5.15.19-rc1 review

From: Manasi Navare <[email protected]>

commit 5ec1cebd59300ddd26dbaa96c17c508764eef911 upstream.

In case of a modeset where a mode gets split across multiple CRTCs in the driver specific implementation (bigjoiner in i915) we wrongly count the affected CRTCs based on the drm_crtc_mask and indicate the stolen CRTC as an affected CRTC in atomic_check_only().
This triggers a warning since affected CRTCs doent match requested CRTC.

To fix this in such bigjoiner configurations, we should only increment affected crtcs if that CRTC is enabled in UAPI not if it is just used internally in the driver to split the mode.

v3: Add the same uapi crtc_state->enable check in requested crtc calc (Ville)

---
 drivers/gpu/drm/drm_atomic.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

@@ -1310,8 +1310,10 @@ int drm_atomic_check_only(struct drm_ato
 
 	DRM_DEBUG_ATOMIC("checking %p\n", state);
 
-	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i)
-		requested_crtc |= drm_crtc_mask(crtc);
+	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
+		if (new_crtc_state->enable)
+			requested_crtc |= drm_crtc_mask(crtc);
+	}
 
 	for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) {
 		ret = drm_atomic_plane_check(old_plane_state, new_plane_state);

@@ -1360,8 +1362,10 @@ int drm_atomic_check_only(struct drm_ato
 		}
 	}
 
-	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i)
-		affected_crtc |= drm_crtc_mask(crtc);
+	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
+		if (new_crtc_state->enable)
+			affected_crtc |= drm_crtc_mask(crtc);
+	}
 
 	/*
 	 * For commits that allow modesets drivers can add other CRTCs to the

From: Naveen N. Rao <[email protected]>

commit fab07611fb2e6a15fac05c4583045ca5582fd826 upstream.

Pad instructions emitted for BPF_CALL so that the number of instructions generated does not change for different function addresses. This is especially important for calls to other bpf functions, whose address will only be known during extra pass.

---
 arch/powerpc/net/bpf_jit_comp32.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -191,6 +191,9 @@ void bpf_jit_emit_func_call_rel(u32 *ima
 
 	if (image && rel < 0x2000000 && rel >= -0x2000000) {
 		PPC_BL_ABS(func);
+		EMIT(PPC_RAW_NOP());
+		EMIT(PPC_RAW_NOP());
+		EMIT(PPC_RAW_NOP());
 	} else {
 		/* Load function address into r0 */
 		EMIT(PPC_RAW_LIS(_R0, IMM_H(func)));

From: Naveen N. Rao <[email protected]>

commit f9320c49993ca3c0ec0f9a7026b313735306bb8b upstream.

These instructions are updated after the initial JIT, so redo codegen during the extra pass. Rename bpf_jit_fixup_subprog_calls() to clarify that this is more than just subprog calls.

---
 arch/powerpc/net/bpf_jit_comp.c   |   29 +++++++++++++++++++++++------
 arch/powerpc/net/bpf_jit_comp32.c |    6 ++++++
 arch/powerpc/net/bpf_jit_comp64.c |    7 ++++++-
 3 files changed, 35 insertions(+), 7 deletions(-)

@@ -23,15 +23,15 @@ static void bpf_jit_fill_ill_insns(void
 	memset32(area, BREAKPOINT_INSTRUCTION, size / 4);
 }
 
-/* Fix the branch target addresses for subprog calls */
-static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image,
-				       struct codegen_context *ctx, u32 *addrs)
+/* Fix updated addresses (for subprog calls, ldimm64, et al) during extra pass */
+static int bpf_jit_fixup_addresses(struct bpf_prog *fp, u32 *image,
+				   struct codegen_context *ctx, u32 *addrs)
 {
 	const struct bpf_insn *insn = fp->insnsi;
 	bool func_addr_fixed;
 	u64 func_addr;
 	u32 tmp_idx;
-	int i, ret;
+	int i, j, ret;
 
 	for (i = 0; i < fp->len; i++) {
 		/*

@@ -66,6 +66,23 @@ static int bpf_jit_fixup_subprog_calls(s
 			 * of the JITed sequence remains unchanged.
 			 */
 			ctx->idx = tmp_idx;
+		} else if (insn[i].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+			tmp_idx = ctx->idx;
+			ctx->idx = addrs[i] / 4;
+#ifdef CONFIG_PPC32
+			PPC_LI32(ctx->b2p[insn[i].dst_reg] - 1, (u32)insn[i + 1].imm);
+			PPC_LI32(ctx->b2p[insn[i].dst_reg], (u32)insn[i].imm);
+			for (j = ctx->idx - addrs[i] / 4; j < 4; j++)
+				EMIT(PPC_RAW_NOP());
+#else
+			func_addr = ((u64)(u32)insn[i].imm) | (((u64)(u32)insn[i + 1].imm) << 32);
+			PPC_LI64(b2p[insn[i].dst_reg], func_addr);
+			/* overwrite rest with nops */
+			for (j = ctx->idx - addrs[i] / 4; j < 5; j++)
+				EMIT(PPC_RAW_NOP());
+#endif
+			ctx->idx = tmp_idx;
+			i++;
 		}
 	}
 

@@ -193,13 +210,13 @@ skip_init_ctx:
 		/*
 		 * Do not touch the prologue and epilogue as they will remain
 		 * unchanged. Only fix the branch target address for subprog
-		 * calls in the body.
+		 * calls in the body, and ldimm64 instructions.
 		 *
 		 * This does not change the offsets and lengths of the subprog
 		 * call instruction sequences and hence, the size of the JITed
 		 * image as well.
 		 */
-		bpf_jit_fixup_subprog_calls(fp, code_base, &cgctx, addrs);
+		bpf_jit_fixup_addresses(fp, code_base, &cgctx, addrs);
 
 		/* There is no need to perform the usual passes. */
 		goto skip_codegen_passes;

@@ -292,6 +292,8 @@ int bpf_jit_build_body(struct bpf_prog *
 		bool func_addr_fixed;
 		u64 func_addr;
 		u32 true_cond;
+		u32 tmp_idx;
+		int j;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from

@@ -839,8 +841,12 @@ int bpf_jit_build_body(struct bpf_prog *
 		 * 16 byte instruction that uses two 'struct bpf_insn'
 		 */
 		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
+			tmp_idx = ctx->idx;
 			PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm);
 			PPC_LI32(dst_reg, (u32)insn[i].imm);
+			/* padding to allow full 4 instructions for later patching */
+			for (j = ctx->idx - tmp_idx; j < 4; j++)
+				EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;

@@ -318,6 +318,7 @@ int bpf_jit_build_body(struct bpf_prog *
 		u64 imm64;
 		u32 true_cond;
 		u32 tmp_idx;
+		int j;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from

@@ -806,9 +807,13 @@ emit_clear:
 		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
 			imm64 = ((u64)(u32) insn[i].imm) |
 				    (((u64)(u32) insn[i+1].imm) << 32);
+			tmp_idx = ctx->idx;
+			PPC_LI64(dst_reg, imm64);
+			/* padding to allow full 5 instructions for later patching */
+			for (j = ctx->idx - tmp_idx; j < 5; j++)
+				EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
-			PPC_LI64(dst_reg, imm64);
 			break;
 
 		/*

From: Eric W. Biederman <[email protected]>

commit f9d87929d451d3e649699d0f1d74f71f77ad38f5 upstream.

When the ucount code was refactored to create get_ucount it was missed that some of the contexts in which a rlimit is kept elevated can be the only reference to the user/ucount in the system.

Ordinary ucount references exist in places that also have a reference to the user namspace, but in POSIX message queues, the SysV shm code, and the SIGPENDING code there is no independent user namespace reference.

Inspection of the the user_namespace show no instance of circular references between struct ucounts and the user_namespace. So hold a reference from struct ucount to i's user_namespace to resolve this problem.

---
 kernel/ucount.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -184,6 +184,7 @@ struct ucounts *alloc_ucounts(struct use
 			kfree(new);
 		} else {
 			hlist_add_head(&new->node, hashent);
+			get_user_ns(new->ns);
 			spin_unlock_irq(&ucounts_lock);
 			return new;
 		}

@@ -204,6 +205,7 @@ void put_ucounts(struct ucounts *ucounts
 	if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) {
 		hlist_del_init(&ucounts->node);
 		spin_unlock_irqrestore(&ucounts_lock, flags);
+		put_user_ns(ucounts->ns);
 		kfree(ucounts);
 	}
 }

From: Greg Kroah-Hartman <[email protected]>

commit c9d967b2ce40d71e968eb839f36c936b8a9cf1ea upstream.

The buffer handling in pm_show_wakelocks() is tricky, and hopefully correct. Ensure it really is correct by using sysfs_emit_at() which handles all of the tricky string handling logic in a PAGE_SIZE buffer for us automatically as this is a sysfs file being read from.

---
 kernel/power/wakelock.c |   11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

@@ -39,23 +39,20 @@ ssize_t pm_show_wakelocks(char *buf, boo
 {
 	struct rb_node *node;
 	struct wakelock *wl;
-	char *str = buf;
-	char *end = buf + PAGE_SIZE;
+	int len = 0;
 
 	mutex_lock(&wakelocks_lock);
 
 	for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) {
 		wl = rb_entry(node, struct wakelock, node);
 		if (wl->ws->active == show_active)
-			str += scnprintf(str, end - str, "%s ", wl->name);
+			len += sysfs_emit_at(buf, len, "%s ", wl->name);
 	}
-	if (str > buf)
-		str--;
 
-	str += scnprintf(str, end - str, "\n");
+	len += sysfs_emit_at(buf, len, "\n");
 
 	mutex_unlock(&wakelocks_lock);
-	return (str - buf);
+	return len;
 }
 
 #if CONFIG_PM_WAKELOCKS_LIMIT > 0

From: Tom Zanussi <[email protected]>

commit 67ab5eb71b37b55f7c5522d080a1b42823351776 upstream.

tr->n_err_log_entries should only be increased if entry allocation succeeds.

Doing it when it fails won't cause any problems other than wasting an entry, but should be fixed anyway.

---
 kernel/trace/trace.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -7749,7 +7749,8 @@ static struct tracing_log_err *get_traci
 		err = kzalloc(sizeof(*err), GFP_KERNEL);
 		if (!err)
 			err = ERR_PTR(-ENOMEM);
-		tr->n_err_log_entries++;
+		else
+			tr->n_err_log_entries++;
 
 		return err;
 	}

From: Ard Biesheuvel <[email protected]>

commit 9f80ccda53b9417236945bc7ece4b519037df74d upstream.

When building for Thumb2, the .alt.smp.init sections that are emitted by the ALT_UP() patching code may not be 32-bit aligned, even though the fixup_smp_on_up() routine expects that. This results in alignment faults at module load time, which need to be fixed up by the fault handler.

So let's align those sections explicitly, and prevent this from occurring.

---
 arch/arm/include/asm/assembler.h |    2 ++
 arch/arm/include/asm/processor.h |    1 +
 2 files changed, 3 insertions(+)

@@ -259,6 +259,7 @@
  */
 #define ALT_UP(instr...)					\
 	.pushsection ".alt.smp.init", "a"			;\
+	.align	2						;\
 	.long	9998b - .					;\
 9997:	instr							;\
 	.if . - 9997b == 2					;\

@@ -270,6 +271,7 @@
 	.popsection
 #define ALT_UP_B(label)					\
 	.pushsection ".alt.smp.init", "a"			;\
+	.align	2						;\
 	.long	9998b - .					;\
 	W(b)	. + (label - 9998b)					;\
 	.popsection

@@ -96,6 +96,7 @@ unsigned long get_wchan(struct task_stru
 #define __ALT_SMP_ASM(smp, up)						\
 	"9998:	" smp "\n"						\
 	"	.pushsection \".alt.smp.init\", \"a\"\n"		\
+	"	.align	2\n"						\
 	"	.long	9998b - .\n"					\
 	"	" up "\n"						\
 	"	.popsection\n"

From: Ilya Leoshkevich <[email protected]>

commit f3b7e73b2c6619884351a3a0a7468642f852b8a2 upstream.

If the size of the PLT entries generated by apply_rela() exceeds 64KiB, the first ones can no longer reach __jump_r1 with brc. Fix by using brcl. An alternative solution is to add a __jump_r1 copy after every 64KiB, however, the space savings are quite small and do not justify the additional complexity.

---
 arch/s390/kernel/module.c |   37 ++++++++++++++++++-------------------
 1 file changed, 18 insertions(+), 19 deletions(-)

@@ -33,7 +33,7 @@
 #define DEBUGP(fmt , ...)
 #endif
 
-#define PLT_ENTRY_SIZE 20
+#define PLT_ENTRY_SIZE 22
 
 void *module_alloc(unsigned long size)
 {

@@ -340,27 +340,26 @@ static int apply_rela(Elf_Rela *rela, El
 	case R_390_PLTOFF32:	/* 32 bit offset from GOT to PLT. */
 	case R_390_PLTOFF64:	/* 16 bit offset from GOT to PLT. */
 		if (info->plt_initialized == 0) {
-			unsigned int insn[5];
-			unsigned int *ip = me->core_layout.base +
-					   me->arch.plt_offset +
-					   info->plt_offset;
-
-			insn[0] = 0x0d10e310;	/* basr 1,0  */
-			insn[1] = 0x100a0004;	/* lg	1,10(1) */
+			unsigned char insn[PLT_ENTRY_SIZE];
+			char *plt_base;
+			char *ip;
+
+			plt_base = me->core_layout.base + me->arch.plt_offset;
+			ip = plt_base + info->plt_offset;
+			*(int *)insn = 0x0d10e310;	/* basr 1,0  */
+			*(int *)&insn[4] = 0x100c0004;	/* lg	1,12(1) */
 			if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) {
-				unsigned int *ij;
-				ij = me->core_layout.base +
-					me->arch.plt_offset +
-					me->arch.plt_size - PLT_ENTRY_SIZE;
-				insn[2] = 0xa7f40000 +	/* j __jump_r1 */
-					(unsigned int)(u16)
-					(((unsigned long) ij - 8 -
-					  (unsigned long) ip) / 2);
+				char *jump_r1;
+
+				jump_r1 = plt_base + me->arch.plt_size -
+					PLT_ENTRY_SIZE;
+				/* brcl	0xf,__jump_r1 */
+				*(short *)&insn[8] = 0xc0f4;
+				*(int *)&insn[10] = (jump_r1 - (ip + 8)) / 2;
 			} else {
-				insn[2] = 0x07f10000;	/* br %r1 */
+				*(int *)&insn[8] = 0x07f10000;	/* br %r1 */
 			}
-			insn[3] = (unsigned int) (val >> 32);
-			insn[4] = (unsigned int) val;
+			*(long *)&insn[14] = val;
 
 			write(ip, insn, sizeof(insn));
 			info->plt_initialized = 1;

This is the start of the stable review cycle for the 5.15.19 release. There are 171 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed, 02 Feb 2022 10:51:59 +0000. Anything received after that time might be too late.

