Merge tag 'timers-vdso-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull vdso data page handling updates from Thomas Gleixner:
 "First steps of consolidating the VDSO data page handling.

  The VDSO data page handling is architecture specific for historical
  reasons, but there is no real technical reason to do so.

  Aside of that VDSO data has become a dump ground for various
  mechanisms and fail to provide a clear separation of the
  functionalities.

  Clean this up by:

   - consolidating the VDSO page data by getting rid of architecture
     specific warts especially in x86 and PowerPC.

   - removing the last includes of header files which are pulling in
     other headers outside of the VDSO namespace.

   - seperating timekeeping and other VDSO data accordingly.

  Further consolidation of the VDSO page handling is done in subsequent
  changes scheduled for the next merge window.

  This also lays the ground for expanding the VDSO time getters for
  independent PTP clocks in a generic way without making every
  architecture add support seperately"

* tag 'timers-vdso-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (42 commits)
  x86/vdso: Add missing brackets in switch case
  vdso: Rename struct arch_vdso_data to arch_vdso_time_data
  powerpc: Split systemcfg struct definitions out from vdso
  powerpc: Split systemcfg data out of vdso data page
  powerpc: Add kconfig option for the systemcfg page
  powerpc/pseries/lparcfg: Use num_possible_cpus() for potential processors
  powerpc/pseries/lparcfg: Fix printing of system_active_processors
  powerpc/procfs: Propagate error of remap_pfn_range()
  powerpc/vdso: Remove offset comment from 32bit vdso_arch_data
  x86/vdso: Split virtual clock pages into dedicated mapping
  x86/vdso: Delete vvar.h
  x86/vdso: Access vdso data without vvar.h
  x86/vdso: Move the rng offset to vsyscall.h
  x86/vdso: Access rng vdso data without vvar.h
  x86/vdso: Access timens vdso data without vvar.h
  x86/vdso: Allocate vvar page from C code
  x86/vdso: Access rng data from kernel without vvar
  x86/vdso: Place vdso_data at beginning of vvar page
  x86/vdso: Use __arch_get_vdso_data() to access vdso data
  x86/mm/mmap: Remove arch_vma_name()
  ...

13 files changed, 118 insertions, 110 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1a2ff0276365..568560671cf4 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -1302,6 +1302,14 @@ config MODULES_SIZE
 
 endmenu
 
+config PPC64_PROC_SYSTEMCFG
+	def_bool y
+	depends on PPC64 && PROC_FS
+	help
+	  This option enables the presence of /proc/ppc64/systemcfg through
+	  which the systemcfg page can be accessed.
+	  This interface only exists for backwards-compatibility.
+
 if PPC64
 # This value must have zeroes in the bottom 60 bits otherwise lots will break
 config PAGE_OFFSET
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 83d0a4fc5f75..af9a2628d1df 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -21,8 +21,7 @@
  * page size. When using 64K pages however, whether we are really supporting
  * 64K pages in HW or not is irrelevant to those definitions.
  */
-#define PAGE_SHIFT		CONFIG_PAGE_SHIFT
-#define PAGE_SIZE		(ASM_CONST(1) << PAGE_SHIFT)
+#include <vdso/page.h>
 
 #ifndef __ASSEMBLY__
 #ifndef CONFIG_HUGETLB_PAGE
@@ -42,13 +41,6 @@ extern unsigned int hpage_shift;
 #endif
 
