4.15.5-stable review

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Steffen Weber <[email protected]>

commit dc2db1dc5fb9ab3a43b305c2720fee5278dbee2a upstream.

If CONFIG_SCSI_SMARTPQI=y then don't build this driver as a module.

---
 drivers/scsi/smartpqi/Makefile |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1,3 +1,3 @@
 ccflags-y += -I.
-obj-m		+= smartpqi.o
+obj-$(CONFIG_SCSI_SMARTPQI) += smartpqi.o
 smartpqi-objs := smartpqi_init.o smartpqi_sis.o smartpqi_sas_transport.o

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Jack Morgenstein <[email protected]>

commit f23a5350e43c810ca36b26d4ed4ecd9a08686f47 upstream.

The ib_write_umad() is protected by taking the umad file mutex. However, it accesses file->port->ib_dev -- which is protected only by the port's mutex (field file_mutex).

The ib_umad_remove_one() calls ib_umad_kill_port() which sets port->ib_dev to NULL under the port mutex (NOT the file mutex). It then sets the mad agent to "dead" under the umad file mutex.

This is a race condition -- because there is a window where port->ib_dev is NULL, while the agent is not "dead".

As a result, we saw stack traces like:

[16490.678059] BUG: unable to handle kernel NULL pointer dereference at 00000000000000b0
[16490.678246] IP: ib_umad_write+0x29c/0xa3a [ib_umad]
[16490.678333] PGD 0 P4D 0
[16490.678404] Oops: 0000 [#1] SMP PTI
[16490.678466] Modules linked in: rdma_ucm(OE) ib_ucm(OE) rdma_cm(OE) iw_cm(OE) ib_ipoib(OE) ib_cm(OE) ib_uverbs(OE) ib_umad(OE) mlx4_en(OE) ptp pps_core mlx4_ib(OE-) ib_core(OE) mlx4_core(OE) mlx_compat
(OE) memtrack(OE) devlink mst_pciconf(OE) mst_pci(OE) netconsole nfsv3 nfs_acl nfs lockd grace fscache cfg80211 rfkill esp6_offload esp6 esp4_offload esp4 sunrpc kvm_intel kvm ppdev parport_pc irqbypass
parport joydev i2c_piix4 virtio_balloon cirrus drm_kms_helper ttm drm e1000 serio_raw virtio_pci virtio_ring virtio ata_generic pata_acpi qemu_fw_cfg [last unloaded: mlxfw]
[16490.679202] CPU: 4 PID: 3115 Comm: sminfo Tainted: G           OE   4.14.13-300.fc27.x86_64 #1
[16490.679339] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu2 04/01/2014
[16490.679477] task: ffff9cf753890000 task.stack: ffffaf70c26b0000
[16490.679571] RIP: 0010:ib_umad_write+0x29c/0xa3a [ib_umad]
[16490.679664] RSP: 0018:ffffaf70c26b3d90 EFLAGS: 00010202
[16490.679747] RAX: 0000000000000010 RBX: ffff9cf75610fd80 RCX: 0000000000000000
[16490.679856] RDX: 0000000000000001 RSI: 00007ffdf2bfd714 RDI: ffff9cf6bb2a9c00

In the above trace, ib_umad_write is trying to dereference the NULL file->port->ib_dev pointer.

Fix this by using the agent's device pointer (the device field in struct ib_mad_agent) -- which IS protected by the umad file mutex.

---
 drivers/infiniband/core/user_mad.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -500,7 +500,7 @@ static ssize_t ib_umad_write(struct file
 	}
 
 	memset(&ah_attr, 0, sizeof ah_attr);
-	ah_attr.type = rdma_ah_find_type(file->port->ib_dev,
+	ah_attr.type = rdma_ah_find_type(agent->device,
 					 file->port->port_num);
 	rdma_ah_set_dlid(&ah_attr, be16_to_cpu(packet->mad.hdr.lid));
 	rdma_ah_set_sl(&ah_attr, packet->mad.hdr.sl);

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Mike Marciniszyn <[email protected]>

commit 87b3524cb5058fdc7c2afdb92bdb2e079661ddc4 upstream.

This failure exists with qib:

ver_rc_compare_swap:
mismatch, sequence 2, expected 123456789abcdef, got 0

The request builder was using the incorrect inlines to build the request header resulting in incorrect data in the atomic header.

Fix by using the appropriate inlines to create the request.

---
 drivers/infiniband/hw/qib/qib_rc.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -434,13 +434,13 @@ no_flow_control:
 				qp->s_state = OP(COMPARE_SWAP);
 				put_ib_ateth_swap(wqe->atomic_wr.swap,
 						  &ohdr->u.atomic_eth);
-				put_ib_ateth_swap(wqe->atomic_wr.compare_add,
-						  &ohdr->u.atomic_eth);
+				put_ib_ateth_compare(wqe->atomic_wr.compare_add,
+						     &ohdr->u.atomic_eth);
 			} else {
 				qp->s_state = OP(FETCH_ADD);
 				put_ib_ateth_swap(wqe->atomic_wr.compare_add,
 						  &ohdr->u.atomic_eth);
-				put_ib_ateth_swap(0, &ohdr->u.atomic_eth);
+				put_ib_ateth_compare(0, &ohdr->u.atomic_eth);
 			}
 			put_ib_ateth_vaddr(wqe->atomic_wr.remote_addr,
 					   &ohdr->u.atomic_eth);

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Jack Morgenstein <[email protected]>

commit 852f6927594d0d3e8632c889b2ab38cbc46476ad upstream.

Allocating steerable UD QPs depends on having at least one IB port, while releasing those QPs does not.

As a result, when there are only ETH ports, the IB (RoCE) driver requests releasing a qp range whose base qp is zero, with qp count zero.

When SR-IOV is enabled, and the VF driver is running on a VM over a hypervisor which treats such qp release calls as errors (rather than NOPs), we see lines in the VM message log like:

mlx4_core 0002:00:02.0: Failed to release qp range base:0 cnt:0

Fix this by adding a check for a zero count in mlx4_release_qp_range() (which thus treats releasing 0 qps as a nop), and eliminating the check for device managed flow steering when releasing steerable UD QPs. (Freeing ib_uc_qpns_bitmap unconditionally is also OK, since it remains NULL when steerable UD QPs are not allocated).

---
 drivers/infiniband/hw/mlx4/main.c       |   13 +++++--------
 drivers/net/ethernet/mellanox/mlx4/qp.c |    3 +++
 2 files changed, 8 insertions(+), 8 deletions(-)

@@ -2995,9 +2995,8 @@ err_steer_free_bitmap:
 	kfree(ibdev->ib_uc_qpns_bitmap);
 
 err_steer_qp_release:
-	if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
-		mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
-				      ibdev->steer_qpn_count);
+	mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
+			      ibdev->steer_qpn_count);
 err_counter:
 	for (i = 0; i < ibdev->num_ports; ++i)
 		mlx4_ib_delete_counters_table(ibdev, &ibdev->counters_table[i]);

@@ -3102,11 +3101,9 @@ static void mlx4_ib_remove(struct mlx4_d
 		ibdev->iboe.nb.notifier_call = NULL;
 	}
 
-	if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) {
-		mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
-				      ibdev->steer_qpn_count);
-		kfree(ibdev->ib_uc_qpns_bitmap);
-	}
+	mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
+			      ibdev->steer_qpn_count);
+	kfree(ibdev->ib_uc_qpns_bitmap);
 
 	iounmap(ibdev->uar_map);
 	for (p = 0; p < ibdev->num_ports; ++p)

@@ -287,6 +287,9 @@ void mlx4_qp_release_range(struct mlx4_d
 	u64 in_param = 0;
 	int err;
 
+	if (!cnt)
+		return;
+
 	if (mlx4_is_mfunc(dev)) {
 		set_param_l(&in_param, base_qpn);
 		set_param_h(&in_param, cnt);

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Bart Van Assche <[email protected]>

commit 02ee9da347873699603d9ce0112a80b5dd69dea1 upstream.

Eliminate the WARN_ONs that create following two warnings when registering an rxe device:

WARNING: CPU: 2 PID: 1005 at drivers/infiniband/core/device.c:449 ib_register_device+0x591/0x640 [ib_core]
CPU: 2 PID: 1005 Comm: run_tests Not tainted 4.15.0-rc4-dbg+ #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:ib_register_device+0x591/0x640 [ib_core]
Call Trace:
 rxe_register_device+0x3c6/0x470 [rdma_rxe]
 rxe_add+0x543/0x5e0 [rdma_rxe]
 rxe_net_add+0x37/0xb0 [rdma_rxe]
 rxe_param_set_add+0x5a/0x120 [rdma_rxe]
 param_attr_store+0x5e/0xc0
 module_attr_store+0x19/0x30
 sysfs_kf_write+0x3d/0x50
 kernfs_fop_write+0x116/0x1a0
 __vfs_write+0x23/0x120
 vfs_write+0xbe/0x1b0
 SyS_write+0x44/0xa0
 entry_SYSCALL_64_fastpath+0x23/0x9a

WARNING: CPU: 2 PID: 1005 at drivers/infiniband/core/sysfs.c:1279 ib_device_register_sysfs+0x11d/0x160 [ib_core]
CPU: 2 PID: 1005 Comm: run_tests Tainted: G        W        4.15.0-rc4-dbg+ #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:ib_device_register_sysfs+0x11d/0x160 [ib_core]
Call Trace:
 ib_register_device+0x3f7/0x640 [ib_core]
 rxe_register_device+0x3c6/0x470 [rdma_rxe]
 rxe_add+0x543/0x5e0 [rdma_rxe]
 rxe_net_add+0x37/0xb0 [rdma_rxe]
 rxe_param_set_add+0x5a/0x120 [rdma_rxe]
 param_attr_store+0x5e/0xc0
 module_attr_store+0x19/0x30
 sysfs_kf_write+0x3d/0x50
 kernfs_fop_write+0x116/0x1a0
 __vfs_write+0x23/0x120
 vfs_write+0xbe/0x1b0
 SyS_write+0x44/0xa0
 entry_SYSCALL_64_fastpath+0x23/0x9a

The code should accept either a parent pointer or a fully specified DMA specification without producing warnings.

---
 drivers/infiniband/core/device.c |   20 ++++++++++++++------
 drivers/infiniband/core/sysfs.c  |    1 -
 2 files changed, 14 insertions(+), 7 deletions(-)

@@ -462,7 +462,6 @@ int ib_register_device(struct ib_device
 	struct ib_udata uhw = {.outlen = 0, .inlen = 0};
 	struct device *parent = device->dev.parent;
 
-	WARN_ON_ONCE(!parent);
 	WARN_ON_ONCE(device->dma_device);
 	if (device->dev.dma_ops) {
 		/*

@@ -471,16 +470,25 @@ int ib_register_device(struct ib_device
 		 * into device->dev.
 		 */
 		device->dma_device = &device->dev;
-		if (!device->dev.dma_mask)
-			device->dev.dma_mask = parent->dma_mask;
-		if (!device->dev.coherent_dma_mask)
-			device->dev.coherent_dma_mask =
-				parent->coherent_dma_mask;
+		if (!device->dev.dma_mask) {
+			if (parent)
+				device->dev.dma_mask = parent->dma_mask;
+			else
+				WARN_ON_ONCE(true);
+		}
+		if (!device->dev.coherent_dma_mask) {
+			if (parent)
+				device->dev.coherent_dma_mask =
+					parent->coherent_dma_mask;
+			else
+				WARN_ON_ONCE(true);
+		}
 	} else {
 		/*
 		 * The caller did not provide custom DMA operations. Use the
 		 * DMA mapping operations of the parent device.
 		 */
+		WARN_ON_ONCE(!parent);
 		device->dma_device = parent;
 	}
 

@@ -1276,7 +1276,6 @@ int ib_device_register_sysfs(struct ib_d
 	int ret;
 	int i;
 
-	WARN_ON_ONCE(!device->dev.parent);
 	ret = dev_set_name(class_dev, "%s", device->name);
 	if (ret)
 		return ret;

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Bodong Wang <[email protected]>

commit cd2a6e7d384b043d5d029e39663061cebc949385 upstream.

The change of slid from u16 to u32 results in sizeof(struct ib_wc) cross 64B boundary, which causes more cache misses. This patch rearranges the fields and remain the size to 64B.

