[PATCH AUTOSEL 5.15 17/37] powerpc/fadump: Fix fadump to work with a different endian capture kernel

[PATCH AUTOSEL 5.15 17/37] powerpc/fadump: Fix fadump to work with a different endian capture kernel

[Sasha Levin]

From: Hari Bathini <hbathini@linux.ibm.com>

[ Upstream commit b74196af372f7cb4902179009265fe63ac81824f ]

Dump capture would fail if capture kernel is not of the endianess as the
production kernel, because the in-memory data structure (struct
opal_fadump_mem_struct) shared across production kernel and capture
kernel assumes the same endianess for both the kernels, which doesn't
have to be true always. Fix it by having a well-defined endianess for
struct opal_fadump_mem_struct.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/161902744901.86147.14719228311655123526.stgit@hbathini
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/powernv/opal-fadump.c | 94 +++++++++++---------
 arch/powerpc/platforms/powernv/opal-fadump.h | 10 +--
 2 files changed, 57 insertions(+), 47 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 9a360ced663b..e23a51a05f99 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -60,7 +60,7 @@ void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
 	addr = be64_to_cpu(addr);
 	pr_debug("Kernel metadata addr: %llx\n", addr);
 	opal_fdm_active = (void *)addr;
-	if (opal_fdm_active->registered_regions == 0)
+	if (be16_to_cpu(opal_fdm_active->registered_regions) == 0)
 		return;
 
 	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_BOOT_MEM, &addr);
@@ -95,17 +95,17 @@ static int opal_fadump_unregister(struct fw_dump *fadump_conf);
 static void opal_fadump_update_config(struct fw_dump *fadump_conf,
 				      const struct opal_fadump_mem_struct *fdm)
 {
-	pr_debug("Boot memory regions count: %d\n", fdm->region_cnt);
+	pr_debug("Boot memory regions count: %d\n", be16_to_cpu(fdm->region_cnt));
 
 	/*
 	 * The destination address of the first boot memory region is the
 	 * destination address of boot memory regions.
 	 */
-	fadump_conf->boot_mem_dest_addr = fdm->rgn[0].dest;
+	fadump_conf->boot_mem_dest_addr = be64_to_cpu(fdm->rgn[0].dest);
 	pr_debug("Destination address of boot memory regions: %#016llx\n",
 		 fadump_conf->boot_mem_dest_addr);
 
-	fadump_conf->fadumphdr_addr = fdm->fadumphdr_addr;
+	fadump_conf->fadumphdr_addr = be64_to_cpu(fdm->fadumphdr_addr);
 }
 
 /*
@@ -126,9 +126,9 @@ static void opal_fadump_get_config(struct fw_dump *fadump_conf,
 	fadump_conf->boot_memory_size = 0;
 
 	pr_debug("Boot memory regions:\n");
-	for (i = 0; i < fdm->region_cnt; i++) {
-		base = fdm->rgn[i].src;
-		size = fdm->rgn[i].size;
+	for (i = 0; i < be16_to_cpu(fdm->region_cnt); i++) {
+		base = be64_to_cpu(fdm->rgn[i].src);
+		size = be64_to_cpu(fdm->rgn[i].size);
 		pr_debug("\t[%03d] base: 0x%lx, size: 0x%lx\n", i, base, size);
 
 		fadump_conf->boot_mem_addr[i] = base;
@@ -143,7 +143,7 @@ static void opal_fadump_get_config(struct fw_dump *fadump_conf,
 	 * Start address of reserve dump area (permanent reservation) for
 	 * re-registering FADump after dump capture.
 	 */
-	fadump_conf->reserve_dump_area_start = fdm->rgn[0].dest;
+	fadump_conf->reserve_dump_area_start = be64_to_cpu(fdm->rgn[0].dest);
 
 	/*
 	 * Rarely, but it can so happen that system crashes before all
@@ -155,13 +155,14 @@ static void opal_fadump_get_config(struct fw_dump *fadump_conf,
 	 * Hope the memory that could not be preserved only has pages
 	 * that are usually filtered out while saving the vmcore.
 	 */
-	if (fdm->region_cnt > fdm->registered_regions) {
+	if (be16_to_cpu(fdm->region_cnt) > be16_to_cpu(fdm->registered_regions)) {
 		pr_warn("Not all memory regions were saved!!!\n");
 		pr_warn("  Unsaved memory regions:\n");
-		i = fdm->registered_regions;
-		while (i < fdm->region_cnt) {
+		i = be16_to_cpu(fdm->registered_regions);
+		while (i < be16_to_cpu(fdm->region_cnt)) {
 			pr_warn("\t[%03d] base: 0x%llx, size: 0x%llx\n",
-				i, fdm->rgn[i].src, fdm->rgn[i].size);
+				i, be64_to_cpu(fdm->rgn[i].src),
+				be64_to_cpu(fdm->rgn[i].size));
 			i++;
 		}
 