 /*
- * Subtle: (1 << PAGE_SHIFT) is an int, not an unsigned long. So if we
- * assign PAGE_MASK to a larger type it gets extended the way we want
- * (i.e. with 1s in the high bits)
- */
-#define PAGE_MASK      (~((1 << PAGE_SHIFT) - 1))
-
-/*
  * KERNELBASE is the virtual address of the start of the kernel, it's often
  * the same as PAGE_OFFSET, but _might not be_.
  *
diff --git a/arch/powerpc/include/asm/systemcfg.h b/arch/powerpc/include/asm/systemcfg.h
new file mode 100644
index 000000000000..2f9b1d6a5c98
--- /dev/null
+++ b/arch/powerpc/include/asm/systemcfg.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _SYSTEMCFG_H
+#define _SYSTEMCFG_H
+
+/*
+ * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM
+ * Copyright (C) 2005 Benjamin Herrenschmidy <benh@kernel.crashing.org>,
+ * 		      IBM Corp.
+ */
+
+#ifdef CONFIG_PPC64
+
+/*
+ * If the major version changes we are incompatible.
+ * Minor version changes are a hint.
+ */
+#define SYSTEMCFG_MAJOR 1
+#define SYSTEMCFG_MINOR 1
+
+#include <linux/types.h>
+
+struct systemcfg {
+	__u8  eye_catcher[16];		/* Eyecatcher: SYSTEMCFG:PPC64	0x00 */
+	struct {			/* Systemcfg version numbers	     */
+		__u32 major;		/* Major number			0x10 */
+		__u32 minor;		/* Minor number			0x14 */
+	} version;
+
+	/* Note about the platform flags: it now only contains the lpar
+	 * bit. The actual platform number is dead and buried
+	 */
+	__u32 platform;			/* Platform flags		0x18 */
+	__u32 processor;		/* Processor type		0x1C */
+	__u64 processorCount;		/* # of physical processors	0x20 */
+	__u64 physicalMemorySize;	/* Size of real memory(B)	0x28 */
+	__u64 tb_orig_stamp;		/* (NU) Timebase at boot	0x30 */
+	__u64 tb_ticks_per_sec;		/* Timebase tics / sec		0x38 */
+	__u64 tb_to_xs;			/* (NU) Inverse of TB to 2^20	0x40 */
+	__u64 stamp_xsec;		/* (NU)				0x48 */
+	__u64 tb_update_count;		/* (NU) Timebase atomicity ctr	0x50 */
+	__u32 tz_minuteswest;		/* (NU) Min. west of Greenwich	0x58 */
+	__u32 tz_dsttime;		/* (NU) Type of dst correction	0x5C */
+	__u32 dcache_size;		/* L1 d-cache size		0x60 */
+	__u32 dcache_line_size;		/* L1 d-cache line size		0x64 */
+	__u32 icache_size;		/* L1 i-cache size		0x68 */
+	__u32 icache_line_size;		/* L1 i-cache line size		0x6C */
+};
+
+extern struct systemcfg *systemcfg;
+
+#endif /* CONFIG_PPC64 */
+#endif /* _SYSTEMCFG_H */
diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h
index 92f480d8cc6d..48560a119559 100644
--- a/arch/powerpc/include/asm/vdso/vsyscall.h
+++ b/arch/powerpc/include/asm/vdso/vsyscall.h
@@ -4,12 +4,8 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/timekeeper_internal.h>
 #include <asm/vdso_datapage.h>
 
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
 static __always_inline
 struct vdso_data *__arch_get_k_vdso_data(void)
 {
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index 248dee138f7b..a9686310be2c 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -9,29 +9,6 @@
  * 		      IBM Corp.
  */
 
-
-/*
- * Note about this structure:
- *
- * This structure was historically called systemcfg and exposed to
- * userland via /proc/ppc64/systemcfg. Unfortunately, this became an
- * ABI issue as some proprietary software started relying on being able
- * to mmap() it, thus we have to keep the base layout at least for a
- * few kernel versions.
- *
- * However, since ppc32 doesn't suffer from this backward handicap,
- * a simpler version of the data structure is used there with only the
- * fields actually used by the vDSO.
- *
- */
-
-/*
- * If the major version changes we are incompatible.
- * Minor version changes are a hint.
- */
-#define SYSTEMCFG_MAJOR 1
-#define SYSTEMCFG_MINOR 1
-
 #ifndef __ASSEMBLY__
 
 #include <linux/unistd.h>
@@ -40,41 +17,10 @@
 
 #define SYSCALL_MAP_SIZE      ((NR_syscalls + 31) / 32)
 
