req);
 		}
 	}
@@ -8485,8 +8487,8 @@ static void io_ring_ctx_wait_and_kill(st
 		__io_cqring_overflow_flush(ctx, true, NULL, NULL);
 	mutex_unlock(&ctx->uring_lock);
 
-	io_kill_timeouts(ctx, NULL);
-	io_poll_remove_all(ctx, NULL);
+	io_kill_timeouts(ctx, NULL, NULL);
+	io_poll_remove_all(ctx, NULL, NULL);
 
 	if (ctx->io_wq)
 		io_wq_cancel_cb(ctx->io_wq, io_cancel_ctx_cb, ctx, true);
@@ -8721,8 +8723,8 @@ static void __io_uring_cancel_task_reque
 			}
 		}
 
-		ret |= io_poll_remove_all(ctx, task);
-		ret |= io_kill_timeouts(ctx, task);
+		ret |= io_poll_remove_all(ctx, task, NULL);
+		ret |= io_kill_timeouts(ctx, task, NULL);
 		if (!ret)
 			break;
 		io_run_task_work();
author maintainer
#28 lore raw

PATCH 28/54 ALSA: hda: intel-dsp-config: add PCI id for TGL-H

In reply to Greg Kroah-Hartman

From: Bard Liao <[email protected]>

[ Upstream commit c5b5ff607d6fe5f4284acabd07066f96ecf96ac4 ]

Adding PCI id for TGL-H. Like for other TGL platforms, SOF is used if Soundwire codecs or PCH-DMIC is detected.

---
 sound/hda/intel-dsp-config.c | 4 ++++
 1 file changed, 4 insertions(+)
sound/hda/intel-dsp-config.c +4 -0
index 1c5114dedda92..fe49e9a97f0ec 100644
@@ -306,6 +306,10 @@ static const struct config_entry config_table[] = {
 		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
 		.device = 0xa0c8,
 	},
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
+		.device = 0x43c8,
+	},
 #endif
 
 /* Elkhart Lake */
Signature · 1 line
2.27.0
author maintainer
#15 lore raw

PATCH 15/54 io_uring: reinforce cancel on flush during exit

In reply to Greg Kroah-Hartman

From: Pavel Begunkov <[email protected]>

[ Upstream commit 3a7efd1ad269ccaf9c1423364d97c9661ba6dafa ]

What 84965ff8a84f0 ("io_uring: if we see flush on exit, cancel related tasks") really wants is to cancel all relevant REQ_F_INFLIGHT requests reliably. That can be achieved by io_uring_cancel_files(), but we'll miss it calling io_uring_cancel_task_requests(files=NULL) from io_uring_flush(), because it will go through __io_uring_cancel_task_requests().

Just always call io_uring_cancel_files() during cancel, it's good enough for now.

---
 fs/io_uring.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
fs/io_uring.c +1 -2
@@ -8692,10 +8692,9 @@ static void io_uring_cancel_task_request
 	io_cancel_defer_files(ctx, task, files);
 	io_cqring_overflow_flush(ctx, true, task, files);
 
+	io_uring_cancel_files(ctx, task, files);
 	if (!files)
 		__io_uring_cancel_task_requests(ctx, task);
-	else
-		io_uring_cancel_files(ctx, task, files);
 
 	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
 		atomic_dec(&task->io_uring->in_idle);
author maintainer
#27 lore raw

PATCH 27/54 pNFS/NFSv4: Improve rejection of out-of-order layouts

In reply to Greg Kroah-Hartman

From: Trond Myklebust <[email protected]>

[ Upstream commit d29b468da4f940bd2bff2628ba8d2d652671d244 ]

If a layoutget ends up being reordered w.r.t. a layoutreturn, e.g. due to a layoutget-on-open not knowing a priori which file to lock, then we must assume the layout is no longer being considered valid state by the server.
Incrementally improve our ability to reject such states by using the cached old stateid in conjunction with the plh_barrier to try to identify them.

