Automatic merge of 'next-test' into merge-test (2024-04-23 15:05)

Author: mpe

Documentation/ABI/testing/sysfs-kernel-fadump

@@ -38,3 +38,14 @@ Contact:	[email protected]
 Description:	read only
 		Provide information about the amount of memory reserved by
 		FADump to save the crash dump in bytes.
+
+What:		/sys/kernel/fadump/hotplug_ready
+Date:		Apr 2024
+Contact:	[email protected]
+Description:	read only
+		Kdump udev rule re-registers fadump on memory add/remove events,
+		primarily to update the elfcorehdr. This sysfs indicates the
+		kdump udev rule that fadump re-registration is not required on
+		memory add/remove events because elfcorehdr is now prepared in
+		the second/fadump kernel.
+User:		kexec-tools

Documentation/arch/powerpc/firmware-assisted-dump.rst

@@ -134,12 +134,12 @@ that are run. If there is dump data, then the
 memory is held.
 
 If there is no waiting dump data, then only the memory required to
-hold CPU state, HPTE region, boot memory dump, FADump header and
-elfcore header, is usually reserved at an offset greater than boot
-memory size (see Fig. 1). This area is *not* released: this region
-will be kept permanently reserved, so that it can act as a receptacle
-for a copy of the boot memory content in addition to CPU state and
-HPTE region, in the case a crash does occur.
+hold CPU state, HPTE region, boot memory dump, and FADump header is
+usually reserved at an offset greater than boot memory size (see Fig. 1).
+This area is *not* released: this region will be kept permanently
+reserved, so that it can act as a receptacle for a copy of the boot
+memory content in addition to CPU state and HPTE region, in the case
+a crash does occur.
 
 Since this reserved memory area is used only after the system crash,
 there is no point in blocking this significant chunk of memory from
@@ -153,22 +153,22 @@ that were present in CMA region::
 
   o Memory Reservation during first kernel
 
-  Low memory                                                 Top of memory
-  0    boot memory size   |<--- Reserved dump area --->|       |
-  |           |           |    Permanent Reservation   |       |
-  V           V           |                            |       V
-  +-----------+-----/ /---+---+----+-------+-----+-----+----+--+
-  |           |           |///|////|  DUMP | HDR | ELF |////|  |
-  +-----------+-----/ /---+---+----+-------+-----+-----+----+--+
-        |                   ^    ^     ^      ^           ^
-        |                   |    |     |      |           |
-        \                  CPU  HPTE   /      |           |
-         ------------------------------       |           |
-      Boot memory content gets transferred    |           |
-      to reserved area by firmware at the     |           |
-      time of crash.                          |           |
-                                          FADump Header   |
-                                           (meta area)    |
+  Low memory                                                  Top of memory
+  0    boot memory size   |<------ Reserved dump area ----->|     |
+  |           |           |      Permanent Reservation      |     |
+  V           V           |                                 |     V
+  +-----------+-----/ /---+---+----+-----------+-------+----+-----+
+  |           |           |///|////|    DUMP   |  HDR  |////|     |
+  +-----------+-----/ /---+---+----+-----------+-------+----+-----+
+        |                   ^    ^       ^         ^      ^
+        |                   |    |       |         |      |
+        \                  CPU  HPTE     /         |      |
+         --------------------------------          |      |
+      Boot memory content gets transferred         |      |
+      to reserved area by firmware at the          |      |
+      time of crash.                               |      |
+                                           FADump Header  |
+                                            (meta area)   |
                                                           |
                                                           |
                       Metadata: This area holds a metadata structure whose
@@ -186,20 +186,33 @@ that were present in CMA region::
   0      boot memory size                                      |
   |           |<------------ Crash preserved area ------------>|
   V           V           |<--- Reserved dump area --->|       |
-  +-----------+-----/ /---+---+----+-------+-----+-----+----+--+
-  |           |           |///|////|  DUMP | HDR | ELF |////|  |
-  +-----------+-----/ /---+---+----+-------+-----+-----+----+--+
-        |                                           |
-        V                                           V
-   Used by second                             /proc/vmcore
-   kernel to boot
+  +----+---+--+-----/ /---+---+----+-------+-----+-----+-------+
+  |    |ELF|  |           |///|////|  DUMP | HDR |/////|       |
+  +----+---+--+-----/ /---+---+----+-------+-----+-----+-------+
+       |   |  |                            |     |             |
+       -----  ------------------------------     ---------------
+         \              |                               |
+           \            |                               |
+             \          |                               |
+               \        |    ----------------------------
+                 \      |   /
+                   \    |  /
+                     \  | /
+                  /proc/vmcore
+
 
         +---+
         |///| -> Regions (CPU, HPTE & Metadata) marked like this in the above
         +---+    figures are not always present. For example, OPAL platform
                  does not have CPU & HPTE regions while Metadata region is
                  not supported on pSeries currently.
 