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

	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.19-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.

thanks,

greg k-h

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

Greg Kroah-Hartman <[email protected]>

    Linux 5.15.19-rc1

OGAWA Hirofumi <[email protected]>
block: Fix wrong offset in bio_truncate()

Amir Goldstein <[email protected]>
fsnotify: invalidate dcache before IN_DELETE event

Dmitry V. Levin <[email protected]>
usr/include/Makefile: add linux/nfc.h to the compile-test coverage

Robert Hancock <[email protected]>
usb: dwc3: xilinx: fix uninitialized return value

Suren Baghdasaryan <[email protected]>
psi: fix "defined but not used" warnings when CONFIG_PROC_FS=n

Suren Baghdasaryan <[email protected]>
psi: fix "no previous prototype" warnings when CONFIG_CGROUPS=n

Namhyung Kim <[email protected]>
perf/core: Fix cgroup event list management

Marc Kleine-Budde <[email protected]>
dt-bindings: can: tcan4x5x: fix mram-cfg RX FIFO config

Sander Vanheule <[email protected]>
irqchip/realtek-rtl: Fix off-by-one in routing

Sander Vanheule <[email protected]>
irqchip/realtek-rtl: Map control data to virq

Brian Gix <[email protected]>
Bluetooth: refactor malicious adv data check

Tim Yi <[email protected]>
net: bridge: vlan: fix memory leak in __allowed_ingress

Eric Dumazet <[email protected]>
ipv4: remove sparse error in ip_neigh_gw4()

Eric Dumazet <[email protected]>
ipv4: tcp: send zero IPID in SYNACK messages

Eric Dumazet <[email protected]>
ipv4: raw: lock the socket in raw_bind()

Nikolay Aleksandrov <[email protected]>
net: bridge: vlan: fix single net device option dumping

Guillaume Nault <[email protected]>
Revert "ipv6: Honor all IPv6 PIO Valid Lifetime values"

Catherine Sullivan <[email protected]>
gve: Fix GFP flags when allocing pages

Xiubo Li <[email protected]>
ceph: put the requests/sessions when it fails to alloc memory

Sean Christopherson <[email protected]>
KVM: selftests: Don't skip L2's VMCALL in SMM test for SVM guest

Dave Airlie <[email protected]>

    Revert "drm/ast: Support 1600x900 with 108MHz PCLK"

Maxim Mikityanskiy <[email protected]>
sch_htb: Fail on unsupported parameters when offload is requested

Yufeng Mo <[email protected]>
net: hns3: handle empty unknown interrupt for VF

Toke Høiland-Jørgensen <[email protected]>
net: cpsw: Properly initialise struct page_pool_params

Hangyu Hua <[email protected]>
yam: fix a memory leak in yam_siocdevprivate()

Rob Clark <[email protected]>
drm/msm/a6xx: Add missing suspend_count increment

José Expósito <[email protected]>
drm/msm/dpu: invalid parameter check in dpu_setup_dspp_pcc

Miaoqian Lin <[email protected]>
drm/msm/hdmi: Fix missing put_device() call in msm_hdmi_get_phy

Marc Kleine-Budde <[email protected]>
can: tcan4x5x: regmap: fix max register value

Michael Kelley <[email protected]>
video: hyperv_fb: Fix validation of screen resolution

Wen Gu <[email protected]>
net/smc: Transitional solution for clcsock race issue

Sukadev Bhattiprolu <[email protected]>
ibmvnic: don't spin in tasklet

Sukadev Bhattiprolu <[email protected]>

    ibmvnic: init ->running_cap_crqs early

Sukadev Bhattiprolu <[email protected]>
ibmvnic: Allow extra failures before disabling

Jakub Kicinski <[email protected]>
ipv4: fix ip option filtering for locally generated fragments

Athira Rajeev <[email protected]>
powerpc/perf: Fix power_pmu_disable to call clear_pmi_irq_pending only if PMI is pending

Dan Carpenter <[email protected]>
hwmon: (adt7470) Prevent divide by zero in adt7470_fan_write()

Guenter Roeck <[email protected]>
hwmon: (lm90) Fix sysfs and udev notifications

Guenter Roeck <[email protected]>
hwmon: (lm90) Mark alert as broken for MAX6654

Guenter Roeck <[email protected]>
hwmon: (lm90) Re-enable interrupts after alert clears

Yanming Liu <[email protected]>
Drivers: hv: balloon: account for vmbus packet header in max_pkt_size

Dylan Yudaken <[email protected]>
io_uring: fix bug in slow unregistering of nodes

Mihai Carabas <[email protected]>
efi/libstub: arm64: Fix image check alignment at entry

David Howells <[email protected]>
rxrpc: Adjust retransmission backoff

Subbaraya Sundeep <[email protected]>
octeontx2-pf: Forward error codes to VF

Geetha sowjanya <[email protected]>
octeontx2-af: cn10k: Do not enable RPM loopback for LPC interfaces

Geetha sowjanya <[email protected]>
octeontx2-af: Increase link credit restore polling timeout

Hariprasad Kelam <[email protected]>
octeontx2-af: verify CQ context updates

Geetha sowjanya <[email protected]>
octeontx2-pf: cn10k: Ensure valid pointers are freed to aura

Geetha sowjanya <[email protected]>
octeontx2-af: Retry until RVU block reset complete

Sunil Goutham <[email protected]>
octeontx2-af: Fix LBK backpressure id count

Subbaraya Sundeep <[email protected]>
octeontx2-af: Do not fixup all VF action entries

Paolo Abeni <[email protected]>
selftests: mptcp: fix ipv6 routing setup

Geliang Tang <[email protected]>
mptcp: fix removing ids bitmap setting

Paolo Abeni <[email protected]>
mptcp: fix msk traversal in mptcp_nl_cmd_set_flags()

Paolo Abeni <[email protected]>
mptcp: keep track of local endpoint still available for each msk

Jean Sacren <[email protected]>
mptcp: clean up harmless false expressions

Davide Caratti <[email protected]>
mptcp: allow changing the "backup" bit by endpoint id

Marek Behún <[email protected]>
phylib: fix potential use-after-free

Yuji Ishikawa <[email protected]>
net: stmmac: dwmac-visconti: Fix clock configuration for RMII mode

Yuji Ishikawa <[email protected]>
net: stmmac: dwmac-visconti: Fix bit definitions for ETHER_CLK_SEL

Robert Hancock <[email protected]>
net: phy: broadcom: hook up soft_reset for BCM54616S

Vincent Guittot <[email protected]>
sched/pelt: Relax the sync of util_sum with util_avg

Peter Zijlstra <[email protected]>
perf: Fix perf_event_read_local() time

Nicholas Piggin <[email protected]>
powerpc/64s: Mask SRR0 before checking against the masked NIP

Florian Westphal <[email protected]>
netfilter: conntrack: don't increment invalid counter on NF_REPEAT

Naveen N. Rao <[email protected]>
powerpc64/bpf: Limit 'ldbrx' to processors compliant with ISA v2.06

Chuck Lever <[email protected]>

    SUNRPC: Don't dereference xprt->snd_task if it's a cookie

Chuck Lever <[email protected]>
SUNRPC: Use BIT() macro in rpc_show_xprt_state()

Marc Zyngier <[email protected]>
KVM: arm64: pkvm: Use the mm_ops indirection for cache maintenance

Trond Myklebust <[email protected]>
NFS: Ensure the server has an up to date ctime before renaming

Trond Myklebust <[email protected]>
NFS: Ensure the server has an up to date ctime before hardlinking

Eric Dumazet <[email protected]>

    ipv6: annotate accesses to fn->fn_sernum

José Expósito <[email protected]>
drm/msm/dsi: invalid parameter check in msm_dsi_phy_enable

Miaoqian Lin <[email protected]>
drm/msm/dsi: Fix missing put_device() call in dsi_get_phy

Xianting Tian <[email protected]>
drm/msm: Fix wrong size calculation

Jianguo Wu <[email protected]>
net-procfs: show net devices bound packet types

Trond Myklebust <[email protected]>
NFSv4: nfs_atomic_open() can race when looking up a non-regular file

Trond Myklebust <[email protected]>
NFSv4: Handle case where the lookup of a directory fails

Guenter Roeck <[email protected]>
hwmon: (lm90) Reduce maximum conversion rate for G781

Eric Dumazet <[email protected]>
ipv4: avoid using shared IP generator for connected sockets

Xin Long <[email protected]>
ping: fix the sk_bound_dev_if match in ping_lookup

Guenter Roeck <[email protected]>
hwmon: (lm90) Mark alert as broken for MAX6680

Guenter Roeck <[email protected]>

    hwmon: (lm90) Mark alert as broken for MAX6646/6647/6649

Congyu Liu <[email protected]>
net: fix information leakage in /proc/net/ptype

sparkhuang <[email protected]>
ARM: 9170/1: fix panic when kasan and kprobe are enabled

Ido Schimmel <[email protected]>
ipv6_tunnel: Rate limit warning messages

John Meneghini <[email protected]>
scsi: bnx2fc: Flush destroy_work queue before calling bnx2fc_interface_put()

Yang Yingliang <[email protected]>
scsi: elx: efct: Don't use GFP_KERNEL under spin lock

Matthias Kaehlcke <[email protected]>
rpmsg: char: Fix race between the release of rpmsg_eptdev and cdev

Sujit Kautkar <[email protected]>
rpmsg: char: Fix race between the release of rpmsg_ctrldev and cdev

Linyu Yuan <[email protected]>
usb: roles: fix include/linux/usb/role.h compile issue

Joe Damato <[email protected]>
i40e: fix unsigned stat widths

Karen Sornek <[email protected]>
i40e: Fix for failed to init adminq while VF reset

Sylwester Dziedziuch <[email protected]>
i40e: Fix queues reservation for XDP

Jedrzej Jagielski <[email protected]>
i40e: Fix issue when maximum queues is exceeded

Jedrzej Jagielski <[email protected]>
i40e: Increase delay to 1 s after global EMP reset

Christophe Leroy <[email protected]>
powerpc/32: Fix boot failure with GCC latent entropy plugin

Christophe Leroy <[email protected]>
powerpc/32s: Fix kasan_init_region() for KASAN

Christophe Leroy <[email protected]>
powerpc/32s: Allocate one 256k IBAT instead of two consecutives 128k IBATs

Tony Luck <[email protected]>
x86/cpu: Add Xeon Icelake-D to list of CPUs that support PPIN

Yazen Ghannam <[email protected]>
x86/MCE/AMD: Allow thresholding interface updates after init

Bjorn Helgaas <[email protected]>
PCI/sysfs: Find shadow ROM before static attribute initialization

Mathieu Desnoyers <[email protected]>
sched/membarrier: Fix membarrier-rseq fence command missing from query bitmask

Joseph Qi <[email protected]>
ocfs2: fix a deadlock when commit trans

Joseph Qi <[email protected]>
jbd2: export jbd2_journal_[grab|put]_journal_head

Peter Collingbourne <[email protected]>
mm, kasan: use compare-exchange operation to set KASAN page tag

Sing-Han Chen <[email protected]>
ucsi_ccg: Check DEV_INT bit only when starting CCG4

Badhri Jagan Sridharan <[email protected]>
usb: typec: tcpm: Do not disconnect when receiving VSAFE0V

Badhri Jagan Sridharan <[email protected]>
usb: typec: tcpm: Do not disconnect while receiving VBUS off

Xu Yang <[email protected]>
usb: typec: tcpci: don't touch CC line if it's Vconn source

Alan Stern <[email protected]>
USB: core: Fix hang in usb_kill_urb by adding memory barriers

Robert Hancock <[email protected]>
usb: dwc3: xilinx: Fix error handling when getting USB3 PHY

Robert Hancock <[email protected]>
usb: dwc3: xilinx: Skip resets and USB3 register settings for USB2.0 mode

Pawel Laszczak <[email protected]>
usb: cdnsp: Fix segmentation fault in cdns_lost_power function

Pavankumar Kondeti <[email protected]>
usb: gadget: f_sourcesink: Fix isoc transfer for USB_SPEED_SUPER_PLUS

Jon Hunter <[email protected]>
usb: common: ulpi: Fix crash in ulpi_match()

Frank Li <[email protected]>
usb: xhci-plat: fix crash when suspend if remote wake enable

Alan Stern <[email protected]>
usb-storage: Add unusual-devs entry for VL817 USB-SATA bridge

Greg Kroah-Hartman <[email protected]>
kbuild: remove include/linux/cyclades.h from header file check

Cameron Williams <[email protected]>
tty: Add support for Brainboxes UC cards.

Maciej W. Rozycki <[email protected]>
tty: Partially revert the removal of the Cyclades public API

[email protected] <[email protected]>
tty: n_gsm: fix SW flow control encoding/handling

Valentin Caron <[email protected]>
serial: stm32: fix software flow control transfer

Robert Hancock <[email protected]>
serial: 8250: of: Fix mapped region size when using reg-offset property

Jochen Mades <[email protected]>
serial: pl011: Fix incorrect rs485 RTS polarity on set_mctrl

Mike Snitzer <[email protected]>
dm: properly fix redundant bio-based IO accounting

Mike Snitzer <[email protected]>
block: add bio_start_io_acct_time() to control start_time

Mike Snitzer <[email protected]>
dm: revert partial fix for redundant bio-based IO accounting

Nicholas Piggin <[email protected]>
KVM: PPC: Book3S HV Nested: Fix nested HFSCR being clobbered with multiple vCPUs

Like Xu <[email protected]>
KVM: x86: Sync the states size with the XCR0/IA32_XSS at, any time

Like Xu <[email protected]>
KVM: x86: Update vCPU's runtime CPUID on write to MSR_IA32_XSS

Xiaoyao Li <[email protected]>
KVM: x86: Keep MSR_IA32_XSS unchanged for INIT

Sean Christopherson <[email protected]>
KVM: x86: Forcibly leave nested virt when SMM state is toggled

Denis Valeev <[email protected]>
KVM: x86: nSVM: skip eax alignment check for non-SVM instructions

Sean Christopherson <[email protected]>
KVM: SVM: Don't intercept #GP for SEV guests

Sean Christopherson <[email protected]>
KVM: SVM: Never reject emulation due to SMAP errata for !SEV guests

Wanpeng Li <[email protected]>
KVM: LAPIC: Also cancel preemption timer during SET_LAPIC

Bas Nieuwenhuizen <[email protected]>
drm/amd/display: Fix FP start/end for dcn30_internal_validate_bw.

Manasi Navare <[email protected]>
drm/atomic: Add the crtc to affected crtc only if uapi.enable = true

Lucas Stach <[email protected]>
drm/etnaviv: relax submit size limits

Kan Liang <[email protected]>
perf/x86/intel: Add a quirk for the calculation of the number of counters on Alder Lake

Zhengjun Xing <[email protected]>
perf/x86/intel/uncore: Fix CAS_COUNT_WRITE issue for ICX

Christophe Leroy <[email protected]>
powerpc/audit: Fix syscall_get_arch()

Suren Baghdasaryan <[email protected]>
psi: Fix uaf issue when psi trigger is destroyed while being polled

Sean Christopherson <[email protected]>
Revert "KVM: SVM: avoid infinite loop on NPF from bad address"

Amir Goldstein <[email protected]>
fsnotify: fix fsnotify hooks in pseudo filesystems

Jeff Layton <[email protected]>
ceph: set pool_ns in new inode layout for async creates

Jeff Layton <[email protected]>
ceph: properly put ceph_string reference after async create attempt

Tom Zanussi <[email protected]>
tracing: Don't inc err_log entry count if entry allocation fails

Xiaoke Wang <[email protected]>
tracing/histogram: Fix a potential memory leak for kstrdup()

Greg Kroah-Hartman <[email protected]>
PM: wakeup: simplify the output logic of pm_show_wakelocks()

Ard Biesheuvel <[email protected]>
efi: runtime: avoid EFIv2 runtime services on Apple x86 machines

Jan Kara <[email protected]>
udf: Fix NULL ptr deref when converting from inline format

Jan Kara <[email protected]>
udf: Restore i_lenAlloc when inode expansion fails

Steffen Maier <[email protected]>
scsi: zfcp: Fix failed recovery on gone remote port with non-NPIV FCP devices

Eric W. Biederman <[email protected]>
ucount: Make get_ucount a safe get_user replacement

Naveen N. Rao <[email protected]>
powerpc/bpf: Update ldimm64 instructions during extra pass

Naveen N. Rao <[email protected]>
powerpc32/bpf: Fix codegen for bpf-to-bpf calls

Naveen N. Rao <[email protected]>
bpf: Guard against accessing NULL pt_regs in bpf_get_task_stack()

Christian Borntraeger <[email protected]>
s390/nmi: handle vector validity failures for KVM guests

Christian Borntraeger <[email protected]>
s390/nmi: handle guarded storage validity failures for KVM guests

Vasily Gorbik <[email protected]>
s390/hypfs: include z/VM guests with access control group set

Ilya Leoshkevich <[email protected]>
s390/module: fix loading modules with a lot of relocations

Marc Zyngier <[email protected]>
KVM: arm64: Use shadow SPSR_EL1 when injecting exceptions on !VHE

Ard Biesheuvel <[email protected]>
ARM: 9180/1: Thumb2: align ALT_UP() sections in modules sufficiently

Ard Biesheuvel <[email protected]>
ARM: 9179/1: uaccess: avoid alignment faults in copy_[from|to]_kernel_nofault