@@ -170,7 +171,7 @@ static void opal_fadump_get_config(struct fw_dump *fadump_conf,
 	}
 
 	fadump_conf->boot_mem_top = (fadump_conf->boot_memory_size + hole_size);
-	fadump_conf->boot_mem_regs_cnt = fdm->region_cnt;
+	fadump_conf->boot_mem_regs_cnt = be16_to_cpu(fdm->region_cnt);
 	opal_fadump_update_config(fadump_conf, fdm);
 }
 
@@ -178,35 +179,38 @@ static void opal_fadump_get_config(struct fw_dump *fadump_conf,
 static void opal_fadump_init_metadata(struct opal_fadump_mem_struct *fdm)
 {
 	fdm->version = OPAL_FADUMP_VERSION;
-	fdm->region_cnt = 0;
-	fdm->registered_regions = 0;
-	fdm->fadumphdr_addr = 0;
+	fdm->region_cnt = cpu_to_be16(0);
+	fdm->registered_regions = cpu_to_be16(0);
+	fdm->fadumphdr_addr = cpu_to_be64(0);
 }
 
 static u64 opal_fadump_init_mem_struct(struct fw_dump *fadump_conf)
 {
 	u64 addr = fadump_conf->reserve_dump_area_start;
+	u16 reg_cnt;
 	int i;
 
 	opal_fdm = __va(fadump_conf->kernel_metadata);
 	opal_fadump_init_metadata(opal_fdm);
 
 	/* Boot memory regions */
+	reg_cnt = be16_to_cpu(opal_fdm->region_cnt);
 	for (i = 0; i < fadump_conf->boot_mem_regs_cnt; i++) {
-		opal_fdm->rgn[i].src	= fadump_conf->boot_mem_addr[i];
-		opal_fdm->rgn[i].dest	= addr;
-		opal_fdm->rgn[i].size	= fadump_conf->boot_mem_sz[i];
+		opal_fdm->rgn[i].src	= cpu_to_be64(fadump_conf->boot_mem_addr[i]);
+		opal_fdm->rgn[i].dest	= cpu_to_be64(addr);
+		opal_fdm->rgn[i].size	= cpu_to_be64(fadump_conf->boot_mem_sz[i]);
 
-		opal_fdm->region_cnt++;
+		reg_cnt++;
 		addr += fadump_conf->boot_mem_sz[i];
 	}
+	opal_fdm->region_cnt = cpu_to_be16(reg_cnt);
 
 	/*
 	 * Kernel metadata is passed to f/w and retrieved in capture kerenl.
 	 * So, use it to save fadump header address instead of calculating it.
 	 */
-	opal_fdm->fadumphdr_addr = (opal_fdm->rgn[0].dest +
-				    fadump_conf->boot_memory_size);
+	opal_fdm->fadumphdr_addr = cpu_to_be64(be64_to_cpu(opal_fdm->rgn[0].dest) +
+					       fadump_conf->boot_memory_size);
 
 	opal_fadump_update_config(fadump_conf, opal_fdm);
 
@@ -269,18 +273,21 @@ static u64 opal_fadump_get_bootmem_min(void)
 static int opal_fadump_register(struct fw_dump *fadump_conf)
 {
 	s64 rc = OPAL_PARAMETER;
+	u16 registered_regs;
 	int i, err = -EIO;
 
-	for (i = 0; i < opal_fdm->region_cnt; i++) {
+	registered_regs = be16_to_cpu(opal_fdm->registered_regions);
+	for (i = 0; i < be16_to_cpu(opal_fdm->region_cnt); i++) {
 		rc = opal_mpipl_update(OPAL_MPIPL_ADD_RANGE,
-				       opal_fdm->rgn[i].src,
-				       opal_fdm->rgn[i].dest,
-				       opal_fdm->rgn[i].size);
+				       be64_to_cpu(opal_fdm->rgn[i].src),
+				       be64_to_cpu(opal_fdm->rgn[i].dest),
+				       be64_to_cpu(opal_fdm->rgn[i].size));
 		if (rc != OPAL_SUCCESS)
 			break;
 