+        +---+
+        |ELF| -> elfcorehdr, it is created in second kernel after crash.
+        +---+
+
+        Note: Memory from 0 to the boot memory size is used by second kernel
+
                    Fig. 2
 
 
@@ -353,26 +366,6 @@ TODO:
  - Need to come up with the better approach to find out more
    accurate boot memory size that is required for a kernel to
    boot successfully when booted with restricted memory.
- - The FADump implementation introduces a FADump crash info structure
-   in the scratch area before the ELF core header. The idea of introducing
-   this structure is to pass some important crash info data to the second
-   kernel which will help second kernel to populate ELF core header with
-   correct data before it gets exported through /proc/vmcore. The current
-   design implementation does not address a possibility of introducing
-   additional fields (in future) to this structure without affecting
-   compatibility. Need to come up with the better approach to address this.
-
-   The possible approaches are:
-
-	1. Introduce version field for version tracking, bump up the version
-	whenever a new field is added to the structure in future. The version
-	field can be used to find out what fields are valid for the current
-	version of the structure.
-	2. Reserve the area of predefined size (say PAGE_SIZE) for this
-	structure and have unused area as reserved (initialized to zero)
-	for future field additions.
-
-   The advantage of approach 1 over 2 is we don't need to reserve extra space.
 
 Author: Mahesh Salgaonkar <[email protected]>
 

arch/powerpc/Kbuild

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror -Wa,--fatal-warnings
+subdir-asflags-$(CONFIG_PPC_WERROR) := -Wa,--fatal-warnings
 
 obj-y += kernel/
 obj-y += mm/

arch/powerpc/include/asm/cpu_has_feature.h

@@ -29,7 +29,7 @@ static __always_inline bool cpu_has_feature(unsigned long feature)
 #endif
 
 #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
-	if (!static_key_initialized) {
+	if (!static_key_feature_checks_initialized) {
 		printk("Warning! cpu_has_feature() used prior to jump label init!\n");
 		dump_stack();
 		return early_cpu_has_feature(feature);

arch/powerpc/include/asm/fadump-internal.h

@@ -42,13 +42,38 @@ static inline u64 fadump_str_to_u64(const char *str)
 
 #define FADUMP_CPU_UNKNOWN		(~((u32)0))
 
-#define FADUMP_CRASH_INFO_MAGIC		fadump_str_to_u64("FADMPINF")
+/*
+ * The introduction of new fields in the fadump crash info header has
+ * led to a change in the magic key from `FADMPINF` to `FADMPSIG` for
+ * identifying a kernel crash from an old kernel.
+ *
+ * To prevent the need for further changes to the magic number in the
+ * event of future modifications to the fadump crash info header, a
+ * version field has been introduced to track the fadump crash info
+ * header version.
+ *
+ * Consider a few points before adding new members to the fadump crash info
+ * header structure:
+ *
+ *  - Append new members; avoid adding them in between.
+ *  - Non-primitive members should have a size member as well.
+ *  - For every change in the fadump header, increment the
+ *    fadump header version. This helps the updated kernel decide how to
+ *    handle kernel dumps from older kernels.
+ */
+#define FADUMP_CRASH_INFO_MAGIC_OLD	fadump_str_to_u64("FADMPINF")
+#define FADUMP_CRASH_INFO_MAGIC		fadump_str_to_u64("FADMPSIG")
+#define FADUMP_HEADER_VERSION		1
 
 /* fadump crash info structure */
 struct fadump_crash_info_header {
 	u64		magic_number;
-	u64		elfcorehdr_addr;
+	u32		version;
 	u32		crashing_cpu;
+	u64		vmcoreinfo_raddr;
+	u64		vmcoreinfo_size;
+	u32		pt_regs_sz;
+	u32		cpu_mask_sz;
 	struct pt_regs	regs;
 	struct cpumask	cpu_mask;
 };
@@ -94,6 +119,8 @@ struct fw_dump {
 	u64		boot_mem_regs_cnt;
 
 	unsigned long	fadumphdr_addr;
+	u64		elfcorehdr_addr;
+	u64		elfcorehdr_size;
 	unsigned long	cpu_notes_buf_vaddr;
 	unsigned long	cpu_notes_buf_size;
 

arch/powerpc/include/asm/feature-fixups.h

@@ -291,6 +291,8 @@ extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
 extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
 extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;
 