Mohammad Athari Bin Ismail <[email protected]>
net: stmmac: skip only stmmac_ptp_register when resume from suspend

Mohammad Athari Bin Ismail <[email protected]>
net: stmmac: configure PTP clock source prior to PTP initialization

Marek Behún <[email protected]>
net: sfp: ignore disabled SFP node

Marc Kleine-Budde <[email protected]>
can: m_can: m_can_fifo_{read,write}: don't read or write from/to FIFO if length is 0

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

Diffstat:

 Documentation/accounting/psi.rst                   |   3 +-
 .../devicetree/bindings/net/can/tcan4x5x.txt       |   2 +-
 Makefile                                           |   4 +-
 arch/arm/include/asm/assembler.h                   |   2 +
 arch/arm/include/asm/processor.h                   |   1 +
 arch/arm/include/asm/uaccess.h                     |  10 +-
 arch/arm/probes/kprobes/Makefile                   |   3 +
 arch/arm64/kvm/hyp/exception.c                     |   5 +-
 arch/arm64/kvm/hyp/pgtable.c                       |  18 +-
 arch/ia64/pci/fixup.c                              |   4 +-
 arch/mips/loongson64/vbios_quirk.c                 |   9 +-
 arch/powerpc/include/asm/book3s/32/mmu-hash.h      |   2 +
 arch/powerpc/include/asm/kvm_book3s_64.h           |   1 -
 arch/powerpc/include/asm/kvm_host.h                |   1 +
 arch/powerpc/include/asm/ppc-opcode.h              |   1 +
 arch/powerpc/include/asm/syscall.h                 |   4 +-
 arch/powerpc/include/asm/thread_info.h             |   2 +
 arch/powerpc/kernel/Makefile                       |   1 +
 arch/powerpc/kernel/interrupt_64.S                 |   2 +
 arch/powerpc/kvm/book3s_hv.c                       |   3 +-
 arch/powerpc/kvm/book3s_hv_nested.c                |   2 +-
 arch/powerpc/lib/Makefile                          |   3 +
 arch/powerpc/mm/book3s32/mmu.c                     |  15 +-
 arch/powerpc/mm/kasan/book3s_32.c                  |  59 ++---
 arch/powerpc/net/bpf_jit_comp.c                    |  29 ++-
 arch/powerpc/net/bpf_jit_comp32.c                  |   9 +
 arch/powerpc/net/bpf_jit_comp64.c                  |  29 ++-
 arch/powerpc/perf/core-book3s.c                    |  17 +-
 arch/s390/hypfs/hypfs_vm.c                         |   6 +-
 arch/s390/kernel/module.c                          |  37 ++-
 arch/s390/kernel/nmi.c                             |  27 ++-
 arch/x86/events/intel/core.c                       |  13 ++
 arch/x86/events/intel/uncore_snbep.c               |   2 +-
 arch/x86/include/asm/kvm_host.h                    |   1 +
 arch/x86/kernel/cpu/mce/amd.c                      |   2 +-
 arch/x86/kernel/cpu/mce/intel.c                    |   1 +
 arch/x86/kvm/lapic.c                               |   2 +-
 arch/x86/kvm/svm/nested.c                          |   9 +-
 arch/x86/kvm/svm/svm.c                             |  41 ++--
 arch/x86/kvm/svm/svm.h                             |   2 +-
 arch/x86/kvm/vmx/nested.c                          |   1 +
 arch/x86/kvm/x86.c                                 |  10 +-
 arch/x86/pci/fixup.c                               |   4 +-
 block/bio.c                                        |   3 +-
 block/blk-core.c                                   |  25 +-
 drivers/firmware/efi/efi.c                         |   7 +
 drivers/firmware/efi/libstub/arm64-stub.c          |   6 +-
 .../gpu/drm/amd/display/dc/dcn30/dcn30_resource.c  |   4 +-
 drivers/gpu/drm/ast/ast_tables.h                   |   2 -
 drivers/gpu/drm/drm_atomic.c                       |  12 +-
 drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c       |   4 +-
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c              |   2 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c        |  11 +-
 drivers/gpu/drm/msm/dsi/dsi.c                      |   7 +-
 drivers/gpu/drm/msm/dsi/phy/dsi_phy.c              |   4 +-
 drivers/gpu/drm/msm/hdmi/hdmi.c                    |   7 +-
 drivers/gpu/drm/msm/msm_drv.c                      |   2 +-
 drivers/hv/hv_balloon.c                            |   7 +
 drivers/hwmon/adt7470.c                            |   3 +
 drivers/hwmon/lm90.c                               |  21 +-
 drivers/irqchip/irq-realtek-rtl.c                  |  10 +-
 drivers/md/dm.c                                    |  20 +-
 drivers/net/can/m_can/m_can.c                      |   6 +
 drivers/net/can/m_can/tcan4x5x-regmap.c            |   2 +-
 drivers/net/ethernet/google/gve/gve.h              |   2 +-
 drivers/net/ethernet/google/gve/gve_main.c         |   6 +-
 drivers/net/ethernet/google/gve/gve_rx.c           |   3 +-
 drivers/net/ethernet/google/gve/gve_rx_dqo.c       |   2 +-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  |   3 +-
 drivers/net/ethernet/ibm/ibmvnic.c                 | 133 +++++++----
 drivers/net/ethernet/intel/i40e/i40e.h             |   9 +-
 drivers/net/ethernet/intel/i40e/i40e_debugfs.c     |   2 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  44 ++--
 drivers/net/ethernet/intel/i40e/i40e_register.h    |   3 +
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 103 ++++++++-
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h |   1 +
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |   3 +
 drivers/net/ethernet/marvell/octeontx2/af/rpm.c    |  27 +--
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c    |   7 +-
 .../ethernet/marvell/octeontx2/af/rvu_debugfs.c    |   2 +
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    |  88 ++++++-
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    |  22 +-
 .../net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c |  20 +-
 .../ethernet/marvell/octeontx2/nic/otx2_common.h   |   1 +
 .../net/ethernet/marvell/octeontx2/nic/otx2_pf.c   |   7 +-
 .../net/ethernet/stmicro/stmmac/dwmac-visconti.c   |  42 ++--
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |  23 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c   |   3 -
 drivers/net/ethernet/ti/cpsw_priv.c                |   2 +-
 drivers/net/hamradio/yam.c                         |   4 +-
 drivers/net/phy/broadcom.c                         |   1 +
 drivers/net/phy/phy_device.c                       |   6 +-
 drivers/net/phy/sfp-bus.c                          |   5 +
 drivers/rpmsg/rpmsg_char.c                         |  22 +-
 drivers/s390/scsi/zfcp_fc.c                        |  13 +-
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c                  |  20 +-
 drivers/scsi/elx/libefc/efc_els.c                  |   8 +-
 drivers/tty/n_gsm.c                                |   4 +-
 drivers/tty/serial/8250/8250_of.c                  |  11 +-
 drivers/tty/serial/8250/8250_pci.c                 | 100 +++++++-
 drivers/tty/serial/amba-pl011.c                    |   8 +-
 drivers/tty/serial/stm32-usart.c                   |   2 +-
 drivers/usb/cdns3/drd.c                            |   6 +-
 drivers/usb/common/ulpi.c                          |   7 +-
 drivers/usb/core/hcd.c                             |  14 ++
 drivers/usb/core/urb.c                             |  12 +
 drivers/usb/dwc3/dwc3-xilinx.c                     |  25 +-
 drivers/usb/gadget/function/f_sourcesink.c         |   1 +
 drivers/usb/host/xhci-plat.c                       |   3 +
 drivers/usb/storage/unusual_devs.h                 |  10 +
 drivers/usb/typec/tcpm/tcpci.c                     |  26 +++
 drivers/usb/typec/tcpm/tcpci.h                     |   1 +
 drivers/usb/typec/tcpm/tcpm.c                      |   7 +-
 drivers/usb/typec/ucsi/ucsi_ccg.c                  |   2 +-
 drivers/video/fbdev/hyperv_fb.c                    |  16 +-
 fs/btrfs/ioctl.c                                   |   6 +-
 fs/ceph/caps.c                                     |  55 +++--
 fs/ceph/file.c                                     |   9 +
 fs/configfs/dir.c                                  |   6 +-
 fs/devpts/inode.c                                  |   2 +-
 fs/io_uring.c                                      |   7 +-
 fs/jbd2/journal.c                                  |   2 +
 fs/namei.c                                         |  10 +-
 fs/nfs/dir.c                                       |  22 ++
 fs/nfsd/nfsctl.c                                   |   5 +-
 fs/ocfs2/suballoc.c                                |  25 +-
 fs/udf/inode.c                                     |   9 +-
 include/linux/blkdev.h                             |   1 +
 include/linux/fsnotify.h                           |  48 +++-
 include/linux/mm.h                                 |  17 +-
 include/linux/netdevice.h                          |   1 +
 include/linux/perf_event.h                         |  15 +-
 include/linux/psi.h                                |  13 +-
 include/linux/psi_types.h                          |   3 -
 include/linux/usb/role.h                           |   6 +
 include/net/addrconf.h                             |   2 +
 include/net/ip.h                                   |  21 +-
 include/net/ip6_fib.h                              |   2 +-
 include/net/route.h                                |   2 +-
 include/trace/events/sunrpc.h                      |  40 ++--
 include/uapi/linux/cyclades.h                      |  35 +++
 kernel/bpf/stackmap.c                              |   5 +-
 kernel/cgroup/cgroup.c                             |  11 +-
 kernel/events/core.c                               | 257 +++++++++++++--------
 kernel/power/wakelock.c                            |  11 +-
 kernel/sched/fair.c                                |  16 +-
 kernel/sched/membarrier.c                          |   9 +-
 kernel/sched/pelt.h                                |   4 +-
 kernel/sched/psi.c                                 | 145 ++++++------
 kernel/trace/trace.c                               |   3 +-
 kernel/trace/trace_events_hist.c                   |   1 +
 kernel/ucount.c                                    |   2 +
 net/bluetooth/hci_event.c                          |  10 +-
 net/bridge/br_vlan.c                               |   9 +-
 net/core/net-procfs.c                              |  38 ++-
 net/ipv4/ip_output.c                               |  26 ++-
 net/ipv4/ping.c                                    |   3 +-
 net/ipv4/raw.c                                     |   5 +-
 net/ipv6/addrconf.c                                |  27 ++-
 net/ipv6/ip6_fib.c                                 |  23 +-
 net/ipv6/ip6_tunnel.c                              |   8 +-
 net/ipv6/route.c                                   |   2 +-
 net/mptcp/pm.c                                     |   1 +
 net/mptcp/pm_netlink.c                             | 176 ++++++++------
 net/mptcp/protocol.c                               |   3 +-
 net/mptcp/protocol.h                               |  12 +-
 net/netfilter/nf_conntrack_core.c                  |   8 +-
 net/packet/af_packet.c                             |   2 +
 net/rxrpc/call_event.c                             |   8 +-
 net/rxrpc/output.c                                 |   2 +-
 net/sched/sch_htb.c                                |  20 ++
 net/smc/af_smc.c                                   |  63 ++++-
 net/sunrpc/rpc_pipe.c                              |   4 +-
 tools/testing/selftests/kvm/x86_64/smm_test.c      |   1 -
 tools/testing/selftests/net/mptcp/mptcp_join.sh    |  10 +-
 usr/include/Makefile                               |   2 +-
 virt/kvm/kvm_main.c                                |   1 -
 177 files changed, 1862 insertions(+), 886 deletions(-)

From: Wanpeng Li <[email protected]>

commit 35fe7cfbab2e81f1afb23fc4212210b1de6d9633 upstream.

The below warning is splatting during guest reboot.

  ------------[ cut here ]------------
  WARNING: CPU: 0 PID: 1931 at arch/x86/kvm/x86.c:10322 kvm_arch_vcpu_ioctl_run+0x874/0x880 [kvm]
  CPU: 0 PID: 1931 Comm: qemu-system-x86 Tainted: G          I       5.17.0-rc1+ #5
  RIP: 0010:kvm_arch_vcpu_ioctl_run+0x874/0x880 [kvm]
  Call Trace:
   <TASK>
   kvm_vcpu_ioctl+0x279/0x710 [kvm]
   __x64_sys_ioctl+0x83/0xb0
   do_syscall_64+0x3b/0xc0
   entry_SYSCALL_64_after_hwframe+0x44/0xae
  RIP: 0033:0x7fd39797350b

This can be triggered by not exposing tsc-deadline mode and doing a reboot in the guest. The lapic_shutdown() function which is called in sys_reboot path will not disarm the flying timer, it just masks LVTT. lapic_shutdown() clears APIC state w/ LVT_MASKED and timer-mode bit is 0, this can trigger timer-mode switch between tsc-deadline and oneshot/periodic, which can result in preemption timer be cancelled in apic_update_lvtt(). However, We can't depend on this when not exposing tsc-deadline mode and oneshot/periodic modes emulated by preemption timer. Qemu will synchronise states around reset, let's cancel preemption timer under KVM_SET_LAPIC.

Message-Id: <[email protected]>

---
 arch/x86/kvm/lapic.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2623,7 +2623,7 @@ int kvm_apic_set_state(struct kvm_vcpu *
 	kvm_apic_set_version(vcpu);
 
 	apic_update_ppr(apic);
-	hrtimer_cancel(&apic->lapic_timer.timer);
+	cancel_apic_timer(apic);
 	apic->lapic_timer.expired_tscdeadline = 0;
 	apic_update_lvtt(apic);
 	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));

From: Marc Zyngier <[email protected]>

commit 278583055a237270fac70518275ba877bf9e4013 upstream.

Injecting an exception into a guest with non-VHE is risky business. Instead of writing in the shadow register for the switch code to restore it, we override the CPU register instead. Which gets overriden a few instructions later by said restore code.

The result is that although the guest correctly gets the exception, it will return to the original context in some random state, depending on what was there the first place... Boo.

Fix the issue by writing to the shadow register. The original code is absolutely fine on VHE, as the state is already loaded, and writing to the shadow register in that case would actually be a bug.

---
 arch/arm64/kvm/hyp/exception.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -38,7 +38,10 @@ static inline void __vcpu_write_sys_reg(
 
 static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, u64 val)
 {
-	write_sysreg_el1(val, SYS_SPSR);
+	if (has_vhe())
+		write_sysreg_el1(val, SYS_SPSR);
+	else
+		__vcpu_sys_reg(vcpu, SPSR_EL1) = val;
 }
 
 static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val)

From: Sean Christopherson <[email protected]>

commit 55467fcd55b89c622e62b4afe60ac0eb2fae91f2 upstream.

Always signal that emulation is possible for !SEV guests regardless of whether or not the CPU provided a valid instruction byte stream. KVM can read all guest state (memory and registers) for !SEV guests, i.e. can fetch the code stream from memory even if the CPU failed to do so because of the SMAP errata.

Message-Id: <[email protected]>

---
 arch/x86/kvm/svm/svm.c |   10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

@@ -4407,8 +4407,13 @@ static bool svm_can_emulate_instruction(
 	bool smep, smap, is_user;
 	unsigned long cr4;
 
+	/* Emulation is always possible when KVM has access to all guest state. */
+	if (!sev_guest(vcpu->kvm))
+		return true;
+
 	/*
-	 * When the guest is an SEV-ES guest, emulation is not possible.
+	 * Emulation is impossible for SEV-ES guests as KVM doesn't have access
+	 * to guest register state.
 	 */
 	if (sev_es_guest(vcpu->kvm))
 		return false;

@@ -4461,9 +4466,6 @@ static bool svm_can_emulate_instruction(
 	smap = cr4 & X86_CR4_SMAP;
 	is_user = svm_get_cpl(vcpu) == 3;
 	if (smap && (!smep || is_user)) {
-		if (!sev_guest(vcpu->kvm))
-			return true;
-
 		pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n");
 		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 	}

From: Sean Christopherson <[email protected]>

commit 0b0be065b7563ac708aaa9f69dd4941c80b3446d upstream.

Never intercept #GP for SEV guests as reading SEV guest private memory will return cyphertext, i.e. emulating on #GP can't work as intended.