---
 fs/nfs/pnfs.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)
fs/nfs/pnfs.c +16 -6
index 2b98286376d40..b8712b835b105 100644
@@ -1000,7 +1000,7 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
 {
 	u32 seqid = be32_to_cpu(stateid->seqid);
 
-	return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
+	return !pnfs_seqid_is_newer(seqid, lo->plh_barrier) && lo->plh_barrier;
 }
 
 /* lget is set to 1 if called from inside send_layoutget call chain */
@@ -1913,6 +1913,11 @@ static void nfs_layoutget_end(struct pnfs_layout_hdr *lo)
 		wake_up_var(&lo->plh_outstanding);
 }
 
+static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo)
+{
+	return test_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags);
+}
+
 static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo)
 {
 	unsigned long *bitlock = &lo->plh_flags;
@@ -2387,17 +2392,17 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		goto out_forget;
 	}
 
-	if (!pnfs_layout_is_valid(lo)) {
-		/* We have a completely new layout */
-		pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true);
-	} else if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
+	if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
 		/* existing state ID, make sure the sequence number matches. */
 		if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
+			if (!pnfs_layout_is_valid(lo) &&
+			    pnfs_is_first_layoutget(lo))
+				lo->plh_barrier = 0;
 			dprintk("%s forget reply due to sequence\n", __func__);
 			goto out_forget;
 		}
 		pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, false);
-	} else {
+	} else if (pnfs_layout_is_valid(lo)) {
 		/*
 		 * We got an entirely new state ID.  Mark all segments for the
 		 * inode invalid, and retry the layoutget
@@ -2410,6 +2415,11 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
 						&range, 0);
 		goto out_forget;
+	} else {
+		/* We have a completely new layout */
+		if (!pnfs_is_first_layoutget(lo))
+			goto out_forget;
+		pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true);
 	}
 
 	pnfs_get_lseg(lseg);
Signature · 1 line
2.27.0
author maintainer
#26 lore raw

PATCH 26/54 pNFS/NFSv4: Try to return invalid layout in pnfs_layout_process()

In reply to Greg Kroah-Hartman

From: Trond Myklebust <[email protected]>

[ 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.

---
 fs/nfs/pnfs.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
fs/nfs/pnfs.c +7 -1
index cbadcf6ca4da2..2b98286376d40 100644
@@ -2402,7 +2402,13 @@ 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;
 	}
 
Signature · 1 line
2.27.0
author maintainer
#23 lore raw

PATCH 23/54 mac80211: 160MHz with extended NSS BW in CSA

In reply to Greg Kroah-Hartman

From: Shay Bar <[email protected]>

[ Upstream commit dcf3c8fb32ddbfa3b8227db38aa6746405bd4527 ]

Upon receiving CSA with 160MHz extended NSS BW from associated AP, STA should set the HT operation_mode based on new_center_freq_seg1 because it is later used as ccfs2 in ieee80211_chandef_vht_oper().

---
 net/mac80211/spectmgmt.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
net/mac80211/spectmgmt.c +7 -3
index ae1cb2c687224..76747bfdaddd0 100644
@@ -133,16 +133,20 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (wide_bw_chansw_ie) {
+		u8 new_seg1 = wide_bw_chansw_ie->new_center_freq_seg1;
 		struct ieee80211_vht_operation vht_oper = {
 			.chan_width =
 				wide_bw_chansw_ie->new_channel_width,
 			.center_freq_seg0_idx =
 				wide_bw_chansw_ie->new_center_freq_seg0,
-			.center_freq_seg1_idx =
-				wide_bw_chansw_ie->new_center_freq_seg1,
+			.center_freq_seg1_idx = new_seg1,
 			/* .basic_mcs_set doesn't matter */
 		};
-		struct ieee80211_ht_operation ht_oper = {};
+		struct ieee80211_ht_operation ht_oper = {
+			.operation_mode =
+				cpu_to_le16(new_seg1 <<
+					    IEEE80211_HT_OP_MODE_CCFS2_SHIFT),
+		};
 
 		/* default, for the case of IEEE80211_VHT_CHANWIDTH_USE_HT,
 		 * to the previously parsed chandef
Signature · 1 line
2.27.0
author maintainer
#22 lore raw

PATCH 22/54 drm/nouveau/nvif: fix method count when pushing an array

In reply to Greg Kroah-Hartman

From: Ben Skeggs <[email protected]>

[ Upstream commit d502297008142645edf5c791af424ed321e5da84 ]

---
 drivers/gpu/drm/nouveau/include/nvif/push.h | 216 ++++++++++----------
 1 file changed, 108 insertions(+), 108 deletions(-)
drivers/gpu/drm/nouveau/include/nvif/push.h +108 -108
index 168d7694ede5c..6d3a8a3d2087b 100644
@@ -123,131 +123,131 @@ PUSH_KICK(struct nvif_push *push)
 } while(0)
 #endif
 