+extern bool static_key_feature_checks_initialized;
+
 void apply_feature_fixups(void);
 void update_mmu_feature_fixups(unsigned long mask);
 void setup_feature_keys(void);

arch/powerpc/include/asm/hvcall.h

@@ -570,7 +570,7 @@ struct hvcall_mpp_data {
 	unsigned long backing_mem;
 };
 
-int h_get_mpp(struct hvcall_mpp_data *);
+long h_get_mpp(struct hvcall_mpp_data *mpp_data);
 
 struct hvcall_mpp_x_data {
 	unsigned long coalesced_bytes;

arch/powerpc/include/asm/interrupt.h

@@ -336,6 +336,14 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte
 	if (IS_ENABLED(CONFIG_KASAN))
 		return;
 
+	/*
+	 * Likewise, do not use it in real mode if percpu first chunk is not
+	 * embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there
+	 * are chances where percpu allocation can come from vmalloc area.
+	 */
+	if (percpu_first_chunk_is_paged)
+		return;
+
 	/* Otherwise, it should be safe to call it */
 	nmi_enter();
 }
@@ -351,6 +359,8 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
 		// no nmi_exit for a pseries hash guest taking a real mode exception
 	} else if (IS_ENABLED(CONFIG_KASAN)) {
 		// no nmi_exit for KASAN in real mode
+	} else if (percpu_first_chunk_is_paged) {
+		// no nmi_exit if percpu first chunk is not embedded
 	} else {
 		nmi_exit();
 	}

arch/powerpc/include/asm/mmu.h

@@ -251,7 +251,7 @@ static __always_inline bool mmu_has_feature(unsigned long feature)
 #endif
 
 #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
-	if (!static_key_initialized) {
+	if (!static_key_feature_checks_initialized) {
 		printk("Warning! mmu_has_feature() used prior to jump label init!\n");
 		dump_stack();
 		return early_mmu_has_feature(feature);

arch/powerpc/include/asm/percpu.h

@@ -15,6 +15,16 @@
 #endif /* CONFIG_SMP */
 #endif /* __powerpc64__ */
 
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) && defined(CONFIG_SMP)
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
+
+#define percpu_first_chunk_is_paged	\
+		(static_key_enabled(&__percpu_first_chunk_is_paged.key))
+#else
+#define percpu_first_chunk_is_paged	false
+#endif /* CONFIG_PPC64 && CONFIG_SMP */
+
 #include <asm-generic/percpu.h>
 
 #include <asm/paca.h>

arch/powerpc/kernel/eeh.c

@@ -506,9 +506,18 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	 * We will punt with the following conditions: Failure to get
 	 * PE's state, EEH not support and Permanently unavailable
 	 * state, PE is in good state.
+	 *
+	 * On the pSeries, after reaching the threshold, get_state might
+	 * return EEH_STATE_NOT_SUPPORT. However, it's possible that the
+	 * device state remains uncleared if the device is not marked
+	 * pci_channel_io_perm_failure. Therefore, consider logging the
+	 * event to let device removal happen.
+	 *
 	 */
 	if ((ret < 0) ||
-	    (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) {
+	    (ret == EEH_STATE_NOT_SUPPORT &&
+	     dev->error_state == pci_channel_io_perm_failure) ||
+	    eeh_state_active(ret)) {
 		eeh_stats.false_positives++;
 		pe->false_positives++;
 		rc = 0;

arch/powerpc/kernel/eeh_driver.c

@@ -865,9 +865,18 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 				devices++;
 
 	if (!devices) {
-		pr_debug("EEH: Frozen PHB#%x-PE#%x is empty!\n",
+		pr_warn("EEH: Frozen PHB#%x-PE#%x is empty!\n",
 			pe->phb->global_number, pe->addr);
-		goto out; /* nothing to recover */
+		/*
+		 * The device is removed, tear down its state, on powernv
+		 * hotplug driver would take care of it but not on pseries,
+		 * permanently disable the card as it is hot removed.
+		 *
+		 * In the case of powernv, note that the removal of device
+		 * is covered by pci rescan lock, so no problem even if hotplug
+		 * driver attempts to remove the device.
+		 */
+		goto recover_failed;
 	}
 
 	/* Log the event */