Message-Id: <[email protected]>

---
 arch/x86/kvm/svm/svm.c |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

@@ -303,7 +303,11 @@ int svm_set_efer(struct kvm_vcpu *vcpu,
 				return ret;
 			}
 
-			if (svm_gp_erratum_intercept)
+			/*
+			 * Never intercept #GP for SEV guests, KVM can't
+			 * decrypt guest memory to workaround the erratum.
+			 */
+			if (svm_gp_erratum_intercept && !sev_guest(vcpu->kvm))
 				set_exception_intercept(svm, GP_VECTOR);
 		}
 	}

@@ -1176,9 +1180,10 @@ static void init_vmcb(struct kvm_vcpu *v
 	 * Guest access to VMware backdoor ports could legitimately
 	 * trigger #GP because of TSS I/O permission bitmap.
 	 * We intercept those #GP and allow access to them anyway
-	 * as VMware does.
+	 * as VMware does.  Don't intercept #GP for SEV guests as KVM can't
+	 * decrypt guest memory to decode the faulting instruction.
 	 */
-	if (enable_vmware_backdoor)
+	if (enable_vmware_backdoor && !sev_guest(vcpu->kvm))
 		set_exception_intercept(svm, GP_VECTOR);
 
 	svm_set_intercept(svm, INTERCEPT_INTR);

From: Xiaoyao Li <[email protected]>

commit be4f3b3f82271c3193ce200a996dc70682c8e622 upstream.

It has been corrected from SDM version 075 that MSR_IA32_XSS is reset to zero on Power up and Reset but keeps unchanged on INIT.

Message-Id: <[email protected]>

---
 arch/x86/kvm/x86.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -10990,6 +10990,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcp
 		vcpu->arch.msr_misc_features_enables = 0;
 
 		vcpu->arch.xcr0 = XFEATURE_MASK_FP;
+		vcpu->arch.ia32_xss = 0;
 	}
 
 	memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));

@@ -11008,8 +11009,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcp
 		eax = 0x600;
 	kvm_rdx_write(vcpu, eax);
 
-	vcpu->arch.ia32_xss = 0;
-
 	static_call(kvm_x86_vcpu_reset)(vcpu, init_event);
 
 	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);

From: Like Xu <[email protected]>

commit 05a9e065059e566f218f8778c4d17ee75db56c55 upstream.

XCR0 is reset to 1 by RESET but not INIT and IA32_XSS is zeroed by both RESET and INIT. The kvm_set_msr_common()'s handling of MSR_IA32_XSS also needs to update kvm_update_cpuid_runtime(). In the above cases, the size in bytes of the XSAVE area containing all states enabled by XCR0 or (XCRO | IA32_XSS) needs to be updated.

For simplicity and consistency, existing helpers are used to write values and call kvm_update_cpuid_runtime(), and it's not exactly a fast path.

Message-Id: <[email protected]>

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

@@ -10990,8 +10990,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcp
 
 		vcpu->arch.msr_misc_features_enables = 0;
 
-		vcpu->arch.xcr0 = XFEATURE_MASK_FP;
-		vcpu->arch.ia32_xss = 0;
+		__kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP);
+		__kvm_set_msr(vcpu, MSR_IA32_XSS, 0, true);
 	}
 
 	memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));

From: Nicholas Piggin <[email protected]>

commit 22f7ff0dea9491e90b6fe808ed40c30bd791e5c2 upstream.

The L0 is storing HFSCR requested by the L1 for the L2 in struct kvm_nested_guest when the L1 requests a vCPU enter L2. kvm_nested_guest is not a per-vCPU structure. Hilarity ensues.

Fix it by moving the nested hfscr into the vCPU structure together with the other per-vCPU nested fields.

---
 arch/powerpc/include/asm/kvm_book3s_64.h |    1 -
 arch/powerpc/include/asm/kvm_host.h      |    1 +
 arch/powerpc/kvm/book3s_hv.c             |    3 +--
 arch/powerpc/kvm/book3s_hv_nested.c      |    2 +-
 4 files changed, 3 insertions(+), 4 deletions(-)

@@ -39,7 +39,6 @@ struct kvm_nested_guest {
 	pgd_t *shadow_pgtable;		/* our page table for this guest */
 	u64 l1_gr_to_hr;		/* L1's addr of part'n-scoped table */
 	u64 process_table;		/* process table entry for this guest */
-	u64 hfscr;			/* HFSCR that the L1 requested for this nested guest */
 	long refcnt;			/* number of pointers to this struct */
 	struct mutex tlb_lock;		/* serialize page faults and tlbies */
 	struct kvm_nested_guest *next;

@@ -814,6 +814,7 @@ struct kvm_vcpu_arch {
 
 	/* For support of nested guests */
 	struct kvm_nested_guest *nested;
+	u64 nested_hfscr;	/* HFSCR that the L1 requested for the nested guest */
 	u32 nested_vcpu_id;
 	gpa_t nested_io_gpr;
 #endif

@@ -1731,7 +1731,6 @@ static int kvmppc_handle_exit_hv(struct
 
 static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 {
-	struct kvm_nested_guest *nested = vcpu->arch.nested;
 	int r;
 	int srcu_idx;
 

@@ -1831,7 +1830,7 @@ static int kvmppc_handle_nested_exit(str
 		 * it into a HEAI.
 		 */
 		if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) ||
-					(nested->hfscr & (1UL << cause))) {
+				(vcpu->arch.nested_hfscr & (1UL << cause))) {
 			vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
 
 			/*

@@ -362,7 +362,7 @@ long kvmhv_enter_nested_guest(struct kvm
 	/* set L1 state to L2 state */
 	vcpu->arch.nested = l2;
 	vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token;
-	l2->hfscr = l2_hv.hfscr;
+	vcpu->arch.nested_hfscr = l2_hv.hfscr;
 	vcpu->arch.regs = l2_regs;
 
 	/* Guest must always run with ME enabled, HV disabled. */

From: Mike Snitzer <[email protected]>

commit f524d9c95fab54783d0038f7a3e8c014d5b56857 upstream.

Reverts a1e1cb72d9649 ("dm: fix redundant IO accounting for bios that need splitting") because it was too narrow in scope (only addressed redundant 'sectors[]' accounting and not ios, nsecs[], etc).

---
 drivers/md/dm.c |   15 ---------------
 1 file changed, 15 deletions(-)

@@ -1514,9 +1514,6 @@ static void init_clone_info(struct clone
 	ci->sector = bio->bi_iter.bi_sector;
 }
 
-#define __dm_part_stat_sub(part, field, subnd)	\
-	(part_stat_get(part, field) -= (subnd))
-
 /*
  * Entry point to split a bio into clones and submit them to the targets.
  */

@@ -1553,18 +1550,6 @@ static blk_qc_t __split_and_process_bio(
 						  GFP_NOIO, &md->queue->bio_split);
 			ci.io->orig_bio = b;
 
-			/*
-			 * Adjust IO stats for each split, otherwise upon queue
-			 * reentry there will be redundant IO accounting.
-			 * NOTE: this is a stop-gap fix, a proper fix involves
-			 * significant refactoring of DM core's bio splitting
-			 * (by eliminating DM's splitting and just using bio_split)
-			 */
-			part_stat_lock();
-			__dm_part_stat_sub(dm_disk(md)->part0,
-					   sectors[op_stat_group(bio_op(bio))], ci.sector_count);
-			part_stat_unlock();
-
 			bio_chain(b, bio);
 			trace_block_split(b, bio->bi_iter.bi_sector);
 			ret = submit_bio_noacct(bio);

From: Sean Christopherson <[email protected]>

commit 31c25585695abdf03d6160aa6d829e855b256329 upstream.

Revert a completely broken check on an "invalid" RIP in SVM's workaround for the DecodeAssists SMAP errata. kvm_vcpu_gfn_to_memslot() obviously expects a gfn, i.e. operates in the guest physical address space, whereas RIP is a virtual (not even linear) address. The "fix" worked for the problematic KVM selftest because the test identity mapped RIP.

Fully revert the hack instead of trying to translate RIP to a GPA, as the non-SEV case is now handled earlier, and KVM cannot access guest page tables to translate RIP.

This reverts commit e72436bc3a5206f95bb384e741154166ddb3202e.

Message-Id: <[email protected]>

---
 arch/x86/kvm/svm/svm.c |    7 -------
 virt/kvm/kvm_main.c    |    1 -
 2 files changed, 8 deletions(-)

@@ -4456,13 +4456,6 @@ static bool svm_can_emulate_instruction(
 	if (likely(!insn || insn_len))
 		return true;
 
-	/*
-	 * If RIP is invalid, go ahead with emulation which will cause an
-	 * internal error exit.
-	 */
-	if (!kvm_vcpu_gfn_to_memslot(vcpu, kvm_rip_read(vcpu) >> PAGE_SHIFT))
-		return true;
-
 	cr4 = kvm_read_cr4(vcpu);
 	smep = cr4 & X86_CR4_SMEP;
 	smap = cr4 & X86_CR4_SMAP;

@@ -2104,7 +2104,6 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_memslot);
 
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {

From: Mike Snitzer <[email protected]>

commit b879f915bc48a18d4f4462729192435bb0f17052 upstream.

Record the start_time for a bio but defer the starting block core's IO accounting until after IO is submitted using bio_start_io_acct_time().

This approach avoids the need to mess around with any of the individual IO stats in response to a bio_split() that follows bio submission.

Depends-on: e45c47d1f94e ("block: add bio_start_io_acct_time() to control start_time")

---
 drivers/md/dm.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

@@ -489,7 +489,7 @@ static void start_io_acct(struct dm_io *
 	struct mapped_device *md = io->md;
 	struct bio *bio = io->orig_bio;
 
-	io->start_time = bio_start_io_acct(bio);
+	bio_start_io_acct_time(bio, io->start_time);
 	if (unlikely(dm_stats_used(&md->stats)))
 		dm_stats_account_io(&md->stats, bio_data_dir(bio),
 				    bio->bi_iter.bi_sector, bio_sectors(bio),

@@ -535,7 +535,7 @@ static struct dm_io *alloc_io(struct map
 	io->md = md;
 	spin_lock_init(&io->endio_lock);
 
-	start_io_acct(io);
+	io->start_time = jiffies;
 
 	return io;
 }

@@ -1555,6 +1555,7 @@ static blk_qc_t __split_and_process_bio(
 			ret = submit_bio_noacct(bio);
 		}
 	}
+	start_io_acct(ci.io);
 
 	/* drop the extra reference count */
 	dm_io_dec_pending(ci.io, errno_to_blk_status(error));

From: Jochen Mades <[email protected]>

commit 62f676ff7898f6c1bd26ce014564773a3dc00601 upstream.

Commit 8d479237727c ("serial: amba-pl011: add RS485 support") sought to keep RTS deasserted on set_mctrl if rs485 is enabled. However it did so only if deasserted RTS polarity is high. Fix it in case it's low.

---
 drivers/tty/serial/amba-pl011.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

@@ -1615,8 +1615,12 @@ static void pl011_set_mctrl(struct uart_
 	    container_of(port, struct uart_amba_port, port);
 	unsigned int cr;
 
-	if (port->rs485.flags & SER_RS485_ENABLED)
-		mctrl &= ~TIOCM_RTS;
+	if (port->rs485.flags & SER_RS485_ENABLED) {
+		if (port->rs485.flags & SER_RS485_RTS_AFTER_SEND)
+			mctrl &= ~TIOCM_RTS;
+		else
+			mctrl |= TIOCM_RTS;
+	}
 
 	cr = pl011_read(uap, REG_CR);
 

From: Robert Hancock <[email protected]>

commit d06b1cf28297e27127d3da54753a3a01a2fa2f28 upstream.

8250_of supports a reg-offset property which is intended to handle cases where the device registers start at an offset inside the region of memory allocated to the device. The Xilinx 16550 UART, for which this support was initially added, requires this. However, the code did not adjust the overall size of the mapped region accordingly, causing the driver to request an area of memory past the end of the device's allocation. For example, if the UART was allocated an address of 0xb0130000, size of 0x10000 and reg-offset of 0x1000 in the device tree, the region of memory reserved was b0131000-b0140fff, which caused the driver for the region starting at b0140000 to fail to probe.

Fix this by subtracting reg-offset from the mapped region size.

---
 drivers/tty/serial/8250/8250_of.c |   11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

@@ -83,8 +83,17 @@ static int of_platform_serial_setup(stru
 		port->mapsize = resource_size(&resource);
 
 		/* Check for shifted address mapping */
-		if (of_property_read_u32(np, "reg-offset", &prop) == 0)
+		if (of_property_read_u32(np, "reg-offset", &prop) == 0) {
+			if (prop >= port->mapsize) {
+				dev_warn(&ofdev->dev, "reg-offset %u exceeds region size %pa\n",
+					 prop, &port->mapsize);
+				ret = -EINVAL;
+				goto err_unprepare;
+			}
+
 			port->mapbase += prop;
+			port->mapsize -= prop;
+		}
 
 		port->iotype = UPIO_MEM;
 		if (of_property_read_u32(np, "reg-io-width", &prop) == 0) {

From: Valentin Caron <[email protected]>

commit 037b91ec7729524107982e36ec4b40f9b174f7a2 upstream.

x_char is ignored by stm32_usart_start_tx() when xmit buffer is empty.

Fix start_tx condition to allow x_char to be sent.

---
 drivers/tty/serial/stm32-usart.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -575,7 +575,7 @@ static void stm32_usart_start_tx(struct
 	struct serial_rs485 *rs485conf = &port->rs485;
 	struct circ_buf *xmit = &port->state->xmit;
 
-	if (uart_circ_empty(xmit))
+	if (uart_circ_empty(xmit) && !port->x_char)
 		return;
 
 	if (rs485conf->flags & SER_RS485_ENABLED) {

From: Maciej W. Rozycki <[email protected]>

commit f23653fe64479d96910bfda2b700b1af17c991ac upstream.

Fix a user API regression introduced with commit f76edd8f7ce0 ("tty:
cyclades, remove this orphan"), which removed a part of the API and caused compilation errors for user programs using said part, such as GCC 9 in its libsanitizer component[1]:

.../libsanitizer/sanitizer_common/sanitizer_platform_limits_posix.cc:160:10: fatal error: linux/cyclades.h: No such file or directory
160 | #include <linux/cyclades.h>

      |          ^~~~~~~~~~~~~~~~~~

compilation terminated.
make[4]: *** [Makefile:664: sanitizer_platform_limits_posix.lo] Error 1

As the absolute minimum required bring `struct cyclades_monitor' and ioctl numbers back then so as to make the library build again. Add a preprocessor warning as to the obsolescence of the features provided.

[1] GCC PR sanitizer/100379, "cyclades.h is removed from linux kernel

    header files", <https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100379>

---
 include/uapi/linux/cyclades.h |   35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 include/uapi/linux/cyclades.h

@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_CYCLADES_H
+#define _UAPI_LINUX_CYCLADES_H
+
+#warning "Support for features provided by this header has been removed"
+#warning "Please consider updating your code"
+
+struct cyclades_monitor {
+	unsigned long int_count;
+	unsigned long char_count;
+	unsigned long char_max;
+	unsigned long char_last;
+};
+
+#define CYGETMON		0x435901
+#define CYGETTHRESH		0x435902
+#define CYSETTHRESH		0x435903
+#define CYGETDEFTHRESH		0x435904
+#define CYSETDEFTHRESH		0x435905
+#define CYGETTIMEOUT		0x435906
+#define CYSETTIMEOUT		0x435907
+#define CYGETDEFTIMEOUT		0x435908
+#define CYSETDEFTIMEOUT		0x435909
+#define CYSETRFLOW		0x43590a
+#define CYGETRFLOW		0x43590b
+#define CYSETRTSDTR_INV		0x43590c
+#define CYGETRTSDTR_INV		0x43590d
+#define CYZSETPOLLCYCLE		0x43590e
+#define CYZGETPOLLCYCLE		0x43590f
+#define CYGETCD1400VER		0x435910
+#define CYSETWAIT		0x435912
+#define CYGETWAIT		0x435913
+
+#endif /* _UAPI_LINUX_CYCLADES_H */

From: Cameron Williams <[email protected]>

commit 152d1afa834c84530828ee031cf07a00e0fc0b8c upstream.