Pahole output before this change:

struct ib_wc {
union {
u64 wr_id; /* 8 */
struct ib_cqe * wr_cqe; /* 8 */
}; /* 0 8 */
enum ib_wc_status status; /* 8 4 */
enum ib_wc_opcode opcode; /* 12 4 */
u32 vendor_err; /* 16 4 */
u32 byte_len; /* 20 4 */
struct ib_qp * qp; /* 24 8 */
union {
__be32 imm_data; /* 4 */
u32 invalidate_rkey; /* 4 */
} ex; /* 32 4 */
u32 src_qp; /* 36 4 */
int wc_flags; /* 40 4 */
u16 pkey_index; /* 44 2 */

/* XXX 2 bytes hole, try to pack */

u32 slid; /* 48 4 */
u8 sl; /* 52 1 */
u8 dlid_path_bits; /* 53 1 */
u8 port_num; /* 54 1 */
u8 smac[6]; /* 55 6 */

/* XXX 1 byte hole, try to pack */

u16 vlan_id; /* 62 2 */
/* --- cacheline 1 boundary (64 bytes) --- */
u8 network_hdr_type; /* 64 1 */

/* size: 72, cachelines: 2, members: 17 */ /* sum members: 62, holes: 2, sum holes: 3 */ /* padding: 7 */
/* last cacheline: 8 bytes */
};

Pahole output after this change:

struct ib_wc {
union {
u64 wr_id; /* 8 */
struct ib_cqe * wr_cqe; /* 8 */
}; /* 0 8 */
enum ib_wc_status status; /* 8 4 */
enum ib_wc_opcode opcode; /* 12 4 */
u32 vendor_err; /* 16 4 */
u32 byte_len; /* 20 4 */
struct ib_qp * qp; /* 24 8 */
union {
__be32 imm_data; /* 4 */
u32 invalidate_rkey; /* 4 */
} ex; /* 32 4 */
u32 src_qp; /* 36 4 */
u32 slid; /* 40 4 */
int wc_flags; /* 44 4 */
u16 pkey_index; /* 48 2 */
u8 sl; /* 50 1 */
u8 dlid_path_bits; /* 51 1 */
u8 port_num; /* 52 1 */
u8 smac[6]; /* 53 6 */

/* XXX 1 byte hole, try to pack */

u16 vlan_id; /* 60 2 */
u8 network_hdr_type; /* 62 1 */

/* size: 64, cachelines: 1, members: 17 */ /* sum members: 62, holes: 1, sum holes: 1 */ /* padding: 1 */
};

---
 include/rdma/ib_verbs.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -983,9 +983,9 @@ struct ib_wc {
 		u32		invalidate_rkey;
 	} ex;
 	u32			src_qp;
+	u32			slid;
 	int			wc_flags;
 	u16			pkey_index;
-	u32			slid;
 	u8			sl;
 	u8			dlid_path_bits;
 	u8			port_num;	/* valid only for DR SMPs on switches */

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Michael J. Ruhl <[email protected]>

commit 2ff124d597c2df8696169ce0006fc974c49a4569 upstream.

The ev_file is an optional parameter for CQ creation. If the parameter is not passed, the ev_file pointer will be NULL. Using that pointer to set the cq_context will result in an OOPs.

Verify that ev_file is not NULL before using.

---
 drivers/infiniband/core/uverbs_std_types.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -315,7 +315,7 @@ static int uverbs_create_cq_handler(stru
 	cq->uobject       = &obj->uobject;
 	cq->comp_handler  = ib_uverbs_comp_handler;
 	cq->event_handler = ib_uverbs_cq_event_handler;
-	cq->cq_context    = &ev_file->ev_queue;
+	cq->cq_context    = ev_file ? &ev_file->ev_queue : NULL;
 	obj->uobject.object = cq;
 	obj->uobject.user_handle = user_handle;
 	atomic_set(&cq->usecnt, 0);

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Anders Roxell <[email protected]>

commit 912ec316686df352028afb6efec59e47a958a24d upstream.

aarch64-linux-gnu-gcc -Wl,-no-as-needed -Wall
-lpthread seccomp_bpf.c -o seccomp_bpf
seccomp_bpf.c: In function 'tracer_ptrace':
seccomp_bpf.c:1720:12: error: '__NR_open' undeclared
(first use in this function)
if (nr == __NR_open)

            ^~~~~~~~~

seccomp_bpf.c:1720:12: note: each undeclared identifier is reported
only once for each function it appears in
In file included from seccomp_bpf.c:48:0:
seccomp_bpf.c: In function 'TRACE_syscall_ptrace_syscall_dropped':
seccomp_bpf.c:1795:39: error: '__NR_open' undeclared
(first use in this function)

  EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_open));
                                       ^

open(2) is a legacy syscall, replaced with openat(2) since 2.6.16. Thus new architectures in the kernel, such as arm64, don't implement these legacy syscalls.

---
 tools/testing/selftests/seccomp/seccomp_bpf.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1717,7 +1717,7 @@ void tracer_ptrace(struct __test_metadat
 
 	if (nr == __NR_getpid)
 		change_syscall(_metadata, tracee, __NR_getppid);
-	if (nr == __NR_open)
+	if (nr == __NR_openat)
 		change_syscall(_metadata, tracee, -1);
 }
 

@@ -1792,7 +1792,7 @@ TEST_F(TRACE_syscall, ptrace_syscall_dro
 					   true);
 
 	/* Tracer should skip the open syscall, resulting in EPERM. */
-	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_open));
+	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_openat));
 }
 
 TEST_F(TRACE_syscall, syscall_allowed)

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Arnd Bergmann <[email protected]>

commit 4c1baad223906943b595a887305f2e8124821dad upstream.

Running the compaction_test sometimes results in out-of-memory failures. When I debugged this, it turned out that the code to reset the number of hugepages to the initial value is simply broken since we write into an open sysctl file descriptor multiple times without seeking back to the start.

Adding the lseek here fixes the problem.

---
 tools/testing/selftests/vm/compaction_test.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -137,6 +137,8 @@ int check_compaction(unsigned long mem_f
 	printf("No of huge pages allocated = %d\n",
 	       (atoi(nr_hugepages)));
 
+	lseek(fd, 0, SEEK_SET);
+
 	if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages))
 	    != strlen(initial_nr_hugepages)) {
 		perror("Failed to write value to /proc/sys/vm/nr_hugepages\n");

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Bart Van Assche <[email protected]>

commit 6f301e06de4cf9ab7303f5acd43e64fcd4aa04be upstream.

The following sequence:
* Change queue pair state into IB_QPS_ERR.
* Post a work request on the queue pair.

Triggers the following race condition in the rdma_rxe driver:
* rxe_qp_error() triggers an asynchronous call of rxe_completer(), the function that examines the QP send queue.
* rxe_post_send() posts a work request on the QP send queue.

If rxe_completer() runs prior to rxe_post_send(), it will drain the send queue and the driver will assume no further action is necessary. However, once we post the send to the send queue, because the queue is in error, no send completion will ever happen and the send will get stuck. In order to process the send, we need to make sure that rxe_completer() gets run after a send is posted to a queue pair in an error state. This patch ensures that happens.

---
 drivers/infiniband/sw/rxe/rxe_verbs.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -814,6 +814,8 @@ static int rxe_post_send_kernel(struct r
 			(queue_count(qp->sq.queue) > 1);
 
 	rxe_run_task(&qp->req.task, must_sched);
+	if (unlikely(qp->req.state == QP_STATE_ERROR))
+		rxe_run_task(&qp->comp.task, 1);
 
 	return err;
 }

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Bart Van Assche <[email protected]>

commit 65567e41219888feec72fee1de98ccf1efbbc16d upstream.

The rxe driver works as follows:
* The send queue, receive queue and completion queues are implemented as circular buffers.
* ib_post_send() and ib_post_recv() calls are serialized through a spinlock.
* Removing elements from various queues happens from tasklet context. Tasklets are guaranteed to run on at most one CPU. This serializes access to these queues. See also rxe_completer(), rxe_requester() and rxe_responder().
* rxe_completer() processes the skbs queued onto qp->resp_pkts.
* rxe_requester() handles the send queue (qp->sq.queue).
* rxe_responder() processes the skbs queued onto qp->req_pkts.

Since rxe_drain_req_pkts() processes qp->req_pkts, calling rxe_drain_req_pkts() from rxe_requester() is racy. Hence this patch.

---
 drivers/infiniband/sw/rxe/rxe_loc.h  |    1 -
 drivers/infiniband/sw/rxe/rxe_req.c  |    9 +--------
 drivers/infiniband/sw/rxe/rxe_resp.c |    2 +-
 3 files changed, 2 insertions(+), 10 deletions(-)

@@ -237,7 +237,6 @@ int rxe_srq_from_attr(struct rxe_dev *rx
 
 void rxe_release(struct kref *kref);
 
-void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify);
 int rxe_completer(void *arg);
 int rxe_requester(void *arg);
 int rxe_responder(void *arg);

@@ -594,15 +594,8 @@ int rxe_requester(void *arg)
 	rxe_add_ref(qp);
 
 next_wqe:
-	if (unlikely(!qp->valid)) {
-		rxe_drain_req_pkts(qp, true);
+	if (unlikely(!qp->valid || qp->req.state == QP_STATE_ERROR))
 		goto exit;
-	}
-
-	if (unlikely(qp->req.state == QP_STATE_ERROR)) {
-		rxe_drain_req_pkts(qp, true);
-		goto exit;
-	}
 
 	if (unlikely(qp->req.state == QP_STATE_RESET)) {
 		qp->req.wqe_index = consumer_index(qp->sq.queue);

@@ -1210,7 +1210,7 @@ static enum resp_states do_class_d1e_err
 	}
 }
 
-void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify)
+static void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify)
 {
 	struct sk_buff *skb;
 

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Bart Van Assche <[email protected]>

commit bb3ffb7ad48a21e98a5c64eb21103a74fd9f03f6 upstream.

rxe_qp_cleanup() can sleep so it must be run in thread context and not in atomic context. This patch avoids that the following bug is triggered:

Kernel BUG at 00000000560033f3 [verbose debug info unavailable]
BUG: sleeping function called from invalid context at net/core/sock.c:2761
in_atomic(): 1, irqs_disabled(): 0, pid: 7, name: ksoftirqd/0
INFO: lockdep is turned off.
Preemption disabled at:
[<00000000b6e69628>] __do_softirq+0x4e/0x540
CPU: 0 PID: 7 Comm: ksoftirqd/0 Not tainted 4.15.0-rc7-dbg+ #4
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
Call Trace:
 dump_stack+0x85/0xbf
 ___might_sleep+0x177/0x260
 lock_sock_nested+0x1d/0x90
 inet_shutdown+0x2e/0xd0
 rxe_qp_cleanup+0x107/0x140 [rdma_rxe]
 rxe_elem_release+0x18/0x80 [rdma_rxe]
 rxe_requester+0x1cf/0x11b0 [rdma_rxe]
 rxe_do_task+0x78/0xf0 [rdma_rxe]
 tasklet_action+0x99/0x270
 __do_softirq+0xc0/0x540
 run_ksoftirqd+0x1c/0x70
 smpboot_thread_fn+0x1be/0x270
 kthread+0x117/0x130
 ret_from_fork+0x24/0x30

---
 drivers/infiniband/sw/rxe/rxe_qp.c    |   12 ++++++++++--
 drivers/infiniband/sw/rxe/rxe_verbs.h |    3 +++
 2 files changed, 13 insertions(+), 2 deletions(-)

@@ -824,9 +824,9 @@ void rxe_qp_destroy(struct rxe_qp *qp)
 }
 
 /* called when the last reference to the qp is dropped */
-void rxe_qp_cleanup(struct rxe_pool_entry *arg)
+static void rxe_qp_do_cleanup(struct work_struct *work)
 {
-	struct rxe_qp *qp = container_of(arg, typeof(*qp), pelem);
+	struct rxe_qp *qp = container_of(work, typeof(*qp), cleanup_work.work);
 
 	rxe_drop_all_mcast_groups(qp);
 

@@ -859,3 +859,11 @@ void rxe_qp_cleanup(struct rxe_pool_entr
 	kernel_sock_shutdown(qp->sk, SHUT_RDWR);
 	sock_release(qp->sk);
 }
+
+/* called when the last reference to the qp is dropped */
+void rxe_qp_cleanup(struct rxe_pool_entry *arg)
+{
+	struct rxe_qp *qp = container_of(arg, typeof(*qp), pelem);
+
+	execute_in_process_context(rxe_qp_do_cleanup, &qp->cleanup_work);
+}

@@ -35,6 +35,7 @@
 #define RXE_VERBS_H
 
 #include <linux/interrupt.h>
+#include <linux/workqueue.h>
 #include <rdma/rdma_user_rxe.h>
 #include "rxe_pool.h"
 #include "rxe_task.h"

@@ -281,6 +282,8 @@ struct rxe_qp {
 	struct timer_list rnr_nak_timer;
 
 	spinlock_t		state_lock; /* guard requester and completer */
+
+	struct execute_work	cleanup_work;
 };
 
 enum rxe_mem_state {

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Shilpasri G Bhat <[email protected]>

commit 3fa4680b860bf48b437d6a2c039789c4abe202ae upstream.

Some OpenPOWER boxes can have same pstate values for nominal and pmin pstates. In these boxes the current code will not initialize 'powernv_pstate_info.min' variable and result in erroneous CPU frequency reporting. This patch fixes this problem.

---
 drivers/cpufreq/powernv-cpufreq.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -288,9 +288,9 @@ next:
 
 		if (id == pstate_max)
 			powernv_pstate_info.max = i;
-		else if (id == pstate_nominal)
+		if (id == pstate_nominal)
 			powernv_pstate_info.nominal = i;
-		else if (id == pstate_min)
+		if (id == pstate_min)
 			powernv_pstate_info.min = i;
 
 		if (powernv_pstate_info.wof_enabled && id == pstate_turbo) {

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Christian König <[email protected]>

commit d0bc0c2a31c95002d37c3cc511ffdcab851b3256 upstream.