-		opal_fdm->registered_regions++;
+		registered_regs++;
 	}
+	opal_fdm->registered_regions = cpu_to_be16(registered_regs);
 
 	switch (rc) {
 	case OPAL_SUCCESS:
@@ -291,7 +298,8 @@ static int opal_fadump_register(struct fw_dump *fadump_conf)
 	case OPAL_RESOURCE:
 		/* If MAX regions limit in f/w is hit, warn and proceed. */
 		pr_warn("%d regions could not be registered for MPIPL as MAX limit is reached!\n",
-			(opal_fdm->region_cnt - opal_fdm->registered_regions));
+			(be16_to_cpu(opal_fdm->region_cnt) -
+			 be16_to_cpu(opal_fdm->registered_regions)));
 		fadump_conf->dump_registered = 1;
 		err = 0;
 		break;
@@ -312,7 +320,7 @@ static int opal_fadump_register(struct fw_dump *fadump_conf)
 	 * If some regions were registered before OPAL_MPIPL_ADD_RANGE
 	 * OPAL call failed, unregister all regions.
 	 */
-	if ((err < 0) && (opal_fdm->registered_regions > 0))
+	if ((err < 0) && (be16_to_cpu(opal_fdm->registered_regions) > 0))
 		opal_fadump_unregister(fadump_conf);
 
 	return err;
@@ -328,7 +336,7 @@ static int opal_fadump_unregister(struct fw_dump *fadump_conf)
 		return -EIO;
 	}
 
-	opal_fdm->registered_regions = 0;
+	opal_fdm->registered_regions = cpu_to_be16(0);
 	fadump_conf->dump_registered = 0;
 	return 0;
 }
@@ -563,19 +571,20 @@ static void opal_fadump_region_show(struct fw_dump *fadump_conf,
 	else
 		fdm_ptr = opal_fdm;
 
-	for (i = 0; i < fdm_ptr->region_cnt; i++) {
+	for (i = 0; i < be16_to_cpu(fdm_ptr->region_cnt); i++) {
 		/*
 		 * Only regions that are registered for MPIPL
 		 * would have dump data.
 		 */
 		if ((fadump_conf->dump_active) &&
-		    (i < fdm_ptr->registered_regions))
-			dumped_bytes = fdm_ptr->rgn[i].size;
+		    (i < be16_to_cpu(fdm_ptr->registered_regions)))
+			dumped_bytes = be64_to_cpu(fdm_ptr->rgn[i].size);
 
 		seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ",
-			   fdm_ptr->rgn[i].src, fdm_ptr->rgn[i].dest);
+			   be64_to_cpu(fdm_ptr->rgn[i].src),
+			   be64_to_cpu(fdm_ptr->rgn[i].dest));
 		seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n",
-			   fdm_ptr->rgn[i].size, dumped_bytes);
+			   be64_to_cpu(fdm_ptr->rgn[i].size), dumped_bytes);
 	}
 
 	/* Dump is active. Show reserved area start address. */
@@ -624,6 +633,7 @@ void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
 {
 	const __be32 *prop;
 	unsigned long dn;
+	__be64 be_addr;
 	u64 addr = 0;
 	int i, len;
 	s64 ret;
@@ -680,13 +690,13 @@ void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
 	if (!prop)
 		return;
 
-	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_KERNEL, &addr);
-	if ((ret != OPAL_SUCCESS) || !addr) {
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_KERNEL, &be_addr);
+	if ((ret != OPAL_SUCCESS) || !be_addr) {
 		pr_err("Failed to get Kernel metadata (%lld)\n", ret);
 		return;
 	}
 
-	addr = be64_to_cpu(addr);
+	addr = be64_to_cpu(be_addr);
 	pr_debug("Kernel metadata addr: %llx\n", addr);
 
 	opal_fdm_active = __va(addr);
@@ -697,14 +707,14 @@ void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
 	}
 
 	/* Kernel regions not registered with f/w for MPIPL */
-	if (opal_fdm_active->registered_regions == 0) {
+	if (be16_to_cpu(opal_fdm_active->registered_regions) == 0) {
 		opal_fdm_active = NULL;
 		return;
 	}
 
-	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_CPU, &addr);
-	if (addr) {
-		addr = be64_to_cpu(addr);
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_CPU, &be_addr);
+	if (be_addr) {
+		addr = be64_to_cpu(be_addr);
 		pr_debug("CPU metadata addr: %llx\n", addr);
 		opal_cpu_metadata = __va(addr);
 	}
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h
index f1e9ecf548c5..3f715efb0aa6 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.h
+++ b/arch/powerpc/platforms/powernv/opal-fadump.h
@@ -31,14 +31,14 @@
  * OPAL FADump kernel metadata
  *
  * The address of this structure will be registered with f/w for retrieving
- * and processing during crash dump.
+ * in the capture kernel to process the crash dump.
  */
 struct opal_fadump_mem_struct {
 	u8	version;
 	u8	reserved[3];
-	u16	region_cnt;		/* number of regions */
-	u16	registered_regions;	/* Regions registered for MPIPL */
-	u64	fadumphdr_addr;
+	__be16	region_cnt;		/* number of regions */
+	__be16	registered_regions;	/* Regions registered for MPIPL */
+	__be64	fadumphdr_addr;
 	struct opal_mpipl_region	rgn[FADUMP_MAX_MEM_REGS];
 } __packed;
 