This commit adds support for the some of the Brainboxes PCI range of cards, including the UC-101, UC-235/246, UC-257, UC-268, UC-275/279, UC-302, UC-310, UC-313, UC-320/324, UC-346, UC-357, UC-368 and UC-420/431.

---
 drivers/tty/serial/8250/8250_pci.c |  100 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 98 insertions(+), 2 deletions(-)

@@ -5203,8 +5203,30 @@ static const struct pci_device_id serial
 	{	PCI_VENDOR_ID_INTASHIELD, PCI_DEVICE_ID_INTASHIELD_IS400,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,    /* 135a.0dc0 */
 		pbn_b2_4_115200 },
+	/* Brainboxes Devices */
 	/*
-	 * BrainBoxes UC-260
+	* Brainboxes UC-101
+	*/
+	{       PCI_VENDOR_ID_INTASHIELD, 0x0BA1,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_2_115200 },
+	/*
+	 * Brainboxes UC-235/246
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0AA1,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_1_115200 },
+	/*
+	 * Brainboxes UC-257
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0861,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_2_115200 },
+	/*
+	 * Brainboxes UC-260/271/701/756
 	 */
 	{	PCI_VENDOR_ID_INTASHIELD, 0x0D21,
 		PCI_ANY_ID, PCI_ANY_ID,

@@ -5212,7 +5234,81 @@ static const struct pci_device_id serial
 		pbn_b2_4_115200 },
 	{	PCI_VENDOR_ID_INTASHIELD, 0x0E34,
 		PCI_ANY_ID, PCI_ANY_ID,
-		 PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00,
+		PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00,
+		pbn_b2_4_115200 },
+	/*
+	 * Brainboxes UC-268
+	 */
+	{       PCI_VENDOR_ID_INTASHIELD, 0x0841,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_4_115200 },
+	/*
+	 * Brainboxes UC-275/279
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0881,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_8_115200 },
+	/*
+	 * Brainboxes UC-302
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x08E1,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_2_115200 },
+	/*
+	 * Brainboxes UC-310
+	 */
+	{       PCI_VENDOR_ID_INTASHIELD, 0x08C1,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_2_115200 },
+	/*
+	 * Brainboxes UC-313
+	 */
+	{       PCI_VENDOR_ID_INTASHIELD, 0x08A3,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_2_115200 },
+	/*
+	 * Brainboxes UC-320/324
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0A61,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_1_115200 },
+	/*
+	 * Brainboxes UC-346
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0B02,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_4_115200 },
+	/*
+	 * Brainboxes UC-357
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0A81,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_2_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0A83,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_2_115200 },
+	/*
+	 * Brainboxes UC-368
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0C41,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_4_115200 },
+	/*
+	 * Brainboxes UC-420/431
+	 */
+	{       PCI_VENDOR_ID_INTASHIELD, 0x0921,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
 		pbn_b2_4_115200 },
 	/*
 	 * Perle PCI-RAS cards

From: Suren Baghdasaryan <[email protected]>

commit a06247c6804f1a7c86a2e5398a4c1f1db1471848 upstream.

With write operation on psi files replacing old trigger with a new one, the lifetime of its waitqueue is totally arbitrary. Overwriting an existing trigger causes its waitqueue to be freed and pending poll() will stumble on trigger->event_wait which was destroyed.
Fix this by disallowing to redefine an existing psi trigger. If a write operation is used on a file descriptor with an already existing psi trigger, the operation will fail with EBUSY error.
Also bypass a check for psi_disabled in the psi_trigger_destroy as the flag can be flipped after the trigger is created, leading to a memory leak.

---
 Documentation/accounting/psi.rst |    3 +
 include/linux/psi.h              |    2 -
 include/linux/psi_types.h        |    3 -
 kernel/cgroup/cgroup.c           |   11 ++++--
 kernel/sched/psi.c               |   66 +++++++++++++++++----------------------
 5 files changed, 40 insertions(+), 45 deletions(-)

@@ -92,7 +92,8 @@ Triggers can be set on more than one psi
 for the same psi metric can be specified. However for each trigger a separate
 file descriptor is required to be able to poll it separately from others,
 therefore for each trigger a separate open() syscall should be made even
-when opening the same psi interface file.
+when opening the same psi interface file. Write operations to a file descriptor
+with an already existing psi trigger will fail with EBUSY.
 
 Monitors activate only when system enters stall state for the monitored
 psi metric and deactivates upon exit from the stall state. While system is

@@ -32,7 +32,7 @@ void cgroup_move_task(struct task_struct
 
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
 			char *buf, size_t nbytes, enum psi_res res);
-void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t);
+void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
 			poll_table *wait);

@@ -140,9 +140,6 @@ struct psi_trigger {
 	 * events to one per window
 	 */
 	u64 last_event_time;
-
-	/* Refcounting to prevent premature destruction */
-	struct kref refcount;
 };
 
 struct psi_group {

@@ -3642,6 +3642,12 @@ static ssize_t cgroup_pressure_write(str
 	cgroup_get(cgrp);
 	cgroup_kn_unlock(of->kn);
 
+	/* Allow only one trigger per file descriptor */
+	if (ctx->psi.trigger) {
+		cgroup_put(cgrp);
+		return -EBUSY;
+	}
+
 	psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
 	new = psi_trigger_create(psi, buf, nbytes, res);
 	if (IS_ERR(new)) {

@@ -3649,8 +3655,7 @@ static ssize_t cgroup_pressure_write(str
 		return PTR_ERR(new);
 	}
 
-	psi_trigger_replace(&ctx->psi.trigger, new);
-
+	smp_store_release(&ctx->psi.trigger, new);
 	cgroup_put(cgrp);
 
 	return nbytes;

@@ -3689,7 +3694,7 @@ static void cgroup_pressure_release(stru
 {
 	struct cgroup_file_ctx *ctx = of->priv;
 
-	psi_trigger_replace(&ctx->psi.trigger, NULL);
+	psi_trigger_destroy(ctx->psi.trigger);
 }
 
 bool cgroup_psi_enabled(void)

From: Greg Kroah-Hartman <[email protected]>

commit d1ad2721b1eb05d54e81393a7ebc332d4a35c68f upstream.

The file now rightfully throws up a big warning that it should never be included, so remove it from the header_check test.

---
 usr/include/Makefile |    1 +
 1 file changed, 1 insertion(+)

@@ -28,6 +28,7 @@ no-header-test += linux/am437x-vpfe.h
 no-header-test += linux/android/binder.h
 no-header-test += linux/android/binderfs.h
 no-header-test += linux/coda.h
+no-header-test += linux/cyclades.h
 no-header-test += linux/errqueue.h
 no-header-test += linux/fsmap.h
 no-header-test += linux/hdlc/ioctl.h

From: Frank Li <[email protected]>

commit 9df478463d9feb90dae24f183383961cf123a0ec upstream.

Crashed at i.mx8qm platform when suspend if enable remote wakeup

Internal error: synchronous external abort: 96000210 [#1] PREEMPT SMP
Modules linked in:
CPU: 2 PID: 244 Comm: kworker/u12:6 Not tainted 5.15.5-dirty #12
Hardware name: Freescale i.MX8QM MEK (DT)
Workqueue: events_unbound async_run_entry_fn
pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : xhci_disable_hub_port_wake.isra.62+0x60/0xf8
lr : xhci_disable_hub_port_wake.isra.62+0x34/0xf8

sp : ffff80001394bbf0
x29: ffff80001394bbf0 x28: 0000000000000000 x27: ffff00081193b578
x26: ffff00081193b570 x25: 0000000000000000 x24: 0000000000000000
x23: ffff00081193a29c x22: 0000000000020001 x21: 0000000000000001
x20: 0000000000000000 x19: ffff800014e90490 x18: 0000000000000000
x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000
x14: 0000000000000000 x13: 0000000000000002 x12: 0000000000000000
x11: 0000000000000000 x10: 0000000000000960 x9 : ffff80001394baa0 x8 : ffff0008145d1780 x7 : ffff0008f95b8e80 x6 : 000000001853b453 x5 : 0000000000000496 x4 : 0000000000000000 x3 : ffff00081193a29c x2 : 0000000000000001 x1 : 0000000000000000 x0 : ffff000814591620

Call trace:
 xhci_disable_hub_port_wake.isra.62+0x60/0xf8
 xhci_suspend+0x58/0x510
 xhci_plat_suspend+0x50/0x78
 platform_pm_suspend+0x2c/0x78
 dpm_run_callback.isra.25+0x50/0xe8
 __device_suspend+0x108/0x3c0

The basic flow:
1. run time suspend call xhci_suspend, xhci parent devices gate the clock.
2. echo mem >/sys/power/state, system _device_suspend call xhci_suspend
3. xhci_suspend call xhci_disable_hub_port_wake, which access register, but clock already gated by run time suspend.

This problem was hidden by power domain driver, which call run time resume before it.

But the below commit remove it and make this issue happen.
commit c1df456d0f06e ("PM: domains: Don't runtime resume devices at genpd_prepare()")

This patch call run time resume before suspend to make sure clock is on before access register.

---
 drivers/usb/host/xhci-plat.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -437,6 +437,9 @@ static int __maybe_unused xhci_plat_susp
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	int ret;
 
+	if (pm_runtime_suspended(dev))
+		pm_runtime_resume(dev);
+
 	ret = xhci_priv_suspend_quirk(hcd);
 	if (ret)
 		return ret;

From: Pavankumar Kondeti <[email protected]>

commit 904edf8aeb459697129be5fde847e2a502f41fd9 upstream.

Currently when gadget enumerates in super speed plus, the isoc endpoint request buffer size is not calculated correctly. Fix this by checking the gadget speed against USB_SPEED_SUPER_PLUS and update the request buffer size.

---
 drivers/usb/gadget/function/f_sourcesink.c |    1 +
 1 file changed, 1 insertion(+)

@@ -584,6 +584,7 @@ static int source_sink_start_ep(struct f
 
 	if (is_iso) {
 		switch (speed) {
+		case USB_SPEED_SUPER_PLUS:
 		case USB_SPEED_SUPER:
 			size = ss->isoc_maxpacket *
 					(ss->isoc_mult + 1) *

From: Pawel Laszczak <[email protected]>

commit 79aa3e19fe8f5be30e846df8a436bfe306e8b1a6 upstream.

CDNSP driver read not initialized cdns->otg_v0_regs which lead to segmentation fault. Patch fixes this issue.

---
 drivers/usb/cdns3/drd.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -483,11 +483,11 @@ int cdns_drd_exit(struct cdns *cdns)
 /* Indicate the cdns3 core was power lost before */
 bool cdns_power_is_lost(struct cdns *cdns)
 {
-	if (cdns->version == CDNS3_CONTROLLER_V1) {
-		if (!(readl(&cdns->otg_v1_regs->simulate) & BIT(0)))
+	if (cdns->version == CDNS3_CONTROLLER_V0) {
+		if (!(readl(&cdns->otg_v0_regs->simulate) & BIT(0)))
 			return true;
 	} else {
-		if (!(readl(&cdns->otg_v0_regs->simulate) & BIT(0)))
+		if (!(readl(&cdns->otg_v1_regs->simulate) & BIT(0)))
 			return true;
 	}
 	return false;

From: Robert Hancock <[email protected]>

commit 9678f3361afc27a3124cd2824aec0227739986fb upstream.

It appears that the PIPE clock should not be selected when only USB 2.0 is being used in the design and no USB 3.0 reference clock is used. Also, the core resets are not required if a USB3 PHY is not in use, and will break things if USB3 is actually used but the PHY entry is not listed in the device tree.

Skip core resets and register settings that are only required for USB3 mode when no USB3 PHY is specified in the device tree.

---
 drivers/usb/dwc3/dwc3-xilinx.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)

@@ -110,6 +110,18 @@ static int dwc3_xlnx_init_zynqmp(struct
 		usb3_phy = NULL;
 	}
 
+	/*
+	 * The following core resets are not required unless a USB3 PHY
+	 * is used, and the subsequent register settings are not required
+	 * unless a core reset is performed (they should be set properly
+	 * by the first-stage boot loader, but may be reverted by a core
+	 * reset). They may also break the configuration if USB3 is actually
+	 * in use but the usb3-phy entry is missing from the device tree.
+	 * Therefore, skip these operations in this case.
+	 */
+	if (!usb3_phy)
+		goto skip_usb3_phy;
+
 	crst = devm_reset_control_get_exclusive(dev, "usb_crst");
 	if (IS_ERR(crst)) {
 		ret = PTR_ERR(crst);

@@ -188,6 +200,7 @@ static int dwc3_xlnx_init_zynqmp(struct
 		goto err;
 	}
 
+skip_usb3_phy:
 	/*
 	 * This routes the USB DMA traffic to go through FPD path instead
 	 * of reaching DDR directly. This traffic routing is needed to

From: Robert Hancock <[email protected]>

commit 2cc9b1c93b1c4caa2d971856c0780fb5f7d04692 upstream.

The code that looked up the USB3 PHY was ignoring all errors other than EPROBE_DEFER in an attempt to handle the PHY not being present. Fix and simplify the code by using devm_phy_optional_get and dev_err_probe so that a missing PHY is not treated as an error and unexpected errors are handled properly.

---
 drivers/usb/dwc3/dwc3-xilinx.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -102,12 +102,12 @@ static int dwc3_xlnx_init_zynqmp(struct
 	int			ret;
 	u32			reg;
 
-	usb3_phy = devm_phy_get(dev, "usb3-phy");
-	if (PTR_ERR(usb3_phy) == -EPROBE_DEFER) {
-		ret = -EPROBE_DEFER;
+	usb3_phy = devm_phy_optional_get(dev, "usb3-phy");
+	if (IS_ERR(usb3_phy)) {
+		ret = PTR_ERR(usb3_phy);
+		dev_err_probe(dev, ret,
+			      "failed to get USB3 PHY\n");
 		goto err;
-	} else if (IS_ERR(usb3_phy)) {
-		usb3_phy = NULL;
 	}
 
 	/*

From: Zhengjun Xing <[email protected]>

commit 96fd2e89fba1aaada6f4b1e5d25a9d9ecbe1943d upstream.

The user recently report a perf issue in the ICX platform, when test by perf event “uncore_imc_x/cas_count_write”,the write bandwidth is always very small (only 0.38MB/s), it is caused by the wrong "umask" for the "cas_count_write" event. When double-checking, find "cas_count_read" also is wrong.

The public document for ICX uncore:

3rd Gen Intel® Xeon® Processor Scalable Family, Codename Ice Lake,Uncore Performance Monitoring Reference Manual, Revision 1.00, May 2021

On 2.4.7, it defines Unit Masks for CAS_COUNT:
RD b00001111
WR b00110000

So corrected both "cas_count_read" and "cas_count_write" for ICX.

Old settings:
hswep_uncore_imc_events

	INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03")
	INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c")

New settings:
snr_uncore_imc_events

	INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x0f")
	INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x30")

---
 arch/x86/events/intel/uncore_snbep.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -5482,7 +5482,7 @@ static struct intel_uncore_type icx_unco
 	.fixed_ctr_bits	= 48,
 	.fixed_ctr	= SNR_IMC_MMIO_PMON_FIXED_CTR,
 	.fixed_ctl	= SNR_IMC_MMIO_PMON_FIXED_CTL,
-	.event_descs	= hswep_uncore_imc_events,
+	.event_descs	= snr_uncore_imc_events,
 	.perf_ctr	= SNR_IMC_MMIO_PMON_CTR0,
 	.event_ctl	= SNR_IMC_MMIO_PMON_CTL0,
 	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,

From: Bas Nieuwenhuizen <[email protected]>

commit 72a8d87b87270bff0c0b2fed4d59c48d0dd840d7 upstream.

It calls populate_dml_pipes which uses doubles to initialize the scale_ratio_depth params. Mirrors the dcn20 logic.