TTM tries to allocate coherent memory in chunks of 2MB first to improve TLB efficiency and falls back to allocating 4K pages if that fails.

Suppress the warning when the 2MB allocations fails since there is a valid fall back path.

---
 lib/swiotlb.c |   15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

@@ -586,7 +586,7 @@ phys_addr_t swiotlb_tbl_map_single(struc
 
 not_found:
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
-	if (printk_ratelimit())
+	if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
 		dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size);
 	return SWIOTLB_MAP_ERROR;
 found:

@@ -713,6 +713,7 @@ void *
 swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		       dma_addr_t *dma_handle, gfp_t flags)
 {
+	bool warn = !(flags & __GFP_NOWARN);
 	dma_addr_t dev_addr;
 	void *ret;
 	int order = get_order(size);

@@ -738,8 +739,8 @@ swiotlb_alloc_coherent(struct device *hw
 		 * GFP_DMA memory; fall back on map_single(), which
 		 * will grab memory from the lowest available address range.
 		 */
-		phys_addr_t paddr = map_single(hwdev, 0, size,
-					       DMA_FROM_DEVICE, 0);
+		phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE,
+					       warn ? 0 : DMA_ATTR_NO_WARN);
 		if (paddr == SWIOTLB_MAP_ERROR)
 			goto err_warn;
 

@@ -769,9 +770,11 @@ swiotlb_alloc_coherent(struct device *hw
 	return ret;
 
 err_warn:
-	pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n",
-		dev_name(hwdev), size);
-	dump_stack();
+	if (warn && printk_ratelimit()) {
+		pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n",
+			dev_name(hwdev), size);
+		dump_stack();
+	}
 
 	return NULL;
 }

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Brian Norris <[email protected]>

commit a64e7a79dd6030479caad603c8d78e6c9c14904f upstream.

Commit b014e96d1abb ("PCI: Protect pci_error_handlers->reset_notify() usage with device_lock()") resolves races between driver reset and removal, but it introduces some new deadlock problems. If we see a timeout while we've already started suspending, removing, or shutting down the driver, we might see:

(a) a worker thread, running mwifiex_pcie_work() ->

    mwifiex_pcie_card_reset_work() -> pci_reset_function()
(b) a removal thread, running mwifiex_pcie_remove() ->
    mwifiex_free_adapter() -> mwifiex_unregister() ->
    mwifiex_cleanup_pcie() -> cancel_work_sync(&card->work)

Unfortunately, mwifiex_pcie_remove() already holds the device lock that pci_reset_function() is now requesting, and so we see a deadlock.

It's necessary to cancel and synchronize our outstanding work before tearing down the driver, so we can't have this work wait indefinitely for the lock.

It's reasonable to only "try" to reset here, since this will mostly happen for cases where it's already difficult to reset the firmware anyway (e.g., while we're suspending or powering off the system). And if reset *really* needs to happen, we can always try again later.

---
 drivers/net/wireless/marvell/mwifiex/pcie.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -2781,7 +2781,10 @@ static void mwifiex_pcie_card_reset_work
 {
 	struct pcie_service_card *card = adapter->card;
 
-	pci_reset_function(card->dev);
+	/* We can't afford to wait here; remove() might be waiting on us. If we
+	 * can't grab the device lock, maybe we'll get another chance later.
+	 */
+	pci_try_reset_function(card->dev);
 }
 
 static void mwifiex_pcie_work(struct work_struct *work)

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Ravi Bangoria <[email protected]>

commit 0e4d819d0893dc043ea7b7cb6baf4be1e310bd96 upstream.

Recently, how the pointers being printed with %p has been changed by commit ad67b74d2469 ("printk: hash addresses printed with %p"). This is causing a regression while showing offset in the uprobe_events file. Instead of %p, use %px to display offset.

Before patch:

  # perf probe -vv -x /tmp/a.out main
  Opening /sys/kernel/debug/tracing//uprobe_events write=1
  Writing event: p:probe_a/main /tmp/a.out:0x58c

  # cat /sys/kernel/debug/tracing/uprobe_events
  p:probe_a/main /tmp/a.out:0x0000000049a0f352

After patch:

  # cat /sys/kernel/debug/tracing/uprobe_events
  p:probe_a/main /tmp/a.out:0x000000000000058c

---
 kernel/trace/trace_uprobe.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -608,7 +608,7 @@ static int probes_seq_show(struct seq_fi
 
 	/* Don't print "0x  (null)" when offset is 0 */
 	if (tu->offset) {
-		seq_printf(m, "0x%p", (void *)tu->offset);
+		seq_printf(m, "0x%px", (void *)tu->offset);
 	} else {
 		switch (sizeof(void *)) {
 		case 4:

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Mahesh Salgaonkar <[email protected]>

commit 8d81296cfcce89013a714feb8d25004a156f8181 upstream.

radix__flush_tlb_all() is called only in kexec path in real mode and any tracepoints at this stage will make kexec to fail if enabled.

To verify enable tlbie trace before kexec.

$ echo 1 > /sys/kernel/debug/tracing/events/powerpc/tlbie/enable
== kexec into new kernel and kexec fails.

Fix this by not calling trace_tlbie from radix__flush_tlb_all().

---
 arch/powerpc/mm/tlb-radix.c |    2 --
 1 file changed, 2 deletions(-)

@@ -600,14 +600,12 @@ void radix__flush_tlb_all(void)
 	 */
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(1), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 	/*
 	 * now flush host entires by passing PRS = 0 and LPID == 0
 	 */
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(0) : "memory");
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-	trace_tlbie(0, 0, rb, 0, ric, prs, r);
 }
 
 void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Sukadev Bhattiprolu <[email protected]>

commit 384dfd627f1ee67d028e6f14c6e9bf5a1e2a7a24 upstream.

clear_thread_tidr() is called in interrupt context as a part of delayed put of the task structure (i.e as a part of timer interrupt). To prevent a deadlock, block interrupts when holding vas_thread_id_lock to set/ clear TIDR for a task.

---
 arch/powerpc/kernel/process.c |   15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

@@ -1509,14 +1509,15 @@ static int assign_thread_tidr(void)
 {
 	int index;
 	int err;
+	unsigned long flags;
 
 again:
 	if (!ida_pre_get(&vas_thread_ida, GFP_KERNEL))
 		return -ENOMEM;
 
-	spin_lock(&vas_thread_id_lock);
+	spin_lock_irqsave(&vas_thread_id_lock, flags);
 	err = ida_get_new_above(&vas_thread_ida, 1, &index);
-	spin_unlock(&vas_thread_id_lock);
+	spin_unlock_irqrestore(&vas_thread_id_lock, flags);
 
 	if (err == -EAGAIN)
 		goto again;

@@ -1524,9 +1525,9 @@ again:
 		return err;
 
 	if (index > MAX_THREAD_CONTEXT) {
-		spin_lock(&vas_thread_id_lock);
+		spin_lock_irqsave(&vas_thread_id_lock, flags);
 		ida_remove(&vas_thread_ida, index);
-		spin_unlock(&vas_thread_id_lock);
+		spin_unlock_irqrestore(&vas_thread_id_lock, flags);
 		return -ENOMEM;
 	}
 

@@ -1535,9 +1536,11 @@ again:
 
 static void free_thread_tidr(int id)
 {
-	spin_lock(&vas_thread_id_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vas_thread_id_lock, flags);
 	ida_remove(&vas_thread_ida, id);
-	spin_unlock(&vas_thread_id_lock);
+	spin_unlock_irqrestore(&vas_thread_id_lock, flags);
 }
 
 /*

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Nicholas Piggin <[email protected]>

commit b00b62898631b756c3e123542bbb0487aa343dd9 upstream.

cp_abort is only required for user windows, because kernel context must not be preempted between a copy/paste pair.

Without this patch, the init task gets used_vas set when it runs the nx842_powernv_init initcall, which opens windows for kernel usage.

used_vas is then never cleared anywhere, so it gets propagated into all other tasks. It's a property of the address space, so it should really be cleared when a new mm is created (or in dup_mmap if the mmaps are marked as VM_DONTCOPY). For now we seem to have no such driver, so leave that for another patch.

---
 arch/powerpc/platforms/powernv/vas-window.c |   16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

@@ -1063,16 +1063,16 @@ struct vas_window *vas_tx_win_open(int v
 			rc = PTR_ERR(txwin->paste_kaddr);
 			goto free_window;
 		}
+	} else {
+		/*
+		 * A user mapping must ensure that context switch issues
+		 * CP_ABORT for this thread.
+		 */
+		rc = set_thread_uses_vas();
+		if (rc)
+			goto free_window;
 	}
 
-	/*
-	 * Now that we have a send window, ensure context switch issues
-	 * CP_ABORT for this thread.
-	 */
-	rc = -EINVAL;
-	if (set_thread_uses_vas() < 0)
-		goto free_window;
-
 	set_vinst_win(vinst, txwin);
 
 	return txwin;

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Alexey Kardashevskiy <[email protected]>

commit 62e984ddfd6b056d399e24113f5e6a7145e579d8 upstream.

Radix guests do normally invalidate process-scoped translations when a new pid is allocated but migrated guests do not invalidate these so migrated guests crash sometime, especially easy to reproduce with migration happening within first 10 seconds after the guest boot start on the same machine.

This adds the "Invalidate process-scoped translations" flush to fix radix guests migration.

---
 arch/powerpc/mm/pgtable_64.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -483,6 +483,8 @@ void mmu_partition_table_set_entry(unsig
 	if (old & PATB_HR) {
 		asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : :
 			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
+		asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
+			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
 		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1);
 	} else {
 		asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Cédric Le Goater <[email protected]>

commit 8e036c8d30a2cd9d8fc7442fbf6824e0a3e986e7 upstream.

The CPU event notification queues on sPAPR should be configured using a hardware CPU identifier.

The problem did not show up on the Power Hypervisor because pHyp supports 8 threads per core which keeps CPU number contiguous. This is not the case on all sPAPR virtual machines, some use SMT=1.

Also improve error logging by adding the CPU number.

---
 arch/powerpc/sysdev/xive/spapr.c |   16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

@@ -356,7 +356,8 @@ static int xive_spapr_configure_queue(u3
 
 	rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size);
 	if (rc) {
-		pr_err("Error %lld getting queue info prio %d\n", rc, prio);
+		pr_err("Error %lld getting queue info CPU %d prio %d\n", rc,
+		       target, prio);
 		rc = -EIO;
 		goto fail;
 	}

@@ -370,7 +371,8 @@ static int xive_spapr_configure_queue(u3
 	/* Configure and enable the queue in HW */
 	rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order);
 	if (rc) {
-		pr_err("Error %lld setting queue for prio %d\n", rc, prio);
+		pr_err("Error %lld setting queue for CPU %d prio %d\n", rc,
+		       target, prio);
 		rc = -EIO;
 	} else {
 		q->qpage = qpage;

@@ -389,8 +391,8 @@ static int xive_spapr_setup_queue(unsign
 	if (IS_ERR(qpage))
 		return PTR_ERR(qpage);
 
-	return xive_spapr_configure_queue(cpu, q, prio, qpage,
-					  xive_queue_shift);
+	return xive_spapr_configure_queue(get_hard_smp_processor_id(cpu),
+					  q, prio, qpage, xive_queue_shift);
 }
 
 static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc,

@@ -399,10 +401,12 @@ static void xive_spapr_cleanup_queue(uns
 	struct xive_q *q = &xc->queue[prio];
 	unsigned int alloc_order;
 	long rc;
+	int hw_cpu = get_hard_smp_processor_id(cpu);
 
-	rc = plpar_int_set_queue_config(0, cpu, prio, 0, 0);
+	rc = plpar_int_set_queue_config(0, hw_cpu, prio, 0, 0);
 	if (rc)
-		pr_err("Error %ld setting queue for prio %d\n", rc, prio);
+		pr_err("Error %ld setting queue for CPU %d prio %d\n", rc,
+		       hw_cpu, prio);
 
 	alloc_order = xive_alloc_order(xive_queue_shift);
 	free_pages((unsigned long)q->qpage, alloc_order);

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Christian König <[email protected]>

commit 5bffee867df7494ecd32c1e6ec4e8fc934c521b7 upstream.