@@ -135,7 +135,7 @@ static inline void opal_fadump_read_regs(char *bufp, unsigned int regs_cnt,
 	for (i = 0; i < regs_cnt; i++, bufp += reg_entry_size) {
 		reg_entry = (struct hdat_fadump_reg_entry *)bufp;
 		val = (cpu_endian ? be64_to_cpu(reg_entry->reg_val) :
-		       reg_entry->reg_val);
+		       (u64)(reg_entry->reg_val));
 		opal_fadump_set_regval_regnum(regs,
 					      be32_to_cpu(reg_entry->reg_type),
 					      be32_to_cpu(reg_entry->reg_num),
-- 
2.35.1

[PATCH AUTOSEL 5.15 24/37] powerpc/rtas: Keep MSR[RI] set when calling RTAS

[Sasha Levin]

From: Laurent Dufour <ldufour@linux.ibm.com>

[ Upstream commit b6b1c3ce06ca438eb24e0f45bf0e63ecad0369f5 ]

RTAS runs in real mode (MSR[DR] and MSR[IR] unset) and in 32-bit big
endian mode (MSR[SF,LE] unset).

The change in MSR is done in enter_rtas() in a relatively complex way,
since the MSR value could be hardcoded.

Furthermore, a panic has been reported when hitting the watchdog interrupt
while running in RTAS, this leads to the following stack trace:

  watchdog: CPU 24 Hard LOCKUP
  watchdog: CPU 24 TB:997512652051031, last heartbeat TB:997504470175378 (15980ms ago)
  ...
  Supported: No, Unreleased kernel
  CPU: 24 PID: 87504 Comm: drmgr Kdump: loaded Tainted: G            E  X    5.14.21-150400.71.1.bz196362_2-default #1 SLE15-SP4 (unreleased) 0d821077ef4faa8dfaf370efb5fdca1fa35f4e2c
  NIP:  000000001fb41050 LR: 000000001fb4104c CTR: 0000000000000000
  REGS: c00000000fc33d60 TRAP: 0100   Tainted: G            E  X     (5.14.21-150400.71.1.bz196362_2-default)
  MSR:  8000000002981000 <SF,VEC,VSX,ME>  CR: 48800002  XER: 20040020
  CFAR: 000000000000011c IRQMASK: 1
  GPR00: 0000000000000003 ffffffffffffffff 0000000000000001 00000000000050dc
  GPR04: 000000001ffb6100 0000000000000020 0000000000000001 000000001fb09010
  GPR08: 0000000020000000 0000000000000000 0000000000000000 0000000000000000
  GPR12: 80040000072a40a8 c00000000ff8b680 0000000000000007 0000000000000034
  GPR16: 000000001fbf6e94 000000001fbf6d84 000000001fbd1db0 000000001fb3f008
  GPR20: 000000001fb41018 ffffffffffffffff 000000000000017f fffffffffffff68f
  GPR24: 000000001fb18fe8 000000001fb3e000 000000001fb1adc0 000000001fb1cf40
  GPR28: 000000001fb26000 000000001fb460f0 000000001fb17f18 000000001fb17000
  NIP [000000001fb41050] 0x1fb41050
  LR [000000001fb4104c] 0x1fb4104c
  Call Trace:
  Instruction dump:
  XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX
  XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX
  Oops: Unrecoverable System Reset, sig: 6 [#1]
  LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
  ...
  Supported: No, Unreleased kernel
  CPU: 24 PID: 87504 Comm: drmgr Kdump: loaded Tainted: G            E  X    5.14.21-150400.71.1.bz196362_2-default #1 SLE15-SP4 (unreleased) 0d821077ef4faa8dfaf370efb5fdca1fa35f4e2c
  NIP:  000000001fb41050 LR: 000000001fb4104c CTR: 0000000000000000
  REGS: c00000000fc33d60 TRAP: 0100   Tainted: G            E  X     (5.14.21-150400.71.1.bz196362_2-default)
  MSR:  8000000002981000 <SF,VEC,VSX,ME>  CR: 48800002  XER: 20040020
  CFAR: 000000000000011c IRQMASK: 1
  GPR00: 0000000000000003 ffffffffffffffff 0000000000000001 00000000000050dc
  GPR04: 000000001ffb6100 0000000000000020 0000000000000001 000000001fb09010
  GPR08: 0000000020000000 0000000000000000 0000000000000000 0000000000000000
  GPR12: 80040000072a40a8 c00000000ff8b680 0000000000000007 0000000000000034
  GPR16: 000000001fbf6e94 000000001fbf6d84 000000001fbd1db0 000000001fb3f008
  GPR20: 000000001fb41018 ffffffffffffffff 000000000000017f fffffffffffff68f
  GPR24: 000000001fb18fe8 000000001fb3e000 000000001fb1adc0 000000001fb1cf40
  GPR28: 000000001fb26000 000000001fb460f0 000000001fb17f18 000000001fb17000
  NIP [000000001fb41050] 0x1fb41050
  LR [000000001fb4104c] 0x1fb4104c
  Call Trace:
  Instruction dump:
  XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX
  XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX
  ---[ end trace 3ddec07f638c34a2 ]---