-/*
- * So here is the ppc64 backward compatible version
- */
-
 #ifdef CONFIG_PPC64
 
 struct vdso_arch_data {
-	__u8  eye_catcher[16];		/* Eyecatcher: SYSTEMCFG:PPC64	0x00 */
-	struct {			/* Systemcfg version numbers	     */
-		__u32 major;		/* Major number			0x10 */
-		__u32 minor;		/* Minor number			0x14 */
-	} version;
-
-	/* Note about the platform flags: it now only contains the lpar
-	 * bit. The actual platform number is dead and buried
-	 */
-	__u32 platform;			/* Platform flags		0x18 */
-	__u32 processor;		/* Processor type		0x1C */
-	__u64 processorCount;		/* # of physical processors	0x20 */
-	__u64 physicalMemorySize;	/* Size of real memory(B)	0x28 */
-	__u64 tb_orig_stamp;		/* (NU) Timebase at boot	0x30 */
-	__u64 tb_ticks_per_sec;		/* Timebase tics / sec		0x38 */
-	__u64 tb_to_xs;			/* (NU) Inverse of TB to 2^20	0x40 */
-	__u64 stamp_xsec;		/* (NU)				0x48 */
-	__u64 tb_update_count;		/* (NU) Timebase atomicity ctr	0x50 */
-	__u32 tz_minuteswest;		/* (NU) Min. west of Greenwich	0x58 */
-	__u32 tz_dsttime;		/* (NU) Type of dst correction	0x5C */
-	__u32 dcache_size;		/* L1 d-cache size		0x60 */
-	__u32 dcache_line_size;		/* L1 d-cache line size		0x64 */
-	__u32 icache_size;		/* L1 i-cache size		0x68 */
-	__u32 icache_line_size;		/* L1 i-cache line size		0x6C */
-
-	/* those additional ones don't have to be located anywhere
-	 * special as they were not part of the original systemcfg
-	 */
+	__u64 tb_ticks_per_sec;			/* Timebase tics / sec */
 	__u32 dcache_block_size;		/* L1 d-cache block size     */
 	__u32 icache_block_size;		/* L1 i-cache block size     */
 	__u32 dcache_log_block_size;		/* L1 d-cache log block size */
@@ -88,11 +34,8 @@ struct vdso_arch_data {
 
 #else /* CONFIG_PPC64 */
 
-/*
- * And here is the simpler 32 bits version
- */
 struct vdso_arch_data {
-	__u64 tb_ticks_per_sec;		/* Timebase tics / sec		0x38 */
+	__u64 tb_ticks_per_sec;		/* Timebase tics / sec */
 	__u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */
 	__u32 compat_syscall_map[0];	/* No compat syscalls on PPC32 */
 	struct vdso_data data[CS_BASES];
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index b109cd7b5d01..3816a2bf2b84 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/proc_fs.h>
 #include <linux/kernel.h>
@@ -12,9 +13,10 @@
 #include <asm/machdep.h>
 #include <asm/vdso_datapage.h>
 #include <asm/rtas.h>
+#include <asm/systemcfg.h>
 #include <linux/uaccess.h>
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
 
 static loff_t page_map_seek(struct file *file, loff_t off, int whence)
 {
@@ -33,10 +35,9 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma )
 	if ((vma->vm_end - vma->vm_start) > PAGE_SIZE)
 		return -EINVAL;
 
-	remap_pfn_range(vma, vma->vm_start,
-			__pa(pde_data(file_inode(file))) >> PAGE_SHIFT,
-			PAGE_SIZE, vma->vm_page_prot);
-	return 0;
+	return remap_pfn_range(vma, vma->vm_start,
+			       __pa(pde_data(file_inode(file))) >> PAGE_SHIFT,
+			       PAGE_SIZE, vma->vm_page_prot);
 }
 
 static const struct proc_ops page_map_proc_ops = {
@@ -45,13 +46,35 @@ static const struct proc_ops page_map_proc_ops = {
 	.proc_mmap	= page_map_mmap,
 };
 
+static union {
+	struct systemcfg	data;
+	u8			page[PAGE_SIZE];
+} systemcfg_data_store __page_aligned_data;
+struct systemcfg *systemcfg = &systemcfg_data_store.data;
 
 static int __init proc_ppc64_init(void)
 {
 	struct proc_dir_entry *pde;
 