We need to set shared_count even if we already have a fence to wait for.

v2: init i to -1 as well

---
 drivers/dma-buf/reservation.c |    8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

@@ -455,13 +455,15 @@ long reservation_object_wait_timeout_rcu
 					 unsigned long timeout)
 {
 	struct dma_fence *fence;
-	unsigned seq, shared_count, i = 0;
+	unsigned seq, shared_count;
 	long ret = timeout ? timeout : 1;
+	int i;
 
 retry:
 	shared_count = 0;
 	seq = read_seqcount_begin(&obj->seq);
 	rcu_read_lock();
+	i = -1;
 
 	fence = rcu_dereference(obj->fence_excl);
 	if (fence && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {

@@ -477,14 +479,14 @@ retry:
 		fence = NULL;
 	}
 
-	if (!fence && wait_all) {
+	if (wait_all) {
 		struct reservation_object_list *fobj =
 						rcu_dereference(obj->fence);
 
 		if (fobj)
 			shared_count = fobj->shared_count;
 
-		for (i = 0; i < shared_count; ++i) {
+		for (i = 0; !fence && i < shared_count; ++i) {
 			struct dma_fence *lfence = rcu_dereference(fobj->shared[i]);
 
 			if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Eugene Syromiatnikov <[email protected]>

commit 6dd0d2d22aa363fec075cb2577ba273ac8462e94 upstream.

For some reason, the implementation of some 16-bit ID system calls (namely, setuid16/setgid16 and setfsuid16/setfsgid16) used type cast instead of low2highgid/low2highuid macros for converting [GU]IDs, which led to incorrect handling of value of -1 (which ought to be considered invalid).

Discovered by strace test suite.

---
 arch/s390/kernel/compat_linux.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -110,7 +110,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setregid16,
 
 COMPAT_SYSCALL_DEFINE1(s390_setgid16, u16, gid)
 {
-	return sys_setgid((gid_t)gid);
+	return sys_setgid(low2highgid(gid));
 }
 
 COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid)

@@ -120,7 +120,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setreuid16,
 
 COMPAT_SYSCALL_DEFINE1(s390_setuid16, u16, uid)
 {
-	return sys_setuid((uid_t)uid);
+	return sys_setuid(low2highuid(uid));
 }
 
 COMPAT_SYSCALL_DEFINE3(s390_setresuid16, u16, ruid, u16, euid, u16, suid)

@@ -173,12 +173,12 @@ COMPAT_SYSCALL_DEFINE3(s390_getresgid16,
 
 COMPAT_SYSCALL_DEFINE1(s390_setfsuid16, u16, uid)
 {
-	return sys_setfsuid((uid_t)uid);
+	return sys_setfsuid(low2highuid(uid));
 }
 
 COMPAT_SYSCALL_DEFINE1(s390_setfsgid16, u16, gid)
 {
-	return sys_setfsgid((gid_t)gid);
+	return sys_setfsgid(low2highgid(gid));
 }
 
 static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info)

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Bjorn Andersson <[email protected]>

commit 566bd8902e7fa20bd412ed753e09e89c1c96939c upstream.

SMSM is not symmetrical, the incoming bits from WCNSS are available at index 6, but the outgoing host id for WCNSS is 3. Further more, upstream references the base of APCS (in contrast to downstream), so the register offset of 8 must be included.

---
 arch/arm64/boot/dts/qcom/msm8916.dtsi |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1435,8 +1435,8 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		qcom,ipc-1 = <&apcs 0 13>;
-		qcom,ipc-6 = <&apcs 0 19>;
+		qcom,ipc-1 = <&apcs 8 13>;
+		qcom,ipc-3 = <&apcs 8 19>;
 
 		apps_smsm: apps@0 {
 			reg = <0>;

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Arnd Bergmann <[email protected]>

commit ca32e0c4bf9ca4b87089c5a5ce945e5f2ec890da upstream.

dtc warns about obviously incorrect GPIO numbers for the audio codec on both lpc32xx boards:

arch/arm/boot/dts/lpc3250-phy3250.dtb: Warning (gpios_property): reset-gpio property size (12) too small for cell size 3 in /ahb/apb/i2c@400A0000/uda1380@18 arch/arm/boot/dts/lpc3250-phy3250.dtb: Warning (gpios_property): power-gpio property size (12) too small for cell size 3 in /ahb/apb/i2c@400A0000/uda1380@18 arch/arm/boot/dts/lpc3250-ea3250.dtb: Warning (gpios_property): reset-gpio property size (12) too small for cell size 3 in /ahb/apb/i2c@400A0000/uda1380@18 arch/arm/boot/dts/lpc3250-ea3250.dtb: Warning (gpios_property): power-gpio property size (12) too small for cell size 3 in /ahb/apb/i2c@400A0000/uda1380@18

It looks like the nodes are written for a different binding that combines the GPIO number into a single number rather than a bank/number pair. I found the right numbers on stackexchange.com, so this patch fixes the warning and has a reasonable chance of getting things to actually work.

---
 arch/arm/boot/dts/lpc3250-ea3250.dts  |    4 ++--
 arch/arm/boot/dts/lpc3250-phy3250.dts |    4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

@@ -156,8 +156,8 @@
 	uda1380: uda1380@18 {
 		compatible = "nxp,uda1380";
 		reg = <0x18>;
-		power-gpio = <&gpio 0x59 0>;
-		reset-gpio = <&gpio 0x51 0>;
+		power-gpio = <&gpio 3 10 0>;
+		reset-gpio = <&gpio 3 2 0>;
 		dac-clk = "wspll";
 	};
 

@@ -81,8 +81,8 @@
 	uda1380: uda1380@18 {
 		compatible = "nxp,uda1380";
 		reg = <0x18>;
-		power-gpio = <&gpio 0x59 0>;
-		reset-gpio = <&gpio 0x51 0>;
+		power-gpio = <&gpio 3 10 0>;
+		reset-gpio = <&gpio 3 2 0>;
 		dac-clk = "wspll";
 	};
 

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Patrice Chotard <[email protected]>

commit 7ac1f59c09a61e6af6622df6809e003b0af07f3d upstream.

The GPIO polarity is missing in the hdmi,hpd-gpio property, this fixes the following DT warnings:

arch/arm/boot/dts/stih410-b2120.dtb: Warning (gpios_property): hdmi,hpd-gpio property size (8) too small for cell size 2 in /soc/sti-display-subsystem/sti-hdmi@8d04000

arch/arm/boot/dts/stih407-b2120.dtb: Warning (gpios_property): hdmi,hpd-gpio property size (8) too small for cell size 2 in /soc/sti-display-subsystem/sti-hdmi@8d04000

arch/arm/boot/dts/stih410-b2260.dtb: Warning (gpios_property): hdmi,hpd-gpio property size (8) too small for cell size 2 in /soc/sti-display-subsystem/sti-hdmi@8d04000

[arnd: marked Cc:stable since this warning shows up with the latest dtc
by default, and is more likely to actually cause problems than the other patches from this series]

---
 arch/arm/boot/dts/stih407.dtsi |    3 ++-
 arch/arm/boot/dts/stih410.dtsi |    3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

@@ -8,6 +8,7 @@
  */
 #include "stih407-clock.dtsi"
 #include "stih407-family.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 / {
 	soc {
 		sti-display-subsystem {

@@ -122,7 +123,7 @@
 					 <&clk_s_d2_quadfs 0>,
 					 <&clk_s_d2_quadfs 1>;
 
-				hdmi,hpd-gpio = <&pio5 3>;
+				hdmi,hpd-gpio = <&pio5 3 GPIO_ACTIVE_LOW>;
 				reset-names = "hdmi";
 				resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
 				ddc = <&hdmiddc>;

@@ -9,6 +9,7 @@
 #include "stih410-clock.dtsi"
 #include "stih407-family.dtsi"
 #include "stih410-pinctrl.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 / {
 	aliases {
 		bdisp0 = &bdisp0;

@@ -213,7 +214,7 @@
 					 <&clk_s_d2_quadfs 0>,
 					 <&clk_s_d2_quadfs 1>;
 
-				hdmi,hpd-gpio = <&pio5 3>;
+				hdmi,hpd-gpio = <&pio5 3 GPIO_ACTIVE_LOW>;
 				reset-names = "hdmi";
 				resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
 				ddc = <&hdmiddc>;

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Arnd Bergmann <[email protected]>

commit e8bfa0422469cdfc86be3f525f621b1d44d2481b upstream.

The clcd device is lacking an interrupt-parent property, which makes the interrupt unusable and shows up as a warning with the latest dtc version:

arch/arm/boot/dts/ste-nomadik-s8815.dtb: Warning (interrupts_property): Missing interrupt-parent for /amba/clcd@10120000 arch/arm/boot/dts/ste-nomadik-nhk15.dtb: Warning (interrupts_property): Missing interrupt-parent for /amba/clcd@10120000

I looked up the old board files and found that this interrupt has the same irqchip as all the other on-chip device, it just needs one extra line.

---
 arch/arm/boot/dts/ste-nomadik-stn8815.dtsi |    1 +
 1 file changed, 1 insertion(+)

@@ -750,6 +750,7 @@
 			reg = <0x10120000 0x1000>;
 			interrupt-names = "combined";
 			interrupts = <14>;
+			interrupt-parent = <&vica>;
 			clocks = <&clcdclk>, <&hclkclcd>;
 			clock-names = "clcdclk", "apb_pclk";
 			status = "disabled";

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Sean Wang <[email protected]>

commit b96a696fb2a8dd1ee4e6cfee48dcac270fc53287 upstream.

Fix that bananapi-r2 booting from SD-card would fail since incorrect polarity is applied to the previous setup with GPIO_ACTIVE_HIGH.

---
 arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -204,7 +204,7 @@
 	bus-width = <4>;
 	max-frequency = <50000000>;
 	cap-sd-highspeed;
-	cd-gpios = <&pio 261 0>;
+	cd-gpios = <&pio 261 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&mt6323_vmch_reg>;
 	vqmmc-supply = <&mt6323_vio18_reg>;
 };

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Viresh Kumar <[email protected]>

commit 6ffb5b4f248fe53e0361b8cbc2a523b432566442 upstream.

The interrupt-parent of rtc was missing, add it.

---
 arch/arm/boot/dts/spear600.dtsi |    1 +
 1 file changed, 1 insertion(+)

@@ -194,6 +194,7 @@
 			rtc: rtc@fc900000 {
 				compatible = "st,spear600-rtc";
 				reg = <0xfc900000 0x1000>;
+				interrupt-parent = <&vic0>;
 				interrupts = <10>;
 				status = "disabled";
 			};

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Viresh Kumar <[email protected]>

commit cdd10409914184c7eee5ae3e11beb890c9c16c61 upstream.

The "dmas" cells for the designware DMA controller need to have only 3 properties apart from the phandle: request line, src master and destination master. But the commit 6e8887f60f60 updated it incorrectly while moving from platform code to DT. Fix it.

---
 Documentation/devicetree/bindings/dma/snps-dma.txt |    2 +-
 arch/arm/boot/dts/spear1340.dtsi                   |    4 ++--
 arch/arm/boot/dts/spear13xx.dtsi                   |    6 +++---
 3 files changed, 6 insertions(+), 6 deletions(-)

@@ -64,6 +64,6 @@ Example:
 		reg = <0xe0000000 0x1000>;
 		interrupts = <0 35 0x4>;
 		dmas = <&dmahost 12 0 1>,
-			<&dmahost 13 0 1 0>;
+			<&dmahost 13 1 0>;
 		dma-names = "rx", "rx";
 	};

@@ -142,8 +142,8 @@
 				reg = <0xb4100000 0x1000>;
 				interrupts = <0 105 0x4>;
 				status = "disabled";
-				dmas = <&dwdma0 0x600 0 0 1>, /* 0xC << 11 */
-					<&dwdma0 0x680 0 1 0>; /* 0xD << 7 */
+				dmas = <&dwdma0 12 0 1>,
+					<&dwdma0 13 1 0>;
 				dma-names = "tx", "rx";
 			};
 

@@ -100,7 +100,7 @@
 			reg = <0xb2800000 0x1000>;
 			interrupts = <0 29 0x4>;
 			status = "disabled";
-			dmas = <&dwdma0 0 0 0 0>;
+			dmas = <&dwdma0 0 0 0>;
 			dma-names = "data";
 		};
 

@@ -290,8 +290,8 @@
 				#size-cells = <0>;
 				interrupts = <0 31 0x4>;
 				status = "disabled";
-				dmas = <&dwdma0 0x2000 0 0 0>, /* 0x4 << 11 */
-					<&dwdma0 0x0280 0 0 0>;  /* 0x5 << 7 */
+				dmas = <&dwdma0 4 0 0>,
+					<&dwdma0 5 0 0>;
 				dma-names = "tx", "rx";
 			};
 

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Viresh Kumar <[email protected]>

commit f8975cb1b8a36d0839b6365235778dd9df1d04ca upstream.

This fixes the following warning by also sending the flags argument for gpio controllers:

Property 'cs-gpios', cell 6 is not a phandle reference in /ahb/apb/spi@e0100000

---
 arch/arm/boot/dts/spear1310-evb.dts |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -349,7 +349,7 @@
 			spi0: spi@e0100000 {
 				status = "okay";
 				num-cs = <3>;
-				cs-gpios = <&gpio1 7 0>, <&spics 0>, <&spics 1>;
+				cs-gpios = <&gpio1 7 0>, <&spics 0 0>, <&spics 1 0>;
 
 				stmpe610@0 {
 					compatible = "st,stmpe610";

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Lucas De Marchi <[email protected]>

commit 33aa69ed8aacd92dea12671e52eb3ca6ac2d7a49 upstream.