This happens because MSR[RI] is unset when entering RTAS but there is no
valid reason to not set it here.

RTAS is expected to be called with MSR[RI] as specified in PAPR+ section
"7.2.1 Machine State":

  R1–7.2.1–9. If called with MSR[RI] equal to 1, then RTAS must protect
  its own critical regions from recursion by setting the MSR[RI] bit to
  0 when in the critical regions.

Fixing this by reviewing the way MSR is compute before calling RTAS. Now a
hardcoded value meaning real mode, 32 bits big endian mode and Recoverable
Interrupt is loaded. In the case MSR[S] is set, it will remain set while
entering RTAS as only urfid can unset it (thanks Fabiano).

In addition a check is added in do_enter_rtas() to detect calls made with
MSR[RI] unset, as we are forcing it on later.

This patch has been tested on the following machines:
Power KVM Guest
  P8 S822L (host Ubuntu kernel 5.11.0-49-generic)
PowerVM LPAR
  P8 9119-MME (FW860.A1)
  p9 9008-22L (FW950.00)
  P10 9080-HEX (FW1010.00)

Suggested-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220504101244.12107-1-ldufour@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/entry_64.S | 24 ++++++++++++------------
 arch/powerpc/kernel/rtas.c     |  9 +++++++++
 2 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 70cff7b49e17..07a1448146e2 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -330,22 +330,22 @@ _GLOBAL(enter_rtas)
 	clrldi	r4,r4,2			/* convert to realmode address */
        	mtlr	r4
 
-	li	r0,0
-	ori	r0,r0,MSR_EE|MSR_SE|MSR_BE|MSR_RI
-	andc	r0,r6,r0
-	
-        li      r9,1
-        rldicr  r9,r9,MSR_SF_LG,(63-MSR_SF_LG)
-	ori	r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI|MSR_LE
-	andc	r6,r0,r9
-
 __enter_rtas:
-	sync				/* disable interrupts so SRR0/1 */
-	mtmsrd	r0			/* don't get trashed */
-
 	LOAD_REG_ADDR(r4, rtas)
 	ld	r5,RTASENTRY(r4)	/* get the rtas->entry value */
 	ld	r4,RTASBASE(r4)		/* get the rtas->base value */
+
+	/*
+	 * RTAS runs in 32-bit big endian real mode, but leave MSR[RI] on as we
+	 * may hit NMI (SRESET or MCE) while in RTAS. RTAS should disable RI in
+	 * its critical regions (as specified in PAPR+ section 7.2.1). MSR[S]
+	 * is not impacted by RFI_TO_KERNEL (only urfid can unset it). So if
+	 * MSR[S] is set, it will remain when entering RTAS.
+	 */
+	LOAD_REG_IMMEDIATE(r6, MSR_ME | MSR_RI)
+
+	li      r0,0
+	mtmsrd  r0,1                    /* disable RI before using SRR0/1 */
 	
 	mtspr	SPRN_SRR0,r5
 	mtspr	SPRN_SRR1,r6
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index e18a725a8e5d..3f5814037035 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -49,6 +49,15 @@ void enter_rtas(unsigned long);
 
 static inline void do_enter_rtas(unsigned long args)
 {
+	unsigned long msr;
+
+	/*
+	 * Make sure MSR[RI] is currently enabled as it will be forced later
+	 * in enter_rtas.
+	 */
+	msr = mfmsr();
+	BUG_ON(!(msr & MSR_RI));
+
 	enter_rtas(args);
 
 	srr_regs_clobbered(); /* rtas uses SRRs, invalidate */
-- 
2.35.1

[PATCH AUTOSEL 5.15 26/37] KVM: PPC: Book3S HV Nested: L2 LPCR should inherit L1 LPES setting

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit 2852ebfa10afdcefff35ec72c8da97141df9845c ]

The L1 should not be able to adjust LPES mode for the L2. Setting LPES
if the L0 needs it clear would cause external interrupts to be sent to
L2 and missed by the L0.

