Automatic merge of 'next-test' into merge-test (2023-10-22 12:35)

Documentation/ABI/testing/sysfs-kernel-fadump

@@ -38,3 +38,15 @@ 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:		Sep 2023
+Contact:	[email protected]
+Description:	read only
+		The Kdump scripts utilize udev rules to monitor memory add/remove
+		events, ensuring that FADUMP is automatically re-registered when
+		system memory changes occur. This re-registration was necessary
+		to update the elfcorehdr, which describes the system memory to the
+		second kernel. Now If this sysfs node holds a value of 1, it
+		indicates to userspace that FADUMP does not require re-registration
+		since the elfcorehdr is now generated in the second kernel.
+User:		kexec-tools

Documentation/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/Kconfig

@@ -237,6 +237,7 @@ config PPC
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_DESCRIPTORS	if PPC64_ELF_ABI_V1
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_TRACER

arch/powerpc/boot/install.sh

@@ -21,13 +21,17 @@ set -e
 # this should work for both the pSeries zImage and the iSeries vmlinux.sm
 image_name=`basename $2`
 
-if [ -f $4/$image_name ]; then
-	mv $4/$image_name $4/$image_name.old
+
+echo "Warning: '${INSTALLKERNEL}' command not available... Copying" \
+     "directly to $4/$image_name-$1" >&2
+
+if [ -f $4/$image_name-$1 ]; then
+	mv $4/$image_name-$1 $4/$image_name-$1.old
 fi
 
-if [ -f $4/System.map ]; then
-	mv $4/System.map $4/System.old
+if [ -f $4/System.map-$1 ]; then
+	mv $4/System.map-$1 $4/System-$1.old
 fi
 
-cat $2 > $4/$image_name
-cp $3 $4/System.map
+cat $2 > $4/$image_name-$1
+cp $3 $4/System.map-$1

arch/powerpc/include/asm/book3s/32/pgtable.h

@@ -20,15 +20,15 @@
 
 #define _PAGE_PRESENT	0x001	/* software: pte contains a translation */
 #define _PAGE_HASHPTE	0x002	/* hash_page has made an HPTE for this pte */
-#define _PAGE_USER	0x004	/* usermode access allowed */
+#define _PAGE_READ	0x004	/* software: read access allowed */
 #define _PAGE_GUARDED	0x008	/* G: prohibit speculative access */
 #define _PAGE_COHERENT	0x010	/* M: enforce memory coherence (SMP systems) */
 #define _PAGE_NO_CACHE	0x020	/* I: cache inhibit */
 #define _PAGE_WRITETHRU	0x040	/* W: cache write-through */
 #define _PAGE_DIRTY	0x080	/* C: page changed */
 #define _PAGE_ACCESSED	0x100	/* R: page referenced */
 #define _PAGE_EXEC	0x200	/* software: exec allowed */
-#define _PAGE_RW	0x400	/* software: user write access allowed */
+#define _PAGE_WRITE	0x400	/* software: user write access allowed */
 #define _PAGE_SPECIAL	0x800	/* software: Special page */
 
 #ifdef CONFIG_PTE_64BIT
@@ -42,26 +42,13 @@
 #define _PMD_PRESENT_MASK (PAGE_MASK)
 #define _PMD_BAD	(~PAGE_MASK)
 
-/* We borrow the _PAGE_USER bit to store the exclusive marker in swap PTEs. */
-#define _PAGE_SWP_EXCLUSIVE	_PAGE_USER
+/* We borrow the _PAGE_READ bit to store the exclusive marker in swap PTEs. */
+#define _PAGE_SWP_EXCLUSIVE	_PAGE_READ
 
 /* And here we include common definitions */
 
-#define _PAGE_KERNEL_RO		0
-#define _PAGE_KERNEL_ROX	(_PAGE_EXEC)
-#define _PAGE_KERNEL_RW		(_PAGE_DIRTY | _PAGE_RW)
-#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC)
-
 #define _PAGE_HPTEFLAGS _PAGE_HASHPTE
 
-#ifndef __ASSEMBLY__
-
-static inline bool pte_user(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_USER;
-}
-#endif /* __ASSEMBLY__ */
-
 /*
  * Location of the PFN in the PTE. Most 32-bit platforms use the same
  * as _PAGE_SHIFT here (ie, naturally aligned).
@@ -97,20 +84,7 @@ static inline bool pte_user(pte_t pte)
 #define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED)
 #define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
 
-/*
- * Permission masks used to generate the __P and __S table.
- *
- * Note:__pgprot is defined in arch/powerpc/include/asm/page.h
- *
- * Write permissions imply read permissions for now.
- */
-#define PAGE_NONE	__pgprot(_PAGE_BASE)
-#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
-#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC)
-#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+#include <asm/pgtable-masks.h>
 
 /* Permission masks used for kernel mappings */
 #define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW)
@@ -170,7 +144,14 @@ void unmap_kernel_page(unsigned long va);
  * value (for now) on others, from where we can start layout kernel
  * virtual space that goes below PKMAP and FIXMAP
  */
-#include <asm/fixmap.h>
+
+#define FIXADDR_SIZE	0
+#ifdef CONFIG_KASAN
+#include <asm/kasan.h>
+#define FIXADDR_TOP	(KASAN_SHADOW_START - PAGE_SIZE)
+#else
+#define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
+#endif
 
 /*
  * ioremap_bot starts at that address. Early ioremaps move down from there,
@@ -224,9 +205,6 @@ void unmap_kernel_page(unsigned long va);
 /* Bits to mask out from a PGD to get to the PUD page */
 #define PGD_MASKED_BITS		0
 
-#define pte_ERROR(e) \
-	pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
-		(unsigned long long)pte_val(e))
 #define pgd_ERROR(e) \
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 /*
@@ -343,7 +321,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
+	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
 }
 
 static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
@@ -402,8 +380,16 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 }
 
 /* Generic accessors to PTE bits */
-static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_RW);}
-static inline int pte_read(pte_t pte)		{ return 1; }
+static inline bool pte_read(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_READ);
+}
+
+static inline bool pte_write(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_WRITE);
+}
+
 static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
 static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
 static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
@@ -438,10 +424,10 @@ static inline bool pte_ci(pte_t pte)
 static inline bool pte_access_permitted(pte_t pte, bool write)
 {
 	/*
-	 * A read-only access is controlled by _PAGE_USER bit.
-	 * We have _PAGE_READ set for WRITE and EXECUTE
+	 * A read-only access is controlled by _PAGE_READ bit.
+	 * We have _PAGE_READ set for WRITE
 	 */
-	if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte))
+	if (!pte_present(pte) || !pte_read(pte))
 		return false;
 
 	if (write && !pte_write(pte))
@@ -465,7 +451,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_RW);
+	return __pte(pte_val(pte) & ~_PAGE_WRITE);
 }
 
 static inline pte_t pte_exprotect(pte_t pte)
@@ -495,6 +481,9 @@ static inline pte_t pte_mkpte(pte_t pte)
 
 static inline pte_t pte_mkwrite_novma(pte_t pte)
 {
+	/*
+	 * write implies read, hence set both
+	 */
 	return __pte(pte_val(pte) | _PAGE_RW);
 }
 
@@ -518,16 +507,6 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
-static inline pte_t pte_mkprivileged(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_USER);
-}
-
-static inline pte_t pte_mkuser(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_USER);
-}
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));