CFL was missing from intel_early_ids[]. The PCI ID needs to be there to allow the memory region to be stolen, otherwise we could have RAM being arbitrarily overwritten if for example we keep using the UEFI framebuffer, depending on how BIOS has set up the e820 map.

---
 arch/x86/kernel/early-quirks.c |    1 +
 include/drm/i915_pciids.h      |    6 ++++++
 2 files changed, 7 insertions(+)

@@ -527,6 +527,7 @@ static const struct pci_device_id intel_
 	INTEL_SKL_IDS(&gen9_early_ops),
 	INTEL_BXT_IDS(&gen9_early_ops),
 	INTEL_KBL_IDS(&gen9_early_ops),
+	INTEL_CFL_IDS(&gen9_early_ops),
 	INTEL_GLK_IDS(&gen9_early_ops),
 	INTEL_CNL_IDS(&gen9_early_ops),
 };

@@ -392,6 +392,12 @@
 	INTEL_VGA_DEVICE(0x3EA8, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x3EA5, info)  /* ULT GT3 */
 
+#define INTEL_CFL_IDS(info) \
+	INTEL_CFL_S_GT1_IDS(info), \
+	INTEL_CFL_S_GT2_IDS(info), \
+	INTEL_CFL_H_GT2_IDS(info), \
+	INTEL_CFL_U_GT3_IDS(info)
+
 /* CNL U 2+2 */
 #define INTEL_CNL_U_GT2_IDS(info) \
 	INTEL_VGA_DEVICE(0x5A52, info), \

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Kirill A. Shutemov <[email protected]>

commit 5bf30316991d5bcda046343ee77d823cf16fdd03 upstream.

Currently kexec() will crash when switching into a 5-level paging enabled kernel.

I missed that we need to change relocate_kernel() to set CR4.LA57 flag if the kernel has 5-level paging enabled.

I avoided using #ifdef CONFIG_X86_5LEVEL here and inferred if we need to enable 5-level paging from previous CR4 value. This way the code is ready for boot-time switching between paging modes.

With this patch applied, in addition to kexec 4-to-4 which always worked, we can kexec 4-to-5 and 5-to-5 - while 5-to-4 will need more work.

---
 arch/x86/kernel/relocate_kernel_64.S |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -68,6 +68,9 @@ relocate_kernel:
 	movq	%cr4, %rax
 	movq	%rax, CR4(%r11)
 
+	/* Save CR4. Required to enable the right paging mode later. */
+	movq	%rax, %r13
+
 	/* zero out flags, and disable interrupts */
 	pushq $0
 	popfq

@@ -126,8 +129,13 @@ identity_mapped:
 	/*
 	 * Set cr4 to a known state:
 	 *  - physical address extension enabled
+	 *  - 5-level paging, if it was enabled before
 	 */
 	movl	$X86_CR4_PAE, %eax
+	testq	$X86_CR4_LA57, %r13
+	jz	1f
+	orl	$X86_CR4_LA57, %eax
+1:
 	movq	%rax, %cr4
 
 	jmp 1f

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Juergen Gross <[email protected]>

commit 4f277295e54c5b7340e48efea3fc5cc21a2872b7 upstream.

When running as Xen pv guest %gs is initialized some time after C code is started. Depending on stack protector usage this might be too late, resulting in page faults.

So setup %gs and MSR_GS_BASE in assembly code already.

---
 arch/x86/xen/xen-head.S |   16 ++++++++++++++++
 1 file changed, 16 insertions(+)

@@ -9,7 +9,9 @@
 
 #include <asm/boot.h>
 #include <asm/asm.h>
+#include <asm/msr.h>
 #include <asm/page_types.h>
+#include <asm/percpu.h>
 #include <asm/unwind_hints.h>
 
 #include <xen/interface/elfnote.h>

@@ -35,6 +37,20 @@ ENTRY(startup_xen)
 	mov %_ASM_SI, xen_start_info
 	mov $init_thread_union+THREAD_SIZE, %_ASM_SP
 
+#ifdef CONFIG_X86_64
+	/* Set up %gs.
+	 *
+	 * The base of %gs always points to the bottom of the irqstack
+	 * union.  If the stack protector canary is enabled, it is
+	 * located at %gs:40.  Note that, on SMP, the boot cpu uses
+	 * init data section till per cpu areas are set up.
+	 */
+	movl	$MSR_GS_BASE,%ecx
+	movq	$INIT_PER_CPU_VAR(irq_stack_union),%rax
+	cdq
+	wrmsr
+#endif
+
 	jmp xen_start_kernel
 END(startup_xen)
 	__FINIT

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Rafael J. Wysocki <[email protected]>

commit f859422075165e32c00c8d75d63f300015cc07ae upstream.

Update the APM driver overlooked by commit 1b39e3f813b4 (cpuidle: Make drivers initialize polling state) to initialize the polling state like the other cpuidle drivers modified by that commit to prevent cpuidle from crashing.

---
 arch/x86/kernel/apm_32.c |    1 +
 1 file changed, 1 insertion(+)

@@ -2389,6 +2389,7 @@ static int __init apm_init(void)
 	if (HZ != 100)
 		idle_period = (idle_period * HZ) / 100;
 	if (idle_threshold < 100) {
+		cpuidle_poll_state_init(&apm_idle_driver);
 		if (!cpuidle_register_driver(&apm_idle_driver))
 			if (cpuidle_register_device(&apm_cpuidle_device))
 				cpuidle_unregister_driver(&apm_idle_driver);

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Michal Hocko <[email protected]>

commit 9bb5a391f9a5707e04763cf14298fc4cc29bfecd upstream.

Bharata has noticed that onlining a newly added memory doesn't increase the total memory, pointing to commit f7f99100d8d9 ("mm: stop zeroing memory during allocation in vmemmap") as a culprit. This commit has changed the way how the memory for memmaps is initialized and moves it from the allocation time to the initialization time. This works properly for the early memmap init path.

It doesn't work for the memory hotplug though because we need to mark page as reserved when the sparsemem section is created and later initialize it completely during onlining. memmap_init_zone is called in the early stage of onlining. With the current code it calls __init_single_page and as such it clears up the whole stage and therefore online_pages_range skips those pages.

Fix this by skipping mm_zero_struct_page in __init_single_page for memory hotplug path. This is quite uggly but unifying both early init and memory hotplug init paths is a large project. Make sure we plug the regression at least.

---
 mm/page_alloc.c |   22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

@@ -1177,9 +1177,10 @@ static void free_one_page(struct zone *z
 }
 
 static void __meminit __init_single_page(struct page *page, unsigned long pfn,
-				unsigned long zone, int nid)
+				unsigned long zone, int nid, bool zero)
 {
-	mm_zero_struct_page(page);
+	if (zero)
+		mm_zero_struct_page(page);
 	set_page_links(page, zone, nid, pfn);
 	init_page_count(page);
 	page_mapcount_reset(page);

@@ -1194,9 +1195,9 @@ static void __meminit __init_single_page
 }
 
 static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone,
-					int nid)
+					int nid, bool zero)
 {
-	return __init_single_page(pfn_to_page(pfn), pfn, zone, nid);
+	return __init_single_page(pfn_to_page(pfn), pfn, zone, nid, zero);
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT

@@ -1217,7 +1218,7 @@ static void __meminit init_reserved_page
 		if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
 			break;
 	}
-	__init_single_pfn(pfn, zid, nid);
+	__init_single_pfn(pfn, zid, nid, true);
 }
 #else
 static inline void init_reserved_page(unsigned long pfn)

@@ -1514,7 +1515,7 @@ static unsigned long __init deferred_ini
 					page++;
 				else
 					page = pfn_to_page(pfn);
-				__init_single_page(page, pfn, zid, nid);
+				__init_single_page(page, pfn, zid, nid, true);
 				cond_resched();
 			}
 		}

@@ -5393,15 +5394,20 @@ not_early:
 		 * can be created for invalid pages (for alignment)
 		 * check here not to call set_pageblock_migratetype() against
 		 * pfn out of zone.
+		 *
+		 * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
+		 * because this is done early in sparse_add_one_section
 		 */
 		if (!(pfn & (pageblock_nr_pages - 1))) {
 			struct page *page = pfn_to_page(pfn);
 
-			__init_single_page(page, pfn, zone, nid);
+			__init_single_page(page, pfn, zone, nid,
+					context != MEMMAP_HOTPLUG);
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 			cond_resched();
 		} else {
-			__init_single_pfn(pfn, zone, nid);
+			__init_single_pfn(pfn, zone, nid,
+					context != MEMMAP_HOTPLUG);
 		}
 	}
 }

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Dan Williams <[email protected]>

commit 8e1eb3fa009aa7c0b944b3c8b26b07de0efb3200 upstream.

At entry userspace may have (maliciously) populated the extra registers outside the syscall calling convention with arbitrary values that could be useful in a speculative execution (Spectre style) attack.

Clear these registers to minimize the kernel's attack surface.

Note, this only clears the extra registers and not the unused registers for syscalls less than 6 arguments, since those registers are likely to be clobbered well before their values could be put to use under speculation.

Note, Linus found that the XOR instructions can be executed with minimized cost if interleaved with the PUSH instructions, and Ingo's analysis found that R10 and R11 should be included in the register clearing beyond the typical 'extra' syscall calling convention registers.

---
 arch/x86/entry/entry_64.S |   13 +++++++++++++
 1 file changed, 13 insertions(+)

@@ -235,13 +235,26 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
 	pushq	%r8				/* pt_regs->r8 */
 	pushq	%r9				/* pt_regs->r9 */
 	pushq	%r10				/* pt_regs->r10 */
+	/*
+	 * Clear extra registers that a speculation attack might
+	 * otherwise want to exploit. Interleave XOR with PUSH
+	 * for better uop scheduling:
+	 */
+	xorq	%r10, %r10			/* nospec   r10 */
 	pushq	%r11				/* pt_regs->r11 */
+	xorq	%r11, %r11			/* nospec   r11 */
 	pushq	%rbx				/* pt_regs->rbx */
+	xorl	%ebx, %ebx			/* nospec   rbx */
 	pushq	%rbp				/* pt_regs->rbp */
+	xorl	%ebp, %ebp			/* nospec   rbp */
 	pushq	%r12				/* pt_regs->r12 */
+	xorq	%r12, %r12			/* nospec   r12 */
 	pushq	%r13				/* pt_regs->r13 */
+	xorq	%r13, %r13			/* nospec   r13 */
 	pushq	%r14				/* pt_regs->r14 */
+	xorq	%r14, %r14			/* nospec   r14 */
 	pushq	%r15				/* pt_regs->r15 */
+	xorq	%r15, %r15			/* nospec   r15 */
 	UNWIND_HINT_REGS
 
 	TRACE_IRQS_OFF

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Dan Williams <[email protected]>

commit 6b8cf5cc9965673951f1ab3f0e3cf23d06e3e2ee upstream.

At entry userspace may have populated registers with values that could otherwise be useful in a speculative execution attack. Clear them to minimize the kernel's attack surface.

Originally-From: Andi Kleen <[email protected]>

---
 arch/x86/entry/entry_64_compat.S |   30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

@@ -85,15 +85,25 @@ ENTRY(entry_SYSENTER_compat)
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
+	xorq	%r15, %r15		/* nospec   r15 */
 	cld
 
 	/*

@@ -214,15 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwfram
 	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
+	xorq	%r15, %r15		/* nospec   r15 */
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER

@@ -338,15 +358,25 @@ ENTRY(entry_INT80_compat)
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   %r12                    /* pt_regs->r12 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   %r13                    /* pt_regs->r13 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   %r14                    /* pt_regs->r14 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   %r15                    /* pt_regs->r15 */
+	xorq	%r15, %r15		/* nospec   r15 */
 	cld
 
 	/*

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Geert Uytterhoeven <[email protected]>

commit df5d45aa08f848b79caf395211b222790534ccc7 upstream.

Create a new function attribute __optimize, which allows to specify an optimization level on a per-function basis.

---
 include/linux/compiler-gcc.h |    4 ++++
 include/linux/compiler.h     |    4 ++++
 2 files changed, 8 insertions(+)

@@ -196,6 +196,10 @@
 #endif /* __CHECKER__ */
 #endif /* GCC_VERSION >= 40300 */
 
+#if GCC_VERSION >= 40400
+#define __optimize(level)	__attribute__((__optimize__(level)))
+#endif /* GCC_VERSION >= 40400 */
+
 #if GCC_VERSION >= 40500
 
 #ifndef __CHECKER__

@@ -271,6 +271,10 @@ static __always_inline void __write_once
 
 #endif /* __ASSEMBLY__ */
 
+#ifndef __optimize
+# define __optimize(level)
+#endif
+
 /* Compile time object size, -1 for unknown */
 #ifndef __compiletime_object_size
 # define __compiletime_object_size(obj) -1

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Geert Uytterhoeven <[email protected]>

commit d9afaaa4ff7af8b87d4a205e48cb8a6f666d7f01 upstream.