Clearing LPES when it may be set, as typically happens with XIVE enabled
could cause a performance issue despite having no native XIVE support in
the guest, because it will cause mediated interrupts for the L2 to be
taken in HV mode, which then have to be injected.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220303053315.1056880-7-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv.c        | 4 ++++
 arch/powerpc/kvm/book3s_hv_nested.c | 3 +--
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7fa685711669..eba77096c443 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -5235,6 +5235,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
 		lpcr &= LPCR_PECE | LPCR_LPES;
 	} else {
+		/*
+		 * The L2 LPES mode will be set by the L0 according to whether
+		 * or not it needs to take external interrupts in HV mode.
+		 */
 		lpcr = 0;
 	}
 	lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 6c4e0e93105f..ddea14e5cb5e 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -261,8 +261,7 @@ static void load_l2_hv_regs(struct kvm_vcpu *vcpu,
 	/*
 	 * Don't let L1 change LPCR bits for the L2 except these:
 	 */
-	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
-		LPCR_LPES | LPCR_MER;
+	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD | LPCR_MER;
 
 	/*
 	 * Additional filtering is required depending on hardware
-- 
2.35.1

[PATCH AUTOSEL 5.15 29/37] powerpc/powernv/vas: Assign real address to rx_fifo in vas_rx_win_attr

[Sasha Levin]

From: Haren Myneni <haren@linux.ibm.com>

[ Upstream commit c127d130f6d59fa81701f6b04023cf7cd1972fb3 ]

In init_winctx_regs(), __pa() is called on winctx->rx_fifo and this
function is called to initialize registers for receive and fault
windows. But the real address is passed in winctx->rx_fifo for
receive windows and the virtual address for fault windows which
causes errors with DEBUG_VIRTUAL enabled. Fixes this issue by
assigning only real address to rx_fifo in vas_rx_win_attr struct
for both receive and fault windows.

Reported-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/338e958c7ab8f3b266fa794a1f80f99b9671829e.camel@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/vas.h              | 2 +-
 arch/powerpc/platforms/powernv/vas-fault.c  | 2 +-
 arch/powerpc/platforms/powernv/vas-window.c | 4 ++--
 arch/powerpc/platforms/powernv/vas.h        | 2 +-
 drivers/crypto/nx/nx-common-powernv.c       | 2 +-
 5 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h
index 57573d9c1e09..56834a8a1465 100644
--- a/arch/powerpc/include/asm/vas.h
+++ b/arch/powerpc/include/asm/vas.h
@@ -112,7 +112,7 @@ static inline void vas_user_win_add_mm_context(struct vas_user_win_ref *ref)
  * Receive window attributes specified by the (in-kernel) owner of window.
  */
 struct vas_rx_win_attr {
-	void *rx_fifo;
+	u64 rx_fifo;
 	int rx_fifo_size;
 	int wcreds_max;
 
diff --git a/arch/powerpc/platforms/powernv/vas-fault.c b/arch/powerpc/platforms/powernv/vas-fault.c
index a7aabc18039e..c1bfad56447d 100644
--- a/arch/powerpc/platforms/powernv/vas-fault.c
+++ b/arch/powerpc/platforms/powernv/vas-fault.c
@@ -216,7 +216,7 @@ int vas_setup_fault_window(struct vas_instance *vinst)
 	vas_init_rx_win_attr(&attr, VAS_COP_TYPE_FAULT);
 
 	attr.rx_fifo_size = vinst->fault_fifo_size;
-	attr.rx_fifo = vinst->fault_fifo;
+	attr.rx_fifo = __pa(vinst->fault_fifo);
 
 	/*
 	 * Max creds is based on number of CRBs can fit in the FIFO.
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 0f8d39fbf2b2..0072682531d8 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -404,7 +404,7 @@ static void init_winctx_regs(struct pnv_vas_window *window,
 	 *
 	 * See also: Design note in function header.
 	 */
-	val = __pa(winctx->rx_fifo);
+	val = winctx->rx_fifo;
 	val = SET_FIELD(VAS_PAGE_MIGRATION_SELECT, val, 0);
 	write_hvwc_reg(window, VREG(LFIFO_BAR), val);
 