-#define PUSH_1(X,f,ds,n,c,o,p,s,mA,dA) do {                            \
-	PUSH_##o##_HDR((p), s, mA, (c)+(n));                           \
-	PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, "");                   \
+#define PUSH_1(X,f,ds,n,o,p,s,mA,dA) do {                             \
+	PUSH_##o##_HDR((p), s, mA, (ds)+(n));                         \
+	PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, "");                  \
 } while(0)
-#define PUSH_2(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1");       \
-	PUSH_1(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_2(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1");      \
+	PUSH_1(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_3(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2");       \
-	PUSH_2(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_3(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2");      \
+	PUSH_2(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_4(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3");       \
-	PUSH_3(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_4(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3");      \
+	PUSH_3(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_5(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4");       \
-	PUSH_4(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_5(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4");      \
+	PUSH_4(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_6(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5");       \
-	PUSH_5(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_6(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5");      \
+	PUSH_5(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_7(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6");       \
-	PUSH_6(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_7(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6");      \
+	PUSH_6(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_8(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7");       \
-	PUSH_7(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_8(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7");      \
+	PUSH_7(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_9(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8");       \
-	PUSH_8(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_9(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8");      \
+	PUSH_8(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_10(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9");       \
-	PUSH_9(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_10(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                 \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9");      \
+	PUSH_9(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
 