Gcc versions before 4.4 do not recognize the __optimize__ compiler attribute:

warning: ‘__optimize__’ attribute directive ignored

---
 include/linux/compiler-gcc.h |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -167,8 +167,6 @@
 
 #if GCC_VERSION >= 40100
 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
-
-#define __nostackprotector	__attribute__((__optimize__("no-stack-protector")))
 #endif
 
 #if GCC_VERSION >= 40300

@@ -198,6 +196,7 @@
 
 #if GCC_VERSION >= 40400
 #define __optimize(level)	__attribute__((__optimize__(level)))
+#define __nostackprotector	__optimize("no-stack-protector")
 #endif /* GCC_VERSION >= 40400 */
 
 #if GCC_VERSION >= 40500

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Artem Savkov <[email protected]>

commit dd78c832ffaf86eb6434e56de4bc3bc31f03f771 upstream.

According to crypto/rng.h generate function should return 0 on success and < 0 on error.

---
 drivers/crypto/sunxi-ss/sun4i-ss-prng.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -52,5 +52,5 @@ int sun4i_ss_prng_generate(struct crypto
 
 	writel(0, ss->base + SS_CTL);
 	spin_unlock(&ss->slock);
-	return dlen;
+	return 0;
 }

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Artem Savkov <[email protected]>

commit 2e7d1d61ea6c0f1c4da5eb82cafac750d55637a7 upstream.

Lockdep detects a possible deadlock in sun4i_ss_prng_generate() and throws an "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage" warning. Disabling softirqs to fix this.

---
 drivers/crypto/sunxi-ss/sun4i-ss-prng.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -28,7 +28,7 @@ int sun4i_ss_prng_generate(struct crypto
 	algt = container_of(alg, struct sun4i_ss_alg_template, alg.rng);
 	ss = algt->ss;
 
-	spin_lock(&ss->slock);
+	spin_lock_bh(&ss->slock);
 
 	writel(mode, ss->base + SS_CTL);
 

@@ -51,6 +51,6 @@ int sun4i_ss_prng_generate(struct crypto
 	}
 
 	writel(0, ss->base + SS_CTL);
-	spin_unlock(&ss->slock);
+	spin_unlock_bh(&ss->slock);
 	return 0;
 }

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Balbir Singh <[email protected]>

commit 4dd5f8a99e791a8c6500e3592f3ce81ae7edcde1 upstream.

This patch splits the linear mapping if the hot-unplug range is smaller than the mapping size. The code detects if the mapping needs to be split into a smaller size and if so, uses the stop machine infrastructure to clear the existing mapping and then remap the remaining range using a smaller page size.

The code will skip any region of the mapping that overlaps with kernel text and warn about it once. We don't want to remove a mapping where the kernel text and the LMB we intend to remove overlap in the same TLB mapping as it may affect the currently executing code.

I've tested these changes under a kvm guest with 2 vcpus, from a split mapping point of view, some of the caveats mentioned above applied to the testing I did.

---
 arch/powerpc/mm/pgtable-radix.c |   95 +++++++++++++++++++++++++++++++---------
 1 file changed, 74 insertions(+), 21 deletions(-)

@@ -17,6 +17,7 @@
 #include <linux/of_fdt.h>
 #include <linux/mm.h>
 #include <linux/string_helpers.h>
+#include <linux/stop_machine.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>

@@ -671,6 +672,30 @@ static void free_pmd_table(pmd_t *pmd_st
 	pud_clear(pud);
 }
 
+struct change_mapping_params {
+	pte_t *pte;
+	unsigned long start;
+	unsigned long end;
+	unsigned long aligned_start;
+	unsigned long aligned_end;
+};
+
+static int stop_machine_change_mapping(void *data)
+{
+	struct change_mapping_params *params =
+			(struct change_mapping_params *)data;
+
+	if (!data)
+		return -1;
+
+	spin_unlock(&init_mm.page_table_lock);
+	pte_clear(&init_mm, params->aligned_start, params->pte);
+	create_physical_mapping(params->aligned_start, params->start);
+	create_physical_mapping(params->end, params->aligned_end);
+	spin_lock(&init_mm.page_table_lock);
+	return 0;
+}
+
 static void remove_pte_table(pte_t *pte_start, unsigned long addr,
 			     unsigned long end)
 {

@@ -699,6 +724,52 @@ static void remove_pte_table(pte_t *pte_
 	}
 }
 
+/*
+ * clear the pte and potentially split the mapping helper
+ */
+static void split_kernel_mapping(unsigned long addr, unsigned long end,
+				unsigned long size, pte_t *pte)
+{
+	unsigned long mask = ~(size - 1);
+	unsigned long aligned_start = addr & mask;
+	unsigned long aligned_end = addr + size;
+	struct change_mapping_params params;
+	bool split_region = false;
+
+	if ((end - addr) < size) {
+		/*
+		 * We're going to clear the PTE, but not flushed
+		 * the mapping, time to remap and flush. The
+		 * effects if visible outside the processor or
+		 * if we are running in code close to the
+		 * mapping we cleared, we are in trouble.
+		 */
+		if (overlaps_kernel_text(aligned_start, addr) ||
+			overlaps_kernel_text(end, aligned_end)) {
+			/*
+			 * Hack, just return, don't pte_clear
+			 */
+			WARN_ONCE(1, "Linear mapping %lx->%lx overlaps kernel "
+				  "text, not splitting\n", addr, end);
+			return;
+		}
+		split_region = true;
+	}
+
+	if (split_region) {
+		params.pte = pte;
+		params.start = addr;
+		params.end = end;
+		params.aligned_start = addr & ~(size - 1);
+		params.aligned_end = min_t(unsigned long, aligned_end,
+				(unsigned long)__va(memblock_end_of_DRAM()));
+		stop_machine(stop_machine_change_mapping, &params, NULL);
+		return;
+	}
+
+	pte_clear(&init_mm, addr, pte);
+}
+
 static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
 			     unsigned long end)
 {

@@ -714,13 +785,7 @@ static void remove_pmd_table(pmd_t *pmd_
 			continue;
 
 		if (pmd_huge(*pmd)) {
-			if (!IS_ALIGNED(addr, PMD_SIZE) ||
-			    !IS_ALIGNED(next, PMD_SIZE)) {
-				WARN_ONCE(1, "%s: unaligned range\n", __func__);
-				continue;
-			}
-
-			pte_clear(&init_mm, addr, (pte_t *)pmd);
+			split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd);
 			continue;
 		}
 

@@ -745,13 +810,7 @@ static void remove_pud_table(pud_t *pud_
 			continue;
 
 		if (pud_huge(*pud)) {
-			if (!IS_ALIGNED(addr, PUD_SIZE) ||
-			    !IS_ALIGNED(next, PUD_SIZE)) {
-				WARN_ONCE(1, "%s: unaligned range\n", __func__);
-				continue;
-			}
-
-			pte_clear(&init_mm, addr, (pte_t *)pud);
+			split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud);
 			continue;
 		}
 

@@ -777,13 +836,7 @@ static void remove_pagetable(unsigned lo
 			continue;
 
 		if (pgd_huge(*pgd)) {
-			if (!IS_ALIGNED(addr, PGDIR_SIZE) ||
-			    !IS_ALIGNED(next, PGDIR_SIZE)) {
-				WARN_ONCE(1, "%s: unaligned range\n", __func__);
-				continue;
-			}
-
-			pte_clear(&init_mm, addr, (pte_t *)pgd);
+			split_kernel_mapping(addr, end, PGDIR_SIZE, (pte_t *)pgd);
 			continue;
 		}
 

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Nadav Amit <[email protected]>

commit 14b1fcc62043729d12e8ae00f8297ab2ffe9fa91 upstream.

The comment is confusing since the path is taken when CONFIG_PAGE_TABLE_ISOLATION=y is disabled (while the comment says it is not taken).

---
 arch/x86/entry/entry_64.S |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -213,7 +213,7 @@ ENTRY(entry_SYSCALL_64)
 
 	swapgs
 	/*
-	 * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+	 * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it
 	 * is not required to switch CR3.
 	 */
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: David Woodhouse <[email protected]>

commit 1751342095f0d2b36fa8114d8e12c5688c455ac4 upstream.

Intel have retroactively blessed the 0xc2 microcode on Skylake mobile and desktop parts, and the Gemini Lake 0x22 microcode is apparently fine too. We blacklisted the latter purely because it was present with all the other problematic ones in the 2018-01-08 release, but now it's explicitly listed as OK.

We still list 0x84 for the various Kaby Lake / Coffee Lake parts, as that appeared in one version of the blacklist and then reverted to 0x80 again. We can change it if 0x84 is actually announced to be safe.

---
 arch/x86/kernel/cpu/intel.c |    4 ----
 1 file changed, 4 deletions(-)

@@ -123,8 +123,6 @@ static const struct sku_microcode spectr
 	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x84 },
 	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
 	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
-	{ INTEL_FAM6_SKYLAKE_MOBILE,	0x03,	0xc2 },
-	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
 	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
 	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
 	{ INTEL_FAM6_BROADWELL_XEON_D,	0x02,	0x14 },

@@ -136,8 +134,6 @@ static const struct sku_microcode spectr
 	{ INTEL_FAM6_HASWELL_X,		0x02,	0x3b },
 	{ INTEL_FAM6_HASWELL_X,		0x04,	0x10 },
 	{ INTEL_FAM6_IVYBRIDGE_X,	0x04,	0x42a },
-	/* Updated in the 20180108 release; blacklist until we know otherwise */
-	{ INTEL_FAM6_ATOM_GEMINI_LAKE,	0x01,	0x22 },
 	/* Observed in the wild */
 	{ INTEL_FAM6_SANDYBRIDGE_X,	0x06,	0x61b },
 	{ INTEL_FAM6_SANDYBRIDGE_X,	0x07,	0x712 },

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: David Woodhouse <[email protected]>

commit d37fc6d360a404b208547ba112e7dabb6533c7fc upstream.

Arjan points out that the Intel document only clears the 0xc2 microcode on *some* parts with CPUID 506E3 (INTEL_FAM6_SKYLAKE_DESKTOP stepping 3). For the Skylake H/S platform it's OK but for Skylake E3 which has the same CPUID it isn't (yet) cleared.

So removing it from the blacklist was premature. Put it back for now.

Also, Arjan assures me that the 0x84 microcode for Kaby Lake which was featured in one of the early revisions of the Intel document was never released to the public, and won't be until/unless it is also validated as safe. So those can change to 0x80 which is what all *other* versions of the doc have identified.

Once the retrospective testing of existing public microcodes is done, we should be back into a mode where new microcodes are only released in batches and we shouldn't even need to update the blacklist for those anyway, so this tweaking of the list isn't expected to be a thing which keeps happening.

---
 arch/x86/kernel/cpu/intel.c |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

@@ -116,13 +116,14 @@ struct sku_microcode {
 	u32 microcode;
 };
 static const struct sku_microcode spectre_bad_microcodes[] = {
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x80 },
 	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
 	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
+	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
 	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
 	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
 	{ INTEL_FAM6_BROADWELL_XEON_D,	0x02,	0x14 },

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: David Woodhouse <[email protected]>

commit f208820a321f9b23d77d7eed89945d862d62a3ed upstream.

This reverts commit 64e16720ea0879f8ab4547e3b9758936d483909b.

We cannot call C functions like that, without marking all the call-clobbered registers as, well, clobbered. We might have got away with it for now because the __ibp_barrier() function was *fairly* unlikely to actually use any other registers. But no. Just no.

---
 arch/x86/include/asm/nospec-branch.h |   13 +++++++++----
 arch/x86/include/asm/processor.h     |    3 ---
 arch/x86/kernel/cpu/bugs.c           |    6 ------
 3 files changed, 9 insertions(+), 13 deletions(-)

@@ -164,10 +164,15 @@ static inline void vmexit_fill_RSB(void)
 
 static inline void indirect_branch_prediction_barrier(void)
 {
-	alternative_input("",
-			  "call __ibp_barrier",
-			  X86_FEATURE_USE_IBPB,
-			  ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory"));
+	asm volatile(ALTERNATIVE("",
+				 "movl %[msr], %%ecx\n\t"
+				 "movl %[val], %%eax\n\t"
+				 "movl $0, %%edx\n\t"
+				 "wrmsr",
+				 X86_FEATURE_USE_IBPB)
+		     : : [msr] "i" (MSR_IA32_PRED_CMD),
+			 [val] "i" (PRED_CMD_IBPB)
+		     : "eax", "ecx", "edx", "memory");
 }
 
 #endif /* __ASSEMBLY__ */

@@ -969,7 +969,4 @@ bool xen_set_default_idle(void);
 
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
-
-void __ibp_barrier(void);
-
 #endif /* _ASM_X86_PROCESSOR_H */

@@ -337,9 +337,3 @@ ssize_t cpu_show_spectre_v2(struct devic
 		       spectre_v2_module_string());
 }
 #endif
-
-void __ibp_barrier(void)
-{
-	__wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0);
-}
-EXPORT_SYMBOL_GPL(__ibp_barrier);

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: David Woodhouse <[email protected]>

commit 928a4c39484281f8ca366f53a1db79330d058401 upstream.