---
 drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1879,7 +1879,6 @@ static noinline bool dcn30_internal_vali
 	dc->res_pool->funcs->update_soc_for_wm_a(dc, context);
 	pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate);
 
-	DC_FP_START();
 	if (!pipe_cnt) {
 		out = true;
 		goto validate_out;

@@ -2103,7 +2102,6 @@ validate_fail:
 	out = false;
 
 validate_out:
-	DC_FP_END();
 	return out;
 }
 

@@ -2304,7 +2302,9 @@ bool dcn30_validate_bandwidth(struct dc
 
 	BW_VAL_TRACE_COUNT();
 
+	DC_FP_START();
 	out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate);
+	DC_FP_END();
 
 	if (pipe_cnt == 0)
 		goto validate_out;

From: Jeff Layton <[email protected]>

commit 4584a768f22b7669cdebabc911543621ac661341 upstream.

Dan reported that he was unable to write to files that had been asynchronously created when the client's OSD caps are restricted to a particular namespace.

The issue is that the layout for the new inode is only partially being filled. Ensure that we populate the pool_ns_data and pool_ns_len in the iinfo before calling ceph_fill_inode.

Cc: [email protected]
URL: https://tracker.ceph.com/issues/54013

---
 fs/ceph/file.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -577,6 +577,7 @@ static int ceph_finish_async_create(stru
 	struct ceph_inode_info *ci = ceph_inode(dir);
 	struct inode *inode;
 	struct timespec64 now;
+	struct ceph_string *pool_ns;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
 	struct ceph_vino vino = { .ino = req->r_deleg_ino,
 				  .snap = CEPH_NOSNAP };

@@ -626,6 +627,12 @@ static int ceph_finish_async_create(stru
 	in.max_size = cpu_to_le64(lo->stripe_unit);
 
 	ceph_file_layout_to_legacy(lo, &in.layout);
+	/* lo is private, so pool_ns can't change */
+	pool_ns = rcu_dereference_raw(lo->pool_ns);
+	if (pool_ns) {
+		iinfo.pool_ns_len = pool_ns->len;
+		iinfo.pool_ns_data = pool_ns->str;
+	}
 
 	down_read(&mdsc->snap_rwsem);
 	ret = ceph_fill_inode(inode, NULL, &iinfo, NULL, req->r_session,

From: Marc Kleine-Budde <[email protected]>

commit db72589c49fd260bfc99c7160c079675bc7417af upstream.

In order to optimize FIFO access, especially on m_can cores attached to slow busses like SPI, in patch

| e39381770ec9 ("can: m_can: Disable IRQs on FIFO bus errors")

bulk read/write support has been added to the m_can_fifo_{read,write} functions.

That change leads to the tcan driver to call regmap_bulk_{read,write}() with a length of 0 (for CAN frames with 0 data length). regmap treats this as an error:

| tcan4x5x spi1.0 tcan4x5x0: FIFO write returned -22

This patch fixes the problem by not calling the cdev->ops->{read,write)_fifo() in case of a 0 length read/write.

---
 drivers/net/can/m_can/m_can.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -336,6 +336,9 @@ m_can_fifo_read(struct m_can_classdev *c
 	u32 addr_offset = cdev->mcfg[MRAM_RXF0].off + fgi * RXF0_ELEMENT_SIZE +
 		offset;
 
+	if (val_count == 0)
+		return 0;
+
 	return cdev->ops->read_fifo(cdev, addr_offset, val, val_count);
 }
 

@@ -346,6 +349,9 @@ m_can_fifo_write(struct m_can_classdev *
 	u32 addr_offset = cdev->mcfg[MRAM_TXB].off + fpi * TXB_ELEMENT_SIZE +
 		offset;
 
+	if (val_count == 0)
+		return 0;
+
 	return cdev->ops->write_fifo(cdev, addr_offset, val, val_count);
 }
 

From: Xu Yang <[email protected]>

commit 5638b0dfb6921f69943c705383ff40fb64b987f2 upstream.

With the AMS and Collision Avoidance, tcpm often needs to change the CC's termination. When one CC line is sourcing Vconn, if we still change its termination, the voltage of the another CC line is likely to be fluctuant and unstable.

Therefore, we should verify whether a CC line is sourcing Vconn before changing its termination and only change the termination that is not a Vconn line. This can be done by reading the Vconn Present bit of POWER_ STATUS register. To determine the polarity, we can read the Plug Orientation bit of TCPC_CONTROL register. Since Vconn can only be sourced if Plug Orientation is set.

---
 drivers/usb/typec/tcpm/tcpci.c |   26 ++++++++++++++++++++++++++
 drivers/usb/typec/tcpm/tcpci.h |    1 +
 2 files changed, 27 insertions(+)

@@ -75,9 +75,25 @@ static int tcpci_write16(struct tcpci *t
 static int tcpci_set_cc(struct tcpc_dev *tcpc, enum typec_cc_status cc)
 {
 	struct tcpci *tcpci = tcpc_to_tcpci(tcpc);
+	bool vconn_pres;
+	enum typec_cc_polarity polarity = TYPEC_POLARITY_CC1;
 	unsigned int reg;
 	int ret;
 
+	ret = regmap_read(tcpci->regmap, TCPC_POWER_STATUS, &reg);
+	if (ret < 0)
+		return ret;
+
+	vconn_pres = !!(reg & TCPC_POWER_STATUS_VCONN_PRES);
+	if (vconn_pres) {
+		ret = regmap_read(tcpci->regmap, TCPC_TCPC_CTRL, &reg);
+		if (ret < 0)
+			return ret;
+
+		if (reg & TCPC_TCPC_CTRL_ORIENTATION)
+			polarity = TYPEC_POLARITY_CC2;
+	}
+
 	switch (cc) {
 	case TYPEC_CC_RA:
 		reg = (TCPC_ROLE_CTRL_CC_RA << TCPC_ROLE_CTRL_CC1_SHIFT) |

@@ -112,6 +128,16 @@ static int tcpci_set_cc(struct tcpc_dev
 		break;
 	}
 
+	if (vconn_pres) {
+		if (polarity == TYPEC_POLARITY_CC2) {
+			reg &= ~(TCPC_ROLE_CTRL_CC1_MASK << TCPC_ROLE_CTRL_CC1_SHIFT);
+			reg |= (TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC1_SHIFT);
+		} else {
+			reg &= ~(TCPC_ROLE_CTRL_CC2_MASK << TCPC_ROLE_CTRL_CC2_SHIFT);
+			reg |= (TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC2_SHIFT);
+		}
+	}
+
 	ret = regmap_write(tcpci->regmap, TCPC_ROLE_CTRL, reg);
 	if (ret < 0)
 		return ret;

@@ -98,6 +98,7 @@
 #define TCPC_POWER_STATUS_SOURCING_VBUS	BIT(4)
 #define TCPC_POWER_STATUS_VBUS_DET	BIT(3)
 #define TCPC_POWER_STATUS_VBUS_PRES	BIT(2)
+#define TCPC_POWER_STATUS_VCONN_PRES	BIT(1)
 #define TCPC_POWER_STATUS_SINKING_VBUS	BIT(0)
 
 #define TCPC_FAULT_STATUS		0x1f

From: Christian Borntraeger <[email protected]>

commit 1ea1d6a847d2b1d17fefd9196664b95f052a0775 upstream.

machine check validity bits reflect the state of the machine check. If a guest does not make use of guarded storage, the validity bit might be off. We can not use the host CR bit to decide if the validity bit must be on. So ignore "invalid" guarded storage controls for KVM guests in the host and rely on the machine check being forwarded to the guest. If no other errors happen from a host perspective everything is fine and no process must be killed and the host can continue to run.

---
 arch/s390/kernel/nmi.c |   18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

@@ -316,11 +316,21 @@ static int notrace s390_validate_registe
 	if (cr2.gse) {
 		if (!mci.gs) {
 			/*
-			 * Guarded storage register can't be restored and
-			 * the current processes uses guarded storage.
-			 * It has to be terminated.
+			 * 2 cases:
+			 * - machine check in kernel or userspace
+			 * - machine check while running SIE (KVM guest)
+			 * For kernel or userspace the userspace values of
+			 * guarded storage control can not be recreated, the
+			 * process must be terminated.
+			 * For SIE the guest values of guarded storage can not
+			 * be recreated. This is either due to a bug or due to
+			 * GS being disabled in the guest. The guest will be
+			 * notified by KVM code and the guests machine check
+			 * handling must take care of this.  The host values
+			 * are saved by KVM and are not affected.
 			 */
-			kill_task = 1;
+			if (!test_cpu_flag(CIF_MCCK_GUEST))
+				kill_task = 1;
 		} else {
 			load_gs_cb((struct gs_cb *)mcesa->guarded_storage_save_area);
 		}

From: Christian Borntraeger <[email protected]>

commit f094a39c6ba168f2df1edfd1731cca377af5f442 upstream.

The machine check validity bit tells about the context. If a KVM guest was running the bit tells about the guest validity and the host state is not affected. As a guest can disable the guest validity this might result in unwanted host errors on machine checks.

---
 arch/s390/kernel/nmi.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

@@ -273,7 +273,14 @@ static int notrace s390_validate_registe
 		/* Validate vector registers */
 		union ctlreg0 cr0;
 
-		if (!mci.vr) {
+		/*
+		 * The vector validity must only be checked if not running a
+		 * KVM guest. For KVM guests the machine check is forwarded by
+		 * KVM and it is the responsibility of the guest to take
+		 * appropriate actions. The host vector or FPU values have been
+		 * saved by KVM and will be restored by KVM.
+		 */
+		if (!mci.vr && !test_cpu_flag(CIF_MCCK_GUEST)) {
 			/*
 			 * Vector registers can't be restored. If the kernel
 			 * currently uses vector registers the system is

From: Naveen N. Rao <[email protected]>

commit b992f01e66150fc5e90be4a96f5eb8e634c8249e upstream.

task_pt_regs() can return NULL on powerpc for kernel threads. This is then used in __bpf_get_stack() to check for user mode, resulting in a kernel oops. Guard against this by checking return value of task_pt_regs() before trying to obtain the call chain.

---
 kernel/bpf/stackmap.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

@@ -525,13 +525,14 @@ BPF_CALL_4(bpf_get_task_stack, struct ta
 	   u32, size, u64, flags)
 {
 	struct pt_regs *regs;
-	long res;
+	long res = -EINVAL;
 
 	if (!try_get_task_stack(task))
 		return -EFAULT;
 
 	regs = task_pt_regs(task);
-	res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
+	if (regs)
+		res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
 	put_task_stack(task);
 
 	return res;

From: Jan Kara <[email protected]>

commit ea8569194b43f0f01f0a84c689388542c7254a1f upstream.

When we fail to expand inode from inline format to a normal format, we restore inode to contain the original inline formatting but we forgot to set i_lenAlloc back. The mismatch between i_lenAlloc and i_size was then causing further problems such as warnings and lost data down the line.

---
 fs/udf/inode.c |    1 +
 1 file changed, 1 insertion(+)

@@ -317,6 +317,7 @@ int udf_expand_file_adinicb(struct inode
 		unlock_page(page);
 		iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB;
 		inode->i_data.a_ops = &udf_adinicb_aops;
+		iinfo->i_lenAlloc = inode->i_size;
 		up_write(&iinfo->i_data_sem);
 	}
 	put_page(page);

From: Steffen Maier <[email protected]>

commit 8c9db6679be4348b8aae108e11d4be2f83976e30 upstream.

Suppose we have an environment with a number of non-NPIV FCP devices (virtual HBAs / FCP devices / zfcp "adapter"s) sharing the same physical FCP channel (HBA port) and its I_T nexus. Plus a number of storage target ports zoned to such shared channel. Now one target port logs out of the fabric causing an RSCN. Zfcp reacts with an ADISC ELS and subsequent port recovery depending on the ADISC result. This happens on all such FCP devices (in different Linux images) concurrently as they all receive a copy of this RSCN. In the following we look at one of those FCP devices.

Requests other than FSF_QTCB_FCP_CMND can be slow until they get a response.

Depending on which requests are affected by slow responses, there are different recovery outcomes. Here we want to fix failed recoveries on port or adapter level by avoiding recovery requests that can be slow.

We need the cached N_Port_ID for the remote port "link" test with ADISC. Just before sending the ADISC, we now intentionally forget the old cached N_Port_ID. The idea is that on receiving an RSCN for a port, we have to assume that any cached information about this port is stale. This forces a fresh new GID_PN [FC-GS] nameserver lookup on any subsequent recovery for the same port. Since we typically can still communicate with the nameserver efficiently, we now reach steady state quicker: Either the nameserver still does not know about the port so we stop recovery, or the nameserver already knows the port potentially with a new N_Port_ID and we can successfully and quickly perform open port recovery. For the one case, where ADISC returns successfully, we re-initialize port->d_id because that case does not involve any port recovery.

This also solves a problem if the storage WWPN quickly logs into the fabric again but with a different N_Port_ID. Such as on virtual WWPN takeover during target NPIV failover.
[https://www.redbooks.ibm.com/abstracts/redp5477.html] In that case the RSCN from the storage FDISC was ignored by zfcp and we could not successfully recover the failover. On some later failback on the storage, we could have been lucky if the virtual WWPN got the same old N_Port_ID from the SAN switch as we still had cached. Then the related RSCN triggered a successful port reopen recovery. However, there is no guarantee to get the same N_Port_ID on NPIV FDISC.

Even though NPIV-enabled FCP devices are not affected by this problem, this code change optimizes recovery time for gone remote ports as a side effect. The timely drop of cached N_Port_IDs prevents unnecessary slow open port attempts.

While the problem might have been in code before v2.6.32 commit 799b76d09aee ("[SCSI] zfcp: Decouple gid_pn requests from erp") this fix depends on the gid_pn_work introduced with that commit, so we mark it as culprit to satisfy fix dependencies.

Note: Point-to-point remote port is already handled separately and gets its N_Port_ID from the cached peer_d_id. So resetting port->d_id in general does not affect PtP.

---
 drivers/s390/scsi/zfcp_fc.c |   13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

@@ -521,6 +521,8 @@ static void zfcp_fc_adisc_handler(void *
 		goto out;
 	}
 
+	/* re-init to undo drop from zfcp_fc_adisc() */
+	port->d_id = ntoh24(adisc_resp->adisc_port_id);
 	/* port is good, unblock rport without going through erp */
 	zfcp_scsi_schedule_rport_register(port);
  out:

@@ -534,6 +536,7 @@ static int zfcp_fc_adisc(struct zfcp_por
 	struct zfcp_fc_req *fc_req;
 	struct zfcp_adapter *adapter = port->adapter;
 	struct Scsi_Host *shost = adapter->scsi_host;
+	u32 d_id;
 	int ret;
 
 	fc_req = kmem_cache_zalloc(zfcp_fc_req_cache, GFP_ATOMIC);

@@ -558,7 +561,15 @@ static int zfcp_fc_adisc(struct zfcp_por
 	fc_req->u.adisc.req.adisc_cmd = ELS_ADISC;
 	hton24(fc_req->u.adisc.req.adisc_port_id, fc_host_port_id(shost));
 
-	ret = zfcp_fsf_send_els(adapter, port->d_id, &fc_req->ct_els,
+	d_id = port->d_id; /* remember as destination for send els below */
+	/*
+	 * Force fresh GID_PN lookup on next port recovery.
+	 * Must happen after request setup and before sending request,
+	 * to prevent race with port->d_id re-init in zfcp_fc_adisc_handler().
+	 */
+	port->d_id = 0;
+
+	ret = zfcp_fsf_send_els(adapter, d_id, &fc_req->ct_els,
 				ZFCP_FC_CTELS_TMO);
 	if (ret)
 		kmem_cache_free(zfcp_fc_req_cache, fc_req);

From: Ard Biesheuvel <[email protected]>

commit f5390cd0b43c2e54c7cf5506c7da4a37c5cef746 upstream.

Aditya reports [0] that his recent MacbookPro crashes in the firmware when using the variable services at runtime. The culprit appears to be a call to QueryVariableInfo(), which we did not use to call on Apple x86 machines in the past as they only upgraded from EFI v1.10 to EFI v2.40 firmware fairly recently, and QueryVariableInfo() (along with UpdateCapsule() et al) was added in EFI v2.00.