-#define PUSH_1D(X,o,p,s,mA,dA)                            \
-	PUSH_1(X, DATA_, 1, 1, 0, o, (p), s, X##mA, (dA))
-#define PUSH_2D(X,o,p,s,mA,dA,mB,dB)                      \
-	PUSH_2(X, DATA_, 1, 1, 0, o, (p), s, X##mB, (dB), \
-					     X##mA, (dA))
-#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC)                \
-	PUSH_3(X, DATA_, 1, 1, 0, o, (p), s, X##mC, (dC), \
-					     X##mB, (dB), \
-					     X##mA, (dA))
-#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD)          \
-	PUSH_4(X, DATA_, 1, 1, 0, o, (p), s, X##mD, (dD), \
-					     X##mC, (dC), \
-					     X##mB, (dB), \
-					     X##mA, (dA))
-#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE)    \
-	PUSH_5(X, DATA_, 1, 1, 0, o, (p), s, X##mE, (dE), \
-					     X##mD, (dD), \
-					     X##mC, (dC), \
-					     X##mB, (dB), \
-					     X##mA, (dA))
+#define PUSH_1D(X,o,p,s,mA,dA)                         \
+	PUSH_1(X, DATA_, 1, 0, o, (p), s, X##mA, (dA))
+#define PUSH_2D(X,o,p,s,mA,dA,mB,dB)                   \
+	PUSH_2(X, DATA_, 1, 0, o, (p), s, X##mB, (dB), \
+					  X##mA, (dA))
+#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC)             \
+	PUSH_3(X, DATA_, 1, 0, o, (p), s, X##mC, (dC), \
+					  X##mB, (dB), \
+					  X##mA, (dA))
+#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD)       \
+	PUSH_4(X, DATA_, 1, 0, o, (p), s, X##mD, (dD), \
+					  X##mC, (dC), \
+					  X##mB, (dB), \
+					  X##mA, (dA))
+#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE) \
+	PUSH_5(X, DATA_, 1, 0, o, (p), s, X##mE, (dE), \
+					  X##mD, (dD), \
+					  X##mC, (dC), \
+					  X##mB, (dB), \
+					  X##mA, (dA))
 #define PUSH_6D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF) \
-	PUSH_6(X, DATA_, 1, 1, 0, o, (p), s, X##mF, (dF),    \
-					     X##mE, (dE),    \
-					     X##mD, (dD),    \
-					     X##mC, (dC),    \
-					     X##mB, (dB),    \
-					     X##mA, (dA))
+	PUSH_6(X, DATA_, 1, 0, o, (p), s, X##mF, (dF),       \
+					  X##mE, (dE),       \
+					  X##mD, (dD),       \
+					  X##mC, (dC),       \
+					  X##mB, (dB),       \
+					  X##mA, (dA))
 #define PUSH_7D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG) \
-	PUSH_7(X, DATA_, 1, 1, 0, o, (p), s, X##mG, (dG),          \
-					     X##mF, (dF),          \
-					     X##mE, (dE),          \
-					     X##mD, (dD),          \
-					     X##mC, (dC),          \
-					     X##mB, (dB),          \
-					     X##mA, (dA))
+	PUSH_7(X, DATA_, 1, 0, o, (p), s, X##mG, (dG),             \
+					  X##mF, (dF),             \
+					  X##mE, (dE),             \
+					  X##mD, (dD),             \
+					  X##mC, (dC),             \
+					  X##mB, (dB),             \
+					  X##mA, (dA))
 #define PUSH_8D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH) \
-	PUSH_8(X, DATA_, 1, 1, 0, o, (p), s, X##mH, (dH),                \
-					     X##mG, (dG),                \
-					     X##mF, (dF),                \
-					     X##mE, (dE),                \
-					     X##mD, (dD),                \
-					     X##mC, (dC),                \
-					     X##mB, (dB),                \
-					     X##mA, (dA))
+	PUSH_8(X, DATA_, 1, 0, o, (p), s, X##mH, (dH),                   \
+					  X##mG, (dG),                   \
+					  X##mF, (dF),                   \
+					  X##mE, (dE),                   \
+					  X##mD, (dD),                   \
+					  X##mC, (dC),                   \
+					  X##mB, (dB),                   \
+					  X##mA, (dA))
 #define PUSH_9D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI) \
-	PUSH_9(X, DATA_, 1, 1, 0, o, (p), s, X##mI, (dI),                      \
-					     X##mH, (dH),                      \
-					     X##mG, (dG),                      \
-					     X##mF, (dF),                      \
-					     X##mE, (dE),                      \
-					     X##mD, (dD),                      \
-					     X##mC, (dC),                      \
-					     X##mB, (dB),                      \
-					     X##mA, (dA))
+	PUSH_9(X, DATA_, 1, 0, o, (p), s, X##mI, (dI),                         \
+					  X##mH, (dH),                         \
+					  X##mG, (dG),                         \
+					  X##mF, (dF),                         \
+					  X##mE, (dE),                         \
+					  X##mD, (dD),                         \
+					  X##mC, (dC),                         \
+					  X##mB, (dB),                         \
+					  X##mA, (dA))
 #define PUSH_10D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI,mJ,dJ) \
-	PUSH_10(X, DATA_, 1, 1, 0, o, (p), s, X##mJ, (dJ),                            \
-					      X##mI, (dI),                            \
-					      X##mH, (dH),                            \
-					      X##mG, (dG),                            \
-					      X##mF, (dF),                            \
-					      X##mE, (dE),                            \
-					      X##mD, (dD),                            \
-					      X##mC, (dC),                            \
-					      X##mB, (dB),                            \
-					      X##mA, (dA))
+	PUSH_10(X, DATA_, 1, 0, o, (p), s, X##mJ, (dJ),                               \
+					   X##mI, (dI),                               \
+					   X##mH, (dH),                               \
+					   X##mG, (dG),                               \
+					   X##mF, (dF),                               \
+					   X##mE, (dE),                               \
+					   X##mD, (dD),                               \
+					   X##mC, (dC),                               \
+					   X##mB, (dB),                               \
+					   X##mA, (dA))
 
-#define PUSH_1P(X,o,p,s,mA,dp,ds)                           \
-	PUSH_1(X, DATAp, ds, ds, 0, o, (p), s, X##mA, (dp))
-#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds)                     \
-	PUSH_2(X, DATAp, ds, ds, 0, o, (p), s, X##mB, (dp), \
-					       X##mA, (dA))
-#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds)               \
-	PUSH_3(X, DATAp, ds, ds, 0, o, (p), s, X##mC, (dp), \
-					       X##mB, (dB), \
-					       X##mA, (dA))
+#define PUSH_1P(X,o,p,s,mA,dp,ds)                       \
+	PUSH_1(X, DATAp, ds, 0, o, (p), s, X##mA, (dp))
+#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds)                 \
+	PUSH_2(X, DATAp, ds, 0, o, (p), s, X##mB, (dp), \
+					   X##mA, (dA))
+#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds)           \
+	PUSH_3(X, DATAp, ds, 0, o, (p), s, X##mC, (dp), \
+					   X##mB, (dB), \
+					   X##mA, (dA))
 
 #define PUSH_(A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,IMPL,...) IMPL
 #define PUSH(A...) PUSH_(A, PUSH_10P, PUSH_10D,          \
Signature · 1 line
2.27.0
author maintainer
#53 lore raw

PATCH 53/54 squashfs: add more sanity checks in inode lookup

In reply to Greg Kroah-Hartman

From: Phillip Lougher <[email protected]>

commit eabac19e40c095543def79cb6ffeb3a8588aaff4 upstream.