With retpoline, tight loops of "call this function for every XXX" are very much pessimised by taking a prediction miss *every* time. This one is by far the biggest contributor to the guest launch time with retpoline.

By marking the iterator slot_handle_…() functions always_inline, we can ensure that the indirect function call can be optimised away into a direct call and it actually generates slightly smaller code because some of the other conditionals can get optimised away too.

Performance is now pretty close to what we see with nospectre_v2 on the command line.

---
 arch/x86/kvm/mmu.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -5058,7 +5058,7 @@ void kvm_mmu_uninit_vm(struct kvm *kvm)
 typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
 
 /* The caller should hold mmu-lock before calling this function. */
-static bool
+static __always_inline bool
 slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			slot_level_handler fn, int start_level, int end_level,
 			gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb)

@@ -5088,7 +5088,7 @@ slot_handle_level_range(struct kvm *kvm,
 	return flush;
 }
 
-static bool
+static __always_inline bool
 slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		  slot_level_handler fn, int start_level, int end_level,
 		  bool lock_flush_tlb)

@@ -5099,7 +5099,7 @@ slot_handle_level(struct kvm *kvm, struc
 			lock_flush_tlb);
 }
 
-static bool
+static __always_inline bool
 slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		      slot_level_handler fn, bool lock_flush_tlb)
 {

@@ -5107,7 +5107,7 @@ slot_handle_all_level(struct kvm *kvm, s
 				 PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
 }
 
-static bool
+static __always_inline bool
 slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			slot_level_handler fn, bool lock_flush_tlb)
 {

@@ -5115,7 +5115,7 @@ slot_handle_large_level(struct kvm *kvm,
 				 PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
 }
 
-static bool
+static __always_inline bool
 slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		 slot_level_handler fn, bool lock_flush_tlb)
 {

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: KarimAllah Ahmed <[email protected]>

commit 206587a9fb764d71f035dc7f6d3b6488f5d5b304 upstream.

These two variables should check whether SPEC_CTRL and PRED_CMD are supposed to be passed through to L2 guests or not. While msr_write_intercepted_l01 would return 'true' if it is not passed through.

So just invert the result of msr_write_intercepted_l01 to implement the correct semantics.

---
 arch/x86/kvm/vmx.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -10220,8 +10220,8 @@ static inline bool nested_vmx_merge_msr_
 	 *    updated to reflect this when L1 (or its L2s) actually write to
 	 *    the MSR.
 	 */
-	bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
-	bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
+	bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
+	bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
 
 	if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
 	    !pred_cmd && !spec_ctrl)

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: KarimAllah Ahmed <[email protected]>

commit 3712caeb14dcb33fb4d5114f14c0beef10aca101 upstream.

We either clear the CPU_BASED_USE_MSR_BITMAPS and end up intercepting all MSR accesses or create a valid L02 MSR bitmap and use that. This decision has to be made every time we evaluate whether we are going to generate the L02 MSR bitmap.

Before commit:

d28b387fb74d ("KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL")

... this was probably OK since the decision was always identical.

This is no longer the case now since the MSR bitmap might actually change once we decide to not intercept SPEC_CTRL and PRED_CMD.

---
 arch/x86/kvm/vmx.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -10131,7 +10131,8 @@ static void nested_get_vmcs12_pages(stru
 	if (cpu_has_vmx_msr_bitmap() &&
 	    nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) &&
 	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
-		;
+		vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL,
+			      CPU_BASED_USE_MSR_BITMAPS);
 	else
 		vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
 				CPU_BASED_USE_MSR_BITMAPS);

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Ingo Molnar <[email protected]>

commit 21e433bdb95bdf3aa48226fd3d33af608437f293 upstream.

Harmonize all the Spectre messages so that a:

dmesg | grep -i spectre

... gives us most Spectre related kernel boot messages.

Also fix a few other details:

- clarify a comment about firmware speculation control

- s/KPTI/PTI

- remove various line-breaks that made the code uglier

---
 arch/x86/kernel/cpu/bugs.c |   28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

@@ -162,8 +162,7 @@ static enum spectre_v2_mitigation_cmd __
 	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
 		return SPECTRE_V2_CMD_NONE;
 	else {
-		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
-					  sizeof(arg));
+		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
 		if (ret < 0)
 			return SPECTRE_V2_CMD_AUTO;
 

@@ -175,8 +174,7 @@ static enum spectre_v2_mitigation_cmd __
 		}
 
 		if (i >= ARRAY_SIZE(mitigation_options)) {
-			pr_err("unknown option (%s). Switching to AUTO select\n",
-			       mitigation_options[i].option);
+			pr_err("unknown option (%s). Switching to AUTO select\n", mitigation_options[i].option);
 			return SPECTRE_V2_CMD_AUTO;
 		}
 	}

@@ -185,8 +183,7 @@ static enum spectre_v2_mitigation_cmd __
 	     cmd == SPECTRE_V2_CMD_RETPOLINE_AMD ||
 	     cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) &&
 	    !IS_ENABLED(CONFIG_RETPOLINE)) {
-		pr_err("%s selected but not compiled in. Switching to AUTO select\n",
-		       mitigation_options[i].option);
+		pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option);
 		return SPECTRE_V2_CMD_AUTO;
 	}
 

@@ -256,14 +253,14 @@ static void __init spectre_v2_select_mit
 			goto retpoline_auto;
 		break;
 	}
-	pr_err("kernel not compiled with retpoline; no mitigation available!");
+	pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!");
 	return;
 
 retpoline_auto:
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
 	retpoline_amd:
 		if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
-			pr_err("LFENCE not serializing. Switching to generic retpoline\n");
+			pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
 			goto retpoline_generic;
 		}
 		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :

@@ -281,7 +278,7 @@ retpoline_auto:
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If neither SMEP or KPTI are available, there is a risk of
+	 * If neither SMEP nor PTI are available, there is a risk of
 	 * hitting userspace addresses in the RSB after a context switch
 	 * from a shallow call stack to a deeper one. To prevent this fill
 	 * the entire RSB, even when using IBRS.

@@ -295,21 +292,20 @@ retpoline_auto:
 	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
 	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
 		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-		pr_info("Filling RSB on context switch\n");
+		pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
 	}
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
-		pr_info("Enabling Indirect Branch Prediction Barrier\n");
+		pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
 	}
 }
 
 #undef pr_fmt
 
 #ifdef CONFIG_SYSFS
-ssize_t cpu_show_meltdown(struct device *dev,
-			  struct device_attribute *attr, char *buf)
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
 		return sprintf(buf, "Not affected\n");

@@ -318,16 +314,14 @@ ssize_t cpu_show_meltdown(struct device
 	return sprintf(buf, "Vulnerable\n");
 }
 
-ssize_t cpu_show_spectre_v1(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
 		return sprintf(buf, "Not affected\n");
 	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
 }
 
-ssize_t cpu_show_spectre_v2(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Lukas Wunner <[email protected]>

commit 433986c2c265d106d6a8e88006e0131fefc92b7b upstream.

Commit baa8809f6097 (PM / runtime: Optimize the use of device links) added an invocation of pm_runtime_drop_link() to __device_link_del(). However there are two variants of that function, one for CONFIG_SRCU and another for !CONFIG_SRCU, and the commit only modified the former.

---
 drivers/base/core.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -313,6 +313,9 @@ static void __device_link_del(struct dev
 	dev_info(link->consumer, "Dropping the link to %s\n",
 		 dev_name(link->supplier));
 
+	if (link->flags & DL_FLAG_PM_RUNTIME)
+		pm_runtime_drop_link(link->consumer);
+
 	list_del(&link->s_node);
 	list_del(&link->c_node);
 	device_link_free(link);

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Rafael J. Wysocki <[email protected]>

commit d7212cfb05ba802bea4dd6c90d61cfe6366ea224 upstream.

Commit f85942207516 (x86: PM: Make APM idle driver initialize polling state) made apm_init() call cpuidle_poll_state_init(), but that only is defined for CONFIG_CPU_IDLE set, so make the empty stub of it available for CONFIG_CPU_IDLE unset too to fix the resulting build issue.

---
 include/linux/cpuidle.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -225,7 +225,7 @@ static inline void cpuidle_coupled_paral
 }
 #endif
 
-#ifdef CONFIG_ARCH_HAS_CPU_RELAX
+#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_ARCH_HAS_CPU_RELAX)
 void cpuidle_poll_state_init(struct cpuidle_driver *drv);
 #else
 static inline void cpuidle_poll_state_init(struct cpuidle_driver *drv) {}

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Andrey Ryabinin <[email protected]>

commit 6e1d8ea90932f77843730ada0bfea63093b7212a upstream.

wmi_dev_probe() allocates one byte less than necessary, thus subsequent sprintf() call writes trailing zero past the end of the 'buf':

    BUG: KASAN: slab-out-of-bounds in vsnprintf+0xda4/0x1240
    Write of size 1 at addr ffff880423529caf by task kworker/1:1/32

    Call Trace:
     dump_stack+0xb3/0x14d
     print_address_description+0xd7/0x380
     kasan_report+0x166/0x2b0
     vsnprintf+0xda4/0x1240
     sprintf+0x9b/0xd0
     wmi_dev_probe+0x1c3/0x400
     driver_probe_device+0x5d1/0x990
     bus_for_each_drv+0x109/0x190
     __device_attach+0x217/0x360
     bus_probe_device+0x1ad/0x260
     deferred_probe_work_func+0x10f/0x5d0
     process_one_work+0xa8b/0x1dc0
     worker_thread+0x20d/0x17d0
     kthread+0x311/0x3d0
     ret_from_fork+0x3a/0x50

    Allocated by task 32:
     kasan_kmalloc+0xa0/0xd0
     __kmalloc+0x14f/0x3e0
     wmi_dev_probe+0x182/0x400
     driver_probe_device+0x5d1/0x990
     bus_for_each_drv+0x109/0x190
     __device_attach+0x217/0x360
     bus_probe_device+0x1ad/0x260
     deferred_probe_work_func+0x10f/0x5d0
     process_one_work+0xa8b/0x1dc0
     worker_thread+0x20d/0x17d0
     kthread+0x311/0x3d0
     ret_from_fork+0x3a/0x50

Increment allocation size to fix this.

---
 drivers/platform/x86/wmi.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -933,7 +933,7 @@ static int wmi_dev_probe(struct device *
 			goto probe_failure;
 		}
 
-		buf = kmalloc(strlen(wdriver->driver.name) + 4, GFP_KERNEL);
+		buf = kmalloc(strlen(wdriver->driver.name) + 5, GFP_KERNEL);
 		if (!buf) {
 			ret = -ENOMEM;
 			goto probe_string_failure;

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Dan Williams <[email protected]>

commit 3ac6d8c787b835b997eb23e43e09aa0895ef7d58 upstream.

Clear the 'extra' registers on entering the 64-bit kernel for exceptions and interrupts. The common registers are not cleared since they are likely clobbered well before they can be exploited in a speculative execution attack.

Originally-From: Andi Kleen <[email protected]>

---
 arch/x86/entry/calling.h  |   19 +++++++++++++++++++
 arch/x86/entry/entry_64.S |    6 +++++-
 2 files changed, 24 insertions(+), 1 deletion(-)

@@ -147,6 +147,25 @@ For 32-bit we have the following convent
 	UNWIND_HINT_REGS offset=\offset
 	.endm
 
+	/*
+	 * Sanitize registers of values that a speculation attack
+	 * might otherwise want to exploit. The lower registers are
+	 * likely clobbered well before they could be put to use in
+	 * a speculative execution gadget:
+	 */
+	.macro CLEAR_REGS_NOSPEC
+	xorl %ebp, %ebp
+	xorl %ebx, %ebx
+	xorq %r8, %r8
+	xorq %r9, %r9
+	xorq %r10, %r10
+	xorq %r11, %r11
+	xorq %r12, %r12
+	xorq %r13, %r13
+	xorq %r14, %r14
+	xorq %r15, %r15
+	.endm
+
 	.macro POP_EXTRA_REGS
 	popq %r15
 	popq %r14

@@ -575,6 +575,7 @@ END(irq_entries_start)
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
+	CLEAR_REGS_NOSPEC
 	ENCODE_FRAME_POINTER
 
 	testb	$3, CS(%rsp)

@@ -1133,6 +1134,7 @@ ENTRY(xen_failsafe_callback)
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
+	CLEAR_REGS_NOSPEC
 	ENCODE_FRAME_POINTER
 	jmp	error_exit
 END(xen_failsafe_callback)

@@ -1178,6 +1180,7 @@ ENTRY(paranoid_entry)
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
+	CLEAR_REGS_NOSPEC
 	ENCODE_FRAME_POINTER 8
 	movl	$1, %ebx
 	movl	$MSR_GS_BASE, %ecx

@@ -1230,8 +1233,8 @@ ENTRY(error_entry)
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
+	CLEAR_REGS_NOSPEC
 	ENCODE_FRAME_POINTER 8
-	xorl	%ebx, %ebx
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
 

@@ -1428,6 +1431,7 @@ ENTRY(nmi)
 	pushq	%r14		/* pt_regs->r14 */
 	pushq	%r15		/* pt_regs->r15 */
 	UNWIND_HINT_REGS
+	CLEAR_REGS_NOSPEC
 	ENCODE_FRAME_POINTER
 
 	/*

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Dominik Brodowski <[email protected]>

commit 2e3f0098bc45f710a2f4cbcc94b80a1fae7a99a1 upstream.