The only runtime service introduced in EFI v2.00 that we actually use in Linux is QueryVariableInfo(), as the capsule based ones are optional, generally not used at runtime (all the LVFS/fwupd firmware update infrastructure uses helper EFI programs that invoke capsule update at boot time, not runtime), and not implemented by Apple machines in the first place. QueryVariableInfo() is used to 'safely' set variables, i.e., only when there is enough space. This prevents machines with buggy firmwares from corrupting their NVRAMs when they run out of space.

Given that Apple machines have been using EFI v1.10 services only for the longest time (the EFI v2.0 spec was released in 2006, and Linux support for the newly introduced runtime services was added in 2011, but the MacbookPro12,1 released in 2015 still claims to be EFI v1.10 only), let's avoid the EFI v2.0 ones on all Apple x86 machines.

[0] https://lore.kernel.org/all/[email protected]/

---
 drivers/firmware/efi/efi.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -719,6 +719,13 @@ void __init efi_systab_report_header(con
 		systab_hdr->revision >> 16,
 		systab_hdr->revision & 0xffff,
 		vendor);
+
+	if (IS_ENABLED(CONFIG_X86_64) &&
+	    systab_hdr->revision > EFI_1_10_SYSTEM_TABLE_REVISION &&
+	    !strcmp(vendor, "Apple")) {
+		pr_info("Apple Mac detected, using EFI v1.10 runtime services only\n");
+		efi.runtime_version = EFI_1_10_SYSTEM_TABLE_REVISION;
+	}
 }
 
 static __initdata char memory_type_name[][13] = {

From: Jan Kara <[email protected]>

commit 7fc3b7c2981bbd1047916ade327beccb90994eee upstream.

udf_expand_file_adinicb() calls directly ->writepage to write data expanded into a page. This however misses to setup inode for writeback properly and so we can crash on inode->i_wb dereference when submitting page for IO like:

  BUG: kernel NULL pointer dereference, address: 0000000000000158
  #PF: supervisor read access in kernel mode
...
  <TASK>
  __folio_start_writeback+0x2ac/0x350
  __block_write_full_page+0x37d/0x490
  udf_expand_file_adinicb+0x255/0x400 [udf]
  udf_file_write_iter+0xbe/0x1b0 [udf]
  new_sync_write+0x125/0x1c0
  vfs_write+0x28e/0x400

Fix the problem by marking the page dirty and going through the standard writeback path to write the page. Strictly speaking we would not even have to write the page but we want to catch e.g. ENOSPC errors early.

---
 fs/udf/inode.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

@@ -258,10 +258,6 @@ int udf_expand_file_adinicb(struct inode
 	char *kaddr;
 	struct udf_inode_info *iinfo = UDF_I(inode);
 	int err;
-	struct writeback_control udf_wbc = {
-		.sync_mode = WB_SYNC_NONE,
-		.nr_to_write = 1,
-	};
 
 	WARN_ON_ONCE(!inode_is_locked(inode));
 	if (!iinfo->i_lenAlloc) {

@@ -305,8 +301,10 @@ int udf_expand_file_adinicb(struct inode
 		iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG;
 	/* from now on we have normal address_space methods */
 	inode->i_data.a_ops = &udf_aops;
+	set_page_dirty(page);
+	unlock_page(page);
 	up_write(&iinfo->i_data_sem);
-	err = inode->i_data.a_ops->writepage(page, &udf_wbc);
+	err = filemap_fdatawrite(inode->i_mapping);
 	if (err) {
 		/* Restore everything back so that we don't lose data... */
 		lock_page(page);

From: Marek Behún <[email protected]>

commit 2148927e6ed43a1667baf7c2ae3e0e05a44b51a0 upstream.

Commit ce0aa27ff3f6 ("sfp: add sfp-bus to bridge between network devices and sfp cages") added code which finds SFP bus DT node even if the node is disabled with status = "disabled". Because of this, when phylink is created, it ends with non-null .sfp_bus member, even though the SFP module is not probed (because the node is disabled).

We need to ignore disabled SFP bus node.

---
 drivers/net/phy/sfp-bus.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -651,6 +651,11 @@ struct sfp_bus *sfp_bus_find_fwnode(stru
 	else if (ret < 0)
 		return ERR_PTR(ret);
 
+	if (!fwnode_device_is_available(ref.fwnode)) {
+		fwnode_handle_put(ref.fwnode);
+		return NULL;
+	}
+
 	bus = sfp_bus_get(ref.fwnode);
 	fwnode_handle_put(ref.fwnode);
 	if (!bus)

From: Xiaoke Wang <[email protected]>

commit e629e7b525a179e29d53463d992bdee759c950fb upstream.

kfree() is missing on an error path to free the memory allocated by kstrdup():

  p = param = kstrdup(data->params[i], GFP_KERNEL);

So it is better to free it via kfree(p).

---
 kernel/trace/trace_events_hist.c |    1 +
 1 file changed, 1 insertion(+)

@@ -3581,6 +3581,7 @@ static int trace_action_create(struct hi
 
 			var_ref_idx = find_var_ref_idx(hist_data, var_ref);
 			if (WARN_ON(var_ref_idx < 0)) {
+				kfree(p);
 				ret = var_ref_idx;
 				goto err;
 			}

From: Tony Luck <[email protected]>

commit e464121f2d40eabc7d11823fb26db807ce945df4 upstream.

Missed adding the Icelake-D CPU to the list. It uses the same MSRs to control and read the inventory number as all the other models.

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

@@ -486,6 +486,7 @@ static void intel_ppin_init(struct cpuin
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_ICELAKE_D:
 	case INTEL_FAM6_SAPPHIRERAPIDS_X:
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:

From: Jeff Layton <[email protected]>

commit 932a9b5870d38b87ba0a9923c804b1af7d3605b9 upstream.

The reference acquired by try_prep_async_create is currently leaked. Ensure we put it.

---
 fs/ceph/file.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -744,8 +744,10 @@ retry:
 				restore_deleg_ino(dir, req->r_deleg_ino);
 				ceph_mdsc_put_request(req);
 				try_async = false;
+				ceph_put_string(rcu_dereference_raw(lo.pool_ns));
 				goto retry;
 			}
+			ceph_put_string(rcu_dereference_raw(lo.pool_ns));
 			goto out_req;
 		}
 	}

From: Mohammad Athari Bin Ismail <[email protected]>

commit 94c82de43e01ef5747a95e4a590880de863fe423 upstream.

For Intel platform, it is required to configure PTP clock source prior PTP initialization in MAC. So, need to move ptp_clk_freq_config execution from stmmac_ptp_register() to stmmac_init_ptp().

---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |    3 +++
 drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c  |    3 ---
 2 files changed, 3 insertions(+), 3 deletions(-)

@@ -899,6 +899,9 @@ static int stmmac_init_ptp(struct stmmac
 	bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 	int ret;
 
+	if (priv->plat->ptp_clk_freq_config)
+		priv->plat->ptp_clk_freq_config(priv);
+
 	ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE);
 	if (ret)
 		return ret;

@@ -297,9 +297,6 @@ void stmmac_ptp_register(struct stmmac_p
 {
 	int i;
 
-	if (priv->plat->ptp_clk_freq_config)
-		priv->plat->ptp_clk_freq_config(priv);
-
 	for (i = 0; i < priv->dma_cap.pps_out_num; i++) {
 		if (i >= STMMAC_PPS_MAX)
 			break;

From: Mohammad Athari Bin Ismail <[email protected]>

commit 0735e639f129dff455aeb91da291f5c578cc33db upstream.

When resume from suspend, besides skipping PTP registration, it also skipping PTP HW initialization. This could cause PTP clock not able to operate properly when resume from suspend.

To fix this, only stmmac_ptp_register() is skipped when resume from suspend.

---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |   20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

@@ -924,8 +924,6 @@ static int stmmac_init_ptp(struct stmmac
 	priv->hwts_tx_en = 0;
 	priv->hwts_rx_en = 0;
 
-	stmmac_ptp_register(priv);
-
 	return 0;
 }
 

@@ -3240,7 +3238,7 @@ static int stmmac_fpe_start_wq(struct st
 /**
  * stmmac_hw_setup - setup mac in a usable state.
  *  @dev : pointer to the device structure.
- *  @init_ptp: initialize PTP if set
+ *  @ptp_register: register PTP if set
  *  Description:
  *  this is the main function to setup the HW in a usable state because the
  *  dma engine is reset, the core registers are configured (e.g. AXI,

@@ -3250,7 +3248,7 @@ static int stmmac_fpe_start_wq(struct st
  *  0 on success and an appropriate (-)ve integer as defined in errno.h
  *  file on failure.
  */
-static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
+static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	u32 rx_cnt = priv->plat->rx_queues_to_use;

@@ -3307,13 +3305,13 @@ static int stmmac_hw_setup(struct net_de
 
 	stmmac_mmc_setup(priv);
 
-	if (init_ptp) {
-		ret = stmmac_init_ptp(priv);
-		if (ret == -EOPNOTSUPP)
-			netdev_warn(priv->dev, "PTP not supported by HW\n");
-		else if (ret)
-			netdev_warn(priv->dev, "PTP init failed\n");
-	}
+	ret = stmmac_init_ptp(priv);
+	if (ret == -EOPNOTSUPP)
+		netdev_warn(priv->dev, "PTP not supported by HW\n");
+	else if (ret)
+		netdev_warn(priv->dev, "PTP init failed\n");
+	else if (ptp_register)
+		stmmac_ptp_register(priv);
 
 	priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS;
 

From: Ard Biesheuvel <[email protected]>

commit 15420269b02a63ed8c1841905d8b8b2403246004 upstream.

The helpers that are used to implement copy_from_kernel_nofault() and copy_to_kernel_nofault() cast a void* to a pointer to a wider type, which may result in alignment faults on ARM if the compiler decides to use double-word or multiple-word load/store instructions.

Only configurations that define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y are affected, given that commit 2423de2e6f4d ("ARM: 9115/1: mm/maccess:
fix unaligned copy_{from,to}_kernel_nofault") ensures that dst and src are sufficiently aligned otherwise.

So use the unaligned accessors for accessing dst and src in cases where they may be misaligned.

---
 arch/arm/include/asm/uaccess.h |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

@@ -11,6 +11,7 @@
 #include <linux/string.h>
 #include <asm/memory.h>
 #include <asm/domain.h>
+#include <asm/unaligned.h>
 #include <asm/unified.h>
 #include <asm/compiler.h>
 

@@ -497,7 +498,10 @@ do {									\
 	}								\
 	default: __err = __get_user_bad(); break;			\
 	}								\
-	*(type *)(dst) = __val;						\
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))		\
+		put_unaligned(__val, (type *)(dst));			\
+	else								\
+		*(type *)(dst) = __val; /* aligned by caller */		\
 	if (__err)							\
 		goto err_label;						\
 } while (0)

@@ -507,7 +511,9 @@ do {									\
 	const type *__pk_ptr = (dst);					\
 	unsigned long __dst = (unsigned long)__pk_ptr;			\
 	int __err = 0;							\
-	type __val = *(type *)src;					\
+	type __val = IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)	\
+		     ? get_unaligned((type *)(src))			\
+		     : *(type *)(src);	/* aligned by caller */		\
 	switch (sizeof(type)) {						\
 	case 1: __put_user_asm_byte(__val, __dst, __err, ""); break;	\
 	case 2:	__put_user_asm_half(__val, __dst, __err, ""); break;	\

From: Christophe Leroy <[email protected]>

commit bba496656a73fc1d1330b49c7f82843836e9feb1 upstream.

Boot fails with GCC latent entropy plugin enabled.

This is due to early boot functions trying to access 'latent_entropy' global data while the kernel is not relocated at its final destination yet.

As there is no way to tell GCC to use PTRRELOC() to access it, disable latent entropy plugin in early_32.o and feature-fixups.o and code-patching.o

---
 arch/powerpc/kernel/Makefile |    1 +
 arch/powerpc/lib/Makefile    |    3 +++
 2 files changed, 4 insertions(+)

@@ -11,6 +11,7 @@ CFLAGS_prom_init.o      += -fPIC
 CFLAGS_btext.o		+= -fPIC
 endif
 
+CFLAGS_early_32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_cputable.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_prom_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)

@@ -19,6 +19,9 @@ CFLAGS_code-patching.o += -DDISABLE_BRAN
 CFLAGS_feature-fixups.o += -DDISABLE_BRANCH_PROFILING
 endif
 
+CFLAGS_code-patching.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+CFLAGS_feature-fixups.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+
 obj-y += alloc.o code-patching.o feature-fixups.o pmem.o test_code-patching.o
 
 ifndef CONFIG_KASAN

From: Vasily Gorbik <[email protected]>

commit 663d34c8df98740f1e90241e78e456d00b3c6cad upstream.

Currently if z/VM guest is allowed to retrieve hypervisor performance data globally for all guests (privilege class B) the query is formed in a way to include all guests but the group name is left empty. This leads to that z/VM guests which have access control group set not being included in the results (even local vm).

Change the query group identifier from empty to "any" to retrieve information about all guests from any groups (or without a group set).

---
 arch/s390/hypfs/hypfs_vm.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -20,6 +20,7 @@
 
 static char local_guest[] = "        ";
 static char all_guests[] = "*       ";
+static char *all_groups = all_guests;
 static char *guest_query;
 
 struct diag2fc_data {

@@ -62,10 +63,11 @@ static int diag2fc(int size, char* query
 
 	memcpy(parm_list.userid, query, NAME_LEN);
 	ASCEBC(parm_list.userid, NAME_LEN);
-	parm_list.addr = (unsigned long) addr ;
+	memcpy(parm_list.aci_grp, all_groups, NAME_LEN);
+	ASCEBC(parm_list.aci_grp, NAME_LEN);
+	parm_list.addr = (unsigned long)addr;
 	parm_list.size = size;
 	parm_list.fmt = 0x02;
-	memset(parm_list.aci_grp, 0x40, NAME_LEN);
 	rc = -1;
 
 	diag_stat_inc(DIAG_STAT_X2FC);

From: Amir Goldstein <[email protected]>

commit 29044dae2e746949ad4b9cbdbfb248994d1dcdb4 upstream.

Commit 49246466a989 ("fsnotify: move fsnotify_nameremove() hook out of d_delete()") moved the fsnotify delete hook before d_delete() so fsnotify will have access to a positive dentry.

This allowed a race where opening the deleted file via cached dentry is now possible after receiving the IN_DELETE event.

To fix the regression in pseudo filesystems, convert d_delete() calls to d_drop() (see commit 46c46f8df9aa ("devpts_pty_kill(): don't bother with d_delete()") and move the fsnotify hook after d_drop().

Add a missing fsnotify_unlink() hook in nfsdfs that was found during the audit of fsnotify hooks in pseudo filesystems.

Note that the fsnotify hooks in simple_recursive_removal() follow d_invalidate(), so they require no change.