Sysbot has reported an "slab-out-of-bounds read" error which has been identified as being caused by a corrupted "ino_num" value read from the inode. This could be because the metadata block is uncompressed, or because the "compression" bit has been corrupted (turning a compressed block into an uncompressed block).

This patch adds additional sanity checks to detect this, and the following corruption.

1. It checks against corruption of the inodes count. This can either lead to a larger table to be read, or a smaller than expected table to be read.

In the case of a too large inodes count, this would often have been trapped by the existing sanity checks, but this patch introduces a more exact check, which can identify too small values.

2. It checks the contents of the index table for corruption.

---
 fs/squashfs/export.c |   41 +++++++++++++++++++++++++++++++++--------
 1 file changed, 33 insertions(+), 8 deletions(-)
fs/squashfs/export.c +33 -8
@@ -41,12 +41,17 @@ static long long squashfs_inode_lookup(s
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
 	int blk = SQUASHFS_LOOKUP_BLOCK(ino_num - 1);
 	int offset = SQUASHFS_LOOKUP_BLOCK_OFFSET(ino_num - 1);
-	u64 start = le64_to_cpu(msblk->inode_lookup_table[blk]);
+	u64 start;
 	__le64 ino;
 	int err;
 
 	TRACE("Entered squashfs_inode_lookup, inode_number = %d\n", ino_num);
 
+	if (ino_num == 0 || (ino_num - 1) >= msblk->inodes)
+		return -EINVAL;
+
+	start = le64_to_cpu(msblk->inode_lookup_table[blk]);
+
 	err = squashfs_read_metadata(sb, &ino, &start, &offset, sizeof(ino));
 	if (err < 0)
 		return err;
@@ -111,7 +116,10 @@ __le64 *squashfs_read_inode_lookup_table
 		u64 lookup_table_start, u64 next_table, unsigned int inodes)
 {
 	unsigned int length = SQUASHFS_LOOKUP_BLOCK_BYTES(inodes);
+	unsigned int indexes = SQUASHFS_LOOKUP_BLOCKS(inodes);
+	int n;
 	__le64 *table;
+	u64 start, end;
 
 	TRACE("In read_inode_lookup_table, length %d\n", length);
 
@@ -121,20 +129,37 @@ __le64 *squashfs_read_inode_lookup_table
 	if (inodes == 0)
 		return ERR_PTR(-EINVAL);
 
-	/* length bytes should not extend into the next table - this check
-	 * also traps instances where lookup_table_start is incorrectly larger
-	 * than the next table start
+	/*
+	 * The computed size of the lookup table (length bytes) should exactly
+	 * match the table start and end points
 	 */
-	if (lookup_table_start + length > next_table)
+	if (length != (next_table - lookup_table_start))
 		return ERR_PTR(-EINVAL);
 
 	table = squashfs_read_table(sb, lookup_table_start, length);
+	if (IS_ERR(table))
+		return table;
 
 	/*
-	 * table[0] points to the first inode lookup table metadata block,
-	 * this should be less than lookup_table_start
+	 * table0], table[1], ... table[indexes - 1] store the locations
+	 * of the compressed inode lookup blocks.  Each entry should be
+	 * less than the next (i.e. table[0] < table[1]), and the difference
+	 * between them should be SQUASHFS_METADATA_SIZE or less.
+	 * table[indexes - 1] should  be less than lookup_table_start, and
+	 * again the difference should be SQUASHFS_METADATA_SIZE or less
 	 */
-	if (!IS_ERR(table) && le64_to_cpu(table[0]) >= lookup_table_start) {
+	for (n = 0; n < (indexes - 1); n++) {
+		start = le64_to_cpu(table[n]);
+		end = le64_to_cpu(table[n + 1]);
+
+		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+			kfree(table);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	start = le64_to_cpu(table[indexes - 1]);
+	if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}
author maintainer
#30 lore raw

PATCH 30/54 ASoC: Intel: sof_sdw: set proper flags for Dell TGL-H SKU 0A5E

In reply to Greg Kroah-Hartman

From: Libin Yang <[email protected]>

[ Upstream commit 9ad9bc59dde106e56dd59ce2bec7c1b08e1f0eb4 ]

Add flag "SOF_RT711_JD_SRC_JD2", flag "SOF_RT715_DAI_ID_FIX" and "SOF_SDW_FOUR_SPK" to the Dell TGL-H based SKU "0A5E".