All current code paths call SAVE_C_REGS and then immediately SAVE_EXTRA_REGS. Therefore, merge these two macros and order the MOV sequeneces properly.

While at it, remove the macros to save all except specific registers, as these macros have been unused for a long time.

---
 arch/x86/entry/calling.h  |   57 ++++++++++++----------------------------------
 arch/x86/entry/entry_64.S |   12 +++------
 2 files changed, 19 insertions(+), 50 deletions(-)

@@ -101,49 +101,22 @@ For 32-bit we have the following convent
 	addq	$-(15*8), %rsp
 	.endm
 
-	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
-	.if \r11
-	movq %r11, 6*8+\offset(%rsp)
-	.endif
-	.if \r8910
-	movq %r10, 7*8+\offset(%rsp)
-	movq %r9,  8*8+\offset(%rsp)
-	movq %r8,  9*8+\offset(%rsp)
-	.endif
-	.if \rax
-	movq %rax, 10*8+\offset(%rsp)
-	.endif
-	.if \rcx
-	movq %rcx, 11*8+\offset(%rsp)
-	.endif
-	movq %rdx, 12*8+\offset(%rsp)
-	movq %rsi, 13*8+\offset(%rsp)
+	.macro SAVE_REGS offset=0
 	movq %rdi, 14*8+\offset(%rsp)
-	UNWIND_HINT_REGS offset=\offset extra=0
-	.endm
-	.macro SAVE_C_REGS offset=0
-	SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0
-	SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_R891011
-	SAVE_C_REGS_HELPER 0, 1, 1, 0, 0
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_RCX_R891011
-	SAVE_C_REGS_HELPER 0, 1, 0, 0, 0
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11
-	SAVE_C_REGS_HELPER 0, 0, 0, 1, 0
-	.endm
-
-	.macro SAVE_EXTRA_REGS offset=0
-	movq %r15, 0*8+\offset(%rsp)
-	movq %r14, 1*8+\offset(%rsp)
-	movq %r13, 2*8+\offset(%rsp)
-	movq %r12, 3*8+\offset(%rsp)
-	movq %rbp, 4*8+\offset(%rsp)
+	movq %rsi, 13*8+\offset(%rsp)
+	movq %rdx, 12*8+\offset(%rsp)
+	movq %rcx, 11*8+\offset(%rsp)
+	movq %rax, 10*8+\offset(%rsp)
+	movq %r8,  9*8+\offset(%rsp)
+	movq %r9,  8*8+\offset(%rsp)
+	movq %r10, 7*8+\offset(%rsp)
+	movq %r11, 6*8+\offset(%rsp)
 	movq %rbx, 5*8+\offset(%rsp)
+	movq %rbp, 4*8+\offset(%rsp)
+	movq %r12, 3*8+\offset(%rsp)
+	movq %r13, 2*8+\offset(%rsp)
+	movq %r14, 1*8+\offset(%rsp)
+	movq %r15, 0*8+\offset(%rsp)
 	UNWIND_HINT_REGS offset=\offset
 	.endm
 

@@ -197,7 +170,7 @@ For 32-bit we have the following convent
  * is just setting the LSB, which makes it an invalid stack address and is also
  * a signal to the unwinder that it's a pt_regs pointer in disguise.
  *
- * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts
+ * NOTE: This macro must be used *after* SAVE_REGS because it corrupts
  * the original rbp.
  */
 .macro ENCODE_FRAME_POINTER ptregs_offset=0

@@ -573,8 +573,7 @@ END(irq_entries_start)
 1:
 
 	ALLOC_PT_GPREGS_ON_STACK
-	SAVE_C_REGS
-	SAVE_EXTRA_REGS
+	SAVE_REGS
 	CLEAR_REGS_NOSPEC
 	ENCODE_FRAME_POINTER
 

@@ -1132,8 +1131,7 @@ ENTRY(xen_failsafe_callback)
 	UNWIND_HINT_IRET_REGS
 	pushq	$-1 /* orig_ax = -1 => not a system call */
 	ALLOC_PT_GPREGS_ON_STACK
-	SAVE_C_REGS
-	SAVE_EXTRA_REGS
+	SAVE_REGS
 	CLEAR_REGS_NOSPEC
 	ENCODE_FRAME_POINTER
 	jmp	error_exit

@@ -1178,8 +1176,7 @@ idtentry machine_check		do_mce			has_err
 ENTRY(paranoid_entry)
 	UNWIND_HINT_FUNC
 	cld
-	SAVE_C_REGS 8
-	SAVE_EXTRA_REGS 8
+	SAVE_REGS 8
 	CLEAR_REGS_NOSPEC
 	ENCODE_FRAME_POINTER 8
 	movl	$1, %ebx

@@ -1231,8 +1228,7 @@ END(paranoid_exit)
 ENTRY(error_entry)
 	UNWIND_HINT_FUNC
 	cld
-	SAVE_C_REGS 8
-	SAVE_EXTRA_REGS 8
+	SAVE_REGS 8
 	CLEAR_REGS_NOSPEC
 	ENCODE_FRAME_POINTER 8
 	testb	$3, CS+8(%rsp)

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Dominik Brodowski <[email protected]>

commit 502af0d70843c2a9405d7ba1f79b4b0305aaf5f5 upstream.

The two special, opencoded cases for POP_C_REGS can be handled by ASM macros.

---
 arch/x86/entry/calling.h  |   15 +++++++++++----
 arch/x86/entry/entry_64.S |   26 ++++----------------------
 2 files changed, 15 insertions(+), 26 deletions(-)

@@ -139,25 +139,32 @@ For 32-bit we have the following convent
 	xorq %r15, %r15
 	.endm
 
-	.macro POP_EXTRA_REGS
+	.macro POP_REGS pop_rdi=1 skip_r11rcx=0
 	popq %r15
 	popq %r14
 	popq %r13
 	popq %r12
 	popq %rbp
 	popq %rbx
-	.endm
-
-	.macro POP_C_REGS
+	.if \skip_r11rcx
+	popq %rsi
+	.else
 	popq %r11
+	.endif
 	popq %r10
 	popq %r9
 	popq %r8
 	popq %rax
+	.if \skip_r11rcx
+	popq %rsi
+	.else
 	popq %rcx
+	.endif
 	popq %rdx
 	popq %rsi
+	.if \pop_rdi
 	popq %rdi
+	.endif
 	.endm
 
 	.macro icebp

@@ -334,15 +334,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
 syscall_return_via_sysret:
 	/* rcx and r11 are already restored (see code above) */
 	UNWIND_HINT_EMPTY
-	POP_EXTRA_REGS
-	popq	%rsi	/* skip r11 */
-	popq	%r10
-	popq	%r9
-	popq	%r8
-	popq	%rax
-	popq	%rsi	/* skip rcx */
-	popq	%rdx
-	popq	%rsi
+	POP_REGS pop_rdi=0 skip_r11rcx=1
 
 	/*
 	 * Now all regs are restored except RSP and RDI.

@@ -635,15 +627,7 @@ GLOBAL(swapgs_restore_regs_and_return_to
 	ud2
 1:
 #endif
-	POP_EXTRA_REGS
-	popq	%r11
-	popq	%r10
-	popq	%r9
-	popq	%r8
-	popq	%rax
-	popq	%rcx
-	popq	%rdx
-	popq	%rsi
+	POP_REGS pop_rdi=0
 
 	/*
 	 * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.

@@ -701,8 +685,7 @@ GLOBAL(restore_regs_and_return_to_kernel
 	ud2
 1:
 #endif
-	POP_EXTRA_REGS
-	POP_C_REGS
+	POP_REGS
 	addq	$8, %rsp	/* skip regs->orig_ax */
 	INTERRUPT_RETURN
 

@@ -1661,8 +1644,7 @@ end_repeat_nmi:
 nmi_swapgs:
 	SWAPGS_UNSAFE_STACK
 nmi_restore:
-	POP_EXTRA_REGS
-	POP_C_REGS
+	POP_REGS
 
 	/*
 	 * Skip orig_ax and the "outermost" frame to point RSP at the "iret"

4.15-stable review patch. If anyone has any objections, please let me know.

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

From: Dominik Brodowski <[email protected]>

commit f7bafa2b05ef25eda1d9179fd930b0330cf2b7d1 upstream.

Same as is done for syscalls, interleave XOR with PUSH instructions for exceptions/interrupts, in order to minimize the cost of the additional instructions required for register clearing.

---
 arch/x86/entry/calling.h  |   40 +++++++++++++++++++---------------------
 arch/x86/entry/entry_64.S |   30 +++++++++++++++++++++---------
 2 files changed, 40 insertions(+), 30 deletions(-)

@@ -101,44 +101,42 @@ For 32-bit we have the following convent
 	addq	$-(15*8), %rsp
 	.endm
 
-	.macro SAVE_REGS offset=0
+	.macro SAVE_AND_CLEAR_REGS offset=0
+	/*
+	 * Save registers and sanitize registers of values that a
+	 * speculation attack might otherwise want to exploit. The
+	 * lower registers are likely clobbered well before they
+	 * could be put to use in a speculative execution gadget.
+	 * Interleave XOR with PUSH for better uop scheduling:
+	 */
 	movq %rdi, 14*8+\offset(%rsp)
 	movq %rsi, 13*8+\offset(%rsp)
 	movq %rdx, 12*8+\offset(%rsp)
 	movq %rcx, 11*8+\offset(%rsp)
 	movq %rax, 10*8+\offset(%rsp)
 	movq %r8,  9*8+\offset(%rsp)
+	xorq %r8, %r8				/* nospec r8 */
 	movq %r9,  8*8+\offset(%rsp)
+	xorq %r9, %r9				/* nospec r9 */
 	movq %r10, 7*8+\offset(%rsp)
+	xorq %r10, %r10				/* nospec r10 */
 	movq %r11, 6*8+\offset(%rsp)
+	xorq %r11, %r11				/* nospec r11 */
 	movq %rbx, 5*8+\offset(%rsp)
+	xorl %ebx, %ebx				/* nospec rbx */
 	movq %rbp, 4*8+\offset(%rsp)
+	xorl %ebp, %ebp				/* nospec rbp */
 	movq %r12, 3*8+\offset(%rsp)
+	xorq %r12, %r12				/* nospec r12 */
 	movq %r13, 2*8+\offset(%rsp)
+	xorq %r13, %r13				/* nospec r13 */
 	movq %r14, 1*8+\offset(%rsp)
+	xorq %r14, %r14				/* nospec r14 */
 	movq %r15, 0*8+\offset(%rsp)
+	xorq %r15, %r15				/* nospec r15 */
 	UNWIND_HINT_REGS offset=\offset
 	.endm
 
-	/*
-	 * Sanitize registers of values that a speculation attack
-	 * might otherwise want to exploit. The lower registers are
-	 * likely clobbered well before they could be put to use in
-	 * a speculative execution gadget:
-	 */
-	.macro CLEAR_REGS_NOSPEC
-	xorl %ebp, %ebp
-	xorl %ebx, %ebx
-	xorq %r8, %r8
-	xorq %r9, %r9
-	xorq %r10, %r10
-	xorq %r11, %r11
-	xorq %r12, %r12
-	xorq %r13, %r13
-	xorq %r14, %r14
-	xorq %r15, %r15
-	.endm
-
 	.macro POP_REGS pop_rdi=1 skip_r11rcx=0
 	popq %r15
 	popq %r14

@@ -177,7 +175,7 @@ For 32-bit we have the following convent
  * is just setting the LSB, which makes it an invalid stack address and is also
  * a signal to the unwinder that it's a pt_regs pointer in disguise.
  *
- * NOTE: This macro must be used *after* SAVE_REGS because it corrupts
+ * NOTE: This macro must be used *after* SAVE_AND_CLEAR_REGS because it corrupts
  * the original rbp.
  */
 .macro ENCODE_FRAME_POINTER ptregs_offset=0

@@ -565,8 +565,7 @@ END(irq_entries_start)
 1:
 
 	ALLOC_PT_GPREGS_ON_STACK
-	SAVE_REGS
-	CLEAR_REGS_NOSPEC
+	SAVE_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 
 	testb	$3, CS(%rsp)

@@ -1114,8 +1113,7 @@ ENTRY(xen_failsafe_callback)
 	UNWIND_HINT_IRET_REGS
 	pushq	$-1 /* orig_ax = -1 => not a system call */
 	ALLOC_PT_GPREGS_ON_STACK
-	SAVE_REGS
-	CLEAR_REGS_NOSPEC
+	SAVE_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 	jmp	error_exit
 END(xen_failsafe_callback)