+	strcpy((char *)systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
+	systemcfg->version.major = SYSTEMCFG_MAJOR;
+	systemcfg->version.minor = SYSTEMCFG_MINOR;
+	systemcfg->processor = mfspr(SPRN_PVR);
+	/*
+	 * Fake the old platform number for pSeries and add
+	 * in LPAR bit if necessary
+	 */
+	systemcfg->platform = 0x100;
+	if (firmware_has_feature(FW_FEATURE_LPAR))
+		systemcfg->platform |= 1;
+	systemcfg->physicalMemorySize = memblock_phys_mem_size();
+	systemcfg->dcache_size = ppc64_caches.l1d.size;
+	systemcfg->dcache_line_size = ppc64_caches.l1d.line_size;
+	systemcfg->icache_size = ppc64_caches.l1i.size;
+	systemcfg->icache_line_size = ppc64_caches.l1i.line_size;
+
 	pde = proc_create_data("powerpc/systemcfg", S_IFREG | 0444, NULL,
-			       &page_map_proc_ops, vdso_data);
+			       &page_map_proc_ops, systemcfg);
 	if (!pde)
 		return 1;
 	proc_set_size(pde, PAGE_SIZE);
@@ -60,7 +83,7 @@ static int __init proc_ppc64_init(void)
 }
 __initcall(proc_ppc64_init);
 
-#endif /* CONFIG_PPC64 */
+#endif /* CONFIG_PPC64_PROC_SYSTEMCFG */
 
 /*
  * Create the ppc64 and ppc64/rtas directories early. This allows us to
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 943430077375..0b732d3b283b 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -67,6 +67,7 @@
 #include <asm/cpu_has_feature.h>
 #include <asm/kasan.h>
 #include <asm/mce.h>
+#include <asm/systemcfg.h>
 
 #include "setup.h"
 
@@ -560,7 +561,9 @@ void __init smp_setup_cpu_maps(void)
 	out:
 		of_node_put(dn);
 	}
-	vdso_data->processorCount = num_present_cpus();
+#endif
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->processorCount = num_present_cpus();
 #endif /* CONFIG_PPC64 */
 
         /* Initialize CPU <=> thread mapping/
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 4ab9b8cee77a..5ac7084eebc0 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -61,6 +61,7 @@
 #include <asm/ftrace.h>
 #include <asm/kup.h>
 #include <asm/fadump.h>
+#include <asm/systemcfg.h>
 
 #include <trace/events/ipi.h>
 
@@ -1186,8 +1187,8 @@ int generic_cpu_disable(void)
 		return -EBUSY;
 
 	set_cpu_online(cpu, false);
-#ifdef CONFIG_PPC64
-	vdso_data->processorCount--;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->processorCount--;
 #endif
 	/* Update affinity of all IRQs previously aimed at this CPU */
 	irq_migrate_all_off_this_cpu();
@@ -1642,10 +1643,12 @@ void start_secondary(void *unused)
 
 	secondary_cpu_time_init();
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
 	if (system_state == SYSTEM_RUNNING)
-		vdso_data->processorCount++;
+		systemcfg->processorCount++;
+#endif
 
+#ifdef CONFIG_PPC64
 	vdso_getcpu_init();
 #endif
 	set_numa_node(numa_cpu_lookup_table[cpu]);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0ff9f038e800..0727332ad86f 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -71,11 +71,11 @@
 #include <asm/vdso_datapage.h>
 #include <asm/firmware.h>
 #include <asm/mce.h>
+#include <asm/systemcfg.h>
 
 /* powerpc clocksource/clockevent code */
 
 #include <linux/clockchips.h>
-#include <linux/timekeeper_internal.h>
 
 static u64 timebase_read(struct clocksource *);
 static struct clocksource clocksource_timebase = {
@@ -951,6 +951,9 @@ void __init time_init(void)
 	}
 