@@ -739,7 +739,7 @@ static void init_winctx_for_rxwin(struct pnv_vas_window *rxwin,
 		 */
 		winctx->fifo_disable = true;
 		winctx->intr_disable = true;
-		winctx->rx_fifo = NULL;
+		winctx->rx_fifo = 0;
 	}
 
 	winctx->lnotify_lpid = rxattr->lnotify_lpid;
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
index 8bb08e395de0..08d9d3d5a22b 100644
--- a/arch/powerpc/platforms/powernv/vas.h
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -376,7 +376,7 @@ struct pnv_vas_window {
  * is a container for the register fields in the window context.
  */
 struct vas_winctx {
-	void *rx_fifo;
+	u64 rx_fifo;
 	int rx_fifo_size;
 	int wcreds_max;
 	int rsvd_txbuf_count;
diff --git a/drivers/crypto/nx/nx-common-powernv.c b/drivers/crypto/nx/nx-common-powernv.c
index 32a036ada5d0..f418817c0f43 100644
--- a/drivers/crypto/nx/nx-common-powernv.c
+++ b/drivers/crypto/nx/nx-common-powernv.c
@@ -827,7 +827,7 @@ static int __init vas_cfg_coproc_info(struct device_node *dn, int chip_id,
 		goto err_out;
 
 	vas_init_rx_win_attr(&rxattr, coproc->ct);
-	rxattr.rx_fifo = (void *)rx_fifo;
+	rxattr.rx_fifo = rx_fifo;
 	rxattr.rx_fifo_size = fifo_size;
 	rxattr.lnotify_lpid = lpid;
 	rxattr.lnotify_pid = pid;
-- 
2.35.1

[PATCH AUTOSEL 5.15 30/37] powerpc/xics: fix refcount leak in icp_opal_init()

[Sasha Levin]

From: Lv Ruyi <lv.ruyi@zte.com.cn>

[ Upstream commit 5dd9e27ea4a39f7edd4bf81e9e70208e7ac0b7c9 ]

The of_find_compatible_node() function returns a node pointer with
refcount incremented, use of_node_put() on it when done.

Reported-by: Zeal Robot <zealci@zte.com.cn>
Signed-off-by: Lv Ruyi <lv.ruyi@zte.com.cn>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220402013419.2410298-1-lv.ruyi@zte.com.cn
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/sysdev/xics/icp-opal.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index 675d708863d5..db0452e7c351 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -196,6 +196,7 @@ int icp_opal_init(void)
 
 	printk("XICS: Using OPAL ICP fallbacks\n");
 
+	of_node_put(np);
 	return 0;
 }
 
-- 
2.35.1

[PATCH AUTOSEL 5.15 31/37] powerpc/powernv: fix missing of_node_put in uv_init()

[Sasha Levin]

From: Lv Ruyi <lv.ruyi@zte.com.cn>

[ Upstream commit 3ffa9fd471f57f365bc54fc87824c530422f64a5 ]

of_find_compatible_node() returns node pointer with refcount incremented,
use of_node_put() on it when done.

Reported-by: Zeal Robot <zealci@zte.com.cn>
Signed-off-by: Lv Ruyi <lv.ruyi@zte.com.cn>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220407090043.2491854-1-lv.ruyi@zte.com.cn
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/powernv/ultravisor.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/platforms/powernv/ultravisor.c b/arch/powerpc/platforms/powernv/ultravisor.c
index e4a00ad06f9d..67c8c4b2d8b1 100644
--- a/arch/powerpc/platforms/powernv/ultravisor.c
+++ b/arch/powerpc/platforms/powernv/ultravisor.c
@@ -55,6 +55,7 @@ static int __init uv_init(void)
 		return -ENODEV;
 
 	uv_memcons = memcons_init(node, "memcons");
+	of_node_put(node);
 	if (!uv_memcons)
 		return -ENOENT;
 
-- 
2.35.1

[PATCH AUTOSEL 5.15 32/37] macintosh/via-pmu: Fix build failure when CONFIG_INPUT is disabled

[Sasha Levin]