---
 fs/configfs/dir.c     |    6 +++---
 fs/devpts/inode.c     |    2 +-
 fs/nfsd/nfsctl.c      |    5 +++--
 net/sunrpc/rpc_pipe.c |    4 ++--
 4 files changed, 9 insertions(+), 8 deletions(-)

@@ -1780,8 +1780,8 @@ void configfs_unregister_group(struct co
 	configfs_detach_group(&group->cg_item);
 	d_inode(dentry)->i_flags |= S_DEAD;
 	dont_mount(dentry);
+	d_drop(dentry);
 	fsnotify_rmdir(d_inode(parent), dentry);
-	d_delete(dentry);
 	inode_unlock(d_inode(parent));
 
 	dput(dentry);

@@ -1922,10 +1922,10 @@ void configfs_unregister_subsystem(struc
 	configfs_detach_group(&group->cg_item);
 	d_inode(dentry)->i_flags |= S_DEAD;
 	dont_mount(dentry);
-	fsnotify_rmdir(d_inode(root), dentry);
 	inode_unlock(d_inode(dentry));
 
-	d_delete(dentry);
+	d_drop(dentry);
+	fsnotify_rmdir(d_inode(root), dentry);
 
 	inode_unlock(d_inode(root));
 

@@ -621,8 +621,8 @@ void devpts_pty_kill(struct dentry *dent
 
 	dentry->d_fsdata = NULL;
 	drop_nlink(dentry->d_inode);
-	fsnotify_unlink(d_inode(dentry->d_parent), dentry);
 	d_drop(dentry);
+	fsnotify_unlink(d_inode(dentry->d_parent), dentry);
 	dput(dentry);	/* d_alloc_name() in devpts_pty_new() */
 }
 

@@ -1249,7 +1249,8 @@ static void nfsdfs_remove_file(struct in
 	clear_ncl(d_inode(dentry));
 	dget(dentry);
 	ret = simple_unlink(dir, dentry);
-	d_delete(dentry);
+	d_drop(dentry);
+	fsnotify_unlink(dir, dentry);
 	dput(dentry);
 	WARN_ON_ONCE(ret);
 }

@@ -1340,8 +1341,8 @@ void nfsd_client_rmdir(struct dentry *de
 	dget(dentry);
 	ret = simple_rmdir(dir, dentry);
 	WARN_ON_ONCE(ret);
+	d_drop(dentry);
 	fsnotify_rmdir(dir, dentry);
-	d_delete(dentry);
 	dput(dentry);
 	inode_unlock(dir);
 }

@@ -600,9 +600,9 @@ static int __rpc_rmdir(struct inode *dir
 
 	dget(dentry);
 	ret = simple_rmdir(dir, dentry);
+	d_drop(dentry);
 	if (!ret)
 		fsnotify_rmdir(dir, dentry);
-	d_delete(dentry);
 	dput(dentry);
 	return ret;
 }

@@ -613,9 +613,9 @@ static int __rpc_unlink(struct inode *di
 
 	dget(dentry);
 	ret = simple_unlink(dir, dentry);
+	d_drop(dentry);
 	if (!ret)
 		fsnotify_unlink(dir, dentry);
-	d_delete(dentry);
 	dput(dentry);
 	return ret;
 }

From: Sean Christopherson <[email protected]>

commit f7e570780efc5cec9b2ed1e0472a7da14e864fdb upstream.

Forcibly leave nested virtualization operation if userspace toggles SMM state via KVM_SET_VCPU_EVENTS or KVM_SYNC_X86_EVENTS. If userspace forces the vCPU out of SMM while it's post-VMXON and then injects an SMI, vmx_enter_smm() will overwrite vmx->nested.smm.vmxon and end up with both vmxon=false and smm.vmxon=false, but all other nVMX state allocated.

Don't attempt to gracefully handle the transition as (a) most transitions are nonsencial, e.g. forcing SMM while L2 is running, (b) there isn't sufficient information to handle all transitions, e.g. SVM wants access to the SMRAM save state, and (c) KVM_SET_VCPU_EVENTS must precede KVM_SET_NESTED_STATE during state restore as the latter disallows putting the vCPU into L2 if SMM is active, and disallows tagging the vCPU as being post-VMXON in SMM if SMM is not active.

Abuse of KVM_SET_VCPU_EVENTS manifests as a WARN and memory leak in nVMX due to failure to free vmcs01's shadow VMCS, but the bug goes far beyond just a memory leak, e.g. toggling SMM on while L2 is active puts the vCPU in an architecturally impossible state.

  WARNING: CPU: 0 PID: 3606 at free_loaded_vmcs arch/x86/kvm/vmx/vmx.c:2665 [inline]
  WARNING: CPU: 0 PID: 3606 at free_loaded_vmcs+0x158/0x1a0 arch/x86/kvm/vmx/vmx.c:2656
  Modules linked in:
  CPU: 1 PID: 3606 Comm: syz-executor725 Not tainted 5.17.0-rc1-syzkaller #0
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
  RIP: 0010:free_loaded_vmcs arch/x86/kvm/vmx/vmx.c:2665 [inline]
  RIP: 0010:free_loaded_vmcs+0x158/0x1a0 arch/x86/kvm/vmx/vmx.c:2656
  Code: <0f> 0b eb b3 e8 8f 4d 9f 00 e9 f7 fe ff ff 48 89 df e8 92 4d 9f 00
  Call Trace:
   <TASK>
   kvm_arch_vcpu_destroy+0x72/0x2f0 arch/x86/kvm/x86.c:11123
   kvm_vcpu_destroy arch/x86/kvm/../../../virt/kvm/kvm_main.c:441 [inline]
   kvm_destroy_vcpus+0x11f/0x290 arch/x86/kvm/../../../virt/kvm/kvm_main.c:460
   kvm_free_vcpus arch/x86/kvm/x86.c:11564 [inline]
   kvm_arch_destroy_vm+0x2e8/0x470 arch/x86/kvm/x86.c:11676
   kvm_destroy_vm arch/x86/kvm/../../../virt/kvm/kvm_main.c:1217 [inline]
   kvm_put_kvm+0x4fa/0xb00 arch/x86/kvm/../../../virt/kvm/kvm_main.c:1250
   kvm_vm_release+0x3f/0x50 arch/x86/kvm/../../../virt/kvm/kvm_main.c:1273
   __fput+0x286/0x9f0 fs/file_table.c:311
   task_work_run+0xdd/0x1a0 kernel/task_work.c:164
   exit_task_work include/linux/task_work.h:32 [inline]
   do_exit+0xb29/0x2a30 kernel/exit.c:806
   do_group_exit+0xd2/0x2f0 kernel/exit.c:935
   get_signal+0x4b0/0x28c0 kernel/signal.c:2862
   arch_do_signal_or_restart+0x2a9/0x1c40 arch/x86/kernel/signal.c:868
   handle_signal_work kernel/entry/common.c:148 [inline]
   exit_to_user_mode_loop kernel/entry/common.c:172 [inline]
   exit_to_user_mode_prepare+0x17d/0x290 kernel/entry/common.c:207
   __syscall_exit_to_user_mode_work kernel/entry/common.c:289 [inline]
   syscall_exit_to_user_mode+0x19/0x60 kernel/entry/common.c:300
   do_syscall_64+0x42/0xb0 arch/x86/entry/common.c:86
   entry_SYSCALL_64_after_hwframe+0x44/0xae
   </TASK>

Message-Id: <[email protected]>

---
 arch/x86/include/asm/kvm_host.h |    1 +
 arch/x86/kvm/svm/nested.c       |    9 +++++----
 arch/x86/kvm/svm/svm.c          |    2 +-
 arch/x86/kvm/svm/svm.h          |    2 +-
 arch/x86/kvm/vmx/nested.c       |    1 +
 arch/x86/kvm/x86.c              |    4 +++-
 6 files changed, 12 insertions(+), 7 deletions(-)

@@ -1487,6 +1487,7 @@ struct kvm_x86_ops {
 };
 
 struct kvm_x86_nested_ops {
+	void (*leave_nested)(struct kvm_vcpu *vcpu);
 	int (*check_events)(struct kvm_vcpu *vcpu);
 	bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
 	void (*triple_fault)(struct kvm_vcpu *vcpu);

@@ -942,9 +942,9 @@ void svm_free_nested(struct vcpu_svm *sv
 /*
  * Forcibly leave nested mode in order to be able to reset the VCPU later on.
  */
-void svm_leave_nested(struct vcpu_svm *svm)
+void svm_leave_nested(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (is_guest_mode(vcpu)) {
 		svm->nested.nested_run_pending = 0;

@@ -1313,7 +1313,7 @@ static int svm_set_nested_state(struct k
 		return -EINVAL;
 
 	if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) {
-		svm_leave_nested(svm);
+		svm_leave_nested(vcpu);
 		svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
 		return 0;
 	}

@@ -1378,7 +1378,7 @@ static int svm_set_nested_state(struct k
 	 */
 
 	if (is_guest_mode(vcpu))
-		svm_leave_nested(svm);
+		svm_leave_nested(vcpu);
 	else
 		svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save;
 

@@ -1432,6 +1432,7 @@ static bool svm_get_nested_state_pages(s
 }
 
 struct kvm_x86_nested_ops svm_nested_ops = {
+	.leave_nested = svm_leave_nested,
 	.check_events = svm_check_nested_events,
 	.triple_fault = nested_svm_triple_fault,
 	.get_nested_state_pages = svm_get_nested_state_pages,

@@ -281,7 +281,7 @@ int svm_set_efer(struct kvm_vcpu *vcpu,
 
 	if ((old_efer & EFER_SVME) != (efer & EFER_SVME)) {
 		if (!(efer & EFER_SVME)) {
-			svm_leave_nested(svm);
+			svm_leave_nested(vcpu);
 			svm_set_gif(svm, true);
 			/* #GP intercept is still needed for vmware backdoor */
 			if (!enable_vmware_backdoor)

@@ -461,7 +461,7 @@ static inline bool nested_exit_on_nmi(st
 
 int enter_svm_guest_mode(struct kvm_vcpu *vcpu,
 			 u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun);
-void svm_leave_nested(struct vcpu_svm *svm);
+void svm_leave_nested(struct kvm_vcpu *vcpu);
 void svm_free_nested(struct vcpu_svm *svm);
 int svm_allocate_nested(struct vcpu_svm *svm);
 int nested_svm_vmrun(struct kvm_vcpu *vcpu);

@@ -6748,6 +6748,7 @@ __init int nested_vmx_hardware_setup(int
 }
 
 struct kvm_x86_nested_ops vmx_nested_ops = {
+	.leave_nested = vmx_leave_nested,
 	.check_events = vmx_check_nested_events,
 	.hv_timer_pending = nested_vmx_preemption_timer_pending,
 	.triple_fault = nested_vmx_triple_fault,

@@ -4727,8 +4727,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_e
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
-		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm)
+		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
+			kvm_x86_ops.nested_ops->leave_nested(vcpu);
 			kvm_smm_changed(vcpu, events->smi.smm);
+		}
 
 		vcpu->arch.smi_pending = events->smi.pending;
 

From: Denis Valeev <[email protected]>

commit 47c28d436f409f5b009dc82bd82d4971088aa391 upstream.

The bug occurs on #GP triggered by VMware backdoor when eax value is unaligned. eax alignment check should not be applied to non-SVM instructions because it leads to incorrect omission of the instructions emulation.
Apply the alignment check only to SVM instructions to fix.

Message-Id: <Yexlhaoe1Fscm59u@q>

---
 arch/x86/kvm/svm/svm.c |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

@@ -2238,10 +2238,6 @@ static int gp_interception(struct kvm_vc
 	if (error_code)
 		goto reinject;
 
-	/* All SVM instructions expect page aligned RAX */
-	if (svm->vmcb->save.rax & ~PAGE_MASK)
-		goto reinject;
-
 	/* Decode the instruction for usage later */
 	if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK)
 		goto reinject;

@@ -2259,8 +2255,13 @@ static int gp_interception(struct kvm_vc
 		if (!is_guest_mode(vcpu))
 			return kvm_emulate_instruction(vcpu,
 				EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE);
-	} else
+	} else {
+		/* All SVM instructions expect page aligned RAX */
+		if (svm->vmcb->save.rax & ~PAGE_MASK)
+			goto reinject;
+
 		return emulate_svm_instr(vcpu, opcode);
+	}
 
 reinject:
 	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);

From: Jedrzej Jagielski <[email protected]>

commit 9b13bd53134c9ddd544a790125199fdbdb505e67 upstream.

Recently simplified i40e_rebuild causes that FW sometimes is not ready after NVM update, the ping does not return.

Increase the delay in case of EMP reset.
Old delay of 300 ms was introduced for specific cards for 710 series. Now it works for all the cards and delay was increased.

---
 drivers/net/ethernet/intel/i40e/i40e_main.c |   12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

@@ -10574,15 +10574,9 @@ static void i40e_rebuild(struct i40e_pf
 	}
 	i40e_get_oem_version(&pf->hw);
 
-	if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) &&
-	    ((hw->aq.fw_maj_ver == 4 && hw->aq.fw_min_ver <= 33) ||
-	     hw->aq.fw_maj_ver < 4) && hw->mac.type == I40E_MAC_XL710) {
-		/* The following delay is necessary for 4.33 firmware and older
-		 * to recover after EMP reset. 200 ms should suffice but we
-		 * put here 300 ms to be sure that FW is ready to operate
-		 * after reset.
-		 */
-		mdelay(300);
+	if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state)) {
+		/* The following delay is necessary for firmware update. */
+		mdelay(1000);
 	}
 
 	/* re-verify the eeprom if we just had an EMP reset */

From: Lucas Stach <[email protected]>

commit e3d26528e083e612314d4dcd713f3d5a26143ddc upstream.

While all userspace tried to limit commandstreams to 64K in size, a bug in the Mesa driver lead to command streams of up to 128K being submitted. Allow those to avoid breaking existing userspace.

---
 drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -469,8 +469,8 @@ int etnaviv_ioctl_gem_submit(struct drm_
 		return -EINVAL;
 	}
 
-	if (args->stream_size > SZ_64K || args->nr_relocs > SZ_64K ||
-	    args->nr_bos > SZ_64K || args->nr_pmrs > 128) {
+	if (args->stream_size > SZ_128K || args->nr_relocs > SZ_128K ||
+	    args->nr_bos > SZ_128K || args->nr_pmrs > 128) {
 		DRM_ERROR("submit arguments out of size limits\n");
 		return -EINVAL;
 	}

From: Yazen Ghannam <[email protected]>

commit 1f52b0aba6fd37653416375cb8a1ca673acf8d5f upstream.

Changes to the AMD Thresholding sysfs code prevents sysfs writes from updating the underlying registers once CPU init is completed, i.e. "threshold_banks" is set.

Allow the registers to be updated if the thresholding interface is already initialized or if in the init path. Use the "set_lvt_off" value to indicate if running in the init path, since this value is only set during init.

---
 arch/x86/kernel/cpu/mce/amd.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -400,7 +400,7 @@ static void threshold_restart_bank(void
 	u32 hi, lo;
 
 	/* sysfs write might race against an offline operation */
-	if (this_cpu_read(threshold_banks))
+	if (!this_cpu_read(threshold_banks) && !tr->set_lvt_off)
 		return;
 
 	rdmsr(tr->b->address, lo, hi);

From: [email protected] <[email protected]>

commit 8838b2af23caf1ff0610caef2795d6668a013b2d upstream.

n_gsm is based on the 3GPP 07.010 and its newer version is the 3GPP 27.010.
See https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=1516
The changes from 07.010 to 27.010 are non-functional. Therefore, I refer to
the newer 27.010 here. Chapter 5.2.7.3 states that DC1 (XON) and DC3 (XOFF)
are the control characters defined in ISO/IEC 646. These shall be quoted if
seen in the data stream to avoid interpretation as flow control characters.

ISO/IEC 646 refers to the set of ISO standards described as the ISO 7-bit coded character set for information interchange. Its final version is also known as ITU T.50.
See https://www.itu.int/rec/T-REC-T.50-199209-I/en

To abide the standard it is needed to quote DC1 and DC3 correctly if these are seen as data bytes and not as control characters. The current implementation already tries to enforce this but fails to catch all defined cases. 3GPP 27.010 chapter 5.2.7.3 clearly states that the most significant bit shall be ignored for DC1 and DC3 handling. The current implementation handles only the case with the most significant bit set 0. Cases in which DC1 and DC3 have the most significant bit set 1 are left unhandled.

This patch fixes this by masking the data bytes with ISO_IEC_646_MASK (only the 7 least significant bits set 1) before comparing them with XON (a.k.a. DC1) and XOFF (a.k.a. DC3) when testing which byte values need quotation via byte stuffing.

---
 drivers/tty/n_gsm.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -318,6 +318,7 @@ static struct tty_driver *gsm_tty_driver
 #define GSM1_ESCAPE_BITS	0x20
 #define XON			0x11
 #define XOFF			0x13
+#define ISO_IEC_646_MASK	0x7F
 
 static const struct tty_port_operations gsm_port_ops;
 

@@ -527,7 +528,8 @@ static int gsm_stuff_frame(const u8 *inp
 	int olen = 0;
 	while (len--) {
 		if (*input == GSM1_SOF || *input == GSM1_ESCAPE
-		    || *input == XON || *input == XOFF) {
+		    || (*input & ISO_IEC_646_MASK) == XON
+		    || (*input & ISO_IEC_646_MASK) == XOFF) {
 			*output++ = GSM1_ESCAPE;
 			*output++ = *input++ ^ GSM1_ESCAPE_BITS;
 			olen++;