---
 sound/soc/intel/boards/sof_sdw.c | 10 ++++++++++
 1 file changed, 10 insertions(+)
sound/soc/intel/boards/sof_sdw.c +10 -0
index b29946eb43551..a8d43c87cb5a2 100644
@@ -57,6 +57,16 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
 		.driver_data = (void *)(SOF_RT711_JD_SRC_JD2 |
 					SOF_RT715_DAI_ID_FIX),
 	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0A5E")
+		},
+		.driver_data = (void *)(SOF_RT711_JD_SRC_JD2 |
+					SOF_RT715_DAI_ID_FIX |
+					SOF_SDW_FOUR_SPK),
+	},
 	{
 		.callback = sof_sdw_quirk_cb,
 		.matches = {
Signature · 1 line
2.27.0
Tested-by Linux Kernel Functional Testing on the v1 series
#55 lore raw
In reply to Greg Kroah-Hartman
Quoted 10 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 8 lines
        https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.16-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
and the diffstat can be found below.

thanks,

greg k-h

Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.

Summary
------------------------------------------------------------------------

kernel: 5.10.16-rc1
git repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
git branch: linux-5.10.y
git commit: 4dd7e46ded5fc095df2bd9a6e3ca023150c55452
git describe: v5.10.15-55-g4dd7e46ded5f
Test details: https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.10.y/build/v5.10.15-55-g4dd7e46ded5f

No regressions (compared to build v5.10.15)

No fixes (compared to build v5.10.15)

Ran 50609 total tests in the following environments and test suites.

Environments
--------------
- arc
- arm
- arm64
- dragonboard-410c
- hi6220-hikey
- i386
- juno-r2
- juno-r2-compat
- juno-r2-kasan
- mips
- nxp-ls2088
- parisc
- powerpc
- qemu-arm-clang
- qemu-arm64-clang
- qemu-arm64-kasan
- qemu-i386-clang
- qemu-x86_64-clang
- qemu-x86_64-kasan
- qemu-x86_64-kcsan
- qemu_arm
- qemu_arm64
- qemu_arm64-compat
- qemu_i386
- qemu_x86_64
- qemu_x86_64-compat
- riscv
- s390
- sh
- sparc
- x15
- x86
- x86-kasan
- x86_64

Test Suites
-----------
* build
* linux-log-parser
* install-android-platform-tools-r2600
* kselftest-bpf
* kselftest-kvm
* kselftest-lkdtm
* kvm-unit-tests
* ltp-containers-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-mm-tests
* ltp-nptl-tests
* ltp-pty-tests
* ltp-sched-tests
* ltp-securebits-tests
* ltp-tracing-tests
* fwts
* kselftest-efivarfs
* kselftest-filesystems
* kselftest-firmware
* kselftest-fpu
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-livepatch
* kselftest-net
* kselftest-netfilter
* kselftest-nsfs
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-splice
* kselftest-static_keys
* kselftest-sync
* kselftest-sysctl
* kselftest-tc-testing
* libhugetlbfs
* ltp-cap_bounds-tests
* ltp-commands-tests
* ltp-cpuhotplug-tests
* ltp-crypto-tests
* ltp-math-tests
* ltp-syscalls-tests
* network-basic-tests
* perf
* kselftest-
* kselftest-android
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-kexec
* kselftest-lib
* kselftest-membarrier
* kselftest-memfd
* kselftest-memory-hotplug
* kselftest-mincore
* kselftest-mount
* kselftest-mqueue
* kselftest-openat2
* kselftest-pid_namespace
* kselftest-pidfd
* kselftest-proc
* kselftest-pstore
* kselftest-timens
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-vm
* kselftest-x86
* kselftest-zram
* ltp-controllers-tests
* ltp-open-posix-tests
* v4l2-compliance
* kunit
* rcutorture
* ssuite

Signature · 2 lines
Linaro LKFT
https://lkft.linaro.org
Tested-by on the v1 series
#57 lore raw
In reply to Greg Kroah-Hartman
Quoted 9 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 9 lines
	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.16-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
and the diffstat can be found below.

thanks,

greg k-h

Compiled and booted on my test system. No dmesg regressions.