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
+#endif
 
 	/* initialise and enable the large decrementer (if we have one) */
 	set_decrementer_max();
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index ee4b9d676cff..924f7f4fa597 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -16,7 +16,6 @@
 #include <linux/user.h>
 #include <linux/elf.h>
 #include <linux/security.h>
-#include <linux/memblock.h>
 #include <linux/syscalls.h>
 #include <linux/time_namespace.h>
 #include <vdso/datapage.h>
@@ -349,25 +348,6 @@ static struct page ** __init vdso_setup_pages(void *start, void *end)
 static int __init vdso_init(void)
 {
 #ifdef CONFIG_PPC64
-	/*
-	 * Fill up the "systemcfg" stuff for backward compatibility
-	 */
-	strcpy((char *)vdso_data->eye_catcher, "SYSTEMCFG:PPC64");
-	vdso_data->version.major = SYSTEMCFG_MAJOR;
-	vdso_data->version.minor = SYSTEMCFG_MINOR;
-	vdso_data->processor = mfspr(SPRN_PVR);
-	/*
-	 * Fake the old platform number for pSeries and add
-	 * in LPAR bit if necessary
-	 */
-	vdso_data->platform = 0x100;
-	if (firmware_has_feature(FW_FEATURE_LPAR))
-		vdso_data->platform |= 1;
-	vdso_data->physicalMemorySize = memblock_phys_mem_size();
-	vdso_data->dcache_size = ppc64_caches.l1d.size;
-	vdso_data->dcache_line_size = ppc64_caches.l1d.line_size;
-	vdso_data->icache_size = ppc64_caches.l1i.size;
-	vdso_data->icache_line_size = ppc64_caches.l1i.line_size;
 	vdso_data->dcache_block_size = ppc64_caches.l1d.block_size;
 	vdso_data->icache_block_size = ppc64_caches.l1i.block_size;
 	vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 8f14f0581a21..2e9da58195f5 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -36,6 +36,7 @@
 #include <asm/kexec.h>
 #include <asm/reg.h>
 #include <asm/powernv.h>
+#include <asm/systemcfg.h>
 
 #include "powernv.h"
 
@@ -136,7 +137,9 @@ static int pnv_smp_cpu_disable(void)
 	 * the generic fixup_irqs. --BenH.
 	 */
 	set_cpu_online(cpu, false);
-	vdso_data->processorCount--;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->processorCount--;
+#endif
 	if (cpu == boot_cpuid)
 		boot_cpuid = cpumask_any(cpu_online_mask);
 	if (xive_enabled())
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 6838a0fcda29..bc6926dbf148 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -33,6 +33,7 @@
 #include <asm/xive.h>
 #include <asm/plpar_wrappers.h>
 #include <asm/topology.h>
+#include <asm/systemcfg.h>
 
 #include "pseries.h"
 
@@ -83,7 +84,9 @@ static int pseries_cpu_disable(void)
 	int cpu = smp_processor_id();
 
 	set_cpu_online(cpu, false);
-	vdso_data->processorCount--;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->processorCount--;
+#endif
 
 	/*fix boot_cpuid here*/
 	if (cpu == boot_cpuid)
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 62da20f9700a..cc22924f159f 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -29,7 +29,6 @@
 #include <asm/firmware.h>
 #include <asm/rtas.h>
 #include <asm/time.h>
-#include <asm/vdso_datapage.h>
 #include <asm/vio.h>
 #include <asm/mmu.h>
 #include <asm/machdep.h>
@@ -530,7 +529,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 		lrdrp = of_get_property(rtas_node, "ibm,lrdr-capacity", NULL);
 
 	if (lrdrp == NULL) {
-		partition_potential_processors = vdso_data->processorCount;
+		partition_potential_processors = num_possible_cpus();
 	} else {
 		partition_potential_processors = be32_to_cpup(lrdrp + 4);
 	}
@@ -553,7 +552,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 	} else {		/* non SPLPAR case */
 
 		seq_printf(m, "system_active_processors=%d\n",
-			   partition_potential_processors);
+			   partition_active_processors);
 
 		seq_printf(m, "system_potential_processors=%d\n",
 			   partition_potential_processors);