From: Finn Thain <fthain@linux-m68k.org>

[ Upstream commit 86ce436e30d86327c9f5260f718104ae7b21f506 ]

drivers/macintosh/via-pmu-event.o: In function `via_pmu_event':
via-pmu-event.c:(.text+0x44): undefined reference to `input_event'
via-pmu-event.c:(.text+0x68): undefined reference to `input_event'
via-pmu-event.c:(.text+0x94): undefined reference to `input_event'
via-pmu-event.c:(.text+0xb8): undefined reference to `input_event'
drivers/macintosh/via-pmu-event.o: In function `via_pmu_event_init':
via-pmu-event.c:(.init.text+0x20): undefined reference to `input_allocate_device'
via-pmu-event.c:(.init.text+0xc4): undefined reference to `input_register_device'
via-pmu-event.c:(.init.text+0xd4): undefined reference to `input_free_device'
make[1]: *** [Makefile:1155: vmlinux] Error 1
make: *** [Makefile:350: __build_one_by_one] Error 2

Don't call into the input subsystem unless CONFIG_INPUT is built-in.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Finn Thain <fthain@linux-m68k.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/5edbe76ce68227f71e09af4614cc4c1bd61c7ec8.1649326292.git.fthain@linux-m68k.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/macintosh/Kconfig   | 4 ++++
 drivers/macintosh/Makefile  | 3 ++-
 drivers/macintosh/via-pmu.c | 2 +-
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/macintosh/Kconfig b/drivers/macintosh/Kconfig
index 5cdc361da37c..3942db15a2b8 100644
--- a/drivers/macintosh/Kconfig
+++ b/drivers/macintosh/Kconfig
@@ -67,6 +67,10 @@ config ADB_PMU
 	  this device; you should do so if your machine is one of those
 	  mentioned above.
 
+config ADB_PMU_EVENT
+	def_bool y
+	depends on ADB_PMU && INPUT=y
+
 config ADB_PMU_LED
 	bool "Support for the Power/iBook front LED"
 	depends on PPC_PMAC && ADB_PMU
diff --git a/drivers/macintosh/Makefile b/drivers/macintosh/Makefile
index 49819b1b6f20..712edcb3e0b0 100644
--- a/drivers/macintosh/Makefile
+++ b/drivers/macintosh/Makefile
@@ -12,7 +12,8 @@ obj-$(CONFIG_MAC_EMUMOUSEBTN)	+= mac_hid.o
 obj-$(CONFIG_INPUT_ADBHID)	+= adbhid.o
 obj-$(CONFIG_ANSLCD)		+= ans-lcd.o
 
-obj-$(CONFIG_ADB_PMU)		+= via-pmu.o via-pmu-event.o
+obj-$(CONFIG_ADB_PMU)		+= via-pmu.o
+obj-$(CONFIG_ADB_PMU_EVENT)	+= via-pmu-event.o
 obj-$(CONFIG_ADB_PMU_LED)	+= via-pmu-led.o
 obj-$(CONFIG_PMAC_BACKLIGHT)	+= via-pmu-backlight.o
 obj-$(CONFIG_ADB_CUDA)		+= via-cuda.o
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 4b98bc26a94b..2109129ea1bb 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -1459,7 +1459,7 @@ pmu_handle_data(unsigned char *data, int len)
 		pmu_pass_intr(data, len);
 		/* len == 6 is probably a bad check. But how do I
 		 * know what PMU versions send what events here? */
-		if (len == 6) {
+		if (IS_ENABLED(CONFIG_ADB_PMU_EVENT) && len == 6) {
 			via_pmu_event(PMU_EVT_POWER, !!(data[1]&8));
 			via_pmu_event(PMU_EVT_LID, data[1]&1);
 		}
-- 
2.35.1

[PATCH AUTOSEL 5.15 33/37] powerpc/iommu: Add missing of_node_put in iommu_init_early_dart

[Sasha Levin]

From: Peng Wu <wupeng58@huawei.com>

[ Upstream commit 57b742a5b8945118022973e6416b71351df512fb ]

The device_node pointer is returned by of_find_compatible_node
with refcount incremented. We should use of_node_put() to avoid
the refcount leak.

Signed-off-by: Peng Wu <wupeng58@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220425081245.21705-1-wupeng58@huawei.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/sysdev/dart_iommu.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 1d33b7a5ea83..dc774b204c06 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -404,9 +404,10 @@ void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
 	}
 
 	/* Initialize the DART HW */
-	if (dart_init(dn) != 0)
+	if (dart_init(dn) != 0) {
+		of_node_put(dn);
 		return;
-
+	}
 	/*
 	 * U4 supports a DART bypass, we use it for 64-bit capable devices to
 	 * improve performance.  However, that only works for devices connected
@@ -419,6 +420,7 @@ void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
 
 	/* Setup pci_dma ops */
 	set_pci_dma_ops(&dma_iommu_ops);
+	of_node_put(dn);
 }
 
 #ifdef CONFIG_PM
-- 
2.35.1