Note: gdm doesn't start and no response to keyboard and mouse.

I can ssh in and use the system. I am going debug and update you. 5.4.98-rc1 and 4.9.176-rc1 are fine and no such issues.

thanks,
-- Shuah

Tested-by on the v1 series
#60 lore raw
In reply to Greg Kroah-Hartman
Quoted 8 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

Build results:

	total: 154 pass: 154 fail: 0
Qemu test results:
	total: 427 pass: 427 fail: 0

Guenter

Tested-by on the v1 series
#62 lore raw
In reply to Greg Kroah-Hartman
Quoted 9 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 8 lines
	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.16-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
and the diffstat can be found below.

thanks,

greg k-h

On ARCH_BRCMSTB, 32-bit and 64-bit ARM, thanks!

Signature · 1 line
Florian
Tested-by on the v1 series
#64 lore raw
In reply to Greg Kroah-Hartman

Hi!

Quoted 4 lines

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

CIP testing did not find any problems here:

https://gitlab.com/cip-project/cip-testing/linux-stable-rc-ci/-/tree/linux-5.10.y

Best regards,
Pavel

Signature · 2 lines
DENX Software Engineering GmbH,      Managing Director: Wolfgang Denk
HRB 165235 Munich, Office: Kirchenstr.5, D-82194 Groebenzell, Germany
Tested-by on the v1 series
#66 lore raw
In reply to Greg Kroah-Hartman
Quoted 5 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Compiled and booted with no regressions on x86_64.

thanks,

Ross

author maintainer
#65 lore raw
In reply to Pavel Machek
Quoted 7 lines · Pavel Machek

Hi!

Quoted 4 lines

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Quoted 5 lines

CIP testing did not find any problems here:

https://gitlab.com/cip-project/cip-testing/linux-stable-rc-ci/-/tree/linux-5.10.y

Thanks for testing some and letting me know.

greg k-h

author maintainer
#67 lore raw
In reply to Ross Schmidt
Quoted 11 lines · Ross Schmidt
Quoted 5 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Compiled and booted with no regressions on x86_64.

Thanks for testing them all and letting me know.

greg k-h

author maintainer
#63 lore raw
In reply to Florian Fainelli
Quoted 17 lines · Florian Fainelli
Quoted 14 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.16-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
and the diffstat can be found below.

Quoted 7 lines
Quoted 3 lines

thanks,

greg k-h

On ARCH_BRCMSTB, 32-bit and 64-bit ARM, thanks!

Thanks for testing.

greg k-h

author maintainer
#61 lore raw
In reply to Guenter Roeck
Quoted 10 lines · Guenter Roeck
Quoted 8 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

Quoted 6 lines

Build results:

	total: 154 pass: 154 fail: 0
Qemu test results:
	total: 427 pass: 427 fail: 0

Great, thanks for testing.

greg k-h

author maintainer
#58 lore raw
In reply to Shuah Khan
Quoted 20 lines · Shuah Khan
Quoted 9 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 9 lines
	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.16-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
and the diffstat can be found below.

thanks,

greg k-h

Quoted 8 lines

Compiled and booted on my test system. No dmesg regressions.

Note: gdm doesn't start and no response to keyboard and mouse.

I can ssh in and use the system. I am going debug and update you. 5.4.98-rc1 and 4.9.176-rc1 are fine and no such issues.

Did you ever track this down?

thanks,

greg k-h

author maintainer
#56 lore raw
In reply to Naresh Kamboju
Quoted 17 lines · Naresh Kamboju
Quoted 15 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

        https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.16-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
and the diffstat can be found below.

Quoted 8 lines
Quoted 3 lines

thanks,

greg k-h

Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.

Thanks for testing them all and letting me know.

greg k-h

#59 lore raw
In reply to Greg Kroah-Hartman
Quoted 23 lines · Greg Kroah-Hartman
Quoted 22 lines · Shuah Khan
Quoted 9 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.10.16 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 13 Feb 2021 15:01:39 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 9 lines
	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.16-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
and the diffstat can be found below.

thanks,

greg k-h

Compiled and booted on my test system. No dmesg regressions.

Quoted 9 lines
Quoted 6 lines

Note: gdm doesn't start and no response to keyboard and mouse.

I can ssh in and use the system. I am going debug and update you. 5.4.98-rc1 and 4.9.176-rc1 are fine and no such issues.

Did you ever track this down?

I am planning make time this week to track this down.

thanks,
-- Shuah